linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	x86@kernel.org, Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, Arnd Bergmann <arnd@arndb.de>,
	"H. Peter Anvin" <hpa@zytor.com>
Cc: Andi Kleen <ak@linux.intel.com>,
	Dave Hansen <dave.hansen@intel.com>,
	Andy Lutomirski <luto@amacapital.net>,
	Michal Hocko <mhocko@suse.com>,
	linux-arch@vger.kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH 15/26] x86/mm: define virtual memory map for 5-level paging
Date: Mon, 13 Mar 2017 08:50:09 +0300	[thread overview]
Message-ID: <20170313055020.69655-16-kirill.shutemov@linux.intel.com> (raw)
In-Reply-To: <20170313055020.69655-1-kirill.shutemov@linux.intel.com>

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
additional page table level.

The rest of the map is uncahnged.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 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 5724092db811..0303a47b82f8 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
 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 ...
+fffe000000000000 - fffe007fffffffff (=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 cc98d5a294ee..747f06f00a22 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -290,6 +290,7 @@ 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 1410b567ecde..f527b02a0ee3 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 9215e0527647..3f5f08b010d0 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 0b2797e5083c..00dc0c2b456e 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 4517d6b93188..1f5bee2c202f 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 */
-- 
2.11.0

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2017-03-13  5:50 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-13  5:49 [PATCH 00/26] x86: 5-level paging enabling for v4.12 Kirill A. Shutemov
2017-03-13  5:49 ` [PATCH 01/26] x86: basic changes into headers for 5-level paging Kirill A. Shutemov
2017-03-13  5:49 ` [PATCH 02/26] x86: trivial portion of 5-level paging conversion Kirill A. Shutemov
2017-03-13  5:49 ` [PATCH 03/26] x86/gup: add 5-level paging support Kirill A. Shutemov
2017-03-13  5:49 ` [PATCH 04/26] x86/ident_map: " Kirill A. Shutemov
2017-03-13  5:49 ` [PATCH 05/26] x86/mm: add support of p4d_t in vmalloc_fault() Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 06/26] x86/power: support p4d_t in hibernate code Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 07/26] x86/kexec: support p4d_t Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 08/26] x86/efi: handle p4d in EFI pagetables Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 09/26] x86/mm/pat: handle additional page table Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 10/26] x86/kasan: prepare clear_pgds() to switch to <asm-generic/pgtable-nop4d.h> Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 11/26] x86/xen: convert __xen_pgd_walk() and xen_cleanmfnmap() to support p4d Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 12/26] x86: convert the rest of the code to support p4d_t Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 13/26] x86: detect 5-level paging support Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 14/26] x86/asm: remove __VIRTUAL_MASK_SHIFT==47 assert Kirill A. Shutemov
2017-03-13  5:50 ` Kirill A. Shutemov [this message]
2017-03-13  5:50 ` [PATCH 16/26] x86/paravirt: make paravirt code support 5-level paging Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 17/26] x86/mm: basic defines/helpers for CONFIG_X86_5LEVEL Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 18/26] x86/dump_pagetables: support 5-level paging Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 19/26] x86/kasan: extend to " Kirill A. Shutemov
2017-03-13  7:25   ` Dmitry Vyukov
2017-03-13  5:50 ` [PATCH 20/26] x86/espfix: " Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 21/26] x86/mm: add support of additional page table level during early boot Kirill A. Shutemov
2017-03-13  7:18   ` Ingo Molnar
2017-04-05 11:36     ` Kirill A. Shutemov
2017-04-05 15:32       ` Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 22/26] x86/mm: add sync_global_pgds() for configuration with 5-level paging Kirill A. Shutemov
2017-03-13  7:22   ` Ingo Molnar
2017-03-13  5:50 ` [PATCH 23/26] x86/mm: make kernel_physical_mapping_init() support " Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 24/26] x86/mm: add support for 5-level paging for KASLR Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 25/26] x86: enable 5-level paging support Kirill A. Shutemov
2017-03-13  5:50 ` [PATCH 26/26] x86/mm: allow to have userspace mappings above 47-bits Kirill A. Shutemov
2017-03-17 17:53   ` Aneesh Kumar K.V
2017-03-17 17:57     ` Kirill A. Shutemov
2017-03-19  8:24       ` Aneesh Kumar K.V
2017-03-19  8:26         ` Kirill A. Shutemov
2017-03-20 18:08           ` hpa
2017-03-20 18:38             ` Matthew Wilcox
2017-03-24  8:59             ` Kirill A. Shutemov
2017-03-19  8:55         ` Aneesh Kumar K.V
2017-03-24  9:03           ` Kirill A. Shutemov
2017-03-20  9:15         ` Michael Ellerman
2017-03-20  5:10   ` Aneesh Kumar K.V
2017-03-24  9:04     ` Kirill A. Shutemov
2017-03-24  9:14       ` Aneesh Kumar K.V
2017-03-24  9:30         ` Kirill A. Shutemov
2017-03-13  7:49 ` [PATCH 00/26] x86: 5-level paging enabling for v4.12 Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20170313055020.69655-16-kirill.shutemov@linux.intel.com \
    --to=kirill.shutemov@linux.intel.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=arnd@arndb.de \
    --cc=dave.hansen@intel.com \
    --cc=hpa@zytor.com \
    --cc=linux-arch@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@amacapital.net \
    --cc=mhocko@suse.com \
    --cc=mingo@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox