x86/mm/doc: Enhance the x86-64 virtual memory layout descriptions

After the cleanups from Baoquan He, make it even more readable: - Remove the 'bits' area size column: it's pretty pointless and was even wrong for some of the entries. Given that MB, GB, TB, PT are 10, 20, 30 and 40 bits, a "8 TB" size description makes it obvious that it's 43 bits. - Introduce an "offset" column: -------------------------------------------------------------------------------- start addr | offset | end addr | size | VM area description -----------------|------------|------------------|---------|-------------------- ... ffff880000000000 | -120 TB | ffffc7ffffffffff | 64 TB | direct mapping of all physical memory (page_offset_base), this is what limits max physical memory supported. The -120 TB notation makes it obvious where this particular virtual memory region starts: 120 TB down from the top of the 64-bit virtual memory space. Especially the layout of the kernel mappings is a *lot* more obvious when written this way, plus it's much easier to compare it with the size column and understand/check/validate and modify the kernel's layout in the future. - Mark the part from where the 47-bit and 56-bit kernel layouts are 100% identical, this starts at the -512 GB offset and the EFI region. - Re-shuffle the size desciptions to be continous blocks of sizes, instead of the often mixed size. I.e. write "0.5 TB" instead of "512 GB" if we are still in the TB-granular region of the map. - Make the 47-bit and 56-bit descriptions use the *exact* same layout and wording, and only differ where there's a material difference. This makes it easy to compare the two tables side by side by switching between two terminal tabs. - Plus enhance a lot of other stylistic/typographical details: make the tables explicitly tabular, add headers, enhance certain entries, etc. etc. Note that there are some apparent errors in the tables as well, but I'll fix them in a separate patch to make it easier to review/validate. Cc: Andy Lutomirski <luto@kernel.org> Cc: Baoquan He <bhe@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Brian Gerst <brgerst@gmail.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Denys Vlasenko <dvlasenk@redhat.com> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rik van Riel <riel@surriel.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: corbet@lwn.net Cc: linux-doc@vger.kernel.org Cc: linux-kernel@vger.kernel.org Cc: thgarnie@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
author: Ingo Molnar <mingo@kernel.org> 2018-10-06 07:41:12 -0400
committer: Ingo Molnar <mingo@kernel.org> 2018-10-06 10:36:12 -0400
commit: 32b89760ddf4477da436c272be2abc016e169031 (patch)
tree: a9d9ff3cf92cc13f0cf2f9979612aa8f0779c4b5
parent: 5b12904065798fee8b153a506ac7b72d5ebbe26c (diff)
1 files changed, 120 insertions, 51 deletions
diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt
index b4bc95c9790e..702898633b00 100644
--- a/Documentation/x86/x86_64/mm.txt
+++ b/Documentation/x86/x86_64/mm.txt
@@ -1,55 +1,124 @@
+====================================================
+Complete virtual memory map with 4-level page tables
+====================================================
-Virtual memory map with 4 level page tables:
+Notes:
-0000000000000000 - 00007fffffffffff (=47 bits,   128 TB) user space, different per mm
+ - Negative addresses such as "-23 TB" are absolute addresses in bytes, counted down
-                                    hole caused by [47:63] sign extension
+   from the top of the 64-bit address space. It's easier to understand the layout
-ffff800000000000 - ffff87ffffffffff (=43 bits,     8 TB) guard hole, reserved for hypervisor
+   when seen both in absolute addresses and in distance-from-top notation.
-ffff880000000000 - ffffc7ffffffffff (=46 bits,    64 TB) direct mapping of all phys. memory (page_offset_base)
-ffffc80000000000 - ffffc8ffffffffff (=40 bits,     1 TB) unused hole
+   For example 0xffffe90000000000 == -23 TB, it's 23 TB lower than the top of the
-ffffc90000000000 - ffffe8ffffffffff (=45 bits,    32 TB) vmalloc/ioremap space (vmalloc_base)
+   64-bit address space (ffffffffffffffff).
-ffffe90000000000 - ffffe9ffffffffff (=40 bits,     1 TB) unused hole
-ffffea0000000000 - ffffeaffffffffff (=40 bits,     1 TB) virtual memory map (vmemmap_base)
+   Note that as we get closer to the top of the address space, the notation changes
-ffffeb0000000000 - ffffebffffffffff (=40 bits,     1 TB) unused hole
+   from TB to GB and then MB/KB.
-ffffec0000000000 - fffffbffffffffff (=44 bits,    16 TB) kasan shadow memory
-fffffc0000000000 - fffffdffffffffff (=41 bits,     2 TB) unused hole
+ - "16M TB" might look weird at first sight, but it's an easier to visualize size
-                                    vaddr_end for KASLR
+   notation than "16 EB", which few will recognize at first sight as 16 exabytes.
-fffffe0000000000 - fffffe7fffffffff (=39 bits,   512 GB) cpu_entry_area mapping
+   It also shows it nicely how incredibly large 64-bit address space is.
-fffffe8000000000 - fffffeffffffffff (=39 bits,   512 GB) LDT remap for PTI
-ffffff0000000000 - ffffff7fffffffff (=39 bits,   512 GB) %esp fixup stacks
+========================================================================================================================
-ffffff8000000000 - fffffffeefffffff (~39 bits,  ~507 GB) unused hole
+    Start addr    |   Offset   |     End addr     |  Size   | VM area description
-ffffffef00000000 - fffffffeffffffff (=36 bits,    64 GB) EFI region mapping space
+========================================================================================================================
-ffffffff00000000 - ffffffff7fffffff (=31 bits,     2 GB) unused hole
+                  |            |                  |         |
-ffffffff80000000 - ffffffff9fffffff (=29 bits,   512 MB) kernel text mapping, from phys 0
+ 0000000000000000 |    0       | 00007fffffffffff |  128 TB | user-space virtual memory, different per mm
-ffffffffa0000000 - fffffffffeffffff (~31 bits,  1520 MB) module mapping space
+__________________|____________|__________________|_________|___________________________________________________________
-[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+                  |            |                  |         |
-ffffffffff600000 - ffffffffff600fff (             =4 kB) legacy vsyscall ABI
+ 0000800000000000 | +128    TB | ffff7fffffffffff | ~16M TB | ... huge, almost 64 bits wide hole of non-canonical
-ffffffffffe00000 - ffffffffffffffff (             =2 MB) unused hole
+                  |            |                  |         |     virtual memory addresses up to the -128 TB
+                  |            |                  |         |     starting offset of kernel mappings.
-Virtual memory map with 5 level page tables:
+__________________|____________|__________________|_________|___________________________________________________________
+                                                            |
-0000000000000000 - 00ffffffffffffff (=56 bits,    64 PB) user space, different per mm
+                                                            | Kernel-space virtual memory, shared between all processes:
-                                    hole caused by [56:63] sign extension
+____________________________________________________________|___________________________________________________________
-ff00000000000000 - ff0fffffffffffff (=52 bits,     4 PB) guard hole, reserved for hypervisor
+                  |            |                  |         |
-ff10000000000000 - ff8fffffffffffff (=55 bits,    32 PB) direct mapping of all phys. memory (page_offset_base)
+ ffff800000000000 | -128    TB | ffff87ffffffffff |    8 TB | ... guard hole, also reserved for hypervisor
-ff90000000000000 - ff9fffffffffffff (=52 bits,     4 PB) LDT remap for PTI
+ ffff880000000000 | -120    TB | ffffc7ffffffffff |   64 TB | direct mapping of all physical memory (page_offset_base)
-ffa0000000000000 - ffd1ffffffffffff (=53 bits, 12800 TB) vmalloc/ioremap space (vmalloc_base)
+ ffffc80000000000 |  -56    TB | ffffc8ffffffffff |    1 TB | ... unused hole
-ffd2000000000000 - ffd3ffffffffffff (=49 bits,   512 TB) unused hole
+ ffffc90000000000 |  -55    TB | ffffe8ffffffffff |   32 TB | vmalloc/ioremap space (vmalloc_base)
-ffd4000000000000 - ffd5ffffffffffff (=49 bits,   512 TB) virtual memory map (vmemmap_base)
+ ffffe90000000000 |  -23    TB | ffffe9ffffffffff |    1 TB | ... unused hole
-ffd6000000000000 - ffdeffffffffffff (~51 bits,  2304 TB) unused hole
+ ffffea0000000000 |  -22    TB | ffffeaffffffffff |    1 TB | virtual memory map (vmemmap_base)
-ffdf000000000000 - fffffdffffffffff (~53 bits,    ~8 PB) kasan shadow memory
+ ffffeb0000000000 |  -21    TB | ffffebffffffffff |    1 TB | ... unused hole
-fffffc0000000000 - fffffdffffffffff (=41 bits,     2 TB) unused hole
+ ffffec0000000000 |  -20    TB | fffffbffffffffff |   16 TB | KASAN shadow memory
-                                    vaddr_end for KASLR
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
-fffffe0000000000 - fffffe7fffffffff (=39 bits,   512 GB) cpu_entry_area mapping
+                  |            |                  |         | vaddr_end for KASLR
-fffffe8000000000 - fffffeffffffffff (=39 bits,   512 GB) unused hole
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
-ffffff0000000000 - ffffff7fffffffff (=39 bits,   512 GB) %esp fixup stacks
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | LDT remap for PTI
-ffffff8000000000 - ffffffeeffffffff (~39 bits,   444 GB) unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
-ffffffef00000000 - fffffffeffffffff (=36 bits,    64 GB) EFI region mapping space
+__________________|____________|__________________|_________|____________________________________________________________
-ffffffff00000000 - ffffffff7fffffff (31 bits,      2 GB) unused hole
+                                                            |
-ffffffff80000000 - ffffffff9fffffff (=29 bits,   512 MB) kernel text mapping, from phys 0
+                                                            | Identical layout to the 47-bit one from here on:
-ffffffffa0000000 - fffffffffeffffff (~31 bits,  1520 MB) module mapping space
+____________________________________________________________|____________________________________________________________
-[fixmap start]   - ffffffffff5fffff kernel-internal fixmap range
+                  |            |                  |         |
-ffffffffff600000 - ffffffffff600fff (             =4 kB) legacy vsyscall ABI
+ ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
-ffffffffffe00000 - ffffffffffffffff (             =2 MB) unused hole
+ ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
+ ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole
+ ffffffff80000000 |   -2    GB | ffffffff9fffffff |  512 MB | kernel text mapping, mapped to physical address 0
+ ffffffff80000000 |-2048    MB |                  |         |
+ ffffffffa0000000 |-1536    MB | fffffffffeffffff | 1520 MB | module mapping space
+ ffffffffff000000 |  -16    MB |                  |         |
+    FIXADDR_START | ~-11    MB | ffffffffff5fffff | ~0.5 MB | kernel-internal fixmap range, variable size and offset
+ ffffffffff600000 |  -10    MB | ffffffffff600fff |    4 kB | legacy vsyscall ABI
+ ffffffffffe00000 |   -2    MB | ffffffffffffffff |    2 MB | ... unused hole
+__________________|____________|__________________|_________|___________________________________________________________
+====================================================
+Complete virtual memory map with 5-level page tables
+====================================================
+Notes:
+ - With 56-bit addresses, user-space memory gets expanded by a factor of 512x,
+   from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PT starting
+   offset and many of the regions expand to support the much larger physical
+   memory supported.
+========================================================================================================================
+    Start addr    |   Offset   |     End addr     |  Size   | VM area description
+========================================================================================================================
+                  |            |                  |         |
+ 0000000000000000 |    0       | 00ffffffffffffff |   64 PB | user-space virtual memory, different per mm
+__________________|____________|__________________|_________|___________________________________________________________
+                  |            |                  |         |
+ 0000800000000000 |  +64    PB | ffff7fffffffffff | ~16K PB | ... huge, still almost 64 bits wide hole of non-canonical
+                  |            |                  |         |     virtual memory addresses up to the -128 TB
+                  |            |                  |         |     starting offset of kernel mappings.
+__________________|____________|__________________|_________|___________________________________________________________
+                                                            |
+                                                            | Kernel-space virtual memory, shared between all processes:
+____________________________________________________________|___________________________________________________________
+                  |            |                  |         |
+ ff00000000000000 |  -64    PB | ff0fffffffffffff |    4 PB | ... guard hole, also reserved for hypervisor
+ ff10000000000000 |  -60    PB | ff8fffffffffffff |   32 PB | direct mapping of all physical memory (page_offset_base)
+ ff90000000000000 |  -28    PB | ff9fffffffffffff |    4 PB | LDT remap for PTI
+ ffa0000000000000 |  -24    PB | ffd1ffffffffffff | 12.5 PB | vmalloc/ioremap space (vmalloc_base)
+ ffd2000000000000 |  -11.5  PB | ffd3ffffffffffff |  0.5 PB | ... unused hole
+ ffd4000000000000 |  -11    PB | ffd5ffffffffffff |  0.5 PB | virtual memory map (vmemmap_base)
+ ffd6000000000000 |  -10.5  PB | ffdeffffffffffff | 2.25 PB | ... unused hole
+ ffdf000000000000 |   -8.25 PB | fffffdffffffffff |   ~8 PB | KASAN shadow memory
+ fffffc0000000000 |   -4    TB | fffffdffffffffff |    2 TB | ... unused hole
+                  |            |                  |         | vaddr_end for KASLR
+ fffffe0000000000 |   -2    TB | fffffe7fffffffff |  0.5 TB | cpu_entry_area mapping
+ fffffe8000000000 |   -1.5  TB | fffffeffffffffff |  0.5 TB | ... unused hole
+ ffffff0000000000 |   -1    TB | ffffff7fffffffff |  0.5 TB | %esp fixup stacks
+__________________|____________|__________________|_________|____________________________________________________________
+                                                            |
+                                                            | Identical layout to the 47-bit one from here on:
+____________________________________________________________|____________________________________________________________
+                  |            |                  |         |
+ ffffff8000000000 | -512    GB | ffffffeeffffffff |  444 GB | ... unused hole
+ ffffffef00000000 |  -68    GB | fffffffeffffffff |   64 GB | EFI region mapping space
+ ffffffff00000000 |   -4    GB | ffffffff7fffffff |    2 GB | ... unused hole
+ ffffffff80000000 |   -2    GB | ffffffff9fffffff |  512 MB | kernel text mapping, mapped to physical address 0
+ ffffffff80000000 |-2048    MB |                  |         |
+ ffffffffa0000000 |-1536    MB | fffffffffeffffff | 1520 MB | module mapping space
+ ffffffffff000000 |  -16    MB |                  |         |
+    FIXADDR_START | ~-11    MB | ffffffffff5fffff | ~0.5 MB | kernel-internal fixmap range, variable size and offset
+ ffffffffff600000 |  -10    MB | ffffffffff600fff |    4 kB | legacy vsyscall ABI
+ ffffffffffe00000 |   -2    MB | 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
author	Ingo Molnar <mingo@kernel.org>	2018-10-06 07:41:12 -0400
committer	Ingo Molnar <mingo@kernel.org>	2018-10-06 10:36:12 -0400
commit	32b89760ddf4477da436c272be2abc016e169031 (patch)
tree	a9d9ff3cf92cc13f0cf2f9979612aa8f0779c4b5
parent	5b12904065798fee8b153a506ac7b72d5ebbe26c (diff)

diff --git a/Documentation/x86/x86_64/mm.txt b/Documentation/x86/x86_64/mm.txt index b4bc95c9790e..702898633b00 100644 --- a/Documentation/x86/x86_64/mm.txt +++ b/Documentation/x86/x86_64/mm.txt
@@ -1,55 +1,124 @@
		1	====================================================
		2	Complete virtual memory map with 4-level page tables
		3	====================================================
1		4
2	Virtual memory map with 4 level page tables:	5	Notes:
3		6
4	0000000000000000 - 00007fffffffffff (=47 bits, 128 TB) user space, different per mm	7	- Negative addresses such as "-23 TB" are absolute addresses in bytes, counted down
5	hole caused by [47:63] sign extension	8	from the top of the 64-bit address space. It's easier to understand the layout
6	ffff800000000000 - ffff87ffffffffff (=43 bits, 8 TB) guard hole, reserved for hypervisor	9	when seen both in absolute addresses and in distance-from-top notation.
7	ffff880000000000 - ffffc7ffffffffff (=46 bits, 64 TB) direct mapping of all phys. memory (page_offset_base)	10
8	ffffc80000000000 - ffffc8ffffffffff (=40 bits, 1 TB) unused hole	11	For example 0xffffe90000000000 == -23 TB, it's 23 TB lower than the top of the
9	ffffc90000000000 - ffffe8ffffffffff (=45 bits, 32 TB) vmalloc/ioremap space (vmalloc_base)	12	64-bit address space (ffffffffffffffff).
10	ffffe90000000000 - ffffe9ffffffffff (=40 bits, 1 TB) unused hole	13
11	ffffea0000000000 - ffffeaffffffffff (=40 bits, 1 TB) virtual memory map (vmemmap_base)	14	Note that as we get closer to the top of the address space, the notation changes
12	ffffeb0000000000 - ffffebffffffffff (=40 bits, 1 TB) unused hole	15	from TB to GB and then MB/KB.
13	ffffec0000000000 - fffffbffffffffff (=44 bits, 16 TB) kasan shadow memory	16
14	fffffc0000000000 - fffffdffffffffff (=41 bits, 2 TB) unused hole	17	- "16M TB" might look weird at first sight, but it's an easier to visualize size
15	vaddr_end for KASLR	18	notation than "16 EB", which few will recognize at first sight as 16 exabytes.
16	fffffe0000000000 - fffffe7fffffffff (=39 bits, 512 GB) cpu_entry_area mapping	19	It also shows it nicely how incredibly large 64-bit address space is.
17	fffffe8000000000 - fffffeffffffffff (=39 bits, 512 GB) LDT remap for PTI	20
18	ffffff0000000000 - ffffff7fffffffff (=39 bits, 512 GB) %esp fixup stacks	21	========================================================================================================================
19	ffffff8000000000 - fffffffeefffffff (~39 bits, ~507 GB) unused hole	22	Start addr \| Offset \| End addr \| Size \| VM area description
20	ffffffef00000000 - fffffffeffffffff (=36 bits, 64 GB) EFI region mapping space	23	========================================================================================================================
21	ffffffff00000000 - ffffffff7fffffff (=31 bits, 2 GB) unused hole	24	\| \| \| \|
22	ffffffff80000000 - ffffffff9fffffff (=29 bits, 512 MB) kernel text mapping, from phys 0	25	0000000000000000 \| 0 \| 00007fffffffffff \| 128 TB \| user-space virtual memory, different per mm
23	ffffffffa0000000 - fffffffffeffffff (~31 bits, 1520 MB) module mapping space	26	__________________\|____________\|__________________\|_________\|___________________________________________________________
24	[fixmap start] - ffffffffff5fffff kernel-internal fixmap range	27	\| \| \| \|
25	ffffffffff600000 - ffffffffff600fff ( =4 kB) legacy vsyscall ABI	28	0000800000000000 \| +128 TB \| ffff7fffffffffff \| ~16M TB \| ... huge, almost 64 bits wide hole of non-canonical
26	ffffffffffe00000 - ffffffffffffffff ( =2 MB) unused hole	29	\| \| \| \| virtual memory addresses up to the -128 TB
27		30	\| \| \| \| starting offset of kernel mappings.
28	Virtual memory map with 5 level page tables:	31	__________________\|____________\|__________________\|_________\|___________________________________________________________
29		32	\|
30	0000000000000000 - 00ffffffffffffff (=56 bits, 64 PB) user space, different per mm	33	\| Kernel-space virtual memory, shared between all processes:
31	hole caused by [56:63] sign extension	34	____________________________________________________________\|___________________________________________________________
32	ff00000000000000 - ff0fffffffffffff (=52 bits, 4 PB) guard hole, reserved for hypervisor	35	\| \| \| \|
33	ff10000000000000 - ff8fffffffffffff (=55 bits, 32 PB) direct mapping of all phys. memory (page_offset_base)	36	ffff800000000000 \| -128 TB \| ffff87ffffffffff \| 8 TB \| ... guard hole, also reserved for hypervisor
34	ff90000000000000 - ff9fffffffffffff (=52 bits, 4 PB) LDT remap for PTI	37	ffff880000000000 \| -120 TB \| ffffc7ffffffffff \| 64 TB \| direct mapping of all physical memory (page_offset_base)
35	ffa0000000000000 - ffd1ffffffffffff (=53 bits, 12800 TB) vmalloc/ioremap space (vmalloc_base)	38	ffffc80000000000 \| -56 TB \| ffffc8ffffffffff \| 1 TB \| ... unused hole
36	ffd2000000000000 - ffd3ffffffffffff (=49 bits, 512 TB) unused hole	39	ffffc90000000000 \| -55 TB \| ffffe8ffffffffff \| 32 TB \| vmalloc/ioremap space (vmalloc_base)
37	ffd4000000000000 - ffd5ffffffffffff (=49 bits, 512 TB) virtual memory map (vmemmap_base)	40	ffffe90000000000 \| -23 TB \| ffffe9ffffffffff \| 1 TB \| ... unused hole
38	ffd6000000000000 - ffdeffffffffffff (~51 bits, 2304 TB) unused hole	41	ffffea0000000000 \| -22 TB \| ffffeaffffffffff \| 1 TB \| virtual memory map (vmemmap_base)
39	ffdf000000000000 - fffffdffffffffff (~53 bits, ~8 PB) kasan shadow memory	42	ffffeb0000000000 \| -21 TB \| ffffebffffffffff \| 1 TB \| ... unused hole
40	fffffc0000000000 - fffffdffffffffff (=41 bits, 2 TB) unused hole	43	ffffec0000000000 \| -20 TB \| fffffbffffffffff \| 16 TB \| KASAN shadow memory
41	vaddr_end for KASLR	44	fffffc0000000000 \| -4 TB \| fffffdffffffffff \| 2 TB \| ... unused hole
42	fffffe0000000000 - fffffe7fffffffff (=39 bits, 512 GB) cpu_entry_area mapping	45	\| \| \| \| vaddr_end for KASLR
43	fffffe8000000000 - fffffeffffffffff (=39 bits, 512 GB) unused hole	46	fffffe0000000000 \| -2 TB \| fffffe7fffffffff \| 0.5 TB \| cpu_entry_area mapping
44	ffffff0000000000 - ffffff7fffffffff (=39 bits, 512 GB) %esp fixup stacks	47	fffffe8000000000 \| -1.5 TB \| fffffeffffffffff \| 0.5 TB \| LDT remap for PTI
45	ffffff8000000000 - ffffffeeffffffff (~39 bits, 444 GB) unused hole	48	ffffff0000000000 \| -1 TB \| ffffff7fffffffff \| 0.5 TB \| %esp fixup stacks
46	ffffffef00000000 - fffffffeffffffff (=36 bits, 64 GB) EFI region mapping space	49	__________________\|____________\|__________________\|_________\|____________________________________________________________
47	ffffffff00000000 - ffffffff7fffffff (31 bits, 2 GB) unused hole	50	\|
48	ffffffff80000000 - ffffffff9fffffff (=29 bits, 512 MB) kernel text mapping, from phys 0	51	\| Identical layout to the 47-bit one from here on:
49	ffffffffa0000000 - fffffffffeffffff (~31 bits, 1520 MB) module mapping space	52	____________________________________________________________\|____________________________________________________________
50	[fixmap start] - ffffffffff5fffff kernel-internal fixmap range	53	\| \| \| \|
51	ffffffffff600000 - ffffffffff600fff ( =4 kB) legacy vsyscall ABI	54	ffffff8000000000 \| -512 GB \| ffffffeeffffffff \| 444 GB \| ... unused hole
52	ffffffffffe00000 - ffffffffffffffff ( =2 MB) unused hole	55	ffffffef00000000 \| -68 GB \| fffffffeffffffff \| 64 GB \| EFI region mapping space
		56	ffffffff00000000 \| -4 GB \| ffffffff7fffffff \| 2 GB \| ... unused hole
		57	ffffffff80000000 \| -2 GB \| ffffffff9fffffff \| 512 MB \| kernel text mapping, mapped to physical address 0
		58	ffffffff80000000 \|-2048 MB \| \| \|
		59	ffffffffa0000000 \|-1536 MB \| fffffffffeffffff \| 1520 MB \| module mapping space
		60	ffffffffff000000 \| -16 MB \| \| \|
		61	FIXADDR_START \| ~-11 MB \| ffffffffff5fffff \| ~0.5 MB \| kernel-internal fixmap range, variable size and offset
		62	ffffffffff600000 \| -10 MB \| ffffffffff600fff \| 4 kB \| legacy vsyscall ABI
		63	ffffffffffe00000 \| -2 MB \| ffffffffffffffff \| 2 MB \| ... unused hole
		64	__________________\|____________\|__________________\|_________\|___________________________________________________________
		65
		66
		67	====================================================
		68	Complete virtual memory map with 5-level page tables
		69	====================================================
		70
		71	Notes:
		72
		73	- With 56-bit addresses, user-space memory gets expanded by a factor of 512x,
		74	from 0.125 PB to 64 PB. All kernel mappings shift down to the -64 PT starting
		75	offset and many of the regions expand to support the much larger physical
		76	memory supported.
		77
		78	========================================================================================================================
		79	Start addr \| Offset \| End addr \| Size \| VM area description
		80	========================================================================================================================
		81	\| \| \| \|
		82	0000000000000000 \| 0 \| 00ffffffffffffff \| 64 PB \| user-space virtual memory, different per mm
		83	__________________\|____________\|__________________\|_________\|___________________________________________________________
		84	\| \| \| \|
		85	0000800000000000 \| +64 PB \| ffff7fffffffffff \| ~16K PB \| ... huge, still almost 64 bits wide hole of non-canonical
		86	\| \| \| \| virtual memory addresses up to the -128 TB
		87	\| \| \| \| starting offset of kernel mappings.
		88	__________________\|____________\|__________________\|_________\|___________________________________________________________
		89	\|
		90	\| Kernel-space virtual memory, shared between all processes:
		91	____________________________________________________________\|___________________________________________________________
		92	\| \| \| \|
		93	ff00000000000000 \| -64 PB \| ff0fffffffffffff \| 4 PB \| ... guard hole, also reserved for hypervisor
		94	ff10000000000000 \| -60 PB \| ff8fffffffffffff \| 32 PB \| direct mapping of all physical memory (page_offset_base)
		95	ff90000000000000 \| -28 PB \| ff9fffffffffffff \| 4 PB \| LDT remap for PTI
		96	ffa0000000000000 \| -24 PB \| ffd1ffffffffffff \| 12.5 PB \| vmalloc/ioremap space (vmalloc_base)
		97	ffd2000000000000 \| -11.5 PB \| ffd3ffffffffffff \| 0.5 PB \| ... unused hole
		98	ffd4000000000000 \| -11 PB \| ffd5ffffffffffff \| 0.5 PB \| virtual memory map (vmemmap_base)
		99	ffd6000000000000 \| -10.5 PB \| ffdeffffffffffff \| 2.25 PB \| ... unused hole
		100	ffdf000000000000 \| -8.25 PB \| fffffdffffffffff \| ~8 PB \| KASAN shadow memory
		101	fffffc0000000000 \| -4 TB \| fffffdffffffffff \| 2 TB \| ... unused hole
		102	\| \| \| \| vaddr_end for KASLR
		103	fffffe0000000000 \| -2 TB \| fffffe7fffffffff \| 0.5 TB \| cpu_entry_area mapping
		104	fffffe8000000000 \| -1.5 TB \| fffffeffffffffff \| 0.5 TB \| ... unused hole
		105	ffffff0000000000 \| -1 TB \| ffffff7fffffffff \| 0.5 TB \| %esp fixup stacks
		106	__________________\|____________\|__________________\|_________\|____________________________________________________________
		107	\|
		108	\| Identical layout to the 47-bit one from here on:
		109	____________________________________________________________\|____________________________________________________________
		110	\| \| \| \|
		111	ffffff8000000000 \| -512 GB \| ffffffeeffffffff \| 444 GB \| ... unused hole
		112	ffffffef00000000 \| -68 GB \| fffffffeffffffff \| 64 GB \| EFI region mapping space
		113	ffffffff00000000 \| -4 GB \| ffffffff7fffffff \| 2 GB \| ... unused hole
		114	ffffffff80000000 \| -2 GB \| ffffffff9fffffff \| 512 MB \| kernel text mapping, mapped to physical address 0
		115	ffffffff80000000 \|-2048 MB \| \| \|
		116	ffffffffa0000000 \|-1536 MB \| fffffffffeffffff \| 1520 MB \| module mapping space
		117	ffffffffff000000 \| -16 MB \| \| \|
		118	FIXADDR_START \| ~-11 MB \| ffffffffff5fffff \| ~0.5 MB \| kernel-internal fixmap range, variable size and offset
		119	ffffffffff600000 \| -10 MB \| ffffffffff600fff \| 4 kB \| legacy vsyscall ABI
		120	ffffffffffe00000 \| -2 MB \| ffffffffffffffff \| 2 MB \| ... unused hole
		121	__________________\|____________\|__________________\|_________\|___________________________________________________________
53		122
54	Architecture defines a 64-bit virtual address. Implementations can support	123	Architecture defines a 64-bit virtual address. Implementations can support
55	less. Currently supported are 48- and 57-bit virtual addresses. Bits 63	124	less. Currently supported are 48- and 57-bit virtual addresses. Bits 63