arm64: Determine the vmalloc/vmemmap space at build time based on VA_BITS

Rather than guessing what the maximum vmmemap space should be, this
patch allows the calculation based on the VA_BITS and sizeof(struct
page). The vmalloc space extends to the beginning of the vmemmap space.

Since the virtual kernel memory layout now depends on the build
configuration, this patch removes the detailed description in
Documentation/arm64/memory.txt in favour of information printed during
kernel booting.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Tested-by: Jungseok Lee <jungseoklee85@gmail.com>

3 files changed, 38 insertions, 95 deletions

diff --git a/Documentation/arm64/memory.txt b/Documentation/arm64/memory.txt
index 4c720d698e8e..8845d0847a66 100644
--- a/Documentation/arm64/memory.txt
+++ b/Documentation/arm64/memory.txt
@@ -2,19 +2,18 @@
 		     ==============================
 
 Author: Catalin Marinas <catalin.marinas@arm.com>
-Date  : 20 February 2012
 
 This document describes the virtual memory layout used by the AArch64
 Linux kernel. The architecture allows up to 4 levels of translation
 tables with a 4KB page size and up to 3 levels with a 64KB page size.
 
-AArch64 Linux uses either 3 levels or 4 levels of translation tables with
-the 4KB page configuration, allowing 39-bit (512GB) or 48-bit (256TB)
-virtual addresses, respectively, for both user and kernel. With 64KB
-pages, only 2 levels of translation tables, allowing 42-bit (4TB)
+AArch64 Linux uses either 3 levels or 4 levels of translation tables
+with the 4KB page configuration, allowing 39-bit (512GB) or 48-bit
+(256TB) virtual addresses, respectively, for both user and kernel. With
+64KB pages, only 2 levels of translation tables, allowing 42-bit (4TB)
 virtual address, are used but the memory layout is the same.
 
-User addresses have bits 63:39 set to 0 while the kernel addresses have
+User addresses have bits 63:48 set to 0 while the kernel addresses have
 the same bits set to 1. TTBRx selection is given by bit 63 of the
 virtual address. The swapper_pg_dir contains only kernel (global)
 mappings while the user pgd contains only user (non-global) mappings.
@@ -27,26 +26,7 @@ AArch64 Linux memory layout with 4KB pages + 3 levels:
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	0000007fffffffff	 512GB		user
-
-ffffff8000000000	ffffffbbfffeffff	~240GB		vmalloc
-
-ffffffbbffff0000	ffffffbbffffffff	  64KB		[guard page]
-
-ffffffbc00000000	ffffffbdffffffff	   8GB		vmemmap
-
-ffffffbe00000000	ffffffbffbbfffff	  ~8GB		[guard, future vmmemap]
-
-ffffffbffa000000	ffffffbffaffffff	  16MB		PCI I/O space
-
-ffffffbffb000000	ffffffbffbbfffff	  12MB		[guard]
-
-ffffffbffbc00000	ffffffbffbdfffff	   2MB		fixed mappings
-
-ffffffbffbe00000	ffffffbffbffffff	   2MB		[guard]
-
-ffffffbffc000000	ffffffbfffffffff	  64MB		modules
-
-ffffffc000000000	ffffffffffffffff	 256GB		kernel logical memory map
+ffffff8000000000	ffffffffffffffff	 512GB		kernel
 
 
 AArch64 Linux memory layout with 4KB pages + 4 levels:
@@ -54,26 +34,7 @@ AArch64 Linux memory layout with 4KB pages + 4 levels:
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	0000ffffffffffff	 256TB		user
-
-ffff000000000000	ffff7bfffffeffff	~124TB		vmalloc
-
-ffff7bffffff0000	ffff7bffffffffff	  64KB		[guard page]
-
-ffff7c0000000000	ffff7dffffffffff	   2TB		vmemmap
-
-ffff7e0000000000	ffff7ffffbbfffff	  ~2TB		[guard, future vmmemap]
-
-ffff7ffffa000000	ffff7ffffaffffff	  16MB		PCI I/O space
-
-ffff7ffffb000000	ffff7ffffbbfffff	  12MB		[guard]
-
-ffff7ffffbc00000	ffff7ffffbdfffff	   2MB		fixed mappings
-
-ffff7ffffbe00000	ffff7ffffbffffff	   2MB		[guard]
-
-ffff7ffffc000000	ffff7fffffffffff	  64MB		modules
-
-ffff800000000000	ffffffffffffffff	 128TB		kernel logical memory map
+ffff000000000000	ffffffffffffffff	 256TB		kernel
 
 
 AArch64 Linux memory layout with 64KB pages + 2 levels:
@@ -81,44 +42,14 @@ AArch64 Linux memory layout with 64KB pages + 2 levels:
 Start			End			Size		Use
 -----------------------------------------------------------------------
 0000000000000000	000003ffffffffff	   4TB		user
+fffffc0000000000	ffffffffffffffff	   4TB		kernel
 
-fffffc0000000000	fffffdfbfffeffff	  ~2TB		vmalloc
-
-fffffdfbffff0000	fffffdfbffffffff	  64KB		[guard page]
 
-fffffdfc00000000	fffffdfdffffffff	   8GB		vmemmap
+For details of the virtual kernel memory layout please see the kernel
+booting log.
 
-fffffdfe00000000	fffffdfffbbfffff	  ~8GB		[guard, future vmmemap]
 
-fffffdfffa000000	fffffdfffaffffff	  16MB		PCI I/O space
-
-fffffdfffb000000	fffffdfffbbfffff	  12MB		[guard]
-
-fffffdfffbc00000	fffffdfffbdfffff	   2MB		fixed mappings
-
-fffffdfffbe00000	fffffdfffbffffff	   2MB		[guard]
-
-fffffdfffc000000	fffffdffffffffff	  64MB		modules
-
-fffffe0000000000	ffffffffffffffff	   2TB		kernel logical memory map
-
-
-Translation table lookup with 4KB pages + 3 levels:
-
-+--------+--------+--------+--------+--------+--------+--------+--------+
-|63    56|55    48|47    40|39    32|31    24|23    16|15     8|7      0|
-+--------+--------+--------+--------+--------+--------+--------+--------+
- |                 |         |         |         |         |
- |                 |         |         |         |         v
- |                 |         |         |         |   [11:0]  in-page offset
- |                 |         |         |         +-> [20:12] L3 index
- |                 |         |         +-----------> [29:21] L2 index
- |                 |         +---------------------> [38:30] L1 index
- |                 +-------------------------------> [47:39] L0 index (not used)
- +-------------------------------------------------> [63] TTBR0/1
-
-
-Translation table lookup with 4KB pages + 4 levels:
+Translation table lookup with 4KB pages:
 
 +--------+--------+--------+--------+--------+--------+--------+--------+
 |63    56|55    48|47    40|39    32|31    24|23    16|15     8|7      0|
@@ -133,7 +64,7 @@ Translation table lookup with 4KB pages + 4 levels:
  +-------------------------------------------------> [63] TTBR0/1
 
 
-Translation table lookup with 64KB pages + 2 levels:
+Translation table lookup with 64KB pages:
 
 +--------+--------+--------+--------+--------+--------+--------+--------+
 |63    56|55    48|47    40|39    32|31    24|23    16|15     8|7      0|
@@ -142,10 +73,11 @@ Translation table lookup with 64KB pages + 2 levels:
  |                 |    |               |              v
  |                 |    |               |            [15:0]  in-page offset
  |                 |    |               +----------> [28:16] L3 index
- |                 |    +--------------------------> [41:29] L2 index (only 38:29 used)
- |                 +-------------------------------> [47:42] L1 index (not used)
+ |                 |    +--------------------------> [41:29] L2 index
+ |                 +-------------------------------> [47:42] L1 index
  +-------------------------------------------------> [63] TTBR0/1
 
+
 When using KVM, the hypervisor maps kernel pages in EL2, at a fixed
 offset from the kernel VA (top 24bits of the kernel VA set to zero):
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 9f862e6e9286..ec82789d03c3 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -33,13 +33,16 @@
 
 /*
  * VMALLOC and SPARSEMEM_VMEMMAP ranges.
+ *
+ * VMEMAP_SIZE: allows the whole VA space to be covered by a struct page array
+ *	(rounded up to PUD_SIZE).
+ * VMALLOC_START: beginning of the kernel VA space
+ * VMALLOC_END: extends to the available space below vmmemmap, PCI I/O space,
+ *	fixed mappings and modules
  */
+#define VMEMMAP_SIZE		ALIGN((1UL << (VA_BITS - PAGE_SHIFT)) * sizeof(struct page), PUD_SIZE)
 #define VMALLOC_START		(UL(0xffffffffffffffff) << VA_BITS)
-#if CONFIG_ARM64_PGTABLE_LEVELS != 4
-#define VMALLOC_END		(PAGE_OFFSET - UL(0x400000000) - SZ_64K)
-#else
-#define VMALLOC_END		(PAGE_OFFSET - UL(0x40000000000) - SZ_64K)
-#endif
+#define VMALLOC_END		(PAGE_OFFSET - PUD_SIZE - VMEMMAP_SIZE - SZ_64K)
 
 #define vmemmap			((struct page *)(VMALLOC_END + SZ_64K))
 
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 7f68804814a1..0b32504e280f 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -33,6 +33,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
 
+#include <asm/fixmap.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/sizes.h>
@@ -256,26 +257,33 @@ void __init mem_init(void)
 
 #define MLK(b, t) b, t, ((t) - (b)) >> 10
 #define MLM(b, t) b, t, ((t) - (b)) >> 20
+#define MLG(b, t) b, t, ((t) - (b)) >> 30
 #define MLK_ROUNDUP(b, t) b, t, DIV_ROUND_UP(((t) - (b)), SZ_1K)
 
 	pr_notice("Virtual kernel memory layout:\n"
-		  "    vmalloc : 0x%16lx - 0x%16lx   (%6ld MB)\n"
+		  "    vmalloc : 0x%16lx - 0x%16lx   (%6ld GB)\n"
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
-		  "    vmemmap : 0x%16lx - 0x%16lx   (%6ld MB)\n"
+		  "    vmemmap : 0x%16lx - 0x%16lx   (%6ld GB maximum)\n"
+		  "              0x%16lx - 0x%16lx   (%6ld MB actual)\n"
 #endif
+		  "    PCI I/O : 0x%16lx - 0x%16lx   (%6ld MB)\n"
+		  "    fixed   : 0x%16lx - 0x%16lx   (%6ld KB)\n"
 		  "    modules : 0x%16lx - 0x%16lx   (%6ld MB)\n"
 		  "    memory  : 0x%16lx - 0x%16lx   (%6ld MB)\n"
-		  "      .init : 0x%p" " - 0x%p" "   (%6ld kB)\n"
-		  "      .text : 0x%p" " - 0x%p" "   (%6ld kB)\n"
-		  "      .data : 0x%p" " - 0x%p" "   (%6ld kB)\n",
-		  MLM(VMALLOC_START, VMALLOC_END),
+		  "      .init : 0x%p" " - 0x%p" "   (%6ld KB)\n"
+		  "      .text : 0x%p" " - 0x%p" "   (%6ld KB)\n"
+		  "      .data : 0x%p" " - 0x%p" "   (%6ld KB)\n",
+		  MLG(VMALLOC_START, VMALLOC_END),
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
+		  MLG((unsigned long)vmemmap,
+		      (unsigned long)vmemmap + VMEMMAP_SIZE),
 		  MLM((unsigned long)virt_to_page(PAGE_OFFSET),
 		      (unsigned long)virt_to_page(high_memory)),
 #endif
+		  MLM((unsigned long)PCI_IOBASE, (unsigned long)PCI_IOBASE + SZ_16M),
+		  MLK(FIXADDR_START, FIXADDR_TOP),
 		  MLM(MODULES_VADDR, MODULES_END),
 		  MLM(PAGE_OFFSET, (unsigned long)high_memory),
-
 		  MLK_ROUNDUP(__init_begin, __init_end),
 		  MLK_ROUNDUP(_text, _etext),
 		  MLK_ROUNDUP(_sdata, _edata));