[PATCH v2 08/20] ARM: LPAE: MMU setup for the 3-level page table format

[Russell King - ARM Linux]

On Fri, Nov 12, 2010 at 06:00:28PM +0000, Catalin Marinas wrote:
> This patch adds the MMU initialisation for the LPAE page table format.
> The swapper_pg_dir size with LPAE is 5 rather than 4 pages. The
> __v7_setup function configures the TTBRx split based on the PAGE_OFFSET
> and sets the corresponding TTB control and MAIRx bits (similar to
> PRRR/NMRR for TEX remapping). The 36-bit mappings (supersections) and
> a few other memory types in mmu.c are conditionally compiled.
> 
> Signed-off-by: Catalin Marinas <catalin.marinas at arm.com>
> ---
>  arch/arm/kernel/head.S    |   96 +++++++++++++++++++++++++++++++------------
>  arch/arm/mm/mmu.c         |   32 ++++++++++++++-
>  arch/arm/mm/proc-macros.S |    5 +-
>  arch/arm/mm/proc-v7.S     |   99 ++++++++++++++++++++++++++++++++++++++++----
>  4 files changed, 193 insertions(+), 39 deletions(-)
> 
> diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
> index dd6b369..fd8a29e 100644
> --- a/arch/arm/kernel/head.S
> +++ b/arch/arm/kernel/head.S
> @@ -21,6 +21,7 @@
>  #include <asm/memory.h>
>  #include <asm/thread_info.h>
>  #include <asm/system.h>
> +#include <asm/pgtable.h>
>  
>  #ifdef CONFIG_DEBUG_LL
>  #include <mach/debug-macro.S>
> @@ -45,11 +46,20 @@
>  #error KERNEL_RAM_VADDR must start at 0xXXXX8000
>  #endif
>  
> +#ifdef CONFIG_ARM_LPAE
> +	/* LPAE requires an additional page for the PGD */
> +#define PG_DIR_SIZE	0x5000
> +#define PTE_WORDS	3
> +#else
> +#define PG_DIR_SIZE	0x4000
> +#define PTE_WORDS	2

PTE is not the right prefix here - we don't deal with the lowest level
of page tables, which in Linux is called PTE.  I think you mean PMD_WORDS
instead.

> +#endif
> +
>  	.globl	swapper_pg_dir
> -	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - 0x4000
> +	.equ	swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE
>  
>  	.macro	pgtbl, rd
> -	ldr	\rd, =(KERNEL_RAM_PADDR - 0x4000)
> +	ldr	\rd, =(KERNEL_RAM_PADDR - PG_DIR_SIZE)
>  	.endm
>  
>  #ifdef CONFIG_XIP_KERNEL
> @@ -129,11 +139,11 @@ __create_page_tables:
>  	pgtbl	r4				@ page table address
>  
>  	/*
> -	 * Clear the 16K level 1 swapper page table
> +	 * Clear the swapper page table
>  	 */
>  	mov	r0, r4
>  	mov	r3, #0
> -	add	r6, r0, #0x4000
> +	add	r6, r0, #PG_DIR_SIZE
>  1:	str	r3, [r0], #4
>  	str	r3, [r0], #4
>  	str	r3, [r0], #4
> @@ -141,6 +151,23 @@ __create_page_tables:
>  	teq	r0, r6
>  	bne	1b
>  
> +#ifdef CONFIG_ARM_LPAE
> +	/*
> +	 * Build the PGD table (first level) to point to the PMD table. A PGD
> +	 * entry is 64-bit wide and the top 32 bits are 0.
> +	 */
> +	mov	r0, r4
> +	add	r3, r4, #0x1000			@ first PMD table address
> +	orr	r3, r3, #3			@ PGD block type
> +	mov	r6, #4				@ PTRS_PER_PGD
> +1:	str	r3, [r0], #8			@ set PGD entry
> +	add	r3, r3, #0x1000			@ next PMD table
> +	subs	r6, r6, #1
> +	bne	1b
> +
> +	add	r4, r4, #0x1000			@ point to the PMD tables
> +#endif
> +
>  	ldr	r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags
>  
>  	/*
> @@ -152,30 +179,30 @@ __create_page_tables:
>  	sub	r0, r0, r3			@ virt->phys offset
>  	add	r5, r5, r0			@ phys __enable_mmu
>  	add	r6, r6, r0			@ phys __enable_mmu_end
> -	mov	r5, r5, lsr #20
> -	mov	r6, r6, lsr #20
> +	mov	r5, r5, lsr #SECTION_SHIFT
> +	mov	r6, r6, lsr #SECTION_SHIFT
>  
> -1:	orr	r3, r7, r5, lsl #20		@ flags + kernel base
> -	str	r3, [r4, r5, lsl #2]		@ identity mapping
> -	teq	r5, r6
> -	addne	r5, r5, #1			@ next section
> -	bne	1b
> +1:	orr	r3, r7, r5, lsl #SECTION_SHIFT	@ flags + kernel base
> +	str	r3, [r4, r5, lsl #PTE_WORDS]	@ identity mapping
> +	cmp	r5, r6
> +	addlo	r5, r5, #SECTION_SHIFT >> 20	@ next section
> +	blo	1b
>  
>  	/*
>  	 * Now setup the pagetables for our kernel direct
>  	 * mapped region.
>  	 */
>  	mov	r3, pc
> -	mov	r3, r3, lsr #20
> -	orr	r3, r7, r3, lsl #20
> +	mov	r3, r3, lsr #SECTION_SHIFT
> +	orr	r3, r7, r3, lsl #SECTION_SHIFT
>  	add	r0, r4,  #(KERNEL_START & 0xff000000) >> 18
> -	str	r3, [r0, #(KERNEL_START & 0x00f00000) >> 18]!
> +	str	r3, [r0, #(KERNEL_START & 0x00e00000) >> 18]!
>  	ldr	r6, =(KERNEL_END - 1)
> -	add	r0, r0, #4
> +	add	r0, r0, #1 << PTE_WORDS
>  	add	r6, r4, r6, lsr #18

Are you sure these shifts by 18 places are correct?  They're actually
(val >> SECTION_SHIFT) << 2, so maybe they should be (SECTION_SHIFT -
PMD_WORDS) ?