Re: [PATCH 4/7] [RFC] enable L1_WRITETHROUGH mode for BG/P

[Benjamin Herrenschmidt <benh@kernel.crashing.org>]

On Wed, 2011-05-18 at 16:24 -0500, Eric Van Hensbergen wrote:
> BG/P nodes need to be configured for writethrough to work in SMP
> configurations.  This patch adds the right hooks in the MMU code
> to make sure L1_WRITETHROUGH configurations are setup for BG/P.

>  /* Storage attribute and access control fields */
>  #define PPC44x_TLB_ATTR_MASK	0x0000ff80
> +#define PPC44x_TLB_WL1		0x00100000	/* Write-through L1 */
>  #define PPC44x_TLB_U0		0x00008000      /* User 0 */
>  #define PPC44x_TLB_U1		0x00004000      /* User 1 */
>  #define PPC44x_TLB_U2		0x00002000      /* User 2 */
> diff --git a/arch/powerpc/kernel/head_44x.S b/arch/powerpc/kernel/head_44x.S
> index 5e12b74..1f7ae60 100644
> --- a/arch/powerpc/kernel/head_44x.S
> +++ b/arch/powerpc/kernel/head_44x.S
> @@ -429,7 +429,16 @@ finish_tlb_load_44x:
>  	andi.	r10,r12,_PAGE_USER		/* User page ? */
>  	beq	1f				/* nope, leave U bits empty */
>  	rlwimi	r11,r11,3,26,28			/* yes, copy S bits to U */
> -1:	tlbwe	r11,r13,PPC44x_TLB_ATTRIB	/* Write ATTRIB */
> +1:
> +#ifdef CONFIG_L1_WRITETHROUGH
> +	andi.	r10, r11, PPC44x_TLB_I
> +	bne	2f
> +	oris    r11,r11,PPC44x_TLB_WL1@h	/* Add coherency for */
> +						/* non-inhibited */
> +	ori	r11,r11,PPC44x_TLB_U2|PPC44x_TLB_M
> +2:
> +#endif /* CONFIG_L1_WRITETHROUGH */

Make it an MMU feature so it's done at runtime rather than compile time.

Also, you should aim toward avoiding that conditional branch in such a
critical hot path :-) A way to do so would be to shove these in the PTE
instead, there's plenty of unused bits in the top part for example.

> +	tlbwe	r11,r13,PPC44x_TLB_ATTRIB	/* Write ATTRIB */
>  
>  	/* Done...restore registers and get out of here.
>  	*/
> @@ -799,7 +808,11 @@ skpinv:	addi	r4,r4,1				/* Increment */
>  	sync
>  
>  	/* Initialize MMUCR */
> +#ifdef CONFIG_L1_WRITETHROUGH
> +	lis	r5, PPC44x_MMUCR_U2@h
> +#else
>  	li	r5,0
> +#endif /* CONFIG_L1_WRITETHROUGH */
>  	mtspr	SPRN_MMUCR,r5
>  	sync
>  
> @@ -814,7 +827,14 @@ skpinv:	addi	r4,r4,1				/* Increment */
>  	/* attrib fields */
>  	/* Added guarded bit to protect against speculative loads/stores */
>  	li	r5,0
> -	ori	r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G)
> +#ifdef CONFIG_L1_WRITETHROUGH
> +	ori	r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | \
> +						PPC44x_TLB_G | PPC44x_TLB_U2)
> +	oris	r5,r5,PPC44x_TLB_WL1@h
> +#else
> +	ori	r5,r5,(PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | \
> +			PPC44x_TLB_G)
> +#endif /* CONFIG_L1_WRITETHROUGH
>  
>          li      r0,63                    /* TLB slot 63 */
>  
> diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
> index 094bd98..d88369b 100644
> --- a/arch/powerpc/kernel/misc_32.S
> +++ b/arch/powerpc/kernel/misc_32.S
> @@ -506,7 +506,20 @@ _GLOBAL(clear_pages)
>  	li	r0,PAGE_SIZE/L1_CACHE_BYTES
>  	slw	r0,r0,r4
>  	mtctr	r0
> +#ifdef CONFIG_L1_WRITETHROUGH
> +	/* assuming 32 byte cacheline */
> +	li      r4, 0
> +1:	stw     r4, 0(r3)
> +	stw     r4, 4(r3)
> +	stw     r4, 8(r3)
> +	stw     r4, 12(r3)
> +	stw     r4, 16(r3)
> +	stw     r4, 20(r3)
> +	stw     r4, 24(r3)
> +	stw     r4, 28(r3)
> +#else
>  1:	dcbz	0,r3
> +#endif /* CONFIG_L1_WRITETHROUGH */

wtf ? dcbz doesn't work ? yuck ! This isn't a HW design, it's a hack :-)

make it an mmu feature btw, as I said, I'd like to keep it a unified
kernel.

>  	addi	r3,r3,L1_CACHE_BYTES
>  	bdnz	1b
>  	blr
> @@ -550,7 +563,9 @@ _GLOBAL(copy_page)
>  	mtctr	r0
>  1:
>  	dcbt	r11,r4
> +#ifndef CONFIG_L1_WRITETHROUGH
>  	dcbz	r5,r3
> +#endif
>  	COPY_16_BYTES
>  #if L1_CACHE_BYTES >= 32
>  	COPY_16_BYTES
> diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
> index 55f19f9..98a07e3 100644
> --- a/arch/powerpc/lib/copy_32.S
> +++ b/arch/powerpc/lib/copy_32.S
> @@ -98,7 +98,11 @@ _GLOBAL(cacheable_memzero)
>  	bdnz	4b
>  3:	mtctr	r9
>  	li	r7,4
> +#ifdef CONFIG_L1_WRITETHROUGH
> +10:
> +#else
>  10:	dcbz	r7,r6
> +#endif /* CONFIG_L1_WRITETHROUGH */
>  	addi	r6,r6,CACHELINE_BYTES
>  	bdnz	10b
>  	clrlwi	r5,r8,32-LG_CACHELINE_BYTES
> @@ -187,7 +191,9 @@ _GLOBAL(cacheable_memcpy)
>  	mtctr	r0
>  	beq	63f
>  53:
> +#ifndef CONFIG_L1_WRITETHROUGH
>  	dcbz	r11,r6
> +#endif /* CONFIG_L1_WRITETHROUGH */
>  	COPY_16_BYTES
>  #if L1_CACHE_BYTES >= 32
>  	COPY_16_BYTES
> @@ -368,7 +374,11 @@ _GLOBAL(__copy_tofrom_user)
>  	mtctr	r8
>  
>  53:	dcbt	r3,r4
> +#ifdef CONFIG_L1_WRITETHROUGH
> +54:
> +#else
>  54:	dcbz	r11,r6
> +#endif
>  	.section __ex_table,"a"
>  	.align	2
>  	.long	54b,105f
> diff --git a/arch/powerpc/mm/44x_mmu.c b/arch/powerpc/mm/44x_mmu.c
> index 024acab..b684c8a 100644
> --- a/arch/powerpc/mm/44x_mmu.c
> +++ b/arch/powerpc/mm/44x_mmu.c
> @@ -80,9 +80,12 @@ static void __init ppc44x_pin_tlb(unsigned int virt, unsigned int phys)
>  	:
>  #ifdef CONFIG_PPC47x
>  	: "r" (PPC47x_TLB2_S_RWX),
> -#else
> +#elseif CONFIG_L1_WRITETHROUGH
> +	: "r" (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_WL1 \
> +		| PPC44x_TLB_U2 | PPC44x_TLB_M),
> +#else /* neither CONFIG_PPC47x or CONFIG_L1_WRITETHROUGH */
>  	: "r" (PPC44x_TLB_SW | PPC44x_TLB_SR | PPC44x_TLB_SX | PPC44x_TLB_G),
> -#endif
> +#endif /* CONFIG_PPC47x */
>  	  "r" (phys),
>  	  "r" (virt | PPC44x_TLB_VALID | PPC44x_TLB_256M),
>  	  "r" (entry),
> diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
> index f7b0772..684a281 100644
> --- a/arch/powerpc/platforms/Kconfig
> +++ b/arch/powerpc/platforms/Kconfig
> @@ -348,4 +348,9 @@ config XILINX_PCI
>  	bool "Xilinx PCI host bridge support"
>  	depends on PCI && XILINX_VIRTEX
>  
> +config L1_WRITETHROUGH
> +	bool "Blue Gene/P enabled writethrough mode"
> +	depends on BGP
> +	default y
> +
>  endmenu
> diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
> index 111138c..3a3c711 100644
> --- a/arch/powerpc/platforms/Kconfig.cputype
> +++ b/arch/powerpc/platforms/Kconfig.cputype
> @@ -329,9 +329,13 @@ config NOT_COHERENT_CACHE
>  	bool
>  	depends on 4xx || 8xx || E200 || PPC_MPC512x || GAMECUBE_COMMON
>  	default n if PPC_47x
> +	default n if BGP
>  	default y
>  
>  config CHECK_CACHE_COHERENCY
>  	bool
>  
> +config L1_WRITETHROUGH
> +	bool
> +
>  endmenu