[PATCH v2] powerpc: Add hibernation support for FSL BookE processors

Fri Apr 16 04:45:13 EST 2010

On Thu, Feb 25, 2010 at 12:38:02AM +0300, Anton Vorontsov wrote:
> This is started as swsusp_32.S modifications, but the amount of #ifdefs
> made the whole file horribly unreadable, so let's put the support into
> its own separate file.
> 
> The code should be relatively easy to modify to support 44x BookEs as
> well, but since I don't have any 44x to test, let's confine the code to
> FSL BookE. (The only FSL-specific parts are 'flush_dcache_L1' and TLB
> invalidation code).
> 
> Signed-off-by: Anton Vorontsov <avorontsov at ru.mvista.com>
> ---
> 
> Sorry for the delayed response...
> 
> On Tue, Jan 12, 2010 at 01:34:08PM +1100, Benjamin Herrenschmidt wrote:
> [...]
> > Here's a quick review. Looks good but two things:
> > 
> >  - Please make it swsusp_booke.c, 44x support is trivial and I don't
> > want to rename the file :-)
> 
> Done.
> 
> >  - Is there really an SDR1 register on FSL BookE ? It's supposed to be
> > the pointer to the hash table on server ...
> 
> Thanks, fixed.
> 
> >  - You probably should save/restore the TCR and ack pending crap DEC or
> > FIT interrupts in the TSR right before you kick the decrementer
> 
> Done.
> 
> >  - Nowadays, we still assume that the "loader" kernel is exactly the
> > same as the "loaded" kernel on resume ?
> 
> I'm pretty sure today we do rely on this, yes. This is not some
> generic code limitation though, it's just hard to test the case
> when loader != loaded. In most cases it will work fine since the
> loader kernel wouldn't differ a lot from the loaded kernel, so
> it'll setup the low level stuff the same way.
> 
> We may try to link the loader kernel to a different address
> (relocate it as in kdump case), and hope that it'll trigger
> all sort of problems so that we could fix them.
> 
> Though, the better test case would be to resume the hibernated
> kernel directly from the bootloader.

Kumar,

According to patchwork, this is now delegated to you. Do you
have any objections to merge this?

Thanks!

>  arch/powerpc/kernel/Makefile       |    8 +-
>  arch/powerpc/kernel/swsusp_booke.S |  200 ++++++++++++++++++++++++++++++++++++
>  2 files changed, 206 insertions(+), 2 deletions(-)
>  create mode 100644 arch/powerpc/kernel/swsusp_booke.S
> 
> diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
> index c002b04..33d9dda 100644
> --- a/arch/powerpc/kernel/Makefile
> +++ b/arch/powerpc/kernel/Makefile
> @@ -57,8 +57,12 @@ obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
>  obj-$(CONFIG_E500)		+= idle_e500.o
>  obj-$(CONFIG_6xx)		+= idle_6xx.o l2cr_6xx.o cpu_setup_6xx.o
>  obj-$(CONFIG_TAU)		+= tau_6xx.o
> -obj-$(CONFIG_HIBERNATION)	+= swsusp.o suspend.o \
> -				   swsusp_$(CONFIG_WORD_SIZE).o
> +obj-$(CONFIG_HIBERNATION)	+= swsusp.o suspend.o
> +ifeq ($(CONFIG_FSL_BOOKE),y)
> +obj-$(CONFIG_HIBERNATION)	+= swsusp_booke.o
> +else
> +obj-$(CONFIG_HIBERNATION)	+= swsusp_$(CONFIG_WORD_SIZE).o
> +endif
>  obj64-$(CONFIG_HIBERNATION)	+= swsusp_asm64.o
>  obj-$(CONFIG_MODULES)		+= module.o module_$(CONFIG_WORD_SIZE).o
>  obj-$(CONFIG_44x)		+= cpu_setup_44x.o
> diff --git a/arch/powerpc/kernel/swsusp_booke.S b/arch/powerpc/kernel/swsusp_booke.S
> new file mode 100644
> index 0000000..dbffad2
> --- /dev/null
> +++ b/arch/powerpc/kernel/swsusp_booke.S
> @@ -0,0 +1,200 @@
> +/*
> + * Based on swsusp_32.S, modified for FSL BookE by
> + * Anton Vorontsov <avorontsov at ru.mvista.com>
> + * Copyright (c) 2009-2010 MontaVista Software, LLC.
> + */
> +
> +#include <linux/threads.h>
> +#include <asm/processor.h>
> +#include <asm/page.h>
> +#include <asm/cputable.h>
> +#include <asm/thread_info.h>
> +#include <asm/ppc_asm.h>
> +#include <asm/asm-offsets.h>
> +#include <asm/mmu.h>
> +
> +/*
> + * Structure for storing CPU registers on the save area.
> + */
> +#define SL_SP		0
> +#define SL_PC		4
> +#define SL_MSR		8
> +#define SL_TCR		0xc
> +#define SL_SPRG0	0x10
> +#define SL_SPRG1	0x14
> +#define SL_SPRG2	0x18
> +#define SL_SPRG3	0x1c
> +#define SL_SPRG4	0x20
> +#define SL_SPRG5	0x24
> +#define SL_SPRG6	0x28
> +#define SL_SPRG7	0x2c
> +#define SL_TBU		0x30
> +#define SL_TBL		0x34
> +#define SL_R2		0x38
> +#define SL_CR		0x3c
> +#define SL_LR		0x40
> +#define SL_R12		0x44	/* r12 to r31 */
> +#define SL_SIZE		(SL_R12 + 80)
> +
> +	.section .data
> +	.align	5
> +
> +_GLOBAL(swsusp_save_area)
> +	.space	SL_SIZE
> +
> +
> +	.section .text
> +	.align	5
> +
> +_GLOBAL(swsusp_arch_suspend)
> +	lis	r11,swsusp_save_area at h
> +	ori	r11,r11,swsusp_save_area at l
> +
> +	mflr	r0
> +	stw	r0,SL_LR(r11)
> +	mfcr	r0
> +	stw	r0,SL_CR(r11)
> +	stw	r1,SL_SP(r11)
> +	stw	r2,SL_R2(r11)
> +	stmw	r12,SL_R12(r11)
> +
> +	/* Save MSR & TCR */
> +	mfmsr	r4
> +	stw	r4,SL_MSR(r11)
> +	mfspr	r4,SPRN_TCR
> +	stw	r4,SL_TCR(r11)
> +
> +	/* Get a stable timebase and save it */
> +1:	mftbu	r4
> +	stw	r4,SL_TBU(r11)
> +	mftb	r5
> +	stw	r5,SL_TBL(r11)
> +	mftbu	r3
> +	cmpw	r3,r4
> +	bne	1b
> +
> +	/* Save SPRGs */
> +	mfsprg	r4,0
> +	stw	r4,SL_SPRG0(r11)
> +	mfsprg	r4,1
> +	stw	r4,SL_SPRG1(r11)
> +	mfsprg	r4,2
> +	stw	r4,SL_SPRG2(r11)
> +	mfsprg	r4,3
> +	stw	r4,SL_SPRG3(r11)
> +	mfsprg	r4,4
> +	stw	r4,SL_SPRG4(r11)
> +	mfsprg	r4,5
> +	stw	r4,SL_SPRG5(r11)
> +	mfsprg	r4,6
> +	stw	r4,SL_SPRG6(r11)
> +	mfsprg	r4,7
> +	stw	r4,SL_SPRG7(r11)
> +
> +	/* Call the low level suspend stuff (we should probably have made
> +	 * a stackframe...
> +	 */
> +	bl	swsusp_save
> +
> +	/* Restore LR from the save area */
> +	lis	r11,swsusp_save_area at h
> +	ori	r11,r11,swsusp_save_area at l
> +	lwz	r0,SL_LR(r11)
> +	mtlr	r0
> +
> +	blr
> +
> +_GLOBAL(swsusp_arch_resume)
> + 	sync
> +
> +	/* Load ptr the list of pages to copy in r3 */
> +	lis	r11,(restore_pblist)@h
> +	ori	r11,r11,restore_pblist at l
> +	lwz	r3,0(r11)
> +
> +	/* Copy the pages. This is a very basic implementation, to
> +	 * be replaced by something more cache efficient */
> +1:
> +	li	r0,256
> +	mtctr	r0
> +	lwz	r5,pbe_address(r3)	/* source */
> +	lwz	r6,pbe_orig_address(r3)	/* destination */
> +2:
> +	lwz	r8,0(r5)
> +	lwz	r9,4(r5)
> +	lwz	r10,8(r5)
> +	lwz	r11,12(r5)
> +	addi	r5,r5,16
> +	stw	r8,0(r6)
> +	stw	r9,4(r6)
> +	stw	r10,8(r6)
> +	stw	r11,12(r6)
> +	addi	r6,r6,16
> +	bdnz	2b
> +	lwz	r3,pbe_next(r3)
> +	cmpwi	0,r3,0
> +	bne	1b
> +
> +	bl flush_dcache_L1
> +	bl flush_instruction_cache
> +
> +	lis	r11,swsusp_save_area at h
> +	ori	r11,r11,swsusp_save_area at l
> +
> +	lwz	r4,SL_SPRG0(r11)
> +	mtsprg	0,r4
> +	lwz	r4,SL_SPRG1(r11)
> +	mtsprg	1,r4
> +	lwz	r4,SL_SPRG2(r11)
> +	mtsprg	2,r4
> +	lwz	r4,SL_SPRG3(r11)
> +	mtsprg	3,r4
> +	lwz	r4,SL_SPRG4(r11)
> +	mtsprg	4,r4
> +	lwz	r4,SL_SPRG5(r11)
> +	mtsprg	5,r4
> +	lwz	r4,SL_SPRG6(r11)
> +	mtsprg	6,r4
> +	lwz	r4,SL_SPRG7(r11)
> +	mtsprg	7,r4
> +
> +	/* Invalidate TLB0 & TLB1 */
> +	li	r6,0x04
> +	tlbivax 0,r6
> +	TLBSYNC
> +	li	r6,0x0c
> +	tlbivax 0,r6
> +	TLBSYNC
> +
> +	/* restore the MSR */
> +	lwz	r3,SL_MSR(r11)
> +
> +	/* Restore TB */
> +	li	r3,0
> +	mttbl	r3
> +	lwz	r3,SL_TBU(r11)
> +	lwz	r4,SL_TBL(r11)
> +	mttbu	r3
> +	mttbl	r4
> +
> +	/* Restore TCR and clear any pending bits in TSR. */
> +	lwz	r4,SL_TCR(r11)
> +	mtspr	SPRN_TCR,r4
> +	lis	r4, (TSR_ENW | TSR_WIS | TSR_DIS | TSR_FIS)@h
> +	mtspr	SPRN_TSR,r4
> +
> +	/* Kick decrementer */
> +	li	r0,1
> +	mtdec	r0
> +
> +	/* Restore the callee-saved registers and return */
> +	lwz	r0,SL_CR(r11)
> +	mtcr	r0
> +	lwz	r2,SL_R2(r11)
> +	lmw	r12,SL_R12(r11)
> +	lwz	r1,SL_SP(r11)
> +	lwz	r0,SL_LR(r11)
> +	mtlr	r0
> +
> +	li	r3,0
> +	blr
> -- 
> 1.7.0

-- 
Anton Vorontsov
email: cbouatmailru at gmail.com
irc://irc.freenode.net/bd2