[RFC] asm code for Hypervisor Call Instrumentation

[Mike Kravetz]

On Mon, Aug 07, 2006 at 04:26:24PM +1000, Paul Mackerras wrote:
> Hmmm, doing the update in assembly would avoid the need to create a
> stack frame, which would be nice...  Maybe we need to add some macros
> to include/asm-powerpc/percpu.h to make it easier to access per-cpu
> variables from assembly code.
> 
> Alternatively, we could put a pointer to the hcall_stats array for
> each cpu in its paca.  That's very easily accessed from assembly code.

I finally got around to doing the update in assembly.  I have attached
the code in question below.  Macros were added (elsewhere) for things like 
stat structure and offsets within the structure.  No macros for per-cpu
data.  Rather, I just used some existing definitions and based code on
descriptions in asm-powerpc/percpu.h.  Let me know if this introduces too
many (unchecked at compile time assumptions) into the code.

The many comments are mostly for my benefit. :)

Thanks,
-- 
Mike

#define STK_PARM(i)     (48 + ((i)-3)*8)

#ifdef CONFIG_HCALL_STATS
/*
 * precall must preserve all registers.  use unused STK_PARM()
 * areas to save snapshots and opcode.
 */
#define HCALL_INST_PRECALL					\
	std	r3,STK_PARM(r3)(r1);	/* save opcode */	\
	mftb	r3;			/* get timebase and */	\
	std     r3,STK_PARM(r5)(r1);	/* save for later */	\
BEGIN_FTR_SECTION;						\
	mfspr	r3,SPRN_PURR;		/* get PURR and */	\
END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
	std	r3,STK_PARM(r6)(r1);	/* save for later */	\
	ld	r3,STK_PARM(r3)(r1);	/* opcode back in r3 */
	
/*
 * postcall is performed immediately before function return which
 * allows liberal use of non-volital registers.
 */
#define HCALL_INST_POSTCALL					\
	/* get time and PURR snapshots after hcall */		\
	mftb	r7;			/* timebase after */	\
BEGIN_FTR_SECTION;						\
	mfspr	r8,SPRN_PURR;		/* PURR after */	\
END_FTR_SECTION_IFSET(CPU_FTR_PURR);				\
								\
	/* calculate time and PURR deltas for call */		\
	ld	r5,STK_PARM(r5)(r1);	/* timebase before */	\
	subf	r5,r5,r7;					\
	ld	r6,STK_PARM(r6)(r1);	/* PURR before */	\
	subf	r6,r6,r8;					\
								\
	/* calculate address of stat structure */		\
	ld	r4,STK_PARM(r3)(r1);	/* use opcode as */	\
	rldicl	r4,r4,62,2;		/* index into array */	\
	mulli	r4,r4,HCALL_STAT_SIZE;				\
	LOAD_REG_ADDR(r7, per_cpu__hcall_stats);		\
	add	r4,r4,r7;					\
	ld	r7,PACA_DATA_OFFSET(r13); /* per cpu offset */	\
	add	r4,r4,r7;					\
								\
	/* update stats	*/					\
	ld	r7,HCALL_STAT_CALLS(r4); /* count */		\
	addi	r7,r7,1;					\
	std	r7,HCALL_STAT_CALLS(r4);			\
	ld      r7,HCALL_STAT_TB(r4);	/* timebase */		\
	add	r7,r7,r5;					\
	std	r7,HCALL_STAT_TB(r4);				\
	ld	r7,HCALL_STAT_PURR(r4);	/* PURR */		\
	add	r7,r7,r6;					\
	std	r7,HCALL_STAT_PURR(r4);
#else

#define HCALL_INST_PRECALL
#define HCALL_INST_POSTCALL
#endif