Ingo Molnar wrote:
quoted text
> * Peter Zijlstra <peterz@infradead.org> wrote:
> 
>>>> NAK
...
quoted text
> 
> seconded. Mike, since none of this is v2.6.27 material, lets do it right 
> with a v2.6.28 target. You know all the cpumask_t using code sites 
> inside out already, so the know-how is all available already :-) Please 
> make it finegrained series of patches so that we can resolve conflicts 
> with other trees more easily.
> 
> perhaps propose the new cpumask_t API early (in this thread?), so that 
> people can comment on it before NAKs come flying against a full patchset 
> ;-)
> 
> 	Ingo


Here's an initial proposal for abstracting cpumask_t to be either
an array of 1 or a pointer to an array...   Hopefully this will
minimize the amount of code changes while providing the capabilities
this change is attempting to do.

Comments most welcome. ;-)

Thanks,
Mike
--

Basically, linux/cpumask.h has the following defines:

	typedef struct { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_data;

	#if NR_CPUS > BITS_PER_LONG
	typedef const cpumask_data	*cpumask_t;
	typedef cpumask_data		*cpumask_var;
	typedef cpumask_t		cpumask_val;
	#define	_NR_CPUS		nr_cpu_ids
	#else
	typedef const cpumask_data	cpumask_t[1];
	typedef cpumask_data		cpumask_var[1];
	typedef cpumask_data		cpumask_val;
	#define	_NR_CPUS		NR_CPUS
	#endif

So in function prototypes:

	cpumask_t function(const cpumask_t *A,
			   cpumask_t *B,
			   cpumask_t cpumask_C)

becomes:

	cpumask_val function(cpumask_t A,
			     cpumask_var B,
			     cpumask_t cpumask_C)

And in local variables:

	cpumask_t ==> cpumask_var  IFF variable is to be written.

This:

	cpumask_t mask = cpu_online_map 
	<change mask>

becomes:

	#include <linux/cpumask_alloc.h>

	cpumask_var mask;

	alloc_cpumask(&mask);
	*mask = *cpu_online_map;
	<change mask>
	free_cpumask(&mask);

Currently, alloc_cpumask is:

	#define BYTES_PER_CPUMASK (BITS_TO_LONGS(nr_cpu_ids)/sizeof(long))

	static inline bool no_cpumask(cpumask_t *m)
	{
		return (*m == NULL);
	}

	static inline void alloc_cpumask(cpumask_t *m)
	{
		cpumask_t d = kmalloc(BYTES_PER_CPUMASK, GFP_KERNEL);
		if (no_cpumask(&d))
			BUG();
		*m = d;
	}

	static inline void alloc_cpumask_nopanic(cpumask_t *m)
	{
		cpumask_t d = kmalloc(BYTES_PER_CPUMASK, GFP_KERNEL);

		*m = d;
	}

	static inline void free_cpumask(cpumask_t *m)
	{
		kfree(*m);
	}

Other means of obtaining a temporary cpumask_t variable will be provided
for those cases where kmalloc() is not available.

Furthermore, system-wide maps become:

	extern cpumask_data _cpu_possible_map;			 /* read/write */
	extern cpumask_data _cpu_online_map;
	extern cpumask_data _cpu_present_map;
	extern cpumask_data _cpu_active_map;
	#define	cpu_possible_map ((cpumask_t)&_cpu_possible_map) /* read only */
	#define	cpu_online_map ((cpumask_t)&_cpu_online_map)
	#define	cpu_present_map ((cpumask_t)&_cpu_present_map)
	#define	cpu_active_map ((cpumask_t)&_cpu_active_map)


So code to set these bits would be:

	cpu_set(cpu, &_cpu_online_map);
	cpu_set(cpu, &_cpu_present_map);
	cpu_set(cpu, &_cpu_possible_map);

Arrays that contain a fixed cpumask would have:

	struct xxx {
		cpumask_data	cpumask;
	};

... though we should probably encourage the map to be allocated:

	struct xxx {
		cpumask_t	readonly_cpumask;
		cpumask_var	readwrite_cpumask;
	};

	alloc_cpumask(&xxx->readonly_cpumask);
	alloc_cpumask(&xxx->readwrite_cpumask);


All the cpu operators become:

	#define cpu_XXX(dst, src) _cpu_XXX(dst, src, _NR_CPUS)
	static inline void __cpu_XXX(cpumask_var dstp, cpumask_t srcp, int count)
	{
		XXX_bit(dstp->bits, srcp->bits, count);
	}

(_NR_CPUS being defined to be nr_cpu_ids allows us to allocate variable lengthed arrays.)


Cpumask initializers become:


	#if NR_CPUS <= BITS_PER_LONG

	#define INIT_CPU_MASK_ALL					\
	(cpumask_t) { {							\
		[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD		\
	} }

	#else
	#define INIT_CPU_MASK_ALL					\
	(cpumask_data) { {						\
		[0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL,		\
		[BITS_TO_LONGS(NR_CPUS)-1] = CPU_MASK_LAST_WORD		\
	} }
	#endif

	#define INIT_CPU_MASK_NONE					\
	(cpumask_data) { {						\
		[0 ... BITS_TO_LONGS(NR_CPUS)-1] =  0UL			\
	} }

	#define INIT_CPU_MASK_CPU0					\
	(cpumask_data) { {						\
		[0] =  1UL						\
	} }

	#if NR_CPUS > BITS_PER_LONG
	extern cpumask_t cpu_mask_all, cpu_mask_none, cpu_mask_cpu0;
	#define CPU_MASK_ALL		(cpu_mask_all)
	#define CPU_MASK_NONE		(cpu_mask_none)
	#define CPU_MASK_CPU0		(cpu_mask_cpu0)
	#else
	#define CPU_MASK_ALL		((cpumask_t)&INIT_CPU_MASK_ALL)
	#define CPU_MASK_NONE		((cpumask_t)&INIT_CPU_MASK_NONE)
	#define CPU_MASK_CPU0		((cpumask_t)&INIT_CPU_MASK_CPU0)
	#endif

And in kernel/cpu.c:

	/*
	 * provide const cpumask_t's
	 */
	#if NR_CPUS > BITS_PER_LONG
	cpumask_data cpu_mask_all __read_mostly = INIT_CPU_MASK_ALL;
	EXPORT_SYMBOL(cpu_mask_all);

	cpumask_data cpu_mask_none __read_mostly = INIT_CPU_MASK_NONE;
	EXPORT_SYMBOL(cpu_mask_none);

	cpumask_data cpu_mask_cpu0 __read_mostly = INIT_CPU_MASK_CPU0;
	EXPORT_SYMBOL(cpu_mask_cpu0);
	#endif

--
unsubscribe notice
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/