linux_old1/lib/cpumask.c

230 lines
5.8 KiB
C
Raw Normal View History

include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/cpumask.h>
#include <linux/export.h>
#include <linux/bootmem.h>
int __first_cpu(const cpumask_t *srcp)
{
return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS));
}
EXPORT_SYMBOL(__first_cpu);
int __next_cpu(int n, const cpumask_t *srcp)
{
return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1));
}
EXPORT_SYMBOL(__next_cpu);
x86: Add performance variants of cpumask operators * Increase performance for systems with large count NR_CPUS by limiting the range of the cpumask operators that loop over the bits in a cpumask_t variable. This removes a large amount of wasted cpu cycles. * Add performance variants of the cpumask operators: int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS int first_cpu_nr(mask) Number lowest set bit, or nr_cpu_ids int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids * Modify following to use performance variants: #define num_online_cpus() cpus_weight_nr(cpu_online_map) #define num_possible_cpus() cpus_weight_nr(cpu_possible_map) #define num_present_cpus() cpus_weight_nr(cpu_present_map) #define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) * Comment added to include/linux/cpumask.h: Note: The alternate operations with the suffix "_nr" are used to limit the range of the loop to nr_cpu_ids instead of NR_CPUS when NR_CPUS > 64 for performance reasons. If NR_CPUS is <= 64 then most assembler bitmask operators execute faster with a constant range, so the operator will continue to use NR_CPUS. Another consideration is that nr_cpu_ids is initialized to NR_CPUS and isn't lowered until the possible cpus are discovered (including any disabled cpus). So early uses will span the entire range of NR_CPUS. (The net effect is that for systems with 64 or less CPU's there are no functional changes.) For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Cc: Paul Jackson <pj@sgi.com> Cc: Christoph Lameter <clameter@sgi.com> Reviewed-by: Paul Jackson <pj@sgi.com> Reviewed-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-13 03:21:13 +08:00
#if NR_CPUS > 64
int __next_cpu_nr(int n, const cpumask_t *srcp)
{
return min_t(int, nr_cpu_ids,
find_next_bit(srcp->bits, nr_cpu_ids, n+1));
}
EXPORT_SYMBOL(__next_cpu_nr);
#endif
/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @src1p: the first cpumask pointer
* @src2p: the second cpumask pointer
*
* Returns >= nr_cpu_ids if no further cpus set in both.
*/
int cpumask_next_and(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
if (cpumask_test_cpu(n, src2p))
break;
return n;
}
EXPORT_SYMBOL(cpumask_next_and);
/**
* cpumask_any_but - return a "random" in a cpumask, but not this one.
* @mask: the cpumask to search
* @cpu: the cpu to ignore.
*
* Often used to find any cpu but smp_processor_id() in a mask.
* Returns >= nr_cpu_ids if no cpus set.
*/
int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
{
unsigned int i;
cpumask_check(cpu);
for_each_cpu(i, mask)
if (i != cpu)
break;
return i;
}
/* These are not inline because of header tangles. */
#ifdef CONFIG_CPUMASK_OFFSTACK
/**
* alloc_cpumask_var_node - allocate a struct cpumask on a given node
* @mask: pointer to cpumask_var_t where the cpumask is returned
* @flags: GFP_ flags
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop returning a constant 1 (in <linux/cpumask.h>)
* Returns TRUE if memory allocation succeeded, FALSE otherwise.
*
* In addition, mask will be NULL if this fails. Note that gcc is
* usually smart enough to know that mask can never be NULL if
* CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case
* too.
*/
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
{
*mask = kmalloc_node(cpumask_size(), flags, node);
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
if (!*mask) {
printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
dump_stack();
}
#endif
/* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
if (*mask) {
unsigned char *ptr = (unsigned char *)cpumask_bits(*mask);
unsigned int tail;
tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
memset(ptr + cpumask_size() - tail, 0, tail);
}
return *mask != NULL;
}
EXPORT_SYMBOL(alloc_cpumask_var_node);
bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
{
return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
}
EXPORT_SYMBOL(zalloc_cpumask_var_node);
/**
* alloc_cpumask_var - allocate a struct cpumask
* @mask: pointer to cpumask_var_t where the cpumask is returned
* @flags: GFP_ flags
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop returning a constant 1 (in <linux/cpumask.h>).
*
* See alloc_cpumask_var_node.
*/
bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
}
EXPORT_SYMBOL(alloc_cpumask_var);
bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return alloc_cpumask_var(mask, flags | __GFP_ZERO);
}
EXPORT_SYMBOL(zalloc_cpumask_var);
/**
* alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
* @mask: pointer to cpumask_var_t where the cpumask is returned
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop (in <linux/cpumask.h>).
* Either returns an allocated (zero-filled) cpumask, or causes the
* system to panic.
*/
void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
{
*mask = memblock_virt_alloc(cpumask_size(), 0);
}
/**
* free_cpumask_var - frees memory allocated for a struct cpumask.
* @mask: cpumask to free
*
* This is safe on a NULL mask.
*/
void free_cpumask_var(cpumask_var_t mask)
{
kfree(mask);
}
EXPORT_SYMBOL(free_cpumask_var);
/**
* free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var
* @mask: cpumask to free
*/
void __init free_bootmem_cpumask_var(cpumask_var_t mask)
{
memblock_free_early(__pa(mask), cpumask_size());
}
#endif
/**
* cpumask_set_cpu_local_first - set i'th cpu with local numa cpu's first
*
* @i: index number
* @numa_node: local numa_node
* @dstp: cpumask with the relevant cpu bit set according to the policy
*
* This function sets the cpumask according to a numa aware policy.
* cpumask could be used as an affinity hint for the IRQ related to a
* queue. When the policy is to spread queues across cores - local cores
* first.
*
* Returns 0 on success, -ENOMEM for no memory, and -EAGAIN when failed to set
* the cpu bit and need to re-call the function.
*/
int cpumask_set_cpu_local_first(int i, int numa_node, cpumask_t *dstp)
{
cpumask_var_t mask;
int cpu;
int ret = 0;
if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
return -ENOMEM;
i %= num_online_cpus();
if (numa_node == -1 || !cpumask_of_node(numa_node)) {
/* Use all online cpu's for non numa aware system */
cpumask_copy(mask, cpu_online_mask);
} else {
int n;
cpumask_and(mask,
cpumask_of_node(numa_node), cpu_online_mask);
n = cpumask_weight(mask);
if (i >= n) {
i -= n;
/* If index > number of local cpu's, mask out local
* cpu's
*/
cpumask_andnot(mask, cpu_online_mask, mask);
}
}
for_each_cpu(cpu, mask) {
if (--i < 0)
goto out;
}
ret = -EAGAIN;
out:
free_cpumask_var(mask);
if (!ret)
cpumask_set_cpu(cpu, dstp);
return ret;
}
EXPORT_SYMBOL(cpumask_set_cpu_local_first);