forge/linux-pinenote
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

x86: reduce stack usage in init_intel_cacheinfo

Browse source 
Impact: reduce stack usage.

init_intel_cacheinfo() does not use the cpumask so define a subset
of struct _cpuid4_info (_cpuid4_info_regs) that can be used instead.

Signed-off-by: Mike Travis <travis@sgi.com>
This commit is contained in:
Mike Travis 2009-01-10 21:58:10 -08:00 • committed by Ingo Molnar
commit f9b90566cd
1 changed files with 44 additions and 19 deletions
Download patch file Download diff file Expand all files Collapse all files

63
arch/x86/kernel/cpu/intel_cacheinfo.c
View file

@ -132,7 +132,16 @@ struct _cpuid4_info {
union _cpuid4_leaf_ecx ecx;
unsigned long size;
unsigned long can_disable;
cpumask_t shared_cpu_map; /* future?: only cpus/node is needed */
DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
};
/* subset of above _cpuid4_info w/o shared_cpu_map */
struct _cpuid4_info_regs {
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
unsigned long can_disable;
};
#ifdef CONFIG_PCI
@ -263,7 +272,7 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
}
static void __cpuinit
amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
if (index < 3)
return;
@ -271,7 +280,8 @@ amd_check_l3_disable(int index, struct _cpuid4_info *this_leaf)
}
static int
__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
__cpuinit cpuid4_cache_lookup_regs(int index,
struct _cpuid4_info_regs *this_leaf)
{
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
@ -299,6 +309,15 @@ __cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
return 0;
}
static int
__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
{
struct _cpuid4_info_regs *leaf_regs =
(struct _cpuid4_info_regs *)this_leaf;
return cpuid4_cache_lookup_regs(index, leaf_regs);
}
static int __cpuinit find_num_cache_leaves(void)
{
unsigned int eax, ebx, ecx, edx;
@ -338,11 +357,10 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
* parameters cpuid leaf to find the cache details
*/
for (i = 0; i < num_cache_leaves; i++) {
struct _cpuid4_info this_leaf;
struct _cpuid4_info_regs this_leaf;
int retval;
retval = cpuid4_cache_lookup(i, &this_leaf);
retval = cpuid4_cache_lookup_regs(i, &this_leaf);
if (retval >= 0) {
switch(this_leaf.eax.split.level) {
case 1:
@ -491,17 +509,20 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
cpu_set(cpu, this_leaf->shared_cpu_map);
cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
else {
index_msb = get_count_order(num_threads_sharing);
for_each_online_cpu(i) {
if (cpu_data(i).apicid >> index_msb ==
c->apicid >> index_msb) {
cpu_set(i, this_leaf->shared_cpu_map);
cpumask_set_cpu(i,
to_cpumask(this_leaf->shared_cpu_map));
if (i != cpu && per_cpu(cpuid4_info, i)) {
sibling_leaf = CPUID4_INFO_IDX(i, index);
cpu_set(cpu, sibling_leaf->shared_cpu_map);
sibling_leaf =
CPUID4_INFO_IDX(i, index);
cpumask_set_cpu(cpu, to_cpumask(
sibling_leaf->shared_cpu_map));
}
}
}
@ -513,9 +534,10 @@ static void __cpuinit cache_remove_shared_cpu_map(unsigned int cpu, int index)
int sibling;
this_leaf = CPUID4_INFO_IDX(cpu, index);
for_each_cpu_mask_nr(sibling, this_leaf->shared_cpu_map) {
for_each_cpu(sibling, to_cpumask(this_leaf->shared_cpu_map)) {
sibling_leaf = CPUID4_INFO_IDX(sibling, index);
cpu_clear(cpu, sibling_leaf->shared_cpu_map);
cpumask_clear_cpu(cpu,
to_cpumask(sibling_leaf->shared_cpu_map));
}
}
#else
@ -620,8 +642,9 @@ static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
int n = 0;
if (len > 1) {
cpumask_t *mask = &this_leaf->shared_cpu_map;
const struct cpumask *mask;
mask = to_cpumask(this_leaf->shared_cpu_map);
n = type?
cpulist_scnprintf(buf, len-2, mask) :
cpumask_scnprintf(buf, len-2, mask);
@ -684,7 +707,8 @@ static struct pci_dev *get_k8_northbridge(int node)
static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf)
{
int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
int node = cpu_to_node(cpumask_first(mask));
struct pci_dev *dev = NULL;
ssize_t ret = 0;
int i;
@ -718,7 +742,8 @@ static ssize_t
store_cache_disable(struct _cpuid4_info *this_leaf, const char *buf,
size_t count)
{
int node = cpu_to_node(first_cpu(this_leaf->shared_cpu_map));
const struct cpumask *mask = to_cpumask(this_leaf->shared_cpu_map);
int node = cpu_to_node(cpumask_first(mask));
struct pci_dev *dev = NULL;
unsigned int ret, index, val;
@ -863,7 +888,7 @@ err_out:
return -ENOMEM;
}
static cpumask_t cache_dev_map = CPU_MASK_NONE;
static DECLARE_BITMAP(cache_dev_map, NR_CPUS);
/* Add/Remove cache interface for CPU device */
static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
@ -903,7 +928,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
}
kobject_uevent(&(this_object->kobj), KOBJ_ADD);
}
cpu_set(cpu, cache_dev_map);
cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
return 0;
@ -916,9 +941,9 @@ static void __cpuinit cache_remove_dev(struct sys_device * sys_dev)
if (per_cpu(cpuid4_info, cpu) == NULL)
return;
if (!cpu_isset(cpu, cache_dev_map))
if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
return;
cpu_clear(cpu, cache_dev_map);
cpumask_clear_cpu(cpu, to_cpumask(cache_dev_map));
for (i = 0; i < num_cache_leaves; i++)
kobject_put(&(INDEX_KOBJECT_PTR(cpu,i)->kobj));