Merge git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild
* git://git.kernel.org/pub/scm/linux/kernel/git/sam/kbuild:
kconfig: add named choice group
kconfig: fix choice dependency check
kconifg: 'select' considered less evil
dontdiff: ignore timeconst.h
dontdiff: add modules.order
kbuild: fix unportability in gen_initramfs_list.sh
kbuild: fix help output to show correct arch
kbuild: show defconfig subdirs in make help
kconfig: reversed borderlines in inputbox
diff --git a/Documentation/vm/slabinfo.c b/Documentation/vm/slabinfo.c
index 22d7e3e..d3ce295 100644
--- a/Documentation/vm/slabinfo.c
+++ b/Documentation/vm/slabinfo.c
@@ -31,7 +31,7 @@
int hwcache_align, object_size, objs_per_slab;
int sanity_checks, slab_size, store_user, trace;
int order, poison, reclaim_account, red_zone;
- unsigned long partial, objects, slabs;
+ unsigned long partial, objects, slabs, objects_partial, objects_total;
unsigned long alloc_fastpath, alloc_slowpath;
unsigned long free_fastpath, free_slowpath;
unsigned long free_frozen, free_add_partial, free_remove_partial;
@@ -540,7 +540,8 @@
return;
store_size(size_str, slab_size(s));
- snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs, s->partial, s->cpu_slabs);
+ snprintf(dist_str, 40, "%lu/%lu/%d", s->slabs - s->cpu_slabs,
+ s->partial, s->cpu_slabs);
if (!line++)
first_line();
@@ -776,7 +777,6 @@
unsigned long used;
unsigned long long wasted;
unsigned long long objwaste;
- long long objects_in_partial_slabs;
unsigned long percentage_partial_slabs;
unsigned long percentage_partial_objs;
@@ -790,18 +790,11 @@
wasted = size - used;
objwaste = s->slab_size - s->object_size;
- objects_in_partial_slabs = s->objects -
- (s->slabs - s->partial - s ->cpu_slabs) *
- s->objs_per_slab;
-
- if (objects_in_partial_slabs < 0)
- objects_in_partial_slabs = 0;
-
percentage_partial_slabs = s->partial * 100 / s->slabs;
if (percentage_partial_slabs > 100)
percentage_partial_slabs = 100;
- percentage_partial_objs = objects_in_partial_slabs * 100
+ percentage_partial_objs = s->objects_partial * 100
/ s->objects;
if (percentage_partial_objs > 100)
@@ -823,8 +816,8 @@
min_objects = s->objects;
if (used < min_used)
min_used = used;
- if (objects_in_partial_slabs < min_partobj)
- min_partobj = objects_in_partial_slabs;
+ if (s->objects_partial < min_partobj)
+ min_partobj = s->objects_partial;
if (percentage_partial_slabs < min_ppart)
min_ppart = percentage_partial_slabs;
if (percentage_partial_objs < min_ppartobj)
@@ -848,8 +841,8 @@
max_objects = s->objects;
if (used > max_used)
max_used = used;
- if (objects_in_partial_slabs > max_partobj)
- max_partobj = objects_in_partial_slabs;
+ if (s->objects_partial > max_partobj)
+ max_partobj = s->objects_partial;
if (percentage_partial_slabs > max_ppart)
max_ppart = percentage_partial_slabs;
if (percentage_partial_objs > max_ppartobj)
@@ -864,7 +857,7 @@
total_objects += s->objects;
total_used += used;
- total_partobj += objects_in_partial_slabs;
+ total_partobj += s->objects_partial;
total_ppart += percentage_partial_slabs;
total_ppartobj += percentage_partial_objs;
@@ -1160,6 +1153,8 @@
slab->hwcache_align = get_obj("hwcache_align");
slab->object_size = get_obj("object_size");
slab->objects = get_obj("objects");
+ slab->objects_partial = get_obj("objects_partial");
+ slab->objects_total = get_obj("objects_total");
slab->objs_per_slab = get_obj("objs_per_slab");
slab->order = get_obj("order");
slab->partial = get_obj("partial");
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index e2d870d..8db8f73 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -339,6 +339,7 @@
{
struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
unsigned int freq;
+ unsigned int cached_freq;
dprintk("get_cur_freq_on_cpu (%d)\n", cpu);
@@ -347,7 +348,16 @@
return 0;
}
+ cached_freq = data->freq_table[data->acpi_data->state].frequency;
freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
+ if (freq != cached_freq) {
+ /*
+ * The dreaded BIOS frequency change behind our back.
+ * Force set the frequency on next target call.
+ */
+ data->resume = 1;
+ }
+
dprintk("cur freq = %u\n", freq);
return freq;
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index b7ab3c3..fad3674 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -209,12 +209,6 @@
EXIT_DATA
}
-/* vdso blob that is mapped into user space */
- vdso_start = . ;
- .vdso : AT(ADDR(.vdso) - LOAD_OFFSET) { *(.vdso) }
- . = ALIGN(PAGE_SIZE);
- vdso_end = .;
-
#ifdef CONFIG_BLK_DEV_INITRD
. = ALIGN(PAGE_SIZE);
__initramfs_start = .;
diff --git a/arch/x86/vdso/vdso.S b/arch/x86/vdso/vdso.S
index 4b1620a..1d3aa6b 100644
--- a/arch/x86/vdso/vdso.S
+++ b/arch/x86/vdso/vdso.S
@@ -1,2 +1,10 @@
- .section ".vdso","a"
+#include <linux/init.h>
+
+__INITDATA
+
+ .globl vdso_start, vdso_end
+vdso_start:
.incbin "arch/x86/vdso/vdso.so"
+vdso_end:
+
+__FINIT
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 9cb43f5..649ae99 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -97,7 +97,7 @@
#define CPUFREQ_THERMAL_MIN_STEP 0
#define CPUFREQ_THERMAL_MAX_STEP 3
-static unsigned int cpufreq_thermal_reduction_pctg[NR_CPUS];
+static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
static unsigned int acpi_thermal_cpufreq_is_init = 0;
static int cpu_has_cpufreq(unsigned int cpu)
@@ -113,9 +113,9 @@
if (!cpu_has_cpufreq(cpu))
return -ENODEV;
- if (cpufreq_thermal_reduction_pctg[cpu] <
+ if (per_cpu(cpufreq_thermal_reduction_pctg, cpu) <
CPUFREQ_THERMAL_MAX_STEP) {
- cpufreq_thermal_reduction_pctg[cpu]++;
+ per_cpu(cpufreq_thermal_reduction_pctg, cpu)++;
cpufreq_update_policy(cpu);
return 0;
}
@@ -128,14 +128,14 @@
if (!cpu_has_cpufreq(cpu))
return -ENODEV;
- if (cpufreq_thermal_reduction_pctg[cpu] >
+ if (per_cpu(cpufreq_thermal_reduction_pctg, cpu) >
(CPUFREQ_THERMAL_MIN_STEP + 1))
- cpufreq_thermal_reduction_pctg[cpu]--;
+ per_cpu(cpufreq_thermal_reduction_pctg, cpu)--;
else
- cpufreq_thermal_reduction_pctg[cpu] = 0;
+ per_cpu(cpufreq_thermal_reduction_pctg, cpu) = 0;
cpufreq_update_policy(cpu);
/* We reached max freq again and can leave passive mode */
- return !cpufreq_thermal_reduction_pctg[cpu];
+ return !per_cpu(cpufreq_thermal_reduction_pctg, cpu);
}
static int acpi_thermal_cpufreq_notifier(struct notifier_block *nb,
@@ -147,9 +147,10 @@
if (event != CPUFREQ_ADJUST)
goto out;
- max_freq =
- (policy->cpuinfo.max_freq *
- (100 - cpufreq_thermal_reduction_pctg[policy->cpu] * 20)) / 100;
+ max_freq = (
+ policy->cpuinfo.max_freq *
+ (100 - per_cpu(cpufreq_thermal_reduction_pctg, policy->cpu) * 20)
+ ) / 100;
cpufreq_verify_within_limits(policy, 0, max_freq);
@@ -174,7 +175,7 @@
if (!cpu_has_cpufreq(cpu))
return 0;
- return cpufreq_thermal_reduction_pctg[cpu];
+ return per_cpu(cpufreq_thermal_reduction_pctg, cpu);
}
static int cpufreq_set_cur_state(unsigned int cpu, int state)
@@ -182,7 +183,7 @@
if (!cpu_has_cpufreq(cpu))
return 0;
- cpufreq_thermal_reduction_pctg[cpu] = state;
+ per_cpu(cpufreq_thermal_reduction_pctg, cpu) = state;
cpufreq_update_policy(cpu);
return 0;
}
@@ -191,8 +192,9 @@
{
int i;
- for (i = 0; i < NR_CPUS; i++)
- cpufreq_thermal_reduction_pctg[i] = 0;
+ for (i = 0; i < nr_cpu_ids; i++)
+ if (cpu_present(i))
+ per_cpu(cpufreq_thermal_reduction_pctg, i) = 0;
i = cpufreq_register_notifier(&acpi_thermal_cpufreq_notifier_block,
CPUFREQ_POLICY_NOTIFIER);
diff --git a/drivers/atm/nicstar.c b/drivers/atm/nicstar.c
index 38c769f..3da804b 100644
--- a/drivers/atm/nicstar.c
+++ b/drivers/atm/nicstar.c
@@ -415,7 +415,7 @@
card->pcidev = pcidev;
membase = pci_resource_start(pcidev, 1);
card->membase = ioremap(membase, NS_IOREMAP_SIZE);
- if (card->membase == 0)
+ if (!card->membase)
{
printk("nicstar%d: can't ioremap() membase.\n",i);
error = 3;
diff --git a/drivers/char/drm/r128_cce.c b/drivers/char/drm/r128_cce.c
index f36adbd..c31afbd 100644
--- a/drivers/char/drm/r128_cce.c
+++ b/drivers/char/drm/r128_cce.c
@@ -817,7 +817,7 @@
for (i = 0; i < dma->buf_count; i++) {
buf = dma->buflist[i];
buf_priv = buf->dev_private;
- if (buf->file_priv == 0)
+ if (!buf->file_priv)
return buf;
}
diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c
index 4d3c701..98b65a2 100644
--- a/drivers/char/tty_io.c
+++ b/drivers/char/tty_io.c
@@ -1180,7 +1180,7 @@
if (*str == ',')
str++;
if (*str == '\0')
- str = 0;
+ str = NULL;
if (tty_line >= 0 && tty_line <= p->num && p->poll_init &&
!p->poll_init(p, tty_line, str)) {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 35a26a3..d3575f5 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -118,9 +118,11 @@
static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
static struct srcu_notifier_head cpufreq_transition_notifier_list;
+static bool init_cpufreq_transition_notifier_list_called;
static int __init init_cpufreq_transition_notifier_list(void)
{
srcu_init_notifier_head(&cpufreq_transition_notifier_list);
+ init_cpufreq_transition_notifier_list_called = true;
return 0;
}
pure_initcall(init_cpufreq_transition_notifier_list);
@@ -216,7 +218,7 @@
}
void cpufreq_debug_printk(unsigned int type, const char *prefix,
- const char *fmt, ...)
+ const char *fmt, ...)
{
char s[256];
va_list args;
@@ -378,7 +380,7 @@
/**
* cpufreq_parse_governor - parse a governor string
*/
-static int cpufreq_parse_governor (char *str_governor, unsigned int *policy,
+static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
struct cpufreq_governor **governor)
{
int err = -EINVAL;
@@ -446,7 +448,7 @@
#define show_one(file_name, object) \
static ssize_t show_##file_name \
-(struct cpufreq_policy * policy, char *buf) \
+(struct cpufreq_policy *policy, char *buf) \
{ \
return sprintf (buf, "%u\n", policy->object); \
}
@@ -465,7 +467,7 @@
*/
#define store_one(file_name, object) \
static ssize_t store_##file_name \
-(struct cpufreq_policy * policy, const char *buf, size_t count) \
+(struct cpufreq_policy *policy, const char *buf, size_t count) \
{ \
unsigned int ret = -EINVAL; \
struct cpufreq_policy new_policy; \
@@ -490,8 +492,8 @@
/**
* show_cpuinfo_cur_freq - current CPU frequency as detected by hardware
*/
-static ssize_t show_cpuinfo_cur_freq (struct cpufreq_policy * policy,
- char *buf)
+static ssize_t show_cpuinfo_cur_freq(struct cpufreq_policy *policy,
+ char *buf)
{
unsigned int cur_freq = __cpufreq_get(policy->cpu);
if (!cur_freq)
@@ -503,8 +505,7 @@
/**
* show_scaling_governor - show the current policy for the specified CPU
*/
-static ssize_t show_scaling_governor (struct cpufreq_policy * policy,
- char *buf)
+static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
{
if(policy->policy == CPUFREQ_POLICY_POWERSAVE)
return sprintf(buf, "powersave\n");
@@ -519,8 +520,8 @@
/**
* store_scaling_governor - store policy for the specified CPU
*/
-static ssize_t store_scaling_governor (struct cpufreq_policy * policy,
- const char *buf, size_t count)
+static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
+ const char *buf, size_t count)
{
unsigned int ret = -EINVAL;
char str_governor[16];
@@ -554,7 +555,7 @@
/**
* show_scaling_driver - show the cpufreq driver currently loaded
*/
-static ssize_t show_scaling_driver (struct cpufreq_policy * policy, char *buf)
+static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
{
return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", cpufreq_driver->name);
}
@@ -562,8 +563,8 @@
/**
* show_scaling_available_governors - show the available CPUfreq governors
*/
-static ssize_t show_scaling_available_governors (struct cpufreq_policy *policy,
- char *buf)
+static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
+ char *buf)
{
ssize_t i = 0;
struct cpufreq_governor *t;
@@ -585,7 +586,7 @@
/**
* show_affected_cpus - show the CPUs affected by each transition
*/
-static ssize_t show_affected_cpus (struct cpufreq_policy * policy, char *buf)
+static ssize_t show_affected_cpus(struct cpufreq_policy *policy, char *buf)
{
ssize_t i = 0;
unsigned int cpu;
@@ -602,7 +603,7 @@
}
static ssize_t store_scaling_setspeed(struct cpufreq_policy *policy,
- const char *buf, size_t count)
+ const char *buf, size_t count)
{
unsigned int freq = 0;
unsigned int ret;
@@ -651,7 +652,7 @@
define_one_rw(scaling_governor);
define_one_rw(scaling_setspeed);
-static struct attribute * default_attrs[] = {
+static struct attribute *default_attrs[] = {
&cpuinfo_min_freq.attr,
&cpuinfo_max_freq.attr,
&scaling_min_freq.attr,
@@ -667,10 +668,10 @@
#define to_policy(k) container_of(k,struct cpufreq_policy,kobj)
#define to_attr(a) container_of(a,struct freq_attr,attr)
-static ssize_t show(struct kobject * kobj, struct attribute * attr ,char * buf)
+static ssize_t show(struct kobject *kobj, struct attribute *attr ,char *buf)
{
- struct cpufreq_policy * policy = to_policy(kobj);
- struct freq_attr * fattr = to_attr(attr);
+ struct cpufreq_policy *policy = to_policy(kobj);
+ struct freq_attr *fattr = to_attr(attr);
ssize_t ret = -EINVAL;
policy = cpufreq_cpu_get(policy->cpu);
if (!policy)
@@ -691,11 +692,11 @@
return ret;
}
-static ssize_t store(struct kobject * kobj, struct attribute * attr,
- const char * buf, size_t count)
+static ssize_t store(struct kobject *kobj, struct attribute *attr,
+ const char *buf, size_t count)
{
- struct cpufreq_policy * policy = to_policy(kobj);
- struct freq_attr * fattr = to_attr(attr);
+ struct cpufreq_policy *policy = to_policy(kobj);
+ struct freq_attr *fattr = to_attr(attr);
ssize_t ret = -EINVAL;
policy = cpufreq_cpu_get(policy->cpu);
if (!policy)
@@ -716,9 +717,9 @@
return ret;
}
-static void cpufreq_sysfs_release(struct kobject * kobj)
+static void cpufreq_sysfs_release(struct kobject *kobj)
{
- struct cpufreq_policy * policy = to_policy(kobj);
+ struct cpufreq_policy *policy = to_policy(kobj);
dprintk("last reference is dropped\n");
complete(&policy->kobj_unregister);
}
@@ -740,7 +741,7 @@
*
* Adds the cpufreq interface for a CPU device.
*/
-static int cpufreq_add_dev (struct sys_device * sys_dev)
+static int cpufreq_add_dev(struct sys_device *sys_dev)
{
unsigned int cpu = sys_dev->id;
int ret = 0;
@@ -800,7 +801,6 @@
ret = cpufreq_driver->init(policy);
if (ret) {
dprintk("initialization failed\n");
- unlock_policy_rwsem_write(cpu);
goto err_out;
}
policy->user_policy.min = policy->cpuinfo.min_freq;
@@ -823,7 +823,7 @@
/* check for existing affected CPUs. They may not be aware
* of it due to CPU Hotplug.
*/
- managed_policy = cpufreq_cpu_get(j);
+ managed_policy = cpufreq_cpu_get(j); // FIXME: Where is this released? What about error paths?
if (unlikely(managed_policy)) {
/* Set proper policy_cpu */
@@ -842,14 +842,11 @@
ret = sysfs_create_link(&sys_dev->kobj,
&managed_policy->kobj,
"cpufreq");
- if (ret) {
- unlock_policy_rwsem_write(cpu);
+ if (ret)
goto err_out_driver_exit;
- }
cpufreq_debug_enable_ratelimit();
ret = 0;
- unlock_policy_rwsem_write(cpu);
goto err_out_driver_exit; /* call driver->exit() */
}
}
@@ -859,33 +856,26 @@
/* prepare interface data */
ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &sys_dev->kobj,
"cpufreq");
- if (ret) {
- unlock_policy_rwsem_write(cpu);
+ if (ret)
goto err_out_driver_exit;
- }
+
/* set up files for this cpu device */
drv_attr = cpufreq_driver->attr;
while ((drv_attr) && (*drv_attr)) {
ret = sysfs_create_file(&policy->kobj, &((*drv_attr)->attr));
- if (ret) {
- unlock_policy_rwsem_write(cpu);
+ if (ret)
goto err_out_driver_exit;
- }
drv_attr++;
}
- if (cpufreq_driver->get){
+ if (cpufreq_driver->get) {
ret = sysfs_create_file(&policy->kobj, &cpuinfo_cur_freq.attr);
- if (ret) {
- unlock_policy_rwsem_write(cpu);
+ if (ret)
goto err_out_driver_exit;
- }
}
- if (cpufreq_driver->target){
+ if (cpufreq_driver->target) {
ret = sysfs_create_file(&policy->kobj, &scaling_cur_freq.attr);
- if (ret) {
- unlock_policy_rwsem_write(cpu);
+ if (ret)
goto err_out_driver_exit;
- }
}
spin_lock_irqsave(&cpufreq_driver_lock, flags);
@@ -907,10 +897,8 @@
cpu_sys_dev = get_cpu_sysdev(j);
ret = sysfs_create_link(&cpu_sys_dev->kobj, &policy->kobj,
"cpufreq");
- if (ret) {
- unlock_policy_rwsem_write(cpu);
+ if (ret)
goto err_out_unregister;
- }
}
policy->governor = NULL; /* to assure that the starting sequence is
@@ -950,6 +938,7 @@
cpufreq_driver->exit(policy);
err_out:
+ unlock_policy_rwsem_write(cpu);
kfree(policy);
nomem_out:
@@ -967,7 +956,7 @@
* Caller should already have policy_rwsem in write mode for this CPU.
* This routine frees the rwsem before returning.
*/
-static int __cpufreq_remove_dev (struct sys_device * sys_dev)
+static int __cpufreq_remove_dev(struct sys_device *sys_dev)
{
unsigned int cpu = sys_dev->id;
unsigned long flags;
@@ -1071,7 +1060,7 @@
}
-static int cpufreq_remove_dev (struct sys_device * sys_dev)
+static int cpufreq_remove_dev(struct sys_device *sys_dev)
{
unsigned int cpu = sys_dev->id;
int retval;
@@ -1138,7 +1127,7 @@
cpufreq_cpu_put(policy);
}
- return (ret_freq);
+ return ret_freq;
}
EXPORT_SYMBOL(cpufreq_quick_get);
@@ -1149,7 +1138,7 @@
unsigned int ret_freq = 0;
if (!cpufreq_driver->get)
- return (ret_freq);
+ return ret_freq;
ret_freq = cpufreq_driver->get(cpu);
@@ -1163,7 +1152,7 @@
}
}
- return (ret_freq);
+ return ret_freq;
}
/**
@@ -1190,7 +1179,7 @@
out_policy:
cpufreq_cpu_put(policy);
out:
- return (ret_freq);
+ return ret_freq;
}
EXPORT_SYMBOL(cpufreq_get);
@@ -1199,7 +1188,7 @@
* cpufreq_suspend - let the low level driver prepare for suspend
*/
-static int cpufreq_suspend(struct sys_device * sysdev, pm_message_t pmsg)
+static int cpufreq_suspend(struct sys_device *sysdev, pm_message_t pmsg)
{
int cpu = sysdev->id;
int ret = 0;
@@ -1221,22 +1210,18 @@
return -EINVAL;
/* only handle each CPU group once */
- if (unlikely(cpu_policy->cpu != cpu)) {
- cpufreq_cpu_put(cpu_policy);
- return 0;
- }
+ if (unlikely(cpu_policy->cpu != cpu))
+ goto out;
if (cpufreq_driver->suspend) {
ret = cpufreq_driver->suspend(cpu_policy, pmsg);
if (ret) {
printk(KERN_ERR "cpufreq: suspend failed in ->suspend "
"step on CPU %u\n", cpu_policy->cpu);
- cpufreq_cpu_put(cpu_policy);
- return ret;
+ goto out;
}
}
-
if (cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)
goto out;
@@ -1270,7 +1255,7 @@
out:
cpufreq_cpu_put(cpu_policy);
- return 0;
+ return ret;
}
/**
@@ -1281,7 +1266,7 @@
* 3.) schedule call cpufreq_update_policy() ASAP as interrupts are
* restored.
*/
-static int cpufreq_resume(struct sys_device * sysdev)
+static int cpufreq_resume(struct sys_device *sysdev)
{
int cpu = sysdev->id;
int ret = 0;
@@ -1302,18 +1287,15 @@
return -EINVAL;
/* only handle each CPU group once */
- if (unlikely(cpu_policy->cpu != cpu)) {
- cpufreq_cpu_put(cpu_policy);
- return 0;
- }
+ if (unlikely(cpu_policy->cpu != cpu))
+ goto fail;
if (cpufreq_driver->resume) {
ret = cpufreq_driver->resume(cpu_policy);
if (ret) {
printk(KERN_ERR "cpufreq: resume failed in ->resume "
"step on CPU %u\n", cpu_policy->cpu);
- cpufreq_cpu_put(cpu_policy);
- return ret;
+ goto fail;
}
}
@@ -1353,6 +1335,7 @@
out:
schedule_work(&cpu_policy->update);
+fail:
cpufreq_cpu_put(cpu_policy);
return ret;
}
@@ -1386,6 +1369,8 @@
{
int ret;
+ WARN_ON(!init_cpufreq_transition_notifier_list_called);
+
switch (list) {
case CPUFREQ_TRANSITION_NOTIFIER:
ret = srcu_notifier_chain_register(
@@ -1848,7 +1833,7 @@
cpufreq_debug_enable_ratelimit();
}
- return (ret);
+ return ret;
}
EXPORT_SYMBOL_GPL(cpufreq_register_driver);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 070421a..ef09e06 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -114,7 +114,7 @@
stat->freq_table[i]);
}
if (len >= PAGE_SIZE)
- return len;
+ return PAGE_SIZE;
len += snprintf(buf + len, PAGE_SIZE - len, "\n");
@@ -131,8 +131,12 @@
len += snprintf(buf + len, PAGE_SIZE - len, "%9u ",
stat->trans_table[i*stat->max_state+j]);
}
+ if (len >= PAGE_SIZE)
+ break;
len += snprintf(buf + len, PAGE_SIZE - len, "\n");
}
+ if (len >= PAGE_SIZE)
+ return PAGE_SIZE;
return len;
}
CPUFREQ_STATDEVICE_ATTR(trans_table,0444,show_trans_table);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 29adaa78..e2bae8d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -42,7 +42,10 @@
* to show when page is mapped
* & limit reverse map searches.
*/
- unsigned int inuse; /* SLUB: Nr of objects */
+ struct { /* SLUB */
+ u16 inuse;
+ u16 objects;
+ };
};
union {
struct {
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 79d59c9..71e43a1 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -29,6 +29,7 @@
DEACTIVATE_TO_HEAD, /* Cpu slab was moved to the head of partials */
DEACTIVATE_TO_TAIL, /* Cpu slab was moved to the tail of partials */
DEACTIVATE_REMOTE_FREES,/* Slab contained remotely freed objects */
+ ORDER_FALLBACK, /* Number of times fallback was necessary */
NR_SLUB_STAT_ITEMS };
struct kmem_cache_cpu {
@@ -48,11 +49,21 @@
struct list_head partial;
#ifdef CONFIG_SLUB_DEBUG
atomic_long_t nr_slabs;
+ atomic_long_t total_objects;
struct list_head full;
#endif
};
/*
+ * Word size structure that can be atomically updated or read and that
+ * contains both the order and the number of objects that a slab of the
+ * given order would contain.
+ */
+struct kmem_cache_order_objects {
+ unsigned long x;
+};
+
+/*
* Slab cache management.
*/
struct kmem_cache {
@@ -61,7 +72,7 @@
int size; /* The size of an object including meta data */
int objsize; /* The size of an object without meta data */
int offset; /* Free pointer offset. */
- int order; /* Current preferred allocation order */
+ struct kmem_cache_order_objects oo;
/*
* Avoid an extra cache line for UP, SMP and for the node local to
@@ -70,7 +81,8 @@
struct kmem_cache_node local_node;
/* Allocation and freeing of slabs */
- int objects; /* Number of objects in slab */
+ struct kmem_cache_order_objects max;
+ struct kmem_cache_order_objects min;
gfp_t allocflags; /* gfp flags to use on each alloc */
int refcount; /* Refcount for slab cache destroy */
void (*ctor)(struct kmem_cache *, void *);
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index 753dc54..7473b0c 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -133,7 +133,7 @@
else
dev = MKDEV(MD_MAJOR, minor);
create_dev(name, dev);
- for (i = 0; i < MD_SB_DISKS && devname != 0; i++) {
+ for (i = 0; i < MD_SB_DISKS && devname != NULL; i++) {
char *p;
char comp_name[64];
u32 rdev;
diff --git a/init/do_mounts_rd.c b/init/do_mounts_rd.c
index 3ac5904..46dfd64 100644
--- a/init/do_mounts_rd.c
+++ b/init/do_mounts_rd.c
@@ -212,7 +212,7 @@
}
buf = kmalloc(BLOCK_SIZE, GFP_KERNEL);
- if (buf == 0) {
+ if (!buf) {
printk(KERN_ERR "RAMDISK: could not allocate buffer\n");
goto done;
}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 024888b..48a976c 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1265,7 +1265,8 @@
return -E2BIG;
/* +1 for nul-terminator */
- if ((buffer = kmalloc(nbytes + 1, GFP_KERNEL)) == 0)
+ buffer = kmalloc(nbytes + 1, GFP_KERNEL);
+ if (!buffer)
return -ENOMEM;
if (copy_from_user(buffer, userbuf, nbytes)) {
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index e379ef0..dea4c91 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -590,7 +590,6 @@
list_add_tail(&timer->cb_entry,
&base->cpu_base->cb_pending);
timer->state = HRTIMER_STATE_PENDING;
- raise_softirq(HRTIMER_SOFTIRQ);
return 1;
default:
BUG();
@@ -633,6 +632,11 @@
return 1;
}
+static inline void hrtimer_raise_softirq(void)
+{
+ raise_softirq(HRTIMER_SOFTIRQ);
+}
+
#else
static inline int hrtimer_hres_active(void) { return 0; }
@@ -651,6 +655,7 @@
{
return 0;
}
+static inline void hrtimer_raise_softirq(void) { }
#endif /* CONFIG_HIGH_RES_TIMERS */
@@ -850,7 +855,7 @@
{
struct hrtimer_clock_base *base, *new_base;
unsigned long flags;
- int ret;
+ int ret, raise;
base = lock_hrtimer_base(timer, &flags);
@@ -884,8 +889,18 @@
enqueue_hrtimer(timer, new_base,
new_base->cpu_base == &__get_cpu_var(hrtimer_bases));
+ /*
+ * The timer may be expired and moved to the cb_pending
+ * list. We can not raise the softirq with base lock held due
+ * to a possible deadlock with runqueue lock.
+ */
+ raise = timer->state == HRTIMER_STATE_PENDING;
+
unlock_hrtimer_base(timer, &flags);
+ if (raise)
+ hrtimer_raise_softirq();
+
return ret;
}
EXPORT_SYMBOL_GPL(hrtimer_start);
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 6d792b6..5ca37fa 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -92,7 +92,7 @@
atomic_set(&ns->pidmap[0].nr_free, BITS_PER_PAGE - 1);
for (i = 1; i < PIDMAP_ENTRIES; i++) {
- ns->pidmap[i].page = 0;
+ ns->pidmap[i].page = NULL;
atomic_set(&ns->pidmap[i].nr_free, BITS_PER_PAGE);
}
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 67e392e..dac4b4e 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -612,7 +612,7 @@
return (copied == sizeof(data)) ? 0 : -EIO;
}
-#ifdef CONFIG_COMPAT
+#if defined CONFIG_COMPAT && defined __ARCH_WANT_COMPAT_SYS_PTRACE
#include <linux/compat.h>
int compat_ptrace_request(struct task_struct *child, compat_long_t request,
@@ -667,7 +667,6 @@
return ret;
}
-#ifdef __ARCH_WANT_COMPAT_SYS_PTRACE
asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
compat_long_t addr, compat_long_t data)
{
@@ -710,6 +709,4 @@
unlock_kernel();
return ret;
}
-#endif /* __ARCH_WANT_COMPAT_SYS_PTRACE */
-
-#endif /* CONFIG_COMPAT */
+#endif /* CONFIG_COMPAT && __ARCH_WANT_COMPAT_SYS_PTRACE */
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index df28c17..2c37c67 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -204,7 +204,7 @@
if (page) {
if (arch_prepare_hugepage(page)) {
__free_pages(page, HUGETLB_PAGE_ORDER);
- return 0;
+ return NULL;
}
set_compound_page_dtor(page, free_huge_page);
spin_lock(&hugetlb_lock);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c4ba85c..b17dca7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -29,6 +29,8 @@
#include <asm/tlbflush.h>
+#include "internal.h"
+
/* add this memory to iomem resource */
static struct resource *register_memory_resource(u64 start, u64 size)
{
diff --git a/mm/slob.c b/mm/slob.c
index e2c3c0e..6038cba 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -533,7 +533,8 @@
{
struct kmem_cache *c;
- c = slob_alloc(sizeof(struct kmem_cache), flags, 0, -1);
+ c = slob_alloc(sizeof(struct kmem_cache),
+ flags, ARCH_KMALLOC_MINALIGN, -1);
if (c) {
c->name = name;
diff --git a/mm/slub.c b/mm/slub.c
index 38914bc..992ecd4 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -149,25 +149,6 @@
/* Enable to test recovery from slab corruption on boot */
#undef SLUB_RESILIENCY_TEST
-#if PAGE_SHIFT <= 12
-
-/*
- * Small page size. Make sure that we do not fragment memory
- */
-#define DEFAULT_MAX_ORDER 1
-#define DEFAULT_MIN_OBJECTS 4
-
-#else
-
-/*
- * Large page machines are customarily able to handle larger
- * page orders.
- */
-#define DEFAULT_MAX_ORDER 2
-#define DEFAULT_MIN_OBJECTS 8
-
-#endif
-
/*
* Mininum number of partial slabs. These will be left on the partial
* lists even if they are empty. kmem_cache_shrink may reclaim them.
@@ -204,8 +185,6 @@
/* Internal SLUB flags */
#define __OBJECT_POISON 0x80000000 /* Poison object */
#define __SYSFS_ADD_DEFERRED 0x40000000 /* Not yet visible via sysfs */
-#define __KMALLOC_CACHE 0x20000000 /* objects freed using kfree */
-#define __PAGE_ALLOC_FALLBACK 0x10000000 /* Allow fallback to page alloc */
static int kmem_size = sizeof(struct kmem_cache);
@@ -296,7 +275,7 @@
return 1;
base = page_address(page);
- if (object < base || object >= base + s->objects * s->size ||
+ if (object < base || object >= base + page->objects * s->size ||
(object - base) % s->size) {
return 0;
}
@@ -322,8 +301,8 @@
}
/* Loop over all objects in a slab */
-#define for_each_object(__p, __s, __addr) \
- for (__p = (__addr); __p < (__addr) + (__s)->objects * (__s)->size;\
+#define for_each_object(__p, __s, __addr, __objects) \
+ for (__p = (__addr); __p < (__addr) + (__objects) * (__s)->size;\
__p += (__s)->size)
/* Scan freelist */
@@ -336,6 +315,26 @@
return (p - addr) / s->size;
}
+static inline struct kmem_cache_order_objects oo_make(int order,
+ unsigned long size)
+{
+ struct kmem_cache_order_objects x = {
+ (order << 16) + (PAGE_SIZE << order) / size
+ };
+
+ return x;
+}
+
+static inline int oo_order(struct kmem_cache_order_objects x)
+{
+ return x.x >> 16;
+}
+
+static inline int oo_objects(struct kmem_cache_order_objects x)
+{
+ return x.x & ((1 << 16) - 1);
+}
+
#ifdef CONFIG_SLUB_DEBUG
/*
* Debug settings:
@@ -446,8 +445,8 @@
static void print_page_info(struct page *page)
{
- printk(KERN_ERR "INFO: Slab 0x%p used=%u fp=0x%p flags=0x%04lx\n",
- page, page->inuse, page->freelist, page->flags);
+ printk(KERN_ERR "INFO: Slab 0x%p objects=%u used=%u fp=0x%p flags=0x%04lx\n",
+ page, page->objects, page->inuse, page->freelist, page->flags);
}
@@ -647,6 +646,7 @@
p + off, POISON_INUSE, s->size - off);
}
+/* Check the pad bytes at the end of a slab page */
static int slab_pad_check(struct kmem_cache *s, struct page *page)
{
u8 *start;
@@ -659,20 +659,20 @@
return 1;
start = page_address(page);
- end = start + (PAGE_SIZE << s->order);
- length = s->objects * s->size;
- remainder = end - (start + length);
+ length = (PAGE_SIZE << compound_order(page));
+ end = start + length;
+ remainder = length % s->size;
if (!remainder)
return 1;
- fault = check_bytes(start + length, POISON_INUSE, remainder);
+ fault = check_bytes(end - remainder, POISON_INUSE, remainder);
if (!fault)
return 1;
while (end > fault && end[-1] == POISON_INUSE)
end--;
slab_err(s, page, "Padding overwritten. 0x%p-0x%p", fault, end - 1);
- print_section("Padding", start, length);
+ print_section("Padding", end - remainder, remainder);
restore_bytes(s, "slab padding", POISON_INUSE, start, end);
return 0;
@@ -734,15 +734,24 @@
static int check_slab(struct kmem_cache *s, struct page *page)
{
+ int maxobj;
+
VM_BUG_ON(!irqs_disabled());
if (!PageSlab(page)) {
slab_err(s, page, "Not a valid slab page");
return 0;
}
- if (page->inuse > s->objects) {
+
+ maxobj = (PAGE_SIZE << compound_order(page)) / s->size;
+ if (page->objects > maxobj) {
+ slab_err(s, page, "objects %u > max %u",
+ s->name, page->objects, maxobj);
+ return 0;
+ }
+ if (page->inuse > page->objects) {
slab_err(s, page, "inuse %u > max %u",
- s->name, page->inuse, s->objects);
+ s->name, page->inuse, page->objects);
return 0;
}
/* Slab_pad_check fixes things up after itself */
@@ -759,8 +768,9 @@
int nr = 0;
void *fp = page->freelist;
void *object = NULL;
+ unsigned long max_objects;
- while (fp && nr <= s->objects) {
+ while (fp && nr <= page->objects) {
if (fp == search)
return 1;
if (!check_valid_pointer(s, page, fp)) {
@@ -772,7 +782,7 @@
} else {
slab_err(s, page, "Freepointer corrupt");
page->freelist = NULL;
- page->inuse = s->objects;
+ page->inuse = page->objects;
slab_fix(s, "Freelist cleared");
return 0;
}
@@ -783,10 +793,20 @@
nr++;
}
- if (page->inuse != s->objects - nr) {
+ max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
+ if (max_objects > 65535)
+ max_objects = 65535;
+
+ if (page->objects != max_objects) {
+ slab_err(s, page, "Wrong number of objects. Found %d but "
+ "should be %d", page->objects, max_objects);
+ page->objects = max_objects;
+ slab_fix(s, "Number of objects adjusted.");
+ }
+ if (page->inuse != page->objects - nr) {
slab_err(s, page, "Wrong object count. Counter is %d but "
- "counted were %d", page->inuse, s->objects - nr);
- page->inuse = s->objects - nr;
+ "counted were %d", page->inuse, page->objects - nr);
+ page->inuse = page->objects - nr;
slab_fix(s, "Object count adjusted.");
}
return search == NULL;
@@ -840,7 +860,7 @@
return atomic_long_read(&n->nr_slabs);
}
-static inline void inc_slabs_node(struct kmem_cache *s, int node)
+static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
@@ -850,14 +870,17 @@
* dilemma by deferring the increment of the count during
* bootstrap (see early_kmem_cache_node_alloc).
*/
- if (!NUMA_BUILD || n)
+ if (!NUMA_BUILD || n) {
atomic_long_inc(&n->nr_slabs);
+ atomic_long_add(objects, &n->total_objects);
+ }
}
-static inline void dec_slabs_node(struct kmem_cache *s, int node)
+static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects)
{
struct kmem_cache_node *n = get_node(s, node);
atomic_long_dec(&n->nr_slabs);
+ atomic_long_sub(objects, &n->total_objects);
}
/* Object debug checks for alloc/free paths */
@@ -905,7 +928,7 @@
* as used avoids touching the remaining objects.
*/
slab_fix(s, "Marking all objects used");
- page->inuse = s->objects;
+ page->inuse = page->objects;
page->freelist = NULL;
}
return 0;
@@ -1055,31 +1078,52 @@
static inline unsigned long slabs_node(struct kmem_cache *s, int node)
{ return 0; }
-static inline void inc_slabs_node(struct kmem_cache *s, int node) {}
-static inline void dec_slabs_node(struct kmem_cache *s, int node) {}
+static inline void inc_slabs_node(struct kmem_cache *s, int node,
+ int objects) {}
+static inline void dec_slabs_node(struct kmem_cache *s, int node,
+ int objects) {}
#endif
+
/*
* Slab allocation and freeing
*/
+static inline struct page *alloc_slab_page(gfp_t flags, int node,
+ struct kmem_cache_order_objects oo)
+{
+ int order = oo_order(oo);
+
+ if (node == -1)
+ return alloc_pages(flags, order);
+ else
+ return alloc_pages_node(node, flags, order);
+}
+
static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
{
struct page *page;
- int pages = 1 << s->order;
+ struct kmem_cache_order_objects oo = s->oo;
flags |= s->allocflags;
- if (node == -1)
- page = alloc_pages(flags, s->order);
- else
- page = alloc_pages_node(node, flags, s->order);
+ page = alloc_slab_page(flags | __GFP_NOWARN | __GFP_NORETRY, node,
+ oo);
+ if (unlikely(!page)) {
+ oo = s->min;
+ /*
+ * Allocation may have failed due to fragmentation.
+ * Try a lower order alloc if possible
+ */
+ page = alloc_slab_page(flags, node, oo);
+ if (!page)
+ return NULL;
- if (!page)
- return NULL;
-
+ stat(get_cpu_slab(s, raw_smp_processor_id()), ORDER_FALLBACK);
+ }
+ page->objects = oo_objects(oo);
mod_zone_page_state(page_zone(page),
(s->flags & SLAB_RECLAIM_ACCOUNT) ?
NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
- pages);
+ 1 << oo_order(oo));
return page;
}
@@ -1106,7 +1150,7 @@
if (!page)
goto out;
- inc_slabs_node(s, page_to_nid(page));
+ inc_slabs_node(s, page_to_nid(page), page->objects);
page->slab = s;
page->flags |= 1 << PG_slab;
if (s->flags & (SLAB_DEBUG_FREE | SLAB_RED_ZONE | SLAB_POISON |
@@ -1116,10 +1160,10 @@
start = page_address(page);
if (unlikely(s->flags & SLAB_POISON))
- memset(start, POISON_INUSE, PAGE_SIZE << s->order);
+ memset(start, POISON_INUSE, PAGE_SIZE << compound_order(page));
last = start;
- for_each_object(p, s, start) {
+ for_each_object(p, s, start, page->objects) {
setup_object(s, page, last);
set_freepointer(s, last, p);
last = p;
@@ -1135,13 +1179,15 @@
static void __free_slab(struct kmem_cache *s, struct page *page)
{
- int pages = 1 << s->order;
+ int order = compound_order(page);
+ int pages = 1 << order;
if (unlikely(SlabDebug(page))) {
void *p;
slab_pad_check(s, page);
- for_each_object(p, s, page_address(page))
+ for_each_object(p, s, page_address(page),
+ page->objects)
check_object(s, page, p, 0);
ClearSlabDebug(page);
}
@@ -1153,7 +1199,7 @@
__ClearPageSlab(page);
reset_page_mapcount(page);
- __free_pages(page, s->order);
+ __free_pages(page, order);
}
static void rcu_free_slab(struct rcu_head *h)
@@ -1179,7 +1225,7 @@
static void discard_slab(struct kmem_cache *s, struct page *page)
{
- dec_slabs_node(s, page_to_nid(page));
+ dec_slabs_node(s, page_to_nid(page), page->objects);
free_slab(s, page);
}
@@ -1515,7 +1561,7 @@
goto debug;
c->freelist = object[c->offset];
- c->page->inuse = s->objects;
+ c->page->inuse = c->page->objects;
c->page->freelist = NULL;
c->node = page_to_nid(c->page);
unlock_out:
@@ -1552,27 +1598,6 @@
c->page = new;
goto load_freelist;
}
-
- /*
- * No memory available.
- *
- * If the slab uses higher order allocs but the object is
- * smaller than a page size then we can fallback in emergencies
- * to the page allocator via kmalloc_large. The page allocator may
- * have failed to obtain a higher order page and we can try to
- * allocate a single page if the object fits into a single page.
- * That is only possible if certain conditions are met that are being
- * checked when a slab is created.
- */
- if (!(gfpflags & __GFP_NORETRY) &&
- (s->flags & __PAGE_ALLOC_FALLBACK)) {
- if (gfpflags & __GFP_WAIT)
- local_irq_enable();
- object = kmalloc_large(s->objsize, gfpflags);
- if (gfpflags & __GFP_WAIT)
- local_irq_disable();
- return object;
- }
return NULL;
debug:
if (!alloc_debug_processing(s, c->page, object, addr))
@@ -1773,8 +1798,8 @@
* take the list_lock.
*/
static int slub_min_order;
-static int slub_max_order = DEFAULT_MAX_ORDER;
-static int slub_min_objects = DEFAULT_MIN_OBJECTS;
+static int slub_max_order = PAGE_ALLOC_COSTLY_ORDER;
+static int slub_min_objects;
/*
* Merge control. If this is set then no merging of slab caches will occur.
@@ -1789,7 +1814,7 @@
* system components. Generally order 0 allocations should be preferred since
* order 0 does not cause fragmentation in the page allocator. Larger objects
* be problematic to put into order 0 slabs because there may be too much
- * unused space left. We go to a higher order if more than 1/8th of the slab
+ * unused space left. We go to a higher order if more than 1/16th of the slab
* would be wasted.
*
* In order to reach satisfactory performance we must ensure that a minimum
@@ -1814,6 +1839,9 @@
int rem;
int min_order = slub_min_order;
+ if ((PAGE_SIZE << min_order) / size > 65535)
+ return get_order(size * 65535) - 1;
+
for (order = max(min_order,
fls(min_objects * size - 1) - PAGE_SHIFT);
order <= max_order; order++) {
@@ -1848,8 +1876,10 @@
* we reduce the minimum objects required in a slab.
*/
min_objects = slub_min_objects;
+ if (!min_objects)
+ min_objects = 4 * (fls(nr_cpu_ids) + 1);
while (min_objects > 1) {
- fraction = 8;
+ fraction = 16;
while (fraction >= 4) {
order = slab_order(size, min_objects,
slub_max_order, fraction);
@@ -2091,7 +2121,7 @@
init_tracking(kmalloc_caches, n);
#endif
init_kmem_cache_node(n);
- inc_slabs_node(kmalloc_caches, node);
+ inc_slabs_node(kmalloc_caches, node, page->objects);
/*
* lockdep requires consistent irq usage for each lock
@@ -2167,11 +2197,12 @@
* calculate_sizes() determines the order and the distribution of data within
* a slab object.
*/
-static int calculate_sizes(struct kmem_cache *s)
+static int calculate_sizes(struct kmem_cache *s, int forced_order)
{
unsigned long flags = s->flags;
unsigned long size = s->objsize;
unsigned long align = s->align;
+ int order;
/*
* Round up object size to the next word boundary. We can only
@@ -2255,26 +2286,16 @@
*/
size = ALIGN(size, align);
s->size = size;
+ if (forced_order >= 0)
+ order = forced_order;
+ else
+ order = calculate_order(size);
- if ((flags & __KMALLOC_CACHE) &&
- PAGE_SIZE / size < slub_min_objects) {
- /*
- * Kmalloc cache that would not have enough objects in
- * an order 0 page. Kmalloc slabs can fallback to
- * page allocator order 0 allocs so take a reasonably large
- * order that will allows us a good number of objects.
- */
- s->order = max(slub_max_order, PAGE_ALLOC_COSTLY_ORDER);
- s->flags |= __PAGE_ALLOC_FALLBACK;
- s->allocflags |= __GFP_NOWARN;
- } else
- s->order = calculate_order(size);
-
- if (s->order < 0)
+ if (order < 0)
return 0;
s->allocflags = 0;
- if (s->order)
+ if (order)
s->allocflags |= __GFP_COMP;
if (s->flags & SLAB_CACHE_DMA)
@@ -2286,9 +2307,12 @@
/*
* Determine the number of objects per slab
*/
- s->objects = (PAGE_SIZE << s->order) / size;
+ s->oo = oo_make(order, size);
+ s->min = oo_make(get_order(size), size);
+ if (oo_objects(s->oo) > oo_objects(s->max))
+ s->max = s->oo;
- return !!s->objects;
+ return !!oo_objects(s->oo);
}
@@ -2304,7 +2328,7 @@
s->align = align;
s->flags = kmem_cache_flags(size, flags, name, ctor);
- if (!calculate_sizes(s))
+ if (!calculate_sizes(s, -1))
goto error;
s->refcount = 1;
@@ -2321,7 +2345,7 @@
if (flags & SLAB_PANIC)
panic("Cannot create slab %s size=%lu realsize=%u "
"order=%u offset=%u flags=%lx\n",
- s->name, (unsigned long)size, s->size, s->order,
+ s->name, (unsigned long)size, s->size, oo_order(s->oo),
s->offset, flags);
return 0;
}
@@ -2367,26 +2391,52 @@
}
EXPORT_SYMBOL(kmem_cache_name);
-/*
- * Attempt to free all slabs on a node. Return the number of slabs we
- * were unable to free.
- */
-static int free_list(struct kmem_cache *s, struct kmem_cache_node *n,
- struct list_head *list)
+static void list_slab_objects(struct kmem_cache *s, struct page *page,
+ const char *text)
{
- int slabs_inuse = 0;
+#ifdef CONFIG_SLUB_DEBUG
+ void *addr = page_address(page);
+ void *p;
+ DECLARE_BITMAP(map, page->objects);
+
+ bitmap_zero(map, page->objects);
+ slab_err(s, page, "%s", text);
+ slab_lock(page);
+ for_each_free_object(p, s, page->freelist)
+ set_bit(slab_index(p, s, addr), map);
+
+ for_each_object(p, s, addr, page->objects) {
+
+ if (!test_bit(slab_index(p, s, addr), map)) {
+ printk(KERN_ERR "INFO: Object 0x%p @offset=%tu\n",
+ p, p - addr);
+ print_tracking(s, p);
+ }
+ }
+ slab_unlock(page);
+#endif
+}
+
+/*
+ * Attempt to free all partial slabs on a node.
+ */
+static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
+{
unsigned long flags;
struct page *page, *h;
spin_lock_irqsave(&n->list_lock, flags);
- list_for_each_entry_safe(page, h, list, lru)
+ list_for_each_entry_safe(page, h, &n->partial, lru) {
if (!page->inuse) {
list_del(&page->lru);
discard_slab(s, page);
- } else
- slabs_inuse++;
+ n->nr_partial--;
+ } else {
+ list_slab_objects(s, page,
+ "Objects remaining on kmem_cache_close()");
+ }
+ }
spin_unlock_irqrestore(&n->list_lock, flags);
- return slabs_inuse;
}
/*
@@ -2403,8 +2453,8 @@
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
- n->nr_partial -= free_list(s, n, &n->partial);
- if (slabs_node(s, node))
+ free_partial(s, n);
+ if (n->nr_partial || slabs_node(s, node))
return 1;
}
free_kmem_cache_nodes(s);
@@ -2422,8 +2472,11 @@
if (!s->refcount) {
list_del(&s->list);
up_write(&slub_lock);
- if (kmem_cache_close(s))
- WARN_ON(1);
+ if (kmem_cache_close(s)) {
+ printk(KERN_ERR "SLUB %s: %s called for cache that "
+ "still has objects.\n", s->name, __func__);
+ dump_stack();
+ }
sysfs_slab_remove(s);
} else
up_write(&slub_lock);
@@ -2482,7 +2535,7 @@
down_write(&slub_lock);
if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
- flags | __KMALLOC_CACHE, NULL))
+ flags, NULL))
goto panic;
list_add(&s->list, &slab_caches);
@@ -2730,8 +2783,9 @@
struct kmem_cache_node *n;
struct page *page;
struct page *t;
+ int objects = oo_objects(s->max);
struct list_head *slabs_by_inuse =
- kmalloc(sizeof(struct list_head) * s->objects, GFP_KERNEL);
+ kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL);
unsigned long flags;
if (!slabs_by_inuse)
@@ -2744,7 +2798,7 @@
if (!n->nr_partial)
continue;
- for (i = 0; i < s->objects; i++)
+ for (i = 0; i < objects; i++)
INIT_LIST_HEAD(slabs_by_inuse + i);
spin_lock_irqsave(&n->list_lock, flags);
@@ -2776,7 +2830,7 @@
* Rebuild the partial list with the slabs filled up most
* first and the least used slabs at the end.
*/
- for (i = s->objects - 1; i >= 0; i--)
+ for (i = objects - 1; i >= 0; i--)
list_splice(slabs_by_inuse + i, n->partial.prev);
spin_unlock_irqrestore(&n->list_lock, flags);
@@ -2997,9 +3051,6 @@
if (slub_nomerge || (s->flags & SLUB_NEVER_MERGE))
return 1;
- if ((s->flags & __PAGE_ALLOC_FALLBACK))
- return 1;
-
if (s->ctor)
return 1;
@@ -3192,7 +3243,8 @@
}
#if (defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)) || defined(CONFIG_SLABINFO)
-static unsigned long count_partial(struct kmem_cache_node *n)
+static unsigned long count_partial(struct kmem_cache_node *n,
+ int (*get_count)(struct page *))
{
unsigned long flags;
unsigned long x = 0;
@@ -3200,10 +3252,25 @@
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->partial, lru)
- x += page->inuse;
+ x += get_count(page);
spin_unlock_irqrestore(&n->list_lock, flags);
return x;
}
+
+static int count_inuse(struct page *page)
+{
+ return page->inuse;
+}
+
+static int count_total(struct page *page)
+{
+ return page->objects;
+}
+
+static int count_free(struct page *page)
+{
+ return page->objects - page->inuse;
+}
#endif
#if defined(CONFIG_SYSFS) && defined(CONFIG_SLUB_DEBUG)
@@ -3218,7 +3285,7 @@
return 0;
/* Now we know that a valid freelist exists */
- bitmap_zero(map, s->objects);
+ bitmap_zero(map, page->objects);
for_each_free_object(p, s, page->freelist) {
set_bit(slab_index(p, s, addr), map);
@@ -3226,7 +3293,7 @@
return 0;
}
- for_each_object(p, s, addr)
+ for_each_object(p, s, addr, page->objects)
if (!test_bit(slab_index(p, s, addr), map))
if (!check_object(s, page, p, 1))
return 0;
@@ -3292,7 +3359,7 @@
{
int node;
unsigned long count = 0;
- unsigned long *map = kmalloc(BITS_TO_LONGS(s->objects) *
+ unsigned long *map = kmalloc(BITS_TO_LONGS(oo_objects(s->max)) *
sizeof(unsigned long), GFP_KERNEL);
if (!map)
@@ -3495,14 +3562,14 @@
struct page *page, enum track_item alloc)
{
void *addr = page_address(page);
- DECLARE_BITMAP(map, s->objects);
+ DECLARE_BITMAP(map, page->objects);
void *p;
- bitmap_zero(map, s->objects);
+ bitmap_zero(map, page->objects);
for_each_free_object(p, s, page->freelist)
set_bit(slab_index(p, s, addr), map);
- for_each_object(p, s, addr)
+ for_each_object(p, s, addr, page->objects)
if (!test_bit(slab_index(p, s, addr), map))
add_location(t, s, get_track(s, p, alloc));
}
@@ -3592,22 +3659,23 @@
}
enum slab_stat_type {
- SL_FULL,
- SL_PARTIAL,
- SL_CPU,
- SL_OBJECTS
+ SL_ALL, /* All slabs */
+ SL_PARTIAL, /* Only partially allocated slabs */
+ SL_CPU, /* Only slabs used for cpu caches */
+ SL_OBJECTS, /* Determine allocated objects not slabs */
+ SL_TOTAL /* Determine object capacity not slabs */
};
-#define SO_FULL (1 << SL_FULL)
+#define SO_ALL (1 << SL_ALL)
#define SO_PARTIAL (1 << SL_PARTIAL)
#define SO_CPU (1 << SL_CPU)
#define SO_OBJECTS (1 << SL_OBJECTS)
+#define SO_TOTAL (1 << SL_TOTAL)
static ssize_t show_slab_objects(struct kmem_cache *s,
char *buf, unsigned long flags)
{
unsigned long total = 0;
- int cpu;
int node;
int x;
unsigned long *nodes;
@@ -3618,56 +3686,60 @@
return -ENOMEM;
per_cpu = nodes + nr_node_ids;
- for_each_possible_cpu(cpu) {
- struct page *page;
- struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
+ if (flags & SO_CPU) {
+ int cpu;
- if (!c)
- continue;
+ for_each_possible_cpu(cpu) {
+ struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
- page = c->page;
- node = c->node;
- if (node < 0)
- continue;
- if (page) {
- if (flags & SO_CPU) {
- if (flags & SO_OBJECTS)
- x = page->inuse;
+ if (!c || c->node < 0)
+ continue;
+
+ if (c->page) {
+ if (flags & SO_TOTAL)
+ x = c->page->objects;
+ else if (flags & SO_OBJECTS)
+ x = c->page->inuse;
else
x = 1;
+
total += x;
- nodes[node] += x;
+ nodes[c->node] += x;
}
- per_cpu[node]++;
+ per_cpu[c->node]++;
}
}
- for_each_node_state(node, N_NORMAL_MEMORY) {
- struct kmem_cache_node *n = get_node(s, node);
+ if (flags & SO_ALL) {
+ for_each_node_state(node, N_NORMAL_MEMORY) {
+ struct kmem_cache_node *n = get_node(s, node);
- if (flags & SO_PARTIAL) {
- if (flags & SO_OBJECTS)
- x = count_partial(n);
+ if (flags & SO_TOTAL)
+ x = atomic_long_read(&n->total_objects);
+ else if (flags & SO_OBJECTS)
+ x = atomic_long_read(&n->total_objects) -
+ count_partial(n, count_free);
+
+ else
+ x = atomic_long_read(&n->nr_slabs);
+ total += x;
+ nodes[node] += x;
+ }
+
+ } else if (flags & SO_PARTIAL) {
+ for_each_node_state(node, N_NORMAL_MEMORY) {
+ struct kmem_cache_node *n = get_node(s, node);
+
+ if (flags & SO_TOTAL)
+ x = count_partial(n, count_total);
+ else if (flags & SO_OBJECTS)
+ x = count_partial(n, count_inuse);
else
x = n->nr_partial;
total += x;
nodes[node] += x;
}
-
- if (flags & SO_FULL) {
- int full_slabs = atomic_long_read(&n->nr_slabs)
- - per_cpu[node]
- - n->nr_partial;
-
- if (flags & SO_OBJECTS)
- x = full_slabs * s->objects;
- else
- x = full_slabs;
- total += x;
- nodes[node] += x;
- }
}
-
x = sprintf(buf, "%lu", total);
#ifdef CONFIG_NUMA
for_each_node_state(node, N_NORMAL_MEMORY)
@@ -3682,14 +3754,6 @@
static int any_slab_objects(struct kmem_cache *s)
{
int node;
- int cpu;
-
- for_each_possible_cpu(cpu) {
- struct kmem_cache_cpu *c = get_cpu_slab(s, cpu);
-
- if (c && c->page)
- return 1;
- }
for_each_online_node(node) {
struct kmem_cache_node *n = get_node(s, node);
@@ -3697,7 +3761,7 @@
if (!n)
continue;
- if (n->nr_partial || atomic_long_read(&n->nr_slabs))
+ if (atomic_read(&n->total_objects))
return 1;
}
return 0;
@@ -3739,15 +3803,27 @@
static ssize_t objs_per_slab_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", s->objects);
+ return sprintf(buf, "%d\n", oo_objects(s->oo));
}
SLAB_ATTR_RO(objs_per_slab);
+static ssize_t order_store(struct kmem_cache *s,
+ const char *buf, size_t length)
+{
+ int order = simple_strtoul(buf, NULL, 10);
+
+ if (order > slub_max_order || order < slub_min_order)
+ return -EINVAL;
+
+ calculate_sizes(s, order);
+ return length;
+}
+
static ssize_t order_show(struct kmem_cache *s, char *buf)
{
- return sprintf(buf, "%d\n", s->order);
+ return sprintf(buf, "%d\n", oo_order(s->oo));
}
-SLAB_ATTR_RO(order);
+SLAB_ATTR(order);
static ssize_t ctor_show(struct kmem_cache *s, char *buf)
{
@@ -3768,7 +3844,7 @@
static ssize_t slabs_show(struct kmem_cache *s, char *buf)
{
- return show_slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU);
+ return show_slab_objects(s, buf, SO_ALL);
}
SLAB_ATTR_RO(slabs);
@@ -3786,10 +3862,22 @@
static ssize_t objects_show(struct kmem_cache *s, char *buf)
{
- return show_slab_objects(s, buf, SO_FULL|SO_PARTIAL|SO_CPU|SO_OBJECTS);
+ return show_slab_objects(s, buf, SO_ALL|SO_OBJECTS);
}
SLAB_ATTR_RO(objects);
+static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
+{
+ return show_slab_objects(s, buf, SO_PARTIAL|SO_OBJECTS);
+}
+SLAB_ATTR_RO(objects_partial);
+
+static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
+{
+ return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
+}
+SLAB_ATTR_RO(total_objects);
+
static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
{
return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
@@ -3869,7 +3957,7 @@
s->flags &= ~SLAB_RED_ZONE;
if (buf[0] == '1')
s->flags |= SLAB_RED_ZONE;
- calculate_sizes(s);
+ calculate_sizes(s, -1);
return length;
}
SLAB_ATTR(red_zone);
@@ -3888,7 +3976,7 @@
s->flags &= ~SLAB_POISON;
if (buf[0] == '1')
s->flags |= SLAB_POISON;
- calculate_sizes(s);
+ calculate_sizes(s, -1);
return length;
}
SLAB_ATTR(poison);
@@ -3907,7 +3995,7 @@
s->flags &= ~SLAB_STORE_USER;
if (buf[0] == '1')
s->flags |= SLAB_STORE_USER;
- calculate_sizes(s);
+ calculate_sizes(s, -1);
return length;
}
SLAB_ATTR(store_user);
@@ -4038,7 +4126,7 @@
STAT_ATTR(DEACTIVATE_TO_HEAD, deactivate_to_head);
STAT_ATTR(DEACTIVATE_TO_TAIL, deactivate_to_tail);
STAT_ATTR(DEACTIVATE_REMOTE_FREES, deactivate_remote_frees);
-
+STAT_ATTR(ORDER_FALLBACK, order_fallback);
#endif
static struct attribute *slab_attrs[] = {
@@ -4047,6 +4135,8 @@
&objs_per_slab_attr.attr,
&order_attr.attr,
&objects_attr.attr,
+ &objects_partial_attr.attr,
+ &total_objects_attr.attr,
&slabs_attr.attr,
&partial_attr.attr,
&cpu_slabs_attr.attr,
@@ -4089,6 +4179,7 @@
&deactivate_to_head_attr.attr,
&deactivate_to_tail_attr.attr,
&deactivate_remote_frees_attr.attr,
+ &order_fallback_attr.attr,
#endif
NULL
};
@@ -4375,7 +4466,8 @@
unsigned long nr_partials = 0;
unsigned long nr_slabs = 0;
unsigned long nr_inuse = 0;
- unsigned long nr_objs;
+ unsigned long nr_objs = 0;
+ unsigned long nr_free = 0;
struct kmem_cache *s;
int node;
@@ -4389,14 +4481,15 @@
nr_partials += n->nr_partial;
nr_slabs += atomic_long_read(&n->nr_slabs);
- nr_inuse += count_partial(n);
+ nr_objs += atomic_long_read(&n->total_objects);
+ nr_free += count_partial(n, count_free);
}
- nr_objs = nr_slabs * s->objects;
- nr_inuse += (nr_slabs - nr_partials) * s->objects;
+ nr_inuse = nr_objs - nr_free;
seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", s->name, nr_inuse,
- nr_objs, s->size, s->objects, (1 << s->order));
+ nr_objs, s->size, oo_objects(s->oo),
+ (1 << oo_order(s->oo)));
seq_printf(m, " : tunables %4u %4u %4u", 0, 0, 0);
seq_printf(m, " : slabdata %6lu %6lu %6lu", nr_slabs, nr_slabs,
0UL);