* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (34 commits)
m68k: rename global variable vmalloc_end to m68k_vmalloc_end
percpu: add missing per_cpu_ptr_to_phys() definition for UP
percpu: Fix kdump failure if booted with percpu_alloc=page
percpu: make misc percpu symbols unique
percpu: make percpu symbols in ia64 unique
percpu: make percpu symbols in powerpc unique
percpu: make percpu symbols in x86 unique
percpu: make percpu symbols in xen unique
percpu: make percpu symbols in cpufreq unique
percpu: make percpu symbols in oprofile unique
percpu: make percpu symbols in tracer unique
percpu: make percpu symbols under kernel/ and mm/ unique
percpu: remove some sparse warnings
percpu: make alloc_percpu() handle array types
vmalloc: fix use of non-existent percpu variable in put_cpu_var()
this_cpu: Use this_cpu_xx in trace_functions_graph.c
this_cpu: Use this_cpu_xx for ftrace
this_cpu: Use this_cpu_xx in nmi handling
this_cpu: Use this_cpu operations in RCU
this_cpu: Use this_cpu ops for VM statistics
...
Fix up trivial (famous last words) global per-cpu naming conflicts in
arch/x86/kvm/svm.c
mm/slab.c
}
#ifdef CONFIG_PPC64
-
-#ifdef CONFIG_HUGETLB_PAGE
-#define is_huge_psize(pagesize) (HPAGE_SHIFT && mmu_huge_psizes[pagesize])
-#else
-#define is_huge_psize(pagesize) 0
-#endif
-
/*
* On 64-bit we don't want to invoke hash_page on user addresses from
* interrupt context, so if the access faults, we read the page tables
{
pgd_t *pgdir;
pte_t *ptep, pte;
- int pagesize;
+ unsigned shift;
unsigned long addr = (unsigned long) ptr;
unsigned long offset;
unsigned long pfn;
if (!pgdir)
return -EFAULT;
- pagesize = get_slice_psize(current->mm, addr);
+ ptep = find_linux_pte_or_hugepte(pgdir, addr, &shift);
+ if (!shift)
+ shift = PAGE_SHIFT;
/* align address to page boundary */
- offset = addr & ((1ul << mmu_psize_defs[pagesize].shift) - 1);
+ offset = addr & ((1UL << shift) - 1);
addr -= offset;
- if (is_huge_psize(pagesize))
- ptep = huge_pte_offset(current->mm, addr);
- else
- ptep = find_linux_pte(pgdir, addr);
-
if (ptep == NULL)
return -EFAULT;
pte = *ptep;
* Since we can't get PMU interrupts inside a PMU interrupt handler,
* we don't need separate irq and nmi entries here.
*/
- static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
+ static DEFINE_PER_CPU(struct perf_callchain_entry, cpu_perf_callchain);
struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
{
- struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
+ struct perf_callchain_entry *entry = &__get_cpu_var(cpu_perf_callchain);
entry->nr = 0;
#endif /* CONFIG_TAU */
#ifdef CONFIG_SMP
- DEFINE_PER_CPU(unsigned int, pvr);
+ DEFINE_PER_CPU(unsigned int, cpu_pvr);
#endif
static int show_cpuinfo(struct seq_file *m, void *v)
}
#ifdef CONFIG_SMP
- pvr = per_cpu(pvr, cpu_id);
+ pvr = per_cpu(cpu_pvr, cpu_id);
#else
pvr = mfspr(SPRN_PVR);
#endif
#ifdef CONFIG_DEBUG_FS
struct dentry *powerpc_debugfs_root;
+EXPORT_SYMBOL(powerpc_debugfs_root);
static int powerpc_debugfs_init(void)
{
static void stop_this_cpu(void *dummy)
{
+ /* Remove this CPU */
+ set_cpu_online(smp_processor_id(), false);
+
local_irq_disable();
while (1)
;
static void __devinit smp_store_cpu_info(int id)
{
- per_cpu(pvr, id) = mfspr(SPRN_PVR);
+ per_cpu(cpu_pvr, id) = mfspr(SPRN_PVR);
}
static void __init smp_create_idle(unsigned int cpu)
struct device_node *node;
};
- static DEFINE_PER_CPU(struct iic, iic);
+ static DEFINE_PER_CPU(struct iic, cpu_iic);
#define IIC_NODE_COUNT 2
static struct irq_host *iic_host;
static void iic_eoi(unsigned int irq)
{
- struct iic *iic = &__get_cpu_var(iic);
+ struct iic *iic = &__get_cpu_var(cpu_iic);
out_be64(&iic->regs->prio, iic->eoi_stack[--iic->eoi_ptr]);
BUG_ON(iic->eoi_ptr < 0);
}
static struct irq_chip iic_chip = {
- .typename = " CELL-IIC ",
+ .name = " CELL-IIC ",
.mask = iic_mask,
.unmask = iic_unmask,
.eoi = iic_eoi,
static struct irq_chip iic_ioexc_chip = {
- .typename = " CELL-IOEX",
+ .name = " CELL-IOEX",
.mask = iic_mask,
.unmask = iic_unmask,
.eoi = iic_ioexc_eoi,
struct iic *iic;
unsigned int virq;
- iic = &__get_cpu_var(iic);
+ iic = &__get_cpu_var(cpu_iic);
*(unsigned long *) &pending =
in_be64((u64 __iomem *) &iic->regs->pending_destr);
if (!(pending.flags & CBE_IIC_IRQ_VALID))
void iic_setup_cpu(void)
{
- out_be64(&__get_cpu_var(iic).regs->prio, 0xff);
+ out_be64(&__get_cpu_var(cpu_iic).regs->prio, 0xff);
}
u8 iic_get_target_id(int cpu)
{
- return per_cpu(iic, cpu).target_id;
+ return per_cpu(cpu_iic, cpu).target_id;
}
EXPORT_SYMBOL_GPL(iic_get_target_id);
void iic_cause_IPI(int cpu, int mesg)
{
- out_be64(&per_cpu(iic, cpu).regs->generate, (0xf - mesg) << 4);
+ out_be64(&per_cpu(cpu_iic, cpu).regs->generate, (0xf - mesg) << 4);
}
struct irq_host *iic_get_irq_host(int node)
}
static int iic_host_xlate(struct irq_host *h, struct device_node *ct,
- u32 *intspec, unsigned int intsize,
+ const u32 *intspec, unsigned int intsize,
irq_hw_number_t *out_hwirq, unsigned int *out_flags)
{
/* XXX FIXME: should locate the linux CPU number from the HW cpu
* number properly. We are lucky for now
*/
- struct iic *iic = &per_cpu(iic, hw_cpu);
+ struct iic *iic = &per_cpu(cpu_iic, hw_cpu);
iic->regs = ioremap(addr, sizeof(struct cbe_iic_thread_regs));
BUG_ON(iic->regs == NULL);
int unknown_nmi_panic;
int nmi_watchdog_enabled;
-static cpumask_t backtrace_mask __read_mostly;
+/* For reliability, we're prepared to waste bits here. */
+static DECLARE_BITMAP(backtrace_mask, NR_CPUS) __read_mostly;
/* nmi_active:
* >0: the lapic NMI watchdog is active, but can be disabled
*/
static DEFINE_PER_CPU(unsigned, last_irq_sum);
- static DEFINE_PER_CPU(local_t, alert_counter);
+ static DEFINE_PER_CPU(long, alert_counter);
static DEFINE_PER_CPU(int, nmi_touch);
void touch_nmi_watchdog(void)
}
/* We can be called before check_nmi_watchdog, hence NULL check. */
- if (cpumask_test_cpu(cpu, &backtrace_mask)) {
+ if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
static DEFINE_SPINLOCK(lock); /* Serialise the printks */
spin_lock(&lock);
show_regs(regs);
dump_stack();
spin_unlock(&lock);
- cpumask_clear_cpu(cpu, &backtrace_mask);
+ cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
rc = 1;
}
* Ayiee, looks like this CPU is stuck ...
* wait a few IRQs (5 seconds) before doing the oops ...
*/
- local_inc(&__get_cpu_var(alert_counter));
- if (local_read(&__get_cpu_var(alert_counter)) == 5 * nmi_hz)
+ __this_cpu_inc(per_cpu_var(alert_counter));
+ if (__this_cpu_read(per_cpu_var(alert_counter)) == 5 * nmi_hz)
/*
* die_nmi will return ONLY if NOTIFY_STOP happens..
*/
regs, panic_on_timeout);
} else {
__get_cpu_var(last_irq_sum) = sum;
- local_set(&__get_cpu_var(alert_counter), 0);
+ __this_cpu_write(per_cpu_var(alert_counter), 0);
}
/* see if the nmi watchdog went off */
{
int i;
- cpumask_copy(&backtrace_mask, cpu_online_mask);
+ cpumask_copy(to_cpumask(backtrace_mask), cpu_online_mask);
printk(KERN_INFO "sending NMI to all CPUs:\n");
apic->send_IPI_all(NMI_VECTOR);
/* Wait for up to 10 seconds for all CPUs to do the backtrace */
for (i = 0; i < 10 * 1000; i++) {
- if (cpumask_empty(&backtrace_mask))
+ if (cpumask_empty(to_cpumask(backtrace_mask)))
break;
mdelay(1);
}
static void __cpuinit default_init(struct cpuinfo_x86 *c)
{
#ifdef CONFIG_X86_64
- display_cacheinfo(c);
+ cpu_detect_cache_sizes(c);
#else
/* Not much we can do here... */
/* Check if at least it has cpuid */
}
}
-void __cpuinit display_cacheinfo(struct cpuinfo_x86 *c)
+void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
{
unsigned int n, dummy, ebx, ecx, edx, l2size;
if (n >= 0x80000005) {
cpuid(0x80000005, &dummy, &ebx, &ecx, &edx);
- printk(KERN_INFO "CPU: L1 I Cache: %dK (%d bytes/line), D cache %dK (%d bytes/line)\n",
- edx>>24, edx&0xFF, ecx>>24, ecx&0xFF);
c->x86_cache_size = (ecx>>24) + (edx>>24);
#ifdef CONFIG_X86_64
/* On K8 L1 TLB is inclusive, so don't count it */
#endif
c->x86_cache_size = l2size;
-
- printk(KERN_INFO "CPU: L2 Cache: %dK (%d bytes/line)\n",
- l2size, ecx & 0xFF);
}
void __cpuinit detect_ht(struct cpuinfo_x86 *c)
const struct cpu_dev *const *cdev;
int count = 0;
+#ifdef PROCESSOR_SELECT
printk(KERN_INFO "KERNEL supported cpus:\n");
+#endif
+
for (cdev = __x86_cpu_dev_start; cdev < __x86_cpu_dev_end; cdev++) {
const struct cpu_dev *cpudev = *cdev;
- unsigned int j;
if (count >= X86_VENDOR_NUM)
break;
cpu_devs[count] = cpudev;
count++;
- for (j = 0; j < 2; j++) {
- if (!cpudev->c_ident[j])
- continue;
- printk(KERN_INFO " %s %s\n", cpudev->c_vendor,
- cpudev->c_ident[j]);
+#ifdef PROCESSOR_SELECT
+ {
+ unsigned int j;
+
+ for (j = 0; j < 2; j++) {
+ if (!cpudev->c_ident[j])
+ continue;
+ printk(KERN_INFO " %s %s\n", cpudev->c_vendor,
+ cpudev->c_ident[j]);
+ }
}
+#endif
}
-
early_identify_cpu(&boot_cpu_data);
}
boot_cpu_data.x86_capability[i] &= c->x86_capability[i];
}
-#ifdef CONFIG_X86_MCE
/* Init Machine Check Exception if available. */
- mcheck_init(c);
-#endif
+ mcheck_cpu_init(c);
select_idle_routine(c);
void __cpuinit cpu_init(void)
{
- struct orig_ist *orig_ist;
+ struct orig_ist *oist;
struct task_struct *me;
struct tss_struct *t;
unsigned long v;
cpu = stack_smp_processor_id();
t = &per_cpu(init_tss, cpu);
- orig_ist = &per_cpu(orig_ist, cpu);
+ oist = &per_cpu(orig_ist, cpu);
#ifdef CONFIG_NUMA
if (cpu != 0 && percpu_read(node_number) == 0 &&
wrmsrl(MSR_KERNEL_GS_BASE, 0);
barrier();
- check_efer();
+ x86_configure_nx();
if (cpu != 0)
enable_x2apic();
/*
* set up and load the per-CPU TSS
*/
- if (!orig_ist->ist[0]) {
+ if (!oist->ist[0]) {
char *estacks = per_cpu(exception_stacks, cpu);
for (v = 0; v < N_EXCEPTION_STACKS; v++) {
estacks += exception_stack_sizes[v];
- orig_ist->ist[v] = t->x86_tss.ist[v] =
+ oist->ist[v] = t->x86_tss.ist[v] =
(unsigned long)estacks;
}
}
unsigned int cpu_feature;
};
- static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+ static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
- static DEFINE_PER_CPU(struct aperfmperf, old_perf);
+ static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance *acpi_perf_data;
if (unlikely(cpumask_empty(mask)))
return 0;
- switch (per_cpu(drv_data, cpumask_first(mask))->cpu_feature) {
+ switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
case SYSTEM_INTEL_MSR_CAPABLE:
cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
break;
case SYSTEM_IO_CAPABLE:
cmd.type = SYSTEM_IO_CAPABLE;
- perf = per_cpu(drv_data, cpumask_first(mask))->acpi_data;
+ perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
cmd.addr.io.port = perf->control_register.address;
cmd.addr.io.bit_width = perf->control_register.bit_width;
break;
if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
return 0;
- ratio = calc_aperfmperf_ratio(&per_cpu(old_perf, cpu), &perf);
- per_cpu(old_perf, cpu) = perf;
+ ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
+ per_cpu(acfreq_old_perf, cpu) = perf;
retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
unsigned int freq;
unsigned int cached_freq;
static int acpi_cpufreq_target(struct cpufreq_policy *policy,
unsigned int target_freq, unsigned int relation)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
struct acpi_processor_performance *perf;
struct cpufreq_freqs freqs;
struct drv_cmd cmd;
static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
dprintk("acpi_cpufreq_verify\n");
static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
{
- /* http://www.intel.com/Assets/PDF/specupdate/314554.pdf
+ /* Intel Xeon Processor 7100 Series Specification Update
+ * http://www.intel.com/Assets/PDF/specupdate/314554.pdf
* AL30: A Machine Check Exception (MCE) Occurring during an
* Enhanced Intel SpeedStep Technology Ratio Change May Cause
- * Both Processor Cores to Lock Up when HT is enabled*/
+ * Both Processor Cores to Lock Up. */
if (c->x86_vendor == X86_VENDOR_INTEL) {
if ((c->x86 == 15) &&
(c->x86_model == 6) &&
- (c->x86_mask == 8) && smt_capable())
+ (c->x86_mask == 8)) {
+ printk(KERN_INFO "acpi-cpufreq: Intel(R) "
+ "Xeon(R) 7100 Errata AL30, processors may "
+ "lock up on frequency changes: disabling "
+ "acpi-cpufreq.\n");
return -ENODEV;
+ }
}
return 0;
}
unsigned int result = 0;
struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
struct acpi_processor_performance *perf;
+#ifdef CONFIG_SMP
+ static int blacklisted;
+#endif
dprintk("acpi_cpufreq_cpu_init\n");
#ifdef CONFIG_SMP
- result = acpi_cpufreq_blacklist(c);
- if (result)
- return result;
+ if (blacklisted)
+ return blacklisted;
+ blacklisted = acpi_cpufreq_blacklist(c);
+ if (blacklisted)
+ return blacklisted;
#endif
data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
return -ENOMEM;
data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
- per_cpu(drv_data, cpu) = data;
+ per_cpu(acfreq_data, cpu) = data;
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
acpi_processor_unregister_performance(perf, cpu);
err_free:
kfree(data);
- per_cpu(drv_data, cpu) = NULL;
+ per_cpu(acfreq_data, cpu) = NULL;
return result;
}
static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
dprintk("acpi_cpufreq_cpu_exit\n");
if (data) {
cpufreq_frequency_table_put_attr(policy->cpu);
- per_cpu(drv_data, policy->cpu) = NULL;
+ per_cpu(acfreq_data, policy->cpu) = NULL;
acpi_processor_unregister_performance(data->acpi_data,
policy->cpu);
kfree(data);
static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
dprintk("acpi_cpufreq_resume\n");
};
static struct cpufreq_driver acpi_cpufreq_driver = {
- .verify = acpi_cpufreq_verify,
- .target = acpi_cpufreq_target,
- .init = acpi_cpufreq_cpu_init,
- .exit = acpi_cpufreq_cpu_exit,
- .resume = acpi_cpufreq_resume,
- .name = "acpi-cpufreq",
- .owner = THIS_MODULE,
- .attr = acpi_cpufreq_attr,
+ .verify = acpi_cpufreq_verify,
+ .target = acpi_cpufreq_target,
+ .bios_limit = acpi_processor_get_bios_limit,
+ .init = acpi_cpufreq_cpu_init,
+ .exit = acpi_cpufreq_cpu_exit,
+ .resume = acpi_cpufreq_resume,
+ .name = "acpi-cpufreq",
+ .owner = THIS_MODULE,
+ .attr = acpi_cpufreq_attr,
};
static int __init acpi_cpufreq_init(void)
{ 0xd1, LVL_3, 1024 }, /* 4-way set assoc, 64 byte line size */
{ 0xd2, LVL_3, 2048 }, /* 4-way set assoc, 64 byte line size */
{ 0xd6, LVL_3, 1024 }, /* 8-way set assoc, 64 byte line size */
- { 0xd7, LVL_3, 2038 }, /* 8-way set assoc, 64 byte line size */
+ { 0xd7, LVL_3, 2048 }, /* 8-way set assoc, 64 byte line size */
{ 0xd8, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */
{ 0xdc, LVL_3, 2048 }, /* 12-way set assoc, 64 byte line size */
{ 0xdd, LVL_3, 4096 }, /* 12-way set assoc, 64 byte line size */
{ 0xe2, LVL_3, 2048 }, /* 16-way set assoc, 64 byte line size */
{ 0xe3, LVL_3, 4096 }, /* 16-way set assoc, 64 byte line size */
{ 0xe4, LVL_3, 8192 }, /* 16-way set assoc, 64 byte line size */
+ { 0xea, LVL_3, 12288 }, /* 24-way set assoc, 64 byte line size */
+ { 0xeb, LVL_3, 18432 }, /* 24-way set assoc, 64 byte line size */
+ { 0xec, LVL_3, 24576 }, /* 24-way set assoc, 64 byte line size */
{ 0x00, 0, 0}
};
#endif
}
- if (trace)
- printk(KERN_INFO "CPU: Trace cache: %dK uops", trace);
- else if (l1i)
- printk(KERN_INFO "CPU: L1 I cache: %dK", l1i);
-
- if (l1d)
- printk(KERN_CONT ", L1 D cache: %dK\n", l1d);
- else
- printk(KERN_CONT "\n");
-
- if (l2)
- printk(KERN_INFO "CPU: L2 cache: %dK\n", l2);
-
- if (l3)
- printk(KERN_INFO "CPU: L3 cache: %dK\n", l3);
-
c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
return l2;
#ifdef CONFIG_SYSFS
/* pointer to _cpuid4_info array (for each cache leaf) */
- static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
- #define CPUID4_INFO_IDX(x, y) (&((per_cpu(cpuid4_info, x))[y]))
+ static DEFINE_PER_CPU(struct _cpuid4_info *, ici_cpuid4_info);
+ #define CPUID4_INFO_IDX(x, y) (&((per_cpu(ici_cpuid4_info, x))[y]))
#ifdef CONFIG_SMP
static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
if ((index == 3) && (c->x86_vendor == X86_VENDOR_AMD)) {
struct cpuinfo_x86 *d;
for_each_online_cpu(i) {
- if (!per_cpu(cpuid4_info, i))
+ if (!per_cpu(ici_cpuid4_info, i))
continue;
d = &cpu_data(i);
this_leaf = CPUID4_INFO_IDX(i, index);
c->apicid >> index_msb) {
cpumask_set_cpu(i,
to_cpumask(this_leaf->shared_cpu_map));
- if (i != cpu && per_cpu(cpuid4_info, i)) {
+ if (i != cpu && per_cpu(ici_cpuid4_info, i)) {
sibling_leaf =
CPUID4_INFO_IDX(i, index);
cpumask_set_cpu(cpu, to_cpumask(
for (i = 0; i < num_cache_leaves; i++)
cache_remove_shared_cpu_map(cpu, i);
- kfree(per_cpu(cpuid4_info, cpu));
- per_cpu(cpuid4_info, cpu) = NULL;
+ kfree(per_cpu(ici_cpuid4_info, cpu));
+ per_cpu(ici_cpuid4_info, cpu) = NULL;
}
static int
if (num_cache_leaves == 0)
return -ENOENT;
- per_cpu(cpuid4_info, cpu) = kzalloc(
+ per_cpu(ici_cpuid4_info, cpu) = kzalloc(
sizeof(struct _cpuid4_info) * num_cache_leaves, GFP_KERNEL);
- if (per_cpu(cpuid4_info, cpu) == NULL)
+ if (per_cpu(ici_cpuid4_info, cpu) == NULL)
return -ENOMEM;
smp_call_function_single(cpu, get_cpu_leaves, &retval, true);
if (retval) {
- kfree(per_cpu(cpuid4_info, cpu));
- per_cpu(cpuid4_info, cpu) = NULL;
+ kfree(per_cpu(ici_cpuid4_info, cpu));
+ per_cpu(ici_cpuid4_info, cpu) = NULL;
}
return retval;
extern struct sysdev_class cpu_sysdev_class; /* from drivers/base/cpu.c */
/* pointer to kobject for cpuX/cache */
- static DEFINE_PER_CPU(struct kobject *, cache_kobject);
+ static DEFINE_PER_CPU(struct kobject *, ici_cache_kobject);
struct _index_kobject {
struct kobject kobj;
};
/* pointer to array of kobjects for cpuX/cache/indexY */
- static DEFINE_PER_CPU(struct _index_kobject *, index_kobject);
- #define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(index_kobject, x))[y]))
+ static DEFINE_PER_CPU(struct _index_kobject *, ici_index_kobject);
+ #define INDEX_KOBJECT_PTR(x, y) (&((per_cpu(ici_index_kobject, x))[y]))
#define show_one_plus(file_name, object, val) \
static ssize_t show_##file_name \
static void __cpuinit cpuid4_cache_sysfs_exit(unsigned int cpu)
{
- kfree(per_cpu(cache_kobject, cpu));
- kfree(per_cpu(index_kobject, cpu));
- per_cpu(cache_kobject, cpu) = NULL;
- per_cpu(index_kobject, cpu) = NULL;
+ kfree(per_cpu(ici_cache_kobject, cpu));
+ kfree(per_cpu(ici_index_kobject, cpu));
+ per_cpu(ici_cache_kobject, cpu) = NULL;
+ per_cpu(ici_index_kobject, cpu) = NULL;
free_cache_attributes(cpu);
}
return err;
/* Allocate all required memory */
- per_cpu(cache_kobject, cpu) =
+ per_cpu(ici_cache_kobject, cpu) =
kzalloc(sizeof(struct kobject), GFP_KERNEL);
- if (unlikely(per_cpu(cache_kobject, cpu) == NULL))
+ if (unlikely(per_cpu(ici_cache_kobject, cpu) == NULL))
goto err_out;
- per_cpu(index_kobject, cpu) = kzalloc(
+ per_cpu(ici_index_kobject, cpu) = kzalloc(
sizeof(struct _index_kobject) * num_cache_leaves, GFP_KERNEL);
- if (unlikely(per_cpu(index_kobject, cpu) == NULL))
+ if (unlikely(per_cpu(ici_index_kobject, cpu) == NULL))
goto err_out;
return 0;
if (unlikely(retval < 0))
return retval;
- retval = kobject_init_and_add(per_cpu(cache_kobject, cpu),
+ retval = kobject_init_and_add(per_cpu(ici_cache_kobject, cpu),
&ktype_percpu_entry,
&sys_dev->kobj, "%s", "cache");
if (retval < 0) {
this_object->index = i;
retval = kobject_init_and_add(&(this_object->kobj),
&ktype_cache,
- per_cpu(cache_kobject, cpu),
+ per_cpu(ici_cache_kobject, cpu),
"index%1lu", i);
if (unlikely(retval)) {
for (j = 0; j < i; j++)
kobject_put(&(INDEX_KOBJECT_PTR(cpu, j)->kobj));
- kobject_put(per_cpu(cache_kobject, cpu));
+ kobject_put(per_cpu(ici_cache_kobject, cpu));
cpuid4_cache_sysfs_exit(cpu);
return retval;
}
}
cpumask_set_cpu(cpu, to_cpumask(cache_dev_map));
- kobject_uevent(per_cpu(cache_kobject, cpu), KOBJ_ADD);
+ kobject_uevent(per_cpu(ici_cache_kobject, cpu), KOBJ_ADD);
return 0;
}
unsigned int cpu = sys_dev->id;
unsigned long i;
- if (per_cpu(cpuid4_info, cpu) == NULL)
+ if (per_cpu(ici_cpuid4_info, cpu) == NULL)
return;
if (!cpumask_test_cpu(cpu, to_cpumask(cache_dev_map)))
return;
for (i = 0; i < num_cache_leaves; i++)
kobject_put(&(INDEX_KOBJECT_PTR(cpu, i)->kobj));
- kobject_put(per_cpu(cache_kobject, cpu));
+ kobject_put(per_cpu(ici_cache_kobject, cpu));
cpuid4_cache_sysfs_exit(cpu);
}
#define SVM_FEATURE_NPT (1 << 0)
#define SVM_FEATURE_LBRV (1 << 1)
#define SVM_FEATURE_SVML (1 << 2)
+#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
#define NESTED_EXIT_DONE 1 /* Exit caused nested vmexit */
#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
-/* Turn on to get debugging output*/
-/* #define NESTED_DEBUG */
-
-#ifdef NESTED_DEBUG
-#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args)
-#else
-#define nsvm_printk(fmt, args...) do {} while(0)
-#endif
-
static const u32 host_save_user_msrs[] = {
#ifdef CONFIG_X86_64
MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
/* gpa pointers to the real vectors */
u64 vmcb_msrpm;
+ /* A VMEXIT is required but not yet emulated */
+ bool exit_required;
+
/* cache for intercepts of the guest */
u16 intercept_cr_read;
u16 intercept_cr_write;
u32 *msrpm;
struct nested_state nested;
+
+ bool nmi_singlestep;
};
/* enable NPT for AMD64 and X86 with PAE */
struct vcpu_svm *svm = to_svm(vcpu);
if (!svm->next_rip) {
- if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) !=
+ if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
EMULATE_DONE)
printk(KERN_DEBUG "%s: NOP\n", __func__);
return;
cpu_svm_disable();
}
-static void svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void *garbage)
{
- struct svm_cpu_data *svm_data;
+ struct svm_cpu_data *sd;
uint64_t efer;
struct descriptor_table gdt_descr;
struct desc_struct *gdt;
int me = raw_smp_processor_id();
+ rdmsrl(MSR_EFER, efer);
+ if (efer & EFER_SVME)
+ return -EBUSY;
+
if (!has_svm()) {
- printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me);
- return;
+ printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n",
+ me);
+ return -EINVAL;
}
- svm_data = per_cpu(svm_data, me);
+ sd = per_cpu(svm_data, me);
- if (!svm_data) {
+ if (!sd) {
- printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n",
+ printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n",
me);
- return;
+ return -EINVAL;
}
- svm_data->asid_generation = 1;
- svm_data->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
- svm_data->next_asid = svm_data->max_asid + 1;
+ sd->asid_generation = 1;
+ sd->max_asid = cpuid_ebx(SVM_CPUID_FUNC) - 1;
+ sd->next_asid = sd->max_asid + 1;
kvm_get_gdt(&gdt_descr);
gdt = (struct desc_struct *)gdt_descr.base;
- svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
+ sd->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
- rdmsrl(MSR_EFER, efer);
wrmsrl(MSR_EFER, efer | EFER_SVME);
-- wrmsrl(MSR_VM_HSAVE_PA,
- page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
- page_to_pfn(sd->save_area) << PAGE_SHIFT);
++ wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
+
+ return 0;
}
static void svm_cpu_uninit(int cpu)
{
- struct svm_cpu_data *svm_data
- = per_cpu(svm_data, raw_smp_processor_id());
+ struct svm_cpu_data *sd = per_cpu(svm_data, raw_smp_processor_id());
- if (!svm_data)
+ if (!sd)
return;
per_cpu(svm_data, raw_smp_processor_id()) = NULL;
- __free_page(svm_data->save_area);
- kfree(svm_data);
+ __free_page(sd->save_area);
+ kfree(sd);
}
static int svm_cpu_init(int cpu)
{
- struct svm_cpu_data *svm_data;
+ struct svm_cpu_data *sd;
int r;
- svm_data = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
- if (!svm_data)
+ sd = kzalloc(sizeof(struct svm_cpu_data), GFP_KERNEL);
+ if (!sd)
return -ENOMEM;
- svm_data->cpu = cpu;
- svm_data->save_area = alloc_page(GFP_KERNEL);
+ sd->cpu = cpu;
+ sd->save_area = alloc_page(GFP_KERNEL);
r = -ENOMEM;
- if (!svm_data->save_area)
+ if (!sd->save_area)
goto err_1;
- per_cpu(svm_data, cpu) = svm_data;
+ per_cpu(svm_data, cpu) = sd;
return 0;
err_1:
- kfree(svm_data);
+ kfree(sd);
return r;
}
kvm_enable_efer_bits(EFER_SVME);
}
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
r = svm_cpu_init(cpu);
if (r)
goto err;
{
int cpu;
- for_each_online_cpu(cpu)
+ for_each_possible_cpu(cpu)
svm_cpu_uninit(cpu);
__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
save->rip = 0x0000fff0;
svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
- /*
- * cr0 val on cpu init should be 0x60000010, we enable cpu
- * cache by default. the orderly way is to enable cache in bios.
+ /* This is the guest-visible cr0 value.
+ * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
*/
- save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
+ svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+ kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0);
+
save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
INTERCEPT_CR3_MASK);
save->g_pat = 0x0007040600070406ULL;
- /* enable caching because the QEMU Bios doesn't enable it */
- save->cr0 = X86_CR0_ET;
save->cr3 = 0;
save->cr4 = 0;
}
svm->nested.vmcb = 0;
svm->vcpu.arch.hflags = 0;
+ if (svm_has(SVM_FEATURE_PAUSE_FILTER)) {
+ control->pause_filter_count = 3000;
+ control->intercept |= (1ULL << INTERCEPT_PAUSE);
+ }
+
enable_gif(svm);
}
int i;
if (unlikely(cpu != vcpu->cpu)) {
- u64 tsc_this, delta;
+ u64 delta;
/*
* Make sure that the guest sees a monotonically
* increasing TSC.
*/
- rdtscll(tsc_this);
- delta = vcpu->arch.host_tsc - tsc_this;
+ delta = vcpu->arch.host_tsc - native_read_tsc();
svm->vmcb->control.tsc_offset += delta;
+ if (is_nested(svm))
+ svm->nested.hsave->control.tsc_offset += delta;
vcpu->cpu = cpu;
kvm_migrate_timers(vcpu);
svm->asid_generation = 0;
for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
- rdtscll(vcpu->arch.host_tsc);
+ vcpu->arch.host_tsc = native_read_tsc();
}
static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
svm->vmcb->control.intercept_exceptions &=
~((1 << DB_VECTOR) | (1 << BP_VECTOR));
- if (vcpu->arch.singlestep)
+ if (svm->nmi_singlestep)
svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR);
if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
vcpu->guest_debug = 0;
}
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
{
- int old_debug = vcpu->guest_debug;
struct vcpu_svm *svm = to_svm(vcpu);
- vcpu->guest_debug = dbg->control;
-
- update_db_intercept(vcpu);
-
if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
else
svm->vmcb->save.dr7 = vcpu->arch.dr7;
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
- svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
- else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
- svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-
- return 0;
+ update_db_intercept(vcpu);
}
static void load_host_msrs(struct kvm_vcpu *vcpu)
#endif
}
- static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *svm_data)
+ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
{
- if (svm_data->next_asid > svm_data->max_asid) {
- ++svm_data->asid_generation;
- svm_data->next_asid = 1;
+ if (sd->next_asid > sd->max_asid) {
+ ++sd->asid_generation;
+ sd->next_asid = 1;
svm->vmcb->control.tlb_ctl = TLB_CONTROL_FLUSH_ALL_ASID;
}
- svm->asid_generation = svm_data->asid_generation;
- svm->vmcb->control.asid = svm_data->next_asid++;
+ svm->asid_generation = sd->asid_generation;
+ svm->vmcb->control.asid = sd->next_asid++;
}
static unsigned long svm_get_dr(struct kvm_vcpu *vcpu, int dr)
}
}
-static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int pf_interception(struct vcpu_svm *svm)
{
u64 fault_address;
u32 error_code;
return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
}
-static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int db_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
if (!(svm->vcpu.guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
- !svm->vcpu.arch.singlestep) {
+ !svm->nmi_singlestep) {
kvm_queue_exception(&svm->vcpu, DB_VECTOR);
return 1;
}
- if (svm->vcpu.arch.singlestep) {
- svm->vcpu.arch.singlestep = false;
+ if (svm->nmi_singlestep) {
+ svm->nmi_singlestep = false;
if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
svm->vmcb->save.rflags &=
~(X86_EFLAGS_TF | X86_EFLAGS_RF);
return 1;
}
-static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int bp_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
kvm_run->exit_reason = KVM_EXIT_DEBUG;
kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
kvm_run->debug.arch.exception = BP_VECTOR;
return 0;
}
-static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int ud_interception(struct vcpu_svm *svm)
{
int er;
- er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD);
+ er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD);
if (er != EMULATE_DONE)
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
}
-static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nm_interception(struct vcpu_svm *svm)
{
svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
if (!(svm->vcpu.arch.cr0 & X86_CR0_TS))
return 1;
}
-static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int mc_interception(struct vcpu_svm *svm)
{
/*
* On an #MC intercept the MCE handler is not called automatically in
return 1;
}
-static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int shutdown_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
/*
* VMCB is undefined after a SHUTDOWN intercept
* so reinitialize it.
return 0;
}
-static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int io_interception(struct vcpu_svm *svm)
{
u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
int size, in, string;
if (string) {
if (emulate_instruction(&svm->vcpu,
- kvm_run, 0, 0, 0) == EMULATE_DO_MMIO)
+ 0, 0, 0) == EMULATE_DO_MMIO)
return 0;
return 1;
}
size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
skip_emulated_instruction(&svm->vcpu);
- return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
+ return kvm_emulate_pio(&svm->vcpu, in, size, port);
}
-static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nmi_interception(struct vcpu_svm *svm)
{
return 1;
}
-static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int intr_interception(struct vcpu_svm *svm)
{
++svm->vcpu.stat.irq_exits;
return 1;
}
-static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nop_on_interception(struct vcpu_svm *svm)
{
return 1;
}
-static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int halt_interception(struct vcpu_svm *svm)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
skip_emulated_instruction(&svm->vcpu);
return kvm_emulate_halt(&svm->vcpu);
}
-static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmmcall_interception(struct vcpu_svm *svm)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
skip_emulated_instruction(&svm->vcpu);
svm->vmcb->control.exit_code = SVM_EXIT_INTR;
- if (nested_svm_exit_handled(svm)) {
- nsvm_printk("VMexit -> INTR\n");
+ if (svm->nested.intercept & 1ULL) {
+ /*
+ * The #vmexit can't be emulated here directly because this
+ * code path runs with irqs and preemtion disabled. A
+ * #vmexit emulation might sleep. Only signal request for
+ * the #vmexit here.
+ */
+ svm->nested.exit_required = true;
+ trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
return 1;
}
{
struct page *page;
- down_read(¤t->mm->mmap_sem);
page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
- up_read(¤t->mm->mmap_sem);
-
if (is_error_page(page))
goto error;
}
default: {
u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
- nsvm_printk("exit code: 0x%x\n", exit_code);
if (svm->nested.intercept & exit_bits)
vmexit = NESTED_EXIT_DONE;
}
}
if (vmexit == NESTED_EXIT_DONE) {
- nsvm_printk("#VMEXIT reason=%04x\n", exit_code);
nested_svm_vmexit(svm);
}
struct vmcb *hsave = svm->nested.hsave;
struct vmcb *vmcb = svm->vmcb;
+ trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
+ vmcb->control.exit_info_1,
+ vmcb->control.exit_info_2,
+ vmcb->control.exit_int_info,
+ vmcb->control.exit_int_info_err);
+
nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0);
if (!nested_vmcb)
return 1;
nested_vmcb->control.exit_info_2 = vmcb->control.exit_info_2;
nested_vmcb->control.exit_int_info = vmcb->control.exit_int_info;
nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err;
+
+ /*
+ * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
+ * to make sure that we do not lose injected events. So check event_inj
+ * here and copy it to exit_int_info if it is valid.
+ * Exit_int_info and event_inj can't be both valid because the case
+ * below only happens on a VMRUN instruction intercept which has
+ * no valid exit_int_info set.
+ */
+ if (vmcb->control.event_inj & SVM_EVTINJ_VALID) {
+ struct vmcb_control_area *nc = &nested_vmcb->control;
+
+ nc->exit_int_info = vmcb->control.event_inj;
+ nc->exit_int_info_err = vmcb->control.event_inj_err;
+ }
+
nested_vmcb->control.tlb_ctl = 0;
nested_vmcb->control.event_inj = 0;
nested_vmcb->control.event_inj_err = 0;
/* Restore the original control entries */
copy_vmcb_control_area(vmcb, hsave);
- /* Kill any pending exceptions */
- if (svm->vcpu.arch.exception.pending == true)
- nsvm_printk("WARNING: Pending Exception\n");
-
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
/* nested_vmcb is our indicator if nested SVM is activated */
svm->nested.vmcb = svm->vmcb->save.rax;
+ trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+ nested_vmcb->save.rip,
+ nested_vmcb->control.int_ctl,
+ nested_vmcb->control.event_inj,
+ nested_vmcb->control.nested_ctl);
+
/* Clear internal status */
kvm_clear_exception_queue(&svm->vcpu);
kvm_clear_interrupt_queue(&svm->vcpu);
svm->nested.intercept = nested_vmcb->control.intercept;
force_new_asid(&svm->vcpu);
- svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info;
- svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err;
svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
- if (nested_vmcb->control.int_ctl & V_IRQ_MASK) {
- nsvm_printk("nSVM Injecting Interrupt: 0x%x\n",
- nested_vmcb->control.int_ctl);
- }
if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
svm->vcpu.arch.hflags |= HF_VINTR_MASK;
else
svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
- nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n",
- nested_vmcb->control.exit_int_info,
- nested_vmcb->control.int_state);
-
svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
svm->vmcb->control.int_state = nested_vmcb->control.int_state;
svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
- if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID)
- nsvm_printk("Injecting Event: 0x%x\n",
- nested_vmcb->control.event_inj);
svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
}
-static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmload_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
return 1;
}
-static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmsave_interception(struct vcpu_svm *svm)
{
struct vmcb *nested_vmcb;
return 1;
}
-static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmrun_interception(struct vcpu_svm *svm)
{
- nsvm_printk("VMrun\n");
-
if (nested_svm_check_permissions(svm))
return 1;
return 1;
}
-static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int stgi_interception(struct vcpu_svm *svm)
{
if (nested_svm_check_permissions(svm))
return 1;
return 1;
}
-static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int clgi_interception(struct vcpu_svm *svm)
{
if (nested_svm_check_permissions(svm))
return 1;
return 1;
}
-static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpga_interception(struct vcpu_svm *svm)
{
struct kvm_vcpu *vcpu = &svm->vcpu;
- nsvm_printk("INVLPGA\n");
+
+ trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX],
+ vcpu->arch.regs[VCPU_REGS_RAX]);
/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
return 1;
}
-static int invalid_op_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int skinit_interception(struct vcpu_svm *svm)
{
+ trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]);
+
kvm_queue_exception(&svm->vcpu, UD_VECTOR);
return 1;
}
-static int task_switch_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int invalid_op_interception(struct vcpu_svm *svm)
+{
+ kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+ return 1;
+}
+
+static int task_switch_interception(struct vcpu_svm *svm)
{
u16 tss_selector;
int reason;
return kvm_task_switch(&svm->vcpu, tss_selector, reason);
}
-static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cpuid_interception(struct vcpu_svm *svm)
{
svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
kvm_emulate_cpuid(&svm->vcpu);
return 1;
}
-static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int iret_interception(struct vcpu_svm *svm)
{
++svm->vcpu.stat.nmi_window_exits;
svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
return 1;
}
-static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpg_interception(struct vcpu_svm *svm)
{
- if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE)
+ if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
return 1;
}
-static int emulate_on_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int emulate_on_interception(struct vcpu_svm *svm)
{
- if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE)
+ if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
return 1;
}
-static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cr8_write_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
/* instruction emulation calls kvm_set_cr8() */
- emulate_instruction(&svm->vcpu, NULL, 0, 0, 0);
+ emulate_instruction(&svm->vcpu, 0, 0, 0);
if (irqchip_in_kernel(svm->vcpu.kvm)) {
svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
return 1;
switch (ecx) {
case MSR_IA32_TSC: {
- u64 tsc;
+ u64 tsc_offset;
- rdtscll(tsc);
- *data = svm->vmcb->control.tsc_offset + tsc;
+ if (is_nested(svm))
+ tsc_offset = svm->nested.hsave->control.tsc_offset;
+ else
+ tsc_offset = svm->vmcb->control.tsc_offset;
+
+ *data = tsc_offset + native_read_tsc();
break;
}
case MSR_K6_STAR:
return 0;
}
-static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int rdmsr_interception(struct vcpu_svm *svm)
{
u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
u64 data;
switch (ecx) {
case MSR_IA32_TSC: {
- u64 tsc;
+ u64 tsc_offset = data - native_read_tsc();
+ u64 g_tsc_offset = 0;
+
+ if (is_nested(svm)) {
+ g_tsc_offset = svm->vmcb->control.tsc_offset -
+ svm->nested.hsave->control.tsc_offset;
+ svm->nested.hsave->control.tsc_offset = tsc_offset;
+ }
+
+ svm->vmcb->control.tsc_offset = tsc_offset + g_tsc_offset;
- rdtscll(tsc);
- svm->vmcb->control.tsc_offset = data - tsc;
break;
}
case MSR_K6_STAR:
return 0;
}
-static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int wrmsr_interception(struct vcpu_svm *svm)
{
u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u)
return 1;
}
-static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int msr_interception(struct vcpu_svm *svm)
{
if (svm->vmcb->control.exit_info_1)
- return wrmsr_interception(svm, kvm_run);
+ return wrmsr_interception(svm);
else
- return rdmsr_interception(svm, kvm_run);
+ return rdmsr_interception(svm);
}
-static int interrupt_window_interception(struct vcpu_svm *svm,
- struct kvm_run *kvm_run)
+static int interrupt_window_interception(struct vcpu_svm *svm)
{
+ struct kvm_run *kvm_run = svm->vcpu.run;
+
svm_clear_vintr(svm);
svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
/*
return 1;
}
-static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
- struct kvm_run *kvm_run) = {
+static int pause_interception(struct vcpu_svm *svm)
+{
+ kvm_vcpu_on_spin(&(svm->vcpu));
+ return 1;
+}
+
+static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
[SVM_EXIT_READ_CR0] = emulate_on_interception,
[SVM_EXIT_READ_CR3] = emulate_on_interception,
[SVM_EXIT_READ_CR4] = emulate_on_interception,
[SVM_EXIT_CPUID] = cpuid_interception,
[SVM_EXIT_IRET] = iret_interception,
[SVM_EXIT_INVD] = emulate_on_interception,
+ [SVM_EXIT_PAUSE] = pause_interception,
[SVM_EXIT_HLT] = halt_interception,
[SVM_EXIT_INVLPG] = invlpg_interception,
[SVM_EXIT_INVLPGA] = invlpga_interception,
[SVM_EXIT_VMSAVE] = vmsave_interception,
[SVM_EXIT_STGI] = stgi_interception,
[SVM_EXIT_CLGI] = clgi_interception,
- [SVM_EXIT_SKINIT] = invalid_op_interception,
+ [SVM_EXIT_SKINIT] = skinit_interception,
[SVM_EXIT_WBINVD] = emulate_on_interception,
[SVM_EXIT_MONITOR] = invalid_op_interception,
[SVM_EXIT_MWAIT] = invalid_op_interception,
[SVM_EXIT_NPF] = pf_interception,
};
-static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int handle_exit(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_run *kvm_run = vcpu->run;
u32 exit_code = svm->vmcb->control.exit_code;
trace_kvm_exit(exit_code, svm->vmcb->save.rip);
+ if (unlikely(svm->nested.exit_required)) {
+ nested_svm_vmexit(svm);
+ svm->nested.exit_required = false;
+
+ return 1;
+ }
+
if (is_nested(svm)) {
int vmexit;
- nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n",
- exit_code, svm->vmcb->control.exit_info_1,
- svm->vmcb->control.exit_info_2, svm->vmcb->save.rip);
+ trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code,
+ svm->vmcb->control.exit_info_1,
+ svm->vmcb->control.exit_info_2,
+ svm->vmcb->control.exit_int_info,
+ svm->vmcb->control.exit_int_info_err);
vmexit = nested_svm_exit_special(svm);
return 0;
}
- return svm_exit_handlers[exit_code](svm, kvm_run);
+ return svm_exit_handlers[exit_code](svm);
}
static void reload_tss(struct kvm_vcpu *vcpu)
{
int cpu = raw_smp_processor_id();
- struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
- svm_data->tss_desc->type = 9; /* available 32/64-bit TSS */
+ struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
+ sd->tss_desc->type = 9; /* available 32/64-bit TSS */
load_TR_desc();
}
{
int cpu = raw_smp_processor_id();
- struct svm_cpu_data *svm_data = per_cpu(svm_data, cpu);
+ struct svm_cpu_data *sd = per_cpu(svm_data, cpu);
svm->vmcb->control.tlb_ctl = TLB_CONTROL_DO_NOTHING;
/* FIXME: handle wraparound of asid_generation */
- if (svm->asid_generation != svm_data->asid_generation)
- new_asid(svm, svm_data);
+ if (svm->asid_generation != sd->asid_generation)
+ new_asid(svm, sd);
}
static void svm_inject_nmi(struct kvm_vcpu *vcpu)
!(svm->vcpu.arch.hflags & HF_NMI_MASK);
}
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ if (masked) {
+ svm->vcpu.arch.hflags |= HF_NMI_MASK;
+ svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+ } else {
+ svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
+ svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+ }
+}
+
static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
struct vmcb *vmcb = svm->vmcb;
- return (vmcb->save.rflags & X86_EFLAGS_IF) &&
- !(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
- gif_set(svm) &&
- !(is_nested(svm) && (svm->vcpu.arch.hflags & HF_VINTR_MASK));
+ int ret;
+
+ if (!gif_set(svm) ||
+ (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK))
+ return 0;
+
+ ret = !!(vmcb->save.rflags & X86_EFLAGS_IF);
+
+ if (is_nested(svm))
+ return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK);
+
+ return ret;
}
static void enable_irq_window(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- nsvm_printk("Trying to open IRQ window\n");
nested_svm_intr(svm);
/* Something prevents NMI from been injected. Single step over
possible problem (IRET or exception injection or interrupt
shadow) */
- vcpu->arch.singlestep = true;
+ svm->nmi_singlestep = true;
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
update_db_intercept(vcpu);
}
#define R "e"
#endif
-static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void svm_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
u16 fs_selector;
u16 gs_selector;
u16 ldt_selector;
+ /*
+ * A vmexit emulation is required before the vcpu can be executed
+ * again.
+ */
+ if (unlikely(svm->nested.exit_required))
+ return;
+
svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
.queue_exception = svm_queue_exception,
.interrupt_allowed = svm_interrupt_allowed,
.nmi_allowed = svm_nmi_allowed,
+ .get_nmi_mask = svm_get_nmi_mask,
+ .set_nmi_mask = svm_set_nmi_mask,
.enable_nmi_window = enable_nmi_window,
.enable_irq_window = enable_irq_window,
.update_cr8_intercept = update_cr8_intercept,
cpumask_var_t xen_cpu_initialized_map;
- static DEFINE_PER_CPU(int, resched_irq);
- static DEFINE_PER_CPU(int, callfunc_irq);
- static DEFINE_PER_CPU(int, callfuncsingle_irq);
- static DEFINE_PER_CPU(int, debug_irq) = -1;
+ static DEFINE_PER_CPU(int, xen_resched_irq);
+ static DEFINE_PER_CPU(int, xen_callfunc_irq);
+ static DEFINE_PER_CPU(int, xen_callfuncsingle_irq);
+ static DEFINE_PER_CPU(int, xen_debug_irq) = -1;
static irqreturn_t xen_call_function_interrupt(int irq, void *dev_id);
static irqreturn_t xen_call_function_single_interrupt(int irq, void *dev_id);
xen_setup_cpu_clockevents();
- cpu_set(cpu, cpu_online_map);
+ set_cpu_online(cpu, true);
percpu_write(cpu_state, CPU_ONLINE);
wmb();
NULL);
if (rc < 0)
goto fail;
- per_cpu(resched_irq, cpu) = rc;
+ per_cpu(xen_resched_irq, cpu) = rc;
callfunc_name = kasprintf(GFP_KERNEL, "callfunc%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_VECTOR,
NULL);
if (rc < 0)
goto fail;
- per_cpu(callfunc_irq, cpu) = rc;
+ per_cpu(xen_callfunc_irq, cpu) = rc;
debug_name = kasprintf(GFP_KERNEL, "debug%d", cpu);
rc = bind_virq_to_irqhandler(VIRQ_DEBUG, cpu, xen_debug_interrupt,
debug_name, NULL);
if (rc < 0)
goto fail;
- per_cpu(debug_irq, cpu) = rc;
+ per_cpu(xen_debug_irq, cpu) = rc;
callfunc_name = kasprintf(GFP_KERNEL, "callfuncsingle%d", cpu);
rc = bind_ipi_to_irqhandler(XEN_CALL_FUNCTION_SINGLE_VECTOR,
NULL);
if (rc < 0)
goto fail;
- per_cpu(callfuncsingle_irq, cpu) = rc;
+ per_cpu(xen_callfuncsingle_irq, cpu) = rc;
return 0;
fail:
- if (per_cpu(resched_irq, cpu) >= 0)
- unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
- if (per_cpu(callfunc_irq, cpu) >= 0)
- unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
- if (per_cpu(debug_irq, cpu) >= 0)
- unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
- if (per_cpu(callfuncsingle_irq, cpu) >= 0)
- unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+ if (per_cpu(xen_resched_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+ if (per_cpu(xen_callfunc_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+ if (per_cpu(xen_debug_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+ if (per_cpu(xen_callfuncsingle_irq, cpu) >= 0)
+ unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu),
+ NULL);
return rc;
}
(unsigned long)task_stack_page(idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
+ xen_setup_runstate_info(cpu);
xen_setup_timer(cpu);
xen_init_lock_cpu(cpu);
current->state = TASK_UNINTERRUPTIBLE;
schedule_timeout(HZ/10);
}
- unbind_from_irqhandler(per_cpu(resched_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(callfunc_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(debug_irq, cpu), NULL);
- unbind_from_irqhandler(per_cpu(callfuncsingle_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_resched_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_callfunc_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_debug_irq, cpu), NULL);
+ unbind_from_irqhandler(per_cpu(xen_callfuncsingle_irq, cpu), NULL);
xen_uninit_lock_cpu(cpu);
xen_teardown_timer(cpu);
#define NS_PER_TICK (1000000000LL / HZ)
/* runstate info updated by Xen */
- static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
+ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
/* snapshots of runstate info */
- static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate_snapshot);
+ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
/* unused ns of stolen and blocked time */
- static DEFINE_PER_CPU(u64, residual_stolen);
- static DEFINE_PER_CPU(u64, residual_blocked);
+ static DEFINE_PER_CPU(u64, xen_residual_stolen);
+ static DEFINE_PER_CPU(u64, xen_residual_blocked);
/* return an consistent snapshot of 64-bit time/counter value */
static u64 get64(const u64 *p)
BUG_ON(preemptible());
- state = &__get_cpu_var(runstate);
+ state = &__get_cpu_var(xen_runstate);
/*
* The runstate info is always updated by the hypervisor on
/* return true when a vcpu could run but has no real cpu to run on */
bool xen_vcpu_stolen(int vcpu)
{
- return per_cpu(runstate, vcpu).state == RUNSTATE_runnable;
+ return per_cpu(xen_runstate, vcpu).state == RUNSTATE_runnable;
}
-static void setup_runstate_info(int cpu)
+void xen_setup_runstate_info(int cpu)
{
struct vcpu_register_runstate_memory_area area;
- area.addr.v = &per_cpu(runstate, cpu);
+ area.addr.v = &per_cpu(xen_runstate, cpu);
if (HYPERVISOR_vcpu_op(VCPUOP_register_runstate_memory_area,
cpu, &area))
WARN_ON(state.state != RUNSTATE_running);
- snap = &__get_cpu_var(runstate_snapshot);
+ snap = &__get_cpu_var(xen_runstate_snapshot);
/* work out how much time the VCPU has not been runn*ing* */
blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked];
/* Add the appropriate number of ticks of stolen time,
including any left-overs from last time. */
- stolen = runnable + offline + __get_cpu_var(residual_stolen);
+ stolen = runnable + offline + __get_cpu_var(xen_residual_stolen);
if (stolen < 0)
stolen = 0;
ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
- __get_cpu_var(residual_stolen) = stolen;
+ __get_cpu_var(xen_residual_stolen) = stolen;
account_steal_ticks(ticks);
/* Add the appropriate number of ticks of blocked time,
including any left-overs from last time. */
- blocked += __get_cpu_var(residual_blocked);
+ blocked += __get_cpu_var(xen_residual_blocked);
if (blocked < 0)
blocked = 0;
ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
- __get_cpu_var(residual_blocked) = blocked;
+ __get_cpu_var(xen_residual_blocked) = blocked;
account_idle_ticks(ticks);
}
name = "<timer kasprintf failed>";
irq = bind_virq_to_irqhandler(VIRQ_TIMER, cpu, xen_timer_interrupt,
- IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING,
+ IRQF_DISABLED|IRQF_PERCPU|IRQF_NOBALANCING|IRQF_TIMER,
name, NULL);
evt = &per_cpu(xen_clock_events, cpu);
evt->cpumask = cpumask_of(cpu);
evt->irq = irq;
-
- setup_runstate_info(cpu);
}
void xen_teardown_timer(int cpu)
setup_force_cpu_cap(X86_FEATURE_TSC);
+ xen_setup_runstate_info(cpu);
xen_setup_timer(cpu);
xen_setup_cpu_clockevents();
}
struct cryptd_cpu_queue *cpu_queue;
cpu = get_cpu();
- cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu);
+ cpu_queue = this_cpu_ptr(queue->cpu_queue);
err = crypto_enqueue_request(&cpu_queue->queue, request);
queue_work_on(cpu, kcrypto_wq, &cpu_queue->work);
put_cpu();
}
EXPORT_SYMBOL_GPL(cryptd_ahash_child);
+struct shash_desc *cryptd_shash_desc(struct ahash_request *req)
+{
+ struct cryptd_hash_request_ctx *rctx = ahash_request_ctx(req);
+ return &rctx->desc;
+}
+EXPORT_SYMBOL_GPL(cryptd_shash_desc);
+
void cryptd_free_ahash(struct cryptd_ahash *tfm)
{
crypto_free_ahash(&tfm->base);
struct cpu *cpu = container_of(dev, struct cpu, sysdev);
ssize_t ret;
+ cpu_hotplug_driver_lock();
switch (buf[0]) {
case '0':
ret = cpu_down(cpu->sysdev.id);
default:
ret = -EINVAL;
}
+ cpu_hotplug_driver_unlock();
if (ret >= 0)
ret = count;
per_cpu(cpu_sys_devices, logical_cpu) = NULL;
return;
}
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
+static ssize_t cpu_probe_store(struct class *class, const char *buf,
+ size_t count)
+{
+ return arch_cpu_probe(buf, count);
+}
+
+static ssize_t cpu_release_store(struct class *class, const char *buf,
+ size_t count)
+{
+ return arch_cpu_release(buf, count);
+}
+
+static CLASS_ATTR(probe, S_IWUSR, NULL, cpu_probe_store);
+static CLASS_ATTR(release, S_IWUSR, NULL, cpu_release_store);
+
+int __init cpu_probe_release_init(void)
+{
+ int rc;
+
+ rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+ &class_attr_probe.attr);
+ if (!rc)
+ rc = sysfs_create_file(&cpu_sysdev_class.kset.kobj,
+ &class_attr_release.attr);
+
+ return rc;
+}
+device_initcall(cpu_probe_release_init);
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
#else /* ... !CONFIG_HOTPLUG_CPU */
static inline void register_cpu_control(struct cpu *cpu)
{
* boot up and this data does not change there after. Hence this
* operation should be safe. No locking required.
*/
- addr = __pa(per_cpu_ptr(crash_notes, cpunum));
+ addr = per_cpu_ptr_to_phys(per_cpu_ptr(crash_notes, cpunum));
rc = sprintf(buf, "%Lx\n", addr);
return rc;
}
static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
#ifdef CONFIG_HOTPLUG_CPU
/* This one keeps track of the previously set governor of a removed CPU */
-static DEFINE_PER_CPU(struct cpufreq_governor *, cpufreq_cpu_governor);
+static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
#endif
static DEFINE_SPINLOCK(cpufreq_driver_lock);
* - Lock should not be held across
* __cpufreq_governor(data, CPUFREQ_GOV_STOP);
*/
- static DEFINE_PER_CPU(int, policy_cpu);
+ static DEFINE_PER_CPU(int, cpufreq_policy_cpu);
static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
#define lock_policy_rwsem(mode, cpu) \
int lock_policy_rwsem_##mode \
(int cpu) \
{ \
- int policy_cpu = per_cpu(policy_cpu, cpu); \
+ int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu); \
BUG_ON(policy_cpu == -1); \
down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu)); \
if (unlikely(!cpu_online(cpu))) { \
void unlock_policy_rwsem_read(int cpu)
{
- int policy_cpu = per_cpu(policy_cpu, cpu);
+ int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
BUG_ON(policy_cpu == -1);
up_read(&per_cpu(cpu_policy_rwsem, policy_cpu));
}
void unlock_policy_rwsem_write(int cpu)
{
- int policy_cpu = per_cpu(policy_cpu, cpu);
+ int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
BUG_ON(policy_cpu == -1);
up_write(&per_cpu(cpu_policy_rwsem, policy_cpu));
}
return policy->governor->show_setspeed(policy, buf);
}
+/**
+ * show_scaling_driver - show the current cpufreq HW/BIOS limitation
+ */
+static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
+{
+ unsigned int limit;
+ int ret;
+ if (cpufreq_driver->bios_limit) {
+ ret = cpufreq_driver->bios_limit(policy->cpu, &limit);
+ if (!ret)
+ return sprintf(buf, "%u\n", limit);
+ }
+ return sprintf(buf, "%u\n", policy->cpuinfo.max_freq);
+}
+
#define define_one_ro(_name) \
static struct freq_attr _name = \
__ATTR(_name, 0444, show_##_name, NULL)
define_one_ro(scaling_available_governors);
define_one_ro(scaling_driver);
define_one_ro(scaling_cur_freq);
+define_one_ro(bios_limit);
define_one_ro(related_cpus);
define_one_ro(affected_cpus);
define_one_rw(scaling_min_freq);
* 0: Success
* Positive: When we have a managed CPU and the sysfs got symlinked
*/
-int cpufreq_add_dev_policy(unsigned int cpu, struct cpufreq_policy *policy,
- struct sys_device *sys_dev)
+static int cpufreq_add_dev_policy(unsigned int cpu,
+ struct cpufreq_policy *policy,
+ struct sys_device *sys_dev)
{
int ret = 0;
#ifdef CONFIG_SMP
unsigned long flags;
unsigned int j;
-
#ifdef CONFIG_HOTPLUG_CPU
- if (per_cpu(cpufreq_cpu_governor, cpu)) {
- policy->governor = per_cpu(cpufreq_cpu_governor, cpu);
+ struct cpufreq_governor *gov;
+
+ gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
+ if (gov) {
+ policy->governor = gov;
dprintk("Restoring governor %s for cpu %d\n",
policy->governor->name, cpu);
}
/* Set proper policy_cpu */
unlock_policy_rwsem_write(cpu);
- per_cpu(policy_cpu, cpu) = managed_policy->cpu;
+ per_cpu(cpufreq_policy_cpu, cpu) = managed_policy->cpu;
if (lock_policy_rwsem_write(cpu) < 0) {
/* Should not go through policy unlock path */
/* symlink affected CPUs */
-int cpufreq_add_dev_symlink(unsigned int cpu, struct cpufreq_policy *policy)
+static int cpufreq_add_dev_symlink(unsigned int cpu,
+ struct cpufreq_policy *policy)
{
unsigned int j;
int ret = 0;
return ret;
}
-int cpufreq_add_dev_interface(unsigned int cpu, struct cpufreq_policy *policy,
- struct sys_device *sys_dev)
+static int cpufreq_add_dev_interface(unsigned int cpu,
+ struct cpufreq_policy *policy,
+ struct sys_device *sys_dev)
{
struct cpufreq_policy new_policy;
struct freq_attr **drv_attr;
if (ret)
goto err_out_kobj_put;
}
+ if (cpufreq_driver->bios_limit) {
+ ret = sysfs_create_file(&policy->kobj, &bios_limit.attr);
+ if (ret)
+ goto err_out_kobj_put;
+ }
spin_lock_irqsave(&cpufreq_driver_lock, flags);
for_each_cpu(j, policy->cpus) {
if (!cpu_online(j))
continue;
per_cpu(cpufreq_cpu_data, j) = policy;
- per_cpu(policy_cpu, j) = policy->cpu;
+ per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
}
spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
static int cpufreq_add_dev(struct sys_device *sys_dev)
{
unsigned int cpu = sys_dev->id;
- int ret = 0;
+ int ret = 0, found = 0;
struct cpufreq_policy *policy;
unsigned long flags;
unsigned int j;
+#ifdef CONFIG_HOTPLUG_CPU
+ int sibling;
+#endif
if (cpu_is_offline(cpu))
return 0;
cpumask_copy(policy->cpus, cpumask_of(cpu));
/* Initially set CPU itself as the policy_cpu */
- per_cpu(policy_cpu, cpu) = cpu;
+ per_cpu(cpufreq_policy_cpu, cpu) = cpu;
ret = (lock_policy_rwsem_write(cpu) < 0);
WARN_ON(ret);
INIT_WORK(&policy->update, handle_update);
/* Set governor before ->init, so that driver could check it */
- policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+#ifdef CONFIG_HOTPLUG_CPU
+ for_each_online_cpu(sibling) {
+ struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
+ if (cp && cp->governor &&
+ (cpumask_test_cpu(cpu, cp->related_cpus))) {
+ policy->governor = cp->governor;
+ found = 1;
+ break;
+ }
+ }
+#endif
+ if (!found)
+ policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
/* call driver. From then on the cpufreq must be able
* to accept all calls to ->verify and ->setpolicy for this CPU
*/
#ifdef CONFIG_SMP
#ifdef CONFIG_HOTPLUG_CPU
- per_cpu(cpufreq_cpu_governor, cpu) = data->governor;
+ strncpy(per_cpu(cpufreq_cpu_governor, cpu), data->governor->name,
+ CPUFREQ_NAME_LEN);
#endif
/* if we have other CPUs still registered, we need to unlink them,
continue;
dprintk("removing link for cpu %u\n", j);
#ifdef CONFIG_HOTPLUG_CPU
- per_cpu(cpufreq_cpu_governor, j) = data->governor;
+ strncpy(per_cpu(cpufreq_cpu_governor, j),
+ data->governor->name, CPUFREQ_NAME_LEN);
#endif
cpu_sys_dev = get_cpu_sysdev(j);
sysfs_remove_link(&cpu_sys_dev->kobj, "cpufreq");
void cpufreq_unregister_governor(struct cpufreq_governor *governor)
{
+#ifdef CONFIG_HOTPLUG_CPU
+ int cpu;
+#endif
+
if (!governor)
return;
+#ifdef CONFIG_HOTPLUG_CPU
+ for_each_present_cpu(cpu) {
+ if (cpu_online(cpu))
+ continue;
+ if (!strcmp(per_cpu(cpufreq_cpu_governor, cpu), governor->name))
+ strcpy(per_cpu(cpufreq_cpu_governor, cpu), "\0");
+ }
+#endif
+
mutex_lock(&cpufreq_governor_mutex);
list_del(&governor->governor_list);
mutex_unlock(&cpufreq_governor_mutex);
int cpu;
for_each_possible_cpu(cpu) {
- per_cpu(policy_cpu, cpu) = -1;
+ per_cpu(cpufreq_policy_cpu, cpu) = -1;
init_rwsem(&per_cpu(cpu_policy_rwsem, cpu));
}
u32 *D;
};
- static DEFINE_PER_CPU(struct cword *, last_cword);
+ static DEFINE_PER_CPU(struct cword *, paes_last_cword);
/* Tells whether the ACE is capable to generate
the extended key for a given key_len. */
ok:
for_each_online_cpu(cpu)
- if (&ctx->cword.encrypt == per_cpu(last_cword, cpu) ||
- &ctx->cword.decrypt == per_cpu(last_cword, cpu))
- per_cpu(last_cword, cpu) = NULL;
+ if (&ctx->cword.encrypt == per_cpu(paes_last_cword, cpu) ||
+ &ctx->cword.decrypt == per_cpu(paes_last_cword, cpu))
+ per_cpu(paes_last_cword, cpu) = NULL;
return 0;
}
{
int cpu = raw_smp_processor_id();
- if (cword != per_cpu(last_cword, cpu))
+ if (cword != per_cpu(paes_last_cword, cpu))
#ifndef CONFIG_X86_64
asm volatile ("pushfl; popfl");
#else
static inline void padlock_store_cword(struct cword *cword)
{
- per_cpu(last_cword, raw_smp_processor_id()) = cword;
+ per_cpu(paes_last_cword, raw_smp_processor_id()) = cword;
}
/*
/* Padlock in ECB mode fetches at least ecb_fetch_bytes of data.
* We could avoid some copying here but it's probably not worth it.
*/
- if (unlikely(((unsigned long)in & PAGE_SIZE) + ecb_fetch_bytes > PAGE_SIZE)) {
+ if (unlikely(((unsigned long)in & ~PAGE_MASK) + ecb_fetch_bytes > PAGE_SIZE)) {
ecb_crypt_copy(in, out, key, cword, count);
return;
}
u8 *iv, struct cword *cword, int count)
{
/* Padlock in CBC mode fetches at least cbc_fetch_bytes of data. */
- if (unlikely(((unsigned long)in & PAGE_SIZE) + cbc_fetch_bytes > PAGE_SIZE))
+ if (unlikely(((unsigned long)in & ~PAGE_MASK) + cbc_fetch_bytes > PAGE_SIZE))
return cbc_crypt_copy(in, out, key, iv, cword, count);
return rep_xcrypt_cbc(in, out, key, iv, cword, count);
*/
struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
{
- struct dma_chan *chan;
- int cpu;
-
- cpu = get_cpu();
- chan = per_cpu_ptr(channel_table[tx_type], cpu)->chan;
- put_cpu();
-
- return chan;
+ return this_cpu_read(channel_table[tx_type]->chan);
}
EXPORT_SYMBOL(dma_find_channel);
#if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE)
if (!dma_has_cap(DMA_XOR, device->cap_mask))
return false;
+
+ #ifndef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA
+ if (!dma_has_cap(DMA_XOR_VAL, device->cap_mask))
+ return false;
+ #endif
#endif
#if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE)
if (!dma_has_cap(DMA_PQ, device->cap_mask))
return false;
+
+ #ifndef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA
+ if (!dma_has_cap(DMA_PQ_VAL, device->cap_mask))
+ return false;
+ #endif
#endif
return true;
struct dma_async_tx_descriptor *tx;
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
- int cpu;
unsigned long flags;
dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
tx->callback = NULL;
cookie = tx->tx_submit(tx);
- cpu = get_cpu();
- per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
- per_cpu_ptr(chan->local, cpu)->memcpy_count++;
- put_cpu();
+ preempt_disable();
+ __this_cpu_add(chan->local->bytes_transferred, len);
+ __this_cpu_inc(chan->local->memcpy_count);
+ preempt_enable();
return cookie;
}
struct dma_async_tx_descriptor *tx;
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
- int cpu;
unsigned long flags;
dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
tx->callback = NULL;
cookie = tx->tx_submit(tx);
- cpu = get_cpu();
- per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
- per_cpu_ptr(chan->local, cpu)->memcpy_count++;
- put_cpu();
+ preempt_disable();
+ __this_cpu_add(chan->local->bytes_transferred, len);
+ __this_cpu_inc(chan->local->memcpy_count);
+ preempt_enable();
return cookie;
}
struct dma_async_tx_descriptor *tx;
dma_addr_t dma_dest, dma_src;
dma_cookie_t cookie;
- int cpu;
unsigned long flags;
dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
tx->callback = NULL;
cookie = tx->tx_submit(tx);
- cpu = get_cpu();
- per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
- per_cpu_ptr(chan->local, cpu)->memcpy_count++;
- put_cpu();
+ preempt_disable();
+ __this_cpu_add(chan->local->bytes_transferred, len);
+ __this_cpu_inc(chan->local->memcpy_count);
+ preempt_enable();
return cookie;
}
/* it's OK to use per_cpu_ptr() because BHs are off */
pcpu_lstats = dev->ml_priv;
- lb_stats = per_cpu_ptr(pcpu_lstats, smp_processor_id());
+ lb_stats = this_cpu_ptr(pcpu_lstats);
len = skb->len;
if (likely(netif_rx(skb) == NET_RX_SUCCESS)) {
out_free_netdev:
free_netdev(dev);
out:
- if (net == &init_net)
+ if (net_eq(net, &init_net))
panic("loopback: Failed to register netdevice: %d\n", err);
return err;
}
-static __net_exit void loopback_net_exit(struct net *net)
-{
- struct net_device *dev = net->loopback_dev;
-
- unregister_netdev(dev);
-}
-
/* Registered in net/core/dev.c */
struct pernet_operations __net_initdata loopback_net_ops = {
.init = loopback_net_init,
- .exit = loopback_net_exit,
};
struct net_device *rcv = NULL;
struct veth_priv *priv, *rcv_priv;
struct veth_net_stats *stats, *rcv_stats;
- int length, cpu;
+ int length;
- skb_orphan(skb);
-
priv = netdev_priv(dev);
rcv = priv->peer;
rcv_priv = netdev_priv(rcv);
- cpu = smp_processor_id();
- stats = per_cpu_ptr(priv->stats, cpu);
- rcv_stats = per_cpu_ptr(rcv_priv->stats, cpu);
+ stats = this_cpu_ptr(priv->stats);
+ rcv_stats = this_cpu_ptr(rcv_priv->stats);
if (!(rcv->flags & IFF_UP))
goto tx_drop;
- if (skb->len > (rcv->mtu + MTU_PAD))
- goto rx_drop;
-
- skb->tstamp.tv64 = 0;
- skb->pkt_type = PACKET_HOST;
- skb->protocol = eth_type_trans(skb, rcv);
if (dev->features & NETIF_F_NO_CSUM)
skb->ip_summed = rcv_priv->ip_summed;
- skb->mark = 0;
- secpath_reset(skb);
- nf_reset(skb);
-
- length = skb->len;
+ length = skb->len + ETH_HLEN;
+ if (dev_forward_skb(rcv, skb) != NET_RX_SUCCESS)
+ goto rx_drop;
stats->tx_bytes += length;
stats->tx_packets++;
rcv_stats->rx_bytes += length;
rcv_stats->rx_packets++;
- netif_rx(skb);
return NETDEV_TX_OK;
tx_drop:
static struct net_device_stats *veth_get_stats(struct net_device *dev)
{
struct veth_priv *priv;
- struct net_device_stats *dev_stats;
int cpu;
- struct veth_net_stats *stats;
+ struct veth_net_stats *stats, total = {0};
priv = netdev_priv(dev);
- dev_stats = &dev->stats;
- dev_stats->rx_packets = 0;
- dev_stats->tx_packets = 0;
- dev_stats->rx_bytes = 0;
- dev_stats->tx_bytes = 0;
- dev_stats->tx_dropped = 0;
- dev_stats->rx_dropped = 0;
-
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
stats = per_cpu_ptr(priv->stats, cpu);
- dev_stats->rx_packets += stats->rx_packets;
- dev_stats->tx_packets += stats->tx_packets;
- dev_stats->rx_bytes += stats->rx_bytes;
- dev_stats->tx_bytes += stats->tx_bytes;
- dev_stats->tx_dropped += stats->tx_dropped;
- dev_stats->rx_dropped += stats->rx_dropped;
+ total.rx_packets += stats->rx_packets;
+ total.tx_packets += stats->tx_packets;
+ total.rx_bytes += stats->rx_bytes;
+ total.tx_bytes += stats->tx_bytes;
+ total.tx_dropped += stats->tx_dropped;
+ total.rx_dropped += stats->rx_dropped;
}
-
- return dev_stats;
+ dev->stats.rx_packets = total.rx_packets;
+ dev->stats.tx_packets = total.tx_packets;
+ dev->stats.rx_bytes = total.rx_bytes;
+ dev->stats.tx_bytes = total.tx_bytes;
+ dev->stats.tx_dropped = total.tx_dropped;
+ dev->stats.rx_dropped = total.rx_dropped;
+
+ return &dev->stats;
}
static int veth_open(struct net_device *dev)
static struct rtnl_link_ops veth_link_ops;
-static int veth_newlink(struct net_device *dev,
+static int veth_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[])
{
int err;
struct veth_priv *priv;
char ifname[IFNAMSIZ];
struct nlattr *peer_tb[IFLA_MAX + 1], **tbp;
+ struct net *net;
/*
* create and register peer first
else
snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
- peer = rtnl_create_link(dev_net(dev), ifname, &veth_link_ops, tbp);
- if (IS_ERR(peer))
+ net = rtnl_link_get_net(src_net, tbp);
+ if (IS_ERR(net))
+ return PTR_ERR(net);
+
+ peer = rtnl_create_link(src_net, net, ifname, &veth_link_ops, tbp);
+ if (IS_ERR(peer)) {
+ put_net(net);
return PTR_ERR(peer);
+ }
if (tbp[IFLA_ADDRESS] == NULL)
random_ether_addr(peer->dev_addr);
err = register_netdevice(peer);
+ put_net(net);
+ net = NULL;
if (err < 0)
goto err_register_peer;
return err;
}
-static void veth_dellink(struct net_device *dev)
+static void veth_dellink(struct net_device *dev, struct list_head *head)
{
struct veth_priv *priv;
struct net_device *peer;
priv = netdev_priv(dev);
peer = priv->peer;
- unregister_netdevice(dev);
- unregister_netdevice(peer);
+ unregister_netdevice_queue(dev, head);
+ unregister_netdevice_queue(peer, head);
}
static const struct nla_policy veth_policy[VETH_INFO_MAX + 1];
#define IUCV_DBF_TEXT_(name, level, text...) \
do { \
if (iucv_dbf_passes(iucv_dbf_##name, level)) { \
- char* iucv_dbf_txt_buf = \
- get_cpu_var(iucv_dbf_txt_buf); \
- sprintf(iucv_dbf_txt_buf, text); \
- debug_text_event(iucv_dbf_##name, level, \
- iucv_dbf_txt_buf); \
+ char* __buf = get_cpu_var(iucv_dbf_txt_buf); \
+ sprintf(__buf, text); \
+ debug_text_event(iucv_dbf_##name, level, __buf); \
put_cpu_var(iucv_dbf_txt_buf); \
} \
} while (0)
if (single_flag) {
if ((skb = skb_dequeue(&conn->commit_queue))) {
atomic_dec(&skb->users);
- dev_kfree_skb_any(skb);
if (privptr) {
privptr->stats.tx_packets++;
privptr->stats.tx_bytes +=
(skb->len - NETIUCV_HDRLEN
- - NETIUCV_HDRLEN);
+ - NETIUCV_HDRLEN);
}
+ dev_kfree_skb_any(skb);
}
}
conn->tx_buff->data = conn->tx_buff->head;
* 2 blocks and the order of allocation is >= sbi->s_mb_order2_reqs. The
* value of s_mb_order2_reqs can be tuned via
* /sys/fs/ext4/<partition>/mb_order2_req. If the request len is equal to
- * stripe size (sbi->s_stripe), we try to search for contigous block in
+ * stripe size (sbi->s_stripe), we try to search for contiguous block in
* stripe size. This should result in better allocation on RAID setups. If
* not, we search in the specific group using bitmap for best extents. The
* tunable min_to_scan and max_to_scan control the behaviour here.
struct ext4_group_info *db;
int err, count = 0, count2 = 0;
struct ext4_free_data *entry;
- ext4_fsblk_t discard_block;
struct list_head *l, *ltmp;
list_for_each_safe(l, ltmp, &txn->t_private_list) {
page_cache_release(e4b.bd_bitmap_page);
}
ext4_unlock_group(sb, entry->group);
- discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
- + entry->start_blk
- + le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
- trace_ext4_discard_blocks(sb, (unsigned long long)discard_block,
- entry->count);
- sb_issue_discard(sb, discard_block, entry->count);
-
+ if (test_opt(sb, DISCARD)) {
+ ext4_fsblk_t discard_block;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+ discard_block = (ext4_fsblk_t)entry->group *
+ EXT4_BLOCKS_PER_GROUP(sb)
+ + entry->start_blk
+ + le32_to_cpu(es->s_first_data_block);
+ trace_ext4_discard_blocks(sb,
+ (unsigned long long)discard_block,
+ entry->count);
+ sb_issue_discard(sb, discard_block, entry->count);
+ }
kmem_cache_free(ext4_free_ext_cachep, entry);
ext4_mb_release_desc(&e4b);
}
trace_ext4_mballoc_prealloc(ac);
}
+/*
+ * Called on failure; free up any blocks from the inode PA for this
+ * context. We don't need this for MB_GROUP_PA because we only change
+ * pa_free in ext4_mb_release_context(), but on failure, we've already
+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed.
+ */
+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
+{
+ struct ext4_prealloc_space *pa = ac->ac_pa;
+ int len;
+
+ if (pa && pa->pa_type == MB_INODE_PA) {
+ len = ac->ac_b_ex.fe_len;
+ pa->pa_free += len;
+ }
+
+}
+
/*
* use blocks preallocated to inode
*/
* per cpu locality group is to reduce the contention between block
* request from multiple CPUs.
*/
- ac->ac_lg = per_cpu_ptr(sbi->s_locality_groups, raw_smp_processor_id());
+ ac->ac_lg = __this_cpu_ptr(sbi->s_locality_groups);
/* we're going to use group allocation */
ac->ac_flags |= EXT4_MB_HINT_GROUP_ALLOC;
ac->ac_status = AC_STATUS_CONTINUE;
goto repeat;
} else if (*errp) {
+ ext4_discard_allocated_blocks(ac);
ac->ac_b_ex.fe_len = 0;
ar->len = 0;
ext4_mb_show_ac(ac);
return 0;
}
-/*
- * Main entry point into mballoc to free blocks
+/**
+ * ext4_free_blocks() -- Free given blocks and update quota
+ * @handle: handle for this transaction
+ * @inode: inode
+ * @block: start physical block to free
+ * @count: number of blocks to count
+ * @metadata: Are these metadata blocks
*/
-void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
- ext4_fsblk_t block, unsigned long count,
- int metadata, unsigned long *freed)
+void ext4_free_blocks(handle_t *handle, struct inode *inode,
+ struct buffer_head *bh, ext4_fsblk_t block,
+ unsigned long count, int flags)
{
struct buffer_head *bitmap_bh = NULL;
struct super_block *sb = inode->i_sb;
struct ext4_allocation_context *ac = NULL;
struct ext4_group_desc *gdp;
struct ext4_super_block *es;
+ unsigned long freed = 0;
unsigned int overflow;
ext4_grpblk_t bit;
struct buffer_head *gd_bh;
int err = 0;
int ret;
- *freed = 0;
+ if (bh) {
+ if (block)
+ BUG_ON(block != bh->b_blocknr);
+ else
+ block = bh->b_blocknr;
+ }
sbi = EXT4_SB(sb);
es = EXT4_SB(sb)->s_es;
- if (block < le32_to_cpu(es->s_first_data_block) ||
- block + count < block ||
- block + count > ext4_blocks_count(es)) {
+ if (!ext4_data_block_valid(sbi, block, count)) {
ext4_error(sb, __func__,
"Freeing blocks not in datazone - "
"block = %llu, count = %lu", block, count);
}
ext4_debug("freeing block %llu\n", block);
- trace_ext4_free_blocks(inode, block, count, metadata);
+ trace_ext4_free_blocks(inode, block, count, flags);
+
+ if (flags & EXT4_FREE_BLOCKS_FORGET) {
+ struct buffer_head *tbh = bh;
+ int i;
+
+ BUG_ON(bh && (count > 1));
+
+ for (i = 0; i < count; i++) {
+ if (!bh)
+ tbh = sb_find_get_block(inode->i_sb,
+ block + i);
+ ext4_forget(handle, flags & EXT4_FREE_BLOCKS_METADATA,
+ inode, tbh, block + i);
+ }
+ }
+
+ /*
+ * We need to make sure we don't reuse the freed block until
+ * after the transaction is committed, which we can do by
+ * treating the block as metadata, below. We make an
+ * exception if the inode is to be written in writeback mode
+ * since writeback mode has weak data consistency guarantees.
+ */
+ if (!ext4_should_writeback_data(inode))
+ flags |= EXT4_FREE_BLOCKS_METADATA;
ac = kmem_cache_alloc(ext4_ac_cachep, GFP_NOFS);
if (ac) {
err = ext4_mb_load_buddy(sb, block_group, &e4b);
if (err)
goto error_return;
- if (metadata && ext4_handle_valid(handle)) {
+
+ if ((flags & EXT4_FREE_BLOCKS_METADATA) && ext4_handle_valid(handle)) {
struct ext4_free_data *new_entry;
/*
* blocks being freed are metadata. these blocks shouldn't
ext4_mb_release_desc(&e4b);
- *freed += count;
+ freed += count;
/* We dirtied the bitmap block */
BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
}
sb->s_dirt = 1;
error_return:
+ if (freed)
+ vfs_dq_free_block(inode, freed);
brelse(bitmap_bh);
ext4_std_error(sb, err);
if (ac)
sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;
- bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), extra_flags);
+ bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR, BTOBB(sector_size),
+ extra_flags);
if (!bp || XFS_BUF_ISERROR(bp)) {
xfs_fs_mount_cmn_err(flags, "SB read failed");
error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
XFS_BUF_UNMANAGE(bp);
xfs_buf_relse(bp);
sector_size = mp->m_sb.sb_sectsize;
- bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
- BTOBB(sector_size), extra_flags);
+ bp = xfs_buf_read(mp->m_ddev_targp, XFS_SB_DADDR,
+ BTOBB(sector_size), extra_flags);
if (!bp || XFS_BUF_ISERROR(bp)) {
xfs_fs_mount_cmn_err(flags, "SB re-read failed");
error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
return 0;
- tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT);
+ tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
error = xfs_trans_reserve(tp, 0, mp->m_sb.sb_sectsize + 128, 0, 0,
XFS_DEFAULT_LOG_COUNT);
if (error) {
mutex_destroy(&mp->m_icsb_mutex);
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_lock_cntr(
xfs_icsb_cnts_t *icsbp)
{
}
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_unlock_cntr(
xfs_icsb_cnts_t *icsbp)
{
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_lock_all_counters(
xfs_mount_t *mp)
{
}
}
-STATIC_INLINE void
+STATIC void
xfs_icsb_unlock_all_counters(
xfs_mount_t *mp)
{
{
xfs_icsb_cnts_t *icsbp;
long long lcounter; /* long counter for 64 bit fields */
- int cpu, ret = 0;
+ int ret = 0;
might_sleep();
again:
- cpu = get_cpu();
- icsbp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, cpu);
+ preempt_disable();
+ icsbp = this_cpu_ptr(mp->m_sb_cnts);
/*
* if the counter is disabled, go to slow path
break;
}
xfs_icsb_unlock_cntr(icsbp);
- put_cpu();
+ preempt_enable();
return 0;
slow_path:
- put_cpu();
+ preempt_enable();
/*
* serialise with a mutex so we don't burn lots of cpu on
balance_counter:
xfs_icsb_unlock_cntr(icsbp);
- put_cpu();
+ preempt_enable();
/*
* We may have multiple threads here if multiple per-cpu
struct neighbour;
-struct neigh_parms
-{
+struct neigh_parms {
#ifdef CONFIG_NET_NS
struct net *net;
#endif
int locktime;
};
-struct neigh_statistics
-{
+struct neigh_statistics {
unsigned long allocs; /* number of allocated neighs */
unsigned long destroys; /* number of destroyed neighs */
unsigned long hash_grows; /* number of hash resizes */
unsigned long unres_discards; /* number of unresolved drops */
};
- #define NEIGH_CACHE_STAT_INC(tbl, field) \
- do { \
- preempt_disable(); \
- (per_cpu_ptr((tbl)->stats, smp_processor_id())->field)++; \
- preempt_enable(); \
- } while (0)
+ #define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field)
-struct neighbour
-{
+struct neighbour {
struct neighbour *next;
struct neigh_table *tbl;
struct neigh_parms *parms;
u8 primary_key[0];
};
-struct neigh_ops
-{
+struct neigh_ops {
int family;
void (*solicit)(struct neighbour *, struct sk_buff*);
void (*error_report)(struct neighbour *, struct sk_buff*);
int (*queue_xmit)(struct sk_buff*);
};
-struct pneigh_entry
-{
+struct pneigh_entry {
struct pneigh_entry *next;
#ifdef CONFIG_NET_NS
struct net *net;
*/
-struct neigh_table
-{
+struct neigh_table {
struct neigh_table *next;
int family;
int entry_size;
struct neigh_parms *p,
int p_id, int pdev_id,
char *p_name,
- proc_handler *proc_handler,
- ctl_handler *strategy);
+ proc_handler *proc_handler);
extern void neigh_sysctl_unregister(struct neigh_parms *p);
static inline void __neigh_parms_put(struct neigh_parms *parms)
}
/* These are for NAT. Icky. */
-/* Update TCP window tracking data when NAT mangles the packet */
-extern void nf_conntrack_tcp_update(const struct sk_buff *skb,
- unsigned int dataoff,
- struct nf_conn *ct, int dir,
- s16 offset);
+extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
+ enum ip_conntrack_dir dir,
+ u32 seq);
/* Fake conntrack entry for untracked connections */
extern struct nf_conn nf_conntrack_untracked;
extern unsigned int nf_conntrack_max;
#define NF_CT_STAT_INC(net, count) \
- (per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++)
+ __this_cpu_inc((net)->ct.stat->count)
#define NF_CT_STAT_INC_ATOMIC(net, count) \
do { \
local_bh_disable(); \
- per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++; \
+ __this_cpu_inc((net)->ct.stat->count); \
local_bh_enable(); \
} while (0)
#include "lockdep_internals.h"
#define CREATE_TRACE_POINTS
-#include <trace/events/lockdep.h>
+#include <trace/events/lock.h>
#ifdef CONFIG_PROVE_LOCKING
int prove_locking = 1;
}
#ifdef CONFIG_LOCK_STAT
- static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS], lock_stats);
+ static DEFINE_PER_CPU(struct lock_class_stats[MAX_LOCKDEP_KEYS],
+ cpu_lock_stats);
+static inline u64 lockstat_clock(void)
+{
+ return cpu_clock(smp_processor_id());
+}
+
static int lock_point(unsigned long points[], unsigned long ip)
{
int i;
return i;
}
-static void lock_time_inc(struct lock_time *lt, s64 time)
+static void lock_time_inc(struct lock_time *lt, u64 time)
{
if (time > lt->max)
lt->max = time;
- if (time < lt->min || !lt->min)
+ if (time < lt->min || !lt->nr)
lt->min = time;
lt->total += time;
static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
{
- dst->min += src->min;
- dst->max += src->max;
+ if (!src->nr)
+ return;
+
+ if (src->max > dst->max)
+ dst->max = src->max;
+
+ if (src->min < dst->min || !dst->nr)
+ dst->min = src->min;
+
dst->total += src->total;
dst->nr += src->nr;
}
memset(&stats, 0, sizeof(struct lock_class_stats));
for_each_possible_cpu(cpu) {
struct lock_class_stats *pcs =
- &per_cpu(lock_stats, cpu)[class - lock_classes];
+ &per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
stats.contention_point[i] += pcs->contention_point[i];
for_each_possible_cpu(cpu) {
struct lock_class_stats *cpu_stats =
- &per_cpu(lock_stats, cpu)[class - lock_classes];
+ &per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
memset(cpu_stats, 0, sizeof(struct lock_class_stats));
}
static struct lock_class_stats *get_lock_stats(struct lock_class *class)
{
- return &get_cpu_var(lock_stats)[class - lock_classes];
+ return &get_cpu_var(cpu_lock_stats)[class - lock_classes];
}
static void put_lock_stats(struct lock_class_stats *stats)
{
- put_cpu_var(lock_stats);
+ put_cpu_var(cpu_lock_stats);
}
static void lock_release_holdtime(struct held_lock *hlock)
{
struct lock_class_stats *stats;
- s64 holdtime;
+ u64 holdtime;
if (!lock_stat)
return;
- holdtime = sched_clock() - hlock->holdtime_stamp;
+ holdtime = lockstat_clock() - hlock->holdtime_stamp;
stats = get_lock_stats(hlock_class(hlock));
if (hlock->read)
* complete trace that maxes out the entries provided will be reported
* as incomplete, friggin useless </rant>
*/
- if (trace->entries[trace->nr_entries-1] == ULONG_MAX)
+ if (trace->nr_entries != 0 &&
+ trace->entries[trace->nr_entries-1] == ULONG_MAX)
trace->nr_entries--;
trace->max_entries = trace->nr_entries;
hlock->references = references;
#ifdef CONFIG_LOCK_STAT
hlock->waittime_stamp = 0;
- hlock->holdtime_stamp = sched_clock();
+ hlock->holdtime_stamp = lockstat_clock();
#endif
if (check == 2 && !mark_irqflags(curr, hlock))
if (hlock->instance != lock)
return;
- hlock->waittime_stamp = sched_clock();
+ hlock->waittime_stamp = lockstat_clock();
contention_point = lock_point(hlock_class(hlock)->contention_point, ip);
contending_point = lock_point(hlock_class(hlock)->contending_point,
struct held_lock *hlock, *prev_hlock;
struct lock_class_stats *stats;
unsigned int depth;
- u64 now;
- s64 waittime = 0;
+ u64 now, waittime = 0;
int i, cpu;
depth = curr->lockdep_depth;
cpu = smp_processor_id();
if (hlock->waittime_stamp) {
- now = sched_clock();
+ now = lockstat_clock();
waittime = now - hlock->waittime_stamp;
hlock->holdtime_stamp = now;
}
#ifdef CONFIG_SMP
- #ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
static void *percpu_modalloc(unsigned long size, unsigned long align,
const char *name)
{
free_percpu(freeme);
}
- #else /* ... CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
- /* Number of blocks used and allocated. */
- static unsigned int pcpu_num_used, pcpu_num_allocated;
- /* Size of each block. -ve means used. */
- static int *pcpu_size;
-
- static int split_block(unsigned int i, unsigned short size)
- {
- /* Reallocation required? */
- if (pcpu_num_used + 1 > pcpu_num_allocated) {
- int *new;
-
- new = krealloc(pcpu_size, sizeof(new[0])*pcpu_num_allocated*2,
- GFP_KERNEL);
- if (!new)
- return 0;
-
- pcpu_num_allocated *= 2;
- pcpu_size = new;
- }
-
- /* Insert a new subblock */
- memmove(&pcpu_size[i+1], &pcpu_size[i],
- sizeof(pcpu_size[0]) * (pcpu_num_used - i));
- pcpu_num_used++;
-
- pcpu_size[i+1] -= size;
- pcpu_size[i] = size;
- return 1;
- }
-
- static inline unsigned int block_size(int val)
- {
- if (val < 0)
- return -val;
- return val;
- }
-
- static void *percpu_modalloc(unsigned long size, unsigned long align,
- const char *name)
- {
- unsigned long extra;
- unsigned int i;
- void *ptr;
- int cpu;
-
- if (align > PAGE_SIZE) {
- printk(KERN_WARNING "%s: per-cpu alignment %li > %li\n",
- name, align, PAGE_SIZE);
- align = PAGE_SIZE;
- }
-
- ptr = __per_cpu_start;
- for (i = 0; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
- /* Extra for alignment requirement. */
- extra = ALIGN((unsigned long)ptr, align) - (unsigned long)ptr;
- BUG_ON(i == 0 && extra != 0);
-
- if (pcpu_size[i] < 0 || pcpu_size[i] < extra + size)
- continue;
-
- /* Transfer extra to previous block. */
- if (pcpu_size[i-1] < 0)
- pcpu_size[i-1] -= extra;
- else
- pcpu_size[i-1] += extra;
- pcpu_size[i] -= extra;
- ptr += extra;
-
- /* Split block if warranted */
- if (pcpu_size[i] - size > sizeof(unsigned long))
- if (!split_block(i, size))
- return NULL;
-
- /* add the per-cpu scanning areas */
- for_each_possible_cpu(cpu)
- kmemleak_alloc(ptr + per_cpu_offset(cpu), size, 0,
- GFP_KERNEL);
-
- /* Mark allocated */
- pcpu_size[i] = -pcpu_size[i];
- return ptr;
- }
-
- printk(KERN_WARNING "Could not allocate %lu bytes percpu data\n",
- size);
- return NULL;
- }
-
- static void percpu_modfree(void *freeme)
- {
- unsigned int i;
- void *ptr = __per_cpu_start + block_size(pcpu_size[0]);
- int cpu;
-
- /* First entry is core kernel percpu data. */
- for (i = 1; i < pcpu_num_used; ptr += block_size(pcpu_size[i]), i++) {
- if (ptr == freeme) {
- pcpu_size[i] = -pcpu_size[i];
- goto free;
- }
- }
- BUG();
-
- free:
- /* remove the per-cpu scanning areas */
- for_each_possible_cpu(cpu)
- kmemleak_free(freeme + per_cpu_offset(cpu));
-
- /* Merge with previous? */
- if (pcpu_size[i-1] >= 0) {
- pcpu_size[i-1] += pcpu_size[i];
- pcpu_num_used--;
- memmove(&pcpu_size[i], &pcpu_size[i+1],
- (pcpu_num_used - i) * sizeof(pcpu_size[0]));
- i--;
- }
- /* Merge with next? */
- if (i+1 < pcpu_num_used && pcpu_size[i+1] >= 0) {
- pcpu_size[i] += pcpu_size[i+1];
- pcpu_num_used--;
- memmove(&pcpu_size[i+1], &pcpu_size[i+2],
- (pcpu_num_used - (i+1)) * sizeof(pcpu_size[0]));
- }
- }
-
- static int percpu_modinit(void)
- {
- pcpu_num_used = 2;
- pcpu_num_allocated = 2;
- pcpu_size = kmalloc(sizeof(pcpu_size[0]) * pcpu_num_allocated,
- GFP_KERNEL);
- /* Static in-kernel percpu data (used). */
- pcpu_size[0] = -(__per_cpu_end-__per_cpu_start);
- /* Free room. */
- pcpu_size[1] = PERCPU_ENOUGH_ROOM + pcpu_size[0];
- if (pcpu_size[1] < 0) {
- printk(KERN_ERR "No per-cpu room for modules.\n");
- pcpu_num_used = 1;
- }
-
- return 0;
- }
- __initcall(percpu_modinit);
-
- #endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
static unsigned int find_pcpusec(Elf_Ehdr *hdr,
Elf_Shdr *sechdrs,
const char *secstrings)
/* Count loaded sections and allocate structures */
for (i = 0; i < nsect; i++)
- if (sechdrs[i].sh_flags & SHF_ALLOC)
+ if (sechdrs[i].sh_flags & SHF_ALLOC
+ && sechdrs[i].sh_size)
nloaded++;
size[0] = ALIGN(sizeof(*sect_attrs)
+ nloaded * sizeof(sect_attrs->attrs[0]),
for (i = 0; i < nsect; i++) {
if (! (sechdrs[i].sh_flags & SHF_ALLOC))
continue;
+ if (!sechdrs[i].sh_size)
+ continue;
sattr->address = sechdrs[i].sh_addr;
sattr->name = kstrdup(secstrings + sechdrs[i].sh_name,
GFP_KERNEL);
cur_ops->deferred_free(rp);
}
+static int rcu_no_completed(void)
+{
+ return 0;
+}
+
static void rcu_torture_deferred_free(struct rcu_torture *p)
{
call_rcu(&p->rtort_rcu, rcu_torture_cb);
.name = "rcu_sync"
};
+static struct rcu_torture_ops rcu_expedited_ops = {
+ .init = rcu_sync_torture_init,
+ .cleanup = NULL,
+ .readlock = rcu_torture_read_lock,
+ .read_delay = rcu_read_delay, /* just reuse rcu's version. */
+ .readunlock = rcu_torture_read_unlock,
+ .completed = rcu_no_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = synchronize_rcu_expedited,
+ .cb_barrier = NULL,
+ .stats = NULL,
+ .irq_capable = 1,
+ .name = "rcu_expedited"
+};
+
/*
* Definitions for rcu_bh torture testing.
*/
.name = "srcu"
};
+static void srcu_torture_synchronize_expedited(void)
+{
+ synchronize_srcu_expedited(&srcu_ctl);
+}
+
+static struct rcu_torture_ops srcu_expedited_ops = {
+ .init = srcu_torture_init,
+ .cleanup = srcu_torture_cleanup,
+ .readlock = srcu_torture_read_lock,
+ .read_delay = srcu_read_delay,
+ .readunlock = srcu_torture_read_unlock,
+ .completed = srcu_torture_completed,
+ .deferred_free = rcu_sync_torture_deferred_free,
+ .sync = srcu_torture_synchronize_expedited,
+ .cb_barrier = NULL,
+ .stats = srcu_torture_stats,
+ .name = "srcu_expedited"
+};
+
/*
* Definitions for sched torture testing.
*/
preempt_enable();
}
-static int sched_torture_completed(void)
-{
- return 0;
-}
-
static void rcu_sched_torture_deferred_free(struct rcu_torture *p)
{
call_rcu_sched(&p->rtort_rcu, rcu_torture_cb);
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sched_torture_deferred_free,
.sync = sched_torture_synchronize,
.cb_barrier = rcu_barrier_sched,
.name = "sched"
};
-static struct rcu_torture_ops sched_ops_sync = {
+static struct rcu_torture_ops sched_sync_ops = {
.init = rcu_sync_torture_init,
.cleanup = NULL,
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = sched_torture_synchronize,
.cb_barrier = NULL,
.name = "sched_sync"
};
-extern int rcu_expedited_torture_stats(char *page);
-
static struct rcu_torture_ops sched_expedited_ops = {
.init = rcu_sync_torture_init,
.cleanup = NULL,
.readlock = sched_torture_read_lock,
.read_delay = rcu_read_delay, /* just reuse rcu's version. */
.readunlock = sched_torture_read_unlock,
- .completed = sched_torture_completed,
+ .completed = rcu_no_completed,
.deferred_free = rcu_sync_torture_deferred_free,
.sync = synchronize_sched_expedited,
.cb_barrier = NULL,
old_rp = rcu_torture_current;
rp->rtort_mbtest = 1;
rcu_assign_pointer(rcu_torture_current, rp);
- smp_wmb();
+ smp_wmb(); /* Mods to old_rp must follow rcu_assign_pointer() */
if (old_rp) {
i = old_rp->rtort_pipe_count;
if (i > RCU_TORTURE_PIPE_LEN)
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_count)[pipe_count];
+ __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
completed = cur_ops->completed() - completed;
if (completed > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
completed = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_batch)[completed];
+ __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
preempt_enable();
cur_ops->readunlock(idx);
}
/* Should not happen, but... */
pipe_count = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_count)[pipe_count];
+ __this_cpu_inc(per_cpu_var(rcu_torture_count)[pipe_count]);
completed = cur_ops->completed() - completed;
if (completed > RCU_TORTURE_PIPE_LEN) {
/* Should not happen, but... */
completed = RCU_TORTURE_PIPE_LEN;
}
- ++__get_cpu_var(rcu_torture_batch)[completed];
+ __this_cpu_inc(per_cpu_var(rcu_torture_batch)[completed]);
preempt_enable();
cur_ops->readunlock(idx);
schedule();
int cpu;
int firsterr = 0;
static struct rcu_torture_ops *torture_ops[] =
- { &rcu_ops, &rcu_sync_ops, &rcu_bh_ops, &rcu_bh_sync_ops,
- &sched_expedited_ops,
- &srcu_ops, &sched_ops, &sched_ops_sync, };
+ { &rcu_ops, &rcu_sync_ops, &rcu_expedited_ops,
+ &rcu_bh_ops, &rcu_bh_sync_ops,
+ &srcu_ops, &srcu_expedited_ops,
+ &sched_ops, &sched_sync_ops, &sched_expedited_ops, };
mutex_lock(&fullstop_mutex);
break;
}
if (i == ARRAY_SIZE(torture_ops)) {
- printk(KERN_ALERT "rcutorture: invalid torture type: \"%s\"\n",
+ printk(KERN_ALERT "rcu-torture: invalid torture type: \"%s\"\n",
torture_type);
+ printk(KERN_ALERT "rcu-torture types:");
+ for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
+ printk(KERN_ALERT " %s", torture_ops[i]->name);
+ printk(KERN_ALERT "\n");
mutex_unlock(&fullstop_mutex);
return -EINVAL;
}
#ifdef CONFIG_RT_GROUP_SCHED
static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity);
- static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
+ static DEFINE_PER_CPU_SHARED_ALIGNED(struct rt_rq, init_rt_rq_var);
#endif /* CONFIG_RT_GROUP_SCHED */
#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
*/
static DEFINE_SPINLOCK(task_group_lock);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
}
#endif
-#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_USER_SCHED
# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD)
#else /* !CONFIG_USER_SCHED */
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ
- unsigned long last_tick_seen;
unsigned char in_nohz_recently;
#endif
/* capture load from *all* tasks on this cpu: */
struct load_weight load;
unsigned long nr_load_updates;
u64 nr_switches;
- u64 nr_migrations_in;
struct cfs_rq cfs;
struct rt_rq rt;
u64 rt_avg;
u64 age_stamp;
+ u64 idle_stamp;
+ u64 avg_idle;
#endif
/* calc_load related fields */
/**
* runqueue_is_locked
+ * @cpu: the processor in question.
*
* Returns true if the current cpu runqueue is locked.
* This interface allows printk to be called with the runqueue lock
if (!sched_feat_names[i])
return -EINVAL;
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
* default: 0.25ms
*/
unsigned int sysctl_sched_shares_ratelimit = 250000;
+unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
/*
* Inject some fuzzyness into changing the per-cpu group shares
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0, shares = 0;
+ unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
unsigned long *usd_rq_weight;
struct sched_domain *sd = data;
unsigned long flags;
weight = tg->cfs_rq[i]->load.weight;
usd_rq_weight[i] = weight;
+ rq_weight += weight;
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
if (!weight)
weight = NICE_0_LOAD;
- rq_weight += weight;
+ sum_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
+ if (!rq_weight)
+ rq_weight = sum_weight;
+
if ((!shares && rq_weight) || shares > tg->shares)
shares = tg->shares;
#endif
static void calc_load_account_active(struct rq *this_rq);
+static void update_sysctl(void);
+static int get_update_sysctl_factor(void);
+
+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+ set_task_rq(p, cpu);
+#ifdef CONFIG_SMP
+ /*
+ * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
+ * successfuly executed on another CPU. We must ensure that updates of
+ * per-task data have been completed by this moment.
+ */
+ smp_wmb();
+ task_thread_info(p)->cpu = cpu;
+#endif
+}
#include "sched_stats.h"
#include "sched_idletask.c"
return cpu_curr(task_cpu(p)) == p;
}
-static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
-{
- set_task_rq(p, cpu);
-#ifdef CONFIG_SMP
- /*
- * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be
- * successfuly executed on another CPU. We must ensure that updates of
- * per-task data have been completed by this moment.
- */
- smp_wmb();
- task_thread_info(p)->cpu = cpu;
-#endif
-}
-
static inline void check_class_changed(struct rq *rq, struct task_struct *p,
const struct sched_class *prev_class,
int oldprio, int running)
p->sched_class->prio_changed(rq, p, oldprio, running);
}
+/**
+ * kthread_bind - bind a just-created kthread to a cpu.
+ * @p: thread created by kthread_create().
+ * @cpu: cpu (might not be online, must be possible) for @k to run on.
+ *
+ * Description: This function is equivalent to set_cpus_allowed(),
+ * except that @cpu doesn't need to be online, and the thread must be
+ * stopped (i.e., just returned from kthread_create()).
+ *
+ * Function lives here instead of kthread.c because it messes with
+ * scheduler internals which require locking.
+ */
+void kthread_bind(struct task_struct *p, unsigned int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ /* Must have done schedule() in kthread() before we set_task_cpu */
+ if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE)) {
+ WARN_ON(1);
+ return;
+ }
+
+ spin_lock_irqsave(&rq->lock, flags);
+ update_rq_clock(rq);
+ set_task_cpu(p, cpu);
+ p->cpus_allowed = cpumask_of_cpu(cpu);
+ p->rt.nr_cpus_allowed = 1;
+ p->flags |= PF_THREAD_BOUND;
+ spin_unlock_irqrestore(&rq->lock, flags);
+}
+EXPORT_SYMBOL(kthread_bind);
+
#ifdef CONFIG_SMP
/*
* Is this task likely cache-hot:
/*
* Buddy candidates are cache hot:
*/
- if (sched_feat(CACHE_HOT_BUDDY) &&
+ if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running &&
(&p->se == cfs_rq_of(&p->se)->next ||
&p->se == cfs_rq_of(&p->se)->last))
return 1;
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
{
int old_cpu = task_cpu(p);
- struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu);
struct cfs_rq *old_cfsrq = task_cfs_rq(p),
*new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu);
- u64 clock_offset;
-
- clock_offset = old_rq->clock - new_rq->clock;
trace_sched_migrate_task(p, new_cpu);
-#ifdef CONFIG_SCHEDSTATS
- if (p->se.wait_start)
- p->se.wait_start -= clock_offset;
- if (p->se.sleep_start)
- p->se.sleep_start -= clock_offset;
- if (p->se.block_start)
- p->se.block_start -= clock_offset;
-#endif
if (old_cpu != new_cpu) {
p->se.nr_migrations++;
- new_rq->nr_migrations_in++;
-#ifdef CONFIG_SCHEDSTATS
- if (task_hot(p, old_rq->clock, NULL))
- schedstat_inc(p, se.nr_forced2_migrations);
-#endif
perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS,
1, 1, NULL, 0);
}
* it is sufficient to simply update the task's cpu field.
*/
if (!p->se.on_rq && !task_running(rq, p)) {
+ update_rq_clock(rq);
set_task_cpu(p, dest_cpu);
return 0;
}
preempt_enable();
}
+#ifdef CONFIG_SMP
+static inline
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
+{
+ return p->sched_class->select_task_rq(p, sd_flags, wake_flags);
+}
+#endif
+
/***
* try_to_wake_up - wake up a thread
* @p: the to-be-woken-up thread
{
int cpu, orig_cpu, this_cpu, success = 0;
unsigned long flags;
- struct rq *rq;
+ struct rq *rq, *orig_rq;
if (!sched_feat(SYNC_WAKEUPS))
wake_flags &= ~WF_SYNC;
this_cpu = get_cpu();
smp_wmb();
- rq = task_rq_lock(p, &flags);
+ rq = orig_rq = task_rq_lock(p, &flags);
update_rq_clock(rq);
if (!(p->state & state))
goto out;
if (task_contributes_to_load(p))
rq->nr_uninterruptible--;
p->state = TASK_WAKING;
- task_rq_unlock(rq, &flags);
+ __task_rq_unlock(rq);
- cpu = p->sched_class->select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
+ cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
if (cpu != orig_cpu)
set_task_cpu(p, cpu);
- rq = task_rq_lock(p, &flags);
+ rq = __task_rq_lock(p);
+ update_rq_clock(rq);
+
WARN_ON(p->state != TASK_WAKING);
cpu = task_cpu(p);
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
p->sched_class->task_wake_up(rq, p);
+
+ if (unlikely(rq->idle_stamp)) {
+ u64 delta = rq->clock - rq->idle_stamp;
+ u64 max = 2*sysctl_sched_migration_cost;
+
+ if (delta > max)
+ rq->avg_idle = max;
+ else
+ update_avg(&rq->avg_idle, delta);
+ rq->idle_stamp = 0;
+ }
#endif
out:
task_rq_unlock(rq, &flags);
p->se.avg_overlap = 0;
p->se.start_runtime = 0;
p->se.avg_wakeup = sysctl_sched_wakeup_granularity;
- p->se.avg_running = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
p->se.nr_failed_migrations_running = 0;
p->se.nr_failed_migrations_hot = 0;
p->se.nr_forced_migrations = 0;
- p->se.nr_forced2_migrations = 0;
p->se.nr_wakeups = 0;
p->se.nr_wakeups_sync = 0;
__sched_fork(p);
- /*
- * Make sure we do not leak PI boosting priority to the child.
- */
- p->prio = current->normal_prio;
-
/*
* Revert to default priority/policy on fork if requested.
*/
if (unlikely(p->sched_reset_on_fork)) {
- if (p->policy == SCHED_FIFO || p->policy == SCHED_RR)
+ if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) {
p->policy = SCHED_NORMAL;
-
- if (p->normal_prio < DEFAULT_PRIO)
- p->prio = DEFAULT_PRIO;
+ p->normal_prio = p->static_prio;
+ }
if (PRIO_TO_NICE(p->static_prio) < 0) {
p->static_prio = NICE_TO_PRIO(0);
+ p->normal_prio = p->static_prio;
set_load_weight(p);
}
p->sched_reset_on_fork = 0;
}
+ /*
+ * Make sure we do not leak PI boosting priority to the child.
+ */
+ p->prio = current->normal_prio;
+
if (!rt_prio(p->prio))
p->sched_class = &fair_sched_class;
+ if (p->sched_class->task_fork)
+ p->sched_class->task_fork(p);
+
#ifdef CONFIG_SMP
- cpu = p->sched_class->select_task_rq(p, SD_BALANCE_FORK, 0);
+ cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
#endif
set_task_cpu(p, cpu);
rq = task_rq_lock(p, &flags);
BUG_ON(p->state != TASK_RUNNING);
update_rq_clock(rq);
-
- p->prio = effective_prio(p);
-
- if (!p->sched_class->task_new || !current->se.on_rq) {
- activate_task(rq, p, 0);
- } else {
- /*
- * Let the scheduling class do new task startup
- * management (if any):
- */
- p->sched_class->task_new(rq, p);
- inc_nr_running(rq);
- }
+ activate_task(rq, p, 0);
trace_sched_wakeup_new(rq, p, 1);
check_preempt_curr(rq, p, WF_FORK);
#ifdef CONFIG_SMP
*/
arch_start_context_switch(prev);
- if (unlikely(!mm)) {
+ if (likely(!mm)) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
- if (unlikely(!prev->mm)) {
+ if (likely(!prev->mm)) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
}
}
-/*
- * Externally visible per-cpu scheduler statistics:
- * cpu_nr_migrations(cpu) - number of migrations into that cpu
- */
-u64 cpu_nr_migrations(int cpu)
-{
- return cpu_rq(cpu)->nr_migrations_in;
-}
-
/*
* Update rq->cpu_load[] statistics. This function is usually called every
* scheduler tick (TICK_NSEC).
void sched_exec(void)
{
int new_cpu, this_cpu = get_cpu();
- new_cpu = current->sched_class->select_task_rq(current, SD_BALANCE_EXEC, 0);
+ new_cpu = select_task_rq(current, SD_BALANCE_EXEC, 0);
put_cpu();
if (new_cpu != this_cpu)
sched_migrate_task(current, new_cpu);
deactivate_task(src_rq, p, 0);
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
- /*
- * Note that idle threads have a prio of MAX_PRIO, for this test
- * to be always true for them.
- */
check_preempt_curr(this_rq, p, 0);
}
/**
* update_sg_lb_stats - Update sched_group's statistics for load balancing.
+ * @sd: The sched_domain whose statistics are to be updated.
* @group: sched_group whose statistics are to be updated.
* @this_cpu: Cpu for which load balance is currently performed.
* @idle: Idle status of this_cpu
unsigned long flags;
struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
- cpumask_setall(cpus);
+ cpumask_copy(cpus, cpu_active_mask);
/*
* When power savings policy is enabled for the parent domain, idle
int all_pinned = 0;
struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
- cpumask_setall(cpus);
+ cpumask_copy(cpus, cpu_active_mask);
/*
* When power savings policy is enabled for the parent domain, idle
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
+ this_rq->idle_stamp = this_rq->clock;
+
+ if (this_rq->avg_idle < sysctl_sched_migration_cost)
+ return;
+
for_each_domain(this_cpu, sd) {
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
next_balance = sd->last_balance + interval;
- if (pulled_task)
+ if (pulled_task) {
+ this_rq->idle_stamp = 0;
break;
+ }
}
if (pulled_task || time_after(jiffies, this_rq->next_balance)) {
/*
cpumask_set_cpu(cpu, nohz.cpu_mask);
/* time for ilb owner also to sleep */
- if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) {
+ if (cpumask_weight(nohz.cpu_mask) == num_active_cpus()) {
if (atomic_read(&nohz.load_balancer) == cpu)
atomic_set(&nohz.load_balancer, -1);
return 0;
p->gtime = cputime_add(p->gtime, cputime);
/* Add guest time to cpustat. */
- cpustat->user = cputime64_add(cpustat->user, tmp);
- cpustat->guest = cputime64_add(cpustat->guest, tmp);
+ if (TASK_NICE(p) > 0) {
+ cpustat->nice = cputime64_add(cpustat->nice, tmp);
+ cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp);
+ } else {
+ cpustat->user = cputime64_add(cpustat->user, tmp);
+ cpustat->guest = cputime64_add(cpustat->guest, tmp);
+ }
}
/*
* Use precise platform statistics if available:
*/
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-cputime_t task_utime(struct task_struct *p)
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- return p->utime;
+ *ut = p->utime;
+ *st = p->stime;
}
-cputime_t task_stime(struct task_struct *p)
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- return p->stime;
+ struct task_cputime cputime;
+
+ thread_group_cputime(p, &cputime);
+
+ *ut = cputime.utime;
+ *st = cputime.stime;
}
#else
-cputime_t task_utime(struct task_struct *p)
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
+#endif
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- clock_t utime = cputime_to_clock_t(p->utime),
- total = utime + cputime_to_clock_t(p->stime);
- u64 temp;
+ cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime);
/*
* Use CFS's precise accounting:
*/
- temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime);
+ rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
if (total) {
- temp *= utime;
+ u64 temp;
+
+ temp = (u64)(rtime * utime);
do_div(temp, total);
- }
- utime = (clock_t)temp;
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
+
+ /*
+ * Compare with previous values, to keep monotonicity:
+ */
+ p->prev_utime = max(p->prev_utime, utime);
+ p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime));
- p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
- return p->prev_utime;
+ *ut = p->prev_utime;
+ *st = p->prev_stime;
}
-cputime_t task_stime(struct task_struct *p)
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
{
- clock_t stime;
+ struct signal_struct *sig = p->signal;
+ struct task_cputime cputime;
+ cputime_t rtime, utime, total;
- /*
- * Use CFS's precise accounting. (we subtract utime from
- * the total, to make sure the total observed by userspace
- * grows monotonically - apps rely on that):
- */
- stime = nsec_to_clock_t(p->se.sum_exec_runtime) -
- cputime_to_clock_t(task_utime(p));
+ thread_group_cputime(p, &cputime);
- if (stime >= 0)
- p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime));
+ total = cputime_add(cputime.utime, cputime.stime);
+ rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
- return p->prev_stime;
-}
-#endif
+ if (total) {
+ u64 temp;
-inline cputime_t task_gtime(struct task_struct *p)
-{
- return p->gtime;
+ temp = (u64)(rtime * cputime.utime);
+ do_div(temp, total);
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
+
+ sig->prev_utime = max(sig->prev_utime, utime);
+ sig->prev_stime = max(sig->prev_stime,
+ cputime_sub(rtime, sig->prev_utime));
+
+ *ut = sig->prev_utime;
+ *st = sig->prev_stime;
}
+#endif
/*
* This function gets called by the timer code, with HZ frequency.
#endif
}
-static void put_prev_task(struct rq *rq, struct task_struct *p)
+static void put_prev_task(struct rq *rq, struct task_struct *prev)
{
- u64 runtime = p->se.sum_exec_runtime - p->se.prev_sum_exec_runtime;
+ if (prev->state == TASK_RUNNING) {
+ u64 runtime = prev->se.sum_exec_runtime;
- update_avg(&p->se.avg_running, runtime);
+ runtime -= prev->se.prev_sum_exec_runtime;
+ runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
- if (p->state == TASK_RUNNING) {
/*
* In order to avoid avg_overlap growing stale when we are
* indeed overlapping and hence not getting put to sleep, grow
* correlates to the amount of cache footprint a task can
* build up.
*/
- runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost);
- update_avg(&p->se.avg_overlap, runtime);
- } else {
- update_avg(&p->se.avg_running, 0);
+ update_avg(&prev->se.avg_overlap, runtime);
}
- p->sched_class->put_prev_task(rq, p);
+ prev->sched_class->put_prev_task(rq, prev);
}
/*
}
EXPORT_SYMBOL(schedule);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Look out! "owner" is an entirely speculative pointer
* access and not reliable.
BUG_ON(p->se.on_rq);
p->policy = policy;
- switch (p->policy) {
- case SCHED_NORMAL:
- case SCHED_BATCH:
- case SCHED_IDLE:
- p->sched_class = &fair_sched_class;
- break;
- case SCHED_FIFO:
- case SCHED_RR:
- p->sched_class = &rt_sched_class;
- break;
- }
-
p->rt_priority = prio;
p->normal_prio = normal_prio(p);
/* we are holding p->pi_lock already */
p->prio = rt_mutex_getprio(p);
+ if (rt_prio(p->prio))
+ p->sched_class = &rt_sched_class;
+ else
+ p->sched_class = &fair_sched_class;
set_load_weight(p);
}
long sched_getaffinity(pid_t pid, struct cpumask *mask)
{
struct task_struct *p;
+ unsigned long flags;
+ struct rq *rq;
int retval;
get_online_cpus();
if (retval)
goto out_unlock;
+ rq = task_rq_lock(p, &flags);
cpumask_and(mask, &p->cpus_allowed, cpu_online_mask);
+ task_rq_unlock(rq, &flags);
out_unlock:
read_unlock(&tasklist_lock);
/*
* This task is about to go to sleep on IO. Increment rq->nr_iowait so
* that process accounting knows that this is a task in IO wait state.
- *
- * But don't do that if it is a deliberate, throttling IO wait (this task
- * has set its backing_dev_info: the queue against which it should throttle)
*/
void __sched io_schedule(void)
{
{
struct task_struct *p;
unsigned int time_slice;
+ unsigned long flags;
+ struct rq *rq;
int retval;
struct timespec t;
if (retval)
goto out_unlock;
- time_slice = p->sched_class->get_rr_interval(p);
+ rq = task_rq_lock(p, &flags);
+ time_slice = p->sched_class->get_rr_interval(rq, p);
+ task_rq_unlock(rq, &flags);
read_unlock(&tasklist_lock);
jiffies_to_timespec(time_slice, &t);
/*
* Only show locks if all tasks are dumped:
*/
- if (state_filter == -1)
+ if (!state_filter)
debug_show_all_locks();
}
__sched_fork(idle);
idle->se.exec_start = sched_clock();
- idle->prio = idle->normal_prio = MAX_PRIO;
cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
__set_task_cpu(idle, cpu);
*
* This idea comes from the SD scheduler of Con Kolivas:
*/
-static inline void sched_init_granularity(void)
+static int get_update_sysctl_factor(void)
{
- unsigned int factor = 1 + ilog2(num_online_cpus());
- const unsigned long limit = 200000000;
+ unsigned int cpus = min_t(int, num_online_cpus(), 8);
+ unsigned int factor;
+
+ switch (sysctl_sched_tunable_scaling) {
+ case SCHED_TUNABLESCALING_NONE:
+ factor = 1;
+ break;
+ case SCHED_TUNABLESCALING_LINEAR:
+ factor = cpus;
+ break;
+ case SCHED_TUNABLESCALING_LOG:
+ default:
+ factor = 1 + ilog2(cpus);
+ break;
+ }
- sysctl_sched_min_granularity *= factor;
- if (sysctl_sched_min_granularity > limit)
- sysctl_sched_min_granularity = limit;
+ return factor;
+}
- sysctl_sched_latency *= factor;
- if (sysctl_sched_latency > limit)
- sysctl_sched_latency = limit;
+static void update_sysctl(void)
+{
+ unsigned int factor = get_update_sysctl_factor();
- sysctl_sched_wakeup_granularity *= factor;
+#define SET_SYSCTL(name) \
+ (sysctl_##name = (factor) * normalized_sysctl_##name)
+ SET_SYSCTL(sched_min_granularity);
+ SET_SYSCTL(sched_latency);
+ SET_SYSCTL(sched_wakeup_granularity);
+ SET_SYSCTL(sched_shares_ratelimit);
+#undef SET_SYSCTL
+}
- sysctl_sched_shares_ratelimit *= factor;
+static inline void sched_init_granularity(void)
+{
+ update_sysctl();
}
#ifdef CONFIG_SMP
int ret = 0;
rq = task_rq_lock(p, &flags);
- if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+ if (!cpumask_intersects(new_mask, cpu_active_mask)) {
ret = -EINVAL;
goto out;
}
if (cpumask_test_cpu(task_cpu(p), new_mask))
goto out;
- if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
+ if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
/* Need help from migration thread: drop lock and wait. */
struct task_struct *mt = rq->migration_thread;
again:
/* Look for allowed, online CPU in same node. */
- for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask)
+ for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask)
if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
goto move;
/* Any allowed, online CPU? */
- dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask);
+ dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
if (dest_cpu < nr_cpu_ids)
goto move;
/* No more Mr. Nice Guy. */
if (dest_cpu >= nr_cpu_ids) {
cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
- dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed);
+ dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
/*
* Don't tell them about moving exiting tasks or
*/
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
+ struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
unsigned long flags;
local_irq_save(flags);
.procname = "sched_domain",
.mode = 0555,
},
- {0, },
+ {}
};
static struct ctl_table sd_ctl_root[] = {
{
- .ctl_name = CTL_KERN,
.procname = "kernel",
.mode = 0555,
.child = sd_ctl_dir,
},
- {0, },
+ {}
};
static struct ctl_table *sd_alloc_ctl_entry(int n)
static struct ctl_table_header *sd_sysctl_header;
static void register_sched_domain_sysctl(void)
{
- int i, cpu_num = num_online_cpus();
+ int i, cpu_num = num_possible_cpus();
struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1);
char buf[32];
if (entry == NULL)
return;
- for_each_online_cpu(i) {
+ for_each_possible_cpu(i) {
snprintf(buf, 32, "cpu%d", i);
entry->procname = kstrdup(buf, GFP_KERNEL);
entry->mode = 0555;
spin_lock_irq(&rq->lock);
update_rq_clock(rq);
deactivate_task(rq, rq->idle, 0);
- rq->idle->static_prio = MAX_PRIO;
__setscheduler(rq, rq->idle, SCHED_NORMAL, 0);
rq->idle->sched_class = &idle_sched_class;
migrate_dead_tasks(cpu);
#ifdef CONFIG_SCHED_DEBUG
+static __read_mostly int sched_domain_debug_enabled;
+
+static int __init sched_domain_debug_setup(char *str)
+{
+ sched_domain_debug_enabled = 1;
+
+ return 0;
+}
+early_param("sched_debug", sched_domain_debug_setup);
+
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
struct cpumask *groupmask)
{
cpumask_var_t groupmask;
int level = 0;
+ if (!sched_domain_debug_enabled)
+ return;
+
if (!sd) {
printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu);
return;
static void free_rootdomain(struct root_domain *rd)
{
+ synchronize_sched();
+
cpupri_cleanup(&rd->cpupri);
free_cpumask_var(rd->rto_mask);
/* Setup the mask of cpus configured for isolated domains */
static int __init isolated_cpu_setup(char *str)
{
+ alloc_bootmem_cpumask_var(&cpu_isolated_map);
cpulist_parse(str, cpu_isolated_map);
return 1;
}
*/
#ifdef CONFIG_SCHED_SMT
static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains);
- static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus);
+ static DEFINE_PER_CPU(struct static_sched_group, sched_groups);
static int
cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
struct sched_group **sg, struct cpumask *unused)
{
if (sg)
- *sg = &per_cpu(sched_group_cpus, cpu).sg;
+ *sg = &per_cpu(sched_groups, cpu).sg;
return cpu;
}
#endif /* CONFIG_SCHED_SMT */
return __build_sched_domains(cpu_map, NULL);
}
-static struct cpumask *doms_cur; /* current sched domains */
+static cpumask_var_t *doms_cur; /* current sched domains */
static int ndoms_cur; /* number of sched domains in 'doms_cur' */
static struct sched_domain_attr *dattr_cur;
/* attribues of custom domains in 'doms_cur' */
return 0;
}
+cpumask_var_t *alloc_sched_domains(unsigned int ndoms)
+{
+ int i;
+ cpumask_var_t *doms;
+
+ doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL);
+ if (!doms)
+ return NULL;
+ for (i = 0; i < ndoms; i++) {
+ if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) {
+ free_sched_domains(doms, i);
+ return NULL;
+ }
+ }
+ return doms;
+}
+
+void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
+{
+ unsigned int i;
+ for (i = 0; i < ndoms; i++)
+ free_cpumask_var(doms[i]);
+ kfree(doms);
+}
+
/*
* Set up scheduler domains and groups. Callers must hold the hotplug lock.
* For now this just excludes isolated cpus, but could be used to
arch_update_cpu_topology();
ndoms_cur = 1;
- doms_cur = kmalloc(cpumask_size(), GFP_KERNEL);
+ doms_cur = alloc_sched_domains(ndoms_cur);
if (!doms_cur)
- doms_cur = fallback_doms;
- cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map);
+ doms_cur = &fallback_doms;
+ cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map);
dattr_cur = NULL;
- err = build_sched_domains(doms_cur);
+ err = build_sched_domains(doms_cur[0]);
register_sched_domain_sysctl();
return err;
* doms_new[] to the current sched domain partitioning, doms_cur[].
* It destroys each deleted domain and builds each new domain.
*
- * 'doms_new' is an array of cpumask's of length 'ndoms_new'.
+ * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'.
* The masks don't intersect (don't overlap.) We should setup one
* sched domain for each mask. CPUs not in any of the cpumasks will
* not be load balanced. If the same cpumask appears both in the
* current 'doms_cur' domains and in the new 'doms_new', we can leave
* it as it is.
*
- * The passed in 'doms_new' should be kmalloc'd. This routine takes
- * ownership of it and will kfree it when done with it. If the caller
- * failed the kmalloc call, then it can pass in doms_new == NULL &&
- * ndoms_new == 1, and partition_sched_domains() will fallback to
- * the single partition 'fallback_doms', it also forces the domains
- * to be rebuilt.
+ * The passed in 'doms_new' should be allocated using
+ * alloc_sched_domains. This routine takes ownership of it and will
+ * free_sched_domains it when done with it. If the caller failed the
+ * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1,
+ * and partition_sched_domains() will fallback to the single partition
+ * 'fallback_doms', it also forces the domains to be rebuilt.
*
* If doms_new == NULL it will be replaced with cpu_online_mask.
* ndoms_new == 0 is a special case for destroying existing domains,
*
* Call with hotplug lock held
*/
-/* FIXME: Change to struct cpumask *doms_new[] */
-void partition_sched_domains(int ndoms_new, struct cpumask *doms_new,
+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
struct sched_domain_attr *dattr_new)
{
int i, j, n;
/* Destroy deleted domains */
for (i = 0; i < ndoms_cur; i++) {
for (j = 0; j < n && !new_topology; j++) {
- if (cpumask_equal(&doms_cur[i], &doms_new[j])
+ if (cpumask_equal(doms_cur[i], doms_new[j])
&& dattrs_equal(dattr_cur, i, dattr_new, j))
goto match1;
}
/* no match - a current sched domain not in new doms_new[] */
- detach_destroy_domains(doms_cur + i);
+ detach_destroy_domains(doms_cur[i]);
match1:
;
}
if (doms_new == NULL) {
ndoms_cur = 0;
- doms_new = fallback_doms;
- cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map);
+ doms_new = &fallback_doms;
+ cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map);
WARN_ON_ONCE(dattr_new);
}
/* Build new domains */
for (i = 0; i < ndoms_new; i++) {
for (j = 0; j < ndoms_cur && !new_topology; j++) {
- if (cpumask_equal(&doms_new[i], &doms_cur[j])
+ if (cpumask_equal(doms_new[i], doms_cur[j])
&& dattrs_equal(dattr_new, i, dattr_cur, j))
goto match2;
}
/* no match - add a new doms_new */
- __build_sched_domains(doms_new + i,
+ __build_sched_domains(doms_new[i],
dattr_new ? dattr_new + i : NULL);
match2:
;
}
/* Remember the new sched domains */
- if (doms_cur != fallback_doms)
- kfree(doms_cur);
+ if (doms_cur != &fallback_doms)
+ free_sched_domains(doms_cur, ndoms_cur);
kfree(dattr_cur); /* kfree(NULL) is safe */
doms_cur = doms_new;
dattr_cur = dattr_new;
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
partition_sched_domains(1, NULL, NULL);
return NOTIFY_OK;
#endif
get_online_cpus();
mutex_lock(&sched_domains_mutex);
- arch_init_sched_domains(cpu_online_mask);
+ arch_init_sched_domains(cpu_active_mask);
cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map);
if (cpumask_empty(non_isolated_cpus))
cpumask_set_cpu(smp_processor_id(), non_isolated_cpus);
#ifdef CONFIG_CPUMASK_OFFSTACK
alloc_size += num_possible_cpus() * cpumask_size();
#endif
- /*
- * As sched_init() is called before page_alloc is setup,
- * we use alloc_bootmem().
- */
if (alloc_size) {
ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT);
#elif defined CONFIG_USER_SCHED
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL);
init_tg_rt_entry(&init_task_group,
- &per_cpu(init_rt_rq, i),
+ &per_cpu(init_rt_rq_var, i),
&per_cpu(init_sched_rt_entity, i), i, 1,
root_task_group.rt_se[i]);
#endif
rq->cpu = i;
rq->online = 0;
rq->migration_thread = NULL;
+ rq->idle_stamp = 0;
+ rq->avg_idle = 2*sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->migration_queue);
rq_attach_root(rq, &def_root_domain);
#endif
current->sched_class = &fair_sched_class;
/* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */
- alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT);
#ifdef CONFIG_SMP
#ifdef CONFIG_NO_HZ
- alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
+ zalloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT);
alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT);
#endif
- alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+ /* May be allocated at isolcpus cmdline parse time */
+ if (cpu_isolated_map == NULL)
+ zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
#endif /* SMP */
perf_event_init();
se = kzalloc_node(sizeof(struct sched_entity),
GFP_KERNEL, cpu_to_node(i));
if (!se)
- goto err;
+ goto err_free_rq;
init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]);
}
return 1;
+ err_free_rq:
+ kfree(cfs_rq);
err:
return 0;
}
rt_se = kzalloc_node(sizeof(struct sched_rt_entity),
GFP_KERNEL, cpu_to_node(i));
if (!rt_se)
- goto err;
+ goto err_free_rq;
init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]);
}
return 1;
+ err_free_rq:
+ kfree(rt_rq);
err:
return 0;
}
spin_unlock_irqrestore(&rq->lock, flags);
}
rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+ synchronize_sched_expedited_count++;
mutex_unlock(&rcu_sched_expedited_mutex);
put_online_cpus();
if (need_full_sync)
if (!in_interrupt() && local_softirq_pending())
invoke_softirq();
+ rcu_irq_exit();
#ifdef CONFIG_NO_HZ
/* Make sure that timer wheel updates are propagated */
- rcu_irq_exit();
if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
tick_nohz_stop_sched_tick(0);
#endif
open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}
- static int ksoftirqd(void * __bind_cpu)
+ static int run_ksoftirqd(void * __bind_cpu)
{
set_current_state(TASK_INTERRUPTIBLE);
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
- p = kthread_create(ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
+ p = kthread_create(run_ksoftirqd, hcpu, "ksoftirqd/%d", hotcpu);
if (IS_ERR(p)) {
printk("ksoftirqd for %i failed\n", hotcpu);
return NOTIFY_BAD;
*/
static int tracing_disabled = 1;
- DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+ DEFINE_PER_CPU(int, ftrace_cpu_disabled);
static inline void ftrace_disable_cpu(void)
{
preempt_disable();
- local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_inc(per_cpu_var(ftrace_cpu_disabled));
}
static inline void ftrace_enable_cpu(void)
{
- local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+ __this_cpu_dec(per_cpu_var(ftrace_cpu_disabled));
preempt_enable();
}
static char bootup_tracer_buf[MAX_TRACER_SIZE] __initdata;
static char *default_bootup_tracer;
-static int __init set_ftrace(char *str)
+static int __init set_cmdline_ftrace(char *str)
{
strncpy(bootup_tracer_buf, str, MAX_TRACER_SIZE);
default_bootup_tracer = bootup_tracer_buf;
ring_buffer_expanded = 1;
return 1;
}
-__setup("ftrace=", set_ftrace);
+__setup("ftrace=", set_cmdline_ftrace);
static int __init set_ftrace_dump_on_oops(char *str)
{
*/
static struct trace_array max_tr;
- static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
+ static DEFINE_PER_CPU(struct trace_array_cpu, max_tr_data);
/* tracer_enabled is used to toggle activation of a tracer */
static int tracer_enabled = 1;
struct ftrace_entry *entry;
/* If we are reading the ring buffer, don't trace */
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_FN, sizeof(*entry),
__raw_spin_lock(&trace_buf_lock);
len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
- len = min(len, TRACE_BUF_SIZE-1);
- trace_buf[len] = 0;
-
size = sizeof(*entry) + len + 1;
buffer = tr->buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
if (!event)
goto out_unlock;
entry = ring_buffer_event_data(event);
- entry->ip = ip;
+ entry->ip = ip;
memcpy(&entry->buf, trace_buf, len);
- entry->buf[len] = 0;
+ entry->buf[len] = '\0';
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
- return trace_array_printk(&global_trace, ip, fmt, args);
+ return trace_array_vprintk(&global_trace, ip, fmt, args);
}
EXPORT_SYMBOL_GPL(trace_vprintk);
int i = (int)*pos;
void *ent;
+ WARN_ON_ONCE(iter->leftover);
+
(*pos)++;
/* can't go backwards */
;
} else {
- l = *pos - 1;
- p = s_next(m, p, &l);
+ /*
+ * If we overflowed the seq_file before, then we want
+ * to just reuse the trace_seq buffer again.
+ */
+ if (iter->leftover)
+ p = iter;
+ else {
+ l = *pos - 1;
+ p = s_next(m, p, &l);
+ }
}
trace_event_read_lock();
static int s_show(struct seq_file *m, void *v)
{
struct trace_iterator *iter = v;
+ int ret;
if (iter->ent == NULL) {
if (iter->tr) {
if (!(trace_flags & TRACE_ITER_VERBOSE))
print_func_help_header(m);
}
+ } else if (iter->leftover) {
+ /*
+ * If we filled the seq_file buffer earlier, we
+ * want to just show it now.
+ */
+ ret = trace_print_seq(m, &iter->seq);
+
+ /* ret should this time be zero, but you never know */
+ iter->leftover = ret;
+
} else {
print_trace_line(iter);
- trace_print_seq(m, &iter->seq);
+ ret = trace_print_seq(m, &iter->seq);
+ /*
+ * If we overflow the seq_file buffer, then it will
+ * ask us for this data again at start up.
+ * Use that instead.
+ * ret is 0 if seq_file write succeeded.
+ * -1 otherwise.
+ */
+ iter->leftover = ret;
}
return 0;
return ret;
}
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
}
mutex_unlock(&trace_types_lock);
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
if (err)
return err;
- filp->f_pos += ret;
+ *ppos += ret;
return ret;
}
else
cpumask_clear_cpu(iter->cpu_file, tracing_reader_cpumask);
+
+ if (iter->trace->pipe_close)
+ iter->trace->pipe_close(iter);
+
mutex_unlock(&trace_types_lock);
free_cpumask_var(iter->started);
}
}
- filp->f_pos += cnt;
+ *ppos += cnt;
/* If check pages failed, return ENOMEM */
if (tracing_disabled)
size_t cnt, loff_t *fpos)
{
char *buf;
- char *end;
if (tracing_disabled)
return -EINVAL;
if (cnt > TRACE_BUF_SIZE)
cnt = TRACE_BUF_SIZE;
- buf = kmalloc(cnt + 1, GFP_KERNEL);
+ buf = kmalloc(cnt + 2, GFP_KERNEL);
if (buf == NULL)
return -ENOMEM;
kfree(buf);
return -EFAULT;
}
+ if (buf[cnt-1] != '\n') {
+ buf[cnt] = '\n';
+ buf[cnt+1] = '\0';
+ } else
+ buf[cnt] = '\0';
- /* Cut from the first nil or newline. */
- buf[cnt] = '\0';
- end = strchr(buf, '\n');
- if (end)
- *end = '\0';
-
- cnt = mark_printk("%s\n", buf);
+ cnt = mark_printk("%s", buf);
kfree(buf);
*fpos += cnt;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
- return ENOMEM;
+ return -ENOMEM;
trace_seq_init(s);
/* Allocate the first page for all buffers */
for_each_tracing_cpu(i) {
global_trace.data[i] = &per_cpu(global_trace_cpu, i);
- max_tr.data[i] = &per_cpu(max_data, i);
+ max_tr.data[i] = &per_cpu(max_tr_data, i);
}
trace_init_cmdlines();
#include <linux/ftrace.h>
#include <trace/boot.h>
#include <linux/kmemtrace.h>
+#include <linux/hw_breakpoint.h>
#include <linux/trace_seq.h>
#include <linux/ftrace_event.h>
TRACE_KMEM_ALLOC,
TRACE_KMEM_FREE,
TRACE_BLK,
+ TRACE_KSYM,
__TRACE_LAST_TYPE,
};
struct syscall_trace_exit {
struct trace_entry ent;
int nr;
- unsigned long ret;
+ long ret;
};
+struct kprobe_trace_entry {
+ struct trace_entry ent;
+ unsigned long ip;
+ int nargs;
+ unsigned long args[];
+};
+
+#define SIZEOF_KPROBE_TRACE_ENTRY(n) \
+ (offsetof(struct kprobe_trace_entry, args) + \
+ (sizeof(unsigned long) * (n)))
+
+struct kretprobe_trace_entry {
+ struct trace_entry ent;
+ unsigned long func;
+ unsigned long ret_ip;
+ int nargs;
+ unsigned long args[];
+};
+
+#define SIZEOF_KRETPROBE_TRACE_ENTRY(n) \
+ (offsetof(struct kretprobe_trace_entry, args) + \
+ (sizeof(unsigned long) * (n)))
+
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
TRACE_KMEM_ALLOC); \
IF_ASSIGN(var, ent, struct kmemtrace_free_entry, \
TRACE_KMEM_FREE); \
+ IF_ASSIGN(var, ent, struct ksym_trace_entry, TRACE_KSYM);\
__ftrace_bad_type(); \
} while (0)
* @pipe_open: called when the trace_pipe file is opened
* @wait_pipe: override how the user waits for traces on trace_pipe
* @close: called when the trace file is released
+ * @pipe_close: called when the trace_pipe file is released
* @read: override the default read callback on trace_pipe
* @splice_read: override the default splice_read callback on trace_pipe
* @selftest: selftest to run on boot (see trace_selftest.c)
void (*pipe_open)(struct trace_iterator *iter);
void (*wait_pipe)(struct trace_iterator *iter);
void (*close)(struct trace_iterator *iter);
+ void (*pipe_close)(struct trace_iterator *iter);
ssize_t (*read)(struct trace_iterator *iter,
struct file *filp, char __user *ubuf,
size_t cnt, loff_t *ppos);
void unregister_tracer(struct tracer *type);
int is_tracing_stopped(void);
+extern int process_new_ksym_entry(char *ksymname, int op, unsigned long addr);
+
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
#ifdef CONFIG_TRACER_MAX_TRACE
extern int ring_buffer_expanded;
extern bool tracing_selftest_disabled;
- DECLARE_PER_CPU(local_t, ftrace_cpu_disabled);
+ DECLARE_PER_CPU(int, ftrace_cpu_disabled);
#ifdef CONFIG_FTRACE_STARTUP_TEST
extern int trace_selftest_startup_function(struct tracer *trace,
struct trace_array *tr);
extern int trace_selftest_startup_hw_branches(struct tracer *trace,
struct trace_array *tr);
+extern int trace_selftest_startup_ksym(struct tracer *trace,
+ struct trace_array *tr);
#endif /* CONFIG_FTRACE_STARTUP_TEST */
extern void *head_page(struct trace_array_cpu *data);
return 0;
}
#else
-static inline int ftrace_trace_addr(unsigned long addr)
-{
- return 1;
-}
static inline int ftrace_graph_addr(unsigned long addr)
{
return 1;
}
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-extern struct pid *ftrace_pid_trace;
+extern struct list_head ftrace_pids;
#ifdef CONFIG_FUNCTION_TRACER
static inline int ftrace_trace_task(struct task_struct *task)
{
- if (!ftrace_pid_trace)
+ if (list_empty(&ftrace_pids))
return 1;
return test_tsk_trace_trace(task);
int n_preds;
struct filter_pred **preds;
char *filter_string;
- bool no_reset;
};
struct event_subsystem {
};
struct filter_pred;
+struct regex;
typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event,
int val1, int val2);
+typedef int (*regex_match_func)(char *str, struct regex *r, int len);
+
+enum regex_type {
+ MATCH_FULL = 0,
+ MATCH_FRONT_ONLY,
+ MATCH_MIDDLE_ONLY,
+ MATCH_END_ONLY,
+};
+
+struct regex {
+ char pattern[MAX_FILTER_STR_VAL];
+ int len;
+ int field_len;
+ regex_match_func match;
+};
+
struct filter_pred {
- filter_pred_fn_t fn;
- u64 val;
- char str_val[MAX_FILTER_STR_VAL];
- int str_len;
- char *field_name;
- int offset;
- int not;
- int op;
- int pop_n;
+ filter_pred_fn_t fn;
+ u64 val;
+ struct regex regex;
+ char *field_name;
+ int offset;
+ int not;
+ int op;
+ int pop_n;
};
+extern enum regex_type
+filter_parse_regex(char *buff, int len, char **search, int *not);
extern void print_event_filter(struct ftrace_event_call *call,
struct trace_seq *s);
extern int apply_event_filter(struct ftrace_event_call *call,
struct ring_buffer *buffer,
struct ring_buffer_event *event)
{
- if (unlikely(call->filter_active) && !filter_match_preds(call, rec)) {
+ if (unlikely(call->filter_active) &&
+ !filter_match_preds(call->filter, rec)) {
ring_buffer_discard_commit(buffer, event);
return 1;
}
#include "trace.h"
#include "trace_output.h"
-struct fgraph_data {
+struct fgraph_cpu_data {
pid_t last_pid;
int depth;
+ int ignore;
+};
+
+struct fgraph_data {
+ struct fgraph_cpu_data *cpu_data;
+
+ /* Place to preserve last processed entry. */
+ struct ftrace_graph_ent_entry ent;
+ struct ftrace_graph_ret_entry ret;
+ int failed;
+ int cpu;
};
#define TRACE_GRAPH_INDENT 2
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ent_entry *entry;
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
return 0;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_ENT,
struct ring_buffer *buffer = tr->buffer;
struct ftrace_graph_ret_entry *entry;
- if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+ if (unlikely(__this_cpu_read(per_cpu_var(ftrace_cpu_disabled))))
return;
event = trace_buffer_lock_reserve(buffer, TRACE_GRAPH_RET,
if (!data)
return TRACE_TYPE_HANDLED;
- last_pid = &(per_cpu_ptr(data, cpu)->last_pid);
+ last_pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
if (*last_pid == pid)
return TRACE_TYPE_HANDLED;
get_return_for_leaf(struct trace_iterator *iter,
struct ftrace_graph_ent_entry *curr)
{
- struct ring_buffer_iter *ring_iter;
+ struct fgraph_data *data = iter->private;
+ struct ring_buffer_iter *ring_iter = NULL;
struct ring_buffer_event *event;
struct ftrace_graph_ret_entry *next;
- ring_iter = iter->buffer_iter[iter->cpu];
+ /*
+ * If the previous output failed to write to the seq buffer,
+ * then we just reuse the data from before.
+ */
+ if (data && data->failed) {
+ curr = &data->ent;
+ next = &data->ret;
+ } else {
- /* First peek to compare current entry and the next one */
- if (ring_iter)
- event = ring_buffer_iter_peek(ring_iter, NULL);
- else {
- /* We need to consume the current entry to see the next one */
- ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
- event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
- NULL);
- }
+ ring_iter = iter->buffer_iter[iter->cpu];
+
+ /* First peek to compare current entry and the next one */
+ if (ring_iter)
+ event = ring_buffer_iter_peek(ring_iter, NULL);
+ else {
+ /*
+ * We need to consume the current entry to see
+ * the next one.
+ */
+ ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+ event = ring_buffer_peek(iter->tr->buffer, iter->cpu,
+ NULL);
+ }
- if (!event)
- return NULL;
+ if (!event)
+ return NULL;
+
+ next = ring_buffer_event_data(event);
- next = ring_buffer_event_data(event);
+ if (data) {
+ /*
+ * Save current and next entries for later reference
+ * if the output fails.
+ */
+ data->ent = *curr;
+ data->ret = *next;
+ }
+ }
if (next->ent.type != TRACE_GRAPH_RET)
return NULL;
if (data) {
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
/*
* Comments display at + 1 to depth. Since
if (data) {
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
*depth = call->depth;
}
print_graph_entry(struct ftrace_graph_ent_entry *field, struct trace_seq *s,
struct trace_iterator *iter)
{
- int cpu = iter->cpu;
+ struct fgraph_data *data = iter->private;
struct ftrace_graph_ent *call = &field->graph_ent;
struct ftrace_graph_ret_entry *leaf_ret;
+ static enum print_line_t ret;
+ int cpu = iter->cpu;
if (print_graph_prologue(iter, s, TRACE_GRAPH_ENT, call->func))
return TRACE_TYPE_PARTIAL_LINE;
leaf_ret = get_return_for_leaf(iter, field);
if (leaf_ret)
- return print_graph_entry_leaf(iter, field, leaf_ret, s);
+ ret = print_graph_entry_leaf(iter, field, leaf_ret, s);
else
- return print_graph_entry_nested(iter, field, s, cpu);
+ ret = print_graph_entry_nested(iter, field, s, cpu);
+ if (data) {
+ /*
+ * If we failed to write our output, then we need to make
+ * note of it. Because we already consumed our entry.
+ */
+ if (s->full) {
+ data->failed = 1;
+ data->cpu = cpu;
+ } else
+ data->failed = 0;
+ }
+
+ return ret;
}
static enum print_line_t
if (data) {
int cpu = iter->cpu;
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
/*
* Comments display at + 1 to depth. This is the
int i;
if (data)
- depth = per_cpu_ptr(data, iter->cpu)->depth;
+ depth = per_cpu_ptr(data->cpu_data, iter->cpu)->depth;
if (print_graph_prologue(iter, s, 0, 0))
return TRACE_TYPE_PARTIAL_LINE;
enum print_line_t
print_graph_function(struct trace_iterator *iter)
{
+ struct ftrace_graph_ent_entry *field;
+ struct fgraph_data *data = iter->private;
struct trace_entry *entry = iter->ent;
struct trace_seq *s = &iter->seq;
+ int cpu = iter->cpu;
+ int ret;
+
+ if (data && per_cpu_ptr(data->cpu_data, cpu)->ignore) {
+ per_cpu_ptr(data->cpu_data, cpu)->ignore = 0;
+ return TRACE_TYPE_HANDLED;
+ }
+
+ /*
+ * If the last output failed, there's a possibility we need
+ * to print out the missing entry which would never go out.
+ */
+ if (data && data->failed) {
+ field = &data->ent;
+ iter->cpu = data->cpu;
+ ret = print_graph_entry(field, s, iter);
+ if (ret == TRACE_TYPE_HANDLED && iter->cpu != cpu) {
+ per_cpu_ptr(data->cpu_data, iter->cpu)->ignore = 1;
+ ret = TRACE_TYPE_NO_CONSUME;
+ }
+ iter->cpu = cpu;
+ return ret;
+ }
switch (entry->type) {
case TRACE_GRAPH_ENT: {
* sizeof(struct ftrace_graph_ent_entry) is very small,
* it can be safely saved at the stack.
*/
- struct ftrace_graph_ent_entry *field, saved;
+ struct ftrace_graph_ent_entry saved;
trace_assign_type(field, entry);
saved = *field;
return print_graph_entry(&saved, s, iter);
static void graph_trace_open(struct trace_iterator *iter)
{
/* pid and depth on the last trace processed */
- struct fgraph_data *data = alloc_percpu(struct fgraph_data);
+ struct fgraph_data *data;
int cpu;
+ iter->private = NULL;
+
+ data = kzalloc(sizeof(*data), GFP_KERNEL);
if (!data)
- pr_warning("function graph tracer: not enough memory\n");
- else
- for_each_possible_cpu(cpu) {
- pid_t *pid = &(per_cpu_ptr(data, cpu)->last_pid);
- int *depth = &(per_cpu_ptr(data, cpu)->depth);
- *pid = -1;
- *depth = 0;
- }
+ goto out_err;
+
+ data->cpu_data = alloc_percpu(struct fgraph_cpu_data);
+ if (!data->cpu_data)
+ goto out_err_free;
+
+ for_each_possible_cpu(cpu) {
+ pid_t *pid = &(per_cpu_ptr(data->cpu_data, cpu)->last_pid);
+ int *depth = &(per_cpu_ptr(data->cpu_data, cpu)->depth);
+ int *ignore = &(per_cpu_ptr(data->cpu_data, cpu)->ignore);
+ *pid = -1;
+ *depth = 0;
+ *ignore = 0;
+ }
iter->private = data;
+
+ return;
+
+ out_err_free:
+ kfree(data);
+ out_err:
+ pr_warning("function graph tracer: not enough memory\n");
}
static void graph_trace_close(struct trace_iterator *iter)
{
- free_percpu(iter->private);
+ struct fgraph_data *data = iter->private;
+
+ if (data) {
+ free_percpu(data->cpu_data);
+ kfree(data);
+ }
}
static struct tracer graph_trace __read_mostly = {
.name = "function_graph",
.open = graph_trace_open,
+ .pipe_open = graph_trace_open,
.close = graph_trace_close,
+ .pipe_close = graph_trace_close,
.wait_pipe = poll_wait_pipe,
.init = graph_trace_init,
.reset = graph_trace_reset,
#define BTS_BUFFER_SIZE (1 << 13)
- static DEFINE_PER_CPU(struct bts_tracer *, tracer);
- static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], buffer);
+ static DEFINE_PER_CPU(struct bts_tracer *, hwb_tracer);
+ static DEFINE_PER_CPU(unsigned char[BTS_BUFFER_SIZE], hwb_buffer);
- #define this_tracer per_cpu(tracer, smp_processor_id())
+ #define this_tracer per_cpu(hwb_tracer, smp_processor_id())
static int trace_hw_branches_enabled __read_mostly;
static int trace_hw_branches_suspended __read_mostly;
static void bts_trace_init_cpu(int cpu)
{
- per_cpu(tracer, cpu) =
- ds_request_bts_cpu(cpu, per_cpu(buffer, cpu), BTS_BUFFER_SIZE,
- NULL, (size_t)-1, BTS_KERNEL);
+ per_cpu(hwb_tracer, cpu) =
+ ds_request_bts_cpu(cpu, per_cpu(hwb_buffer, cpu),
+ BTS_BUFFER_SIZE, NULL, (size_t)-1,
+ BTS_KERNEL);
- if (IS_ERR(per_cpu(tracer, cpu)))
- per_cpu(tracer, cpu) = NULL;
+ if (IS_ERR(per_cpu(hwb_tracer, cpu)))
+ per_cpu(hwb_tracer, cpu) = NULL;
}
static int bts_trace_init(struct trace_array *tr)
for_each_online_cpu(cpu) {
bts_trace_init_cpu(cpu);
- if (likely(per_cpu(tracer, cpu)))
+ if (likely(per_cpu(hwb_tracer, cpu)))
trace_hw_branches_enabled = 1;
}
trace_hw_branches_suspended = 0;
get_online_cpus();
for_each_online_cpu(cpu) {
- if (likely(per_cpu(tracer, cpu))) {
- ds_release_bts(per_cpu(tracer, cpu));
- per_cpu(tracer, cpu) = NULL;
+ if (likely(per_cpu(hwb_tracer, cpu))) {
+ ds_release_bts(per_cpu(hwb_tracer, cpu));
+ per_cpu(hwb_tracer, cpu) = NULL;
}
}
trace_hw_branches_enabled = 0;
get_online_cpus();
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_resume_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_resume_bts(per_cpu(hwb_tracer, cpu));
trace_hw_branches_suspended = 0;
put_online_cpus();
}
get_online_cpus();
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_suspend_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
trace_hw_branches_suspended = 1;
put_online_cpus();
}
bts_trace_init_cpu(cpu);
if (trace_hw_branches_suspended &&
- likely(per_cpu(tracer, cpu)))
- ds_suspend_bts(per_cpu(tracer, cpu));
+ likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
}
break;
case CPU_DOWN_PREPARE:
/* The notification is sent with interrupts enabled. */
- if (likely(per_cpu(tracer, cpu))) {
- ds_release_bts(per_cpu(tracer, cpu));
- per_cpu(tracer, cpu) = NULL;
+ if (likely(per_cpu(hwb_tracer, cpu))) {
+ ds_release_bts(per_cpu(hwb_tracer, cpu));
+ per_cpu(hwb_tracer, cpu) = NULL;
}
}
struct ftrace_event_call *call = &event_hw_branch;
struct trace_array *tr = hw_branch_trace;
struct ring_buffer_event *event;
+ struct ring_buffer *buf;
struct hw_branch_entry *entry;
unsigned long irq1;
int cpu;
if (atomic_inc_return(&tr->data[cpu]->disabled) != 1)
goto out;
- event = trace_buffer_lock_reserve(tr, TRACE_HW_BRANCHES,
+ buf = tr->buffer;
+ event = trace_buffer_lock_reserve(buf, TRACE_HW_BRANCHES,
sizeof(*entry), 0, 0);
if (!event)
goto out;
entry->ent.type = TRACE_HW_BRANCHES;
entry->from = from;
entry->to = to;
- if (!filter_check_discard(call, entry, tr->buffer, event))
- trace_buffer_unlock_commit(tr, event, 0, 0);
+ if (!filter_check_discard(call, entry, buf, event))
+ trace_buffer_unlock_commit(buf, event, 0, 0);
out:
atomic_dec(&tr->data[cpu]->disabled);
get_online_cpus();
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_suspend_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_suspend_bts(per_cpu(hwb_tracer, cpu));
/*
* We need to collect the trace on the respective cpu since ftrace
* implicitly adds the record for the current cpu.
on_each_cpu(trace_bts_cpu, iter->tr, 1);
for_each_online_cpu(cpu)
- if (likely(per_cpu(tracer, cpu)))
- ds_resume_bts(per_cpu(tracer, cpu));
+ if (likely(per_cpu(hwb_tracer, cpu)))
+ ds_resume_bts(per_cpu(hwb_tracer, cpu));
put_online_cpus();
}
#define BAD_ALIEN_MAGIC 0x01020304ul
+/*
+ * chicken and egg problem: delay the per-cpu array allocation
+ * until the general caches are up.
+ */
+static enum {
+ NONE,
+ PARTIAL_AC,
+ PARTIAL_L3,
+ EARLY,
+ FULL
+} g_cpucache_up;
+
+/*
+ * used by boot code to determine if it can use slab based allocator
+ */
+int slab_is_available(void)
+{
+ return g_cpucache_up >= EARLY;
+}
+
#ifdef CONFIG_LOCKDEP
/*
static struct lock_class_key on_slab_l3_key;
static struct lock_class_key on_slab_alc_key;
-static inline void init_lock_keys(void)
-
+static void init_node_lock_keys(int q)
{
- int q;
struct cache_sizes *s = malloc_sizes;
- while (s->cs_size != ULONG_MAX) {
- for_each_node(q) {
- struct array_cache **alc;
- int r;
- struct kmem_list3 *l3 = s->cs_cachep->nodelists[q];
- if (!l3 || OFF_SLAB(s->cs_cachep))
- continue;
- lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
- alc = l3->alien;
- /*
- * FIXME: This check for BAD_ALIEN_MAGIC
- * should go away when common slab code is taught to
- * work even without alien caches.
- * Currently, non NUMA code returns BAD_ALIEN_MAGIC
- * for alloc_alien_cache,
- */
- if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
- continue;
- for_each_node(r) {
- if (alc[r])
- lockdep_set_class(&alc[r]->lock,
- &on_slab_alc_key);
- }
+ if (g_cpucache_up != FULL)
+ return;
+
+ for (s = malloc_sizes; s->cs_size != ULONG_MAX; s++) {
+ struct array_cache **alc;
+ struct kmem_list3 *l3;
+ int r;
+
+ l3 = s->cs_cachep->nodelists[q];
+ if (!l3 || OFF_SLAB(s->cs_cachep))
+ return;
+ lockdep_set_class(&l3->list_lock, &on_slab_l3_key);
+ alc = l3->alien;
+ /*
+ * FIXME: This check for BAD_ALIEN_MAGIC
+ * should go away when common slab code is taught to
+ * work even without alien caches.
+ * Currently, non NUMA code returns BAD_ALIEN_MAGIC
+ * for alloc_alien_cache,
+ */
+ if (!alc || (unsigned long)alc == BAD_ALIEN_MAGIC)
+ return;
+ for_each_node(r) {
+ if (alc[r])
+ lockdep_set_class(&alc[r]->lock,
+ &on_slab_alc_key);
}
- s++;
}
}
+
+static inline void init_lock_keys(void)
+{
+ int node;
+
+ for_each_node(node)
+ init_node_lock_keys(node);
+}
#else
+static void init_node_lock_keys(int q)
+{
+}
+
static inline void init_lock_keys(void)
{
}
static DEFINE_MUTEX(cache_chain_mutex);
static struct list_head cache_chain;
- static DEFINE_PER_CPU(struct delayed_work, reap_work);
-/*
- * chicken and egg problem: delay the per-cpu array allocation
- * until the general caches are up.
- */
-static enum {
- NONE,
- PARTIAL_AC,
- PARTIAL_L3,
- EARLY,
- FULL
-} g_cpucache_up;
-
-/*
- * used by boot code to determine if it can use slab based allocator
- */
-int slab_is_available(void)
-{
- return g_cpucache_up >= EARLY;
-}
-
+ static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
{
* objects freed on different nodes from which they were allocated) and the
* flushing of remote pcps by calling drain_node_pages.
*/
- static DEFINE_PER_CPU(unsigned long, reap_node);
+ static DEFINE_PER_CPU(unsigned long, slab_reap_node);
static void init_reap_node(int cpu)
{
if (node == MAX_NUMNODES)
node = first_node(node_online_map);
- per_cpu(reap_node, cpu) = node;
+ per_cpu(slab_reap_node, cpu) = node;
}
static void next_reap_node(void)
{
- int node = __get_cpu_var(reap_node);
+ int node = __get_cpu_var(slab_reap_node);
node = next_node(node, node_online_map);
if (unlikely(node >= MAX_NUMNODES))
node = first_node(node_online_map);
- __get_cpu_var(reap_node) = node;
+ __get_cpu_var(slab_reap_node) = node;
}
#else
*/
static void __cpuinit start_cpu_timer(int cpu)
{
- struct delayed_work *reap_work = &per_cpu(reap_work, cpu);
+ struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
/*
* When this gets called from do_initcalls via cpucache_init(),
*/
static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
{
- int node = __get_cpu_var(reap_node);
+ int node = __get_cpu_var(slab_reap_node);
if (l3->alien) {
struct array_cache *ac = l3->alien[node];
kfree(shared);
free_alien_cache(alien);
}
+ init_node_lock_keys(node);
+
return 0;
bad:
cpuup_canceled(cpu);
* anything expensive but will only modify reap_work
* and reschedule the timer.
*/
- cancel_rearming_delayed_work(&per_cpu(reap_work, cpu));
+ cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
/* Now the cache_reaper is guaranteed to be not running. */
- per_cpu(reap_work, cpu).work.func = NULL;
+ per_cpu(slab_reap_work, cpu).work.func = NULL;
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
} else {
STATS_INC_ALLOCMISS(cachep);
objp = cache_alloc_refill(cachep, flags);
+ /*
+ * the 'ac' may be updated by cache_alloc_refill(),
+ * and kmemleak_erase() requires its correct value.
+ */
+ ac = cpu_cache_get(cachep);
}
/*
* To avoid a false negative, if an object that is in one of the
* per-CPU caches is leaked, we need to make sure kmemleak doesn't
* treat the array pointers as a reference to the object.
*/
- kmemleak_erase(&ac->entry[ac->avail]);
+ if (objp)
+ kmemleak_erase(&ac->entry[ac->avail]);
return objp;
}
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
- if (unlikely(nodeid == -1))
+ if (nodeid == -1)
nodeid = numa_node_id();
if (unlikely(!cachep->nodelists[nodeid])) {
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/highmem.h>
+#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/interrupt.h>
#include <linux/rcupdate.h>
#include <linux/pfn.h>
#include <linux/kmemleak.h>
-#include <linux/highmem.h>
#include <asm/atomic.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
+#include <asm/shmparam.h>
/*** Page table manipulation functions ***/
spin_lock(&vbq->lock);
list_add(&vb->free_list, &vbq->free);
spin_unlock(&vbq->lock);
- put_cpu_var(vmap_cpu_blocks);
+ put_cpu_var(vmap_block_queue);
return vb;
}
}
spin_unlock(&vb->lock);
}
- put_cpu_var(vmap_cpu_blocks);
+ put_cpu_var(vmap_block_queue);
rcu_read_unlock();
if (!addr) {
}
static struct vm_struct *__get_vm_area_node(unsigned long size,
- unsigned long flags, unsigned long start, unsigned long end,
- int node, gfp_t gfp_mask, void *caller)
+ unsigned long align, unsigned long flags, unsigned long start,
+ unsigned long end, int node, gfp_t gfp_mask, void *caller)
{
static struct vmap_area *va;
struct vm_struct *area;
- unsigned long align = 1;
BUG_ON(in_interrupt());
if (flags & VM_IOREMAP) {
struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
unsigned long start, unsigned long end)
{
- return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
+ return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
__builtin_return_address(0));
}
EXPORT_SYMBOL_GPL(__get_vm_area);
unsigned long start, unsigned long end,
void *caller)
{
- return __get_vm_area_node(size, flags, start, end, -1, GFP_KERNEL,
+ return __get_vm_area_node(size, 1, flags, start, end, -1, GFP_KERNEL,
caller);
}
*/
struct vm_struct *get_vm_area(unsigned long size, unsigned long flags)
{
- return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
+ return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
-1, GFP_KERNEL, __builtin_return_address(0));
}
struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
void *caller)
{
- return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END,
+ return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
-1, GFP_KERNEL, caller);
}
struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
int node, gfp_t gfp_mask)
{
- return __get_vm_area_node(size, flags, VMALLOC_START, VMALLOC_END, node,
- gfp_mask, __builtin_return_address(0));
+ return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
+ node, gfp_mask, __builtin_return_address(0));
}
static struct vm_struct *find_vm_area(const void *addr)
}
EXPORT_SYMBOL(vmap);
-static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+ gfp_t gfp_mask, pgprot_t prot,
int node, void *caller);
static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
pgprot_t prot, int node, void *caller)
area->nr_pages = nr_pages;
/* Please note that the recursion is strictly bounded. */
if (array_size > PAGE_SIZE) {
- pages = __vmalloc_node(array_size, gfp_mask | __GFP_ZERO,
+ pages = __vmalloc_node(array_size, 1, gfp_mask | __GFP_ZERO,
PAGE_KERNEL, node, caller);
area->flags |= VM_VPAGES;
} else {
/**
* __vmalloc_node - allocate virtually contiguous memory
* @size: allocation size
+ * @align: desired alignment
* @gfp_mask: flags for the page level allocator
* @prot: protection mask for the allocated pages
* @node: node to use for allocation or -1
* allocator with @gfp_mask flags. Map them into contiguous
* kernel virtual space, using a pagetable protection of @prot.
*/
-static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
- int node, void *caller)
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+ gfp_t gfp_mask, pgprot_t prot,
+ int node, void *caller)
{
struct vm_struct *area;
void *addr;
if (!size || (size >> PAGE_SHIFT) > totalram_pages)
return NULL;
- area = __get_vm_area_node(size, VM_ALLOC, VMALLOC_START, VMALLOC_END,
- node, gfp_mask, caller);
+ area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START,
+ VMALLOC_END, node, gfp_mask, caller);
if (!area)
return NULL;
void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
- return __vmalloc_node(size, gfp_mask, prot, -1,
+ return __vmalloc_node(size, 1, gfp_mask, prot, -1,
__builtin_return_address(0));
}
EXPORT_SYMBOL(__vmalloc);
*/
void *vmalloc(unsigned long size)
{
- return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+ return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
-1, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc);
struct vm_struct *area;
void *ret;
- ret = __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+ ret = __vmalloc_node(size, SHMLBA,
+ GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
PAGE_KERNEL, -1, __builtin_return_address(0));
if (ret) {
area = find_vm_area(ret);
*/
void *vmalloc_node(unsigned long size, int node)
{
- return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
+ return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
node, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_node);
void *vmalloc_exec(unsigned long size)
{
- return __vmalloc_node(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
+ return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC,
-1, __builtin_return_address(0));
}
*/
void *vmalloc_32(unsigned long size)
{
- return __vmalloc_node(size, GFP_VMALLOC32, PAGE_KERNEL,
+ return __vmalloc_node(size, 1, GFP_VMALLOC32, PAGE_KERNEL,
-1, __builtin_return_address(0));
}
EXPORT_SYMBOL(vmalloc_32);
struct vm_struct *area;
void *ret;
- ret = __vmalloc_node(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
+ ret = __vmalloc_node(size, 1, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL,
-1, __builtin_return_address(0));
if (ret) {
area = find_vm_area(ret);
projects / linux.git / commitdiff