struct tss_struct;
struct mm_struct;
struct desc_struct;
+struct task_struct;
/*
* Wrapper type for pointers to code which uses the non-standard
void (*swapgs)(void);
- struct pv_lazy_ops lazy_mode;
+ void (*start_context_switch)(struct task_struct *prev);
+ void (*end_context_switch)(struct task_struct *next);
};
struct pv_irq_ops {
/* Sometimes the physical address is a pfn, and sometimes its
an mfn. We can tell which is which from the index. */
void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
- unsigned long phys, pgprot_t flags);
+ phys_addr_t phys, pgprot_t flags);
};
struct raw_spinlock;
};
enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
+void paravirt_start_context_switch(struct task_struct *prev);
+void paravirt_end_context_switch(struct task_struct *next);
+
void paravirt_enter_lazy_mmu(void);
void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
-#define __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
+#define __HAVE_ARCH_START_CONTEXT_SWITCH
+static inline void arch_start_context_switch(struct task_struct *prev)
{
- PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+ PVOP_VCALL1(pv_cpu_ops.start_context_switch, prev);
}
-static inline void arch_leave_lazy_cpu_mode(void)
+static inline void arch_end_context_switch(struct task_struct *next)
{
- PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+ PVOP_VCALL1(pv_cpu_ops.end_context_switch, next);
}
-void arch_flush_lazy_cpu_mode(void);
-
#define __HAVE_ARCH_ENTER_LAZY_MMU_MODE
static inline void arch_enter_lazy_mmu_mode(void)
{
void arch_flush_lazy_mmu_mode(void);
static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
- unsigned long phys, pgprot_t flags)
+ phys_addr_t phys, pgprot_t flags)
{
pv_mmu_ops.set_fixmap(idx, phys, flags);
}
/* When lazy mode is turned off reset the per-cpu lazy mode variable and then
* issue the do-nothing hypercall to flush any stored calls. */
-static void lguest_leave_lazy_mode(void)
+static void lguest_leave_lazy_mmu_mode(void)
{
- paravirt_leave_lazy(paravirt_get_lazy_mode());
kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+ paravirt_leave_lazy_mmu();
+}
+
+static void lguest_end_context_switch(struct task_struct *next)
+{
+ kvm_hypercall0(LHCALL_FLUSH_ASYNC);
+ paravirt_end_context_switch(next);
}
/*G:033
* controls the entire thing and the Guest asks it to make changes using the
* LOAD_GDT hypercall.
*
- * This is the opposite of the IDT code where we have a LOAD_IDT_ENTRY
- * hypercall and use that repeatedly to load a new IDT. I don't think it
- * really matters, but wouldn't it be nice if they were the same? Wouldn't
- * it be even better if you were the one to send the patch to fix it?
+ * This is the exactly like the IDT code.
*/
static void lguest_load_gdt(const struct desc_ptr *desc)
{
- BUG_ON((desc->size + 1) / 8 != GDT_ENTRIES);
- kvm_hypercall2(LHCALL_LOAD_GDT, __pa(desc->address), GDT_ENTRIES);
+ unsigned int i;
+ struct desc_struct *gdt = (void *)desc->address;
+
+ for (i = 0; i < (desc->size+1)/8; i++)
+ kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, i, gdt[i].a, gdt[i].b);
}
/* For a single GDT entry which changes, we do the lazy thing: alter our GDT,
const void *desc, int type)
{
native_write_gdt_entry(dt, entrynum, desc, type);
- kvm_hypercall2(LHCALL_LOAD_GDT, __pa(dt), GDT_ENTRIES);
+ /* Tell Host about this new entry. */
+ kvm_hypercall3(LHCALL_LOAD_GDT_ENTRY, entrynum,
+ dt[entrynum].a, dt[entrynum].b);
}
/* OK, I lied. There are three "thread local storage" GDT entries which change
/* If we can't use the TSC, the kernel falls back to our lower-priority
* "lguest_clock", where we read the time value given to us by the Host. */
- static cycle_t lguest_clock_read(void)
+ static cycle_t lguest_clock_read(struct clocksource *cs)
{
unsigned long sec, nsec;
pv_cpu_ops.write_gdt_entry = lguest_write_gdt_entry;
pv_cpu_ops.write_idt_entry = lguest_write_idt_entry;
pv_cpu_ops.wbinvd = lguest_wbinvd;
- pv_cpu_ops.lazy_mode.enter = paravirt_enter_lazy_cpu;
- pv_cpu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+ pv_cpu_ops.start_context_switch = paravirt_start_context_switch;
+ pv_cpu_ops.end_context_switch = lguest_end_context_switch;
/* pagetable management */
pv_mmu_ops.write_cr3 = lguest_write_cr3;
pv_mmu_ops.read_cr2 = lguest_read_cr2;
pv_mmu_ops.read_cr3 = lguest_read_cr3;
pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
- pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mode;
+ pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
pv_mmu_ops.pte_update = lguest_pte_update;
pv_mmu_ops.pte_update_defer = lguest_pte_update;
vm_unmap_aliases();
- /*
- * If we're called with lazy mmu updates enabled, the
- * in-memory pte state may be stale. Flush pending updates to
- * bring them up to date.
- */
- arch_flush_lazy_mmu_mode();
-
cpa.vaddr = addr;
cpa.pages = pages;
cpa.numpages = numpages;
} else
cpa_flush_all(cache);
- /*
- * If we've been called with lazy mmu updates enabled, then
- * make sure that everything gets flushed out before we
- * return.
- */
- arch_flush_lazy_mmu_mode();
-
out:
return ret;
}
int set_memory_uc(unsigned long addr, int numpages)
{
+ int ret;
+
/*
* for now UC MINUS. see comments in ioremap_nocache()
*/
- if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
- _PAGE_CACHE_UC_MINUS, NULL))
- return -EINVAL;
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_UC_MINUS, NULL);
+ if (ret)
+ goto out_err;
+
+ ret = _set_memory_uc(addr, numpages);
+ if (ret)
+ goto out_free;
- return _set_memory_uc(addr, numpages);
+ return 0;
+
+ out_free:
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ out_err:
+ return ret;
}
EXPORT_SYMBOL(set_memory_uc);
int set_memory_array_uc(unsigned long *addr, int addrinarray)
{
- unsigned long start;
- unsigned long end;
- int i;
+ int i, j;
+ int ret;
+
/*
* for now UC MINUS. see comments in ioremap_nocache()
*/
for (i = 0; i < addrinarray; i++) {
- start = __pa(addr[i]);
- for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
- if (end != __pa(addr[i + 1]))
- break;
- i++;
- }
- if (reserve_memtype(start, end, _PAGE_CACHE_UC_MINUS, NULL))
- goto out;
+ ret = reserve_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE,
+ _PAGE_CACHE_UC_MINUS, NULL);
+ if (ret)
+ goto out_free;
}
- return change_page_attr_set(addr, addrinarray,
+ ret = change_page_attr_set(addr, addrinarray,
__pgprot(_PAGE_CACHE_UC_MINUS), 1);
- out:
- for (i = 0; i < addrinarray; i++) {
- unsigned long tmp = __pa(addr[i]);
-
- if (tmp == start)
- break;
- for (end = tmp + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
- if (end != __pa(addr[i + 1]))
- break;
- i++;
- }
- free_memtype(tmp, end);
- }
- return -EINVAL;
+ if (ret)
+ goto out_free;
+
+ return 0;
+
+ out_free:
+ for (j = 0; j < i; j++)
+ free_memtype(__pa(addr[j]), __pa(addr[j]) + PAGE_SIZE);
+
+ return ret;
}
EXPORT_SYMBOL(set_memory_array_uc);
int _set_memory_wc(unsigned long addr, int numpages)
{
- return change_page_attr_set(&addr, numpages,
+ int ret;
+ ret = change_page_attr_set(&addr, numpages,
+ __pgprot(_PAGE_CACHE_UC_MINUS), 0);
+
+ if (!ret) {
+ ret = change_page_attr_set(&addr, numpages,
__pgprot(_PAGE_CACHE_WC), 0);
+ }
+ return ret;
}
int set_memory_wc(unsigned long addr, int numpages)
{
+ int ret;
+
if (!pat_enabled)
return set_memory_uc(addr, numpages);
- if (reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
- _PAGE_CACHE_WC, NULL))
- return -EINVAL;
+ ret = reserve_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE,
+ _PAGE_CACHE_WC, NULL);
+ if (ret)
+ goto out_err;
+
+ ret = _set_memory_wc(addr, numpages);
+ if (ret)
+ goto out_free;
+
+ return 0;
- return _set_memory_wc(addr, numpages);
+ out_free:
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ out_err:
+ return ret;
}
EXPORT_SYMBOL(set_memory_wc);
int set_memory_wb(unsigned long addr, int numpages)
{
- free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ int ret;
+
+ ret = _set_memory_wb(addr, numpages);
+ if (ret)
+ return ret;
- return _set_memory_wb(addr, numpages);
+ free_memtype(__pa(addr), __pa(addr) + numpages * PAGE_SIZE);
+ return 0;
}
EXPORT_SYMBOL(set_memory_wb);
int set_memory_array_wb(unsigned long *addr, int addrinarray)
{
int i;
+ int ret;
- for (i = 0; i < addrinarray; i++) {
- unsigned long start = __pa(addr[i]);
- unsigned long end;
-
- for (end = start + PAGE_SIZE; i < addrinarray - 1; end += PAGE_SIZE) {
- if (end != __pa(addr[i + 1]))
- break;
- i++;
- }
- free_memtype(start, end);
- }
- return change_page_attr_clear(addr, addrinarray,
+ ret = change_page_attr_clear(addr, addrinarray,
__pgprot(_PAGE_CACHE_MASK), 1);
+ if (ret)
+ return ret;
+
+ for (i = 0; i < addrinarray; i++)
+ free_memtype(__pa(addr[i]), __pa(addr[i]) + PAGE_SIZE);
+
+ return 0;
}
EXPORT_SYMBOL(set_memory_array_wb);
retval = cpa_clear_pages_array(pages, addrinarray,
__pgprot(_PAGE_CACHE_MASK));
+ if (retval)
+ return retval;
for (i = 0; i < addrinarray; i++) {
start = (unsigned long)page_address(pages[i]);
free_memtype(start, end);
}
- return retval;
+ return 0;
}
EXPORT_SYMBOL(set_pages_array_wb);
void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
pte_t *ptep, pte_t pteval)
{
- /* updates to init_mm may be done without lock */
- if (mm == &init_mm)
- preempt_disable();
-
ADD_STATS(set_pte_at, 1);
// ADD_STATS(set_pte_at_pinned, xen_page_pinned(ptep));
ADD_STATS(set_pte_at_current, mm == current->mm);
}
xen_set_pte(ptep, pteval);
-out:
- if (mm == &init_mm)
- preempt_enable();
+out: return;
}
pte_t xen_ptep_modify_prot_start(struct mm_struct *mm,
/* If this cpu still has a stale cr3 reference, then make sure
it has been flushed. */
- if (percpu_read(xen_current_cr3) == __pa(mm->pgd)) {
+ if (percpu_read(xen_current_cr3) == __pa(mm->pgd))
load_cr3(swapper_pg_dir);
- arch_flush_lazy_cpu_mode();
- }
}
static void xen_drop_mm_ref(struct mm_struct *mm)
load_cr3(swapper_pg_dir);
else
leave_mm(smp_processor_id());
- arch_flush_lazy_cpu_mode();
}
/* Get the "official" set of cpus referring to our pagetable. */
pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(swapper_pg_dir)));
+ reserve_early(__pa(xen_start_info->pt_base),
+ __pa(xen_start_info->pt_base +
+ xen_start_info->nr_pt_frames * PAGE_SIZE),
+ "XEN PAGETABLES");
+
return swapper_pg_dir;
}
#endif /* CONFIG_X86_64 */
- static void xen_set_fixmap(unsigned idx, unsigned long phys, pgprot_t prot)
+ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
{
pte_t pte;
xen_mark_init_mm_pinned();
}
+static void xen_leave_lazy_mmu(void)
+{
+ preempt_disable();
+ xen_mc_flush();
+ paravirt_leave_lazy_mmu();
+ preempt_enable();
+}
+
const struct pv_mmu_ops xen_mmu_ops __initdata = {
.pagetable_setup_start = xen_pagetable_setup_start,
.pagetable_setup_done = xen_pagetable_setup_done,
.lazy_mode = {
.enter = paravirt_enter_lazy_mmu,
- .leave = xen_leave_lazy,
+ .leave = xen_leave_lazy_mmu,
},
.set_fixmap = xen_set_fixmap,
struct rq_iterator *iterator);
#endif
+ /* Time spent by the tasks of the cpu accounting group executing in ... */
+ enum cpuacct_stat_index {
+ CPUACCT_STAT_USER, /* ... user mode */
+ CPUACCT_STAT_SYSTEM, /* ... kernel mode */
+
+ CPUACCT_STAT_NSTATS,
+ };
+
#ifdef CONFIG_CGROUP_CPUACCT
static void cpuacct_charge(struct task_struct *tsk, u64 cputime);
+ static void cpuacct_update_stats(struct task_struct *tsk,
+ enum cpuacct_stat_index idx, cputime_t val);
#else
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
+ static inline void cpuacct_update_stats(struct task_struct *tsk,
+ enum cpuacct_stat_index idx, cputime_t val) {}
#endif
static inline void inc_cpu_load(struct rq *rq, unsigned long load)
* combine the page table reload and the switch backend into
* one hypercall.
*/
- arch_enter_lazy_cpu_mode();
+ arch_start_context_switch(prev);
if (unlikely(!mm)) {
next->active_mm = oldmm;
EXPORT_PER_CPU_SYMBOL(kstat);
/*
- * Return any ns on the sched_clock that have not yet been banked in
+ * Return any ns on the sched_clock that have not yet been accounted in
* @p in case that task is currently running.
+ *
+ * Called with task_rq_lock() held on @rq.
*/
+ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq)
+ {
+ u64 ns = 0;
+
+ if (task_current(rq, p)) {
+ update_rq_clock(rq);
+ ns = rq->clock - p->se.exec_start;
+ if ((s64)ns < 0)
+ ns = 0;
+ }
+
+ return ns;
+ }
+
unsigned long long task_delta_exec(struct task_struct *p)
{
unsigned long flags;
u64 ns = 0;
rq = task_rq_lock(p, &flags);
+ ns = do_task_delta_exec(p, rq);
+ task_rq_unlock(rq, &flags);
- if (task_current(rq, p)) {
- u64 delta_exec;
+ return ns;
+ }
- update_rq_clock(rq);
- delta_exec = rq->clock - p->se.exec_start;
- if ((s64)delta_exec > 0)
- ns = delta_exec;
- }
+ /*
+ * Return accounted runtime for the task.
+ * In case the task is currently running, return the runtime plus current's
+ * pending runtime that have not been accounted yet.
+ */
+ unsigned long long task_sched_runtime(struct task_struct *p)
+ {
+ unsigned long flags;
+ struct rq *rq;
+ u64 ns = 0;
+
+ rq = task_rq_lock(p, &flags);
+ ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq);
+ task_rq_unlock(rq, &flags);
+
+ return ns;
+ }
+
+ /*
+ * Return sum_exec_runtime for the thread group.
+ * In case the task is currently running, return the sum plus current's
+ * pending runtime that have not been accounted yet.
+ *
+ * Note that the thread group might have other running tasks as well,
+ * so the return value not includes other pending runtime that other
+ * running tasks might have.
+ */
+ unsigned long long thread_group_sched_runtime(struct task_struct *p)
+ {
+ struct task_cputime totals;
+ unsigned long flags;
+ struct rq *rq;
+ u64 ns;
+ rq = task_rq_lock(p, &flags);
+ thread_group_cputime(p, &totals);
+ ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
task_rq_unlock(rq, &flags);
return ns;
cpustat->nice = cputime64_add(cpustat->nice, tmp);
else
cpustat->user = cputime64_add(cpustat->user, tmp);
+
+ cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime);
/* Account for user time used */
acct_update_integrals(p);
}
else
cpustat->system = cputime64_add(cpustat->system, tmp);
+ cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime);
+
/* Account for system time used */
acct_update_integrals(p);
}
if (user_tick)
account_user_time(p, one_jiffy, one_jiffy_scaled);
- else if (p != rq->idle)
+ else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
account_system_time(p, HARDIRQ_OFFSET, one_jiffy,
one_jiffy_scaled);
else
#endif
}
- unsigned long get_parent_ip(unsigned long addr)
+ notrace unsigned long get_parent_ip(unsigned long addr)
{
if (in_lock_functions(addr)) {
addr = CALLER_ADDR2;
cpumask_or(groupmask, groupmask, sched_group_cpus(group));
cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group));
+
printk(KERN_CONT " %s", str);
+ if (group->__cpu_power != SCHED_LOAD_SCALE) {
+ printk(KERN_CONT " (__cpu_power = %d)",
+ group->__cpu_power);
+ }
group = group->next;
} while (group != sd->groups);
struct cgroup_subsys_state css;
/* cpuusage holds pointer to a u64-type object on every cpu */
u64 *cpuusage;
+ struct percpu_counter cpustat[CPUACCT_STAT_NSTATS];
struct cpuacct *parent;
};
struct cgroup_subsys *ss, struct cgroup *cgrp)
{
struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL);
+ int i;
if (!ca)
- return ERR_PTR(-ENOMEM);
+ goto out;
ca->cpuusage = alloc_percpu(u64);
- if (!ca->cpuusage) {
- kfree(ca);
- return ERR_PTR(-ENOMEM);
- }
+ if (!ca->cpuusage)
+ goto out_free_ca;
+
+ for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
+ if (percpu_counter_init(&ca->cpustat[i], 0))
+ goto out_free_counters;
if (cgrp->parent)
ca->parent = cgroup_ca(cgrp->parent);
return &ca->css;
+
+ out_free_counters:
+ while (--i >= 0)
+ percpu_counter_destroy(&ca->cpustat[i]);
+ free_percpu(ca->cpuusage);
+ out_free_ca:
+ kfree(ca);
+ out:
+ return ERR_PTR(-ENOMEM);
}
/* destroy an existing cpu accounting group */
cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp)
{
struct cpuacct *ca = cgroup_ca(cgrp);
+ int i;
+ for (i = 0; i < CPUACCT_STAT_NSTATS; i++)
+ percpu_counter_destroy(&ca->cpustat[i]);
free_percpu(ca->cpuusage);
kfree(ca);
}
return 0;
}
+ static const char *cpuacct_stat_desc[] = {
+ [CPUACCT_STAT_USER] = "user",
+ [CPUACCT_STAT_SYSTEM] = "system",
+ };
+
+ static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft,
+ struct cgroup_map_cb *cb)
+ {
+ struct cpuacct *ca = cgroup_ca(cgrp);
+ int i;
+
+ for (i = 0; i < CPUACCT_STAT_NSTATS; i++) {
+ s64 val = percpu_counter_read(&ca->cpustat[i]);
+ val = cputime64_to_clock_t(val);
+ cb->fill(cb, cpuacct_stat_desc[i], val);
+ }
+ return 0;
+ }
+
static struct cftype files[] = {
{
.name = "usage",
.name = "usage_percpu",
.read_seq_string = cpuacct_percpu_seq_read,
},
-
+ {
+ .name = "stat",
+ .read_map = cpuacct_stats_show,
+ },
};
static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
return;
cpu = task_cpu(tsk);
+
+ rcu_read_lock();
+
ca = task_ca(tsk);
for (; ca; ca = ca->parent) {
u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu);
*cpuusage += cputime;
}
+
+ rcu_read_unlock();
+ }
+
+ /*
+ * Charge the system/user time to the task's accounting group.
+ */
+ static void cpuacct_update_stats(struct task_struct *tsk,
+ enum cpuacct_stat_index idx, cputime_t val)
+ {
+ struct cpuacct *ca;
+
+ if (unlikely(!cpuacct_subsys.active))
+ return;
+
+ rcu_read_lock();
+ ca = task_ca(tsk);
+
+ do {
+ percpu_counter_add(&ca->cpustat[idx], val);
+ ca = ca->parent;
+ } while (ca);
+ rcu_read_unlock();
}
struct cgroup_subsys cpuacct_subsys = {