* 'perfcounters-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits)
perfcounter: Handle some IO return values
perf_counter: Push perf_sample_data through the swcounter code
perf_counter tools: Define and use our own u64, s64 etc. definitions
perf_counter: Close race in perf_lock_task_context()
perf_counter, x86: Improve interactions with fast-gup
perf_counter: Simplify and fix task migration counting
perf_counter tools: Add a data file header
perf_counter: Update userspace callchain sampling uses
perf_counter: Make callchain samples extensible
perf report: Filter to parent set by default
perf_counter tools: Handle lost events
perf_counter: Add event overlow handling
fs: Provide empty .set_page_dirty() aop for anon inodes
perf_counter: tools: Makefile tweaks for 64-bit powerpc
perf_counter: powerpc: Add processor back-end for MPC7450 family
perf_counter: powerpc: Make powerpc perf_counter code safe for 32-bit kernels
perf_counter: powerpc: Change how processor-specific back-ends get selected
perf_counter: powerpc: Use unsigned long for register and constraint values
perf_counter: powerpc: Enable use of software counters on 32-bit powerpc
perf_counter tools: Add and use isprint()
...
CFLAGS_ptrace.o += -DUTS_MACHINE='"$(UTS_MACHINE)"'
+subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
+
ifeq ($(CONFIG_PPC64),y)
CFLAGS_prom_init.o += -mno-minimal-toc
endif
obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o
obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o
- obj-$(CONFIG_PERF_COUNTERS) += perf_counter.o power4-pmu.o ppc970-pmu.o \
- power5-pmu.o power5+-pmu.o power6-pmu.o \
- power7-pmu.o
+ obj-$(CONFIG_PPC_PERF_CTRS) += perf_counter.o
+ obj64-$(CONFIG_PPC_PERF_CTRS) += power4-pmu.o ppc970-pmu.o power5-pmu.o \
+ power5+-pmu.o power6-pmu.o power7-pmu.o
+ obj32-$(CONFIG_PPC_PERF_CTRS) += mpc7450-pmu.o
obj-$(CONFIG_8XX_MINIMAL_FPEMU) += softemu8xx.o
endif
obj-$(CONFIG_PPC64) += $(obj64-y)
+ obj-$(CONFIG_PPC32) += $(obj32-y)
ifneq ($(CONFIG_XMON)$(CONFIG_KEXEC),)
obj-y += ppc_save_regs.o
config PPC64
bool "64-bit kernel"
default n
- select HAVE_PERF_COUNTERS
+ select PPC_HAVE_PMU_SUPPORT
help
This option selects whether a 32-bit or a 64-bit kernel
will be built.
If unsure, select 52xx/6xx/7xx/74xx/82xx/83xx/86xx.
-config PPC_BOOK3S
+config PPC_BOOK3S_32
bool "512x/52xx/6xx/7xx/74xx/82xx/83xx/86xx"
select PPC_FPU
endchoice
-config PPC_BOOK3S
- default y
+config PPC_BOOK3S_64
+ def_bool y
depends on PPC64
select PPC_FPU
+config PPC_BOOK3S
+ def_bool y
+ depends on PPC_BOOK3S_32 || PPC_BOOK3S_64
config POWER4_ONLY
bool "Optimize for POWER4"
config 6xx
def_bool y
depends on PPC32 && PPC_BOOK3S
+ select PPC_HAVE_PMU_SUPPORT
config POWER3
bool
If in doubt, say Y here.
+ config PPC_HAVE_PMU_SUPPORT
+ bool
+
+ config PPC_PERF_CTRS
+ def_bool y
+ depends on PERF_COUNTERS && PPC_HAVE_PMU_SUPPORT
+ help
+ This enables the powerpc-specific perf_counter back-end.
+
config SMP
depends on PPC_STD_MMU || FSL_BOOKE
bool "Symmetric multi-processing support"
static inline pte_t gup_get_pte(pte_t *ptep)
{
#ifndef CONFIG_X86_PAE
- return *ptep;
+ return ACCESS_ONCE(*ptep);
#else
/*
* With get_user_pages_fast, we walk down the pagetables without taking
return 1;
}
+ /*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ */
+ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
+ struct page **pages)
+ {
+ struct mm_struct *mm = current->mm;
+ unsigned long addr, len, end;
+ unsigned long next;
+ unsigned long flags;
+ pgd_t *pgdp;
+ int nr = 0;
+
+ start &= PAGE_MASK;
+ addr = start;
+ len = (unsigned long) nr_pages << PAGE_SHIFT;
+ end = start + len;
+ if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
+ (void __user *)start, len)))
+ return 0;
+
+ /*
+ * XXX: batch / limit 'nr', to avoid large irq off latency
+ * needs some instrumenting to determine the common sizes used by
+ * important workloads (eg. DB2), and whether limiting the batch size
+ * will decrease performance.
+ *
+ * It seems like we're in the clear for the moment. Direct-IO is
+ * the main guy that batches up lots of get_user_pages, and even
+ * they are limited to 64-at-a-time which is not so many.
+ */
+ /*
+ * This doesn't prevent pagetable teardown, but does prevent
+ * the pagetables and pages from being freed on x86.
+ *
+ * So long as we atomically load page table pointers versus teardown
+ * (which we do on x86, with the above PAE exception), we can follow the
+ * address down to the the page and take a ref on it.
+ */
+ local_irq_save(flags);
+ pgdp = pgd_offset(mm, addr);
+ do {
+ pgd_t pgd = *pgdp;
+
+ next = pgd_addr_end(addr, end);
+ if (pgd_none(pgd))
+ break;
+ if (!gup_pud_range(pgd, addr, next, write, pages, &nr))
+ break;
+ } while (pgdp++, addr = next, addr != end);
+ local_irq_restore(flags);
+
+ return nr;
+ }
+
/**
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
start &= PAGE_MASK;
addr = start;
len = (unsigned long) nr_pages << PAGE_SHIFT;
+
end = start + len;
- if (unlikely(!access_ok(write ? VERIFY_WRITE : VERIFY_READ,
- (void __user *)start, len)))
+ if (end < start)
goto slow_irqon;
+#ifdef CONFIG_X86_64
+ if (end >> __VIRTUAL_MASK_SHIFT)
+ goto slow_irqon;
+#endif
+
/*
* XXX: batch / limit 'nr', to avoid large irq off latency
* needs some instrumenting to determine the common sizes used by
if (task_hot(p, old_rq->clock, NULL))
schedstat_inc(p, se.nr_forced2_migrations);
#endif
- perf_counter_task_migration(p, new_cpu);
+ perf_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS,
+ 1, 1, NULL, 0);
}
p->se.vruntime -= old_cfsrq->min_vruntime -
new_cfsrq->min_vruntime;
if (cpu_is_offline(cpu)) {
spin_unlock_irq(&rq->lock);
- goto wait_to_die;
+ break;
}
if (rq->active_balance) {
complete(&req->done);
}
__set_current_state(TASK_RUNNING);
- return 0;
-wait_to_die:
- /* Wait for kthread_stop */
- set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
- schedule();
- set_current_state(TASK_INTERRUPTIBLE);
- }
- __set_current_state(TASK_RUNNING);
return 0;
}
rq = task_rq_lock(p, &flags);
__setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1);
task_rq_unlock(rq, &flags);
+ get_task_struct(p);
cpu_rq(cpu)->migration_thread = p;
break;
kthread_bind(cpu_rq(cpu)->migration_thread,
cpumask_any(cpu_online_mask));
kthread_stop(cpu_rq(cpu)->migration_thread);
+ put_task_struct(cpu_rq(cpu)->migration_thread);
cpu_rq(cpu)->migration_thread = NULL;
break;
migrate_live_tasks(cpu);
rq = cpu_rq(cpu);
kthread_stop(rq->migration_thread);
+ put_task_struct(rq->migration_thread);
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
spin_lock_irq(&rq->lock);
free_rootdomain(old_rd);
}
-static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem)
+static int init_rootdomain(struct root_domain *rd, bool bootmem)
{
gfp_t gfp = GFP_KERNEL;