aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/cpu.c41
-rw-r--r--kernel/dma-coherent.c154
-rw-r--r--kernel/exit.c30
-rw-r--r--kernel/fork.c18
-rw-r--r--kernel/module.c33
-rw-r--r--kernel/rcuclassic.c4
-rw-r--r--kernel/stop_machine.c288
-rw-r--r--kernel/sysctl.c16
-rw-r--r--kernel/time/tick-common.c8
-rw-r--r--kernel/trace/ftrace.c6
-rw-r--r--kernel/trace/trace.c1
-rw-r--r--kernel/trace/trace_sysprof.c4
-rw-r--r--kernel/tsacct.c8
14 files changed, 363 insertions, 249 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 54f69837d35..4e1d7df7c3e 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -84,6 +84,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
obj-$(CONFIG_MARKERS) += marker.o
obj-$(CONFIG_LATENCYTOP) += latencytop.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
obj-$(CONFIG_FTRACE) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 10ba5f1004a..e202a68d1cc 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -216,7 +216,6 @@ static int __ref take_cpu_down(void *_param)
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
{
int err, nr_calls = 0;
- struct task_struct *p;
cpumask_t old_allowed, tmp;
void *hcpu = (void *)(long)cpu;
unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
@@ -249,21 +248,18 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
cpus_setall(tmp);
cpu_clear(cpu, tmp);
set_cpus_allowed_ptr(current, &tmp);
+ tmp = cpumask_of_cpu(cpu);
- p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
-
- if (IS_ERR(p) || cpu_online(cpu)) {
+ err = __stop_machine(take_cpu_down, &tcd_param, &tmp);
+ if (err) {
/* CPU didn't die: tell everyone. Can't complain. */
if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
hcpu) == NOTIFY_BAD)
BUG();
- if (IS_ERR(p)) {
- err = PTR_ERR(p);
- goto out_allowed;
- }
- goto out_thread;
+ goto out_allowed;
}
+ BUG_ON(cpu_online(cpu));
/* Wait for it to sleep (leaving idle task). */
while (!idle_cpu(cpu))
@@ -279,8 +275,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
check_for_tasks(cpu);
-out_thread:
- err = kthread_stop(p);
out_allowed:
set_cpus_allowed_ptr(current, &old_allowed);
out_release:
@@ -461,3 +455,28 @@ out:
#endif /* CONFIG_PM_SLEEP_SMP */
#endif /* CONFIG_SMP */
+
+/*
+ * cpu_bit_bitmap[] is a special, "compressed" data structure that
+ * represents all NR_CPUS bits binary values of 1<<nr.
+ *
+ * It is used by cpumask_of_cpu() to get a constant address to a CPU
+ * mask value that has a single bit set only.
+ */
+
+/* cpu_bit_bitmap[0] is empty - so we can back into it */
+#define MASK_DECLARE_1(x) [x+1][0] = 1UL << (x)
+#define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
+#define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
+#define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)
+
+const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {
+
+ MASK_DECLARE_8(0), MASK_DECLARE_8(8),
+ MASK_DECLARE_8(16), MASK_DECLARE_8(24),
+#if BITS_PER_LONG > 32
+ MASK_DECLARE_8(32), MASK_DECLARE_8(40),
+ MASK_DECLARE_8(48), MASK_DECLARE_8(56),
+#endif
+};
+EXPORT_SYMBOL_GPL(cpu_bit_bitmap);
diff --git a/kernel/dma-coherent.c b/kernel/dma-coherent.c
new file mode 100644
index 00000000000..7517115a8cc
--- /dev/null
+++ b/kernel/dma-coherent.c
@@ -0,0 +1,154 @@
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/kernel.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+ void *virt_base;
+ u32 device_base;
+ int size;
+ int flags;
+ unsigned long *bitmap;
+};
+
+int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ void __iomem *mem_base = NULL;
+ int pages = size >> PAGE_SHIFT;
+ int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+
+ if ((flags & (DMA_MEMORY_MAP | DMA_MEMORY_IO)) == 0)
+ goto out;
+ if (!size)
+ goto out;
+ if (dev->dma_mem)
+ goto out;
+
+ /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */
+
+ mem_base = ioremap(bus_addr, size);
+ if (!mem_base)
+ goto out;
+
+ dev->dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+ if (!dev->dma_mem)
+ goto out;
+ dev->dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ if (!dev->dma_mem->bitmap)
+ goto free1_out;
+
+ dev->dma_mem->virt_base = mem_base;
+ dev->dma_mem->device_base = device_addr;
+ dev->dma_mem->size = pages;
+ dev->dma_mem->flags = flags;
+
+ if (flags & DMA_MEMORY_MAP)
+ return DMA_MEMORY_MAP;
+
+ return DMA_MEMORY_IO;
+
+ free1_out:
+ kfree(dev->dma_mem);
+ out:
+ if (mem_base)
+ iounmap(mem_base);
+ return 0;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+
+ if (!mem)
+ return;
+ dev->dma_mem = NULL;
+ iounmap(mem->virt_base);
+ kfree(mem->bitmap);
+ kfree(mem);
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+ int pos, err;
+ int pages = (size + (device_addr & ~PAGE_MASK) + PAGE_SIZE - 1);
+
+ pages >>= PAGE_SHIFT;
+
+ if (!mem)
+ return ERR_PTR(-EINVAL);
+
+ pos = (device_addr - mem->device_base) >> PAGE_SHIFT;
+ err = bitmap_allocate_region(mem->bitmap, pos, get_order(pages));
+ if (err != 0)
+ return ERR_PTR(err);
+ return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+/**
+ * Try to allocate memory from the per-device coherent area.
+ *
+ * @dev: device from which we allocate memory
+ * @size: size of requested memory area
+ * @dma_handle: This will be filled with the correct dma handle
+ * @ret: This pointer will be filled with the virtual address
+ * to allocated area.
+ *
+ * This function should be only called from per-arch %dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return %ret.
+ */
+int dma_alloc_from_coherent(struct device *dev, ssize_t size,
+ dma_addr_t *dma_handle, void **ret)
+{
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+ int order = get_order(size);
+
+ if (mem) {
+ int page = bitmap_find_free_region(mem->bitmap, mem->size,
+ order);
+ if (page >= 0) {
+ *dma_handle = mem->device_base + (page << PAGE_SHIFT);
+ *ret = mem->virt_base + (page << PAGE_SHIFT);
+ memset(*ret, 0, size);
+ } else if (mem->flags & DMA_MEMORY_EXCLUSIVE)
+ *ret = NULL;
+ }
+ return (mem != NULL);
+}
+
+/**
+ * Try to free the memory allocated from per-device coherent memory pool.
+ * @dev: device from which the memory was allocated
+ * @order: the order of pages allocated
+ * @vaddr: virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if
+ * %dma_release_coherent() should proceed with releasing memory from
+ * generic pools.
+ */
+int dma_release_from_coherent(struct device *dev, int order, void *vaddr)
+{
+ struct dma_coherent_mem *mem = dev ? dev->dma_mem : NULL;
+
+ if (mem && vaddr >= mem->virt_base && vaddr <
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+
+ bitmap_release_region(mem->bitmap, page, order);
+ return 1;
+ }
+ return 0;
+}
diff --git a/kernel/exit.c b/kernel/exit.c
index 0caf590548a..eb4d6470d1d 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -121,18 +121,7 @@ static void __exit_signal(struct task_struct *tsk)
sig->nivcsw += tsk->nivcsw;
sig->inblock += task_io_get_inblock(tsk);
sig->oublock += task_io_get_oublock(tsk);
-#ifdef CONFIG_TASK_XACCT
- sig->rchar += tsk->rchar;
- sig->wchar += tsk->wchar;
- sig->syscr += tsk->syscr;
- sig->syscw += tsk->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
- sig->ioac.read_bytes += tsk->ioac.read_bytes;
- sig->ioac.write_bytes += tsk->ioac.write_bytes;
- sig->ioac.cancelled_write_bytes +=
- tsk->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+ task_io_accounting_add(&sig->ioac, &tsk->ioac);
sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
sig = NULL; /* Marker for below. */
}
@@ -1363,21 +1352,8 @@ static int wait_task_zombie(struct task_struct *p, int options,
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
-#ifdef CONFIG_TASK_XACCT
- psig->rchar += p->rchar + sig->rchar;
- psig->wchar += p->wchar + sig->wchar;
- psig->syscr += p->syscr + sig->syscr;
- psig->syscw += p->syscw + sig->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
- psig->ioac.read_bytes +=
- p->ioac.read_bytes + sig->ioac.read_bytes;
- psig->ioac.write_bytes +=
- p->ioac.write_bytes + sig->ioac.write_bytes;
- psig->ioac.cancelled_write_bytes +=
- p->ioac.cancelled_write_bytes +
- sig->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+ task_io_accounting_add(&psig->ioac, &p->ioac);
+ task_io_accounting_add(&psig->ioac, &sig->ioac);
spin_unlock_irq(&p->parent->sighand->siglock);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 5e050c1317c..7ce2ebe8479 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -27,6 +27,7 @@
#include <linux/key.h>
#include <linux/binfmts.h>
#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
#include <linux/fs.h>
#include <linux/nsproxy.h>
#include <linux/capability.h>
@@ -414,6 +415,7 @@ static struct mm_struct * mm_init(struct mm_struct * mm, struct task_struct *p)
if (likely(!mm_alloc_pgd(mm))) {
mm->def_flags = 0;
+ mmu_notifier_mm_init(mm);
return mm;
}
@@ -446,6 +448,7 @@ void __mmdrop(struct mm_struct *mm)
BUG_ON(mm == &init_mm);
mm_free_pgd(mm);
destroy_context(mm);
+ mmu_notifier_mm_destroy(mm);
free_mm(mm);
}
EXPORT_SYMBOL_GPL(__mmdrop);
@@ -806,12 +809,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
-#ifdef CONFIG_TASK_XACCT
- sig->rchar = sig->wchar = sig->syscr = sig->syscw = 0;
-#endif
-#ifdef CONFIG_TASK_IO_ACCOUNTING
- memset(&sig->ioac, 0, sizeof(sig->ioac));
-#endif
+ task_io_accounting_init(&sig->ioac);
sig->sum_sched_runtime = 0;
INIT_LIST_HEAD(&sig->cpu_timers[0]);
INIT_LIST_HEAD(&sig->cpu_timers[1]);
@@ -994,13 +992,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
p->last_switch_timestamp = 0;
#endif
-#ifdef CONFIG_TASK_XACCT
- p->rchar = 0; /* I/O counter: bytes read */
- p->wchar = 0; /* I/O counter: bytes written */
- p->syscr = 0; /* I/O counter: read syscalls */
- p->syscw = 0; /* I/O counter: write syscalls */
-#endif
- task_io_accounting_init(p);
+ task_io_accounting_init(&p->ioac);
acct_clear_integrals(p);
p->it_virt_expires = cputime_zero;
diff --git a/kernel/module.c b/kernel/module.c
index d8b5605132a..61d212120df 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -325,18 +325,6 @@ static unsigned long find_symbol(const char *name,
return -ENOENT;
}
-/* lookup symbol in given range of kernel_symbols */
-static const struct kernel_symbol *lookup_symbol(const char *name,
- const struct kernel_symbol *start,
- const struct kernel_symbol *stop)
-{
- const struct kernel_symbol *ks = start;
- for (; ks < stop; ks++)
- if (strcmp(ks->name, name) == 0)
- return ks;
- return NULL;
-}
-
/* Search for module by name: must hold module_mutex. */
static struct module *find_module(const char *name)
{
@@ -690,7 +678,7 @@ static int try_stop_module(struct module *mod, int flags, int *forced)
if (flags & O_NONBLOCK) {
struct stopref sref = { mod, flags, forced };
- return stop_machine_run(__try_stop_module, &sref, NR_CPUS);
+ return stop_machine(__try_stop_module, &sref, NULL);
} else {
/* We don't need to stop the machine for this. */
mod->state = MODULE_STATE_GOING;
@@ -1428,7 +1416,7 @@ static int __unlink_module(void *_mod)
static void free_module(struct module *mod)
{
/* Delete from various lists */
- stop_machine_run(__unlink_module, mod, NR_CPUS);
+ stop_machine(__unlink_module, mod, NULL);
remove_notes_attrs(mod);
remove_sect_attrs(mod);
mod_kobject_remove(mod);
@@ -1703,6 +1691,19 @@ static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
}
#ifdef CONFIG_KALLSYMS
+
+/* lookup symbol in given range of kernel_symbols */
+static const struct kernel_symbol *lookup_symbol(const char *name,
+ const struct kernel_symbol *start,
+ const struct kernel_symbol *stop)
+{
+ const struct kernel_symbol *ks = start;
+ for (; ks < stop; ks++)
+ if (strcmp(ks->name, name) == 0)
+ return ks;
+ return NULL;
+}
+
static int is_exported(const char *name, const struct module *mod)
{
if (!mod && lookup_symbol(name, __start___ksymtab, __stop___ksymtab))
@@ -2196,7 +2197,7 @@ static struct module *load_module(void __user *umod,
/* Now sew it into the lists so we can get lockdep and oops
* info during argument parsing. Noone should access us, since
* strong_try_module_get() will fail. */
- stop_machine_run(__link_module, mod, NR_CPUS);
+ stop_machine(__link_module, mod, NULL);
/* Size of section 0 is 0, so this works well if no params */
err = parse_args(mod->name, mod->args,
@@ -2230,7 +2231,7 @@ static struct module *load_module(void __user *umod,
return mod;
unlink:
- stop_machine_run(__unlink_module, mod, NR_CPUS);
+ stop_machine(__unlink_module, mod, NULL);
module_arch_cleanup(mod);
cleanup:
kobject_del(&mod->mkobj.kobj);
diff --git a/kernel/rcuclassic.c b/kernel/rcuclassic.c
index 6f8696c502f..aad93cdc9f6 100644
--- a/kernel/rcuclassic.c
+++ b/kernel/rcuclassic.c
@@ -91,8 +91,8 @@ static void force_quiescent_state(struct rcu_data *rdp,
* rdp->cpu is the current cpu.
*
* cpu_online_map is updated by the _cpu_down()
- * using stop_machine_run(). Since we're in irqs disabled
- * section, stop_machine_run() is not exectuting, hence
+ * using __stop_machine(). Since we're in irqs disabled
+ * section, __stop_machine() is not exectuting, hence
* the cpu_online_map is stable.
*
* However, a cpu might have been offlined _just_ before
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 738b411ff2d..e446c7c7d6a 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -1,4 +1,4 @@
-/* Copyright 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
+/* Copyright 2008, 2005 Rusty Russell rusty@rustcorp.com.au IBM Corporation.
* GPL v2 and any later version.
*/
#include <linux/cpu.h>
@@ -13,204 +13,178 @@
#include <asm/atomic.h>
#include <asm/uaccess.h>
-/* Since we effect priority and affinity (both of which are visible
- * to, and settable by outside processes) we do indirection via a
- * kthread. */
-
-/* Thread to stop each CPU in user context. */
+/* This controls the threads on each CPU. */
enum stopmachine_state {
- STOPMACHINE_WAIT,
+ /* Dummy starting state for thread. */
+ STOPMACHINE_NONE,
+ /* Awaiting everyone to be scheduled. */
STOPMACHINE_PREPARE,
+ /* Disable interrupts. */
STOPMACHINE_DISABLE_IRQ,
+ /* Run the function */
+ STOPMACHINE_RUN,
+ /* Exit */
STOPMACHINE_EXIT,
};
+static enum stopmachine_state state;
-static enum stopmachine_state stopmachine_state;
-static unsigned int stopmachine_num_threads;
-static atomic_t stopmachine_thread_ack;
-
-static int stopmachine(void *cpu)
-{
- int irqs_disabled = 0;
- int prepared = 0;
- cpumask_of_cpu_ptr(cpumask, (int)(long)cpu);
-
- set_cpus_allowed_ptr(current, cpumask);
-
- /* Ack: we are alive */
- smp_mb(); /* Theoretically the ack = 0 might not be on this CPU yet. */
- atomic_inc(&stopmachine_thread_ack);
-
- /* Simple state machine */
- while (stopmachine_state != STOPMACHINE_EXIT) {
- if (stopmachine_state == STOPMACHINE_DISABLE_IRQ
- && !irqs_disabled) {
- local_irq_disable();
- hard_irq_disable();
- irqs_disabled = 1;
- /* Ack: irqs disabled. */
- smp_mb(); /* Must read state first. */
- atomic_inc(&stopmachine_thread_ack);
- } else if (stopmachine_state == STOPMACHINE_PREPARE
- && !prepared) {
- /* Everyone is in place, hold CPU. */
- preempt_disable();
- prepared = 1;
- smp_mb(); /* Must read state first. */
- atomic_inc(&stopmachine_thread_ack);
- }
- /* Yield in first stage: migration threads need to
- * help our sisters onto their CPUs. */
- if (!prepared && !irqs_disabled)
- yield();
- cpu_relax();
- }
-
- /* Ack: we are exiting. */
- smp_mb(); /* Must read state first. */
- atomic_inc(&stopmachine_thread_ack);
-
- if (irqs_disabled)
- local_irq_enable();
- if (prepared)
- preempt_enable();
+struct stop_machine_data {
+ int (*fn)(void *);
+ void *data;
+ int fnret;
+};
- return 0;
-}
+/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+static unsigned int num_threads;
+static atomic_t thread_ack;
+static struct completion finished;
+static DEFINE_MUTEX(lock);
-/* Change the thread state */
-static void stopmachine_set_state(enum stopmachine_state state)
+static void set_state(enum stopmachine_state newstate)
{
- atomic_set(&stopmachine_thread_ack, 0);
+ /* Reset ack counter. */
+ atomic_set(&thread_ack, num_threads);
smp_wmb();
- stopmachine_state = state;
- while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads)
- cpu_relax();
+ state = newstate;
}
-static int stop_machine(void)
+/* Last one to ack a state moves to the next state. */
+static void ack_state(void)
{
- int i, ret = 0;
-
- atomic_set(&stopmachine_thread_ack, 0);
- stopmachine_num_threads = 0;
- stopmachine_state = STOPMACHINE_WAIT;
-
- for_each_online_cpu(i) {
- if (i == raw_smp_processor_id())
- continue;
- ret = kernel_thread(stopmachine, (void *)(long)i,CLONE_KERNEL);
- if (ret < 0)
- break;
- stopmachine_num_threads++;
- }
-
- /* Wait for them all to come to life. */
- while (atomic_read(&stopmachine_thread_ack) != stopmachine_num_threads) {
- yield();
- cpu_relax();
+ if (atomic_dec_and_test(&thread_ack)) {
+ /* If we're the last one to ack the EXIT, we're finished. */
+ if (state == STOPMACHINE_EXIT)
+ complete(&finished);
+ else
+ set_state(state + 1);
}
+}
- /* If some failed, kill them all. */
- if (ret < 0) {
- stopmachine_set_state(STOPMACHINE_EXIT);
- return ret;
- }
+/* This is the actual thread which stops the CPU. It exits by itself rather
+ * than waiting for kthread_stop(), because it's easier for hotplug CPU. */
+static int stop_cpu(struct stop_machine_data *smdata)
+{
+ enum stopmachine_state curstate = STOPMACHINE_NONE;
+ int uninitialized_var(ret);
- /* Now they are all started, make them hold the CPUs, ready. */
- preempt_disable();
- stopmachine_set_state(STOPMACHINE_PREPARE);
+ /* Simple state machine */
+ do {
+ /* Chill out and ensure we re-read stopmachine_state. */
+ cpu_relax();
+ if (state != curstate) {
+ curstate = state;
+ switch (curstate) {
+ case STOPMACHINE_DISABLE_IRQ:
+ local_irq_disable();
+ hard_irq_disable();
+ break;
+ case STOPMACHINE_RUN:
+ /* |= allows error detection if functions on
+ * multiple CPUs. */
+ smdata->fnret |= smdata->fn(smdata->data);
+ break;
+ default:
+ break;
+ }
+ ack_state();
+ }
+ } while (curstate != STOPMACHINE_EXIT);
- /* Make them disable irqs. */
- local_irq_disable();
- hard_irq_disable();
- stopmachine_set_state(STOPMACHINE_DISABLE_IRQ);
+ local_irq_enable();
+ do_exit(0);
+}
+/* Callback for CPUs which aren't supposed to do anything. */
+static int chill(void *unused)
+{
return 0;
}
-static void restart_machine(void)
+int __stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
{
- stopmachine_set_state(STOPMACHINE_EXIT);
- local_irq_enable();
- preempt_enable_no_resched();
-}
+ int i, err;
+ struct stop_machine_data active, idle;
+ struct task_struct **threads;
+
+ active.fn = fn;
+ active.data = data;
+ active.fnret = 0;
+ idle.fn = chill;
+ idle.data = NULL;
+
+ /* This could be too big for stack on large machines. */
+ threads = kcalloc(NR_CPUS, sizeof(threads[0]), GFP_KERNEL);
+ if (!threads)
+ return -ENOMEM;
+
+ /* Set up initial state. */
+ mutex_lock(&lock);
+ init_completion(&finished);
+ num_threads = num_online_cpus();
+ set_state(STOPMACHINE_PREPARE);
-struct stop_machine_data {
- int (*fn)(void *);
- void *data;
- struct completion done;
-};
+ for_each_online_cpu(i) {
+ struct stop_machine_data *smdata = &idle;
+ struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
-static int do_stop(void *_smdata)
-{
- struct stop_machine_data *smdata = _smdata;
- int ret;
+ if (!cpus) {
+ if (i == first_cpu(cpu_online_map))
+ smdata = &active;
+ } else {
+ if (cpu_isset(i, *cpus))
+ smdata = &active;
+ }
- ret = stop_machine();
- if (ret == 0) {
- ret = smdata->fn(smdata->data);
- restart_machine();
- }
+ threads[i] = kthread_create((void *)stop_cpu, smdata, "kstop%u",
+ i);
+ if (IS_ERR(threads[i])) {
+ err = PTR_ERR(threads[i]);
+ threads[i] = NULL;
+ goto kill_threads;
+ }
- /* We're done: you can kthread_stop us now */
- complete(&smdata->done);
+ /* Place it onto correct cpu. */
+ kthread_bind(threads[i], i);
- /* Wait for kthread_stop */
- set_current_state(TASK_INTERRUPTIBLE);
- while (!kthread_should_stop()) {
- schedule();
- set_current_state(TASK_INTERRUPTIBLE);
+ /* Make it highest prio. */
+ if (sched_setscheduler_nocheck(threads[i], SCHED_FIFO, &param))
+ BUG();
}
- __set_current_state(TASK_RUNNING);
- return ret;
-}
-struct task_struct *__stop_machine_run(int (*fn)(void *), void *data,
- unsigned int cpu)
-{
- static DEFINE_MUTEX(stopmachine_mutex);
- struct stop_machine_data smdata;
- struct task_struct *p;
+ /* We've created all the threads. Wake them all: hold this CPU so one
+ * doesn't hit this CPU until we're ready. */
+ get_cpu();
+ for_each_online_cpu(i)
+ wake_up_process(threads[i]);
- smdata.fn = fn;
- smdata.data = data;
- init_completion(&smdata.done);
+ /* This will release the thread on our CPU. */
+ put_cpu();
+ wait_for_completion(&finished);
+ mutex_unlock(&lock);
- mutex_lock(&stopmachine_mutex);
+ kfree(threads);
- /* If they don't care which CPU fn runs on, bind to any online one. */
- if (cpu == NR_CPUS)
- cpu = raw_smp_processor_id();
+ return active.fnret;
- p = kthread_create(do_stop, &smdata, "kstopmachine");
- if (!IS_ERR(p)) {
- struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
+kill_threads:
+ for_each_online_cpu(i)
+ if (threads[i])
+ kthread_stop(threads[i]);
+ mutex_unlock(&lock);
- /* One high-prio thread per cpu. We'll do this one. */
- sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
- kthread_bind(p, cpu);
- wake_up_process(p);
- wait_for_completion(&smdata.done);
- }
- mutex_unlock(&stopmachine_mutex);
- return p;
+ kfree(threads);
+ return err;
}
-int stop_machine_run(int (*fn)(void *), void *data, unsigned int cpu)
+int stop_machine(int (*fn)(void *), void *data, const cpumask_t *cpus)
{
- struct task_struct *p;
int ret;
/* No CPUs can come up or down during this. */
get_online_cpus();
- p = __stop_machine_run(fn, data, cpu);
- if (!IS_ERR(p))
- ret = kthread_stop(p);
- else
- ret = PTR_ERR(p);
+ ret = __stop_machine(fn, data, cpus);
put_online_cpus();
return ret;
}
-EXPORT_SYMBOL_GPL(stop_machine_run);
+EXPORT_SYMBOL_GPL(stop_machine);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 911d846f050..fe471334727 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1680,43 +1680,45 @@ static __init int sysctl_init(void)
core_initcall(sysctl_init);
-static int is_branch_in(struct ctl_table *branch, struct ctl_table *table)
+static struct ctl_table *is_branch_in(struct ctl_table *branch,
+ struct ctl_table *table)
{
struct ctl_table *p;
const char *s = branch->procname;
/* branch should have named subdirectory as its first element */
if (!s || !branch->child)
- return 0;
+ return NULL;
/* ... and nothing else */
if (branch[1].procname || branch[1].ctl_name)
- return 0;
+ return NULL;
/* table should contain subdirectory with the same name */
for (p = table; p->procname || p->ctl_name; p++) {
if (!p->child)
continue;
if (p->procname && strcmp(p->procname, s) == 0)
- return 1;
+ return p;
}
- return 0;
+ return NULL;
}
/* see if attaching q to p would be an improvement */
static void try_attach(struct ctl_table_header *p, struct ctl_table_header *q)
{
struct ctl_table *to = p->ctl_table, *by = q->ctl_table;
+ struct ctl_table *next;
int is_better = 0;
int not_in_parent = !p->attached_by;
- while (is_branch_in(by, to)) {
+ while ((next = is_branch_in(by, to)) != NULL) {
if (by == q->attached_by)
is_better = 1;
if (to == p->attached_by)
not_in_parent = 1;
by = by->child;
- to = to->child;
+ to = next->child;
}
if (is_better && not_in_parent) {
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index bf43284d685..80c4336f418 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -196,12 +196,10 @@ static int tick_check_new_device(struct clock_event_device *newdev)
struct tick_device *td;
int cpu, ret = NOTIFY_OK;
unsigned long flags;
- cpumask_of_cpu_ptr_declare(cpumask);
spin_lock_irqsave(&tick_device_lock, flags);
cpu = smp_processor_id();
- cpumask_of_cpu_ptr_next(cpumask, cpu);
if (!cpu_isset(cpu, newdev->cpumask))
goto out_bc;
@@ -209,7 +207,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
curdev = td->evtdev;
/* cpu local device ? */
- if (!cpus_equal(newdev->cpumask, *cpumask)) {
+ if (!cpus_equal(newdev->cpumask, cpumask_of_cpu(cpu))) {
/*
* If the cpu affinity of the device interrupt can not
@@ -222,7 +220,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
* If we have a cpu local device already, do not replace it
* by a non cpu local device
*/
- if (curdev && cpus_equal(curdev->cpumask, *cpumask))
+ if (curdev && cpus_equal(curdev->cpumask, cpumask_of_cpu(cpu)))
goto out_bc;
}
@@ -254,7 +252,7 @@ static int tick_check_new_device(struct clock_event_device *newdev)
curdev = NULL;
}
clockevents_exchange_device(curdev, newdev);
- tick_setup_device(td, newdev, cpu, cpumask);
+ tick_setup_device(td, newdev, cpu, &cpumask_of_cpu(cpu));
if (newdev->features & CLOCK_EVT_FEAT_ONESHOT)
tick_oneshot_notify();
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4231a3dc224..f6e3af31b40 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -587,7 +587,7 @@ static int __ftrace_modify_code(void *data)
static void ftrace_run_update_code(int command)
{
- stop_machine_run(__ftrace_modify_code, &command, NR_CPUS);
+ stop_machine(__ftrace_modify_code, &command, NULL);
}
void ftrace_disable_daemon(void)
@@ -787,7 +787,7 @@ static int ftrace_update_code(void)
!ftrace_enabled || !ftraced_trigger)
return 0;
- stop_machine_run(__ftrace_update_code, NULL, NR_CPUS);
+ stop_machine(__ftrace_update_code, NULL, NULL);
return 1;
}
@@ -1564,7 +1564,7 @@ static int __init ftrace_dynamic_init(void)
addr = (unsigned long)ftrace_record_ip;
- stop_machine_run(ftrace_dyn_arch_init, &addr, NR_CPUS);
+ stop_machine(ftrace_dyn_arch_init, &addr, NULL);
/* ftrace_dyn_arch_init places the return code in addr */
if (addr) {
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index fc20e09a6cb..8f3fb3db61c 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1183,7 +1183,6 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
static void *s_next(struct seq_file *m, void *v, loff_t *pos)
{
struct trace_iterator *iter = m->private;
- void *last_ent = iter->ent;
int i = (int)*pos;
void *ent;
diff --git a/kernel/trace/trace_sysprof.c b/kernel/trace/trace_sysprof.c
index ce2d723c10e..bb948e52ce2 100644
--- a/kernel/trace/trace_sysprof.c
+++ b/kernel/trace/trace_sysprof.c
@@ -213,9 +213,7 @@ static void start_stack_timers(void)
int cpu;
for_each_online_cpu(cpu) {
- cpumask_of_cpu_ptr(new_mask, cpu);
-
- set_cpus_allowed_ptr(current, new_mask);
+ set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
start_stack_timer(cpu);
}
set_cpus_allowed_ptr(current, &saved_mask);
diff --git a/kernel/tsacct.c b/kernel/tsacct.c
index 3da47ccdc5e..8ebcd8532df 100644
--- a/kernel/tsacct.c
+++ b/kernel/tsacct.c
@@ -94,10 +94,10 @@ void xacct_add_tsk(struct taskstats *stats, struct task_struct *p)
stats->hiwater_vm = mm->hiwater_vm * PAGE_SIZE / KB;
mmput(mm);
}
- stats->read_char = p->rchar;
- stats->write_char = p->wchar;
- stats->read_syscalls = p->syscr;
- stats->write_syscalls = p->syscw;
+ stats->read_char = p->ioac.rchar;
+ stats->write_char = p->ioac.wchar;
+ stats->read_syscalls = p->ioac.syscr;
+ stats->write_syscalls = p->ioac.syscw;
#ifdef CONFIG_TASK_IO_ACCOUNTING
stats->read_bytes = p->ioac.read_bytes;
stats->write_bytes = p->ioac.write_bytes;
generated by cgit v1.2.3-18-g5258 (git 2.32.0) at 2025-02-20 07:17:27 +0000