aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/futex.c10
-rw-r--r--kernel/hw_breakpoint.c146
-rw-r--r--kernel/kgdb.c56
-rw-r--r--kernel/lockdep.c16
-rw-r--r--kernel/perf_event.c75
-rw-r--r--kernel/resource.c26
-rw-r--r--kernel/trace/trace.c57
-rw-r--r--kernel/trace/trace.h2
-rw-r--r--kernel/trace/trace_functions_graph.c165
-rw-r--r--kernel/trace/trace_kprobe.c41
-rw-r--r--kernel/trace/trace_ksym.c5
-rw-r--r--kernel/trace/trace_output.c75
-rw-r--r--kernel/workqueue.c131
14 files changed, 604 insertions, 203 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index 1143012951e..6f50ef55a6f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -971,7 +971,7 @@ NORET_TYPE void do_exit(long code)
exit_thread();
cgroup_exit(tsk, 1);
- if (group_dead && tsk->signal->leader)
+ if (group_dead)
disassociate_ctty(1);
module_put(task_thread_info(tsk)->exec_domain->module);
diff --git a/kernel/futex.c b/kernel/futex.c
index fb65e822fc4..d73ef1f3e55 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -304,8 +304,14 @@ void put_futex_key(int fshared, union futex_key *key)
*/
static int fault_in_user_writeable(u32 __user *uaddr)
{
- int ret = get_user_pages(current, current->mm, (unsigned long)uaddr,
- 1, 1, 0, NULL, NULL);
+ struct mm_struct *mm = current->mm;
+ int ret;
+
+ down_read(&mm->mmap_sem);
+ ret = get_user_pages(current, mm, (unsigned long)uaddr,
+ 1, 1, 0, NULL, NULL);
+ up_read(&mm->mmap_sem);
+
return ret < 0 ? ret : 0;
}
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index cf5ee162841..366eedf949c 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -52,7 +52,7 @@
static DEFINE_PER_CPU(unsigned int, nr_cpu_bp_pinned);
/* Number of pinned task breakpoints in a cpu */
-static DEFINE_PER_CPU(unsigned int, task_bp_pinned[HBP_NUM]);
+static DEFINE_PER_CPU(unsigned int, nr_task_bp_pinned[HBP_NUM]);
/* Number of non-pinned cpu/task breakpoints in a cpu */
static DEFINE_PER_CPU(unsigned int, nr_bp_flexible);
@@ -73,7 +73,7 @@ static DEFINE_MUTEX(nr_bp_mutex);
static unsigned int max_task_bp_pinned(int cpu)
{
int i;
- unsigned int *tsk_pinned = per_cpu(task_bp_pinned, cpu);
+ unsigned int *tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
for (i = HBP_NUM -1; i >= 0; i--) {
if (tsk_pinned[i] > 0)
@@ -83,15 +83,51 @@ static unsigned int max_task_bp_pinned(int cpu)
return 0;
}
+static int task_bp_pinned(struct task_struct *tsk)
+{
+ struct perf_event_context *ctx = tsk->perf_event_ctxp;
+ struct list_head *list;
+ struct perf_event *bp;
+ unsigned long flags;
+ int count = 0;
+
+ if (WARN_ONCE(!ctx, "No perf context for this task"))
+ return 0;
+
+ list = &ctx->event_list;
+
+ spin_lock_irqsave(&ctx->lock, flags);
+
+ /*
+ * The current breakpoint counter is not included in the list
+ * at the open() callback time
+ */
+ list_for_each_entry(bp, list, event_entry) {
+ if (bp->attr.type == PERF_TYPE_BREAKPOINT)
+ count++;
+ }
+
+ spin_unlock_irqrestore(&ctx->lock, flags);
+
+ return count;
+}
+
/*
* Report the number of pinned/un-pinned breakpoints we have in
* a given cpu (cpu > -1) or in all of them (cpu = -1).
*/
-static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu)
+static void
+fetch_bp_busy_slots(struct bp_busy_slots *slots, struct perf_event *bp)
{
+ int cpu = bp->cpu;
+ struct task_struct *tsk = bp->ctx->task;
+
if (cpu >= 0) {
slots->pinned = per_cpu(nr_cpu_bp_pinned, cpu);
- slots->pinned += max_task_bp_pinned(cpu);
+ if (!tsk)
+ slots->pinned += max_task_bp_pinned(cpu);
+ else
+ slots->pinned += task_bp_pinned(tsk);
slots->flexible = per_cpu(nr_bp_flexible, cpu);
return;
@@ -101,7 +137,10 @@ static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu)
unsigned int nr;
nr = per_cpu(nr_cpu_bp_pinned, cpu);
- nr += max_task_bp_pinned(cpu);
+ if (!tsk)
+ nr += max_task_bp_pinned(cpu);
+ else
+ nr += task_bp_pinned(tsk);
if (nr > slots->pinned)
slots->pinned = nr;
@@ -118,35 +157,12 @@ static void fetch_bp_busy_slots(struct bp_busy_slots *slots, int cpu)
*/
static void toggle_bp_task_slot(struct task_struct *tsk, int cpu, bool enable)
{
- int count = 0;
- struct perf_event *bp;
- struct perf_event_context *ctx = tsk->perf_event_ctxp;
unsigned int *tsk_pinned;
- struct list_head *list;
- unsigned long flags;
-
- if (WARN_ONCE(!ctx, "No perf context for this task"))
- return;
-
- list = &ctx->event_list;
-
- spin_lock_irqsave(&ctx->lock, flags);
-
- /*
- * The current breakpoint counter is not included in the list
- * at the open() callback time
- */
- list_for_each_entry(bp, list, event_entry) {
- if (bp->attr.type == PERF_TYPE_BREAKPOINT)
- count++;
- }
+ int count = 0;
- spin_unlock_irqrestore(&ctx->lock, flags);
+ count = task_bp_pinned(tsk);
- if (WARN_ONCE(count < 0, "No breakpoint counter found in the counter list"))
- return;
-
- tsk_pinned = per_cpu(task_bp_pinned, cpu);
+ tsk_pinned = per_cpu(nr_task_bp_pinned, cpu);
if (enable) {
tsk_pinned[count]++;
if (count > 0)
@@ -193,7 +209,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
* - If attached to a single cpu, check:
*
* (per_cpu(nr_bp_flexible, cpu) || (per_cpu(nr_cpu_bp_pinned, cpu)
- * + max(per_cpu(task_bp_pinned, cpu)))) < HBP_NUM
+ * + max(per_cpu(nr_task_bp_pinned, cpu)))) < HBP_NUM
*
* -> If there are already non-pinned counters in this cpu, it means
* there is already a free slot for them.
@@ -204,7 +220,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
* - If attached to every cpus, check:
*
* (per_cpu(nr_bp_flexible, *) || (max(per_cpu(nr_cpu_bp_pinned, *))
- * + max(per_cpu(task_bp_pinned, *)))) < HBP_NUM
+ * + max(per_cpu(nr_task_bp_pinned, *)))) < HBP_NUM
*
* -> This is roughly the same, except we check the number of per cpu
* bp for every cpu and we keep the max one. Same for the per tasks
@@ -216,7 +232,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
* - If attached to a single cpu, check:
*
* ((per_cpu(nr_bp_flexible, cpu) > 1) + per_cpu(nr_cpu_bp_pinned, cpu)
- * + max(per_cpu(task_bp_pinned, cpu))) < HBP_NUM
+ * + max(per_cpu(nr_task_bp_pinned, cpu))) < HBP_NUM
*
* -> Same checks as before. But now the nr_bp_flexible, if any, must keep
* one register at least (or they will never be fed).
@@ -224,7 +240,7 @@ static void toggle_bp_slot(struct perf_event *bp, bool enable)
* - If attached to every cpus, check:
*
* ((per_cpu(nr_bp_flexible, *) > 1) + max(per_cpu(nr_cpu_bp_pinned, *))
- * + max(per_cpu(task_bp_pinned, *))) < HBP_NUM
+ * + max(per_cpu(nr_task_bp_pinned, *))) < HBP_NUM
*/
int reserve_bp_slot(struct perf_event *bp)
{
@@ -233,7 +249,7 @@ int reserve_bp_slot(struct perf_event *bp)
mutex_lock(&nr_bp_mutex);
- fetch_bp_busy_slots(&slots, bp->cpu);
+ fetch_bp_busy_slots(&slots, bp);
/* Flexible counters need to keep at least one slot */
if (slots.pinned + (!!slots.flexible) == HBP_NUM) {
@@ -259,7 +275,7 @@ void release_bp_slot(struct perf_event *bp)
}
-int __register_perf_hw_breakpoint(struct perf_event *bp)
+int register_perf_hw_breakpoint(struct perf_event *bp)
{
int ret;
@@ -276,19 +292,12 @@ int __register_perf_hw_breakpoint(struct perf_event *bp)
* This is a quick hack that will be removed soon, once we remove
* the tmp breakpoints from ptrace
*/
- if (!bp->attr.disabled || bp->callback == perf_bp_event)
+ if (!bp->attr.disabled || !bp->overflow_handler)
ret = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
return ret;
}
-int register_perf_hw_breakpoint(struct perf_event *bp)
-{
- bp->callback = perf_bp_event;
-
- return __register_perf_hw_breakpoint(bp);
-}
-
/**
* register_user_hw_breakpoint - register a hardware breakpoint for user space
* @attr: breakpoint attributes
@@ -297,7 +306,7 @@ int register_perf_hw_breakpoint(struct perf_event *bp)
*/
struct perf_event *
register_user_hw_breakpoint(struct perf_event_attr *attr,
- perf_callback_t triggered,
+ perf_overflow_handler_t triggered,
struct task_struct *tsk)
{
return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
@@ -311,19 +320,40 @@ EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
* @triggered: callback to trigger when we hit the breakpoint
* @tsk: pointer to 'task_struct' of the process to which the address belongs
*/
-struct perf_event *
-modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr,
- perf_callback_t triggered,
- struct task_struct *tsk)
+int modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr)
{
- /*
- * FIXME: do it without unregistering
- * - We don't want to lose our slot
- * - If the new bp is incorrect, don't lose the older one
- */
- unregister_hw_breakpoint(bp);
+ u64 old_addr = bp->attr.bp_addr;
+ int old_type = bp->attr.bp_type;
+ int old_len = bp->attr.bp_len;
+ int err = 0;
- return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+ perf_event_disable(bp);
+
+ bp->attr.bp_addr = attr->bp_addr;
+ bp->attr.bp_type = attr->bp_type;
+ bp->attr.bp_len = attr->bp_len;
+
+ if (attr->disabled)
+ goto end;
+
+ err = arch_validate_hwbkpt_settings(bp, bp->ctx->task);
+ if (!err)
+ perf_event_enable(bp);
+
+ if (err) {
+ bp->attr.bp_addr = old_addr;
+ bp->attr.bp_type = old_type;
+ bp->attr.bp_len = old_len;
+ if (!bp->attr.disabled)
+ perf_event_enable(bp);
+
+ return err;
+ }
+
+end:
+ bp->attr.disabled = attr->disabled;
+
+ return 0;
}
EXPORT_SYMBOL_GPL(modify_user_hw_breakpoint);
@@ -348,7 +378,7 @@ EXPORT_SYMBOL_GPL(unregister_hw_breakpoint);
*/
struct perf_event **
register_wide_hw_breakpoint(struct perf_event_attr *attr,
- perf_callback_t triggered)
+ perf_overflow_handler_t triggered)
{
struct perf_event **cpu_events, **pevent, *bp;
long err;
diff --git a/kernel/kgdb.c b/kernel/kgdb.c
index 7d701463402..2eb517e2351 100644
--- a/kernel/kgdb.c
+++ b/kernel/kgdb.c
@@ -129,6 +129,7 @@ struct task_struct *kgdb_usethread;
struct task_struct *kgdb_contthread;
int kgdb_single_step;
+pid_t kgdb_sstep_pid;
/* Our I/O buffers. */
static char remcom_in_buffer[BUFMAX];
@@ -541,12 +542,17 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
*/
if (tid == 0 || tid == -1)
tid = -atomic_read(&kgdb_active) - 2;
- if (tid < 0) {
+ if (tid < -1 && tid > -NR_CPUS - 2) {
if (kgdb_info[-tid - 2].task)
return kgdb_info[-tid - 2].task;
else
return idle_task(-tid - 2);
}
+ if (tid <= 0) {
+ printk(KERN_ERR "KGDB: Internal thread select error\n");
+ dump_stack();
+ return NULL;
+ }
/*
* find_task_by_pid_ns() does not take the tasklist lock anymore
@@ -619,7 +625,8 @@ static void kgdb_flush_swbreak_addr(unsigned long addr)
static int kgdb_activate_sw_breakpoints(void)
{
unsigned long addr;
- int error = 0;
+ int error;
+ int ret = 0;
int i;
for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
@@ -629,13 +636,16 @@ static int kgdb_activate_sw_breakpoints(void)
addr = kgdb_break[i].bpt_addr;
error = kgdb_arch_set_breakpoint(addr,
kgdb_break[i].saved_instr);
- if (error)
- return error;
+ if (error) {
+ ret = error;
+ printk(KERN_INFO "KGDB: BP install failed: %lx", addr);
+ continue;
+ }
kgdb_flush_swbreak_addr(addr);
kgdb_break[i].state = BP_ACTIVE;
}
- return 0;
+ return ret;
}
static int kgdb_set_sw_break(unsigned long addr)
@@ -682,7 +692,8 @@ static int kgdb_set_sw_break(unsigned long addr)
static int kgdb_deactivate_sw_breakpoints(void)
{
unsigned long addr;
- int error = 0;
+ int error;
+ int ret = 0;
int i;
for (i = 0; i < KGDB_MAX_BREAKPOINTS; i++) {
@@ -691,13 +702,15 @@ static int kgdb_deactivate_sw_breakpoints(void)
addr = kgdb_break[i].bpt_addr;
error = kgdb_arch_remove_breakpoint(addr,
kgdb_break[i].saved_instr);
- if (error)
- return error;
+ if (error) {
+ printk(KERN_INFO "KGDB: BP remove failed: %lx\n", addr);
+ ret = error;
+ }
kgdb_flush_swbreak_addr(addr);
kgdb_break[i].state = BP_SET;
}
- return 0;
+ return ret;
}
static int kgdb_remove_sw_break(unsigned long addr)
@@ -1204,8 +1217,10 @@ static int gdb_cmd_exception_pass(struct kgdb_state *ks)
return 1;
} else {
- error_packet(remcom_out_buffer, -EINVAL);
- return 0;
+ kgdb_msg_write("KGDB only knows signal 9 (pass)"
+ " and 15 (pass and disconnect)\n"
+ "Executing a continue without signal passing\n", 0);
+ remcom_in_buffer[0] = 'c';
}
/* Indicate fall through */
@@ -1395,6 +1410,7 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
struct kgdb_state kgdb_var;
struct kgdb_state *ks = &kgdb_var;
unsigned long flags;
+ int sstep_tries = 100;
int error = 0;
int i, cpu;
@@ -1425,13 +1441,14 @@ acquirelock:
cpu_relax();
/*
- * Do not start the debugger connection on this CPU if the last
- * instance of the exception handler wanted to come into the
- * debugger on a different CPU via a single step
+ * For single stepping, try to only enter on the processor
+ * that was single stepping. To gaurd against a deadlock, the
+ * kernel will only try for the value of sstep_tries before
+ * giving up and continuing on.
*/
if (atomic_read(&kgdb_cpu_doing_single_step) != -1 &&
- atomic_read(&kgdb_cpu_doing_single_step) != cpu) {
-
+ (kgdb_info[cpu].task &&
+ kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
atomic_set(&kgdb_active, -1);
touch_softlockup_watchdog();
clocksource_touch_watchdog();
@@ -1524,6 +1541,13 @@ acquirelock:
}
kgdb_restore:
+ if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
+ int sstep_cpu = atomic_read(&kgdb_cpu_doing_single_step);
+ if (kgdb_info[sstep_cpu].task)
+ kgdb_sstep_pid = kgdb_info[sstep_cpu].task->pid;
+ else
+ kgdb_sstep_pid = 0;
+ }
/* Free kgdb_active */
atomic_set(&kgdb_active, -1);
touch_softlockup_watchdog();
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index f5dcd36d315..4f8df01dbe5 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -168,7 +168,7 @@ 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;
@@ -177,8 +177,15 @@ static void lock_time_inc(struct lock_time *lt, u64 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;
}
@@ -379,7 +386,8 @@ static int save_trace(struct stack_trace *trace)
* 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;
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 40a996ec39f..e73e53c7582 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -36,7 +36,7 @@
/*
* Each CPU has a list of per CPU events:
*/
-DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
+static DEFINE_PER_CPU(struct perf_cpu_context, perf_cpu_context);
int perf_max_events __read_mostly = 1;
static int perf_reserved_percpu __read_mostly;
@@ -567,7 +567,7 @@ static void __perf_event_disable(void *info)
* is the current context on this CPU and preemption is disabled,
* hence we can't get into perf_event_task_sched_out for this context.
*/
-static void perf_event_disable(struct perf_event *event)
+void perf_event_disable(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
@@ -971,7 +971,7 @@ static void __perf_event_enable(void *info)
* perf_event_for_each_child or perf_event_for_each as described
* for perf_event_disable.
*/
-static void perf_event_enable(struct perf_event *event)
+void perf_event_enable(struct perf_event *event)
{
struct perf_event_context *ctx = event->ctx;
struct task_struct *task = ctx->task;
@@ -1579,7 +1579,6 @@ static void
__perf_event_init_context(struct perf_event_context *ctx,
struct task_struct *task)
{
- memset(ctx, 0, sizeof(*ctx));
spin_lock_init(&ctx->lock);
mutex_init(&ctx->mutex);
INIT_LIST_HEAD(&ctx->group_list);
@@ -1654,7 +1653,7 @@ static struct perf_event_context *find_get_context(pid_t pid, int cpu)
}
if (!ctx) {
- ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
+ ctx = kzalloc(sizeof(struct perf_event_context), GFP_KERNEL);
err = -ENOMEM;
if (!ctx)
goto errout;
@@ -4011,6 +4010,7 @@ static enum hrtimer_restart perf_swevent_hrtimer(struct hrtimer *hrtimer)
event->pmu->read(event);
data.addr = 0;
+ data.raw = NULL;
data.period = event->hw.last_period;
regs = get_irq_regs();
/*
@@ -4080,8 +4080,7 @@ static void cpu_clock_perf_event_update(struct perf_event *event)
u64 now;
now = cpu_clock(cpu);
- prev = atomic64_read(&event->hw.prev_count);
- atomic64_set(&event->hw.prev_count, now);
+ prev = atomic64_xchg(&event->hw.prev_count, now);
atomic64_add(now - prev, &event->count);
}
@@ -4286,15 +4285,8 @@ static void bp_perf_event_destroy(struct perf_event *event)
static const struct pmu *bp_perf_event_init(struct perf_event *bp)
{
int err;
- /*
- * The breakpoint is already filled if we haven't created the counter
- * through perf syscall
- * FIXME: manage to get trigerred to NULL if it comes from syscalls
- */
- if (!bp->callback)
- err = register_perf_hw_breakpoint(bp);
- else
- err = __register_perf_hw_breakpoint(bp);
+
+ err = register_perf_hw_breakpoint(bp);
if (err)
return ERR_PTR(err);
@@ -4308,6 +4300,7 @@ void perf_bp_event(struct perf_event *bp, void *data)
struct perf_sample_data sample;
struct pt_regs *regs = data;
+ sample.raw = NULL;
sample.addr = bp->attr.bp_addr;
if (!perf_exclude_event(bp, regs))
@@ -4390,7 +4383,7 @@ perf_event_alloc(struct perf_event_attr *attr,
struct perf_event_context *ctx,
struct perf_event *group_leader,
struct perf_event *parent_event,
- perf_callback_t callback,
+ perf_overflow_handler_t overflow_handler,
gfp_t gfpflags)
{
const struct pmu *pmu;
@@ -4433,10 +4426,10 @@ perf_event_alloc(struct perf_event_attr *attr,
event->state = PERF_EVENT_STATE_INACTIVE;
- if (!callback && parent_event)
- callback = parent_event->callback;
+ if (!overflow_handler && parent_event)
+ overflow_handler = parent_event->overflow_handler;
- event->callback = callback;
+ event->overflow_handler = overflow_handler;
if (attr->disabled)
event->state = PERF_EVENT_STATE_OFF;
@@ -4776,7 +4769,8 @@ err_put_context:
*/
struct perf_event *
perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
- pid_t pid, perf_callback_t callback)
+ pid_t pid,
+ perf_overflow_handler_t overflow_handler)
{
struct perf_event *event;
struct perf_event_context *ctx;
@@ -4793,7 +4787,7 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
}
event = perf_event_alloc(attr, cpu, ctx, NULL,
- NULL, callback, GFP_KERNEL);
+ NULL, overflow_handler, GFP_KERNEL);
if (IS_ERR(event)) {
err = PTR_ERR(event);
goto err_put_context;
@@ -5090,7 +5084,7 @@ again:
*/
int perf_event_init_task(struct task_struct *child)
{
- struct perf_event_context *child_ctx, *parent_ctx;
+ struct perf_event_context *child_ctx = NULL, *parent_ctx;
struct perf_event_context *cloned_ctx;
struct perf_event *event;
struct task_struct *parent = current;
@@ -5106,20 +5100,6 @@ int perf_event_init_task(struct task_struct *child)
return 0;
/*
- * This is executed from the parent task context, so inherit
- * events that have been marked for cloning.
- * First allocate and initialize a context for the child.
- */
-
- child_ctx = kmalloc(sizeof(struct perf_event_context), GFP_KERNEL);
- if (!child_ctx)
- return -ENOMEM;
-
- __perf_event_init_context(child_ctx, child);
- child->perf_event_ctxp = child_ctx;
- get_task_struct(child);
-
- /*
* If the parent's context is a clone, pin it so it won't get
* swapped under us.
*/
@@ -5149,6 +5129,26 @@ int perf_event_init_task(struct task_struct *child)
continue;
}
+ if (!child->perf_event_ctxp) {
+ /*
+ * This is executed from the parent task context, so
+ * inherit events that have been marked for cloning.
+ * First allocate and initialize a context for the
+ * child.
+ */
+
+ child_ctx = kzalloc(sizeof(struct perf_event_context),
+ GFP_KERNEL);
+ if (!child_ctx) {
+ ret = -ENOMEM;
+ goto exit;
+ }
+
+ __perf_event_init_context(child_ctx, child);
+ child->perf_event_ctxp = child_ctx;
+ get_task_struct(child);
+ }
+
ret = inherit_group(event, parent, parent_ctx,
child, child_ctx);
if (ret) {
@@ -5177,6 +5177,7 @@ int perf_event_init_task(struct task_struct *child)
get_ctx(child_ctx->parent_ctx);
}
+exit:
mutex_unlock(&parent_ctx->mutex);
perf_unpin_context(parent_ctx);
diff --git a/kernel/resource.c b/kernel/resource.c
index fb11a58b959..dc15686b7a7 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -308,35 +308,37 @@ static int find_resource(struct resource *root, struct resource *new,
void *alignf_data)
{
struct resource *this = root->child;
+ resource_size_t start, end;
- new->start = root->start;
+ start = root->start;
/*
* Skip past an allocated resource that starts at 0, since the assignment
* of this->start - 1 to new->end below would cause an underflow.
*/
if (this && this->start == 0) {
- new->start = this->end + 1;
+ start = this->end + 1;
this = this->sibling;
}
for(;;) {
if (this)
- new->end = this->start - 1;
+ end = this->start - 1;
else
- new->end = root->end;
- if (new->start < min)
- new->start = min;
- if (new->end > max)
- new->end = max;
- new->start = ALIGN(new->start, align);
+ end = root->end;
+ if (start < min)
+ start = min;
+ if (end > max)
+ end = max;
+ start = ALIGN(start, align);
if (alignf)
alignf(alignf_data, new, size, align);
- if (new->start < new->end && new->end - new->start >= size - 1) {
- new->end = new->start + size - 1;
+ if (start < end && end - start >= size - 1) {
+ new->start = start;
+ new->end = start + size - 1;
return 0;
}
if (!this)
break;
- new->start = this->end + 1;
+ start = this->end + 1;
this = this->sibling;
}
return -EBUSY;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 874f2893cff..88bd9ae2a9e 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1361,11 +1361,7 @@ int trace_array_vprintk(struct trace_array *tr,
pause_graph_tracing();
raw_local_irq_save(irq_flags);
__raw_spin_lock(&trace_buf_lock);
- if (args == NULL) {
- strncpy(trace_buf, fmt, TRACE_BUF_SIZE);
- len = strlen(trace_buf);
- } else
- len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
+ len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, args);
size = sizeof(*entry) + len + 1;
buffer = tr->buffer;
@@ -1516,6 +1512,8 @@ static void *s_next(struct seq_file *m, void *v, loff_t *pos)
int i = (int)*pos;
void *ent;
+ WARN_ON_ONCE(iter->leftover);
+
(*pos)++;
/* can't go backwards */
@@ -1614,8 +1612,16 @@ static void *s_start(struct seq_file *m, loff_t *pos)
;
} 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();
@@ -1923,6 +1929,7 @@ static enum print_line_t print_trace_line(struct trace_iterator *iter)
static int s_show(struct seq_file *m, void *v)
{
struct trace_iterator *iter = v;
+ int ret;
if (iter->ent == NULL) {
if (iter->tr) {
@@ -1942,9 +1949,27 @@ static int s_show(struct seq_file *m, void *v)
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;
@@ -2898,6 +2923,10 @@ static int tracing_release_pipe(struct inode *inode, struct file *file)
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);
@@ -3320,6 +3349,16 @@ tracing_entries_write(struct file *filp, const char __user *ubuf,
return cnt;
}
+static int mark_printk(const char *fmt, ...)
+{
+ int ret;
+ va_list args;
+ va_start(args, fmt);
+ ret = trace_vprintk(0, fmt, args);
+ va_end(args);
+ return ret;
+}
+
static ssize_t
tracing_mark_write(struct file *filp, const char __user *ubuf,
size_t cnt, loff_t *fpos)
@@ -3346,7 +3385,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf,
} else
buf[cnt] = '\0';
- cnt = trace_vprintk(0, buf, NULL);
+ cnt = mark_printk("%s", buf);
kfree(buf);
*fpos += cnt;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 1d7f4830a80..7fa33cab696 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -272,6 +272,7 @@ struct tracer_flags {
* @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)
@@ -290,6 +291,7 @@ struct tracer {
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);
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 45e6c01b2e4..a43d009c561 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -14,9 +14,20 @@
#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
@@ -384,7 +395,7 @@ verif_pid(struct trace_seq *s, pid_t pid, int cpu, struct fgraph_data *data)
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;
@@ -435,26 +446,49 @@ static struct ftrace_graph_ret_entry *
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;
@@ -640,7 +674,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
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
@@ -688,7 +722,7 @@ print_graph_entry_nested(struct trace_iterator *iter,
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;
}
@@ -782,19 +816,34 @@ static enum print_line_t
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
@@ -810,7 +859,7 @@ print_graph_return(struct ftrace_graph_ret *trace, struct trace_seq *s,
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
@@ -873,7 +922,7 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
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;
@@ -941,8 +990,33 @@ print_graph_comment(struct trace_seq *s, struct trace_entry *ent,
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: {
@@ -952,7 +1026,7 @@ print_graph_function(struct trace_iterator *iter)
* 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);
@@ -1030,31 +1104,54 @@ static void print_graph_headers(struct seq_file *s)
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,
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index aff5f80b59b..b52d397e57e 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -606,23 +606,22 @@ static int create_trace_probe(int argc, char **argv)
*/
struct trace_probe *tp;
int i, ret = 0;
- int is_return = 0;
+ int is_return = 0, is_delete = 0;
char *symbol = NULL, *event = NULL, *arg = NULL, *group = NULL;
unsigned long offset = 0;
void *addr = NULL;
char buf[MAX_EVENT_NAME_LEN];
- if (argc < 2) {
- pr_info("Probe point is not specified.\n");
- return -EINVAL;
- }
-
+ /* argc must be >= 1 */
if (argv[0][0] == 'p')
is_return = 0;
else if (argv[0][0] == 'r')
is_return = 1;
+ else if (argv[0][0] == '-')
+ is_delete = 1;
else {
- pr_info("Probe definition must be started with 'p' or 'r'.\n");
+ pr_info("Probe definition must be started with 'p', 'r' or"
+ " '-'.\n");
return -EINVAL;
}
@@ -642,7 +641,29 @@ static int create_trace_probe(int argc, char **argv)
return -EINVAL;
}
}
+ if (!group)
+ group = KPROBE_EVENT_SYSTEM;
+ if (is_delete) {
+ if (!event) {
+ pr_info("Delete command needs an event name.\n");
+ return -EINVAL;
+ }
+ tp = find_probe_event(event, group);
+ if (!tp) {
+ pr_info("Event %s/%s doesn't exist.\n", group, event);
+ return -ENOENT;
+ }
+ /* delete an event */
+ unregister_trace_probe(tp);
+ free_trace_probe(tp);
+ return 0;
+ }
+
+ if (argc < 2) {
+ pr_info("Probe point is not specified.\n");
+ return -EINVAL;
+ }
if (isdigit(argv[1][0])) {
if (is_return) {
pr_info("Return probe point must be a symbol.\n");
@@ -671,8 +692,6 @@ static int create_trace_probe(int argc, char **argv)
argc -= 2; argv += 2;
/* setup a probe */
- if (!group)
- group = KPROBE_EVENT_SYSTEM;
if (!event) {
/* Make a new event name */
if (symbol)
@@ -1114,7 +1133,7 @@ static int kprobe_event_define_fields(struct ftrace_event_call *event_call)
struct trace_probe *tp = (struct trace_probe *)event_call->data;
ret = trace_define_common_fields(event_call);
- if (!ret)
+ if (ret)
return ret;
DEFINE_FIELD(unsigned long, ip, FIELD_STRING_IP, 0);
@@ -1132,7 +1151,7 @@ static int kretprobe_event_define_fields(struct ftrace_event_call *event_call)
struct trace_probe *tp = (struct trace_probe *)event_call->data;
ret = trace_define_common_fields(event_call);
- if (!ret)
+ if (ret)
return ret;
DEFINE_FIELD(unsigned long, func, FIELD_STRING_FUNC, 0);
diff --git a/kernel/trace/trace_ksym.c b/kernel/trace/trace_ksym.c
index ddfa0fd43bc..acb87d4a4ac 100644
--- a/kernel/trace/trace_ksym.c
+++ b/kernel/trace/trace_ksym.c
@@ -79,11 +79,12 @@ void ksym_collect_stats(unsigned long hbp_hit_addr)
}
#endif /* CONFIG_PROFILE_KSYM_TRACER */
-void ksym_hbp_handler(struct perf_event *hbp, void *data)
+void ksym_hbp_handler(struct perf_event *hbp, int nmi,
+ struct perf_sample_data *data,
+ struct pt_regs *regs)
{
struct ring_buffer_event *event;
struct ksym_trace_entry *entry;
- struct pt_regs *regs = data;
struct ring_buffer *buffer;
int pc;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index b6c12c6a1bc..8e46b3323cd 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -23,13 +23,21 @@ static struct hlist_head event_hash[EVENT_HASHSIZE] __read_mostly;
static int next_event_type = __TRACE_LAST_TYPE + 1;
-void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+int trace_print_seq(struct seq_file *m, struct trace_seq *s)
{
int len = s->len >= PAGE_SIZE ? PAGE_SIZE - 1 : s->len;
+ int ret;
+
+ ret = seq_write(m, s->buffer, len);
- seq_write(m, s->buffer, len);
+ /*
+ * Only reset this buffer if we successfully wrote to the
+ * seq_file buffer.
+ */
+ if (!ret)
+ trace_seq_init(s);
- trace_seq_init(s);
+ return ret;
}
enum print_line_t trace_print_bprintk_msg_only(struct trace_iterator *iter)
@@ -85,7 +93,7 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
va_list ap;
int ret;
- if (!len)
+ if (s->full || !len)
return 0;
va_start(ap, fmt);
@@ -93,8 +101,10 @@ trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
va_end(ap);
/* If we can't write it all, don't bother writing anything */
- if (ret >= len)
+ if (ret >= len) {
+ s->full = 1;
return 0;
+ }
s->len += ret;
@@ -119,14 +129,16 @@ trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
int len = (PAGE_SIZE - 1) - s->len;
int ret;
- if (!len)
+ if (s->full || !len)
return 0;
ret = vsnprintf(s->buffer + s->len, len, fmt, args);
/* If we can't write it all, don't bother writing anything */
- if (ret >= len)
+ if (ret >= len) {
+ s->full = 1;
return 0;
+ }
s->len += ret;
@@ -139,14 +151,16 @@ int trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
int len = (PAGE_SIZE - 1) - s->len;
int ret;
- if (!len)
+ if (s->full || !len)
return 0;
ret = bstr_printf(s->buffer + s->len, len, fmt, binary);
/* If we can't write it all, don't bother writing anything */
- if (ret >= len)
+ if (ret >= len) {
+ s->full = 1;
return 0;
+ }
s->len += ret;
@@ -167,8 +181,13 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
{
int len = strlen(str);
- if (len > ((PAGE_SIZE - 1) - s->len))
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
return 0;
+ }
memcpy(s->buffer + s->len, str, len);
s->len += len;
@@ -178,9 +197,14 @@ int trace_seq_puts(struct trace_seq *s, const char *str)
int trace_seq_putc(struct trace_seq *s, unsigned char c)
{
- if (s->len >= (PAGE_SIZE - 1))
+ if (s->full)
return 0;
+ if (s->len >= (PAGE_SIZE - 1)) {
+ s->full = 1;
+ return 0;
+ }
+
s->buffer[s->len++] = c;
return 1;
@@ -188,9 +212,14 @@ int trace_seq_putc(struct trace_seq *s, unsigned char c)
int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
{
- if (len > ((PAGE_SIZE - 1) - s->len))
+ if (s->full)
return 0;
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
+ return 0;
+ }
+
memcpy(s->buffer + s->len, mem, len);
s->len += len;
@@ -203,6 +232,9 @@ int trace_seq_putmem_hex(struct trace_seq *s, const void *mem, size_t len)
const unsigned char *data = mem;
int i, j;
+ if (s->full)
+ return 0;
+
#ifdef __BIG_ENDIAN
for (i = 0, j = 0; i < len; i++) {
#else
@@ -220,8 +252,13 @@ void *trace_seq_reserve(struct trace_seq *s, size_t len)
{
void *ret;
- if (len > ((PAGE_SIZE - 1) - s->len))
+ if (s->full)
+ return 0;
+
+ if (len > ((PAGE_SIZE - 1) - s->len)) {
+ s->full = 1;
return NULL;
+ }
ret = s->buffer + s->len;
s->len += len;
@@ -233,8 +270,14 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
{
unsigned char *p;
- if (s->len >= (PAGE_SIZE - 1))
+ if (s->full)
+ return 0;
+
+ if (s->len >= (PAGE_SIZE - 1)) {
+ s->full = 1;
return 0;
+ }
+
p = d_path(path, s->buffer + s->len, PAGE_SIZE - s->len);
if (!IS_ERR(p)) {
p = mangle_path(s->buffer + s->len, p, "\n");
@@ -247,6 +290,7 @@ int trace_seq_path(struct trace_seq *s, struct path *path)
return 1;
}
+ s->full = 1;
return 0;
}
@@ -373,6 +417,9 @@ int seq_print_user_ip(struct trace_seq *s, struct mm_struct *mm,
unsigned long vmstart = 0;
int ret = 1;
+ if (s->full)
+ return 0;
+
if (mm) {
const struct vm_area_struct *vma;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 67e526b6ae8..dee48658805 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -68,6 +68,116 @@ struct workqueue_struct {
#endif
};
+#ifdef CONFIG_DEBUG_OBJECTS_WORK
+
+static struct debug_obj_descr work_debug_descr;
+
+/*
+ * fixup_init is called when:
+ * - an active object is initialized
+ */
+static int work_fixup_init(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_init(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_activate is called when:
+ * - an active object is activated
+ * - an unknown object is activated (might be a statically initialized object)
+ */
+static int work_fixup_activate(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+
+ case ODEBUG_STATE_NOTAVAILABLE:
+ /*
+ * This is not really a fixup. The work struct was
+ * statically initialized. We just make sure that it
+ * is tracked in the object tracker.
+ */
+ if (test_bit(WORK_STRUCT_STATIC, work_data_bits(work))) {
+ debug_object_init(work, &work_debug_descr);
+ debug_object_activate(work, &work_debug_descr);
+ return 0;
+ }
+ WARN_ON_ONCE(1);
+ return 0;
+
+ case ODEBUG_STATE_ACTIVE:
+ WARN_ON(1);
+
+ default:
+ return 0;
+ }
+}
+
+/*
+ * fixup_free is called when:
+ * - an active object is freed
+ */
+static int work_fixup_free(void *addr, enum debug_obj_state state)
+{
+ struct work_struct *work = addr;
+
+ switch (state) {
+ case ODEBUG_STATE_ACTIVE:
+ cancel_work_sync(work);
+ debug_object_free(work, &work_debug_descr);
+ return 1;
+ default:
+ return 0;
+ }
+}
+
+static struct debug_obj_descr work_debug_descr = {
+ .name = "work_struct",
+ .fixup_init = work_fixup_init,
+ .fixup_activate = work_fixup_activate,
+ .fixup_free = work_fixup_free,
+};
+
+static inline void debug_work_activate(struct work_struct *work)
+{
+ debug_object_activate(work, &work_debug_descr);
+}
+
+static inline void debug_work_deactivate(struct work_struct *work)
+{
+ debug_object_deactivate(work, &work_debug_descr);
+}
+
+void __init_work(struct work_struct *work, int onstack)
+{
+ if (onstack)
+ debug_object_init_on_stack(work, &work_debug_descr);
+ else
+ debug_object_init(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(__init_work);
+
+void destroy_work_on_stack(struct work_struct *work)
+{
+ debug_object_free(work, &work_debug_descr);
+}
+EXPORT_SYMBOL_GPL(destroy_work_on_stack);
+
+#else
+static inline void debug_work_activate(struct work_struct *work) { }
+static inline void debug_work_deactivate(struct work_struct *work) { }
+#endif
+
/* Serializes the accesses to the list of workqueues. */
static DEFINE_SPINLOCK(workqueue_lock);
static LIST_HEAD(workqueues);
@@ -145,6 +255,7 @@ static void __queue_work(struct cpu_workqueue_struct *cwq,
{
unsigned long flags;
+ debug_work_activate(work);
spin_lock_irqsave(&cwq->lock, flags);
insert_work(cwq, work, &cwq->worklist);
spin_unlock_irqrestore(&cwq->lock, flags);
@@ -280,6 +391,7 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
struct lockdep_map lockdep_map = work->lockdep_map;
#endif
trace_workqueue_execution(cwq->thread, work);
+ debug_work_deactivate(work);
cwq->current_work = work;
list_del_init(cwq->worklist.next);
spin_unlock_irq(&cwq->lock);
@@ -350,11 +462,18 @@ static void wq_barrier_func(struct work_struct *work)
static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
struct wq_barrier *barr, struct list_head *head)
{
- INIT_WORK(&barr->work, wq_barrier_func);
+ /*
+ * debugobject calls are safe here even with cwq->lock locked
+ * as we know for sure that this will not trigger any of the
+ * checks and call back into the fixup functions where we
+ * might deadlock.
+ */
+ INIT_WORK_ON_STACK(&barr->work, wq_barrier_func);
__set_bit(WORK_STRUCT_PENDING, work_data_bits(&barr->work));
init_completion(&barr->done);
+ debug_work_activate(&barr->work);
insert_work(cwq, &barr->work, head);
}
@@ -372,8 +491,10 @@ static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
}
spin_unlock_irq(&cwq->lock);
- if (active)
+ if (active) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
return active;
}
@@ -451,6 +572,7 @@ out:
return 0;
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
return 1;
}
EXPORT_SYMBOL_GPL(flush_work);
@@ -485,6 +607,7 @@ static int try_to_grab_pending(struct work_struct *work)
*/
smp_rmb();
if (cwq == get_wq_data(work)) {
+ debug_work_deactivate(work);
list_del_init(&work->entry);
ret = 1;
}
@@ -507,8 +630,10 @@ static void wait_on_cpu_work(struct cpu_workqueue_struct *cwq,
}
spin_unlock_irq(&cwq->lock);
- if (unlikely(running))
+ if (unlikely(running)) {
wait_for_completion(&barr.done);
+ destroy_work_on_stack(&barr.work);
+ }
}
static void wait_on_work(struct work_struct *work)
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-23 01:52:30 +0000