#include <linux/poll.h>
#include <linux/gfp.h>
#include <linux/fs.h>
+#include <linux/kprobes.h>
+#include <linux/writeback.h>
#include <linux/stacktrace.h>
#define for_each_tracing_cpu(cpu) \
for_each_cpu_mask(cpu, tracing_buffer_mask)
-/* dummy trace to disable tracing */
-static struct tracer no_tracer __read_mostly = {
- .name = "none",
-};
-
static int trace_alloc_page(void);
static int trace_free_page(void);
static int tracing_disabled = 1;
+static unsigned long tracing_pages_allocated;
+
long
ns2usecs(cycle_t nsec)
{
/* trace_flags holds iter_ctrl options */
unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
+static notrace void no_trace_init(struct trace_array *tr)
+{
+ int cpu;
+
+ if(tr->ctrl)
+ for_each_online_cpu(cpu)
+ tracing_reset(tr->data[cpu]);
+ tracer_enabled = 0;
+}
+
+/* dummy trace to disable tracing */
+static struct tracer no_tracer __read_mostly = {
+ .name = "none",
+ .init = no_trace_init
+};
+
+
/**
* trace_wake_up - wake up tasks waiting for trace input
*
tracing_record_cmdline(current);
}
+#define CHECK_COND(cond) \
+ if (unlikely(cond)) { \
+ tracing_disabled = 1; \
+ WARN_ON(1); \
+ return -1; \
+ }
+
/**
* check_pages - integrity check of trace buffers
*
* As a safty measure we check to make sure the data pages have not
- * been corrupted. TODO: configure to disable this because it adds
- * a bit of overhead.
+ * been corrupted.
*/
-void check_pages(struct trace_array_cpu *data)
+int check_pages(struct trace_array_cpu *data)
{
struct page *page, *tmp;
- BUG_ON(data->trace_pages.next->prev != &data->trace_pages);
- BUG_ON(data->trace_pages.prev->next != &data->trace_pages);
+ CHECK_COND(data->trace_pages.next->prev != &data->trace_pages);
+ CHECK_COND(data->trace_pages.prev->next != &data->trace_pages);
list_for_each_entry_safe(page, tmp, &data->trace_pages, lru) {
- BUG_ON(page->lru.next->prev != &page->lru);
- BUG_ON(page->lru.prev->next != &page->lru);
+ CHECK_COND(page->lru.next->prev != &page->lru);
+ CHECK_COND(page->lru.prev->next != &page->lru);
}
+
+ return 0;
}
/**
{
struct page *page;
- check_pages(data);
if (list_empty(&data->trace_pages))
return NULL;
trace_seq_reset(struct trace_seq *s)
{
s->len = 0;
+ s->readpos = 0;
+}
+
+ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf, size_t cnt)
+{
+ int len;
+ int ret;
+
+ if (s->len <= s->readpos)
+ return -EBUSY;
+
+ len = s->len - s->readpos;
+ if (cnt > len)
+ cnt = len;
+ ret = copy_to_user(ubuf, s->buffer + s->readpos, cnt);
+ if (ret)
+ return -EFAULT;
+
+ s->readpos += len;
+ return cnt;
}
static void
void tracing_reset(struct trace_array_cpu *data)
{
data->trace_idx = 0;
+ data->overrun = 0;
data->trace_head = data->trace_tail = head_page(data);
data->trace_head_idx = 0;
data->trace_tail_idx = 0;
static char saved_cmdlines[SAVED_CMDLINES][TASK_COMM_LEN];
static int cmdline_idx;
static DEFINE_SPINLOCK(trace_cmdline_lock);
-atomic_t trace_record_cmdline_disabled;
+
+/* temporary disable recording */
+atomic_t trace_record_cmdline_disabled __read_mostly;
static void trace_init_cmdlines(void)
{
if (data->trace_head == data->trace_tail &&
idx_next == data->trace_tail_idx) {
/* overrun */
+ data->overrun++;
data->trace_tail_idx++;
if (data->trace_tail_idx >= ENTRIES_PER_PAGE) {
data->trace_tail =
trace_function(tr, data, ip, parent_ip, flags);
}
-void
-__trace_special(void *__tr, void *__data,
- unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
- struct trace_array_cpu *data = __data;
- struct trace_array *tr = __tr;
- struct trace_entry *entry;
- unsigned long irq_flags;
-
- raw_local_irq_save(irq_flags);
- __raw_spin_lock(&data->lock);
- entry = tracing_get_trace_entry(tr, data);
- tracing_generic_entry_update(entry, 0);
- entry->type = TRACE_SPECIAL;
- entry->special.arg1 = arg1;
- entry->special.arg2 = arg2;
- entry->special.arg3 = arg3;
- __raw_spin_unlock(&data->lock);
- raw_local_irq_restore(irq_flags);
-
- trace_wake_up();
-}
-
void __trace_stack(struct trace_array *tr,
struct trace_array_cpu *data,
unsigned long flags,
save_stack_trace(&trace);
}
+void
+__trace_special(void *__tr, void *__data,
+ unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+ struct trace_array_cpu *data = __data;
+ struct trace_array *tr = __tr;
+ struct trace_entry *entry;
+ unsigned long irq_flags;
+
+ raw_local_irq_save(irq_flags);
+ __raw_spin_lock(&data->lock);
+ entry = tracing_get_trace_entry(tr, data);
+ tracing_generic_entry_update(entry, 0);
+ entry->type = TRACE_SPECIAL;
+ entry->special.arg1 = arg1;
+ entry->special.arg2 = arg2;
+ entry->special.arg3 = arg3;
+ __trace_stack(tr, data, irq_flags, 4);
+ __raw_spin_unlock(&data->lock);
+ raw_local_irq_restore(irq_flags);
+
+ trace_wake_up();
+}
+
void
tracing_sched_switch_trace(struct trace_array *tr,
struct trace_array_cpu *data,
entry->ctx.next_pid = next->pid;
entry->ctx.next_prio = next->prio;
entry->ctx.next_state = next->state;
- __trace_stack(tr, data, flags, 4);
+ __trace_stack(tr, data, flags, 5);
__raw_spin_unlock(&data->lock);
raw_local_irq_restore(irq_flags);
}
entry->ctx.next_pid = wakee->pid;
entry->ctx.next_prio = wakee->prio;
entry->ctx.next_state = wakee->state;
- __trace_stack(tr, data, flags, 5);
+ __trace_stack(tr, data, flags, 6);
__raw_spin_unlock(&data->lock);
raw_local_irq_restore(irq_flags);
trace_wake_up();
}
+void
+ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+ struct trace_array *tr = &global_trace;
+ struct trace_array_cpu *data;
+ unsigned long flags;
+ long disabled;
+ int cpu;
+
+ if (tracing_disabled || current_trace == &no_tracer || !tr->ctrl)
+ return;
+
+ local_irq_save(flags);
+ cpu = raw_smp_processor_id();
+ data = tr->data[cpu];
+ disabled = atomic_inc_return(&data->disabled);
+
+ if (likely(disabled == 1))
+ __trace_special(tr, data, arg1, arg2, arg3);
+
+ atomic_dec(&data->disabled);
+ local_irq_restore(flags);
+}
+
#ifdef CONFIG_FTRACE
static void
function_trace_call(unsigned long ip, unsigned long parent_ip)
if (unlikely(!tracer_enabled))
return;
+ if (skip_trace(ip))
+ return;
+
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = tr->data[cpu];
mutex_unlock(&trace_types_lock);
}
+#define KRETPROBE_MSG "[unknown/kretprobe'd]"
+
+#ifdef CONFIG_KRETPROBES
+static inline int kretprobed(unsigned long addr)
+{
+ return addr == (unsigned long)kretprobe_trampoline;
+}
+#else
+static inline int kretprobed(unsigned long addr)
+{
+ return 0;
+}
+#endif /* CONFIG_KRETPROBES */
+
static int
seq_print_sym_short(struct trace_seq *s, const char *fmt, unsigned long address)
{
case TRACE_FN:
seq_print_ip_sym(s, entry->fn.ip, sym_flags);
trace_seq_puts(s, " (");
- seq_print_ip_sym(s, entry->fn.parent_ip, sym_flags);
+ if (kretprobed(entry->fn.parent_ip))
+ trace_seq_puts(s, KRETPROBE_MSG);
+ else
+ seq_print_ip_sym(s, entry->fn.parent_ip, sym_flags);
trace_seq_puts(s, ")\n");
break;
case TRACE_CTX:
ret = trace_seq_printf(s, " <-");
if (!ret)
return 0;
- ret = seq_print_ip_sym(s, entry->fn.parent_ip,
- sym_flags);
+ if (kretprobed(entry->fn.parent_ip))
+ ret = trace_seq_puts(s, KRETPROBE_MSG);
+ else
+ ret = seq_print_ip_sym(s, entry->fn.parent_ip,
+ sym_flags);
if (!ret)
return 0;
}
if (!iter)
return -ENOMEM;
+ mutex_lock(&trace_types_lock);
iter->tr = &global_trace;
iter->trace = current_trace;
-
filp->private_data = iter;
+ if (iter->trace->pipe_open)
+ iter->trace->pipe_open(iter);
+ mutex_unlock(&trace_types_lock);
+
return 0;
}
{
struct trace_iterator *iter = filp->private_data;
struct trace_array_cpu *data;
- struct trace_array *tr = iter->tr;
- struct tracer *tracer = iter->trace;
static cpumask_t mask;
- static int start;
unsigned long flags;
#ifdef CONFIG_FTRACE
int ftrace_save;
#endif
- int read = 0;
int cpu;
- int len;
- int ret;
+ ssize_t sret;
/* return any leftover data */
- if (iter->seq.len > start) {
- len = iter->seq.len - start;
- if (cnt > len)
- cnt = len;
- ret = copy_to_user(ubuf, iter->seq.buffer + start, cnt);
- if (ret)
- cnt = -EFAULT;
+ sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ if (sret != -EBUSY)
+ return sret;
+ sret = 0;
- start += len;
+ trace_seq_reset(&iter->seq);
- return cnt;
+ mutex_lock(&trace_types_lock);
+ if (iter->trace->read) {
+ sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
+ if (sret)
+ goto out;
}
- trace_seq_reset(&iter->seq);
- start = 0;
-
while (trace_empty(iter)) {
- if ((filp->f_flags & O_NONBLOCK))
- return -EAGAIN;
+ if ((filp->f_flags & O_NONBLOCK)) {
+ sret = -EAGAIN;
+ goto out;
+ }
/*
* This is a make-shift waitqueue. The reason we don't use
set_current_state(TASK_INTERRUPTIBLE);
iter->tr->waiter = current;
- /* sleep for one second, and try again. */
- schedule_timeout(HZ);
+ mutex_unlock(&trace_types_lock);
+
+ /* sleep for 100 msecs, and try again. */
+ schedule_timeout(HZ/10);
+
+ mutex_lock(&trace_types_lock);
iter->tr->waiter = NULL;
- if (signal_pending(current))
- return -EINTR;
+ if (signal_pending(current)) {
+ sret = -EINTR;
+ goto out;
+ }
if (iter->trace != current_trace)
- return 0;
+ goto out;
/*
* We block until we read something and tracing is disabled.
/* stop when tracing is finished */
if (trace_empty(iter))
- return 0;
+ goto out;
if (cnt >= PAGE_SIZE)
cnt = PAGE_SIZE - 1;
- memset(iter, 0, sizeof(*iter));
- iter->tr = tr;
- iter->trace = tracer;
+ /* reset all but tr, trace, and overruns */
+ memset(&iter->seq, 0,
+ sizeof(struct trace_iterator) -
+ offsetof(struct trace_iterator, seq));
iter->pos = -1;
/*
for_each_cpu_mask(cpu, mask) {
data = iter->tr->data[cpu];
__raw_spin_lock(&data->lock);
+
+ if (data->overrun > iter->last_overrun[cpu])
+ iter->overrun[cpu] +=
+ data->overrun - iter->last_overrun[cpu];
+ iter->last_overrun[cpu] = data->overrun;
}
while (find_next_entry_inc(iter) != NULL) {
+ int ret;
int len = iter->seq.len;
ret = print_trace_line(iter);
local_irq_restore(flags);
/* Now copy what we have to the user */
- read = iter->seq.len;
- if (read > cnt)
- read = cnt;
-
- ret = copy_to_user(ubuf, iter->seq.buffer, read);
-
- if (read < iter->seq.len)
- start = read;
- else
+ sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+ if (iter->seq.readpos >= iter->seq.len)
trace_seq_reset(&iter->seq);
+ if (sret == -EBUSY)
+ sret = 0;
- if (ret)
- read = -EFAULT;
+out:
+ mutex_unlock(&trace_types_lock);
- return read;
+ return sret;
}
static ssize_t
{
unsigned long val;
char buf[64];
- int ret;
+ int i, ret;
if (cnt >= sizeof(buf))
return -EINVAL;
}
if (val > global_trace.entries) {
+ long pages_requested;
+ unsigned long freeable_pages;
+
+ /* make sure we have enough memory before mapping */
+ pages_requested =
+ (val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE;
+
+ /* account for each buffer (and max_tr) */
+ pages_requested *= tracing_nr_buffers * 2;
+
+ /* Check for overflow */
+ if (pages_requested < 0) {
+ cnt = -ENOMEM;
+ goto out;
+ }
+
+ freeable_pages = determine_dirtyable_memory();
+
+ /* we only allow to request 1/4 of useable memory */
+ if (pages_requested >
+ ((freeable_pages + tracing_pages_allocated) / 4)) {
+ cnt = -ENOMEM;
+ goto out;
+ }
+
while (global_trace.entries < val) {
if (trace_alloc_page()) {
cnt = -ENOMEM;
goto out;
}
+ /* double check that we don't go over the known pages */
+ if (tracing_pages_allocated > pages_requested)
+ break;
}
+
} else {
/* include the number of entries in val (inc of page entries) */
while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))
trace_free_page();
}
+ /* check integrity */
+ for_each_tracing_cpu(i)
+ check_pages(global_trace.data[i]);
+
filp->f_pos += cnt;
+ /* If check pages failed, return ENOMEM */
+ if (tracing_disabled)
+ cnt = -ENOMEM;
out:
max_tr.entries = global_trace.entries;
mutex_unlock(&trace_types_lock);
struct page *page, *tmp;
LIST_HEAD(pages);
void *array;
+ unsigned pages_allocated = 0;
int i;
/* first allocate a page for each CPU */
goto free_pages;
}
+ pages_allocated++;
page = virt_to_page(array);
list_add(&page->lru, &pages);
"for trace buffer!\n");
goto free_pages;
}
+ pages_allocated++;
page = virt_to_page(array);
list_add(&page->lru, &pages);
#endif
SetPageLRU(page);
#endif
}
+ tracing_pages_allocated += pages_allocated;
global_trace.entries += ENTRIES_PER_PAGE;
return 0;
page = list_entry(p, struct page, lru);
ClearPageLRU(page);
list_del(&page->lru);
+ tracing_pages_allocated--;
+ tracing_pages_allocated--;
__free_page(page);
tracing_reset(data);
int ret = -ENOMEM;
int i;
- global_trace.ctrl = tracer_enabled;
-
/* TODO: make the number of buffers hot pluggable with CPUS */
tracing_nr_buffers = num_possible_cpus();
tracing_buffer_mask = cpu_possible_map;
}
max_tr.entries = global_trace.entries;
- pr_info("tracer: %d pages allocated for %ld",
- pages, trace_nr_entries);
- pr_info(" entries of %ld bytes\n", (long)TRACE_ENTRY_SIZE);
+ pr_info("tracer: %d pages allocated for %ld entries of %ld bytes\n",
+ pages, trace_nr_entries, (long)TRACE_ENTRY_SIZE);
pr_info(" actual entries %ld\n", global_trace.entries);
tracer_init_debugfs();
current_trace = &no_tracer;
/* All seems OK, enable tracing */
+ global_trace.ctrl = tracer_enabled;
tracing_disabled = 0;
return 0;
projects / linux-2.6 / blobdiff