[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20080428215534.079c378e@daedalus.pq.iki.fi>
Date: Mon, 28 Apr 2008 21:55:34 +0300
From: Pekka Paalanen <pq@....fi>
To: linux-kernel@...r.kernel.org
Cc: Pekka Paalanen <pq@....fi>, Ingo Molnar <mingo@...e.hu>,
Christoph Hellwig <hch@...radead.org>,
Arjan van de Ven <arjan@...radead.org>,
Pavel Roskin <proski@....org>,
Steven Rostedt <rostedt@...dmis.org>,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Andrew Morton <akpm@...ux-foundation.org>
Subject: [RFC 2/3] mmiotrace full patch, preview 3
On Mon, 28 Apr 2008 21:45:04 +0300
Pekka Paalanen <pq@....fi> wrote:
> Hi all,
>
> this is the third full mmiotrace patch set for review (a bit late, sorry).
> These patches do not apply to any git tree that I know of, but after Ingo
> pushes a new version of his sched-devel/latest tree, these patches should
> be subtractable from there.
...
> This first patch adds the bulk of the new code, only introducing new files.
> The second patch establishes the interfaces to the ftrace framework, and
> the third patch hooks everything up into the Kbuild system, page fault
> handler, and ioremap functions.
kernel/trace/Makefile | 1 +
kernel/trace/trace.c | 66 +++++++---
kernel/trace/trace.h | 29 ++++
kernel/trace/trace_mmiotrace.c | 291 ++++++++++++++++++++++++++++++++++++++++
4 files changed, 370 insertions(+), 17 deletions(-)
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 7aec123..71d17de 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -19,5 +19,6 @@ obj-$(CONFIG_FTRACE) += trace_functions.o
obj-$(CONFIG_IRQSOFF_TRACER) += trace_irqsoff.o
obj-$(CONFIG_PREEMPT_TRACER) += trace_irqsoff.o
obj-$(CONFIG_SCHED_TRACER) += trace_sched_wakeup.o
+obj-$(CONFIG_MMIOTRACE) += trace_mmiotrace.o
libftrace-y := ftrace.o
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index cbe476f..06c85b3 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -54,7 +54,7 @@ static int tracing_disabled = 1;
static unsigned long tracing_pages_allocated;
-static long
+long
ns2usecs(cycle_t nsec)
{
nsec += 500;
@@ -173,18 +173,6 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
return nsecs / 1000;
}
-enum trace_type {
- __TRACE_FIRST_TYPE = 0,
-
- TRACE_FN,
- TRACE_CTX,
- TRACE_WAKE,
- TRACE_STACK,
- TRACE_SPECIAL,
-
- __TRACE_LAST_TYPE
-};
-
/*
* trace_flag_type is an enumeration that holds different
* states when a trace occurs. These are:
@@ -313,7 +301,7 @@ void *head_page(struct trace_array_cpu *data)
* buffer (@s). Then the output may be either used by
* the sequencer or pulled into another buffer.
*/
-static int
+int
trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
{
int len = (PAGE_SIZE - 1) - s->len;
@@ -328,7 +316,7 @@ 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)
return 0;
s->len += ret;
@@ -809,7 +797,7 @@ tracing_generic_entry_update(struct trace_entry *entry, unsigned long flags)
pc = preempt_count();
entry->preempt_count = pc & 0xff;
- entry->pid = tsk->pid;
+ entry->pid = (tsk) ? tsk->pid : 0;
entry->t = ftrace_now(raw_smp_processor_id());
entry->flags = (irqs_disabled_flags(flags) ? TRACE_FLAG_IRQS_OFF : 0) |
((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) |
@@ -843,6 +831,48 @@ ftrace(struct trace_array *tr, struct trace_array_cpu *data,
trace_function(tr, data, ip, parent_ip, flags);
}
+#ifdef CONFIG_MMIOTRACE
+void __trace_mmiotrace_rw(struct trace_array *tr, struct trace_array_cpu *data,
+ struct mmiotrace_rw *rw)
+{
+ 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_MMIO_RW;
+ entry->mmiorw = *rw;
+
+ __raw_spin_unlock(&data->lock);
+ raw_local_irq_restore(irq_flags);
+
+ trace_wake_up();
+}
+
+void __trace_mmiotrace_map(struct trace_array *tr, struct trace_array_cpu *data,
+ struct mmiotrace_map *map)
+{
+ 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_MMIO_MAP;
+ entry->mmiomap = *map;
+
+ __raw_spin_unlock(&data->lock);
+ raw_local_irq_restore(irq_flags);
+
+ trace_wake_up();
+}
+#endif
+
void __trace_stack(struct trace_array *tr,
struct trace_array_cpu *data,
unsigned long flags,
@@ -1714,6 +1744,9 @@ static int trace_empty(struct trace_iterator *iter)
static int print_trace_line(struct trace_iterator *iter)
{
+ if (iter->trace && iter->trace->print_line)
+ return iter->trace->print_line(iter);
+
if (trace_flags & TRACE_ITER_BIN)
return print_bin_fmt(iter);
@@ -2342,7 +2375,6 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
mutex_lock(&trace_types_lock);
iter->tr = &global_trace;
-
iter->trace = current_trace;
filp->private_data = iter;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f2ca481..3e15c23 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -5,6 +5,21 @@
#include <asm/atomic.h>
#include <linux/sched.h>
#include <linux/clocksource.h>
+#include <linux/mmiotrace.h>
+
+enum trace_type {
+ __TRACE_FIRST_TYPE = 0,
+
+ TRACE_FN,
+ TRACE_CTX,
+ TRACE_WAKE,
+ TRACE_STACK,
+ TRACE_SPECIAL,
+ TRACE_MMIO_RW,
+ TRACE_MMIO_MAP,
+
+ __TRACE_LAST_TYPE
+};
/*
* Function trace entry - function address and parent function addres:
@@ -63,6 +78,8 @@ struct trace_entry {
struct ctx_switch_entry ctx;
struct special_entry special;
struct stack_entry stack;
+ struct mmiotrace_rw mmiorw;
+ struct mmiotrace_map mmiomap;
};
};
@@ -135,6 +152,7 @@ struct tracer {
int (*selftest)(struct tracer *trace,
struct trace_array *tr);
#endif
+ int (*print_line)(struct trace_iterator *iter);
struct tracer *next;
int print_max;
};
@@ -244,6 +262,15 @@ extern unsigned long ftrace_update_tot_cnt;
extern int DYN_FTRACE_TEST_NAME(void);
#endif
+#ifdef CONFIG_MMIOTRACE
+extern void __trace_mmiotrace_rw(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ struct mmiotrace_rw *rw);
+extern void __trace_mmiotrace_map(struct trace_array *tr,
+ struct trace_array_cpu *data,
+ struct mmiotrace_map *map);
+#endif
+
#ifdef CONFIG_FTRACE_STARTUP_TEST
#ifdef CONFIG_FTRACE
extern int trace_selftest_startup_function(struct tracer *trace,
@@ -276,8 +303,10 @@ extern int trace_selftest_startup_sysprof(struct tracer *trace,
#endif /* CONFIG_FTRACE_STARTUP_TEST */
extern void *head_page(struct trace_array_cpu *data);
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...);
extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
size_t cnt);
+extern long ns2usecs(cycle_t nsec);
extern unsigned long trace_flags;
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
new file mode 100644
index 0000000..3c1dacd
--- /dev/null
+++ b/kernel/trace/trace_mmiotrace.c
@@ -0,0 +1,291 @@
+/*
+ * Memory mapped I/O tracing
+ *
+ * Copyright (C) 2008 Pekka Paalanen <pq@....fi>
+ */
+
+#define DEBUG 1
+
+#include <linux/kernel.h>
+#include <linux/mmiotrace.h>
+#include <linux/pci.h>
+
+#include "trace.h"
+
+struct header_iter {
+ struct pci_dev *dev;
+};
+
+static struct trace_array *mmio_trace_array;
+static bool overrun_detected;
+
+static void mmio_reset_data(struct trace_array *tr)
+{
+ int cpu;
+
+ overrun_detected = false;
+ tr->time_start = ftrace_now(tr->cpu);
+
+ for_each_online_cpu(cpu)
+ tracing_reset(tr->data[cpu]);
+}
+
+static void mmio_trace_init(struct trace_array *tr)
+{
+ pr_debug("in %s\n", __func__);
+ mmio_trace_array = tr;
+ if (tr->ctrl) {
+ mmio_reset_data(tr);
+ enable_mmiotrace();
+ }
+}
+
+static void mmio_trace_reset(struct trace_array *tr)
+{
+ pr_debug("in %s\n", __func__);
+ if (tr->ctrl)
+ disable_mmiotrace();
+ mmio_reset_data(tr);
+ mmio_trace_array = NULL;
+}
+
+static void mmio_trace_ctrl_update(struct trace_array *tr)
+{
+ pr_debug("in %s\n", __func__);
+ if (tr->ctrl) {
+ mmio_reset_data(tr);
+ enable_mmiotrace();
+ } else {
+ disable_mmiotrace();
+ }
+}
+
+static int mmio_print_pcidev(struct trace_seq *s, const struct pci_dev *dev)
+{
+ int ret = 0;
+ int i;
+ resource_size_t start, end;
+ const struct pci_driver *drv = pci_dev_driver(dev);
+
+ /* XXX: incomplete checks for trace_seq_printf() return value */
+ ret += trace_seq_printf(s, "PCIDEV %02x%02x %04x%04x %x",
+ dev->bus->number, dev->devfn,
+ dev->vendor, dev->device, dev->irq);
+ /*
+ * XXX: is pci_resource_to_user() appropriate, since we are
+ * supposed to interpret the __ioremap() phys_addr argument based on
+ * these printed values?
+ */
+ for (i = 0; i < 7; i++) {
+ pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+ ret += trace_seq_printf(s, " %llx",
+ (unsigned long long)(start |
+ (dev->resource[i].flags & PCI_REGION_FLAG_MASK)));
+ }
+ for (i = 0; i < 7; i++) {
+ pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+ ret += trace_seq_printf(s, " %llx",
+ dev->resource[i].start < dev->resource[i].end ?
+ (unsigned long long)(end - start) + 1 : 0);
+ }
+ if (drv)
+ ret += trace_seq_printf(s, " %s\n", drv->name);
+ else
+ ret += trace_seq_printf(s, " \n");
+ return ret;
+}
+
+static void destroy_header_iter(struct header_iter *hiter)
+{
+ if (!hiter)
+ return;
+ pci_dev_put(hiter->dev);
+ kfree(hiter);
+}
+
+static void mmio_pipe_open(struct trace_iterator *iter)
+{
+ struct header_iter *hiter;
+ struct trace_seq *s = &iter->seq;
+
+ trace_seq_printf(s, "VERSION 20070824\n");
+
+ hiter = kzalloc(sizeof(*hiter), GFP_KERNEL);
+ if (!hiter)
+ return;
+
+ hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, NULL);
+ iter->private = hiter;
+}
+
+/* XXX: This is not called when the pipe is closed! */
+static void mmio_close(struct trace_iterator *iter)
+{
+ struct header_iter *hiter = iter->private;
+ destroy_header_iter(hiter);
+ iter->private = NULL;
+}
+
+static unsigned long count_overruns(struct trace_iterator *iter)
+{
+ int cpu;
+ unsigned long cnt = 0;
+ for_each_online_cpu(cpu) {
+ cnt += iter->overrun[cpu];
+ iter->overrun[cpu] = 0;
+ }
+ return cnt;
+}
+
+static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp,
+ char __user *ubuf, size_t cnt, loff_t *ppos)
+{
+ ssize_t ret;
+ struct header_iter *hiter = iter->private;
+ struct trace_seq *s = &iter->seq;
+ unsigned long n;
+
+ n = count_overruns(iter);
+ if (n) {
+ /* XXX: This is later than where events were lost. */
+ trace_seq_printf(s, "MARK 0.000000 Lost %lu events.\n", n);
+ if (!overrun_detected)
+ pr_warning("mmiotrace has lost events.\n");
+ overrun_detected = true;
+ goto print_out;
+ }
+
+ if (!hiter)
+ return 0;
+
+ mmio_print_pcidev(s, hiter->dev);
+ hiter->dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, hiter->dev);
+
+ if (!hiter->dev) {
+ destroy_header_iter(hiter);
+ iter->private = NULL;
+ }
+
+print_out:
+ ret = trace_seq_to_user(s, ubuf, cnt);
+ return (ret == -EBUSY) ? 0 : ret;
+}
+
+static int mmio_print_rw(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct mmiotrace_rw *rw = &entry->mmiorw;
+ struct trace_seq *s = &iter->seq;
+ unsigned long long t = ns2usecs(entry->t);
+ unsigned long usec_rem = do_div(t, 1000000ULL);
+ unsigned secs = (unsigned long)t;
+ int ret = 1;
+
+ switch (entry->mmiorw.opcode) {
+ case MMIO_READ:
+ ret = trace_seq_printf(s,
+ "R %d %lu.%06lu %d 0x%lx 0x%lx 0x%lx %d\n",
+ rw->width, secs, usec_rem, rw->map_id, rw->phys,
+ rw->value, rw->pc, 0);
+ break;
+ case MMIO_WRITE:
+ ret = trace_seq_printf(s,
+ "W %d %lu.%06lu %d 0x%lx 0x%lx 0x%lx %d\n",
+ rw->width, secs, usec_rem, rw->map_id, rw->phys,
+ rw->value, rw->pc, 0);
+ break;
+ case MMIO_UNKNOWN_OP:
+ ret = trace_seq_printf(s,
+ "UNKNOWN %lu.%06lu %d 0x%lx %02x,%02x,%02x 0x%lx %d\n",
+ secs, usec_rem, rw->map_id, rw->phys,
+ (rw->value >> 16) & 0xff, (rw->value >> 8) & 0xff,
+ (rw->value >> 0) & 0xff, rw->pc, 0);
+ break;
+ default:
+ ret = trace_seq_printf(s, "rw what?\n");
+ break;
+ }
+ if (ret)
+ return 1;
+ return 0;
+}
+
+static int mmio_print_map(struct trace_iterator *iter)
+{
+ struct trace_entry *entry = iter->ent;
+ struct mmiotrace_map *m = &entry->mmiomap;
+ struct trace_seq *s = &iter->seq;
+ unsigned long long t = ns2usecs(entry->t);
+ unsigned long usec_rem = do_div(t, 1000000ULL);
+ unsigned secs = (unsigned long)t;
+ int ret = 1;
+
+ switch (entry->mmiorw.opcode) {
+ case MMIO_PROBE:
+ ret = trace_seq_printf(s,
+ "MAP %lu.%06lu %d 0x%lx 0x%lx 0x%lx 0x%lx %d\n",
+ secs, usec_rem, m->map_id, m->phys, m->virt, m->len,
+ 0UL, 0);
+ break;
+ case MMIO_UNPROBE:
+ ret = trace_seq_printf(s,
+ "UNMAP %lu.%06lu %d 0x%lx %d\n",
+ secs, usec_rem, m->map_id, 0UL, 0);
+ break;
+ default:
+ ret = trace_seq_printf(s, "map what?\n");
+ break;
+ }
+ if (ret)
+ return 1;
+ return 0;
+}
+
+/* return 0 to abort printing without consuming current entry in pipe mode */
+static int mmio_print_line(struct trace_iterator *iter)
+{
+ switch (iter->ent->type) {
+ case TRACE_MMIO_RW:
+ return mmio_print_rw(iter);
+ case TRACE_MMIO_MAP:
+ return mmio_print_map(iter);
+ default:
+ return 1; /* ignore unknown entries */
+ }
+}
+
+static struct tracer mmio_tracer __read_mostly =
+{
+ .name = "mmiotrace",
+ .init = mmio_trace_init,
+ .reset = mmio_trace_reset,
+ .pipe_open = mmio_pipe_open,
+ .close = mmio_close,
+ .read = mmio_read,
+ .ctrl_update = mmio_trace_ctrl_update,
+ .print_line = mmio_print_line,
+};
+
+__init static int init_mmio_trace(void)
+{
+ return register_tracer(&mmio_tracer);
+}
+device_initcall(init_mmio_trace);
+
+void mmio_trace_rw(struct mmiotrace_rw *rw)
+{
+ struct trace_array *tr = mmio_trace_array;
+ struct trace_array_cpu *data = tr->data[smp_processor_id()];
+ __trace_mmiotrace_rw(tr, data, rw);
+}
+
+void mmio_trace_mapping(struct mmiotrace_map *map)
+{
+ struct trace_array *tr = mmio_trace_array;
+ struct trace_array_cpu *data;
+
+ preempt_disable();
+ data = tr->data[smp_processor_id()];
+ __trace_mmiotrace_map(tr, data, map);
+ preempt_enable();
+}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists