lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090813152356.GC16682@hmsreliant.think-freely.org>
Date:	Thu, 13 Aug 2009 11:23:56 -0400
From:	Neil Horman <nhorman@...driver.com>
To:	netdev@...r.kernel.org
Cc:	davem@...emloft.net, rostedt@...dmis.org
Subject: Re: [PATCH 3/3] net: skb ftracer - Add actual ftrace code to
	kernel (v3)

skb allocation / consumption correlator

Add ftracer module to kernel to print out a list that correlates a process id,
an skb it read, and the numa nodes on wich the process was running when it was
read along with the numa node the skbuff was allocated on.

Signed-off-by: Neil Horman <nhorman@...driver.com>


 Makefile            |    1 
 trace.h             |   19 ++++++
 trace_skb_sources.c |  154 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 174 insertions(+)

diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 844164d..ee5e5b1 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -49,6 +49,7 @@ obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
 ifeq ($(CONFIG_BLOCK),y)
 obj-$(CONFIG_EVENT_TRACING) += blktrace.o
 endif
+obj-$(CONFIG_SKB_SOURCES_TRACER) += trace_skb_sources.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events.o
 obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 8b9f4f6..8a6281b 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -11,6 +11,7 @@
 #include <trace/boot.h>
 #include <linux/kmemtrace.h>
 #include <trace/power.h>
+#include <trace/events/skb.h>
 
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
@@ -40,6 +41,7 @@ enum trace_type {
 	TRACE_KMEM_FREE,
 	TRACE_POWER,
 	TRACE_BLK,
+	TRACE_SKB_SOURCE,
 
 	__TRACE_LAST_TYPE,
 };
@@ -171,6 +173,21 @@ struct trace_power {
 	struct power_trace	state_data;
 };
 
+struct skb_record {
+	pid_t pid;		/* pid of the copying process */
+	int anid;		/* node where skb was allocated */
+	int cnid;		/* node to which skb was copied in userspace */
+	char ifname[IFNAMSIZ];	/* Name of the receiving interface */
+	int rx_queue;		/* The rx queue the skb was received on */
+	int ccpu;		/* Cpu the application got this frame from */
+	int len;		/* length of the data copied */
+};
+
+struct trace_skb_event {
+	struct trace_entry	ent;
+	struct skb_record	event_data;
+};
+
 enum kmemtrace_type_id {
 	KMEMTRACE_TYPE_KMALLOC = 0,	/* kmalloc() or kfree(). */
 	KMEMTRACE_TYPE_CACHE,		/* kmem_cache_*(). */
@@ -323,6 +340,8 @@ extern void __ftrace_bad_type(void);
 			  TRACE_SYSCALL_ENTER);				\
 		IF_ASSIGN(var, ent, struct syscall_trace_exit,		\
 			  TRACE_SYSCALL_EXIT);				\
+		IF_ASSIGN(var, ent, struct trace_skb_event,		\
+			  TRACE_SKB_SOURCE);				\
 		__ftrace_bad_type();					\
 	} while (0)
 
diff --git a/kernel/trace/trace_skb_sources.c b/kernel/trace/trace_skb_sources.c
new file mode 100644
index 0000000..4ba3671
--- /dev/null
+++ b/kernel/trace/trace_skb_sources.c
@@ -0,0 +1,154 @@
+/*
+ * ring buffer based tracer for analyzing per-socket skb sources
+ *
+ * Neil Horman <nhorman@...driver.com> 
+ * Copyright (C) 2009
+ *
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <trace/events/skb.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/netdevice.h>
+#include <net/sock.h>
+
+#include "trace.h"
+#include "trace_output.h"
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(skb_copy_datagram_iovec);
+
+static struct trace_array *skb_trace;
+static int __read_mostly trace_skb_source_enabled;
+
+static void probe_skb_dequeue(const struct sk_buff *skb, int len)
+{
+	struct ring_buffer_event *event;
+	struct trace_skb_event *entry;
+	struct trace_array *tr = skb_trace;
+	struct net_device *dev;
+
+	if (!trace_skb_source_enabled)
+		return;
+
+	if (in_interrupt())
+		return;
+
+	event = trace_buffer_lock_reserve(tr, TRACE_SKB_SOURCE,
+					  sizeof(*entry), 0, 0);
+	if (!event)
+		return;
+	entry = ring_buffer_event_data(event);
+
+	entry->event_data.pid = current->pid;
+	entry->event_data.anid = page_to_nid(virt_to_page(skb->data));
+	entry->event_data.cnid = cpu_to_node(smp_processor_id());
+	entry->event_data.len = len;
+	entry->event_data.rx_queue = skb->queue_mapping;
+	entry->event_data.ccpu = smp_processor_id();
+
+	dev = dev_get_by_index(sock_net(skb->sk), skb->iif);
+	if (dev) {
+		memcpy(entry->event_data.ifname, dev->name, IFNAMSIZ);
+		dev_put(dev);
+	} else {
+		strcpy(entry->event_data.ifname, "Unknown");
+	}
+
+	trace_buffer_unlock_commit(tr, event, 0, 0);
+}
+
+static int tracing_skb_source_register(void)
+{
+	int ret;
+
+	ret = register_trace_skb_copy_datagram_iovec(probe_skb_dequeue);
+	if (ret)
+		pr_info("skb source trace: Couldn't activate dequeue tracepoint");
+	
+	return ret;
+}
+
+static void start_skb_source_trace(struct trace_array *tr)
+{
+	trace_skb_source_enabled = 1;
+}
+
+static void stop_skb_source_trace(struct trace_array *tr)
+{
+	trace_skb_source_enabled = 0;
+}
+
+static void skb_source_trace_reset(struct trace_array *tr)
+{
+	trace_skb_source_enabled = 0;
+	unregister_trace_skb_copy_datagram_iovec(probe_skb_dequeue);
+}
+
+
+static int skb_source_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	skb_trace = tr;
+
+	trace_skb_source_enabled = 1;
+	tracing_skb_source_register();
+
+	for_each_cpu(cpu, cpu_possible_mask)
+		tracing_reset(tr, cpu);
+	return 0;
+}
+
+static enum print_line_t skb_source_print_line(struct trace_iterator *iter)
+{
+	int ret = 0;
+	struct trace_entry *entry = iter->ent;
+	struct trace_skb_event *event;
+	struct skb_record *record;
+	struct trace_seq *s = &iter->seq;
+
+	trace_assign_type(event, entry);
+	record = &event->event_data;
+	if (entry->type != TRACE_SKB_SOURCE)
+		return TRACE_TYPE_UNHANDLED;
+
+	ret = trace_seq_printf(s, "	%d	%d	%d	%s	%d	%d	%d\n",
+			record->pid,
+			record->anid,
+			record->cnid,
+			record->ifname,
+			record->rx_queue,
+			record->ccpu,
+			record->len);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+
+	return TRACE_TYPE_HANDLED;
+}
+
+static void skb_source_print_header(struct seq_file *s)
+{
+	seq_puts(s, "#	PID	ANID	CNID	IFC	RXQ	CCPU	LEN\n");
+	seq_puts(s, "#	 |	 |	 |	 |	 |	 |	 |\n");
+}
+
+static struct tracer skb_source_tracer __read_mostly =
+{
+	.name		= "skb_sources",
+	.init		= skb_source_trace_init,
+	.start		= start_skb_source_trace,
+	.stop		= stop_skb_source_trace,
+	.reset		= skb_source_trace_reset,
+	.print_line	= skb_source_print_line,
+	.print_header	= skb_source_print_header,
+};
+
+static int init_skb_source_trace(void)
+{
+	return register_tracer(&skb_source_tracer);
+}
+device_initcall(init_skb_source_trace);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ