[PATCH 3.4 08/32] connector: improved unaligned access error fix

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

3.4-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Chris Metcalf <cmetcalf@tilera.com>

[ Upstream commit 1ca1a4cf59ea343a1a70084fe7cc96f37f3cf5b1 ]

In af3e095a1fb4, Erik Jacobsen fixed one type of unaligned access
bug for ia64 by converting a 64-bit write to use put_unaligned().
Unfortunately, since gcc will convert a short memset() to a series
of appropriately-aligned stores, the problem is now visible again
on tilegx, where the memset that zeros out proc_event is converted
to three 64-bit stores, causing an unaligned access panic.

A better fix for the original problem is to ensure that proc_event
is aligned to 8 bytes here.  We can do that relatively easily by
arranging to start the struct cn_msg aligned to 8 bytes and then
offset by 4 bytes.  Doing so means that the immediately following
proc_event structure is then correctly aligned to 8 bytes.

The result is that the memset() stores are now aligned, and as an
added benefit, we can remove the put_unaligned() calls in the code.

Signed-off-by: Chris Metcalf <cmetcalf@tilera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/connector/cn_proc.c |   66 ++++++++++++++++++++++++++------------------
 1 file changed, 39 insertions(+), 27 deletions(-)

--- a/drivers/connector/cn_proc.c
+++ b/drivers/connector/cn_proc.c
@@ -31,11 +31,23 @@
 #include <linux/ptrace.h>
 #include <linux/atomic.h>
 
-#include <asm/unaligned.h>
-
 #include <linux/cn_proc.h>
 
-#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event))
+/*
+ * Size of a cn_msg followed by a proc_event structure.  Since the
+ * sizeof struct cn_msg is a multiple of 4 bytes, but not 8 bytes, we
+ * add one 4-byte word to the size here, and then start the actual
+ * cn_msg structure 4 bytes into the stack buffer.  The result is that
+ * the immediately following proc_event structure is aligned to 8 bytes.
+ */
+#define CN_PROC_MSG_SIZE (sizeof(struct cn_msg) + sizeof(struct proc_event) + 4)
+
+/* See comment above; we test our assumption about sizeof struct cn_msg here. */
+static inline struct cn_msg *buffer_to_cn_msg(__u8 *buffer)
+{
+	BUILD_BUG_ON(sizeof(struct cn_msg) != 20);
+	return (struct cn_msg *)(buffer + 4);
+}
 
 static atomic_t proc_event_num_listeners = ATOMIC_INIT(0);
 static struct cb_id cn_proc_event_id = { CN_IDX_PROC, CN_VAL_PROC };
@@ -55,19 +67,19 @@ void proc_fork_connector(struct task_str
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 	struct task_struct *parent;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg*)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event*)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_FORK;
 	rcu_read_lock();
 	parent = rcu_dereference(task->real_parent);
@@ -90,17 +102,17 @@ void proc_exec_connector(struct task_str
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg*)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event*)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_EXEC;
 	ev->event_data.exec.process_pid = task->pid;
 	ev->event_data.exec.process_tgid = task->tgid;
@@ -116,14 +128,14 @@ void proc_id_connector(struct task_struc
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 	const struct cred *cred;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg*)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event*)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	ev->what = which_id;
@@ -144,7 +156,7 @@ void proc_id_connector(struct task_struc
 	rcu_read_unlock();
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 
 	memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id));
 	msg->ack = 0; /* not used */
@@ -158,17 +170,17 @@ void proc_sid_connector(struct task_stru
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_SID;
 	ev->event_data.sid.process_pid = task->pid;
 	ev->event_data.sid.process_tgid = task->tgid;
@@ -185,17 +197,17 @@ void proc_ptrace_connector(struct task_s
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_PTRACE;
 	ev->event_data.ptrace.process_pid  = task->pid;
 	ev->event_data.ptrace.process_tgid = task->tgid;
@@ -220,17 +232,17 @@ void proc_comm_connector(struct task_str
 	struct cn_msg *msg;
 	struct proc_event *ev;
 	struct timespec ts;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg *)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event *)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_COMM;
 	ev->event_data.comm.process_pid  = task->pid;
 	ev->event_data.comm.process_tgid = task->tgid;
@@ -247,18 +259,18 @@ void proc_exit_connector(struct task_str
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg*)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event*)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	get_seq(&msg->seq, &ev->cpu);
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->what = PROC_EVENT_EXIT;
 	ev->event_data.exit.process_pid = task->pid;
 	ev->event_data.exit.process_tgid = task->tgid;
@@ -284,18 +296,18 @@ static void cn_proc_ack(int err, int rcv
 {
 	struct cn_msg *msg;
 	struct proc_event *ev;
-	__u8 buffer[CN_PROC_MSG_SIZE];
+	__u8 buffer[CN_PROC_MSG_SIZE] __aligned(8);
 	struct timespec ts;
 
 	if (atomic_read(&proc_event_num_listeners) < 1)
 		return;
 
-	msg = (struct cn_msg*)buffer;
+	msg = buffer_to_cn_msg(buffer);
 	ev = (struct proc_event*)msg->data;
 	memset(&ev->event_data, 0, sizeof(ev->event_data));
 	msg->seq = rcvd_seq;
 	ktime_get_ts(&ts); /* get high res monotonic timestamp */
-	put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns);
+	ev->timestamp_ns = timespec_to_ns(&ts);
 	ev->cpu = -1;
 	ev->what = PROC_EVENT_NONE;
 	ev->event_data.ack.err = err;