summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorJeff Mahoney <jeffm@suse.com>2010-12-21 17:24:30 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2010-12-22 19:43:34 -0800
commit4be2c95d1f7706ca0e74499f2bd118e1cee19669 (patch)
tree97e8e316b9072ea84cb0afa5a161b1d1b10640cd
parent4e06fd14d5fa78826397c891654a37e5a36ee827 (diff)
downloadop-kernel-dev-4be2c95d1f7706ca0e74499f2bd118e1cee19669.zip
op-kernel-dev-4be2c95d1f7706ca0e74499f2bd118e1cee19669.tar.gz
taskstats: pad taskstats netlink response for aligment issues on ia64
The taskstats structure is internally aligned on 8 byte boundaries but the layout of the aggregrate reply, with two NLA headers and the pid (each 4 bytes), actually force the entire structure to be unaligned. This causes the kernel to issue unaligned access warnings on some architectures like ia64. Unfortunately, some software out there doesn't properly unroll the NLA packet and assumes that the start of the taskstats structure will always be 20 bytes from the start of the netlink payload. Aligning the start of the taskstats structure breaks this software, which we don't want. So, for now the alignment only happens on architectures that require it and those users will have to update to fixed versions of those packages. Space is reserved in the packet only when needed. This ifdef should be removed in several years e.g. 2012 once we can be confident that fixed versions are installed on most systems. We add the padding before the aggregate since the aggregate is already a defined type. Commit 85893120 ("delayacct: align to 8 byte boundary on 64-bit systems") previously addressed the alignment issues by padding out the pid field. This was supposed to be a compatible change but the circumstances described above mean that it wasn't. This patch backs out that change, since it was a hack, and introduces a new NULL attribute type to provide the padding. Padding the response with 4 bytes avoids allocating an aligned taskstats structure and copying it back. Since the structure weighs in at 328 bytes, it's too big to do it on the stack. Signed-off-by: Jeff Mahoney <jeffm@suse.com> Reported-by: Brian Rogers <brian@xyzw.org> Cc: Jeff Mahoney <jeffm@suse.com> Cc: Guillaume Chazarain <guichaz@gmail.com> Cc: Balbir Singh <balbir@in.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--Documentation/accounting/getdelays.c1
-rw-r--r--include/linux/taskstats.h3
-rw-r--r--kernel/taskstats.c57
3 files changed, 47 insertions, 14 deletions
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index a2976a6..e9c7778 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -516,6 +516,7 @@ int main(int argc, char *argv[])
default:
fprintf(stderr, "Unknown nla_type %d\n",
na->nla_type);
+ case TASKSTATS_TYPE_NULL:
break;
}
na = (struct nlattr *) (GENLMSG_DATA(&msg) + len);
diff --git a/include/linux/taskstats.h b/include/linux/taskstats.h
index 341dddb..2466e55 100644
--- a/include/linux/taskstats.h
+++ b/include/linux/taskstats.h
@@ -33,7 +33,7 @@
*/
-#define TASKSTATS_VERSION 7
+#define TASKSTATS_VERSION 8
#define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN
* in linux/sched.h */
@@ -188,6 +188,7 @@ enum {
TASKSTATS_TYPE_STATS, /* taskstats structure */
TASKSTATS_TYPE_AGGR_PID, /* contains pid + stats */
TASKSTATS_TYPE_AGGR_TGID, /* contains tgid + stats */
+ TASKSTATS_TYPE_NULL, /* contains nothing */
__TASKSTATS_TYPE_MAX,
};
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index c8231fb..3308fd7 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -349,25 +349,47 @@ static int parse(struct nlattr *na, struct cpumask *mask)
return ret;
}
+#ifdef CONFIG_IA64
+#define TASKSTATS_NEEDS_PADDING 1
+#endif
+
static struct taskstats *mk_reply(struct sk_buff *skb, int type, u32 pid)
{
struct nlattr *na, *ret;
int aggr;
- /* If we don't pad, we end up with alignment on a 4 byte boundary.
- * This causes lots of runtime warnings on systems requiring 8 byte
- * alignment */
- u32 pids[2] = { pid, 0 };
- int pid_size = ALIGN(sizeof(pid), sizeof(long));
-
aggr = (type == TASKSTATS_TYPE_PID)
? TASKSTATS_TYPE_AGGR_PID
: TASKSTATS_TYPE_AGGR_TGID;
+ /*
+ * The taskstats structure is internally aligned on 8 byte
+ * boundaries but the layout of the aggregrate reply, with
+ * two NLA headers and the pid (each 4 bytes), actually
+ * force the entire structure to be unaligned. This causes
+ * the kernel to issue unaligned access warnings on some
+ * architectures like ia64. Unfortunately, some software out there
+ * doesn't properly unroll the NLA packet and assumes that the start
+ * of the taskstats structure will always be 20 bytes from the start
+ * of the netlink payload. Aligning the start of the taskstats
+ * structure breaks this software, which we don't want. So, for now
+ * the alignment only happens on architectures that require it
+ * and those users will have to update to fixed versions of those
+ * packages. Space is reserved in the packet only when needed.
+ * This ifdef should be removed in several years e.g. 2012 once
+ * we can be confident that fixed versions are installed on most
+ * systems. We add the padding before the aggregate since the
+ * aggregate is already a defined type.
+ */
+#ifdef TASKSTATS_NEEDS_PADDING
+ if (nla_put(skb, TASKSTATS_TYPE_NULL, 0, NULL) < 0)
+ goto err;
+#endif
na = nla_nest_start(skb, aggr);
if (!na)
goto err;
- if (nla_put(skb, type, pid_size, pids) < 0)
+
+ if (nla_put(skb, type, sizeof(pid), &pid) < 0)
goto err;
ret = nla_reserve(skb, TASKSTATS_TYPE_STATS, sizeof(struct taskstats));
if (!ret)
@@ -456,6 +478,18 @@ out:
return rc;
}
+static size_t taskstats_packet_size(void)
+{
+ size_t size;
+
+ size = nla_total_size(sizeof(u32)) +
+ nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+#ifdef TASKSTATS_NEEDS_PADDING
+ size += nla_total_size(0); /* Padding for alignment */
+#endif
+ return size;
+}
+
static int cmd_attr_pid(struct genl_info *info)
{
struct taskstats *stats;
@@ -464,8 +498,7 @@ static int cmd_attr_pid(struct genl_info *info)
u32 pid;
int rc;
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
@@ -494,8 +527,7 @@ static int cmd_attr_tgid(struct genl_info *info)
u32 tgid;
int rc;
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
rc = prepare_reply(info, TASKSTATS_CMD_NEW, &rep_skb, size);
if (rc < 0)
@@ -570,8 +602,7 @@ void taskstats_exit(struct task_struct *tsk, int group_dead)
/*
* Size includes space for nested attributes
*/
- size = nla_total_size(sizeof(u32)) +
- nla_total_size(sizeof(struct taskstats)) + nla_total_size(0);
+ size = taskstats_packet_size();
is_thread_group = !!taskstats_tgid_alloc(tsk);
if (is_thread_group) {
OpenPOWER on IntegriCloud