* [PATCH net-next v2 5/8] sctp: move flushing of data chunks out of sctp_outq_flush
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142784.git.marcelo.leitner@gmail.com>
To the new sctp_outq_flush_data. Again, smaller functions and with well
defined objectives.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 148 ++++++++++++++++++++++++++--------------------------
1 file changed, 75 insertions(+), 73 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 6d7ee372a9d6b8e68a759277830d5334ec992d47..7522188107792643f3bb5f00e5c254b00e91ef12 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1038,45 +1038,17 @@ static bool sctp_outq_flush_rtx(struct sctp_outq *q,
return true;
}
-/*
- * Try to flush an outqueue.
- *
- * Description: Send everything in q which we legally can, subject to
- * congestion limitations.
- * * Note: This function can be called from multiple contexts so appropriate
- * locking concerns must be made. Today we use the sock lock to protect
- * this function.
- */
-static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
+
+static void sctp_outq_flush_data(struct sctp_outq *q,
+ struct sctp_transport **_transport,
+ struct list_head *transport_list,
+ int rtx_timeout, gfp_t gfp)
{
- struct sctp_packet *packet;
+ struct sctp_transport *transport = *_transport;
+ struct sctp_packet *packet = transport ? &transport->packet : NULL;
struct sctp_association *asoc = q->asoc;
- struct sctp_transport *transport = NULL;
struct sctp_chunk *chunk;
enum sctp_xmit status;
- int error = 0;
-
- /* These transports have chunks to send. */
- struct list_head transport_list;
- struct list_head *ltransport;
-
- INIT_LIST_HEAD(&transport_list);
- packet = NULL;
-
- /*
- * 6.10 Bundling
- * ...
- * When bundling control chunks with DATA chunks, an
- * endpoint MUST place control chunks first in the outbound
- * SCTP packet. The transmitter MUST transmit DATA chunks
- * within a SCTP packet in increasing order of TSN.
- * ...
- */
-
- sctp_outq_flush_ctrl(q, &transport, &transport_list, gfp);
-
- if (q->asoc->src_out_of_asoc_ok)
- goto sctp_flush_out;
/* Is it OK to send data chunks? */
switch (asoc->state) {
@@ -1101,10 +1073,11 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
* current cwnd).
*/
if (!list_empty(&q->retransmit)) {
- if (!sctp_outq_flush_rtx(q, &transport, &transport_list,
+ if (!sctp_outq_flush_rtx(q, _transport, transport_list,
rtx_timeout))
break;
/* We may have switched current transport */
+ transport = *_transport;
packet = &transport->packet;
}
@@ -1130,12 +1103,14 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
sctp_outq_head_data(q, chunk);
- goto sctp_flush_out;
+ break;
}
- if (sctp_outq_select_transport(chunk, asoc, &transport,
- &transport_list))
+ if (sctp_outq_select_transport(chunk, asoc, _transport,
+ transport_list)) {
+ transport = *_transport;
packet = &transport->packet;
+ }
pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
"skb->users:%d\n",
@@ -1147,8 +1122,10 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
/* Add the chunk to the packet. */
status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp);
-
switch (status) {
+ case SCTP_XMIT_OK:
+ break;
+
case SCTP_XMIT_PMTU_FULL:
case SCTP_XMIT_RWND_FULL:
case SCTP_XMIT_DELAY:
@@ -1160,41 +1137,25 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
status);
sctp_outq_head_data(q, chunk);
- goto sctp_flush_out;
-
- case SCTP_XMIT_OK:
- /* The sender is in the SHUTDOWN-PENDING state,
- * The sender MAY set the I-bit in the DATA
- * chunk header.
- */
- if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
- chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
- if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
- asoc->stats.ouodchunks++;
- else
- asoc->stats.oodchunks++;
-
- /* Only now it's safe to consider this
- * chunk as sent, sched-wise.
- */
- sctp_sched_dequeue_done(q, chunk);
-
- break;
-
- default:
- BUG();
+ return;
}
- /* BUG: We assume that the sctp_packet_transmit()
- * call below will succeed all the time and add the
- * chunk to the transmitted list and restart the
- * timers.
- * It is possible that the call can fail under OOM
- * conditions.
- *
- * Is this really a problem? Won't this behave
- * like a lost TSN?
+ /* The sender is in the SHUTDOWN-PENDING state,
+ * The sender MAY set the I-bit in the DATA
+ * chunk header.
*/
+ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
+ chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
+ if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
+ asoc->stats.ouodchunks++;
+ else
+ asoc->stats.oodchunks++;
+
+ /* Only now it's safe to consider this
+ * chunk as sent, sched-wise.
+ */
+ sctp_sched_dequeue_done(q, chunk);
+
list_add_tail(&chunk->transmitted_list,
&transport->transmitted);
@@ -1205,7 +1166,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
* COOKIE-ECHO chunk.
*/
if (packet->has_cookie_echo)
- goto sctp_flush_out;
+ break;
}
break;
@@ -1213,6 +1174,47 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
/* Do nothing. */
break;
}
+}
+
+/*
+ * Try to flush an outqueue.
+ *
+ * Description: Send everything in q which we legally can, subject to
+ * congestion limitations.
+ * * Note: This function can be called from multiple contexts so appropriate
+ * locking concerns must be made. Today we use the sock lock to protect
+ * this function.
+ */
+static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
+{
+ struct sctp_packet *packet;
+ struct sctp_association *asoc = q->asoc;
+ struct sctp_transport *transport = NULL;
+ int error = 0;
+
+ /* These transports have chunks to send. */
+ struct list_head transport_list;
+ struct list_head *ltransport;
+
+ INIT_LIST_HEAD(&transport_list);
+ packet = NULL;
+
+ /*
+ * 6.10 Bundling
+ * ...
+ * When bundling control chunks with DATA chunks, an
+ * endpoint MUST place control chunks first in the outbound
+ * SCTP packet. The transmitter MUST transmit DATA chunks
+ * within a SCTP packet in increasing order of TSN.
+ * ...
+ */
+
+ sctp_outq_flush_ctrl(q, &transport, &transport_list, gfp);
+
+ if (q->asoc->src_out_of_asoc_ok)
+ goto sctp_flush_out;
+
+ sctp_outq_flush_data(q, &transport, &transport_list, rtx_timeout, gfp);
sctp_flush_out:
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v2 6/8] sctp: move transport flush code out of sctp_outq_flush
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142784.git.marcelo.leitner@gmail.com>
To the new sctp_outq_flush_transports.
Comment on Nagle is outdated and removed. Nagle is performed earlier, while
checking if the chunk fits the packet: if the outq length is not enough to
fill the packet, it returns SCTP_XMIT_DELAY.
So by when it gets to sctp_outq_flush_transports, it has to go through all
enlisted transports.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 56 +++++++++++++++++++++++++----------------------------
1 file changed, 26 insertions(+), 30 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 7522188107792643f3bb5f00e5c254b00e91ef12..3b738fdb08b9c596e6d4d4b18bef645187e0da4a 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1176,6 +1176,29 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
}
}
+static void sctp_outq_flush_transports(struct sctp_outq *q,
+ struct list_head *transport_list,
+ gfp_t gfp)
+{
+ struct list_head *ltransport;
+ struct sctp_packet *packet;
+ struct sctp_transport *t;
+ int error = 0;
+
+ while ((ltransport = sctp_list_dequeue(transport_list)) != NULL) {
+ t = list_entry(ltransport, struct sctp_transport, send_ready);
+ packet = &t->packet;
+ if (!sctp_packet_empty(packet)) {
+ error = sctp_packet_transmit(packet, gfp);
+ if (error < 0)
+ q->asoc->base.sk->sk_err = -error;
+ }
+
+ /* Clear the burst limited state, if any */
+ sctp_transport_burst_reset(t);
+ }
+}
+
/*
* Try to flush an outqueue.
*
@@ -1187,17 +1210,10 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
*/
static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
{
- struct sctp_packet *packet;
- struct sctp_association *asoc = q->asoc;
+ /* Current transport being used. It's NOT the same as curr active one */
struct sctp_transport *transport = NULL;
- int error = 0;
-
/* These transports have chunks to send. */
- struct list_head transport_list;
- struct list_head *ltransport;
-
- INIT_LIST_HEAD(&transport_list);
- packet = NULL;
+ LIST_HEAD(transport_list);
/*
* 6.10 Bundling
@@ -1218,27 +1234,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
sctp_flush_out:
- /* Before returning, examine all the transports touched in
- * this call. Right now, we bluntly force clear all the
- * transports. Things might change after we implement Nagle.
- * But such an examination is still required.
- *
- * --xguo
- */
- while ((ltransport = sctp_list_dequeue(&transport_list)) != NULL) {
- struct sctp_transport *t = list_entry(ltransport,
- struct sctp_transport,
- send_ready);
- packet = &t->packet;
- if (!sctp_packet_empty(packet)) {
- error = sctp_packet_transmit(packet, gfp);
- if (error < 0)
- asoc->base.sk->sk_err = -error;
- }
-
- /* Clear the burst limited state, if any */
- sctp_transport_burst_reset(t);
- }
+ sctp_outq_flush_transports(q, &transport_list, gfp);
}
/* Update unack_data based on the incoming SACK chunk */
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v2 7/8] sctp: make use of gfp on retransmissions
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142784.git.marcelo.leitner@gmail.com>
Retransmissions may be triggered when in user context, so lets make use
of gfp.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 17 +++++++++--------
1 file changed, 9 insertions(+), 8 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 3b738fdb08b9c596e6d4d4b18bef645187e0da4a..8173dd26f5878cbf67dd7e162ac5e6b18d9a3332 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -608,7 +608,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport,
* The return value is a normal kernel error return value.
*/
static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
- int rtx_timeout, int *start_timer)
+ int rtx_timeout, int *start_timer, gfp_t gfp)
{
struct sctp_transport *transport = pkt->transport;
struct sctp_chunk *chunk, *chunk1;
@@ -684,12 +684,12 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
* control chunks are already freed so there
* is nothing we can do.
*/
- sctp_packet_transmit(pkt, GFP_ATOMIC);
+ sctp_packet_transmit(pkt, gfp);
goto redo;
}
/* Send this packet. */
- error = sctp_packet_transmit(pkt, GFP_ATOMIC);
+ error = sctp_packet_transmit(pkt, gfp);
/* If we are retransmitting, we should only
* send a single packet.
@@ -705,7 +705,7 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
case SCTP_XMIT_RWND_FULL:
/* Send this packet. */
- error = sctp_packet_transmit(pkt, GFP_ATOMIC);
+ error = sctp_packet_transmit(pkt, gfp);
/* Stop sending DATA as there is no more room
* at the receiver.
@@ -715,7 +715,7 @@ static int __sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt,
case SCTP_XMIT_DELAY:
/* Send this packet. */
- error = sctp_packet_transmit(pkt, GFP_ATOMIC);
+ error = sctp_packet_transmit(pkt, gfp);
/* Stop sending DATA because of nagle delay. */
done = 1;
@@ -991,7 +991,7 @@ static void sctp_outq_flush_ctrl(struct sctp_outq *q,
static bool sctp_outq_flush_rtx(struct sctp_outq *q,
struct sctp_transport **_transport,
struct list_head *transport_list,
- int rtx_timeout)
+ int rtx_timeout, gfp_t gfp)
{
struct sctp_transport *transport = *_transport;
struct sctp_packet *packet = transport ? &transport->packet : NULL;
@@ -1015,7 +1015,8 @@ static bool sctp_outq_flush_rtx(struct sctp_outq *q,
asoc->peer.ecn_capable);
}
- error = __sctp_outq_flush_rtx(q, packet, rtx_timeout, &start_timer);
+ error = __sctp_outq_flush_rtx(q, packet, rtx_timeout, &start_timer,
+ gfp);
if (error < 0)
asoc->base.sk->sk_err = -error;
@@ -1074,7 +1075,7 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
*/
if (!list_empty(&q->retransmit)) {
if (!sctp_outq_flush_rtx(q, _transport, transport_list,
- rtx_timeout))
+ rtx_timeout, gfp))
break;
/* We may have switched current transport */
transport = *_transport;
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v2 8/8] sctp: rework switch cases in sctp_outq_flush_data
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142784.git.marcelo.leitner@gmail.com>
Remove an inner one, which tended to be error prone due to the cascading
and it can be replaced by a simple if ().
Rework the outer one so that the actual flush code is not inside it. Now
we first validate if we can or cannot send data, return if not, and then
the flush code.
Suggested-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 191 +++++++++++++++++++++++++---------------------------
1 file changed, 93 insertions(+), 98 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index 8173dd26f5878cbf67dd7e162ac5e6b18d9a3332..a9400cb0cc249affcf2bedfc7a070d9e48843d27 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -1058,122 +1058,117 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
* chunk.
*/
if (!packet || !packet->has_cookie_echo)
- break;
+ return;
/* fallthru */
case SCTP_STATE_ESTABLISHED:
case SCTP_STATE_SHUTDOWN_PENDING:
case SCTP_STATE_SHUTDOWN_RECEIVED:
- /*
- * RFC 2960 6.1 Transmission of DATA Chunks
- *
- * C) When the time comes for the sender to transmit,
- * before sending new DATA chunks, the sender MUST
- * first transmit any outstanding DATA chunks which
- * are marked for retransmission (limited by the
- * current cwnd).
- */
- if (!list_empty(&q->retransmit)) {
- if (!sctp_outq_flush_rtx(q, _transport, transport_list,
- rtx_timeout, gfp))
- break;
- /* We may have switched current transport */
- transport = *_transport;
- packet = &transport->packet;
- }
+ break;
- /* Apply Max.Burst limitation to the current transport in
- * case it will be used for new data. We are going to
- * rest it before we return, but we want to apply the limit
- * to the currently queued data.
- */
- if (transport)
- sctp_transport_burst_limited(transport);
-
- /* Finally, transmit new packets. */
- while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
- __u32 sid = ntohs(chunk->subh.data_hdr->stream);
-
- /* Has this chunk expired? */
- if (sctp_chunk_abandoned(chunk)) {
- sctp_sched_dequeue_done(q, chunk);
- sctp_chunk_fail(chunk, 0);
- sctp_chunk_free(chunk);
- continue;
- }
+ default:
+ /* Do nothing. */
+ return;
+ }
- if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
- sctp_outq_head_data(q, chunk);
- break;
- }
+ /*
+ * RFC 2960 6.1 Transmission of DATA Chunks
+ *
+ * C) When the time comes for the sender to transmit,
+ * before sending new DATA chunks, the sender MUST
+ * first transmit any outstanding DATA chunks which
+ * are marked for retransmission (limited by the
+ * current cwnd).
+ */
+ if (!list_empty(&q->retransmit)) {
+ if (!sctp_outq_flush_rtx(q, _transport, transport_list,
+ rtx_timeout, gfp))
+ return;
+ /* We may have switched current transport */
+ transport = *_transport;
+ packet = &transport->packet;
+ }
- if (sctp_outq_select_transport(chunk, asoc, _transport,
- transport_list)) {
- transport = *_transport;
- packet = &transport->packet;
- }
+ /* Apply Max.Burst limitation to the current transport in
+ * case it will be used for new data. We are going to
+ * rest it before we return, but we want to apply the limit
+ * to the currently queued data.
+ */
+ if (transport)
+ sctp_transport_burst_limited(transport);
- pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
- "skb->users:%d\n",
- __func__, q, chunk, chunk && chunk->chunk_hdr ?
- sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
- "illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
- chunk->skb ? chunk->skb->head : NULL, chunk->skb ?
- refcount_read(&chunk->skb->users) : -1);
-
- /* Add the chunk to the packet. */
- status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp);
- switch (status) {
- case SCTP_XMIT_OK:
- break;
+ /* Finally, transmit new packets. */
+ while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
+ __u32 sid = ntohs(chunk->subh.data_hdr->stream);
- case SCTP_XMIT_PMTU_FULL:
- case SCTP_XMIT_RWND_FULL:
- case SCTP_XMIT_DELAY:
- /* We could not append this chunk, so put
- * the chunk back on the output queue.
- */
- pr_debug("%s: could not transmit tsn:0x%x, status:%d\n",
- __func__, ntohl(chunk->subh.data_hdr->tsn),
- status);
+ /* Has this chunk expired? */
+ if (sctp_chunk_abandoned(chunk)) {
+ sctp_sched_dequeue_done(q, chunk);
+ sctp_chunk_fail(chunk, 0);
+ sctp_chunk_free(chunk);
+ continue;
+ }
- sctp_outq_head_data(q, chunk);
- return;
- }
+ if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
+ sctp_outq_head_data(q, chunk);
+ break;
+ }
- /* The sender is in the SHUTDOWN-PENDING state,
- * The sender MAY set the I-bit in the DATA
- * chunk header.
- */
- if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
- chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
- if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
- asoc->stats.ouodchunks++;
- else
- asoc->stats.oodchunks++;
+ if (sctp_outq_select_transport(chunk, asoc, _transport,
+ transport_list)) {
+ transport = *_transport;
+ packet = &transport->packet;
+ }
- /* Only now it's safe to consider this
- * chunk as sent, sched-wise.
+ pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
+ "skb->users:%d\n",
+ __func__, q, chunk, chunk && chunk->chunk_hdr ?
+ sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
+ "illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
+ chunk->skb ? chunk->skb->head : NULL, chunk->skb ?
+ refcount_read(&chunk->skb->users) : -1);
+
+ /* Add the chunk to the packet. */
+ status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp);
+ if (status != SCTP_XMIT_OK) {
+ /* We could not append this chunk, so put
+ * the chunk back on the output queue.
*/
- sctp_sched_dequeue_done(q, chunk);
+ pr_debug("%s: could not transmit tsn:0x%x, status:%d\n",
+ __func__, ntohl(chunk->subh.data_hdr->tsn),
+ status);
+
+ sctp_outq_head_data(q, chunk);
+ break;
+ }
- list_add_tail(&chunk->transmitted_list,
- &transport->transmitted);
+ /* The sender is in the SHUTDOWN-PENDING state,
+ * The sender MAY set the I-bit in the DATA
+ * chunk header.
+ */
+ if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
+ chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
+ if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
+ asoc->stats.ouodchunks++;
+ else
+ asoc->stats.oodchunks++;
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
+ /* Only now it's safe to consider this
+ * chunk as sent, sched-wise.
+ */
+ sctp_sched_dequeue_done(q, chunk);
- /* Only let one DATA chunk get bundled with a
- * COOKIE-ECHO chunk.
- */
- if (packet->has_cookie_echo)
- break;
- }
- break;
+ list_add_tail(&chunk->transmitted_list,
+ &transport->transmitted);
- default:
- /* Do nothing. */
- break;
+ sctp_transport_reset_t3_rtx(transport);
+ transport->last_time_sent = jiffies;
+
+ /* Only let one DATA chunk get bundled with a
+ * COOKIE-ECHO chunk.
+ */
+ if (packet->has_cookie_echo)
+ break;
}
}
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v2 0/3] sctp: Introduce sctp_flush_ctx
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
This struct will hold all the context used during the outq flush, so we
don't have to pass lots of pointers all around.
Checked on x86_64, the compiler inlines all these functions and there is no
derreference added because of the struct.
This patchset depends on 'sctp: refactor sctp_outq_flush'
Changes since v1:
- updated to build on top of v2 of 'sctp: refactor sctp_outq_flush'
Marcelo Ricardo Leitner (3):
sctp: add sctp_flush_ctx, a context struct on outq_flush routines
sctp: add asoc and packet to sctp_flush_ctx
sctp: checkpatch fixups
net/sctp/outqueue.c | 259 ++++++++++++++++++++++++----------------------------
1 file changed, 119 insertions(+), 140 deletions(-)
^ permalink raw reply
* [PATCH net-next v2 1/3] sctp: add sctp_flush_ctx, a context struct on outq_flush routines
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142994.git.marcelo.leitner@gmail.com>
With this struct we avoid passing lots of variables around and taking care
of updating the current transport/packet.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 182 +++++++++++++++++++++++++---------------------------
1 file changed, 88 insertions(+), 94 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index a9400cb0cc249affcf2bedfc7a070d9e48843d27..db94a2513dd874149aa77c4936f68537e97f8855 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -791,13 +791,22 @@ static int sctp_packet_singleton(struct sctp_transport *transport,
return sctp_packet_transmit(&singleton, gfp);
}
-static bool sctp_outq_select_transport(struct sctp_chunk *chunk,
- struct sctp_association *asoc,
- struct sctp_transport **transport,
- struct list_head *transport_list)
+/* Struct to hold the context during sctp outq flush */
+struct sctp_flush_ctx {
+ struct sctp_outq *q;
+ /* Current transport being used. It's NOT the same as curr active one */
+ struct sctp_transport *transport;
+ /* These transports have chunks to send. */
+ struct list_head transport_list;
+ gfp_t gfp;
+};
+
+/* transport: current transport */
+static bool sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
+ struct sctp_chunk *chunk)
{
struct sctp_transport *new_transport = chunk->transport;
- struct sctp_transport *curr = *transport;
+ struct sctp_association *asoc = ctx->q->asoc;
bool changed = false;
if (!new_transport) {
@@ -812,9 +821,9 @@ static bool sctp_outq_select_transport(struct sctp_chunk *chunk,
* after processing ASCONFs, we may have new
* transports created.
*/
- if (curr && sctp_cmp_addr_exact(&chunk->dest,
- &curr->ipaddr))
- new_transport = curr;
+ if (ctx->transport && sctp_cmp_addr_exact(&chunk->dest,
+ &ctx->transport->ipaddr))
+ new_transport = ctx->transport;
else
new_transport = sctp_assoc_lookup_paddr(asoc,
&chunk->dest);
@@ -857,37 +866,33 @@ static bool sctp_outq_select_transport(struct sctp_chunk *chunk,
}
/* Are we switching transports? Take care of transport locks. */
- if (new_transport != curr) {
+ if (new_transport != ctx->transport) {
changed = true;
- curr = new_transport;
- *transport = curr;
- if (list_empty(&curr->send_ready))
- list_add_tail(&curr->send_ready, transport_list);
+ ctx->transport = new_transport;
+ if (list_empty(&ctx->transport->send_ready))
+ list_add_tail(&ctx->transport->send_ready,
+ &ctx->transport_list);
- sctp_packet_config(&curr->packet, asoc->peer.i.init_tag,
+ sctp_packet_config(&ctx->transport->packet, asoc->peer.i.init_tag,
asoc->peer.ecn_capable);
/* We've switched transports, so apply the
* Burst limit to the new transport.
*/
- sctp_transport_burst_limited(curr);
+ sctp_transport_burst_limited(ctx->transport);
}
return changed;
}
-static void sctp_outq_flush_ctrl(struct sctp_outq *q,
- struct sctp_transport **_transport,
- struct list_head *transport_list,
- gfp_t gfp)
+static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
{
- struct sctp_transport *transport = *_transport;
- struct sctp_association *asoc = q->asoc;
+ struct sctp_association *asoc = ctx->q->asoc;
struct sctp_packet *packet = NULL;
struct sctp_chunk *chunk, *tmp;
enum sctp_xmit status;
int one_packet, error;
- list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) {
+ list_for_each_entry_safe(chunk, tmp, &ctx->q->control_chunk_list, list) {
one_packet = 0;
/* RFC 5061, 5.3
@@ -905,11 +910,8 @@ static void sctp_outq_flush_ctrl(struct sctp_outq *q,
/* Pick the right transport to use. Should always be true for
* the first chunk as we don't have a transport by then.
*/
- if (sctp_outq_select_transport(chunk, asoc, &transport,
- transport_list)) {
- transport = *_transport;
- packet = &transport->packet;
- }
+ if (sctp_outq_select_transport(ctx, chunk))
+ packet = &ctx->transport->packet;
switch (chunk->chunk_hdr->type) {
/*
@@ -921,7 +923,8 @@ static void sctp_outq_flush_ctrl(struct sctp_outq *q,
case SCTP_CID_INIT:
case SCTP_CID_INIT_ACK:
case SCTP_CID_SHUTDOWN_COMPLETE:
- error = sctp_packet_singleton(transport, chunk, gfp);
+ error = sctp_packet_singleton(ctx->transport, chunk,
+ ctx->gfp);
if (error < 0) {
asoc->base.sk->sk_err = -error;
return;
@@ -957,10 +960,10 @@ static void sctp_outq_flush_ctrl(struct sctp_outq *q,
case SCTP_CID_I_FWD_TSN:
case SCTP_CID_RECONF:
status = sctp_packet_transmit_chunk(packet, chunk,
- one_packet, gfp);
+ one_packet, ctx->gfp);
if (status != SCTP_XMIT_OK) {
/* put the chunk back */
- list_add(&chunk->list, &q->control_chunk_list);
+ list_add(&chunk->list, &ctx->q->control_chunk_list);
break;
}
@@ -971,12 +974,12 @@ static void sctp_outq_flush_ctrl(struct sctp_outq *q,
*/
if (chunk->chunk_hdr->type == SCTP_CID_FWD_TSN ||
chunk->chunk_hdr->type == SCTP_CID_I_FWD_TSN) {
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
+ sctp_transport_reset_t3_rtx(ctx->transport);
+ ctx->transport->last_time_sent = jiffies;
}
if (chunk == asoc->strreset_chunk)
- sctp_transport_reset_reconf_timer(transport);
+ sctp_transport_reset_reconf_timer(ctx->transport);
break;
@@ -988,41 +991,38 @@ static void sctp_outq_flush_ctrl(struct sctp_outq *q,
}
/* Returns false if new data shouldn't be sent */
-static bool sctp_outq_flush_rtx(struct sctp_outq *q,
- struct sctp_transport **_transport,
- struct list_head *transport_list,
- int rtx_timeout, gfp_t gfp)
+static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx,
+ int rtx_timeout)
{
- struct sctp_transport *transport = *_transport;
- struct sctp_packet *packet = transport ? &transport->packet : NULL;
- struct sctp_association *asoc = q->asoc;
+ struct sctp_packet *packet = ctx->transport ? &ctx->transport->packet :
+ NULL;
+ struct sctp_association *asoc = ctx->q->asoc;
int error, start_timer = 0;
if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
return false;
- if (transport != asoc->peer.retran_path) {
+ if (ctx->transport != asoc->peer.retran_path) {
/* Switch transports & prepare the packet. */
- transport = asoc->peer.retran_path;
- *_transport = transport;
+ ctx->transport = asoc->peer.retran_path;
- if (list_empty(&transport->send_ready))
- list_add_tail(&transport->send_ready,
- transport_list);
+ if (list_empty(&ctx->transport->send_ready))
+ list_add_tail(&ctx->transport->send_ready,
+ &ctx->transport_list);
- packet = &transport->packet;
+ packet = &ctx->transport->packet;
sctp_packet_config(packet, asoc->peer.i.init_tag,
asoc->peer.ecn_capable);
}
- error = __sctp_outq_flush_rtx(q, packet, rtx_timeout, &start_timer,
- gfp);
+ error = __sctp_outq_flush_rtx(ctx->q, packet, rtx_timeout, &start_timer,
+ ctx->gfp);
if (error < 0)
asoc->base.sk->sk_err = -error;
if (start_timer) {
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
+ sctp_transport_reset_t3_rtx(ctx->transport);
+ ctx->transport->last_time_sent = jiffies;
}
/* This can happen on COOKIE-ECHO resend. Only
@@ -1034,20 +1034,18 @@ static bool sctp_outq_flush_rtx(struct sctp_outq *q,
/* Don't send new data if there is still data
* waiting to retransmit.
*/
- if (!list_empty(&q->retransmit))
+ if (!list_empty(&ctx->q->retransmit))
return false;
return true;
}
-static void sctp_outq_flush_data(struct sctp_outq *q,
- struct sctp_transport **_transport,
- struct list_head *transport_list,
- int rtx_timeout, gfp_t gfp)
+static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
+ int rtx_timeout)
{
- struct sctp_transport *transport = *_transport;
- struct sctp_packet *packet = transport ? &transport->packet : NULL;
- struct sctp_association *asoc = q->asoc;
+ struct sctp_packet *packet = ctx->transport ? &ctx->transport->packet :
+ NULL;
+ struct sctp_association *asoc = ctx->q->asoc;
struct sctp_chunk *chunk;
enum sctp_xmit status;
@@ -1080,13 +1078,11 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
* are marked for retransmission (limited by the
* current cwnd).
*/
- if (!list_empty(&q->retransmit)) {
- if (!sctp_outq_flush_rtx(q, _transport, transport_list,
- rtx_timeout, gfp))
+ if (!list_empty(&ctx->q->retransmit)) {
+ if (!sctp_outq_flush_rtx(ctx, rtx_timeout))
return;
/* We may have switched current transport */
- transport = *_transport;
- packet = &transport->packet;
+ packet = &ctx->transport->packet;
}
/* Apply Max.Burst limitation to the current transport in
@@ -1094,42 +1090,39 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
* rest it before we return, but we want to apply the limit
* to the currently queued data.
*/
- if (transport)
- sctp_transport_burst_limited(transport);
+ if (ctx->transport)
+ sctp_transport_burst_limited(ctx->transport);
/* Finally, transmit new packets. */
- while ((chunk = sctp_outq_dequeue_data(q)) != NULL) {
+ while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) {
__u32 sid = ntohs(chunk->subh.data_hdr->stream);
/* Has this chunk expired? */
if (sctp_chunk_abandoned(chunk)) {
- sctp_sched_dequeue_done(q, chunk);
+ sctp_sched_dequeue_done(ctx->q, chunk);
sctp_chunk_fail(chunk, 0);
sctp_chunk_free(chunk);
continue;
}
if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
- sctp_outq_head_data(q, chunk);
+ sctp_outq_head_data(ctx->q, chunk);
break;
}
- if (sctp_outq_select_transport(chunk, asoc, _transport,
- transport_list)) {
- transport = *_transport;
- packet = &transport->packet;
- }
+ if (sctp_outq_select_transport(ctx, chunk))
+ packet = &ctx->transport->packet;
pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
"skb->users:%d\n",
- __func__, q, chunk, chunk && chunk->chunk_hdr ?
+ __func__, ctx->q, chunk, chunk && chunk->chunk_hdr ?
sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
"illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
chunk->skb ? chunk->skb->head : NULL, chunk->skb ?
refcount_read(&chunk->skb->users) : -1);
/* Add the chunk to the packet. */
- status = sctp_packet_transmit_chunk(packet, chunk, 0, gfp);
+ status = sctp_packet_transmit_chunk(packet, chunk, 0, ctx->gfp);
if (status != SCTP_XMIT_OK) {
/* We could not append this chunk, so put
* the chunk back on the output queue.
@@ -1138,7 +1131,7 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
__func__, ntohl(chunk->subh.data_hdr->tsn),
status);
- sctp_outq_head_data(q, chunk);
+ sctp_outq_head_data(ctx->q, chunk);
break;
}
@@ -1156,13 +1149,13 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
/* Only now it's safe to consider this
* chunk as sent, sched-wise.
*/
- sctp_sched_dequeue_done(q, chunk);
+ sctp_sched_dequeue_done(ctx->q, chunk);
list_add_tail(&chunk->transmitted_list,
- &transport->transmitted);
+ &ctx->transport->transmitted);
- sctp_transport_reset_t3_rtx(transport);
- transport->last_time_sent = jiffies;
+ sctp_transport_reset_t3_rtx(ctx->transport);
+ ctx->transport->last_time_sent = jiffies;
/* Only let one DATA chunk get bundled with a
* COOKIE-ECHO chunk.
@@ -1172,22 +1165,20 @@ static void sctp_outq_flush_data(struct sctp_outq *q,
}
}
-static void sctp_outq_flush_transports(struct sctp_outq *q,
- struct list_head *transport_list,
- gfp_t gfp)
+static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx)
{
struct list_head *ltransport;
struct sctp_packet *packet;
struct sctp_transport *t;
int error = 0;
- while ((ltransport = sctp_list_dequeue(transport_list)) != NULL) {
+ while ((ltransport = sctp_list_dequeue(&ctx->transport_list)) != NULL) {
t = list_entry(ltransport, struct sctp_transport, send_ready);
packet = &t->packet;
if (!sctp_packet_empty(packet)) {
- error = sctp_packet_transmit(packet, gfp);
+ error = sctp_packet_transmit(packet, ctx->gfp);
if (error < 0)
- q->asoc->base.sk->sk_err = -error;
+ ctx->q->asoc->base.sk->sk_err = -error;
}
/* Clear the burst limited state, if any */
@@ -1204,12 +1195,15 @@ static void sctp_outq_flush_transports(struct sctp_outq *q,
* locking concerns must be made. Today we use the sock lock to protect
* this function.
*/
+
static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
{
- /* Current transport being used. It's NOT the same as curr active one */
- struct sctp_transport *transport = NULL;
- /* These transports have chunks to send. */
- LIST_HEAD(transport_list);
+ struct sctp_flush_ctx ctx = {
+ .q = q,
+ .transport = NULL,
+ .transport_list = LIST_HEAD_INIT(ctx.transport_list),
+ .gfp = gfp,
+ };
/*
* 6.10 Bundling
@@ -1221,16 +1215,16 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
* ...
*/
- sctp_outq_flush_ctrl(q, &transport, &transport_list, gfp);
+ sctp_outq_flush_ctrl(&ctx);
if (q->asoc->src_out_of_asoc_ok)
goto sctp_flush_out;
- sctp_outq_flush_data(q, &transport, &transport_list, rtx_timeout, gfp);
+ sctp_outq_flush_data(&ctx, rtx_timeout);
sctp_flush_out:
- sctp_outq_flush_transports(q, &transport_list, gfp);
+ sctp_outq_flush_transports(&ctx);
}
/* Update unack_data based on the incoming SACK chunk */
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v2 2/3] sctp: add asoc and packet to sctp_flush_ctx
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142994.git.marcelo.leitner@gmail.com>
Pre-compute these so the compiler won't reload them (due to
no-strict-aliasing).
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 99 ++++++++++++++++++++++++-----------------------------
1 file changed, 45 insertions(+), 54 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index db94a2513dd874149aa77c4936f68537e97f8855..a594d181fa1178c34cf477e13d700f7b37e72e21 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -798,16 +798,17 @@ struct sctp_flush_ctx {
struct sctp_transport *transport;
/* These transports have chunks to send. */
struct list_head transport_list;
+ struct sctp_association *asoc;
+ /* Packet on the current transport above */
+ struct sctp_packet *packet;
gfp_t gfp;
};
/* transport: current transport */
-static bool sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
+static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
struct sctp_chunk *chunk)
{
struct sctp_transport *new_transport = chunk->transport;
- struct sctp_association *asoc = ctx->q->asoc;
- bool changed = false;
if (!new_transport) {
if (!sctp_chunk_is_data(chunk)) {
@@ -825,7 +826,7 @@ static bool sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
&ctx->transport->ipaddr))
new_transport = ctx->transport;
else
- new_transport = sctp_assoc_lookup_paddr(asoc,
+ new_transport = sctp_assoc_lookup_paddr(ctx->asoc,
&chunk->dest);
}
@@ -833,7 +834,7 @@ static bool sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
* use the current active path.
*/
if (!new_transport)
- new_transport = asoc->peer.active_path;
+ new_transport = ctx->asoc->peer.active_path;
} else {
__u8 type;
@@ -858,7 +859,7 @@ static bool sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
if (type != SCTP_CID_HEARTBEAT &&
type != SCTP_CID_HEARTBEAT_ACK &&
type != SCTP_CID_ASCONF_ACK)
- new_transport = asoc->peer.active_path;
+ new_transport = ctx->asoc->peer.active_path;
break;
default:
break;
@@ -867,27 +868,25 @@ static bool sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
/* Are we switching transports? Take care of transport locks. */
if (new_transport != ctx->transport) {
- changed = true;
ctx->transport = new_transport;
+ ctx->packet = &ctx->transport->packet;
+
if (list_empty(&ctx->transport->send_ready))
list_add_tail(&ctx->transport->send_ready,
&ctx->transport_list);
- sctp_packet_config(&ctx->transport->packet, asoc->peer.i.init_tag,
- asoc->peer.ecn_capable);
+ sctp_packet_config(ctx->packet,
+ ctx->asoc->peer.i.init_tag,
+ ctx->asoc->peer.ecn_capable);
/* We've switched transports, so apply the
* Burst limit to the new transport.
*/
sctp_transport_burst_limited(ctx->transport);
}
-
- return changed;
}
static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
{
- struct sctp_association *asoc = ctx->q->asoc;
- struct sctp_packet *packet = NULL;
struct sctp_chunk *chunk, *tmp;
enum sctp_xmit status;
int one_packet, error;
@@ -901,7 +900,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
* NOT use the new IP address as a source for ANY SCTP
* packet except on carrying an ASCONF Chunk.
*/
- if (asoc->src_out_of_asoc_ok &&
+ if (ctx->asoc->src_out_of_asoc_ok &&
chunk->chunk_hdr->type != SCTP_CID_ASCONF)
continue;
@@ -910,8 +909,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
/* Pick the right transport to use. Should always be true for
* the first chunk as we don't have a transport by then.
*/
- if (sctp_outq_select_transport(ctx, chunk))
- packet = &ctx->transport->packet;
+ sctp_outq_select_transport(ctx, chunk);
switch (chunk->chunk_hdr->type) {
/*
@@ -926,14 +924,14 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
error = sctp_packet_singleton(ctx->transport, chunk,
ctx->gfp);
if (error < 0) {
- asoc->base.sk->sk_err = -error;
+ ctx->asoc->base.sk->sk_err = -error;
return;
}
break;
case SCTP_CID_ABORT:
if (sctp_test_T_bit(chunk))
- packet->vtag = asoc->c.my_vtag;
+ ctx->packet->vtag = ctx->asoc->c.my_vtag;
/* fallthru */
/* The following chunks are "response" chunks, i.e.
@@ -959,7 +957,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
case SCTP_CID_FWD_TSN:
case SCTP_CID_I_FWD_TSN:
case SCTP_CID_RECONF:
- status = sctp_packet_transmit_chunk(packet, chunk,
+ status = sctp_packet_transmit_chunk(ctx->packet, chunk,
one_packet, ctx->gfp);
if (status != SCTP_XMIT_OK) {
/* put the chunk back */
@@ -967,7 +965,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
break;
}
- asoc->stats.octrlchunks++;
+ ctx->asoc->stats.octrlchunks++;
/* PR-SCTP C5) If a FORWARD TSN is sent, the
* sender MUST assure that at least one T3-rtx
* timer is running.
@@ -978,7 +976,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
ctx->transport->last_time_sent = jiffies;
}
- if (chunk == asoc->strreset_chunk)
+ if (chunk == ctx->asoc->strreset_chunk)
sctp_transport_reset_reconf_timer(ctx->transport);
break;
@@ -994,31 +992,28 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx,
int rtx_timeout)
{
- struct sctp_packet *packet = ctx->transport ? &ctx->transport->packet :
- NULL;
- struct sctp_association *asoc = ctx->q->asoc;
int error, start_timer = 0;
- if (asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
+ if (ctx->asoc->peer.retran_path->state == SCTP_UNCONFIRMED)
return false;
- if (ctx->transport != asoc->peer.retran_path) {
+ if (ctx->transport != ctx->asoc->peer.retran_path) {
/* Switch transports & prepare the packet. */
- ctx->transport = asoc->peer.retran_path;
+ ctx->transport = ctx->asoc->peer.retran_path;
+ ctx->packet = &ctx->transport->packet;
if (list_empty(&ctx->transport->send_ready))
list_add_tail(&ctx->transport->send_ready,
&ctx->transport_list);
- packet = &ctx->transport->packet;
- sctp_packet_config(packet, asoc->peer.i.init_tag,
- asoc->peer.ecn_capable);
+ sctp_packet_config(ctx->packet, ctx->asoc->peer.i.init_tag,
+ ctx->asoc->peer.ecn_capable);
}
- error = __sctp_outq_flush_rtx(ctx->q, packet, rtx_timeout, &start_timer,
- ctx->gfp);
+ error = __sctp_outq_flush_rtx(ctx->q, ctx->packet, rtx_timeout,
+ &start_timer, ctx->gfp);
if (error < 0)
- asoc->base.sk->sk_err = -error;
+ ctx->asoc->base.sk->sk_err = -error;
if (start_timer) {
sctp_transport_reset_t3_rtx(ctx->transport);
@@ -1028,7 +1023,7 @@ static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx,
/* This can happen on COOKIE-ECHO resend. Only
* one chunk can get bundled with a COOKIE-ECHO.
*/
- if (packet->has_cookie_echo)
+ if (ctx->packet->has_cookie_echo)
return false;
/* Don't send new data if there is still data
@@ -1043,20 +1038,17 @@ static bool sctp_outq_flush_rtx(struct sctp_flush_ctx *ctx,
static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
int rtx_timeout)
{
- struct sctp_packet *packet = ctx->transport ? &ctx->transport->packet :
- NULL;
- struct sctp_association *asoc = ctx->q->asoc;
struct sctp_chunk *chunk;
enum sctp_xmit status;
/* Is it OK to send data chunks? */
- switch (asoc->state) {
+ switch (ctx->asoc->state) {
case SCTP_STATE_COOKIE_ECHOED:
/* Only allow bundling when this packet has a COOKIE-ECHO
* chunk.
*/
- if (!packet || !packet->has_cookie_echo)
- return;
+ if (!ctx->packet || !ctx->packet->has_cookie_echo)
+ break;
/* fallthru */
case SCTP_STATE_ESTABLISHED:
@@ -1078,12 +1070,9 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
* are marked for retransmission (limited by the
* current cwnd).
*/
- if (!list_empty(&ctx->q->retransmit)) {
- if (!sctp_outq_flush_rtx(ctx, rtx_timeout))
- return;
- /* We may have switched current transport */
- packet = &ctx->transport->packet;
- }
+ if (!list_empty(&ctx->q->retransmit) &&
+ !sctp_outq_flush_rtx(ctx, rtx_timeout))
+ return;
/* Apply Max.Burst limitation to the current transport in
* case it will be used for new data. We are going to
@@ -1105,13 +1094,12 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
continue;
}
- if (asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
+ if (ctx->asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
sctp_outq_head_data(ctx->q, chunk);
break;
}
- if (sctp_outq_select_transport(ctx, chunk))
- packet = &ctx->transport->packet;
+ sctp_outq_select_transport(ctx, chunk);
pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
"skb->users:%d\n",
@@ -1122,7 +1110,8 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
refcount_read(&chunk->skb->users) : -1);
/* Add the chunk to the packet. */
- status = sctp_packet_transmit_chunk(packet, chunk, 0, ctx->gfp);
+ status = sctp_packet_transmit_chunk(ctx->packet, chunk, 0,
+ ctx->gfp);
if (status != SCTP_XMIT_OK) {
/* We could not append this chunk, so put
* the chunk back on the output queue.
@@ -1139,12 +1128,12 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
* The sender MAY set the I-bit in the DATA
* chunk header.
*/
- if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
+ if (ctx->asoc->state == SCTP_STATE_SHUTDOWN_PENDING)
chunk->chunk_hdr->flags |= SCTP_DATA_SACK_IMM;
if (chunk->chunk_hdr->flags & SCTP_DATA_UNORDERED)
- asoc->stats.ouodchunks++;
+ ctx->asoc->stats.ouodchunks++;
else
- asoc->stats.oodchunks++;
+ ctx->asoc->stats.oodchunks++;
/* Only now it's safe to consider this
* chunk as sent, sched-wise.
@@ -1160,7 +1149,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
/* Only let one DATA chunk get bundled with a
* COOKIE-ECHO chunk.
*/
- if (packet->has_cookie_echo)
+ if (ctx->packet->has_cookie_echo)
break;
}
}
@@ -1202,6 +1191,8 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
.q = q,
.transport = NULL,
.transport_list = LIST_HEAD_INIT(ctx.transport_list),
+ .asoc = q->asoc,
+ .packet = NULL,
.gfp = gfp,
};
--
2.14.3
^ permalink raw reply related
* [PATCH net-next v2 3/3] sctp: checkpatch fixups
From: Marcelo Ricardo Leitner @ 2018-05-12 22:21 UTC (permalink / raw)
To: netdev; +Cc: linux-sctp, Neil Horman, Vlad Yasevich, Xin Long
In-Reply-To: <cover.1526142994.git.marcelo.leitner@gmail.com>
A collection of fixups from previous patches, left for later to not
introduce unnecessary changes while moving code around.
Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
---
net/sctp/outqueue.c | 20 +++++++-------------
1 file changed, 7 insertions(+), 13 deletions(-)
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index a594d181fa1178c34cf477e13d700f7b37e72e21..9a2fa7d6d68b1d695cd745ed612eb32193f947e0 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -812,8 +812,7 @@ static void sctp_outq_select_transport(struct sctp_flush_ctx *ctx,
if (!new_transport) {
if (!sctp_chunk_is_data(chunk)) {
- /*
- * If we have a prior transport pointer, see if
+ /* If we have a prior transport pointer, see if
* the destination address of the chunk
* matches the destination address of the
* current transport. If not a match, then
@@ -912,8 +911,7 @@ static void sctp_outq_flush_ctrl(struct sctp_flush_ctx *ctx)
sctp_outq_select_transport(ctx, chunk);
switch (chunk->chunk_hdr->type) {
- /*
- * 6.10 Bundling
+ /* 6.10 Bundling
* ...
* An endpoint MUST NOT bundle INIT, INIT ACK or SHUTDOWN
* COMPLETE with any other chunks. [Send them immediately.]
@@ -1061,8 +1059,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
return;
}
- /*
- * RFC 2960 6.1 Transmission of DATA Chunks
+ /* RFC 2960 6.1 Transmission of DATA Chunks
*
* C) When the time comes for the sender to transmit,
* before sending new DATA chunks, the sender MUST
@@ -1101,8 +1098,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
sctp_outq_select_transport(ctx, chunk);
- pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p "
- "skb->users:%d\n",
+ pr_debug("%s: outq:%p, chunk:%p[%s], tx-tsn:0x%x skb->head:%p skb->users:%d\n",
__func__, ctx->q, chunk, chunk && chunk->chunk_hdr ?
sctp_cname(SCTP_ST_CHUNK(chunk->chunk_hdr->type)) :
"illegal chunk", ntohl(chunk->subh.data_hdr->tsn),
@@ -1175,8 +1171,7 @@ static void sctp_outq_flush_transports(struct sctp_flush_ctx *ctx)
}
}
-/*
- * Try to flush an outqueue.
+/* Try to flush an outqueue.
*
* Description: Send everything in q which we legally can, subject to
* congestion limitations.
@@ -1196,8 +1191,7 @@ static void sctp_outq_flush(struct sctp_outq *q, int rtx_timeout, gfp_t gfp)
.gfp = gfp,
};
- /*
- * 6.10 Bundling
+ /* 6.10 Bundling
* ...
* When bundling control chunks with DATA chunks, an
* endpoint MUST place control chunks first in the outbound
@@ -1768,7 +1762,7 @@ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn)
if (TSN_lte(tsn, ctsn))
goto pass;
- /* 3.3.4 Selective Acknowledgement (SACK) (3):
+ /* 3.3.4 Selective Acknowledgment (SACK) (3):
*
* Gap Ack Blocks:
* These fields contain the Gap Ack Blocks. They are repeated
--
2.14.3
^ permalink raw reply related
* Re: [PATCH bpf] tools: bpf: fix NULL return handling in bpf__prepare_load
From: Daniel Borkmann @ 2018-05-12 23:20 UTC (permalink / raw)
To: YueHaibing, alexander.shishkin, mingo, peterz; +Cc: netdev, namhyung, acme
In-Reply-To: <20180511112142.23324-1-yuehaibing@huawei.com>
[ +Arnaldo ]
On 05/11/2018 01:21 PM, YueHaibing wrote:
> bpf_object__open()/bpf_object__open_buffer can return error pointer or NULL,
> check the return values with IS_ERR_OR_NULL() in bpf__prepare_load and
> bpf__prepare_load_buffer
>
> Signed-off-by: YueHaibing <yuehaibing@huawei.com>
> ---
> tools/perf/util/bpf-loader.c | 6 +++---
> 1 file changed, 3 insertions(+), 3 deletions(-)
This should probably be routed via Arnaldo due to the fix in perf itself. If
there's no particular preference on which tree, we could potentially route it
as well via bpf with Acked-by from Arnaldo, but that is up to him. Arnaldo,
any preference?
> diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
> index af7ad81..cee6587 100644
> --- a/tools/perf/util/bpf-loader.c
> +++ b/tools/perf/util/bpf-loader.c
> @@ -66,7 +66,7 @@ bpf__prepare_load_buffer(void *obj_buf, size_t obj_buf_sz, const char *name)
> }
>
> obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, name);
> - if (IS_ERR(obj)) {
> + if (IS_ERR_OR_NULL(obj)) {
> pr_debug("bpf: failed to load buffer\n");
> return ERR_PTR(-EINVAL);
> }
> @@ -102,14 +102,14 @@ struct bpf_object *bpf__prepare_load(const char *filename, bool source)
> pr_debug("bpf: successfull builtin compilation\n");
> obj = bpf_object__open_buffer(obj_buf, obj_buf_sz, filename);
>
> - if (!IS_ERR(obj) && llvm_param.dump_obj)
> + if (!IS_ERR_OR_NULL(obj) && llvm_param.dump_obj)
> llvm__dump_obj(filename, obj_buf, obj_buf_sz);
>
> free(obj_buf);
> } else
> obj = bpf_object__open(filename);
>
> - if (IS_ERR(obj)) {
> + if (IS_ERR_OR_NULL(obj)) {
> pr_debug("bpf: failed to load %s\n", filename);
> return obj;
> }
>
^ permalink raw reply
* Re: [PATCH bpf-next 3/4] samples: bpf: fix build after move to compiling full libbpf.a
From: Daniel Borkmann @ 2018-05-12 23:22 UTC (permalink / raw)
To: Jakub Kicinski, alexei.starovoitov
Cc: oss-drivers, netdev, Björn Töpel
In-Reply-To: <20180512123757.7970f381@cakuba>
On 05/12/2018 09:38 PM, Jakub Kicinski wrote:
> On Fri, 11 May 2018 17:17:28 -0700, Jakub Kicinski wrote:
>> There are many ways users may compile samples, some of them got
>> broken by commit 5f9380572b4b ("samples: bpf: compile and link
>> against full libbpf"). Improve path resolution and make libbpf
>> building a dependency of source files to force its build.
>>
>> Samples should now again build with any of:
>> cd samples/bpf; make
>> make samples/bpf
>> make -C samples/bpf
>> cd samples/bpf; make O=builddir
>> make samples/bpf O=builddir
>> make -C samples/bpf O=builddir
>>
>> Fixes: 5f9380572b4b ("samples: bpf: compile and link against full libbpf")
>> Reported-by: Björn Töpel <bjorn.topel@gmail.com>
>> Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
>
> Unfortunately Björn reports this still doesn't fix the build for him.
> Investigating further.
Ok, thanks for letting us know.
^ permalink raw reply
* [PATCH ghak81 RFC V2 0/5] audit: group task params
From: Richard Guy Briggs @ 2018-05-13 1:58 UTC (permalink / raw)
To: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list
Cc: Eric Paris, Paul Moore, Steve Grubb, Ingo Molnar, David Howells,
Richard Guy Briggs
Group the audit parameters for each task into one structure.
In particular, remove the loginuid and sessionid values and the audit
context pointer from the task structure, replacing them with an audit
task information structure to contain them. Use access functions to
access audit values.
Note: Use static allocation of the audit task information structure
initially. Dynamic allocation was considered and attempted, but isn't
ready yet. Static allocation has the limitation that future audit task
information structure changes would cause a visible change to the rest
of the kernel, whereas dynamic allocation would mostly hide any future
changes.
The first four access normalization patches could stand alone.
Passes audit-testsuite.
Changelog:
v2
- p2/5: add audit header to init/init_task.c to quiet kbuildbot
- audit_signal_info(): fetch loginuid once
- remove task_struct from audit_context() param list
- remove extra task_struct local vars
- do nothing on request to set audit context when audit is disabled
Richard Guy Briggs (5):
audit: normalize loginuid read access
audit: convert sessionid unset to a macro
audit: use inline function to get audit context
audit: use inline function to set audit context
audit: collect audit task parameters
MAINTAINERS | 2 +-
include/linux/audit.h | 28 ++++++++---
include/linux/audit_task.h | 31 ++++++++++++
include/linux/sched.h | 6 +--
include/net/xfrm.h | 4 +-
include/uapi/linux/audit.h | 1 +
init/init_task.c | 8 ++-
kernel/audit.c | 6 +--
kernel/audit_watch.c | 2 +-
kernel/auditsc.c | 97 +++++++++++++++++-------------------
kernel/fork.c | 2 +-
net/bridge/netfilter/ebtables.c | 2 +-
net/core/dev.c | 2 +-
net/netfilter/x_tables.c | 2 +-
net/netlabel/netlabel_user.c | 2 +-
security/integrity/ima/ima_api.c | 2 +-
security/integrity/integrity_audit.c | 2 +-
security/lsm_audit.c | 2 +-
security/selinux/hooks.c | 4 +-
security/selinux/selinuxfs.c | 6 +--
security/selinux/ss/services.c | 12 ++---
21 files changed, 133 insertions(+), 90 deletions(-)
create mode 100644 include/linux/audit_task.h
--
1.8.3.1
^ permalink raw reply
* [PATCH ghak81 RFC V2 1/5] audit: normalize loginuid read access
From: Richard Guy Briggs @ 2018-05-13 1:58 UTC (permalink / raw)
To: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list
Cc: Eric Paris, Paul Moore, Steve Grubb, Ingo Molnar, David Howells,
Richard Guy Briggs
In-Reply-To: <cover.1526173613.git.rgb@redhat.com>
Recognizing that the loginuid is an internal audit value, use an access
function to retrieve the audit loginuid value for the task rather than
reaching directly into the task struct to get it.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
kernel/auditsc.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 479c031..0d4e269 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -374,7 +374,7 @@ static int audit_field_compare(struct task_struct *tsk,
case AUDIT_COMPARE_EGID_TO_OBJ_GID:
return audit_compare_gid(cred->egid, name, f, ctx);
case AUDIT_COMPARE_AUID_TO_OBJ_UID:
- return audit_compare_uid(tsk->loginuid, name, f, ctx);
+ return audit_compare_uid(audit_get_loginuid(tsk), name, f, ctx);
case AUDIT_COMPARE_SUID_TO_OBJ_UID:
return audit_compare_uid(cred->suid, name, f, ctx);
case AUDIT_COMPARE_SGID_TO_OBJ_GID:
@@ -385,7 +385,7 @@ static int audit_field_compare(struct task_struct *tsk,
return audit_compare_gid(cred->fsgid, name, f, ctx);
/* uid comparisons */
case AUDIT_COMPARE_UID_TO_AUID:
- return audit_uid_comparator(cred->uid, f->op, tsk->loginuid);
+ return audit_uid_comparator(cred->uid, f->op, audit_get_loginuid(tsk));
case AUDIT_COMPARE_UID_TO_EUID:
return audit_uid_comparator(cred->uid, f->op, cred->euid);
case AUDIT_COMPARE_UID_TO_SUID:
@@ -394,11 +394,11 @@ static int audit_field_compare(struct task_struct *tsk,
return audit_uid_comparator(cred->uid, f->op, cred->fsuid);
/* auid comparisons */
case AUDIT_COMPARE_AUID_TO_EUID:
- return audit_uid_comparator(tsk->loginuid, f->op, cred->euid);
+ return audit_uid_comparator(audit_get_loginuid(tsk), f->op, cred->euid);
case AUDIT_COMPARE_AUID_TO_SUID:
- return audit_uid_comparator(tsk->loginuid, f->op, cred->suid);
+ return audit_uid_comparator(audit_get_loginuid(tsk), f->op, cred->suid);
case AUDIT_COMPARE_AUID_TO_FSUID:
- return audit_uid_comparator(tsk->loginuid, f->op, cred->fsuid);
+ return audit_uid_comparator(audit_get_loginuid(tsk), f->op, cred->fsuid);
/* euid comparisons */
case AUDIT_COMPARE_EUID_TO_SUID:
return audit_uid_comparator(cred->euid, f->op, cred->suid);
@@ -611,7 +611,7 @@ static int audit_filter_rules(struct task_struct *tsk,
result = match_tree_refs(ctx, rule->tree);
break;
case AUDIT_LOGINUID:
- result = audit_uid_comparator(tsk->loginuid, f->op, f->uid);
+ result = audit_uid_comparator(audit_get_loginuid(tsk), f->op, f->uid);
break;
case AUDIT_LOGINUID_SET:
result = audit_comparator(audit_loginuid_set(tsk), f->op, f->val);
@@ -2281,14 +2281,14 @@ int audit_signal_info(int sig, struct task_struct *t)
struct audit_aux_data_pids *axp;
struct task_struct *tsk = current;
struct audit_context *ctx = tsk->audit_context;
- kuid_t uid = current_uid(), t_uid = task_uid(t);
+ kuid_t uid = current_uid(), auid, t_uid = task_uid(t);
if (auditd_test_task(t) &&
(sig == SIGTERM || sig == SIGHUP ||
sig == SIGUSR1 || sig == SIGUSR2)) {
audit_sig_pid = task_tgid_nr(tsk);
- if (uid_valid(tsk->loginuid))
- audit_sig_uid = tsk->loginuid;
+ if (uid_valid(auid = audit_get_loginuid(tsk)))
+ audit_sig_uid = auid;
else
audit_sig_uid = uid;
security_task_getsecid(tsk, &audit_sig_sid);
--
1.8.3.1
^ permalink raw reply related
* [PATCH ghak81 RFC V2 2/5] audit: convert sessionid unset to a macro
From: Richard Guy Briggs @ 2018-05-13 1:58 UTC (permalink / raw)
To: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list
Cc: Eric Paris, Paul Moore, Steve Grubb, Ingo Molnar, David Howells,
Richard Guy Briggs
In-Reply-To: <cover.1526173613.git.rgb@redhat.com>
Use a macro, "AUDIT_SID_UNSET", to replace each instance of
initialization and comparison to an audit session ID.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
include/linux/audit.h | 2 +-
include/net/xfrm.h | 2 +-
include/uapi/linux/audit.h | 1 +
init/init_task.c | 3 ++-
kernel/auditsc.c | 4 ++--
5 files changed, 7 insertions(+), 5 deletions(-)
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 75d5b03..5f86f7c 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -513,7 +513,7 @@ static inline kuid_t audit_get_loginuid(struct task_struct *tsk)
}
static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
{
- return -1;
+ return AUDIT_SID_UNSET;
}
static inline void audit_ipc_obj(struct kern_ipc_perm *ipcp)
{ }
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index a872379..fcce8ee 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -751,7 +751,7 @@ static inline void xfrm_audit_helper_usrinfo(bool task_valid,
audit_get_loginuid(current) :
INVALID_UID);
const unsigned int ses = task_valid ? audit_get_sessionid(current) :
- (unsigned int) -1;
+ AUDIT_SID_UNSET;
audit_log_format(audit_buf, " auid=%u ses=%u", auid, ses);
audit_log_task_context(audit_buf);
diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index 4e61a9e..04f9bd2 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -465,6 +465,7 @@ struct audit_tty_status {
};
#define AUDIT_UID_UNSET (unsigned int)-1
+#define AUDIT_SID_UNSET ((unsigned int)-1)
/* audit_rule_data supports filter rules with both integer and string
* fields. It corresponds with AUDIT_ADD_RULE, AUDIT_DEL_RULE and
diff --git a/init/init_task.c b/init/init_task.c
index 3ac6e75..74f60ba 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -9,6 +9,7 @@
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
+#include <linux/audit.h>
#include <asm/pgtable.h>
#include <linux/uaccess.h>
@@ -119,7 +120,7 @@ struct task_struct init_task
.thread_node = LIST_HEAD_INIT(init_signals.thread_head),
#ifdef CONFIG_AUDITSYSCALL
.loginuid = INVALID_UID,
- .sessionid = (unsigned int)-1,
+ .sessionid = AUDIT_SID_UNSET,
#endif
#ifdef CONFIG_PERF_EVENTS
.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 0d4e269..e157595 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2050,7 +2050,7 @@ static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid,
int audit_set_loginuid(kuid_t loginuid)
{
struct task_struct *task = current;
- unsigned int oldsessionid, sessionid = (unsigned int)-1;
+ unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET;
kuid_t oldloginuid;
int rc;
@@ -2064,7 +2064,7 @@ int audit_set_loginuid(kuid_t loginuid)
/* are we setting or clearing? */
if (uid_valid(loginuid)) {
sessionid = (unsigned int)atomic_inc_return(&session_id);
- if (unlikely(sessionid == (unsigned int)-1))
+ if (unlikely(sessionid == AUDIT_SID_UNSET))
sessionid = (unsigned int)atomic_inc_return(&session_id);
}
--
1.8.3.1
^ permalink raw reply related
* [PATCH ghak81 RFC V2 3/5] audit: use inline function to get audit context
From: Richard Guy Briggs @ 2018-05-13 1:58 UTC (permalink / raw)
To: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list
Cc: Richard Guy Briggs, David Howells, Ingo Molnar
In-Reply-To: <cover.1526173613.git.rgb@redhat.com>
Recognizing that the audit context is an internal audit value, use an
access function to retrieve the audit context pointer for the task
rather than reaching directly into the task struct to get it.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
include/linux/audit.h | 14 ++++++--
include/net/xfrm.h | 2 +-
kernel/audit.c | 6 ++--
kernel/audit_watch.c | 2 +-
kernel/auditsc.c | 64 +++++++++++++++++-------------------
net/bridge/netfilter/ebtables.c | 2 +-
net/core/dev.c | 2 +-
net/netfilter/x_tables.c | 2 +-
net/netlabel/netlabel_user.c | 2 +-
security/integrity/ima/ima_api.c | 2 +-
security/integrity/integrity_audit.c | 2 +-
security/lsm_audit.c | 2 +-
security/selinux/hooks.c | 4 +--
security/selinux/selinuxfs.c | 6 ++--
security/selinux/ss/services.c | 12 +++----
15 files changed, 64 insertions(+), 60 deletions(-)
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 5f86f7c..786aa8e 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -235,9 +235,13 @@ extern void __audit_inode_child(struct inode *parent,
extern void __audit_seccomp(unsigned long syscall, long signr, int code);
extern void __audit_ptrace(struct task_struct *t);
+static inline struct audit_context *audit_context(void)
+{
+ return current->audit_context;
+}
static inline bool audit_dummy_context(void)
{
- void *p = current->audit_context;
+ void *p = audit_context();
return !p || *(int *)p;
}
static inline void audit_free(struct task_struct *task)
@@ -249,12 +253,12 @@ static inline void audit_syscall_entry(int major, unsigned long a0,
unsigned long a1, unsigned long a2,
unsigned long a3)
{
- if (unlikely(current->audit_context))
+ if (unlikely(audit_context()))
__audit_syscall_entry(major, a0, a1, a2, a3);
}
static inline void audit_syscall_exit(void *pt_regs)
{
- if (unlikely(current->audit_context)) {
+ if (unlikely(audit_context())) {
int success = is_syscall_success(pt_regs);
long return_code = regs_return_value(pt_regs);
@@ -468,6 +472,10 @@ static inline bool audit_dummy_context(void)
{
return true;
}
+static inline struct audit_context *audit_context(void)
+{
+ return NULL;
+}
static inline struct filename *audit_reusename(const __user char *name)
{
return NULL;
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index fcce8ee..7f2e31a 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -736,7 +736,7 @@ static inline struct audit_buffer *xfrm_audit_start(const char *op)
if (audit_enabled == 0)
return NULL;
- audit_buf = audit_log_start(current->audit_context, GFP_ATOMIC,
+ audit_buf = audit_log_start(audit_context(), GFP_ATOMIC,
AUDIT_MAC_IPSEC_EVENT);
if (audit_buf == NULL)
return NULL;
diff --git a/kernel/audit.c b/kernel/audit.c
index e9f9a90..e7478cb 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1099,8 +1099,7 @@ static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature
if (audit_enabled == AUDIT_OFF)
return;
- ab = audit_log_start(current->audit_context,
- GFP_KERNEL, AUDIT_FEATURE_CHANGE);
+ ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE);
if (!ab)
return;
audit_log_task_info(ab, current);
@@ -2317,8 +2316,7 @@ void audit_log_link_denied(const char *operation)
return;
/* Generate AUDIT_ANOM_LINK with subject, operation, outcome. */
- ab = audit_log_start(current->audit_context, GFP_KERNEL,
- AUDIT_ANOM_LINK);
+ ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_LINK);
if (!ab)
return;
audit_log_format(ab, "op=%s", operation);
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 9eb8b35..f1ba889 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -274,7 +274,7 @@ static void audit_update_watch(struct audit_parent *parent,
/* If the update involves invalidating rules, do the inode-based
* filtering now, so we don't omit records. */
if (invalidating && !audit_dummy_context())
- audit_filter_inodes(current, current->audit_context);
+ audit_filter_inodes(current, audit_context());
/* updating ino will likely change which audit_hash_list we
* are on so we need a new watch for the new list */
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index e157595..ecc0c23 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1509,8 +1509,7 @@ void __audit_free(struct task_struct *tsk)
void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
unsigned long a3, unsigned long a4)
{
- struct task_struct *tsk = current;
- struct audit_context *context = tsk->audit_context;
+ struct audit_context *context = audit_context();
enum audit_state state;
if (!audit_enabled || !context)
@@ -1525,7 +1524,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
context->dummy = !audit_n_rules;
if (!context->dummy && state == AUDIT_BUILD_CONTEXT) {
context->prio = 0;
- if (auditd_test_task(tsk))
+ if (auditd_test_task(current))
return;
}
@@ -1563,12 +1562,12 @@ void __audit_syscall_exit(int success, long return_code)
else
success = AUDITSC_FAILURE;
- context = audit_take_context(tsk, success, return_code);
+ context = audit_take_context(current, success, return_code);
if (!context)
return;
if (context->in_syscall && context->current_state == AUDIT_RECORD_CONTEXT)
- audit_log_exit(context, tsk);
+ audit_log_exit(context, current);
context->in_syscall = 0;
context->prio = context->state == AUDIT_RECORD_CONTEXT ? ~0ULL : 0;
@@ -1602,7 +1601,7 @@ static inline void handle_one(const struct inode *inode)
int count;
if (likely(!inode->i_fsnotify_marks))
return;
- context = current->audit_context;
+ context = audit_context();
p = context->trees;
count = context->tree_count;
rcu_read_lock();
@@ -1633,7 +1632,7 @@ static void handle_path(const struct dentry *dentry)
unsigned long seq;
int count;
- context = current->audit_context;
+ context = audit_context();
p = context->trees;
count = context->tree_count;
retry:
@@ -1715,7 +1714,7 @@ static struct audit_names *audit_alloc_name(struct audit_context *context,
struct filename *
__audit_reusename(const __user char *uptr)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
struct audit_names *n;
list_for_each_entry(n, &context->names_list, list) {
@@ -1738,7 +1737,7 @@ struct filename *
*/
void __audit_getname(struct filename *name)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
struct audit_names *n;
if (!context->in_syscall)
@@ -1766,7 +1765,7 @@ void __audit_getname(struct filename *name)
void __audit_inode(struct filename *name, const struct dentry *dentry,
unsigned int flags)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
struct inode *inode = d_backing_inode(dentry);
struct audit_names *n;
bool parent = flags & AUDIT_INODE_PARENT;
@@ -1865,7 +1864,7 @@ void __audit_inode_child(struct inode *parent,
const struct dentry *dentry,
const unsigned char type)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
struct inode *inode = d_backing_inode(dentry);
const char *dname = dentry->d_name.name;
struct audit_names *n, *found_parent = NULL, *found_child = NULL;
@@ -2084,7 +2083,7 @@ int audit_set_loginuid(kuid_t loginuid)
*/
void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
if (attr)
memcpy(&context->mq_open.attr, attr, sizeof(struct mq_attr));
@@ -2108,7 +2107,7 @@ void __audit_mq_open(int oflag, umode_t mode, struct mq_attr *attr)
void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
const struct timespec64 *abs_timeout)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
struct timespec64 *p = &context->mq_sendrecv.abs_timeout;
if (abs_timeout)
@@ -2132,7 +2131,7 @@ void __audit_mq_sendrecv(mqd_t mqdes, size_t msg_len, unsigned int msg_prio,
void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
if (notification)
context->mq_notify.sigev_signo = notification->sigev_signo;
@@ -2151,7 +2150,7 @@ void __audit_mq_notify(mqd_t mqdes, const struct sigevent *notification)
*/
void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->mq_getsetattr.mqdes = mqdes;
context->mq_getsetattr.mqstat = *mqstat;
context->type = AUDIT_MQ_GETSETATTR;
@@ -2164,7 +2163,7 @@ void __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat)
*/
void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->ipc.uid = ipcp->uid;
context->ipc.gid = ipcp->gid;
context->ipc.mode = ipcp->mode;
@@ -2184,7 +2183,7 @@ void __audit_ipc_obj(struct kern_ipc_perm *ipcp)
*/
void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mode)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->ipc.qbytes = qbytes;
context->ipc.perm_uid = uid;
@@ -2195,7 +2194,7 @@ void __audit_ipc_set_perm(unsigned long qbytes, uid_t uid, gid_t gid, umode_t mo
void __audit_bprm(struct linux_binprm *bprm)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->type = AUDIT_EXECVE;
context->execve.argc = bprm->argc;
@@ -2210,7 +2209,7 @@ void __audit_bprm(struct linux_binprm *bprm)
*/
int __audit_socketcall(int nargs, unsigned long *args)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
if (nargs <= 0 || nargs > AUDITSC_ARGS || !args)
return -EINVAL;
@@ -2228,7 +2227,7 @@ int __audit_socketcall(int nargs, unsigned long *args)
*/
void __audit_fd_pair(int fd1, int fd2)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->fds[0] = fd1;
context->fds[1] = fd2;
}
@@ -2242,7 +2241,7 @@ void __audit_fd_pair(int fd1, int fd2)
*/
int __audit_sockaddr(int len, void *a)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
if (!context->sockaddr) {
void *p = kmalloc(sizeof(struct sockaddr_storage), GFP_KERNEL);
@@ -2258,7 +2257,7 @@ int __audit_sockaddr(int len, void *a)
void __audit_ptrace(struct task_struct *t)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->target_pid = task_tgid_nr(t);
context->target_auid = audit_get_loginuid(t);
@@ -2279,19 +2278,18 @@ void __audit_ptrace(struct task_struct *t)
int audit_signal_info(int sig, struct task_struct *t)
{
struct audit_aux_data_pids *axp;
- struct task_struct *tsk = current;
- struct audit_context *ctx = tsk->audit_context;
+ struct audit_context *ctx = audit_context();
kuid_t uid = current_uid(), auid, t_uid = task_uid(t);
if (auditd_test_task(t) &&
(sig == SIGTERM || sig == SIGHUP ||
sig == SIGUSR1 || sig == SIGUSR2)) {
- audit_sig_pid = task_tgid_nr(tsk);
- if (uid_valid(auid = audit_get_loginuid(tsk)))
+ audit_sig_pid = task_tgid_nr(current);
+ if (uid_valid(auid = audit_get_loginuid(current)))
audit_sig_uid = auid;
else
audit_sig_uid = uid;
- security_task_getsecid(tsk, &audit_sig_sid);
+ security_task_getsecid(current, &audit_sig_sid);
}
if (!audit_signals || audit_dummy_context())
@@ -2347,7 +2345,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
const struct cred *new, const struct cred *old)
{
struct audit_aux_data_bprm_fcaps *ax;
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
struct cpu_vfs_cap_data vcaps;
ax = kmalloc(sizeof(*ax), GFP_KERNEL);
@@ -2387,7 +2385,7 @@ int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
*/
void __audit_log_capset(const struct cred *new, const struct cred *old)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->capset.pid = task_tgid_nr(current);
context->capset.cap.effective = new->cap_effective;
context->capset.cap.inheritable = new->cap_effective;
@@ -2398,7 +2396,7 @@ void __audit_log_capset(const struct cred *new, const struct cred *old)
void __audit_mmap_fd(int fd, int flags)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->mmap.fd = fd;
context->mmap.flags = flags;
context->type = AUDIT_MMAP;
@@ -2406,7 +2404,7 @@ void __audit_mmap_fd(int fd, int flags)
void __audit_log_kern_module(char *name)
{
- struct audit_context *context = current->audit_context;
+ struct audit_context *context = audit_context();
context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL);
strcpy(context->module.name, name);
@@ -2415,7 +2413,7 @@ void __audit_log_kern_module(char *name)
void __audit_fanotify(unsigned int response)
{
- audit_log(current->audit_context, GFP_KERNEL,
+ audit_log(audit_context(), GFP_KERNEL,
AUDIT_FANOTIFY, "resp=%u", response);
}
@@ -2482,7 +2480,7 @@ void __audit_seccomp(unsigned long syscall, long signr, int code)
struct list_head *audit_killed_trees(void)
{
- struct audit_context *ctx = current->audit_context;
+ struct audit_context *ctx = audit_context();
if (likely(!ctx || !ctx->in_syscall))
return NULL;
return &ctx->killed_trees;
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index 032e0fe..894c96a 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -1062,7 +1062,7 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl,
#ifdef CONFIG_AUDIT
if (audit_enabled) {
- audit_log(current->audit_context, GFP_KERNEL,
+ audit_log(audit_context(), GFP_KERNEL,
AUDIT_NETFILTER_CFG,
"table=%s family=%u entries=%u",
repl->name, AF_BRIDGE, repl->nentries);
diff --git a/net/core/dev.c b/net/core/dev.c
index 969462e..5f38862 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6749,7 +6749,7 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc, bool notify)
dev->flags & IFF_PROMISC ? "entered" : "left");
if (audit_enabled) {
current_uid_gid(&uid, &gid);
- audit_log(current->audit_context, GFP_ATOMIC,
+ audit_log(audit_context(), GFP_ATOMIC,
AUDIT_ANOM_PROMISCUOUS,
"dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u",
dev->name, (dev->flags & IFF_PROMISC),
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 71325fe..1540263 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -1414,7 +1414,7 @@ struct xt_table_info *
#ifdef CONFIG_AUDIT
if (audit_enabled) {
- audit_log(current->audit_context, GFP_KERNEL,
+ audit_log(audit_context(), GFP_KERNEL,
AUDIT_NETFILTER_CFG,
"table=%s family=%u entries=%u",
table->name, table->af, private->number);
diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c
index 58495f4..2f328af 100644
--- a/net/netlabel/netlabel_user.c
+++ b/net/netlabel/netlabel_user.c
@@ -104,7 +104,7 @@ struct audit_buffer *netlbl_audit_start_common(int type,
if (audit_enabled == 0)
return NULL;
- audit_buf = audit_log_start(current->audit_context, GFP_ATOMIC, type);
+ audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, type);
if (audit_buf == NULL)
return NULL;
diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
index bf88236..a02c5ac 100644
--- a/security/integrity/ima/ima_api.c
+++ b/security/integrity/ima/ima_api.c
@@ -326,7 +326,7 @@ void ima_audit_measurement(struct integrity_iint_cache *iint,
hex_byte_pack(hash + (i * 2), iint->ima_hash->digest[i]);
hash[i * 2] = '\0';
- ab = audit_log_start(current->audit_context, GFP_KERNEL,
+ ab = audit_log_start(audit_context(), GFP_KERNEL,
AUDIT_INTEGRITY_RULE);
if (!ab)
goto out;
diff --git a/security/integrity/integrity_audit.c b/security/integrity/integrity_audit.c
index 90987d1..ab10a25 100644
--- a/security/integrity/integrity_audit.c
+++ b/security/integrity/integrity_audit.c
@@ -38,7 +38,7 @@ void integrity_audit_msg(int audit_msgno, struct inode *inode,
if (!integrity_audit_info && audit_info == 1) /* Skip info messages */
return;
- ab = audit_log_start(current->audit_context, GFP_KERNEL, audit_msgno);
+ ab = audit_log_start(audit_context(), GFP_KERNEL, audit_msgno);
audit_log_format(ab, "pid=%d uid=%u auid=%u ses=%u",
task_pid_nr(current),
from_kuid(&init_user_ns, current_cred()->uid),
diff --git a/security/lsm_audit.c b/security/lsm_audit.c
index 67703db..f840010 100644
--- a/security/lsm_audit.c
+++ b/security/lsm_audit.c
@@ -447,7 +447,7 @@ void common_lsm_audit(struct common_audit_data *a,
if (a == NULL)
return;
/* we use GFP_ATOMIC so we won't sleep */
- ab = audit_log_start(current->audit_context, GFP_ATOMIC | __GFP_NOWARN,
+ ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN,
AUDIT_AVC);
if (ab == NULL)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 4cafe6a..6dd582b 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3294,7 +3294,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
} else {
audit_size = 0;
}
- ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR);
+ ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR);
audit_log_format(ab, "op=setxattr invalid_context=");
audit_log_n_untrustedstring(ab, value, audit_size);
audit_log_end(ab);
@@ -6431,7 +6431,7 @@ static int selinux_setprocattr(const char *name, void *value, size_t size)
audit_size = size - 1;
else
audit_size = size;
- ab = audit_log_start(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR);
+ ab = audit_log_start(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR);
audit_log_format(ab, "op=fscreate invalid_context=");
audit_log_n_untrustedstring(ab, value, audit_size);
audit_log_end(ab);
diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index efdc633..b4c51d1 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -167,7 +167,7 @@ static ssize_t sel_write_enforce(struct file *file, const char __user *buf,
NULL);
if (length)
goto out;
- audit_log(current->audit_context, GFP_KERNEL, AUDIT_MAC_STATUS,
+ audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_STATUS,
"enforcing=%d old_enforcing=%d auid=%u ses=%u"
" enabled=%d old-enabled=%d lsm=selinux res=1",
new_value, old_value,
@@ -303,7 +303,7 @@ static ssize_t sel_write_disable(struct file *file, const char __user *buf,
length = selinux_disable(fsi->state);
if (length)
goto out;
- audit_log(current->audit_context, GFP_KERNEL, AUDIT_MAC_STATUS,
+ audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_STATUS,
"enforcing=%d old_enforcing=%d auid=%u ses=%u"
" enabled=%d old-enabled=%d lsm=selinux res=1",
enforcing, enforcing,
@@ -581,7 +581,7 @@ static ssize_t sel_write_load(struct file *file, const char __user *buf,
length = count;
out1:
- audit_log(current->audit_context, GFP_KERNEL, AUDIT_MAC_POLICY_LOAD,
+ audit_log(audit_context(), GFP_KERNEL, AUDIT_MAC_POLICY_LOAD,
"auid=%u ses=%u lsm=selinux res=1",
from_kuid(&init_user_ns, audit_get_loginuid(current)),
audit_get_sessionid(current));
diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index 8057e19..0fd8ad9 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -501,7 +501,7 @@ static void security_dump_masked_av(struct policydb *policydb,
goto out;
/* audit a message */
- ab = audit_log_start(current->audit_context,
+ ab = audit_log_start(audit_context(),
GFP_ATOMIC, AUDIT_SELINUX_ERR);
if (!ab)
goto out;
@@ -743,7 +743,7 @@ static int security_validtrans_handle_fail(struct selinux_state *state,
goto out;
if (context_struct_to_string(p, tcontext, &t, &tlen))
goto out;
- audit_log(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR,
+ audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR,
"op=security_validate_transition seresult=denied"
" oldcontext=%s newcontext=%s taskcontext=%s tclass=%s",
o, n, t, sym_name(p, SYM_CLASSES, tclass-1));
@@ -929,7 +929,7 @@ int security_bounded_transition(struct selinux_state *state,
&old_name, &length) &&
!context_struct_to_string(policydb, new_context,
&new_name, &length)) {
- audit_log(current->audit_context,
+ audit_log(audit_context(),
GFP_ATOMIC, AUDIT_SELINUX_ERR,
"op=security_bounded_transition "
"seresult=denied "
@@ -1586,7 +1586,7 @@ static int compute_sid_handle_invalid_context(
goto out;
if (context_struct_to_string(policydb, newcontext, &n, &nlen))
goto out;
- audit_log(current->audit_context, GFP_ATOMIC, AUDIT_SELINUX_ERR,
+ audit_log(audit_context(), GFP_ATOMIC, AUDIT_SELINUX_ERR,
"op=security_compute_sid invalid_context=%s"
" scontext=%s"
" tcontext=%s"
@@ -2882,7 +2882,7 @@ int security_set_bools(struct selinux_state *state, int len, int *values)
for (i = 0; i < len; i++) {
if (!!values[i] != policydb->bool_val_to_struct[i]->state) {
- audit_log(current->audit_context, GFP_ATOMIC,
+ audit_log(audit_context(), GFP_ATOMIC,
AUDIT_MAC_CONFIG_CHANGE,
"bool=%s val=%d old_val=%d auid=%u ses=%u",
sym_name(policydb, SYM_BOOLS, i),
@@ -3025,7 +3025,7 @@ int security_sid_mls_copy(struct selinux_state *state,
if (rc) {
if (!context_struct_to_string(policydb, &newcon, &s,
&len)) {
- audit_log(current->audit_context,
+ audit_log(audit_context(),
GFP_ATOMIC, AUDIT_SELINUX_ERR,
"op=security_sid_mls_copy "
"invalid_context=%s", s);
--
1.8.3.1
^ permalink raw reply related
* [PATCH ghak81 RFC V2 4/5] audit: use inline function to set audit context
From: Richard Guy Briggs @ 2018-05-13 1:58 UTC (permalink / raw)
To: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list
Cc: Eric Paris, Paul Moore, Steve Grubb, Ingo Molnar, David Howells,
Richard Guy Briggs
In-Reply-To: <cover.1526173613.git.rgb@redhat.com>
Recognizing that the audit context is an internal audit value, use an
access function to set the audit context pointer for the task
rather than reaching directly into the task struct to set it.
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
include/linux/audit.h | 6 ++++++
kernel/auditsc.c | 7 +++----
kernel/fork.c | 2 +-
3 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 786aa8e..f7973e4 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -235,6 +235,10 @@ extern void __audit_inode_child(struct inode *parent,
extern void __audit_seccomp(unsigned long syscall, long signr, int code);
extern void __audit_ptrace(struct task_struct *t);
+static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx)
+{
+ task->audit_context = ctx;
+}
static inline struct audit_context *audit_context(void)
{
return current->audit_context;
@@ -472,6 +476,8 @@ static inline bool audit_dummy_context(void)
{
return true;
}
+static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx)
+{ }
static inline struct audit_context *audit_context(void)
{
return NULL;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ecc0c23..d441d68 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -865,7 +865,7 @@ static inline struct audit_context *audit_take_context(struct task_struct *tsk,
audit_filter_inodes(tsk, context);
}
- tsk->audit_context = NULL;
+ audit_set_context(tsk, NULL);
return context;
}
@@ -952,7 +952,7 @@ int audit_alloc(struct task_struct *tsk)
}
context->filterkey = key;
- tsk->audit_context = context;
+ audit_set_context(tsk, context);
set_tsk_thread_flag(tsk, TIF_SYSCALL_AUDIT);
return 0;
}
@@ -1554,7 +1554,6 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
*/
void __audit_syscall_exit(int success, long return_code)
{
- struct task_struct *tsk = current;
struct audit_context *context;
if (success)
@@ -1589,7 +1588,7 @@ void __audit_syscall_exit(int success, long return_code)
kfree(context->filterkey);
context->filterkey = NULL;
}
- tsk->audit_context = context;
+ audit_set_context(current, context);
}
static inline void handle_one(const struct inode *inode)
diff --git a/kernel/fork.c b/kernel/fork.c
index 242c8c9..cd18448 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1713,7 +1713,7 @@ static __latent_entropy struct task_struct *copy_process(
p->start_time = ktime_get_ns();
p->real_start_time = ktime_get_boot_ns();
p->io_context = NULL;
- p->audit_context = NULL;
+ audit_set_context(p, NULL);
cgroup_fork(p);
#ifdef CONFIG_NUMA
p->mempolicy = mpol_dup(p->mempolicy);
--
1.8.3.1
^ permalink raw reply related
* [PATCH ghak81 RFC V2 5/5] audit: collect audit task parameters
From: Richard Guy Briggs @ 2018-05-13 1:58 UTC (permalink / raw)
To: Linux-Audit Mailing List, LKML,
Linux NetDev Upstream Mailing List, Netfilter Devel List,
Linux Security Module list, Integrity Measurement Architecture,
SElinux list
Cc: Eric Paris, Paul Moore, Steve Grubb, Ingo Molnar, David Howells,
Richard Guy Briggs
In-Reply-To: <cover.1526173613.git.rgb@redhat.com>
The audit-related parameters in struct task_struct should ideally be
collected together and accessed through a standard audit API.
Collect the existing loginuid, sessionid and audit_context together in a
new struct audit_task_info called "audit" in struct task_struct.
See: https://github.com/linux-audit/audit-kernel/issues/81
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
---
MAINTAINERS | 2 +-
include/linux/audit.h | 10 +++++-----
include/linux/audit_task.h | 31 +++++++++++++++++++++++++++++++
include/linux/sched.h | 6 ++----
init/init_task.c | 7 +++++--
kernel/auditsc.c | 6 +++---
6 files changed, 47 insertions(+), 15 deletions(-)
create mode 100644 include/linux/audit_task.h
diff --git a/MAINTAINERS b/MAINTAINERS
index 0a1410d..8c7992d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2510,7 +2510,7 @@ L: linux-audit@redhat.com (moderated for non-subscribers)
W: https://github.com/linux-audit
T: git git://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git
S: Supported
-F: include/linux/audit.h
+F: include/linux/audit*.h
F: include/uapi/linux/audit.h
F: kernel/audit*
diff --git a/include/linux/audit.h b/include/linux/audit.h
index f7973e4..6d599b6 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -237,11 +237,11 @@ extern void __audit_inode_child(struct inode *parent,
static inline void audit_set_context(struct task_struct *task, struct audit_context *ctx)
{
- task->audit_context = ctx;
+ task->audit.ctx = ctx;
}
static inline struct audit_context *audit_context(void)
{
- return current->audit_context;
+ return current->audit.ctx;
}
static inline bool audit_dummy_context(void)
{
@@ -250,7 +250,7 @@ static inline bool audit_dummy_context(void)
}
static inline void audit_free(struct task_struct *task)
{
- if (unlikely(task->audit_context))
+ if (unlikely(task->audit.ctx))
__audit_free(task);
}
static inline void audit_syscall_entry(int major, unsigned long a0,
@@ -330,12 +330,12 @@ extern int auditsc_get_stamp(struct audit_context *ctx,
static inline kuid_t audit_get_loginuid(struct task_struct *tsk)
{
- return tsk->loginuid;
+ return tsk->audit.loginuid;
}
static inline unsigned int audit_get_sessionid(struct task_struct *tsk)
{
- return tsk->sessionid;
+ return tsk->audit.sessionid;
}
extern void __audit_ipc_obj(struct kern_ipc_perm *ipcp);
diff --git a/include/linux/audit_task.h b/include/linux/audit_task.h
new file mode 100644
index 0000000..d4b3a20
--- /dev/null
+++ b/include/linux/audit_task.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* audit_task.h -- definition of audit_task_info structure
+ *
+ * Copyright 2018 Red Hat Inc., Raleigh, North Carolina.
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * Written by Richard Guy Briggs <rgb@redhat.com>
+ *
+ */
+
+#ifndef _LINUX_AUDIT_TASK_H_
+#define _LINUX_AUDIT_TASK_H_
+
+struct audit_context;
+struct audit_task_info {
+ kuid_t loginuid;
+ unsigned int sessionid;
+ struct audit_context *ctx;
+};
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b3d697f..b58eca0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -27,9 +27,9 @@
#include <linux/signal_types.h>
#include <linux/mm_types_task.h>
#include <linux/task_io_accounting.h>
+#include <linux/audit_task.h>
/* task_struct member predeclarations (sorted alphabetically): */
-struct audit_context;
struct backing_dev_info;
struct bio_list;
struct blk_plug;
@@ -832,10 +832,8 @@ struct task_struct {
struct callback_head *task_works;
- struct audit_context *audit_context;
#ifdef CONFIG_AUDITSYSCALL
- kuid_t loginuid;
- unsigned int sessionid;
+ struct audit_task_info audit;
#endif
struct seccomp seccomp;
diff --git a/init/init_task.c b/init/init_task.c
index 74f60ba..d33260d 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -119,8 +119,11 @@ struct task_struct init_task
.thread_group = LIST_HEAD_INIT(init_task.thread_group),
.thread_node = LIST_HEAD_INIT(init_signals.thread_head),
#ifdef CONFIG_AUDITSYSCALL
- .loginuid = INVALID_UID,
- .sessionid = AUDIT_SID_UNSET,
+ .audit = {
+ .loginuid = INVALID_UID,
+ .sessionid = AUDIT_SID_UNSET,
+ .ctx = NULL,
+ },
#endif
#ifdef CONFIG_PERF_EVENTS
.perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index d441d68..4c1fd18 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -836,7 +836,7 @@ static inline struct audit_context *audit_take_context(struct task_struct *tsk,
int return_valid,
long return_code)
{
- struct audit_context *context = tsk->audit_context;
+ struct audit_context *context = tsk->audit.ctx;
if (!context)
return NULL;
@@ -2066,8 +2066,8 @@ int audit_set_loginuid(kuid_t loginuid)
sessionid = (unsigned int)atomic_inc_return(&session_id);
}
- task->sessionid = sessionid;
- task->loginuid = loginuid;
+ task->audit.sessionid = sessionid;
+ task->audit.loginuid = loginuid;
out:
audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc);
return rc;
--
1.8.3.1
^ permalink raw reply related
* Re: [RFC] net: Add new LoRaWAN subsystem
From: Jian-Hong Pan @ 2018-05-13 2:42 UTC (permalink / raw)
To: Marcel Holtmann
Cc: David S. Miller, Alexander Aring, Stefan Schmidt, linux-wpan - ML,
netdev, linux-kernel
In-Reply-To: <677E6987-24AE-4D7C-9BF2-6BE3F43212C7@holtmann.org>
Hi Jiri and Marcel,
2018-05-11 23:39 GMT+08:00 Marcel Holtmann <marcel@holtmann.org>:
> Hi Jian-Hong,
>
>> A Low-Power Wide-Area Network (LPWAN) is a type of wireless
>> telecommunication wide area network designed to allow long range
>> communications at a low bit rate among things (connected objects), such
>> as sensors operated on a battery. It can be used widely in IoT area.
>> LoRaWAN, which is one kind of implementation of LPWAN, is a medium
>> access control (MAC) layer protocol for managing communication between
>> LPWAN gateways and end-node devices, maintained by the LoRa Alliance.
>> LoRaWAN™ Specification could be downloaded at:
>> https://lora-alliance.org/lorawan-for-developers
>>
>> However, LoRaWAN is not implemented in Linux kernel right now, so I am
>> trying to develop it. Here is my repository:
>> https://github.com/starnight/LoRa/tree/lorawan-ndo/LoRaWAN
>>
>> Because it is a kind of network, the ideal usage in an user space
>> program should be like "socket(PF_LORAWAN, SOCK_DGRAM, 0)" and with
>> other socket APIs. Therefore, the definitions like AF_LORAWAN,
>> PF_LORAWAN ..., must be listed in the header files of glibc.
>> For the driver in kernel space, the definitions also must be listed in
>> the corresponding Linux socket header files.
>> Especially, both are for the testing programs.
>>
>> Back to the mentioned "LoRaWAN is not implemented in Linux kernel now".
>> Could or should we add the definitions into corresponding kernel header
>> files now, if LoRaWAN will be accepted as a subsystem in Linux?
>
> when you submit your LoRaWAN subsystem to netdev for review, include a patch that adds these new address family definitions. Just pick the next one available. There will be no pre-allocation of numbers until your work has been accepted upstream. Meaning, that the number might change if other address families get merged before yours. So you have to keep updating. glibc will eventually follow the number assigned by the kernel.
Thanks for your guidance. I will follow the steps.
Thanks a lot,
Jian-Hong Pan
> Regards
>
> Marcel
>
^ permalink raw reply
* Re: BUG: unable to handle kernel paging request in cgroup_mt_destroy_v1
From: Eric Biggers @ 2018-05-13 6:50 UTC (permalink / raw)
To: syzbot
Cc: coreteam, davem, fw, kadlec, linux-kernel, netdev,
netfilter-devel, pablo, syzkaller-bugs
In-Reply-To: <f4f5e803bcb8f8c5e305641cecbe@google.com>
On Wed, Jan 31, 2018 at 05:58:01PM -0800, syzbot wrote:
> Hello,
>
> syzbot hit the following crash on upstream commit
> 3da90b159b146672f830bcd2489dd3a1f4e9e089 (Wed Jan 31 03:07:32 2018 +0000)
> Merge tag 'f2fs-for-4.16-rc1' of
> git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs
>
> So far this crash happened 3 times on net-next, upstream.
> C reproducer is attached.
> syzkaller reproducer is attached.
> Raw console output is attached.
> compiler: gcc (GCC) 7.1.1 20170620
> .config is attached.
>
> IMPORTANT: if you fix the bug, please add the following tag to the commit:
> Reported-by: syzbot+eeed2602160e4cc17410@syzkaller.appspotmail.com
> It will help syzbot understand when the bug is fixed. See footer for
> details.
> If you forward the report, please keep this part and the footer.
>
> audit: type=1400 audit(1517426494.787:7): avc: denied { map } for
> pid=4176 comm="syzkaller493328" path="/root/syzkaller493328633" dev="sda1"
> ino=16481 scontext=unconfined_u:system_r:insmod_t:s0-s0:c0.c1023
> tcontext=unconfined_u:object_r:user_home_t:s0 tclass=file permissive=1
> BUG: unable to handle kernel paging request at ffffffffffffff6d
> IP: css_put include/linux/cgroup.h:386 [inline]
> IP: cgroup_put include/linux/cgroup.h:415 [inline]
> IP: cgroup_mt_destroy_v1+0xe5/0x310 net/netfilter/xt_cgroup.c:102
> PGD 6a25067 P4D 6a25067 PUD 6a27067 PMD 0
> Oops: 0000 [#1] SMP KASAN
> Dumping ftrace buffer:
> (ftrace buffer empty)
> Modules linked in:
> CPU: 0 PID: 4176 Comm: syzkaller493328 Not tainted 4.15.0+ #288
> Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS
> Google 01/01/2011
> RIP: 0010:css_put include/linux/cgroup.h:386 [inline]
> RIP: 0010:cgroup_put include/linux/cgroup.h:415 [inline]
> RIP: 0010:cgroup_mt_destroy_v1+0xe5/0x310 net/netfilter/xt_cgroup.c:102
> RSP: 0018:ffff8801b19e7958 EFLAGS: 00010246
> RAX: 0000000000000008 RBX: 1ffff1003633cf2b RCX: ffffffff847188c6
> RDX: 0000000000000000 RSI: ffffffff8709b900 RDI: ffffffffffffff6d
> RBP: ffff8801b19e79e0 R08: 1ffff1003633cef9 R09: 0000000000000000
> R10: 0000000000000000 R11: 0000000000000000 R12: ffffffffffffff01
> R13: ffff8801b19e79b8 R14: dffffc0000000000 R15: ffffffff84718810
> FS: 0000000000c16880(0000) GS:ffff8801db400000(0000) knlGS:0000000000000000
> CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> CR2: ffffffffffffff6d CR3: 00000001b1f38004 CR4: 00000000001606f0
> DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
> Call Trace:
> cleanup_match+0x14e/0x220 net/ipv6/netfilter/ip6_tables.c:481
> cleanup_entry+0xcb/0x350 net/ipv4/netfilter/ip_tables.c:646
> __do_replace+0x7d7/0xa90 net/ipv4/netfilter/ip_tables.c:1091
> do_replace net/ipv4/netfilter/ip_tables.c:1147 [inline]
> do_ipt_set_ctl+0x40f/0x5f0 net/ipv4/netfilter/ip_tables.c:1677
> nf_sockopt net/netfilter/nf_sockopt.c:106 [inline]
> nf_setsockopt+0x67/0xc0 net/netfilter/nf_sockopt.c:115
> ip_setsockopt+0xa1/0xb0 net/ipv4/ip_sockglue.c:1256
> tcp_setsockopt+0x82/0xd0 net/ipv4/tcp.c:2875
> sock_common_setsockopt+0x95/0xd0 net/core/sock.c:2968
> SYSC_setsockopt net/socket.c:1831 [inline]
> SyS_setsockopt+0x189/0x360 net/socket.c:1810
> entry_SYSCALL_64_fastpath+0x29/0xa0
> RIP: 0033:0x4408a9
> RSP: 002b:00007ffddd061cc8 EFLAGS: 00000207 ORIG_RAX: 0000000000000036
> RAX: ffffffffffffffda RBX: ffffffffffffffff RCX: 00000000004408a9
> RDX: 0000000000000040 RSI: 0000000000000000 RDI: 0000000000000004
> RBP: faaff2414ccfc19e R08: 00000000000012f0 R09: 0000000000000000
> R10: 000000002000b000 R11: 0000000000000207 R12: 886f734548d4d66b
> R13: ffffffffffffff01 R14: 0000000000000000 R15: 0000000000000000
> Code: 6c 48 b8 00 00 00 00 00 fc ff df 48 89 fa 48 c1 ea 03 0f b6 14 02 48
> 89 f8 83 e0 07 83 c0 03 38 d0 7c 08 84 d2 0f 85 a6 01 00 00 <41> f6 44 24 6c
> 01 74 2e e8 be 06 ff fc 48 b8 00 00 00 00 00 fc
> RIP: css_put include/linux/cgroup.h:386 [inline] RSP: ffff8801b19e7958
> RIP: cgroup_put include/linux/cgroup.h:415 [inline] RSP: ffff8801b19e7958
> RIP: cgroup_mt_destroy_v1+0xe5/0x310 net/netfilter/xt_cgroup.c:102 RSP:
> ffff8801b19e7958
> CR2: ffffffffffffff6d
> ---[ end trace bfd8c145aa41ae03 ]---
>
>
> ---
> This bug is generated by a dumb bot. It may contain errors.
> See https://goo.gl/tpsmEJ for details.
> Direct all questions to syzkaller@googlegroups.com.
>
> syzbot will keep track of this bug report.
> If you forgot to add the Reported-by tag, once the fix for this bug is
> merged
> into any tree, please reply to this email with:
> #syz fix: exact-commit-title
This was fixed by commit ba7cd5d95f25cc6:
#syz fix: netfilter: xt_cgroup: initialize info->priv in cgroup_mt_check_v1()
- Eric
^ permalink raw reply
* Re: [Intel-wired-lan] [PATCH] e1000e: Ignore TSYNCRXCTL when getting I219 clock attributes
From: Neftin, Sasha @ 2018-05-13 6:55 UTC (permalink / raw)
To: Keller, Jacob E, Benjamin Poirier, Kirsher, Jeffrey T
Cc: ehabkost@redhat.com, netdev@vger.kernel.org, jayanth@goubiq.com,
linux-kernel@vger.kernel.org, postmodern.mod3@gmail.com,
Achim Mildenberger, intel-wired-lan@lists.osuosl.org,
Bart.VanAssche@wdc.com, olouvignes@gmail.com
In-Reply-To: <02874ECE860811409154E81DA85FBB5882DD85D3@ORSMSX115.amr.corp.intel.com>
On 5/10/2018 21:42, Keller, Jacob E wrote:
>> -----Original Message-----
>> From: Benjamin Poirier [mailto:bpoirier@suse.com]
>> Sent: Thursday, May 10, 2018 12:29 AM
>> To: Kirsher, Jeffrey T <jeffrey.t.kirsher@intel.com>
>> Cc: Keller, Jacob E <jacob.e.keller@intel.com>; Achim Mildenberger
>> <admin@fph.physik.uni-karlsruhe.de>; olouvignes@gmail.com;
>> jayanth@goubiq.com; ehabkost@redhat.com; postmodern.mod3@gmail.com;
>> Bart.VanAssche@wdc.com; intel-wired-lan@lists.osuosl.org;
>> netdev@vger.kernel.org; linux-kernel@vger.kernel.org
>> Subject: [PATCH] e1000e: Ignore TSYNCRXCTL when getting I219 clock attributes
>>
>> There have been multiple reports of crashes that look like
>> kernel: RIP: 0010:[<ffffffff8110303f>] timecounter_read+0xf/0x50
>> [...]
>> kernel: Call Trace:
>> kernel: [<ffffffffa0806b0f>] e1000e_phc_gettime+0x2f/0x60 [e1000e]
>> kernel: [<ffffffffa0806c5d>] e1000e_systim_overflow_work+0x1d/0x80 [e1000e]
>> kernel: [<ffffffff810992c5>] process_one_work+0x155/0x440
>> kernel: [<ffffffff81099e16>] worker_thread+0x116/0x4b0
>> kernel: [<ffffffff8109f422>] kthread+0xd2/0xf0
>> kernel: [<ffffffff8163184f>] ret_from_fork+0x3f/0x70
>>
>> These can be traced back to the fact that e1000e_systim_reset() skips the
>> timecounter_init() call if e1000e_get_base_timinca() returns -EINVAL, which
>> leads to a null deref in timecounter_read().
>>
>> Commit 83129b37ef35 ("e1000e: fix systim issues", v4.2-rc1) reworked
>> e1000e_get_base_timinca() in such a way that it can return -EINVAL for
>> e1000_pch_spt if the SYSCFI bit is not set in TSYNCRXCTL.
>>
>> Some experimentation has shown that on I219 (e1000_pch_spt, "MAC: 12")
>> adapters, the E1000_TSYNCRXCTL_SYSCFI flag is unstable; TSYNCRXCTL reads
>> sometimes don't have the SYSCFI bit set. Retrying the read shortly after
>> finds the bit to be set. This was observed at boot (probe) but also link up
>> and link down.
>>
>> Moreover, the phc (PTP Hardware Clock) seems to operate normally even after
>> reads where SYSCFI=0. Therefore, remove this register read and
>> unconditionally set the clock parameters.
>>
>> Reported-by: Achim Mildenberger <admin@fph.physik.uni-karlsruhe.de>
>> Message-Id: <20180425065243.g5mqewg5irkwgwgv@f2>
>> Bugzilla: https://bugzilla.suse.com/show_bug.cgi?id=1075876
>> Fixes: 83129b37ef35 ("e1000e: fix systim issues")
>> Signed-off-by: Benjamin Poirier <bpoirier@suse.com>
>> ---
>> drivers/net/ethernet/intel/e1000e/netdev.c | 15 ++++++---------
>> 1 file changed, 6 insertions(+), 9 deletions(-)
>>
>> diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c
>> b/drivers/net/ethernet/intel/e1000e/netdev.c
>> index ec4a9759a6f2..3afb1f3b6f91 100644
>> --- a/drivers/net/ethernet/intel/e1000e/netdev.c
>> +++ b/drivers/net/ethernet/intel/e1000e/netdev.c
>> @@ -3546,15 +3546,12 @@ s32 e1000e_get_base_timinca(struct e1000_adapter
>> *adapter, u32 *timinca)
>> }
>> break;
>> case e1000_pch_spt:
>> - if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
>> - /* Stable 24MHz frequency */
>> - incperiod = INCPERIOD_24MHZ;
>> - incvalue = INCVALUE_24MHZ;
>> - shift = INCVALUE_SHIFT_24MHZ;
>> - adapter->cc.shift = shift;
>> - break;
>> - }
>> - return -EINVAL;
>> + /* Stable 24MHz frequency */
>> + incperiod = INCPERIOD_24MHZ;
>> + incvalue = INCVALUE_24MHZ;
>> + shift = INCVALUE_SHIFT_24MHZ;
>> + adapter->cc.shift = shift;
>> + break;
>> case e1000_pch_cnp:
>> if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI) {
>> /* Stable 24MHz frequency */
>> --
>> 2.16.3
>
> Given testing showing that the clock operates fine regardless of the register read, I think this is probably fine. Normally I believe the register was used to check which frequency was in use, but it doesn't seem to serve that purpose here.
>
> Thanks,
> Jake
> _______________________________________________
> Intel-wired-lan mailing list
> Intel-wired-lan@osuosl.org
> https://lists.osuosl.org/mailman/listinfo/intel-wired-lan
>
I've checked our specification, looks only 24MHz used for this product.
Hope no different platform with another clock support has been
distributed. So, let's pick up this change.
^ permalink raw reply
* [PATCH v2] {net, IB}/mlx5: Use 'kvfree()' for memory allocated by 'kvzalloc()'
From: Christophe JAILLET @ 2018-05-13 7:00 UTC (permalink / raw)
To: saeedm, matanb, leon, dledford, jgg, davem
Cc: netdev, linux-rdma, linux-kernel, kernel-janitors,
Christophe JAILLET
When 'kvzalloc()' is used to allocate memory, 'kvfree()' must be used to
free it.
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
---
v1 -> v2: More places to update have been added to the patch
---
drivers/infiniband/hw/mlx5/cq.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c | 2 +-
drivers/net/ethernet/mellanox/mlx5/core/vport.c | 6 +++---
3 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index 77d257ec899b..6d52ea03574e 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -849,7 +849,7 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
return 0;
err_cqb:
- kfree(*cqb);
+ kvfree(*cqb);
err_db:
mlx5_ib_db_unmap_user(to_mucontext(context), &cq->db);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 35e256eb2f6e..b123f8a52ad8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -663,7 +663,7 @@ static int esw_create_vport_rx_group(struct mlx5_eswitch *esw)
esw->offloads.vport_rx_group = g;
out:
- kfree(flow_group_in);
+ kvfree(flow_group_in);
return err;
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 177e076b8d17..719cecb182c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -511,7 +511,7 @@ int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
*system_image_guid = MLX5_GET64(query_nic_vport_context_out, out,
nic_vport_context.system_image_guid);
- kfree(out);
+ kvfree(out);
return 0;
}
@@ -531,7 +531,7 @@ int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid)
*node_guid = MLX5_GET64(query_nic_vport_context_out, out,
nic_vport_context.node_guid);
- kfree(out);
+ kvfree(out);
return 0;
}
@@ -587,7 +587,7 @@ int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
*qkey_viol_cntr = MLX5_GET(query_nic_vport_context_out, out,
nic_vport_context.qkey_violation_counter);
- kfree(out);
+ kvfree(out);
return 0;
}
--
2.17.0
^ permalink raw reply related
* Re: [PATCH] net/mlx4_core: Fix error handling in mlx4_init_port_info.
From: Tariq Toukan @ 2018-05-13 7:02 UTC (permalink / raw)
To: Tarick Bedeir, gthelen, netdev, linux-rdma, linux-kernel
In-Reply-To: <7e5d6d30-ed89-8a8e-55c1-a25897937727@mellanox.com>
On 02/05/2018 4:31 PM, Tariq Toukan wrote:
>
>
> On 27/04/2018 6:20 PM, Tarick Bedeir wrote:
>> Avoid exiting the function with a lingering sysfs file (if the first
>> call to device_create_file() fails while the second succeeds), and avoid
>> calling devlink_port_unregister() twice.
>>
>> In other words, either mlx4_init_port_info() succeeds and returns
>> zero, or
>> it fails, returns non-zero, and requires no cleanup.
>>
>> Signed-off-by: Tarick Bedeir <tarick@google.com>
>> ---
>> drivers/net/ethernet/mellanox/mlx4/main.c | 4 +++-
>> 1 file changed, 3 insertions(+), 1 deletion(-)
>>
>> diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c
>> b/drivers/net/ethernet/mellanox/mlx4/main.c
>> index 4d84cab77105..e8a3a45d0b53 100644
>> --- a/drivers/net/ethernet/mellanox/mlx4/main.c
>> +++ b/drivers/net/ethernet/mellanox/mlx4/main.c
>> @@ -3007,6 +3007,7 @@ static int mlx4_init_port_info(struct mlx4_dev
>> *dev, int port)
>> mlx4_err(dev, "Failed to create file for port %d\n", port);
>> devlink_port_unregister(&info->devlink_port);
>> info->port = -1;
>> + return err;
>> }
>> sprintf(info->dev_mtu_name, "mlx4_port%d_mtu", port);
>> @@ -3028,9 +3029,10 @@ static int mlx4_init_port_info(struct mlx4_dev
>> *dev, int port)
>> &info->port_attr);
>> devlink_port_unregister(&info->devlink_port);
>> info->port = -1;
>> + return err;
>> }
>> - return err;
>> + return 0;
>> }
>> static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
>>
> Acked-by: Tariq Toukan <tariqt@mellanox.com>
>
> Thanks Tarick.
Actually, you need to add a Fixes line:
Fixes: 096335b3f983 ("mlx4_core: Allow dynamic MTU configuration for IB
ports")
^ permalink raw reply
* Re: [PATCH] dt-bindings: net: ravb: Add support for r8a77990 SoC
From: Simon Horman @ 2018-05-13 7:58 UTC (permalink / raw)
To: David Miller
Cc: yoshihiro.shimoda.uh, netdev, linux-renesas-soc, robh+dt,
mark.rutland, sergei.shtylyov, devicetree
In-Reply-To: <20180511.155942.16024095909155343.davem@davemloft.net>
On Fri, May 11, 2018 at 03:59:42PM -0400, David Miller wrote:
> From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
> Date: Fri, 11 May 2018 12:18:56 +0900
>
> > Add documentation for r8a77990 compatible string to renesas ravb device
> > tree bindings documentation.
> >
> > Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
>
> I'm assuming this isn't targetted at one of my trees. Just FYI.
Hi Dave,
I think this is appropriate for net-next but if not I can take it.
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Shimoda-san,
please use "[PATCH net-next]" for non-bugfix networking updates which
are targeted at Dave's net-next tree. Bug fixes should be for "net".
Patches should of course apply cleanly to whichever tree it is targeted at.
^ permalink raw reply
* Re: [PATCH V2] mlx4_core: allocate ICM memory in page size chunks
From: Tariq Toukan @ 2018-05-13 9:00 UTC (permalink / raw)
To: Qing Huang, tariqt, davem, haakon.bugge, yanjun.zhu
Cc: netdev, linux-rdma, linux-kernel
In-Reply-To: <20180511192318.22342-1-qing.huang@oracle.com>
On 11/05/2018 10:23 PM, Qing Huang wrote:
> When a system is under memory presure (high usage with fragments),
> the original 256KB ICM chunk allocations will likely trigger kernel
> memory management to enter slow path doing memory compact/migration
> ops in order to complete high order memory allocations.
>
> When that happens, user processes calling uverb APIs may get stuck
> for more than 120s easily even though there are a lot of free pages
> in smaller chunks available in the system.
>
> Syslog:
> ...
> Dec 10 09:04:51 slcc03db02 kernel: [397078.572732] INFO: task
> oracle_205573_e:205573 blocked for more than 120 seconds.
> ...
>
> With 4KB ICM chunk size on x86_64 arch, the above issue is fixed.
>
> However in order to support smaller ICM chunk size, we need to fix
> another issue in large size kcalloc allocations.
>
> E.g.
> Setting log_num_mtt=30 requires 1G mtt entries. With the 4KB ICM chunk
> size, each ICM chunk can only hold 512 mtt entries (8 bytes for each mtt
> entry). So we need a 16MB allocation for a table->icm pointer array to
> hold 2M pointers which can easily cause kcalloc to fail.
>
> The solution is to use vzalloc to replace kcalloc. There is no need
> for contiguous memory pages for a driver meta data structure (no need
> of DMA ops).
>
> Signed-off-by: Qing Huang <qing.huang@oracle.com>
> Acked-by: Daniel Jurgens <danielj@mellanox.com>
> Reviewed-by: Zhu Yanjun <yanjun.zhu@oracle.com>
> ---
> v2 -> v1: adjusted chunk size to reflect different architectures.
>
> drivers/net/ethernet/mellanox/mlx4/icm.c | 14 +++++++-------
> 1 file changed, 7 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx4/icm.c b/drivers/net/ethernet/mellanox/mlx4/icm.c
> index a822f7a..ccb62b8 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/icm.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/icm.c
> @@ -43,12 +43,12 @@
> #include "fw.h"
>
> /*
> - * We allocate in as big chunks as we can, up to a maximum of 256 KB
> - * per chunk.
> + * We allocate in page size (default 4KB on many archs) chunks to avoid high
> + * order memory allocations in fragmented/high usage memory situation.
> */
> enum {
> - MLX4_ICM_ALLOC_SIZE = 1 << 18,
> - MLX4_TABLE_CHUNK_SIZE = 1 << 18
> + MLX4_ICM_ALLOC_SIZE = 1 << PAGE_SHIFT,
> + MLX4_TABLE_CHUNK_SIZE = 1 << PAGE_SHIFT
Which is actually PAGE_SIZE.
Also, please add a comma at the end of the last entry.
> };
>
> static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
> @@ -400,7 +400,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
> obj_per_chunk = MLX4_TABLE_CHUNK_SIZE / obj_size;
> num_icm = (nobj + obj_per_chunk - 1) / obj_per_chunk;
>
> - table->icm = kcalloc(num_icm, sizeof(*table->icm), GFP_KERNEL);
> + table->icm = vzalloc(num_icm * sizeof(*table->icm));
Why not kvzalloc ?
> if (!table->icm)
> return -ENOMEM;
> table->virt = virt;
> @@ -446,7 +446,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
> mlx4_free_icm(dev, table->icm[i], use_coherent);
> }
>
> - kfree(table->icm);
> + vfree(table->icm);
>
> return -ENOMEM;
> }
> @@ -462,5 +462,5 @@ void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table)
> mlx4_free_icm(dev, table->icm[i], table->coherent);
> }
>
> - kfree(table->icm);
> + vfree(table->icm);
> }
>
Thanks for your patch.
I need to verify there is no dramatic performance degradation here.
You can prepare and send a v3 in the meanwhile.
Thanks,
Tariq
^ permalink raw reply
* [RFC PATCH] net: Remove a confusing comment of macro SIOCDEVPRIVATE
From: Jian-Hong Pan @ 2018-05-13 9:54 UTC (permalink / raw)
To: Philippe Ombredanne, Greg Kroah-Hartman, Thomas Gleixner,
Kate Stewart, David S. Miller, netdev, linux-kernel
Cc: Jian-Hong Pan
I have been reading the NET related header files recently. I found
there is a macro "#define SIOCDEVPRIVATE 0x89F0" defined in
include/uapi/linux/sockios.h which is useful for private controls of net
devices. When I read this section:
/* Device private ioctl calls */
/*
* These 16 ioctls are available to devices via the do_ioctl() device
* vector. Each device should include this file and redefine these names
* as their own. Because these are device dependent it is a good idea
* _NOT_ to issue them to random objects and hope.
*
* THESE IOCTLS ARE _DEPRECATED_ AND WILL DISAPPEAR IN 2.5.X -DaveM
*/
I notice there is a string in the comment:
"THESE IOCTLS ARE _DEPRECATED_ AND WILL DISAPPEAR IN 2.5.X -DaveM"
which makes me confused. Because, there are still a lot of devices or
subsystems using this macro, for example, ethernet, appletalk,
usb/rtl8150 ..., etc.
Therefore, I make this patch to remove the confusing comment.
Signed-off-by: Jian-Hong Pan <starnight@g.ncu.edu.tw>
---
include/uapi/linux/sockios.h | 2 --
1 file changed, 2 deletions(-)
diff --git a/include/uapi/linux/sockios.h b/include/uapi/linux/sockios.h
index d393e9ed3964..c166f8c6b20f 100644
--- a/include/uapi/linux/sockios.h
+++ b/include/uapi/linux/sockios.h
@@ -139,8 +139,6 @@
* vector. Each device should include this file and redefine these names
* as their own. Because these are device dependent it is a good idea
* _NOT_ to issue them to random objects and hope.
- *
- * THESE IOCTLS ARE _DEPRECATED_ AND WILL DISAPPEAR IN 2.5.X -DaveM
*/
#define SIOCDEVPRIVATE 0x89F0 /* to 89FF */
--
2.17.0
^ permalink raw reply related
* Kernel panic on kernel-3.10.0-693.21.1.el7 in ndisc.h
From: Roman Makhov @ 2018-05-13 11:35 UTC (permalink / raw)
To: linux-wpan, netdev
Hello,
We have a problem with Kernel panic after upgrade from CentOS 7.3
(kernel-3.10.0-514.el7) to CentOS 7.4 (kernel-3.10.0-693.21.1.el7).
It occurs when we have the incoming traffic from other nodes and we
are performing the re-configuration of IPv6 interfaces.
It is high-availability system without 802.15.4 support.
The log of crash:
=========================================================
#10 [ffff88043fc03cf0] async_page_fault at ffffffff816b7798
[exception RIP: ndisc_send_rs+238]
RIP: ffffffff8166575e RSP: ffff88043fc03da8 RFLAGS: 00010202
RAX: 0000000000000002 RBX: ffff88042caa9000 RCX: 0000000000000001
RDX: 0000000000000000 RSI: 0000000000000200 RDI: ffffffff816534f7
RBP: ffff88043fc03dd0 R8: 0000000000000000 R9: ffffffff81e9f1c0
R10: 0000000000000002 R11: ffff88043fc03da8 R12: 0000000000000008
R13: 0000000000000006 R14: ffff88043fc03de0 R15: ffffffff81772410
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#11 [ffff88043fc03da0] ndisc_send_rs at ffffffff81665704
=========================================================
I see that crash points on ndisc.h, it is ndisc_ops_opt_addr_space()
in function:
=========================================================
crash> kmem ffffffff8166575e
ffffffff8166575e (T) ndisc_send_rs+238
/usr/src/debug/kernel-3.10.0-693.21.1.el7/linux-3.10.0-693.21.1.el7.x86_64/include/net/ndisc.h:
251
PAGE PHYSICAL MAPPING INDEX CNT FLAGS
ffffea0000059940 1665000 0 0 1 1fffff00000400 reserved
crash>
=========================================================
I checked the difference between 514 and 693 kernels is in the patch
https://patchwork.kernel.org/patch/9179229/ .
Any suggesions about what I am doing wrong are welcome.
Thanks!
Roman Makhov
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox