Merge branch 'strparser'

Tom Herbert says:

====================
strp: Stream parser for messages

This patch set introduces a utility for parsing application layer
protocol messages in a TCP stream. This is a generalization of the
mechanism implemented of Kernel Connection Multiplexor.

This patch set adapts KCM to use the strparser. We expect that kTLS
can use this mechanism also. RDS would probably be another candidate
to use a common stream parsing mechanism.

The API includes a context structure, a set of callbacks, utility
functions, and a data ready function. The callbacks include
a parse_msg function that is called to perform parsing (e.g.
BPF parsing in case of KCM), and a rcv_msg function that is called
when a full message has been completed.

For strparser we specify the return codes from the parser to allow
the backend to indicate that control of the socket should be
transferred back to userspace to handle some exceptions in the
stream: The return values are:

      >0 : indicates length of successfully parsed message
       0  : indicates more data must be received to parse the message
       -ESTRPIPE : current message should not be processed by the
          kernel, return control of the socket to userspace which
          can proceed to read the messages itself
       other < 0 : Error is parsing, give control back to userspace
          assuming that synchronization is lost and the stream
          is unrecoverable (application expected to close TCP socket)

There is one issue I haven't been able to fully resolve. If parse_msg
returns ESTRPIPE (wants control back to userspace) the parser may
already have consumed some bytes of the message. There is no way to
put bytes back into the TCP receive queue and tcp_read_sock does not
allow an easy way to peek messages. In lieu of a better solution, we
return ENODATA on the socket to indicate that the data stream is
unrecoverable (application needs to close socket). This condition
should only happen if an application layer message header is split
across two skbuffs and parsing just the first skbuff wasn't sufficient
to determine the that transfer to userspace is needed.

This patch set contains:

  - strparser implementation
  - changes to kcm to use strparser
  - strparser.txt documentation

v2:
  - Add copyright notice to C files
  - Remove GPL module license from strparser.c
  - Add report of rxpause

v3:
  - Restore GPL module license
  - Use EXPORT_SYMBOL_GPL

v4:
  - Removed unused function, changed another to be static as suggested
    by davem
  - Rewoked data_ready to be called from upper layer, no longer requires
    taking over socket data_ready callback as suggested by Lance Chao

Tested:
  - Ran a KCM thrash test for 24 hours. No behavioral or performance
    differences observed.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 151 insertions, 31 deletions

diff --git a/include/net/kcm.h b/include/net/kcm.h
index 2840b5825dcc..2a8965819db0 100644
--- a/include/net/kcm.h
+++ b/include/net/kcm.h
@@ -13,6 +13,7 @@
 
 #include <linux/skbuff.h>
 #include <net/sock.h>
+#include <net/strparser.h>
 #include <uapi/linux/kcm.h>
 
 extern unsigned int kcm_net_id;
@@ -21,16 +22,8 @@ extern unsigned int kcm_net_id;
 #define KCM_STATS_INCR(stat) ((stat)++)
 
 struct kcm_psock_stats {
-	unsigned long long rx_msgs;
-	unsigned long long rx_bytes;
 	unsigned long long tx_msgs;
 	unsigned long long tx_bytes;
-	unsigned int rx_aborts;
-	unsigned int rx_mem_fail;
-	unsigned int rx_need_more_hdr;
-	unsigned int rx_msg_too_big;
-	unsigned int rx_msg_timeouts;
-	unsigned int rx_bad_hdr_len;
 	unsigned long long reserved;
 	unsigned long long unreserved;
 	unsigned int tx_aborts;
@@ -64,13 +57,6 @@ struct kcm_tx_msg {
 	struct sk_buff *last_skb;
 };
 
-struct kcm_rx_msg {
-	int full_len;
-	int accum_len;
-	int offset;
-	int early_eaten;
-};
-
 /* Socket structure for KCM client sockets */
 struct kcm_sock {
 	struct sock sk;
@@ -87,6 +73,7 @@ struct kcm_sock {
 	struct work_struct tx_work;
 	struct list_head wait_psock_list;
 	struct sk_buff *seq_skb;
+	u32 tx_stopped : 1;
 
 	/* Don't use bit fields here, these are set under different locks */
 	bool tx_wait;
@@ -104,11 +91,11 @@ struct bpf_prog;
 /* Structure for an attached lower socket */
 struct kcm_psock {
 	struct sock *sk;
+	struct strparser strp;
 	struct kcm_mux *mux;
 	int index;
 
 	u32 tx_stopped : 1;
-	u32 rx_stopped : 1;
 	u32 done : 1;
 	u32 unattaching : 1;
 
@@ -121,18 +108,12 @@ struct kcm_psock {
 	struct kcm_psock_stats stats;
 
 	/* Receive */
-	struct sk_buff *rx_skb_head;
-	struct sk_buff **rx_skb_nextp;
-	struct sk_buff *ready_rx_msg;
 	struct list_head psock_ready_list;
-	struct work_struct rx_work;
-	struct delayed_work rx_delayed_work;
 	struct bpf_prog *bpf_prog;
 	struct kcm_sock *rx_kcm;
 	unsigned long long saved_rx_bytes;
 	unsigned long long saved_rx_msgs;
-	struct timer_list rx_msg_timer;
-	unsigned int rx_need_bytes;
+	struct sk_buff *ready_rx_msg;
 
 	/* Transmit */
 	struct kcm_sock *tx_kcm;
@@ -146,6 +127,7 @@ struct kcm_net {
 	struct mutex mutex;
 	struct kcm_psock_stats aggregate_psock_stats;
 	struct kcm_mux_stats aggregate_mux_stats;
+	struct strp_aggr_stats aggregate_strp_stats;
 	struct list_head mux_list;
 	int count;
 };
@@ -163,6 +145,7 @@ struct kcm_mux {
 
 	struct kcm_mux_stats stats;
 	struct kcm_psock_stats aggregate_psock_stats;
+	struct strp_aggr_stats aggregate_strp_stats;
 
 	/* Receive */
 	spinlock_t rx_lock ____cacheline_aligned_in_smp;
@@ -190,14 +173,6 @@ static inline void aggregate_psock_stats(struct kcm_psock_stats *stats,
 	/* Save psock statistics in the mux when psock is being unattached. */
 
 #define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
-	SAVE_PSOCK_STATS(rx_msgs);
-	SAVE_PSOCK_STATS(rx_bytes);
-	SAVE_PSOCK_STATS(rx_aborts);
-	SAVE_PSOCK_STATS(rx_mem_fail);
-	SAVE_PSOCK_STATS(rx_need_more_hdr);
-	SAVE_PSOCK_STATS(rx_msg_too_big);
-	SAVE_PSOCK_STATS(rx_msg_timeouts);
-	SAVE_PSOCK_STATS(rx_bad_hdr_len);
 	SAVE_PSOCK_STATS(tx_msgs);
 	SAVE_PSOCK_STATS(tx_bytes);
 	SAVE_PSOCK_STATS(reserved);
diff --git a/include/net/strparser.h b/include/net/strparser.h
new file mode 100644
index 000000000000..fdb3d6746cc4
--- /dev/null
+++ b/include/net/strparser.h
@@ -0,0 +1,145 @@
+/*
+ * Stream Parser
+ *
+ * Copyright (c) 2016 Tom Herbert <tom@herbertland.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef __NET_STRPARSER_H_
+#define __NET_STRPARSER_H_
+
+#include <linux/skbuff.h>
+#include <net/sock.h>
+
+#define STRP_STATS_ADD(stat, count) ((stat) += (count))
+#define STRP_STATS_INCR(stat) ((stat)++)
+
+struct strp_stats {
+	unsigned long long rx_msgs;
+	unsigned long long rx_bytes;
+	unsigned int rx_mem_fail;
+	unsigned int rx_need_more_hdr;
+	unsigned int rx_msg_too_big;
+	unsigned int rx_msg_timeouts;
+	unsigned int rx_bad_hdr_len;
+};
+
+struct strp_aggr_stats {
+	unsigned long long rx_msgs;
+	unsigned long long rx_bytes;
+	unsigned int rx_mem_fail;
+	unsigned int rx_need_more_hdr;
+	unsigned int rx_msg_too_big;
+	unsigned int rx_msg_timeouts;
+	unsigned int rx_bad_hdr_len;
+	unsigned int rx_aborts;
+	unsigned int rx_interrupted;
+	unsigned int rx_unrecov_intr;
+};
+
+struct strparser;
+
+/* Callbacks are called with lock held for the attached socket */
+struct strp_callbacks {
+	int (*parse_msg)(struct strparser *strp, struct sk_buff *skb);
+	void (*rcv_msg)(struct strparser *strp, struct sk_buff *skb);
+	int (*read_sock_done)(struct strparser *strp, int err);
+	void (*abort_parser)(struct strparser *strp, int err);
+};
+
+struct strp_rx_msg {
+	int full_len;
+	int offset;
+};
+
+static inline struct strp_rx_msg *strp_rx_msg(struct sk_buff *skb)
+{
+	return (struct strp_rx_msg *)((void *)skb->cb +
+		offsetof(struct qdisc_skb_cb, data));
+}
+
+/* Structure for an attached lower socket */
+struct strparser {
+	struct sock *sk;
+
+	u32 rx_stopped : 1;
+	u32 rx_paused : 1;
+	u32 rx_aborted : 1;
+	u32 rx_interrupted : 1;
+	u32 rx_unrecov_intr : 1;
+
+	struct sk_buff **rx_skb_nextp;
+	struct timer_list rx_msg_timer;
+	struct sk_buff *rx_skb_head;
+	unsigned int rx_need_bytes;
+	struct delayed_work rx_delayed_work;
+	struct work_struct rx_work;
+	struct strp_stats stats;
+	struct strp_callbacks cb;
+};
+
+/* Must be called with lock held for attached socket */
+static inline void strp_pause(struct strparser *strp)
+{
+	strp->rx_paused = 1;
+}
+
+/* May be called without holding lock for attached socket */
+static inline void strp_unpause(struct strparser *strp)
+{
+	strp->rx_paused = 0;
+}
+
+static inline void save_strp_stats(struct strparser *strp,
+				   struct strp_aggr_stats *agg_stats)
+{
+	/* Save psock statistics in the mux when psock is being unattached. */
+
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat +=		\
+				 strp->stats._stat)
+	SAVE_PSOCK_STATS(rx_msgs);
+	SAVE_PSOCK_STATS(rx_bytes);
+	SAVE_PSOCK_STATS(rx_mem_fail);
+	SAVE_PSOCK_STATS(rx_need_more_hdr);
+	SAVE_PSOCK_STATS(rx_msg_too_big);
+	SAVE_PSOCK_STATS(rx_msg_timeouts);
+	SAVE_PSOCK_STATS(rx_bad_hdr_len);
+#undef SAVE_PSOCK_STATS
+
+	if (strp->rx_aborted)
+		agg_stats->rx_aborts++;
+	if (strp->rx_interrupted)
+		agg_stats->rx_interrupted++;
+	if (strp->rx_unrecov_intr)
+		agg_stats->rx_unrecov_intr++;
+}
+
+static inline void aggregate_strp_stats(struct strp_aggr_stats *stats,
+					struct strp_aggr_stats *agg_stats)
+{
+#define SAVE_PSOCK_STATS(_stat) (agg_stats->_stat += stats->_stat)
+	SAVE_PSOCK_STATS(rx_msgs);
+	SAVE_PSOCK_STATS(rx_bytes);
+	SAVE_PSOCK_STATS(rx_mem_fail);
+	SAVE_PSOCK_STATS(rx_need_more_hdr);
+	SAVE_PSOCK_STATS(rx_msg_too_big);
+	SAVE_PSOCK_STATS(rx_msg_timeouts);
+	SAVE_PSOCK_STATS(rx_bad_hdr_len);
+	SAVE_PSOCK_STATS(rx_aborts);
+	SAVE_PSOCK_STATS(rx_interrupted);
+	SAVE_PSOCK_STATS(rx_unrecov_intr);
+#undef SAVE_PSOCK_STATS
+
+}
+
+void strp_done(struct strparser *strp);
+void strp_stop(struct strparser *strp);
+void strp_check_rcv(struct strparser *strp);
+int strp_init(struct strparser *strp, struct sock *csk,
+	      struct strp_callbacks *cb);
+void strp_tcp_data_ready(struct strparser *strp);
+
+#endif /* __NET_STRPARSER_H_ */