Merge tag 'mlx5-tls-2020-06-26' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-tls-2020-06-26

1) Improve hardware layouts and structure for kTLS support

2) Generalize ICOSQ (Internal Channel Operations Send Queue)
Due to the asynchronous nature of adding new kTLS flows and handling
HW asynchronous kTLS resync requests, the XSK ICOSQ was extended to
support generic async operations, such as kTLS add flow and resync, in
addition to the existing XSK usages.

3) kTLS hardware flow steering and classification:
The driver already has the means to classify TCP ipv4/6 flows to send them
to the corresponding RSS HW engine, as reflected in patches 3 through 5,
the series will add a steering layer that will hook to the driver's TCP
classifiers and will match on well known kTLS connection, in case of a
match traffic will be redirected to the kTLS decryption engine, otherwise
traffic will continue flowing normally to the TCP RSS engine.

3) kTLS add flow RX HW offload support
New offload contexts post their static/progress params WQEs
(Work Queue Element) to communicate the newly added kTLS contexts
over the per-channel async ICOSQ.

The Channel/RQ is selected according to the socket's rxq index.

A new TLS-RX workqueue is used to allow asynchronous addition of
steering rules, out of the NAPI context.
It will be also used in a downstream patch in the resync procedure.

Feature is OFF by default. Can be turned on by:
$ ethtool -K <if> tls-hw-rx-offload on

4) Added mlx5 kTLS sw stats and new counters are documented in
Documentation/networking/tls-offload.rst
rx_tls_ctx - number of TLS RX HW offload contexts added to device for
decryption.

rx_tls_ooo - number of RX packets which were part of a TLS stream
but did not arrive in the expected order and triggered the resync
procedure.

rx_tls_del - number of TLS RX HW offload contexts deleted from device
(connection has finished).

rx_tls_err - number of RX packets which were part of a TLS stream
 but were not decrypted due to unexpected error in the state machine.

5) Asynchronous RX resync

a. The NIC driver indicates that it would like to resync on some TLS
record within the received packet (P), but the driver does not
know (yet) which of the TLS records within the packet.
At this stage, the NIC driver will query the device to find the exact
TCP sequence for resync (tcpsn), however, the driver does not wait
for the device to provide the response.

b. Eventually, the device responds, and the driver provides the tcpsn
within the resync packet to KTLS. Now, KTLS can check the tcpsn against
any processed TLS records within packet P, and also against any record
that is processed in the future within packet P.

The asynchronous resync path simplifies the device driver, as it can
save bits on the packet completion (32-bit TCP sequence), and pass this
information on an asynchronous command instead.

Performance:
    CPU: Intel(R) Xeon(R) CPU E5-2687W v4 @ 3.00GHz, 24 cores, HT off
    NIC: ConnectX-6 Dx 100GbE dual port

    Goodput (app-layer throughput) comparison:
    +---------------+-------+-------+---------+
    | # connections |   1   |   4   |    8    |
    +---------------+-------+-------+---------+
    | SW (Gbps)     |  7.26 | 24.70 |   50.30 |
    +---------------+-------+-------+---------+
    | HW (Gbps)     | 18.50 | 64.30 |   92.90 |
    +---------------+-------+-------+---------+
    | Speedup       | 2.55x | 2.56x | 1.85x * |
    +---------------+-------+-------+---------+

    * After linerate is reached, diff is observed in CPU util
====================

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

1 files changed, 30 insertions, 4 deletions

diff --git a/include/net/tls.h b/include/net/tls.h
index 3212d3c214a9..c875c0a445a6 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -291,11 +291,19 @@ struct tlsdev_ops {
 enum tls_offload_sync_type {
 	TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ = 0,
 	TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT = 1,
+	TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC = 2,
 };
 
 #define TLS_DEVICE_RESYNC_NH_START_IVAL		2
 #define TLS_DEVICE_RESYNC_NH_MAX_IVAL		128
 
+#define TLS_DEVICE_RESYNC_ASYNC_LOGMAX		13
+struct tls_offload_resync_async {
+	atomic64_t req;
+	u32 loglen;
+	u32 log[TLS_DEVICE_RESYNC_ASYNC_LOGMAX];
+};
+
 struct tls_offload_context_rx {
 	/* sw must be the first member of tls_offload_context_rx */
 	struct tls_sw_context_rx sw;
@@ -314,6 +322,10 @@ struct tls_offload_context_rx {
 			u32 decrypted_failed;
 			u32 decrypted_tgt;
 		} resync_nh;
+		/* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ_ASYNC */
+		struct {
+			struct tls_offload_resync_async *resync_async;
+		};
 	};
 	u8 driver_state[] __aligned(8);
 	/* The TLS layer reserves room for driver specific state
@@ -606,9 +618,9 @@ tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction)
 }
 #endif
 
+#define RESYNC_REQ BIT(0)
+#define RESYNC_REQ_ASYNC BIT(1)
 /* The TLS context is valid until sk_destruct is called */
-#define RESYNC_REQ (1 << 0)
-#define RESYNC_REQ_FORCE (1 << 1)
 static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
@@ -617,12 +629,26 @@ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
 	atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | RESYNC_REQ);
 }
 
-static inline void tls_offload_rx_force_resync_request(struct sock *sk)
+/* Log all TLS record header TCP sequences in [seq, seq+len] */
+static inline void
+tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
+
+	atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) |
+		     (len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC);
+	rx_ctx->resync_async->loglen = 0;
+}
+
+static inline void
+tls_offload_rx_resync_async_request_end(struct sock *sk, __be32 seq)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
 
-	atomic64_set(&rx_ctx->resync_req, RESYNC_REQ | RESYNC_REQ_FORCE);
+	atomic64_set(&rx_ctx->resync_async->req,
+		     ((u64)ntohl(seq) << 32) | RESYNC_REQ);
 }
 
 static inline void