From 26149e3e1f44d27897d0af9ca4bcd723674bad44 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 21 Jul 2019 14:18:42 +0300
Subject: net/mlx5: kTLS, Fix wrong TIS opmod constants

Fix the used constants for TLS TIS opmods, per the HW specification.

Fixes: a12ff35e0fb7 ("net/mlx5: Introduce TLS TX offload hardware bits and structures")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 include/linux/mlx5/device.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index ce9839c8bc1a..c2f056b5766d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -446,11 +446,11 @@ enum {
 };
 
 enum {
-	MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x20,
+	MLX5_OPC_MOD_TLS_TIS_STATIC_PARAMS = 0x1,
 };
 
 enum {
-	MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x20,
+	MLX5_OPC_MOD_TLS_TIS_PROGRESS_PARAMS = 0x1,
 };
 
 enum {
-- 
cgit v1.2.3


From a9bc3390327317345dd4683b70970c83ab400ea3 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 30 Jul 2019 11:55:25 +0300
Subject: net/mlx5e: kTLS, Fix progress params context WQE layout

The TLS progress params context WQE should not include an
Eth segment, drop it.
In addition, align the tls_progress_params layout with the
HW specification document:
- fix the tisn field name.
- remove the valid bit.

Fixes: a12ff35e0fb7 ("net/mlx5: Introduce TLS TX offload hardware bits and structures")
Fixes: d2ead1f360e8 ("net/mlx5e: Add kTLS TX HW offload support")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h               | 9 +++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h    | 6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c | 4 ++--
 include/linux/mlx5/mlx5_ifc.h                              | 5 ++---
 4 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index ce1be2a84231..f6b64a03cd06 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -184,8 +184,13 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev)
 
 struct mlx5e_tx_wqe {
 	struct mlx5_wqe_ctrl_seg ctrl;
-	struct mlx5_wqe_eth_seg  eth;
-	struct mlx5_wqe_data_seg data[0];
+	union {
+		struct {
+			struct mlx5_wqe_eth_seg  eth;
+			struct mlx5_wqe_data_seg data[0];
+		};
+		u8 tls_progress_params_ctx[0];
+	};
 };
 
 struct mlx5e_rx_wqe_ll {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
index 407da83474ef..b7298f9ee3d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls.h
@@ -11,12 +11,14 @@
 #include "accel/tls.h"
 
 #define MLX5E_KTLS_STATIC_UMR_WQE_SZ \
-	(sizeof(struct mlx5e_umr_wqe) + MLX5_ST_SZ_BYTES(tls_static_params))
+	(offsetof(struct mlx5e_umr_wqe, tls_static_params_ctx) + \
+	 MLX5_ST_SZ_BYTES(tls_static_params))
 #define MLX5E_KTLS_STATIC_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_KTLS_STATIC_UMR_WQE_SZ, MLX5_SEND_WQE_BB))
 
 #define MLX5E_KTLS_PROGRESS_WQE_SZ \
-	(sizeof(struct mlx5e_tx_wqe) + MLX5_ST_SZ_BYTES(tls_progress_params))
+	(offsetof(struct mlx5e_tx_wqe, tls_progress_params_ctx) + \
+	 MLX5_ST_SZ_BYTES(tls_progress_params))
 #define MLX5E_KTLS_PROGRESS_WQEBBS \
 	(DIV_ROUND_UP(MLX5E_KTLS_PROGRESS_WQE_SZ, MLX5_SEND_WQE_BB))
 #define MLX5E_KTLS_MAX_DUMP_WQEBBS 2
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
index 3766545ce259..9f67bfb559f1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c
@@ -80,7 +80,7 @@ build_static_params(struct mlx5e_umr_wqe *wqe, u16 pc, u32 sqn,
 static void
 fill_progress_params_ctx(void *ctx, struct mlx5e_ktls_offload_context_tx *priv_tx)
 {
-	MLX5_SET(tls_progress_params, ctx, pd, priv_tx->tisn);
+	MLX5_SET(tls_progress_params, ctx, tisn, priv_tx->tisn);
 	MLX5_SET(tls_progress_params, ctx, record_tracker_state,
 		 MLX5E_TLS_PROGRESS_PARAMS_RECORD_TRACKER_STATE_START);
 	MLX5_SET(tls_progress_params, ctx, auth_state,
@@ -104,7 +104,7 @@ build_progress_params(struct mlx5e_tx_wqe *wqe, u16 pc, u32 sqn,
 					     PROGRESS_PARAMS_DS_CNT);
 	cseg->fm_ce_se         = fence ? MLX5_FENCE_MODE_INITIATOR_SMALL : 0;
 
-	fill_progress_params_ctx(wqe->data, priv_tx);
+	fill_progress_params_ctx(wqe->tls_progress_params_ctx, priv_tx);
 }
 
 static void tx_fill_wi(struct mlx5e_txqsq *sq,
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ec571fd7fcf8..b8b570c30b5e 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10054,9 +10054,8 @@ struct mlx5_ifc_tls_static_params_bits {
 };
 
 struct mlx5_ifc_tls_progress_params_bits {
-	u8         valid[0x1];
-	u8         reserved_at_1[0x7];
-	u8         pd[0x18];
+	u8         reserved_at_0[0x8];
+	u8         tisn[0x18];
 
 	u8         next_record_tcp_sn[0x20];
 
-- 
cgit v1.2.3


From 891584f48a9084ba462f10da4c6bb28b6181b543 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 2 Aug 2019 17:15:03 +0200
Subject: inet: frags: re-introduce skb coalescing for local delivery

Before commit d4289fcc9b16 ("net: IP6 defrag: use rbtrees for IPv6
defrag"), a netperf UDP_STREAM test[0] using big IPv6 datagrams (thus
generating many fragments) and running over an IPsec tunnel, reported
more than 6Gbps throughput. After that patch, the same test gets only
9Mbps when receiving on a be2net nic (driver can make a big difference
here, for example, ixgbe doesn't seem to be affected).

By reusing the IPv4 defragmentation code, IPv6 lost fragment coalescing
(IPv4 fragment coalescing was dropped by commit 14fe22e33462 ("Revert
"ipv4: use skb coalescing in defragmentation"")).

Without fragment coalescing, be2net runs out of Rx ring entries and
starts to drop frames (ethtool reports rx_drops_no_frags errors). Since
the netperf traffic is only composed of UDP fragments, any lost packet
prevents reassembly of the full datagram. Therefore, fragments which
have no possibility to ever get reassembled pile up in the reassembly
queue, until the memory accounting exeeds the threshold. At that point
no fragment is accepted anymore, which effectively discards all
netperf traffic.

When reassembly timeout expires, some stale fragments are removed from
the reassembly queue, so a few packets can be received, reassembled
and delivered to the netperf receiver. But the nic still drops frames
and soon the reassembly queue gets filled again with stale fragments.
These long time frames where no datagram can be received explain why
the performance drop is so significant.

Re-introducing fragment coalescing is enough to get the initial
performances again (6.6Gbps with be2net): driver doesn't drop frames
anymore (no more rx_drops_no_frags errors) and the reassembly engine
works at full speed.

This patch is quite conservative and only coalesces skbs for local
IPv4 and IPv6 delivery (in order to avoid changing skb geometry when
forwarding). Coalescing could be extended in the future if need be, as
more scenarios would probably benefit from it.

[0]: Test configuration
Sender:
ip xfrm policy flush
ip xfrm state flush
ip xfrm state add src fc00:1::1 dst fc00:2::1 proto esp spi 0x1000 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:1::1 dst fc00:2::1
ip xfrm policy add src fc00:1::1 dst fc00:2::1 dir in tmpl src fc00:1::1 dst fc00:2::1 proto esp mode transport action allow
ip xfrm state add src fc00:2::1 dst fc00:1::1 proto esp spi 0x1001 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:2::1 dst fc00:1::1
ip xfrm policy add src fc00:2::1 dst fc00:1::1 dir out tmpl src fc00:2::1 dst fc00:1::1 proto esp mode transport action allow
netserver -D -L fc00:2::1

Receiver:
ip xfrm policy flush
ip xfrm state flush
ip xfrm state add src fc00:2::1 dst fc00:1::1 proto esp spi 0x1001 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:2::1 dst fc00:1::1
ip xfrm policy add src fc00:2::1 dst fc00:1::1 dir in tmpl src fc00:2::1 dst fc00:1::1 proto esp mode transport action allow
ip xfrm state add src fc00:1::1 dst fc00:2::1 proto esp spi 0x1000 aead 'rfc4106(gcm(aes))' 0x0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b0b 96 mode transport sel src fc00:1::1 dst fc00:2::1
ip xfrm policy add src fc00:1::1 dst fc00:2::1 dir out tmpl src fc00:1::1 dst fc00:2::1 proto esp mode transport action allow
netperf -H fc00:2::1 -f k -P 0 -L fc00:1::1 -l 60 -t UDP_STREAM -I 99,5 -i 5,5 -T5,5 -6

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h                 |  2 +-
 net/ieee802154/6lowpan/reassembly.c     |  2 +-
 net/ipv4/inet_fragment.c                | 39 +++++++++++++++++++++++----------
 net/ipv4/ip_fragment.c                  |  8 ++++++-
 net/ipv6/netfilter/nf_conntrack_reasm.c |  2 +-
 net/ipv6/reassembly.c                   |  2 +-
 6 files changed, 39 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 010f26b31c89..bac79e817776 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -171,7 +171,7 @@ int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb,
 void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 			      struct sk_buff *parent);
 void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
-			    void *reasm_data);
+			    void *reasm_data, bool try_coalesce);
 struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q);
 
 #endif
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index e4aba5d485be..bbe9b3b2d395 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -170,7 +170,7 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb,
 	reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
 	if (!reasm_data)
 		goto out_oom;
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, false);
 
 	skb->dev = ldev;
 	skb->tstamp = fq->q.stamp;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index a999451345f9..10d31733297d 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -475,11 +475,12 @@ void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb,
 EXPORT_SYMBOL(inet_frag_reasm_prepare);
 
 void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
-			    void *reasm_data)
+			    void *reasm_data, bool try_coalesce)
 {
 	struct sk_buff **nextp = (struct sk_buff **)reasm_data;
 	struct rb_node *rbn;
 	struct sk_buff *fp;
+	int sum_truesize;
 
 	skb_push(head, head->data - skb_network_header(head));
 
@@ -487,25 +488,41 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 	fp = FRAG_CB(head)->next_frag;
 	rbn = rb_next(&head->rbnode);
 	rb_erase(&head->rbnode, &q->rb_fragments);
+
+	sum_truesize = head->truesize;
 	while (rbn || fp) {
 		/* fp points to the next sk_buff in the current run;
 		 * rbn points to the next run.
 		 */
 		/* Go through the current run. */
 		while (fp) {
-			*nextp = fp;
-			nextp = &fp->next;
-			fp->prev = NULL;
-			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
-			fp->sk = NULL;
-			head->data_len += fp->len;
-			head->len += fp->len;
+			struct sk_buff *next_frag = FRAG_CB(fp)->next_frag;
+			bool stolen;
+			int delta;
+
+			sum_truesize += fp->truesize;
 			if (head->ip_summed != fp->ip_summed)
 				head->ip_summed = CHECKSUM_NONE;
 			else if (head->ip_summed == CHECKSUM_COMPLETE)
 				head->csum = csum_add(head->csum, fp->csum);
-			head->truesize += fp->truesize;
-			fp = FRAG_CB(fp)->next_frag;
+
+			if (try_coalesce && skb_try_coalesce(head, fp, &stolen,
+							     &delta)) {
+				kfree_skb_partial(fp, stolen);
+			} else {
+				fp->prev = NULL;
+				memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+				fp->sk = NULL;
+
+				head->data_len += fp->len;
+				head->len += fp->len;
+				head->truesize += fp->truesize;
+
+				*nextp = fp;
+				nextp = &fp->next;
+			}
+
+			fp = next_frag;
 		}
 		/* Move to the next run. */
 		if (rbn) {
@@ -516,7 +533,7 @@ void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head,
 			rbn = rbnext;
 		}
 	}
-	sub_frag_mem_limit(q->fqdir, head->truesize);
+	sub_frag_mem_limit(q->fqdir, sum_truesize);
 
 	*nextp = NULL;
 	skb_mark_not_on_list(head);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 4385eb9e781f..cfeb8890f94e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -393,6 +393,11 @@ err:
 	return err;
 }
 
+static bool ip_frag_coalesce_ok(const struct ipq *qp)
+{
+	return qp->q.key.v4.user == IP_DEFRAG_LOCAL_DELIVER;
+}
+
 /* Build a new IP datagram from all its fragments. */
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 			 struct sk_buff *prev_tail, struct net_device *dev)
@@ -421,7 +426,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	if (len > 65535)
 		goto out_oversize;
 
-	inet_frag_reasm_finish(&qp->q, skb, reasm_data);
+	inet_frag_reasm_finish(&qp->q, skb, reasm_data,
+			       ip_frag_coalesce_ok(qp));
 
 	skb->dev = dev;
 	IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 0f82c150543b..fed9666a2f7d 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -348,7 +348,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
 
 	skb_reset_transport_header(skb);
 
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, false);
 
 	skb->ignore_df = 1;
 	skb->dev = dev;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index ca05b16f1bb9..1f5d4d196dcc 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -282,7 +282,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 
 	skb_reset_transport_header(skb);
 
-	inet_frag_reasm_finish(&fq->q, skb, reasm_data);
+	inet_frag_reasm_finish(&fq->q, skb, reasm_data, true);
 
 	skb->dev = dev;
 	ipv6_hdr(skb)->payload_len = htons(payload_len);
-- 
cgit v1.2.3


From 414776621d1006e57e80e6db7fdc3837897aaa64 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 7 Aug 2019 17:03:59 -0700
Subject: net/tls: prevent skb_orphan() from leaking TLS plain text with
 offload

sk_validate_xmit_skb() and drivers depend on the sk member of
struct sk_buff to identify segments requiring encryption.
Any operation which removes or does not preserve the original TLS
socket such as skb_orphan() or skb_clone() will cause clear text
leaks.

Make the TCP socket underlying an offloaded TLS connection
mark all skbs as decrypted, if TLS TX is in offload mode.
Then in sk_validate_xmit_skb() catch skbs which have no socket
(or a socket with no validation) and decrypted flag set.

Note that CONFIG_SOCK_VALIDATE_XMIT, CONFIG_TLS_DEVICE and
sk->sk_validate_xmit_skb are slightly interchangeable right now,
they all imply TLS offload. The new checks are guarded by
CONFIG_TLS_DEVICE because that's the option guarding the
sk_buff->decrypted member.

Second, smaller issue with orphaning is that it breaks
the guarantee that packets will be delivered to device
queues in-order. All TLS offload drivers depend on that
scheduling property. This means skb_orphan_partial()'s
trick of preserving partial socket references will cause
issues in the drivers. We need a full orphan, and as a
result netem delay/throttling will cause all TLS offload
skbs to be dropped.

Reusing the sk_buff->decrypted flag also protects from
leaking clear text when incoming, decrypted skb is redirected
(e.g. by TC).

See commit 0608c69c9a80 ("bpf: sk_msg, sock{map|hash} redirect
through ULP") for justification why the internal flag is safe.
The only location which could leak the flag in is tcp_bpf_sendmsg(),
which is taken care of by clearing the previously unused bit.

v2:
 - remove superfluous decrypted mark copy (Willem);
 - remove the stale doc entry (Boris);
 - rely entirely on EOR marking to prevent coalescing (Boris);
 - use an internal sendpages flag instead of marking the socket
   (Boris).
v3 (Willem):
 - reorganize the can_skb_orphan_partial() condition;
 - fix the flag leak-in through tcp_bpf_sendmsg.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/tls-offload.rst | 18 ------------------
 include/linux/skbuff.h                   |  8 ++++++++
 include/linux/socket.h                   |  3 +++
 include/net/sock.h                       | 10 +++++++++-
 net/core/sock.c                          | 19 ++++++++++++++-----
 net/ipv4/tcp.c                           |  3 +++
 net/ipv4/tcp_bpf.c                       |  6 +++++-
 net/ipv4/tcp_output.c                    |  3 +++
 net/tls/tls_device.c                     |  9 +++++++--
 9 files changed, 52 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/Documentation/networking/tls-offload.rst b/Documentation/networking/tls-offload.rst
index b70b70dc4524..0dd3f748239f 100644
--- a/Documentation/networking/tls-offload.rst
+++ b/Documentation/networking/tls-offload.rst
@@ -506,21 +506,3 @@ Drivers should ignore the changes to TLS the device feature flags.
 These flags will be acted upon accordingly by the core ``ktls`` code.
 TLS device feature flags only control adding of new TLS connection
 offloads, old connections will remain active after flags are cleared.
-
-Known bugs
-==========
-
-skb_orphan() leaks clear text
------------------------------
-
-Currently drivers depend on the :c:member:`sk` member of
-:c:type:`struct sk_buff <sk_buff>` to identify segments requiring
-encryption. Any operation which removes or does not preserve the socket
-association such as :c:func:`skb_orphan` or :c:func:`skb_clone`
-will cause the driver to miss the packets and lead to clear text leaks.
-
-Redirects leak clear text
--------------------------
-
-In the RX direction, if segment has already been decrypted by the device
-and it gets redirected or mirrored - clear text will be transmitted out.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d8af86d995d6..ba5583522d24 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1374,6 +1374,14 @@ static inline void skb_copy_hash(struct sk_buff *to, const struct sk_buff *from)
 	to->l4_hash = from->l4_hash;
 };
 
+static inline void skb_copy_decrypted(struct sk_buff *to,
+				      const struct sk_buff *from)
+{
+#ifdef CONFIG_TLS_DEVICE
+	to->decrypted = from->decrypted;
+#endif
+}
+
 #ifdef NET_SKBUFF_DATA_USES_OFFSET
 static inline unsigned char *skb_end_pointer(const struct sk_buff *skb)
 {
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 97523818cb14..fc0bed59fc84 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -292,6 +292,9 @@ struct ucred {
 #define MSG_BATCH	0x40000 /* sendmmsg(): more messages coming */
 #define MSG_EOF         MSG_FIN
 #define MSG_NO_SHARED_FRAGS 0x80000 /* sendpage() internal : page frags are not shared */
+#define MSG_SENDPAGE_DECRYPTED	0x100000 /* sendpage() internal : page may carry
+					  * plain text and require encryption
+					  */
 
 #define MSG_ZEROCOPY	0x4000000	/* Use user data in kernel path */
 #define MSG_FASTOPEN	0x20000000	/* Send data in TCP SYN */
diff --git a/include/net/sock.h b/include/net/sock.h
index 228db3998e46..2c53f1a1d905 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2482,6 +2482,7 @@ static inline bool sk_fullsock(const struct sock *sk)
 
 /* Checks if this SKB belongs to an HW offloaded socket
  * and whether any SW fallbacks are required based on dev.
+ * Check decrypted mark in case skb_orphan() cleared socket.
  */
 static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
 						   struct net_device *dev)
@@ -2489,8 +2490,15 @@ static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb,
 #ifdef CONFIG_SOCK_VALIDATE_XMIT
 	struct sock *sk = skb->sk;
 
-	if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb)
+	if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) {
 		skb = sk->sk_validate_xmit_skb(sk, dev, skb);
+#ifdef CONFIG_TLS_DEVICE
+	} else if (unlikely(skb->decrypted)) {
+		pr_warn_ratelimited("unencrypted skb with no associated socket - dropping\n");
+		kfree_skb(skb);
+		skb = NULL;
+#endif
+	}
 #endif
 
 	return skb;
diff --git a/net/core/sock.c b/net/core/sock.c
index d57b0cc995a0..6d08553f885c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1992,6 +1992,19 @@ void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
 }
 EXPORT_SYMBOL(skb_set_owner_w);
 
+static bool can_skb_orphan_partial(const struct sk_buff *skb)
+{
+#ifdef CONFIG_TLS_DEVICE
+	/* Drivers depend on in-order delivery for crypto offload,
+	 * partial orphan breaks out-of-order-OK logic.
+	 */
+	if (skb->decrypted)
+		return false;
+#endif
+	return (skb->destructor == sock_wfree ||
+		(IS_ENABLED(CONFIG_INET) && skb->destructor == tcp_wfree));
+}
+
 /* This helper is used by netem, as it can hold packets in its
  * delay queue. We want to allow the owner socket to send more
  * packets, as if they were already TX completed by a typical driver.
@@ -2003,11 +2016,7 @@ void skb_orphan_partial(struct sk_buff *skb)
 	if (skb_is_tcp_pure_ack(skb))
 		return;
 
-	if (skb->destructor == sock_wfree
-#ifdef CONFIG_INET
-	    || skb->destructor == tcp_wfree
-#endif
-		) {
+	if (can_skb_orphan_partial(skb)) {
 		struct sock *sk = skb->sk;
 
 		if (refcount_inc_not_zero(&sk->sk_refcnt)) {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 776905899ac0..77b485d60b9d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -984,6 +984,9 @@ new_segment:
 			if (!skb)
 				goto wait_for_memory;
 
+#ifdef CONFIG_TLS_DEVICE
+			skb->decrypted = !!(flags & MSG_SENDPAGE_DECRYPTED);
+#endif
 			skb_entail(sk, skb);
 			copy = size_goal;
 		}
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 3d1e15401384..8a56e09cfb0e 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -398,10 +398,14 @@ more_data:
 static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 {
 	struct sk_msg tmp, *msg_tx = NULL;
-	int flags = msg->msg_flags | MSG_NO_SHARED_FRAGS;
 	int copied = 0, err = 0;
 	struct sk_psock *psock;
 	long timeo;
+	int flags;
+
+	/* Don't let internal do_tcp_sendpages() flags through */
+	flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED);
+	flags |= MSG_NO_SHARED_FRAGS;
 
 	psock = sk_psock_get(sk);
 	if (unlikely(!psock))
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 6e4afc48d7bb..979520e46e33 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1320,6 +1320,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	buff = sk_stream_alloc_skb(sk, nsize, gfp, true);
 	if (!buff)
 		return -ENOMEM; /* We'll just try again later. */
+	skb_copy_decrypted(buff, skb);
 
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
@@ -1874,6 +1875,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 	buff = sk_stream_alloc_skb(sk, 0, gfp, true);
 	if (unlikely(!buff))
 		return -ENOMEM;
+	skb_copy_decrypted(buff, skb);
 
 	sk->sk_wmem_queued += buff->truesize;
 	sk_mem_charge(sk, buff->truesize);
@@ -2143,6 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	sk_mem_charge(sk, nskb->truesize);
 
 	skb = tcp_send_head(sk);
+	skb_copy_decrypted(nskb, skb);
 
 	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
 	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 7c0b2b778703..43922d86e510 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -373,9 +373,9 @@ static int tls_push_data(struct sock *sk,
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_prot_info *prot = &tls_ctx->prot_info;
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
-	int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
 	int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
 	struct tls_record_info *record = ctx->open_record;
+	int tls_push_record_flags;
 	struct page_frag *pfrag;
 	size_t orig_size = size;
 	u32 max_open_record_len;
@@ -390,6 +390,9 @@ static int tls_push_data(struct sock *sk,
 	if (sk->sk_err)
 		return -sk->sk_err;
 
+	flags |= MSG_SENDPAGE_DECRYPTED;
+	tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
+
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 	if (tls_is_partially_sent_record(tls_ctx)) {
 		rc = tls_push_partial_record(sk, tls_ctx, flags);
@@ -576,7 +579,9 @@ void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
 		gfp_t sk_allocation = sk->sk_allocation;
 
 		sk->sk_allocation = GFP_ATOMIC;
-		tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL);
+		tls_push_partial_record(sk, ctx,
+					MSG_DONTWAIT | MSG_NOSIGNAL |
+					MSG_SENDPAGE_DECRYPTED);
 		sk->sk_allocation = sk_allocation;
 	}
 }
-- 
cgit v1.2.3


From 6a0a8d10a3661a036b55af695542a714c429ab7c Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 9 Aug 2019 11:01:27 +0200
Subject: netfilter: nf_tables: use-after-free in failing rule with bound set

If a rule that has already a bound anonymous set fails to be added, the
preparation phase releases the rule and the bound set. However, the
transaction object from the abort path still has a reference to the set
object that is stale, leading to a use-after-free when checking for the
set->bound field. Add a new field to the transaction that specifies if
the set is bound, so the abort path can skip releasing it since the rule
command owns it and it takes care of releasing it. After this update,
the set->bound field is removed.

[   24.649883] Unable to handle kernel paging request at virtual address 0000000000040434
[   24.657858] Mem abort info:
[   24.660686]   ESR = 0x96000004
[   24.663769]   Exception class = DABT (current EL), IL = 32 bits
[   24.669725]   SET = 0, FnV = 0
[   24.672804]   EA = 0, S1PTW = 0
[   24.675975] Data abort info:
[   24.678880]   ISV = 0, ISS = 0x00000004
[   24.682743]   CM = 0, WnR = 0
[   24.685723] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000428952000
[   24.692207] [0000000000040434] pgd=0000000000000000
[   24.697119] Internal error: Oops: 96000004 [#1] SMP
[...]
[   24.889414] Call trace:
[   24.891870]  __nf_tables_abort+0x3f0/0x7a0
[   24.895984]  nf_tables_abort+0x20/0x40
[   24.899750]  nfnetlink_rcv_batch+0x17c/0x588
[   24.904037]  nfnetlink_rcv+0x13c/0x190
[   24.907803]  netlink_unicast+0x18c/0x208
[   24.911742]  netlink_sendmsg+0x1b0/0x350
[   24.915682]  sock_sendmsg+0x4c/0x68
[   24.919185]  ___sys_sendmsg+0x288/0x2c8
[   24.923037]  __sys_sendmsg+0x7c/0xd0
[   24.926628]  __arm64_sys_sendmsg+0x2c/0x38
[   24.930744]  el0_svc_common.constprop.0+0x94/0x158
[   24.935556]  el0_svc_handler+0x34/0x90
[   24.939322]  el0_svc+0x8/0xc
[   24.942216] Code: 37280300 f9404023 91014262 aa1703e0 (f9401863)
[   24.948336] ---[ end trace cebbb9dcbed3b56f ]---

Fixes: f6ac85858976 ("netfilter: nf_tables: unbind set in rule from commit path")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  9 +++++++--
 net/netfilter/nf_tables_api.c     | 15 ++++++++++-----
 2 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 9b624566b82d..475d6f28ca67 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -421,8 +421,7 @@ struct nft_set {
 	unsigned char			*udata;
 	/* runtime data below here */
 	const struct nft_set_ops	*ops ____cacheline_aligned;
-	u16				flags:13,
-					bound:1,
+	u16				flags:14,
 					genmask:2;
 	u8				klen;
 	u8				dlen;
@@ -1348,12 +1347,15 @@ struct nft_trans_rule {
 struct nft_trans_set {
 	struct nft_set			*set;
 	u32				set_id;
+	bool				bound;
 };
 
 #define nft_trans_set(trans)	\
 	(((struct nft_trans_set *)trans->data)->set)
 #define nft_trans_set_id(trans)	\
 	(((struct nft_trans_set *)trans->data)->set_id)
+#define nft_trans_set_bound(trans)	\
+	(((struct nft_trans_set *)trans->data)->bound)
 
 struct nft_trans_chain {
 	bool				update;
@@ -1384,12 +1386,15 @@ struct nft_trans_table {
 struct nft_trans_elem {
 	struct nft_set			*set;
 	struct nft_set_elem		elem;
+	bool				bound;
 };
 
 #define nft_trans_elem_set(trans)	\
 	(((struct nft_trans_elem *)trans->data)->set)
 #define nft_trans_elem(trans)	\
 	(((struct nft_trans_elem *)trans->data)->elem)
+#define nft_trans_elem_set_bound(trans)	\
+	(((struct nft_trans_elem *)trans->data)->bound)
 
 struct nft_trans_obj {
 	struct nft_object		*obj;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 605a7cfe7ca7..88abbddf8967 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -138,9 +138,14 @@ static void nft_set_trans_bind(const struct nft_ctx *ctx, struct nft_set *set)
 		return;
 
 	list_for_each_entry_reverse(trans, &net->nft.commit_list, list) {
-		if (trans->msg_type == NFT_MSG_NEWSET &&
-		    nft_trans_set(trans) == set) {
-			set->bound = true;
+		switch (trans->msg_type) {
+		case NFT_MSG_NEWSET:
+			if (nft_trans_set(trans) == set)
+				nft_trans_set_bound(trans) = true;
+			break;
+		case NFT_MSG_NEWSETELEM:
+			if (nft_trans_elem_set(trans) == set)
+				nft_trans_elem_set_bound(trans) = true;
 			break;
 		}
 	}
@@ -6906,7 +6911,7 @@ static int __nf_tables_abort(struct net *net)
 			break;
 		case NFT_MSG_NEWSET:
 			trans->ctx.table->use--;
-			if (nft_trans_set(trans)->bound) {
+			if (nft_trans_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
@@ -6918,7 +6923,7 @@ static int __nf_tables_abort(struct net *net)
 			nft_trans_destroy(trans);
 			break;
 		case NFT_MSG_NEWSETELEM:
-			if (nft_trans_elem_set(trans)->bound) {
+			if (nft_trans_elem_set_bound(trans)) {
 				nft_trans_destroy(trans);
 				break;
 			}
-- 
cgit v1.2.3


From cd48bdda4fb82c2fe569d97af4217c530168c99c Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 8 Aug 2019 13:57:25 +0200
Subject: sock: make cookie generation global instead of per netns

Generating and retrieving socket cookies are a useful feature that is
exposed to BPF for various program types through bpf_get_socket_cookie()
helper.

The fact that the cookie counter is per netns is quite a limitation
for BPF in practice in particular for programs in host namespace that
use socket cookies as part of a map lookup key since they will be
causing socket cookie collisions e.g. when attached to BPF cgroup hooks
or cls_bpf on tc egress in host namespace handling container traffic
from veth or ipvlan devices with peer in different netns. Change the
counter to be global instead.

Socket cookie consumers must assume the value as opqaue in any case.
Not every socket must have a cookie generated and knowledge of the
counter value itself does not provide much value either way hence
conversion to global is fine.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Martynas Pumputis <m@lambda.lt>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 1 -
 include/uapi/linux/bpf.h    | 4 ++--
 net/core/sock_diag.c        | 3 ++-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index 4a9da951a794..cb668bc2692d 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -61,7 +61,6 @@ struct net {
 	spinlock_t		rules_mod_lock;
 
 	u32			hash_mix;
-	atomic64_t		cookie_gen;
 
 	struct list_head	list;		/* list of network namespaces */
 	struct list_head	exit_list;	/* To linked to call pernet exit
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index fa1c753dcdbc..a5aa7d3ac6a1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1466,8 +1466,8 @@ union bpf_attr {
  * 		If no cookie has been set yet, generate a new cookie. Once
  * 		generated, the socket cookie remains stable for the life of the
  * 		socket. This helper can be useful for monitoring per socket
- * 		networking traffic statistics as it provides a unique socket
- * 		identifier per namespace.
+ * 		networking traffic statistics as it provides a global socket
+ * 		identifier that can be assumed unique.
  * 	Return
  * 		A 8-byte long non-decreasing number on success, or 0 if the
  * 		socket field is missing inside *skb*.
diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index 3312a5849a97..c13ffbd33d8d 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -19,6 +19,7 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
 static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
 static DEFINE_MUTEX(sock_diag_table_mutex);
 static struct workqueue_struct *broadcast_wq;
+static atomic64_t cookie_gen;
 
 u64 sock_gen_cookie(struct sock *sk)
 {
@@ -27,7 +28,7 @@ u64 sock_gen_cookie(struct sock *sk)
 
 		if (res)
 			return res;
-		res = atomic64_inc_return(&sock_net(sk)->cookie_gen);
+		res = atomic64_inc_return(&cookie_gen);
 		atomic64_cmpxchg(&sk->sk_cookie, 0, res);
 	}
 }
-- 
cgit v1.2.3


From d00ee64e1dcf09b3afefd1340f3e9eb637272714 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Mon, 12 Aug 2019 13:07:07 -0700
Subject: netlink: Fix nlmsg_parse as a wrapper for strict message parsing

Eric reported a syzbot warning:

BUG: KMSAN: uninit-value in nh_valid_get_del_req+0x6f1/0x8c0 net/ipv4/nexthop.c:1510
CPU: 0 PID: 11812 Comm: syz-executor444 Not tainted 5.3.0-rc3+ #17
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x191/0x1f0 lib/dump_stack.c:113
 kmsan_report+0x162/0x2d0 mm/kmsan/kmsan_report.c:109
 __msan_warning+0x75/0xe0 mm/kmsan/kmsan_instr.c:294
 nh_valid_get_del_req+0x6f1/0x8c0 net/ipv4/nexthop.c:1510
 rtm_del_nexthop+0x1b1/0x610 net/ipv4/nexthop.c:1543
 rtnetlink_rcv_msg+0x115a/0x1580 net/core/rtnetlink.c:5223
 netlink_rcv_skb+0x431/0x620 net/netlink/af_netlink.c:2477
 rtnetlink_rcv+0x50/0x60 net/core/rtnetlink.c:5241
 netlink_unicast_kernel net/netlink/af_netlink.c:1302 [inline]
 netlink_unicast+0xf6c/0x1050 net/netlink/af_netlink.c:1328
 netlink_sendmsg+0x110f/0x1330 net/netlink/af_netlink.c:1917
 sock_sendmsg_nosec net/socket.c:637 [inline]
 sock_sendmsg net/socket.c:657 [inline]
 ___sys_sendmsg+0x14ff/0x1590 net/socket.c:2311
 __sys_sendmmsg+0x53a/0xae0 net/socket.c:2413
 __do_sys_sendmmsg net/socket.c:2442 [inline]
 __se_sys_sendmmsg+0xbd/0xe0 net/socket.c:2439
 __x64_sys_sendmmsg+0x56/0x70 net/socket.c:2439
 do_syscall_64+0xbc/0xf0 arch/x86/entry/common.c:297
 entry_SYSCALL_64_after_hwframe+0x63/0xe7

The root cause is nlmsg_parse calling __nla_parse which means the
header struct size is not checked.

nlmsg_parse should be a wrapper around __nlmsg_parse with
NL_VALIDATE_STRICT for the validate argument very much like
nlmsg_parse_deprecated is for NL_VALIDATE_LIBERAL.

Fixes: 3de6440354465 ("netlink: re-add parse/validate functions in strict mode")
Reported-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: David Ahern <dsahern@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
---
 include/net/netlink.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/netlink.h b/include/net/netlink.h
index e4650e5b64a1..b140c8f1be22 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -684,9 +684,8 @@ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen,
 			      const struct nla_policy *policy,
 			      struct netlink_ext_ack *extack)
 {
-	return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen),
-			   nlmsg_attrlen(nlh, hdrlen), policy,
-			   NL_VALIDATE_STRICT, extack);
+	return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy,
+			     NL_VALIDATE_STRICT, extack);
 }
 
 /**
-- 
cgit v1.2.3


From 06d9532fa6b34f12a6d75711162d47c17c1add72 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 13 Aug 2019 22:26:36 +0100
Subject: rxrpc: Fix read-after-free in rxrpc_queue_local()

rxrpc_queue_local() attempts to queue the local endpoint it is given and
then, if successful, prints a trace line.  The trace line includes the
current usage count - but we're not allowed to look at the local endpoint
at this point as we passed our ref on it to the workqueue.

Fix this by reading the usage count before queuing the work item.

Also fix the reading of local->debug_id for trace lines, which must be done
with the same consideration as reading the usage count.

Fixes: 09d2bf595db4 ("rxrpc: Add a tracepoint to track rxrpc_local refcounting")
Reported-by: syzbot+78e71c5bab4f76a6a719@syzkaller.appspotmail.com
Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h |  6 +++---
 net/rxrpc/local_object.c     | 19 ++++++++++---------
 2 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index cc1d060cbf13..fa06b528c73c 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -498,10 +498,10 @@ rxrpc_tx_points;
 #define E_(a, b)	{ a, b }
 
 TRACE_EVENT(rxrpc_local,
-	    TP_PROTO(struct rxrpc_local *local, enum rxrpc_local_trace op,
+	    TP_PROTO(unsigned int local_debug_id, enum rxrpc_local_trace op,
 		     int usage, const void *where),
 
-	    TP_ARGS(local, op, usage, where),
+	    TP_ARGS(local_debug_id, op, usage, where),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,	local		)
@@ -511,7 +511,7 @@ TRACE_EVENT(rxrpc_local,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->local = local->debug_id;
+		    __entry->local = local_debug_id;
 		    __entry->op = op;
 		    __entry->usage = usage;
 		    __entry->where = where;
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index c45765b7263e..72a6e12a9304 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -93,7 +93,7 @@ static struct rxrpc_local *rxrpc_alloc_local(struct rxrpc_net *rxnet,
 		local->debug_id = atomic_inc_return(&rxrpc_debug_id);
 		memcpy(&local->srx, srx, sizeof(*srx));
 		local->srx.srx_service = 0;
-		trace_rxrpc_local(local, rxrpc_local_new, 1, NULL);
+		trace_rxrpc_local(local->debug_id, rxrpc_local_new, 1, NULL);
 	}
 
 	_leave(" = %p", local);
@@ -321,7 +321,7 @@ struct rxrpc_local *rxrpc_get_local(struct rxrpc_local *local)
 	int n;
 
 	n = atomic_inc_return(&local->usage);
-	trace_rxrpc_local(local, rxrpc_local_got, n, here);
+	trace_rxrpc_local(local->debug_id, rxrpc_local_got, n, here);
 	return local;
 }
 
@@ -335,7 +335,8 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 	if (local) {
 		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
 		if (n > 0)
-			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
+			trace_rxrpc_local(local->debug_id, rxrpc_local_got,
+					  n + 1, here);
 		else
 			local = NULL;
 	}
@@ -343,16 +344,16 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 }
 
 /*
- * Queue a local endpoint unless it has become unreferenced and pass the
- * caller's reference to the work item.
+ * Queue a local endpoint and pass the caller's reference to the work item.
  */
 void rxrpc_queue_local(struct rxrpc_local *local)
 {
 	const void *here = __builtin_return_address(0);
+	unsigned int debug_id = local->debug_id;
+	int n = atomic_read(&local->usage);
 
 	if (rxrpc_queue_work(&local->processor))
-		trace_rxrpc_local(local, rxrpc_local_queued,
-				  atomic_read(&local->usage), here);
+		trace_rxrpc_local(debug_id, rxrpc_local_queued, n, here);
 	else
 		rxrpc_put_local(local);
 }
@@ -367,7 +368,7 @@ void rxrpc_put_local(struct rxrpc_local *local)
 
 	if (local) {
 		n = atomic_dec_return(&local->usage);
-		trace_rxrpc_local(local, rxrpc_local_put, n, here);
+		trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here);
 
 		if (n == 0)
 			call_rcu(&local->rcu, rxrpc_local_rcu);
@@ -456,7 +457,7 @@ static void rxrpc_local_processor(struct work_struct *work)
 		container_of(work, struct rxrpc_local, processor);
 	bool again;
 
-	trace_rxrpc_local(local, rxrpc_local_processing,
+	trace_rxrpc_local(local->debug_id, rxrpc_local_processing,
 			  atomic_read(&local->usage), NULL);
 
 	do {
-- 
cgit v1.2.3


From 58a96fc35375ab87db7c5b69336f5befde1b548f Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Tue, 16 Jul 2019 20:34:41 +0200
Subject: Bluetooth: Add debug setting for changing minimum encryption key size

For testing and qualification purposes it is useful to allow changing
the minimum encryption key size value that the host stack is going to
enforce. This adds a new debugfs setting min_encrypt_key_size to achieve
this functionality.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         |  1 +
 net/bluetooth/hci_debugfs.c      | 31 +++++++++++++++++++++++++++++++
 net/bluetooth/l2cap_core.c       |  2 +-
 4 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ded574b32c20..ffc95b382eb5 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -278,6 +278,7 @@ struct hci_dev {
 	__u16		conn_info_min_age;
 	__u16		conn_info_max_age;
 	__u16		auth_payload_timeout;
+	__u8		min_enc_key_size;
 	__u8		ssp_debug_mode;
 	__u8		hw_error_code;
 	__u32		clock;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index b9585e7d9d2e..04bc79359a17 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3202,6 +3202,7 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->conn_info_min_age = DEFAULT_CONN_INFO_MIN_AGE;
 	hdev->conn_info_max_age = DEFAULT_CONN_INFO_MAX_AGE;
 	hdev->auth_payload_timeout = DEFAULT_AUTH_PAYLOAD_TIMEOUT;
+	hdev->min_enc_key_size = HCI_MIN_ENC_KEY_SIZE;
 
 	mutex_init(&hdev->lock);
 	mutex_init(&hdev->req_lock);
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index bb67f4a5479a..402e2cc54044 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -433,6 +433,35 @@ static int auto_accept_delay_set(void *data, u64 val)
 	return 0;
 }
 
+static int min_encrypt_key_size_set(void *data, u64 val)
+{
+	struct hci_dev *hdev = data;
+
+	if (val < 1 || val > 16)
+		return -EINVAL;
+
+	hci_dev_lock(hdev);
+	hdev->min_enc_key_size = val;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+static int min_encrypt_key_size_get(void *data, u64 *val)
+{
+	struct hci_dev *hdev = data;
+
+	hci_dev_lock(hdev);
+	*val = hdev->min_enc_key_size;
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(min_encrypt_key_size_fops,
+			min_encrypt_key_size_get,
+			min_encrypt_key_size_set, "%llu\n");
+
 static int auto_accept_delay_get(void *data, u64 *val)
 {
 	struct hci_dev *hdev = data;
@@ -545,6 +574,8 @@ void hci_debugfs_create_bredr(struct hci_dev *hdev)
 	if (lmp_ssp_capable(hdev)) {
 		debugfs_create_file("ssp_debug_mode", 0444, hdev->debugfs,
 				    hdev, &ssp_debug_mode_fops);
+		debugfs_create_file("min_encrypt_key_size", 0644, hdev->debugfs,
+				    hdev, &min_encrypt_key_size_fops);
 		debugfs_create_file("auto_accept_delay", 0644, hdev->debugfs,
 				    hdev, &auto_accept_delay_fops);
 	}
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index cc506fe99b4d..dfc1edb168b7 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -1361,7 +1361,7 @@ static bool l2cap_check_enc_key_size(struct hci_conn *hcon)
 	 * actually encrypted before enforcing a key size.
 	 */
 	return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) ||
-		hcon->enc_key_size >= HCI_MIN_ENC_KEY_SIZE);
+		hcon->enc_key_size >= hcon->hdev->min_enc_key_size);
 }
 
 static void l2cap_do_start(struct l2cap_chan *chan)
-- 
cgit v1.2.3


From ef01adae0e43cfb2468d0ea07137cc63cf31495c Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 16 Aug 2019 03:24:09 +0200
Subject: net: sched: use major priority number as hardware priority

tc transparently maps the software priority number to hardware. Update
it to pass the major priority which is what most drivers expect. Update
drivers too so they do not need to lshift the priority field of the
flow_cls_common_offload object. The stmmac driver is an exception, since
this code assumes the tc software priority is fine, therefore, lshift it
just to be conservative.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c      |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c   |  2 +-
 drivers/net/ethernet/mscc/ocelot_flower.c            | 12 +++---------
 drivers/net/ethernet/netronome/nfp/flower/qos_conf.c |  2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c      |  2 +-
 include/net/pkt_cls.h                                |  2 +-
 6 files changed, 8 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index deeb65da99f3..00b2d4a86159 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -3167,7 +3167,7 @@ mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr,
 
 	esw_attr->parse_attr = parse_attr;
 	esw_attr->chain = f->common.chain_index;
-	esw_attr->prio = TC_H_MAJ(f->common.prio) >> 16;
+	esw_attr->prio = f->common.prio;
 
 	esw_attr->in_rep = in_rep;
 	esw_attr->in_mdev = in_mdev;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index e8ac90564dbe..84a87d059333 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -471,7 +471,7 @@ int mlxsw_sp_acl_rulei_commit(struct mlxsw_sp_acl_rule_info *rulei)
 void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
 				 unsigned int priority)
 {
-	rulei->priority = priority >> 16;
+	rulei->priority = priority;
 }
 
 void mlxsw_sp_acl_rulei_keymask_u32(struct mlxsw_sp_acl_rule_info *rulei,
diff --git a/drivers/net/ethernet/mscc/ocelot_flower.c b/drivers/net/ethernet/mscc/ocelot_flower.c
index 59487d446a09..b894bc0c9c16 100644
--- a/drivers/net/ethernet/mscc/ocelot_flower.c
+++ b/drivers/net/ethernet/mscc/ocelot_flower.c
@@ -13,12 +13,6 @@ struct ocelot_port_block {
 	struct ocelot_port *port;
 };
 
-static u16 get_prio(u32 prio)
-{
-	/* prio starts from 0x1000 while the ids starts from 0 */
-	return prio >> 16;
-}
-
 static int ocelot_flower_parse_action(struct flow_cls_offload *f,
 				      struct ocelot_ace_rule *rule)
 {
@@ -168,7 +162,7 @@ static int ocelot_flower_parse(struct flow_cls_offload *f,
 	}
 
 finished_key_parsing:
-	ocelot_rule->prio = get_prio(f->common.prio);
+	ocelot_rule->prio = f->common.prio;
 	ocelot_rule->id = f->cookie;
 	return ocelot_flower_parse_action(f, ocelot_rule);
 }
@@ -218,7 +212,7 @@ static int ocelot_flower_destroy(struct flow_cls_offload *f,
 	struct ocelot_ace_rule rule;
 	int ret;
 
-	rule.prio = get_prio(f->common.prio);
+	rule.prio = f->common.prio;
 	rule.port = port_block->port;
 	rule.id = f->cookie;
 
@@ -236,7 +230,7 @@ static int ocelot_flower_stats_update(struct flow_cls_offload *f,
 	struct ocelot_ace_rule rule;
 	int ret;
 
-	rule.prio = get_prio(f->common.prio);
+	rule.prio = f->common.prio;
 	rule.port = port_block->port;
 	rule.id = f->cookie;
 	ret = ocelot_ace_rule_stats_update(&rule);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
index 86e968cd5ffd..124a43dc136a 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/qos_conf.c
@@ -93,7 +93,7 @@ nfp_flower_install_rate_limiter(struct nfp_app *app, struct net_device *netdev,
 		return -EOPNOTSUPP;
 	}
 
-	if (flow->common.prio != (1 << 16)) {
+	if (flow->common.prio != 1) {
 		NL_SET_ERR_MSG_MOD(extack, "unsupported offload: qos rate limit offload requires highest priority");
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 37c0bc699cd9..6c305b6ecad0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -94,7 +94,7 @@ static int tc_fill_entry(struct stmmac_priv *priv,
 	struct stmmac_tc_entry *entry, *frag = NULL;
 	struct tc_u32_sel *sel = cls->knode.sel;
 	u32 off, data, mask, real_off, rem;
-	u32 prio = cls->common.prio;
+	u32 prio = cls->common.prio << 16;
 	int ret;
 
 	/* Only 1 match per entry */
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e429809ca90d..98be18ef1ed3 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -646,7 +646,7 @@ tc_cls_common_offload_init(struct flow_cls_common_offload *cls_common,
 {
 	cls_common->chain_index = tp->chain->index;
 	cls_common->protocol = tp->protocol;
-	cls_common->prio = tp->prio;
+	cls_common->prio = tp->prio >> 16;
 	if (tc_skip_sw(flags) || flags & TCA_CLS_FLAGS_VERBOSE)
 		cls_common->extack = extack;
 }
-- 
cgit v1.2.3


From 3bc158f8d0330f0ac58597c023acca2234c14616 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 16 Aug 2019 03:24:10 +0200
Subject: netfilter: nf_tables: map basechain priority to hardware priority

This patch adds initial support for offloading basechains using the
priority range from 1 to 65535. This is restricting the netfilter
priority range to 16-bit integer since this is what most drivers assume
so far from tc. It should be possible to extend this range of supported
priorities later on once drivers are updated to support for 32-bit
integer priorities.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/nf_tables_offload.h |  2 ++
 net/netfilter/nf_tables_api.c             |  4 ++++
 net/netfilter/nf_tables_offload.c         | 17 ++++++++++++++---
 3 files changed, 20 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/netfilter/nf_tables_offload.h b/include/net/netfilter/nf_tables_offload.h
index 3196663a10e3..c8b9dec376f5 100644
--- a/include/net/netfilter/nf_tables_offload.h
+++ b/include/net/netfilter/nf_tables_offload.h
@@ -73,4 +73,6 @@ int nft_flow_rule_offload_commit(struct net *net);
 	(__reg)->key		= __key;				\
 	memset(&(__reg)->mask, 0xff, (__reg)->len);
 
+int nft_chain_offload_priority(struct nft_base_chain *basechain);
+
 #endif
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 88abbddf8967..d47469f824a1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1667,6 +1667,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 
 		chain->flags |= NFT_BASE_CHAIN | flags;
 		basechain->policy = NF_ACCEPT;
+		if (chain->flags & NFT_CHAIN_HW_OFFLOAD &&
+		    nft_chain_offload_priority(basechain) < 0)
+			return -EOPNOTSUPP;
+
 		flow_block_init(&basechain->flow_block);
 	} else {
 		chain = kzalloc(sizeof(*chain), GFP_KERNEL);
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 64f5fd5f240e..c0d18c1d77ac 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -103,10 +103,11 @@ void nft_offload_update_dependency(struct nft_offload_ctx *ctx,
 }
 
 static void nft_flow_offload_common_init(struct flow_cls_common_offload *common,
-					 __be16 proto,
-					struct netlink_ext_ack *extack)
+					 __be16 proto, int priority,
+					 struct netlink_ext_ack *extack)
 {
 	common->protocol = proto;
+	common->prio = priority;
 	common->extack = extack;
 }
 
@@ -124,6 +125,15 @@ static int nft_setup_cb_call(struct nft_base_chain *basechain,
 	return 0;
 }
 
+int nft_chain_offload_priority(struct nft_base_chain *basechain)
+{
+	if (basechain->ops.priority <= 0 ||
+	    basechain->ops.priority > USHRT_MAX)
+		return -1;
+
+	return 0;
+}
+
 static int nft_flow_offload_rule(struct nft_trans *trans,
 				 enum flow_cls_command command)
 {
@@ -142,7 +152,8 @@ static int nft_flow_offload_rule(struct nft_trans *trans,
 	if (flow)
 		proto = flow->proto;
 
-	nft_flow_offload_common_init(&cls_flow.common, proto, &extack);
+	nft_flow_offload_common_init(&cls_flow.common, proto,
+				     basechain->ops.priority, &extack);
 	cls_flow.command = command;
 	cls_flow.cookie = (unsigned long) rule;
 	if (flow)
-- 
cgit v1.2.3