[PATCH AUTOSEL 4.19 068/209] ixgbe: Fix ixgbe TX hangs with XDP_TX beyond queue limit

[PATCH AUTOSEL 4.19 068/209] ixgbe: Fix ixgbe TX hangs with XDP_TX beyond queue limit

[Sasha Levin]

From: Radoslaw Tyl <radoslawx.tyl@intel.com>

[ Upstream commit 8d7179b1e2d64b3493c0114916486fe92e6109a9 ]

We have Tx hang when number Tx and XDP queues are more than 64.
In XDP always is MTQC == 0x0 (64TxQs). We need more space for Tx queues.

Signed-off-by: Radoslaw Tyl <radoslawx.tyl@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 85280765d793d..f3e21de3b1f0b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3582,12 +3582,18 @@ static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter)
 		else
 			mtqc |= IXGBE_MTQC_64VF;
 	} else {
-		if (tcs > 4)
+		if (tcs > 4) {
 			mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ;
-		else if (tcs > 1)
+		} else if (tcs > 1) {
 			mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
-		else
-			mtqc = IXGBE_MTQC_64Q_1PB;
+		} else {
+			u8 max_txq = adapter->num_tx_queues +
+				adapter->num_xdp_queues;
+			if (max_txq > 63)
+				mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ;
+			else
+				mtqc = IXGBE_MTQC_64Q_1PB;
+		}
 	}
 
 	IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc);
-- 
2.20.1

[PATCH AUTOSEL 4.19 124/209] tc-testing: fix build of eBPF programs

[Sasha Levin]

From: Davide Caratti <dcaratti@redhat.com>

[ Upstream commit cf5eafbfa586d030f9321cee516b91d089e38280 ]

rely on uAPI headers in the current kernel tree, rather than requiring the
correct version installed on the test system. While at it, group all
sections in a single binary and test the 'section' parameter.

Reported-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../testing/selftests/tc-testing/bpf/Makefile | 29 +++++++++++++++++++
 .../testing/selftests/tc-testing/bpf/action.c | 23 +++++++++++++++
 .../tc-testing/tc-tests/actions/bpf.json      | 16 +++++-----
 .../selftests/tc-testing/tdc_config.py        |  4 ++-
 4 files changed, 63 insertions(+), 9 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/bpf/Makefile
 create mode 100644 tools/testing/selftests/tc-testing/bpf/action.c

diff --git a/tools/testing/selftests/tc-testing/bpf/Makefile b/tools/testing/selftests/tc-testing/bpf/Makefile
new file mode 100644
index 0000000000000..dc92eb271d9a1
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/bpf/Makefile
@@ -0,0 +1,29 @@
+# SPDX-License-Identifier: GPL-2.0
+
+APIDIR := ../../../../include/uapi
+TEST_GEN_FILES = action.o
+
+top_srcdir = ../../../../..
+include ../../lib.mk
+
+CLANG ?= clang
+LLC   ?= llc
+PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1)
+
+ifeq ($(PROBE),)
+  CPU ?= probe
+else
+  CPU ?= generic
+endif
+
+CLANG_SYS_INCLUDES := $(shell $(CLANG) -v -E - </dev/null 2>&1 \
+	| sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }')
+
+CLANG_FLAGS = -I. -I$(APIDIR) \
+	      $(CLANG_SYS_INCLUDES) \
+	      -Wno-compare-distinct-pointer-types
+
+$(OUTPUT)/%.o: %.c
+	$(CLANG) $(CLANG_FLAGS) \
+		 -O2 -target bpf -emit-llvm -c $< -o - |      \
+	$(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@
diff --git a/tools/testing/selftests/tc-testing/bpf/action.c b/tools/testing/selftests/tc-testing/bpf/action.c
new file mode 100644
index 0000000000000..c32b99b80e19e
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/bpf/action.c
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018 Davide Caratti, Red Hat inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ */
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+
+__attribute__((section("action-ok"),used)) int action_ok(struct __sk_buff *s)
+{
+	return TC_ACT_OK;
+}
+
+__attribute__((section("action-ko"),used)) int action_ko(struct __sk_buff *s)
+{
+	s->data = 0x0;
+	return TC_ACT_OK;
+}
+
+char _license[] __attribute__((section("license"),used)) = "GPL";
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
index 6f289a49e5ecf..1a9b282dd0be2 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/bpf.json
@@ -55,7 +55,7 @@
             "bpf"
         ],
         "setup": [
-            "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { return 2; }' | clang -O2 -x c -c - -target bpf -o _b.o",
+            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -63,14 +63,14 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file _b.o index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ok index 667",
         "expExitCode": "0",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _b.o:\\[action\\] id [0-9]* tag 3b185187f1855c4c( jited)? default-action pipe.*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ok\\] id [0-9]* tag [0-9a-f]{16}( jited)? default-action pipe.*index 667 ref",
         "matchCount": "1",
         "teardown": [
             "$TC action flush action bpf",
-            "rm -f _b.o"
+            "make -C bpf clean"
         ]
     },
     {
@@ -81,7 +81,7 @@
             "bpf"
         ],
         "setup": [
-            "printf '#include <linux/bpf.h>\nchar l[] __attribute__((section(\"license\"),used))=\"GPL\"; __attribute__((section(\"action\"),used)) int m(struct __sk_buff *s) { s->data = 0x0; return 2; }' | clang -O2 -x c -c - -target bpf -o _c.o",
+            "make -C bpf",
             [
                 "$TC action flush action bpf",
                 0,
@@ -89,10 +89,10 @@
                 255
             ]
         ],
-        "cmdUnderTest": "$TC action add action bpf object-file _c.o index 667",
+        "cmdUnderTest": "$TC action add action bpf object-file $EBPFDIR/action.o section action-ko index 667",
         "expExitCode": "255",
         "verifyCmd": "$TC action get action bpf index 667",
-        "matchPattern": "action order [0-9]*: bpf _c.o:\\[action\\] id [0-9].*index 667 ref",
+        "matchPattern": "action order [0-9]*: bpf action.o:\\[action-ko\\] id [0-9].*index 667 ref",
         "matchCount": "0",
         "teardown": [
             [
@@ -101,7 +101,7 @@
                 1,
                 255
             ],
-            "rm -f _c.o"
+            "make -C bpf clean"
         ]
     },
     {
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index a023d0d62b25c..d651bc1501bdb 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -16,7 +16,9 @@ NAMES = {
           'DEV2': '',
           'BATCH_FILE': './batch.txt',
           # Name of the namespace to use
-          'NS': 'tcut'
+          'NS': 'tcut',
+          # Directory containing eBPF test programs
+          'EBPFDIR': './bpf'
         }
 
 
-- 
2.20.1

[PATCH AUTOSEL 4.19 135/209] xsk: proper AF_XDP socket teardown ordering

[Sasha Levin]

From: Björn Töpel <bjorn.topel@intel.com>

[ Upstream commit 541d7fdd7694560404c502f64298a90ffe017e6b ]

The AF_XDP socket struct can exist in three different, implicit
states: setup, bound and released. Setup is prior the socket has been
bound to a device. Bound is when the socket is active for receive and
send. Released is when the process/userspace side of the socket is
released, but the sock object is still lingering, e.g. when there is a
reference to the socket in an XSKMAP after process termination.

The Rx fast-path code uses the "dev" member of struct xdp_sock to
check whether a socket is bound or relased, and the Tx code uses the
struct xdp_umem "xsk_list" member in conjunction with "dev" to
determine the state of a socket.

However, the transition from bound to released did not tear the socket
down in correct order.

On the Rx side "dev" was cleared after synchronize_net() making the
synchronization useless. On the Tx side, the internal queues were
destroyed prior removing them from the "xsk_list".

This commit corrects the cleanup order, and by doing so
xdp_del_sk_umem() can be simplified and one synchronize_net() can be
removed.

Fixes: 965a99098443 ("xsk: add support for bind for Rx")
Fixes: ac98d8aab61b ("xsk: wire upp Tx zero-copy functions")
Reported-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/xdp/xdp_umem.c | 11 +++--------
 net/xdp/xsk.c      | 13 ++++++++-----
 2 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index 8cab91c482ff5..d9117ab035f7c 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -32,14 +32,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 {
 	unsigned long flags;
 
-	if (xs->dev) {
-		spin_lock_irqsave(&umem->xsk_list_lock, flags);
-		list_del_rcu(&xs->list);
-		spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
-
-		if (umem->zc)
-			synchronize_net();
-	}
+	spin_lock_irqsave(&umem->xsk_list_lock, flags);
+	list_del_rcu(&xs->list);
+	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
 }
 
 int xdp_umem_query(struct net_device *dev, u16 queue_id)
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 661504042d304..ff15207036dc5 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -343,12 +343,18 @@ static int xsk_release(struct socket *sock)
 	local_bh_enable();
 
 	if (xs->dev) {
+		struct net_device *dev = xs->dev;
+
 		/* Wait for driver to stop using the xdp socket. */
-		synchronize_net();
-		dev_put(xs->dev);
+		xdp_del_sk_umem(xs->umem, xs);
 		xs->dev = NULL;
+		synchronize_net();
+		dev_put(dev);
 	}
 
+	xskq_destroy(xs->rx);
+	xskq_destroy(xs->tx);
+
 	sock_orphan(sk);
 	sock->sk = NULL;
 
@@ -707,9 +713,6 @@ static void xsk_destruct(struct sock *sk)
 	if (!sock_flag(sk, SOCK_DEAD))
 		return;
 
-	xskq_destroy(xs->rx);
-	xskq_destroy(xs->tx);
-	xdp_del_sk_umem(xs->umem, xs);
 	xdp_put_umem(xs->umem);
 
 	sk_refcnt_debug_dec(sk);
-- 
2.20.1

[PATCH AUTOSEL 4.19 177/209] bpf: btf: Fix a missing check bug

[Sasha Levin]

From: Wenwen Wang <wang6495@umn.edu>

[ Upstream commit 8af03d1ae2e154a8be3631e8694b87007e1bdbc2 ]

In btf_parse_hdr(), the length of the btf data header is firstly copied
from the user space to 'hdr_len' and checked to see whether it is larger
than 'btf_data_size'. If yes, an error code EINVAL is returned. Otherwise,
the whole header is copied again from the user space to 'btf->hdr'.
However, after the second copy, there is no check between
'btf->hdr->hdr_len' and 'hdr_len' to confirm that the two copies get the
same value. Given that the btf data is in the user space, a malicious user
can race to change the data between the two copies. By doing so, the user
can provide malicious data to the kernel and cause undefined behavior.

This patch adds a necessary check after the second copy, to make sure
'btf->hdr->hdr_len' has the same value as 'hdr_len'. Otherwise, an error
code EINVAL will be returned.

Signed-off-by: Wenwen Wang <wang6495@umn.edu>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/btf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 138f0302692ec..378cef70341c4 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -2114,6 +2114,9 @@ static int btf_parse_hdr(struct btf_verifier_env *env, void __user *btf_data,
 
 	hdr = &btf->hdr;
 
+	if (hdr->hdr_len != hdr_len)
+		return -EINVAL;
+
 	btf_verifier_log_hdr(env, btf_data_size);
 
 	if (hdr->magic != BTF_MAGIC) {
-- 
2.20.1

[PATCH AUTOSEL 4.19 178/209] net: fix generic XDP to handle if eth header was mangled

[Sasha Levin]

From: Jesper Dangaard Brouer <brouer@redhat.com>

[ Upstream commit 2972495699320229b55b8e5065a310be5c81485b ]

XDP can modify (and resize) the Ethernet header in the packet.

There is a bug in generic-XDP, because skb->protocol and skb->pkt_type
are setup before reaching (netif_receive_)generic_xdp.

This bug was hit when XDP were popping VLAN headers (changing
eth->h_proto), as skb->protocol still contains VLAN-indication
(ETH_P_8021Q) causing invocation of skb_vlan_untag(skb), which corrupt
the packet (basically popping the VLAN again).

This patch catch if XDP changed eth header in such a way, that SKB
fields needs to be updated.

V2: on request from Song Liu, use ETH_HLEN instead of mac_len,
in __skb_push() as eth_type_trans() use ETH_HLEN in paired skb_pull_inline().

Fixes: d445516966dc ("net: xdp: support xdp generic on virtual devices")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/core/dev.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index ddd8aab20adf2..3e8b468a9f264 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4296,6 +4296,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	struct netdev_rx_queue *rxqueue;
 	void *orig_data, *orig_data_end;
 	u32 metalen, act = XDP_DROP;
+	__be16 orig_eth_type;
+	struct ethhdr *eth;
+	bool orig_bcast;
 	int hlen, off;
 	u32 mac_len;
 
@@ -4336,6 +4339,9 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	xdp->data_hard_start = skb->data - skb_headroom(skb);
 	orig_data_end = xdp->data_end;
 	orig_data = xdp->data;
+	eth = (struct ethhdr *)xdp->data;
+	orig_bcast = is_multicast_ether_addr_64bits(eth->h_dest);
+	orig_eth_type = eth->h_proto;
 
 	rxqueue = netif_get_rxqueue(skb);
 	xdp->rxq = &rxqueue->xdp_rxq;
@@ -4359,6 +4365,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 
 	}
 
+	/* check if XDP changed eth hdr such SKB needs update */
+	eth = (struct ethhdr *)xdp->data;
+	if ((orig_eth_type != eth->h_proto) ||
+	    (orig_bcast != is_multicast_ether_addr_64bits(eth->h_dest))) {
+		__skb_push(skb, ETH_HLEN);
+		skb->protocol = eth_type_trans(skb, skb->dev);
+	}
+
 	switch (act) {
 	case XDP_REDIRECT:
 	case XDP_TX:
-- 
2.20.1