[PATCH AUTOSEL 5.15 04/13] xfrm: fix tunnel model fragmentation behavior

[PATCH AUTOSEL 5.15 04/13] xfrm: fix tunnel model fragmentation behavior

[Sasha Levin]

From: Lina Wang <lina.wang@mediatek.com>

[ Upstream commit 4ff2980b6bd2aa6b4ded3ce3b7c0ccfab29980af ]

in tunnel mode, if outer interface(ipv4) is less, it is easily to let
inner IPV6 mtu be less than 1280. If so, a Packet Too Big ICMPV6 message
is received. When send again, packets are fragmentized with 1280, they
are still rejected with ICMPV6(Packet Too Big) by xfrmi_xmit2().

According to RFC4213 Section3.2.2:
if (IPv4 path MTU - 20) is less than 1280
	if packet is larger than 1280 bytes
		Send ICMPv6 "packet too big" with MTU=1280
                Drop packet
        else
		Encapsulate but do not set the Don't Fragment
                flag in the IPv4 header.  The resulting IPv4
                packet might be fragmented by the IPv4 layer
                on the encapsulator or by some router along
                the IPv4 path.
	endif
else
	if packet is larger than (IPv4 path MTU - 20)
        	Send ICMPv6 "packet too big" with
                MTU = (IPv4 path MTU - 20).
                Drop packet.
        else
                Encapsulate and set the Don't Fragment flag
                in the IPv4 header.
        endif
endif
Packets should be fragmentized with ipv4 outer interface, so change it.

After it is fragemtized with ipv4, there will be double fragmenation.
No.48 & No.51 are ipv6 fragment packets, No.48 is double fragmentized,
then tunneled with IPv4(No.49& No.50), which obey spec. And received peer
cannot decrypt it rightly.

48              2002::10        2002::11 1296(length) IPv6 fragment (off=0 more=y ident=0xa20da5bc nxt=50)
49   0x0000 (0) 2002::10        2002::11 1304         IPv6 fragment (off=0 more=y ident=0x7448042c nxt=44)
50   0x0000 (0) 2002::10        2002::11 200          ESP (SPI=0x00035000)
51              2002::10        2002::11 180          Echo (ping) request
52   0x56dc     2002::10        2002::11 248          IPv6 fragment (off=1232 more=n ident=0xa20da5bc nxt=50)

xfrm6_noneed_fragment has fixed above issues. Finally, it acted like below:
1   0x6206 192.168.1.138   192.168.1.1 1316 Fragmented IP protocol (proto=Encap Security Payload 50, off=0, ID=6206) [Reassembled in #2]
2   0x6206 2002::10        2002::11    88   IPv6 fragment (off=0 more=y ident=0x1f440778 nxt=50)
3   0x0000 2002::10        2002::11    248  ICMPv6    Echo (ping) request

Signed-off-by: Lina Wang <lina.wang@mediatek.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/ipv6/xfrm6_output.c   | 16 ++++++++++++++++
 net/xfrm/xfrm_interface.c |  5 ++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c
index d0d280077721..ad07904642ca 100644
--- a/net/ipv6/xfrm6_output.c
+++ b/net/ipv6/xfrm6_output.c
@@ -45,6 +45,19 @@ static int __xfrm6_output_finish(struct net *net, struct sock *sk, struct sk_buf
 	return xfrm_output(sk, skb);
 }
 
+static int xfrm6_noneed_fragment(struct sk_buff *skb)
+{
+	struct frag_hdr *fh;
+	u8 prevhdr = ipv6_hdr(skb)->nexthdr;
+
+	if (prevhdr != NEXTHDR_FRAGMENT)
+		return 0;
+	fh = (struct frag_hdr *)(skb->data + sizeof(struct ipv6hdr));
+	if (fh->nexthdr == NEXTHDR_ESP || fh->nexthdr == NEXTHDR_AUTH)
+		return 1;
+	return 0;
+}
+
 static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb);
@@ -73,6 +86,9 @@ static int __xfrm6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		xfrm6_local_rxpmtu(skb, mtu);
 		kfree_skb(skb);
 		return -EMSGSIZE;
+	} else if (toobig && xfrm6_noneed_fragment(skb)) {
+		skb->ignore_df = 1;
+		goto skip_frag;
 	} else if (!skb->ignore_df && toobig && skb->sk) {
 		xfrm_local_error(skb, mtu);
 		kfree_skb(skb);
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 4e3c62d1ad9e..1e8b26eecb3f 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -304,7 +304,10 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 			if (mtu < IPV6_MIN_MTU)
 				mtu = IPV6_MIN_MTU;
 
-			icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			if (skb->len > 1280)
+				icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+			else
+				goto xmit;
 		} else {
 			if (!(ip_hdr(skb)->frag_off & htons(IP_DF)))
 				goto xmit;
-- 
2.34.1

[PATCH AUTOSEL 5.15 08/13] Revert "xfrm: state and policy should fail if XFRMA_IF_ID 0"

[Sasha Levin]

From: Kai Lueke <kailueke@linux.microsoft.com>

[ Upstream commit a3d9001b4e287fc043e5539d03d71a32ab114bcb ]

This reverts commit 68ac0f3810e76a853b5f7b90601a05c3048b8b54 because ID
0 was meant to be used for configuring the policy/state without
matching for a specific interface (e.g., Cilium is affected, see
https://github.com/cilium/cilium/pull/18789 and
https://github.com/cilium/cilium/pull/19019).

Signed-off-by: Kai Lueke <kailueke@linux.microsoft.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/xfrm/xfrm_user.c | 21 +++------------------
 1 file changed, 3 insertions(+), 18 deletions(-)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index b10f88822c0d..e13198f7e4e9 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -629,13 +629,8 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 
 	xfrm_smark_init(attrs, &x->props.smark);
 
-	if (attrs[XFRMA_IF_ID]) {
+	if (attrs[XFRMA_IF_ID])
 		x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
-		if (!x->if_id) {
-			err = -EINVAL;
-			goto error;
-		}
-	}
 
 	err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]);
 	if (err)
@@ -1431,13 +1426,8 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	mark = xfrm_mark_get(attrs, &m);
 
-	if (attrs[XFRMA_IF_ID]) {
+	if (attrs[XFRMA_IF_ID])
 		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
-		if (!if_id) {
-			err = -EINVAL;
-			goto out_noput;
-		}
-	}
 
 	if (p->info.seq) {
 		x = xfrm_find_acq_byseq(net, mark, p->info.seq);
@@ -1750,13 +1740,8 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us
 
 	xfrm_mark_get(attrs, &xp->mark);
 
-	if (attrs[XFRMA_IF_ID]) {
+	if (attrs[XFRMA_IF_ID])
 		xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
-		if (!xp->if_id) {
-			err = -EINVAL;
-			goto error;
-		}
-	}
 
 	return xp;
  error:
-- 
2.34.1

[PATCH AUTOSEL 5.15 10/13] ethernet: sun: Free the coherent when failing in probing

[Sasha Levin]

From: Zheyu Ma <zheyuma97@gmail.com>

[ Upstream commit bb77bd31c281f70ec77c9c4f584950a779e05cf8 ]

When the driver fails to register net device, it should free the DMA
region first, and then do other cleanup.

Signed-off-by: Zheyu Ma <zheyuma97@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/sun/sunhme.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sun/sunhme.c b/drivers/net/ethernet/sun/sunhme.c
index 62f81b0d14ed..b05ee2e0e305 100644
--- a/drivers/net/ethernet/sun/sunhme.c
+++ b/drivers/net/ethernet/sun/sunhme.c
@@ -3139,7 +3139,7 @@ static int happy_meal_pci_probe(struct pci_dev *pdev,
 	if (err) {
 		printk(KERN_ERR "happymeal(PCI): Cannot register net device, "
 		       "aborting.\n");
-		goto err_out_iounmap;
+		goto err_out_free_coherent;
 	}
 
 	pci_set_drvdata(pdev, hp);
@@ -3172,6 +3172,10 @@ static int happy_meal_pci_probe(struct pci_dev *pdev,
 
 	return 0;
 
+err_out_free_coherent:
+	dma_free_coherent(hp->dma_dev, PAGE_SIZE,
+			  hp->happy_block, hp->hblock_dvma);
+
 err_out_iounmap:
 	iounmap(hp->gregs);
 
-- 
2.34.1

[PATCH AUTOSEL 5.15 13/13] net:mcf8390: Use platform_get_irq() to get the interrupt

[Sasha Levin]

From: "Minghao Chi (CGEL ZTE)" <chi.minghao@zte.com.cn>

[ Upstream commit 2a760554dcba450d3ad61b32375b50ed6d59a87c ]

It is not recommened to use platform_get_resource(pdev, IORESOURCE_IRQ)
for requesting IRQ's resources any more, as they can be not ready yet in
case of DT-booting.

platform_get_irq() instead is a recommended way for getting IRQ even if
it was not retrieved earlier.

It also makes code simpler because we're getting "int" value right away
and no conversion from resource to int is required.

Reported-by: Zeal Robot <zealci@zte.com.cn>
Signed-off-by: Minghao Chi (CGEL ZTE) <chi.minghao@zte.com.cn>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/8390/mcf8390.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/8390/mcf8390.c b/drivers/net/ethernet/8390/mcf8390.c
index 4ad8031ab669..065fdbe66c42 100644
--- a/drivers/net/ethernet/8390/mcf8390.c
+++ b/drivers/net/ethernet/8390/mcf8390.c
@@ -406,12 +406,12 @@ static int mcf8390_init(struct net_device *dev)
 static int mcf8390_probe(struct platform_device *pdev)
 {
 	struct net_device *dev;
-	struct resource *mem, *irq;
+	struct resource *mem;
 	resource_size_t msize;
-	int ret;
+	int ret, irq;
 
-	irq = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (irq == NULL) {
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
 		dev_err(&pdev->dev, "no IRQ specified?\n");
 		return -ENXIO;
 	}
@@ -434,7 +434,7 @@ static int mcf8390_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 	platform_set_drvdata(pdev, dev);
 
-	dev->irq = irq->start;
+	dev->irq = irq;
 	dev->base_addr = mem->start;
 
 	ret = mcf8390_init(dev);
-- 
2.34.1