* [PATCH AUTOSEL 4.20 55/72] net: macb: Apply RXUBR workaround only to versions with errata
From: Sasha Levin @ 2019-02-23 21:04 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Harini Katakam, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210422.199966-1-sashal@kernel.org>
From: Harini Katakam <harini.katakam@xilinx.com>
[ Upstream commit e501070e4db0b67a4c17a5557d1e9d098f3db310 ]
The interrupt handler contains a workaround for RX hang applicable
to Zynq and AT91RM9200 only. Subsequent versions do not need this
workaround. This workaround unnecessarily resets RX whenever RX used
bit read is observed, which can be often under heavy traffic. There
is no other action performed on RX UBR interrupt. Hence introduce a
CAPS mask; enable this interrupt and workaround only on affected
versions.
Signed-off-by: Harini Katakam <harini.katakam@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/cadence/macb.h | 3 +++
drivers/net/ethernet/cadence/macb_main.c | 28 ++++++++++++++----------
2 files changed, 20 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 3d45f4c92cf6e..9bbaad9f3d632 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -643,6 +643,7 @@
#define MACB_CAPS_JUMBO 0x00000020
#define MACB_CAPS_GEM_HAS_PTP 0x00000040
#define MACB_CAPS_BD_RD_PREFETCH 0x00000080
+#define MACB_CAPS_NEEDS_RSTONUBR 0x00000100
#define MACB_CAPS_FIFO_MODE 0x10000000
#define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000
#define MACB_CAPS_SG_DISABLED 0x40000000
@@ -1214,6 +1215,8 @@ struct macb {
int rx_bd_rd_prefetch;
int tx_bd_rd_prefetch;
+
+ u32 rx_intr_mask;
};
#ifdef CONFIG_MACB_USE_HWSTAMP
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4c816e5a841fa..73aa7969db962 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -56,8 +56,7 @@
/* level of occupied TX descriptors under which we wake up TX process */
#define MACB_TX_WAKEUP_THRESH(bp) (3 * (bp)->tx_ring_size / 4)
-#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(RXUBR) \
- | MACB_BIT(ISR_ROVR))
+#define MACB_RX_INT_FLAGS (MACB_BIT(RCOMP) | MACB_BIT(ISR_ROVR))
#define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \
| MACB_BIT(ISR_RLE) \
| MACB_BIT(TXERR))
@@ -1270,7 +1269,7 @@ static int macb_poll(struct napi_struct *napi, int budget)
queue_writel(queue, ISR, MACB_BIT(RCOMP));
napi_reschedule(napi);
} else {
- queue_writel(queue, IER, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IER, bp->rx_intr_mask);
}
}
@@ -1288,7 +1287,7 @@ static void macb_hresp_error_task(unsigned long data)
u32 ctrl;
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
- queue_writel(queue, IDR, MACB_RX_INT_FLAGS |
+ queue_writel(queue, IDR, bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
@@ -1318,7 +1317,7 @@ static void macb_hresp_error_task(unsigned long data)
/* Enable interrupts */
queue_writel(queue, IER,
- MACB_RX_INT_FLAGS |
+ bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
@@ -1372,14 +1371,14 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
(unsigned int)(queue - bp->queues),
(unsigned long)status);
- if (status & MACB_RX_INT_FLAGS) {
+ if (status & bp->rx_intr_mask) {
/* There's no point taking any more interrupts
* until we have processed the buffers. The
* scheduling call may fail if the poll routine
* is already scheduled, so disable interrupts
* now.
*/
- queue_writel(queue, IDR, MACB_RX_INT_FLAGS);
+ queue_writel(queue, IDR, bp->rx_intr_mask);
if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
queue_writel(queue, ISR, MACB_BIT(RCOMP));
@@ -1412,8 +1411,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
/* There is a hardware issue under heavy load where DMA can
* stop, this causes endless "used buffer descriptor read"
* interrupts but it can be cleared by re-enabling RX. See
- * the at91 manual, section 41.3.1 or the Zynq manual
- * section 16.7.4 for details.
+ * the at91rm9200 manual, section 41.3.1 or the Zynq manual
+ * section 16.7.4 for details. RXUBR is only enabled for
+ * these two versions.
*/
if (status & MACB_BIT(RXUBR)) {
ctrl = macb_readl(bp, NCR);
@@ -2263,7 +2263,7 @@ static void macb_init_hw(struct macb *bp)
/* Enable interrupts */
queue_writel(queue, IER,
- MACB_RX_INT_FLAGS |
+ bp->rx_intr_mask |
MACB_TX_INT_FLAGS |
MACB_BIT(HRESP));
}
@@ -3911,6 +3911,7 @@ static const struct macb_config sama5d4_config = {
};
static const struct macb_config emac_config = {
+ .caps = MACB_CAPS_NEEDS_RSTONUBR,
.clk_init = at91ether_clk_init,
.init = at91ether_init,
};
@@ -3932,7 +3933,8 @@ static const struct macb_config zynqmp_config = {
};
static const struct macb_config zynq_config = {
- .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF,
+ .caps = MACB_CAPS_GIGABIT_MODE_AVAILABLE | MACB_CAPS_NO_GIGABIT_HALF |
+ MACB_CAPS_NEEDS_RSTONUBR,
.dma_burst_length = 16,
.clk_init = macb_clk_init,
.init = macb_init,
@@ -4087,6 +4089,10 @@ static int macb_probe(struct platform_device *pdev)
macb_dma_desc_get_size(bp);
}
+ bp->rx_intr_mask = MACB_RX_INT_FLAGS;
+ if (bp->caps & MACB_CAPS_NEEDS_RSTONUBR)
+ bp->rx_intr_mask |= MACB_BIT(RXUBR);
+
mac = of_get_mac_address(np);
if (mac) {
ether_addr_copy(bp->dev->dev_addr, mac);
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.19 01/65] vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel
From: Sasha Levin @ 2019-02-23 21:05 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Su Yanjun, Steffen Klassert, Sasha Levin, netdev
From: Su Yanjun <suyj.fnst@cn.fujitsu.com>
[ Upstream commit dd9ee3444014e8f28c0eefc9fffc9ac9c5248c12 ]
Recently we run a network test over ipcomp virtual tunnel.We find that
if a ipv4 packet needs fragment, then the peer can't receive
it.
We deep into the code and find that when packet need fragment the smaller
fragment will be encapsulated by ipip not ipcomp. So when the ipip packet
goes into xfrm, it's skb->dev is not properly set. The ipv4 reassembly code
always set skb'dev to the last fragment's dev. After ipv4 defrag processing,
when the kernel rp_filter parameter is set, the skb will be drop by -EXDEV
error.
This patch adds compatible support for the ipip process in ipcomp virtual tunnel.
Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/ipv4/ip_vti.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 7f56944b020f6..40a7cd56e0087 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -74,6 +74,33 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
return 0;
}
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb)
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
@@ -435,6 +470,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.priority = 100,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
@@ -603,6 +644,13 @@ static int __init vti_init(void)
if (err < 0)
goto xfrm_proto_comp_failed;
+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
@@ -612,6 +660,8 @@ static int __init vti_init(void)
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.19 05/65] netfilter: nft_compat: make lists per netns
From: Sasha Levin @ 2019-02-23 21:05 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Florian Westphal, Pablo Neira Ayuso, Sasha Levin, netfilter-devel,
coreteam, netdev
In-Reply-To: <20190223210640.200911-1-sashal@kernel.org>
From: Florian Westphal <fw@strlen.de>
[ Upstream commit cf52572ebbd7189a1966c2b5fc34b97078cd1dce ]
There are two problems with nft_compat since the netlink config
plane uses a per-netns mutex:
1. Concurrent add/del accesses to the same list
2. accesses to a list element after it has been free'd already.
This patch fixes the first problem.
Freeing occurs from a work queue, after transaction mutexes have been
released, i.e., it still possible for a new transaction (even from
same net ns) to find the to-be-deleted expression in the list.
The ->destroy functions are not allowed to have any such side effects,
i.e. the list_del() in the destroy function is not allowed.
This part of the problem is solved in the next patch.
I tried to make this work by serializing list access via mutex
and by moving list_del() to a deactivate callback, but
Taehee spotted following race on this approach:
NET #0 NET #1
>select_ops()
->init()
->select_ops()
->deactivate()
->destroy()
nft_xt_put()
kfree_rcu(xt, rcu_head);
->init() <-- use-after-free occurred.
Unfortunately, we can't increment reference count in
select_ops(), because we can't undo the refcount increase in
case a different expression fails in the same batch.
(The destroy hook will only be called in case the expression
was initialized successfully).
Fixes: f102d66b335a ("netfilter: nf_tables: use dedicated mutex to guard transactions")
Reported-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/netfilter/nft_compat.c | 129 +++++++++++++++++++++++++------------
1 file changed, 89 insertions(+), 40 deletions(-)
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 3e629ee59ddab..c56eb909f718c 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -22,6 +22,7 @@
#include <linux/netfilter_bridge/ebtables.h>
#include <linux/netfilter_arp/arp_tables.h>
#include <net/netfilter/nf_tables.h>
+#include <net/netns/generic.h>
struct nft_xt {
struct list_head head;
@@ -43,6 +44,20 @@ struct nft_xt_match_priv {
void *info;
};
+struct nft_compat_net {
+ struct list_head nft_target_list;
+ struct list_head nft_match_list;
+};
+
+static unsigned int nft_compat_net_id __read_mostly;
+static struct nft_expr_type nft_match_type;
+static struct nft_expr_type nft_target_type;
+
+static struct nft_compat_net *nft_compat_pernet(struct net *net)
+{
+ return net_generic(net, nft_compat_net_id);
+}
+
static bool nft_xt_put(struct nft_xt *xt)
{
if (refcount_dec_and_test(&xt->refcnt)) {
@@ -714,10 +729,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = {
.cb = nfnl_nft_compat_cb,
};
-static LIST_HEAD(nft_match_list);
-
-static struct nft_expr_type nft_match_type;
-
static bool nft_match_cmp(const struct xt_match *match,
const char *name, u32 rev, u32 family)
{
@@ -729,6 +740,7 @@ static const struct nft_expr_ops *
nft_match_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_match;
struct xt_match *match;
unsigned int matchsize;
@@ -745,8 +757,10 @@ nft_match_select_ops(const struct nft_ctx *ctx,
rev = ntohl(nla_get_be32(tb[NFTA_MATCH_REV]));
family = ctx->family;
+ cn = nft_compat_pernet(ctx->net);
+
/* Re-use the existing match if it's already loaded. */
- list_for_each_entry(nft_match, &nft_match_list, head) {
+ list_for_each_entry(nft_match, &cn->nft_match_list, head) {
struct xt_match *match = nft_match->ops.data;
if (nft_match_cmp(match, mt_name, rev, family))
@@ -790,7 +804,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
nft_match->ops.size = matchsize;
- list_add(&nft_match->head, &nft_match_list);
+ list_add(&nft_match->head, &cn->nft_match_list);
return &nft_match->ops;
err:
@@ -806,10 +820,6 @@ static struct nft_expr_type nft_match_type __read_mostly = {
.owner = THIS_MODULE,
};
-static LIST_HEAD(nft_target_list);
-
-static struct nft_expr_type nft_target_type;
-
static bool nft_target_cmp(const struct xt_target *tg,
const char *name, u32 rev, u32 family)
{
@@ -821,6 +831,7 @@ static const struct nft_expr_ops *
nft_target_select_ops(const struct nft_ctx *ctx,
const struct nlattr * const tb[])
{
+ struct nft_compat_net *cn;
struct nft_xt *nft_target;
struct xt_target *target;
char *tg_name;
@@ -841,8 +852,9 @@ nft_target_select_ops(const struct nft_ctx *ctx,
strcmp(tg_name, "standard") == 0)
return ERR_PTR(-EINVAL);
+ cn = nft_compat_pernet(ctx->net);
/* Re-use the existing target if it's already loaded. */
- list_for_each_entry(nft_target, &nft_target_list, head) {
+ list_for_each_entry(nft_target, &cn->nft_target_list, head) {
struct xt_target *target = nft_target->ops.data;
if (!target->target)
@@ -887,7 +899,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
else
nft_target->ops.eval = nft_target_eval_xt;
- list_add(&nft_target->head, &nft_target_list);
+ list_add(&nft_target->head, &cn->nft_target_list);
return &nft_target->ops;
err:
@@ -903,13 +915,74 @@ static struct nft_expr_type nft_target_type __read_mostly = {
.owner = THIS_MODULE,
};
+static int __net_init nft_compat_init_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+
+ INIT_LIST_HEAD(&cn->nft_target_list);
+ INIT_LIST_HEAD(&cn->nft_match_list);
+
+ return 0;
+}
+
+static void __net_exit nft_compat_exit_net(struct net *net)
+{
+ struct nft_compat_net *cn = nft_compat_pernet(net);
+ struct nft_xt *xt, *next;
+
+ if (list_empty(&cn->nft_match_list) &&
+ list_empty(&cn->nft_target_list))
+ return;
+
+ /* If there was an error that caused nft_xt expr to not be initialized
+ * fully and noone else requested the same expression later, the lists
+ * contain 0-refcount entries that still hold module reference.
+ *
+ * Clean them here.
+ */
+ mutex_lock(&net->nft.commit_mutex);
+ list_for_each_entry_safe(xt, next, &cn->nft_target_list, head) {
+ struct xt_target *target = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(target->me);
+ kfree(xt);
+ }
+
+ list_for_each_entry_safe(xt, next, &cn->nft_match_list, head) {
+ struct xt_match *match = xt->ops.data;
+
+ list_del_init(&xt->head);
+
+ if (refcount_read(&xt->refcnt))
+ continue;
+ module_put(match->me);
+ kfree(xt);
+ }
+ mutex_unlock(&net->nft.commit_mutex);
+}
+
+static struct pernet_operations nft_compat_net_ops = {
+ .init = nft_compat_init_net,
+ .exit = nft_compat_exit_net,
+ .id = &nft_compat_net_id,
+ .size = sizeof(struct nft_compat_net),
+};
+
static int __init nft_compat_module_init(void)
{
int ret;
+ ret = register_pernet_subsys(&nft_compat_net_ops);
+ if (ret < 0)
+ goto err_target;
+
ret = nft_register_expr(&nft_match_type);
if (ret < 0)
- return ret;
+ goto err_pernet;
ret = nft_register_expr(&nft_target_type);
if (ret < 0)
@@ -922,45 +995,21 @@ static int __init nft_compat_module_init(void)
}
return ret;
-
err_target:
nft_unregister_expr(&nft_target_type);
err_match:
nft_unregister_expr(&nft_match_type);
+err_pernet:
+ unregister_pernet_subsys(&nft_compat_net_ops);
return ret;
}
static void __exit nft_compat_module_exit(void)
{
- struct nft_xt *xt, *next;
-
- /* list should be empty here, it can be non-empty only in case there
- * was an error that caused nft_xt expr to not be initialized fully
- * and noone else requested the same expression later.
- *
- * In this case, the lists contain 0-refcount entries that still
- * hold module reference.
- */
- list_for_each_entry_safe(xt, next, &nft_target_list, head) {
- struct xt_target *target = xt->ops.data;
-
- if (WARN_ON_ONCE(refcount_read(&xt->refcnt)))
- continue;
- module_put(target->me);
- kfree(xt);
- }
-
- list_for_each_entry_safe(xt, next, &nft_match_list, head) {
- struct xt_match *match = xt->ops.data;
-
- if (WARN_ON_ONCE(refcount_read(&xt->refcnt)))
- continue;
- module_put(match->me);
- kfree(xt);
- }
nfnetlink_subsys_unregister(&nfnl_compat_subsys);
nft_unregister_expr(&nft_target_type);
nft_unregister_expr(&nft_match_type);
+ unregister_pernet_subsys(&nft_compat_net_ops);
}
MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT);
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.19 14/65] ipvs: Fix signed integer overflow when setsockopt timeout
From: Sasha Levin @ 2019-02-23 21:05 UTC (permalink / raw)
To: linux-kernel, stable
Cc: ZhangXiaoxu, Pablo Neira Ayuso, Sasha Levin, netdev, lvs-devel,
netfilter-devel, coreteam
In-Reply-To: <20190223210640.200911-1-sashal@kernel.org>
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
[ Upstream commit 53ab60baa1ac4f20b080a22c13b77b6373922fd7 ]
There is a UBSAN bug report as below:
UBSAN: Undefined behaviour in net/netfilter/ipvs/ip_vs_ctl.c:2227:21
signed integer overflow:
-2147483647 * 1000 cannot be represented in type 'int'
Reproduce program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#define IPPROTO_IP 0
#define IPPROTO_RAW 255
#define IP_VS_BASE_CTL (64+1024+64)
#define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10)
/* The argument to IP_VS_SO_GET_TIMEOUT */
struct ipvs_timeout_t {
int tcp_timeout;
int tcp_fin_timeout;
int udp_timeout;
};
int main() {
int ret = -1;
int sockfd = -1;
struct ipvs_timeout_t to;
sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
if (sockfd == -1) {
printf("socket init error\n");
return -1;
}
to.tcp_timeout = -2147483647;
to.tcp_fin_timeout = -2147483647;
to.udp_timeout = -2147483647;
ret = setsockopt(sockfd,
IPPROTO_IP,
IP_VS_SO_SET_TIMEOUT,
(char *)(&to),
sizeof(to));
printf("setsockopt return %d\n", ret);
return ret;
}
Return -EINVAL if the timeout value is negative or max than 'INT_MAX / HZ'.
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 518364f4abccd..55a77314340a5 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2220,6 +2220,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user
u->tcp_fin_timeout,
u->udp_timeout);
+#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.14 19/45] net: hns: Fix wrong read accesses via Clause 45 MDIO protocol
From: Sasha Levin @ 2019-02-23 21:08 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Yonglong Liu, Peng Li, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210835.201708-1-sashal@kernel.org>
From: Yonglong Liu <liuyonglong@huawei.com>
[ Upstream commit cec8abba13e6a26729dfed41019720068eeeff2b ]
When reading phy registers via Clause 45 MDIO protocol, after write
address operation, the driver use another write address operation, so
can not read the right value of any phy registers. This patch fixes it.
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 017e08452d8c0..baf5cc251f329 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -321,7 +321,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
}
hns_mdio_cmd_write(mdio_dev, is_c45,
- MDIO_C45_WRITE_ADDR, phy_id, devad);
+ MDIO_C45_READ, phy_id, devad);
}
/* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.14 18/45] net: hns: Restart autoneg need return failed when autoneg off
From: Sasha Levin @ 2019-02-23 21:08 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Yonglong Liu, Peng Li, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210835.201708-1-sashal@kernel.org>
From: Yonglong Liu <liuyonglong@huawei.com>
[ Upstream commit ed29ca8b9592562559c64d027fb5eb126e463e2c ]
The hns driver of earlier devices, when autoneg off, restart autoneg
will return -EINVAL, so make the hns driver for the latest devices
do the same.
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 16 +++++++++-------
1 file changed, 9 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index c1e947bb852ff..14df03f60e059 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -1154,16 +1154,18 @@ static int hns_get_regs_len(struct net_device *net_dev)
*/
static int hns_nic_nway_reset(struct net_device *netdev)
{
- int ret = 0;
struct phy_device *phy = netdev->phydev;
- if (netif_running(netdev)) {
- /* if autoneg is disabled, don't restart auto-negotiation */
- if (phy && phy->autoneg == AUTONEG_ENABLE)
- ret = genphy_restart_aneg(phy);
- }
+ if (!netif_running(netdev))
+ return 0;
- return ret;
+ if (!phy)
+ return -EOPNOTSUPP;
+
+ if (phy->autoneg != AUTONEG_ENABLE)
+ return -EINVAL;
+
+ return genphy_restart_aneg(phy);
}
static u32
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.14 17/45] net: hns: Fix for missing of_node_put() after of_parse_phandle()
From: Sasha Levin @ 2019-02-23 21:08 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Yonglong Liu, Peng Li, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210835.201708-1-sashal@kernel.org>
From: Yonglong Liu <liuyonglong@huawei.com>
[ Upstream commit 263c6d75f9a544a3c2f8f6a26de4f4808d8f59cf ]
In hns enet driver, we use of_parse_handle() to get hold of the
device node related to "ae-handle" but we have missed to put
the node reference using of_node_put() after we are done using
the node. This patch fixes it.
Note:
This problem is stated in Link: https://lkml.org/lkml/2018/12/22/217
Fixes: 48189d6aaf1e ("net: hns: enet specifies a reference to dsaf")
Reported-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 86662a14208eb..d30c28fba2499 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2532,6 +2532,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
out_notify_fail:
(void)cancel_work_sync(&priv->service_task);
out_read_prop_fail:
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
free_netdev(ndev);
return ret;
}
@@ -2561,6 +2563,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev)
set_bit(NIC_STATE_REMOVING, &priv->state);
(void)cancel_work_sync(&priv->service_task);
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
+
free_netdev(ndev);
return 0;
}
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 01/32] vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Su Yanjun, Steffen Klassert, Sasha Levin, netdev
From: Su Yanjun <suyj.fnst@cn.fujitsu.com>
[ Upstream commit dd9ee3444014e8f28c0eefc9fffc9ac9c5248c12 ]
Recently we run a network test over ipcomp virtual tunnel.We find that
if a ipv4 packet needs fragment, then the peer can't receive
it.
We deep into the code and find that when packet need fragment the smaller
fragment will be encapsulated by ipip not ipcomp. So when the ipip packet
goes into xfrm, it's skb->dev is not properly set. The ipv4 reassembly code
always set skb'dev to the last fragment's dev. After ipv4 defrag processing,
when the kernel rp_filter parameter is set, the skb will be drop by -EXDEV
error.
This patch adds compatible support for the ipip process in ipcomp virtual tunnel.
Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/ipv4/ip_vti.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index cbff0d6ff1ac8..270e79f4d40e6 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -74,6 +74,33 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
return 0;
}
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -82,6 +109,14 @@ static int vti_rcv(struct sk_buff *skb)
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
@@ -439,6 +474,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.priority = 100,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
@@ -622,6 +663,13 @@ static int __init vti_init(void)
if (err < 0)
goto xfrm_proto_comp_failed;
+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
@@ -631,6 +679,8 @@ static int __init vti_init(void)
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 02/26] xfrm: refine validation of template and selector families
From: Sasha Levin @ 2019-02-23 21:10 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Florian Westphal, Steffen Klassert, Sasha Levin, netdev
In-Reply-To: <20190223211047.202725-1-sashal@kernel.org>
From: Florian Westphal <fw@strlen.de>
[ Upstream commit 35e6103861a3a970de6c84688c6e7a1f65b164ca ]
The check assumes that in transport mode, the first templates family
must match the address family of the policy selector.
Syzkaller managed to build a template using MODE_ROUTEOPTIMIZATION,
with ipv4-in-ipv6 chain, leading to following splat:
BUG: KASAN: stack-out-of-bounds in xfrm_state_find+0x1db/0x1854
Read of size 4 at addr ffff888063e57aa0 by task a.out/2050
xfrm_state_find+0x1db/0x1854
xfrm_tmpl_resolve+0x100/0x1d0
xfrm_resolve_and_create_bundle+0x108/0x1000 [..]
Problem is that addresses point into flowi4 struct, but xfrm_state_find
treats them as being ipv6 because it uses templ->encap_family is used
(AF_INET6 in case of reproducer) rather than family (AF_INET).
This patch inverts the logic: Enforce 'template family must match
selector' EXCEPT for tunnel and BEET mode.
In BEET and Tunnel mode, xfrm_tmpl_resolve_one will have remote/local
address pointers changed to point at the addresses found in the template,
rather than the flowi ones, so no oob read will occur.
Reported-by: 3ntr0py1337@gmail.com
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/xfrm/xfrm_user.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 476f1fc6d655c..177a6c75f136b 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1404,10 +1404,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
if (!ut[i].family)
ut[i].family = family;
- if ((ut[i].mode == XFRM_MODE_TRANSPORT) &&
- (ut[i].family != prev_family))
- return -EINVAL;
-
+ switch (ut[i].mode) {
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ break;
+ default:
+ if (ut[i].family != prev_family)
+ return -EINVAL;
+ break;
+ }
if (ut[i].mode >= XFRM_MODE_MAX)
return -EINVAL;
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 3.18 10/18] net: altera_tse: fix msgdma_tx_completion on non-zero fill_level case
From: Sasha Levin @ 2019-02-23 21:11 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Tomonori Sakita, Atsushi Nemoto, David S . Miller, Sasha Levin,
netdev
In-Reply-To: <20190223211135.203082-1-sashal@kernel.org>
From: Tomonori Sakita <tomonori.sakita@sord.co.jp>
[ Upstream commit 6571ebce112a21ec9be68ef2f53b96fcd41fd81b ]
If fill_level was not zero and status was not BUSY,
result of "tx_prod - tx_cons - inuse" might be zero.
Subtracting 1 unconditionally results invalid negative return value
on this case.
Make sure not to return an negative value.
Signed-off-by: Tomonori Sakita <tomonori.sakita@sord.co.jp>
Signed-off-by: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Reviewed-by: Dalon L Westergreen <dalon.westergreen@linux.intel.com>
Acked-by: Thor Thayer <thor.thayer@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/altera/altera_msgdma.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 0fb986ba32905..0ae723f753417 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
& 0xffff;
if (inuse) { /* Tx FIFO is not empty */
- ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+ ready = max_t(int,
+ priv->tx_prod - priv->tx_cons - inuse - 1, 0);
} else {
/* Check for buffered last packet */
status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 3.18 04/18] ipvs: Fix signed integer overflow when setsockopt timeout
From: Sasha Levin @ 2019-02-23 21:11 UTC (permalink / raw)
To: linux-kernel, stable
Cc: ZhangXiaoxu, Pablo Neira Ayuso, Sasha Levin, netdev, lvs-devel,
netfilter-devel, coreteam
In-Reply-To: <20190223211135.203082-1-sashal@kernel.org>
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
[ Upstream commit 53ab60baa1ac4f20b080a22c13b77b6373922fd7 ]
There is a UBSAN bug report as below:
UBSAN: Undefined behaviour in net/netfilter/ipvs/ip_vs_ctl.c:2227:21
signed integer overflow:
-2147483647 * 1000 cannot be represented in type 'int'
Reproduce program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#define IPPROTO_IP 0
#define IPPROTO_RAW 255
#define IP_VS_BASE_CTL (64+1024+64)
#define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10)
/* The argument to IP_VS_SO_GET_TIMEOUT */
struct ipvs_timeout_t {
int tcp_timeout;
int tcp_fin_timeout;
int udp_timeout;
};
int main() {
int ret = -1;
int sockfd = -1;
struct ipvs_timeout_t to;
sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
if (sockfd == -1) {
printf("socket init error\n");
return -1;
}
to.tcp_timeout = -2147483647;
to.tcp_fin_timeout = -2147483647;
to.udp_timeout = -2147483647;
ret = setsockopt(sockfd,
IPPROTO_IP,
IP_VS_SO_SET_TIMEOUT,
(char *)(&to),
sizeof(to));
printf("setsockopt return %d\n", ret);
return ret;
}
Return -EINVAL if the timeout value is negative or max than 'INT_MAX / HZ'.
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 9b1452e8e868f..444a0cb33e979 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2182,6 +2182,18 @@ static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u)
u->tcp_fin_timeout,
u->udp_timeout);
+#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(net, IPPROTO_TCP);
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 3.18 01/18] vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel
From: Sasha Levin @ 2019-02-23 21:11 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Su Yanjun, Steffen Klassert, Sasha Levin, netdev
From: Su Yanjun <suyj.fnst@cn.fujitsu.com>
[ Upstream commit dd9ee3444014e8f28c0eefc9fffc9ac9c5248c12 ]
Recently we run a network test over ipcomp virtual tunnel.We find that
if a ipv4 packet needs fragment, then the peer can't receive
it.
We deep into the code and find that when packet need fragment the smaller
fragment will be encapsulated by ipip not ipcomp. So when the ipip packet
goes into xfrm, it's skb->dev is not properly set. The ipv4 reassembly code
always set skb'dev to the last fragment's dev. After ipv4 defrag processing,
when the kernel rp_filter parameter is set, the skb will be drop by -EXDEV
error.
This patch adds compatible support for the ipip process in ipcomp virtual tunnel.
Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/ipv4/ip_vti.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index c35e0aa57e66c..e224ca2ea1c06 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -75,6 +75,33 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
return 0;
}
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -83,6 +110,14 @@ static int vti_rcv(struct sk_buff *skb)
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
@@ -409,6 +444,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.priority = 100,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
@@ -562,6 +603,13 @@ static int __init vti_init(void)
if (err < 0)
goto xfrm_proto_comp_failed;
+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
@@ -571,6 +619,8 @@ static int __init vti_init(void)
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 3.18 02/18] xfrm: refine validation of template and selector families
From: Sasha Levin @ 2019-02-23 21:11 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Florian Westphal, Steffen Klassert, Sasha Levin, netdev
In-Reply-To: <20190223211135.203082-1-sashal@kernel.org>
From: Florian Westphal <fw@strlen.de>
[ Upstream commit 35e6103861a3a970de6c84688c6e7a1f65b164ca ]
The check assumes that in transport mode, the first templates family
must match the address family of the policy selector.
Syzkaller managed to build a template using MODE_ROUTEOPTIMIZATION,
with ipv4-in-ipv6 chain, leading to following splat:
BUG: KASAN: stack-out-of-bounds in xfrm_state_find+0x1db/0x1854
Read of size 4 at addr ffff888063e57aa0 by task a.out/2050
xfrm_state_find+0x1db/0x1854
xfrm_tmpl_resolve+0x100/0x1d0
xfrm_resolve_and_create_bundle+0x108/0x1000 [..]
Problem is that addresses point into flowi4 struct, but xfrm_state_find
treats them as being ipv6 because it uses templ->encap_family is used
(AF_INET6 in case of reproducer) rather than family (AF_INET).
This patch inverts the logic: Enforce 'template family must match
selector' EXCEPT for tunnel and BEET mode.
In BEET and Tunnel mode, xfrm_tmpl_resolve_one will have remote/local
address pointers changed to point at the addresses found in the template,
rather than the flowi ones, so no oob read will occur.
Reported-by: 3ntr0py1337@gmail.com
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/xfrm/xfrm_user.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 017b1c91d58ea..05b72d45dda05 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1377,10 +1377,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
if (!ut[i].family)
ut[i].family = family;
- if ((ut[i].mode == XFRM_MODE_TRANSPORT) &&
- (ut[i].family != prev_family))
- return -EINVAL;
-
+ switch (ut[i].mode) {
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ break;
+ default:
+ if (ut[i].family != prev_family)
+ return -EINVAL;
+ break;
+ }
if (ut[i].mode >= XFRM_MODE_MAX)
return -EINVAL;
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 14/26] net: stmmac: dwmac-rk: fix error handling in rk_gmac_powerup()
From: Sasha Levin @ 2019-02-23 21:10 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Alexey Khoroshilov, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223211047.202725-1-sashal@kernel.org>
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
[ Upstream commit c69c29a1a0a8f68cd87e98ba4a5a79fb8ef2a58c ]
If phy_power_on() fails in rk_gmac_powerup(), clocks are left enabled.
Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 0cd3ecff768b3..398b08e07149b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -535,8 +535,10 @@ static int rk_gmac_init(struct platform_device *pdev, void *priv)
int ret;
ret = phy_power_on(bsp_priv, true);
- if (ret)
+ if (ret) {
+ gmac_clk_enable(bsp_priv, false);
return ret;
+ }
ret = gmac_clk_enable(bsp_priv, true);
if (ret)
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 13/26] net: hns: Fix wrong read accesses via Clause 45 MDIO protocol
From: Sasha Levin @ 2019-02-23 21:10 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Yonglong Liu, Peng Li, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223211047.202725-1-sashal@kernel.org>
From: Yonglong Liu <liuyonglong@huawei.com>
[ Upstream commit cec8abba13e6a26729dfed41019720068eeeff2b ]
When reading phy registers via Clause 45 MDIO protocol, after write
address operation, the driver use another write address operation, so
can not read the right value of any phy registers. This patch fixes it.
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 37491c85bc422..6ff13c559e527 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -319,7 +319,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
}
hns_mdio_cmd_write(mdio_dev, is_c45,
- MDIO_C45_WRITE_ADDR, phy_id, devad);
+ MDIO_C45_READ, phy_id, devad);
}
/* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 12/26] net: altera_tse: fix msgdma_tx_completion on non-zero fill_level case
From: Sasha Levin @ 2019-02-23 21:10 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Tomonori Sakita, Atsushi Nemoto, David S . Miller, Sasha Levin,
netdev
In-Reply-To: <20190223211047.202725-1-sashal@kernel.org>
From: Tomonori Sakita <tomonori.sakita@sord.co.jp>
[ Upstream commit 6571ebce112a21ec9be68ef2f53b96fcd41fd81b ]
If fill_level was not zero and status was not BUSY,
result of "tx_prod - tx_cons - inuse" might be zero.
Subtracting 1 unconditionally results invalid negative return value
on this case.
Make sure not to return an negative value.
Signed-off-by: Tomonori Sakita <tomonori.sakita@sord.co.jp>
Signed-off-by: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Reviewed-by: Dalon L Westergreen <dalon.westergreen@linux.intel.com>
Acked-by: Thor Thayer <thor.thayer@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/altera/altera_msgdma.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 0fb986ba32905..0ae723f753417 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
& 0xffff;
if (inuse) { /* Tx FIFO is not empty */
- ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+ ready = max_t(int,
+ priv->tx_prod - priv->tx_cons - inuse - 1, 0);
} else {
/* Check for buffered last packet */
status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 05/26] ipvs: Fix signed integer overflow when setsockopt timeout
From: Sasha Levin @ 2019-02-23 21:10 UTC (permalink / raw)
To: linux-kernel, stable
Cc: ZhangXiaoxu, Pablo Neira Ayuso, Sasha Levin, netdev, lvs-devel,
netfilter-devel, coreteam
In-Reply-To: <20190223211047.202725-1-sashal@kernel.org>
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
[ Upstream commit 53ab60baa1ac4f20b080a22c13b77b6373922fd7 ]
There is a UBSAN bug report as below:
UBSAN: Undefined behaviour in net/netfilter/ipvs/ip_vs_ctl.c:2227:21
signed integer overflow:
-2147483647 * 1000 cannot be represented in type 'int'
Reproduce program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#define IPPROTO_IP 0
#define IPPROTO_RAW 255
#define IP_VS_BASE_CTL (64+1024+64)
#define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10)
/* The argument to IP_VS_SO_GET_TIMEOUT */
struct ipvs_timeout_t {
int tcp_timeout;
int tcp_fin_timeout;
int udp_timeout;
};
int main() {
int ret = -1;
int sockfd = -1;
struct ipvs_timeout_t to;
sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
if (sockfd == -1) {
printf("socket init error\n");
return -1;
}
to.tcp_timeout = -2147483647;
to.tcp_fin_timeout = -2147483647;
to.udp_timeout = -2147483647;
ret = setsockopt(sockfd,
IPPROTO_IP,
IP_VS_SO_SET_TIMEOUT,
(char *)(&to),
sizeof(to));
printf("setsockopt return %d\n", ret);
return ret;
}
Return -EINVAL if the timeout value is negative or max than 'INT_MAX / HZ'.
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 3167ec76903a2..56c62b65923f1 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2217,6 +2217,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user
u->tcp_fin_timeout,
u->udp_timeout);
+#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.4 01/26] vti4: Fix a ipip packet processing bug in 'IPCOMP' virtual tunnel
From: Sasha Levin @ 2019-02-23 21:10 UTC (permalink / raw)
To: linux-kernel, stable; +Cc: Su Yanjun, Steffen Klassert, Sasha Levin, netdev
From: Su Yanjun <suyj.fnst@cn.fujitsu.com>
[ Upstream commit dd9ee3444014e8f28c0eefc9fffc9ac9c5248c12 ]
Recently we run a network test over ipcomp virtual tunnel.We find that
if a ipv4 packet needs fragment, then the peer can't receive
it.
We deep into the code and find that when packet need fragment the smaller
fragment will be encapsulated by ipip not ipcomp. So when the ipip packet
goes into xfrm, it's skb->dev is not properly set. The ipv4 reassembly code
always set skb'dev to the last fragment's dev. After ipv4 defrag processing,
when the kernel rp_filter parameter is set, the skb will be drop by -EXDEV
error.
This patch adds compatible support for the ipip process in ipcomp virtual tunnel.
Signed-off-by: Su Yanjun <suyj.fnst@cn.fujitsu.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/ipv4/ip_vti.c | 50 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 50 insertions(+)
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 4b7c81f88abf2..fcf327ebd1345 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -75,6 +75,33 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
return 0;
}
+static int vti_input_ipip(struct sk_buff *skb, int nexthdr, __be32 spi,
+ int encap_type)
+{
+ struct ip_tunnel *tunnel;
+ const struct iphdr *iph = ip_hdr(skb);
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
+
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY,
+ iph->saddr, iph->daddr, 0);
+ if (tunnel) {
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ goto drop;
+
+ XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
+
+ skb->dev = tunnel->dev;
+
+ return xfrm_input(skb, nexthdr, spi, encap_type);
+ }
+
+ return -EINVAL;
+drop:
+ kfree_skb(skb);
+ return 0;
+}
+
static int vti_rcv(struct sk_buff *skb)
{
XFRM_SPI_SKB_CB(skb)->family = AF_INET;
@@ -83,6 +110,14 @@ static int vti_rcv(struct sk_buff *skb)
return vti_input(skb, ip_hdr(skb)->protocol, 0, 0);
}
+static int vti_rcv_ipip(struct sk_buff *skb)
+{
+ XFRM_SPI_SKB_CB(skb)->family = AF_INET;
+ XFRM_SPI_SKB_CB(skb)->daddroff = offsetof(struct iphdr, daddr);
+
+ return vti_input_ipip(skb, ip_hdr(skb)->protocol, ip_hdr(skb)->saddr, 0);
+}
+
static int vti_rcv_cb(struct sk_buff *skb, int err)
{
unsigned short family;
@@ -409,6 +444,12 @@ static struct xfrm4_protocol vti_ipcomp4_protocol __read_mostly = {
.priority = 100,
};
+static struct xfrm_tunnel ipip_handler __read_mostly = {
+ .handler = vti_rcv_ipip,
+ .err_handler = vti4_err,
+ .priority = 0,
+};
+
static int __net_init vti_init_net(struct net *net)
{
int err;
@@ -592,6 +633,13 @@ static int __init vti_init(void)
if (err < 0)
goto xfrm_proto_comp_failed;
+ msg = "ipip tunnel";
+ err = xfrm4_tunnel_register(&ipip_handler, AF_INET);
+ if (err < 0) {
+ pr_info("%s: cant't register tunnel\n",__func__);
+ goto xfrm_tunnel_failed;
+ }
+
msg = "netlink interface";
err = rtnl_link_register(&vti_link_ops);
if (err < 0)
@@ -601,6 +649,8 @@ static int __init vti_init(void)
rtnl_link_failed:
xfrm4_protocol_deregister(&vti_ipcomp4_protocol, IPPROTO_COMP);
+xfrm_tunnel_failed:
+ xfrm4_tunnel_deregister(&ipip_handler, AF_INET);
xfrm_proto_comp_failed:
xfrm4_protocol_deregister(&vti_ah4_protocol, IPPROTO_AH);
xfrm_proto_ah_failed:
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 21/32] qed: Fix VF probe failure while FLR
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Manish Chopra, Ariel Elior, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: Manish Chopra <manishc@marvell.com>
[ Upstream commit 327852ec64205bb651be391a069784872098a3b2 ]
VFs may hit VF-PF channel timeout while probing, as in some
cases it was observed that VF FLR and VF "acquire" message
transaction (i.e first message from VF to PF in VF's probe flow)
could occur simultaneously which could lead VF to fail sending
"acquire" message to PF as VF is marked disabled from HW perspective
due to FLR, which will result into channel timeout and VF probe failure.
In such cases, try retrying VF "acquire" message so that in later
attempts it could be successful to pass message to PF after the VF
FLR is completed and can be probed successfully.
Signed-off-by: Manish Chopra <manishc@marvell.com>
Signed-off-by: Ariel Elior <aelior@marvell.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/qlogic/qed/qed_vf.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index 9cc02b94328a8..cf34908ec8e1f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -158,6 +158,7 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
struct pfvf_acquire_resp_tlv *resp = &p_iov->pf2vf_reply->acquire_resp;
struct pf_vf_pfdev_info *pfdev_info = &resp->pfdev_info;
struct vf_pf_resc_request *p_resc;
+ u8 retry_cnt = VF_ACQUIRE_THRESH;
bool resources_acquired = false;
struct vfpf_acquire_tlv *req;
int rc = 0, attempts = 0;
@@ -203,6 +204,15 @@ static int qed_vf_pf_acquire(struct qed_hwfn *p_hwfn)
/* send acquire request */
rc = qed_send_msg2pf(p_hwfn, &resp->hdr.status, sizeof(*resp));
+
+ /* Re-try acquire in case of vf-pf hw channel timeout */
+ if (retry_cnt && rc == -EBUSY) {
+ DP_VERBOSE(p_hwfn, QED_MSG_IOV,
+ "VF retrying to acquire due to VPC timeout\n");
+ retry_cnt--;
+ continue;
+ }
+
if (rc)
goto exit;
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 17/32] net: hns: Fix wrong read accesses via Clause 45 MDIO protocol
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Yonglong Liu, Peng Li, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: Yonglong Liu <liuyonglong@huawei.com>
[ Upstream commit cec8abba13e6a26729dfed41019720068eeeff2b ]
When reading phy registers via Clause 45 MDIO protocol, after write
address operation, the driver use another write address operation, so
can not read the right value of any phy registers. This patch fixes it.
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index 501eb2090ca62..de23a0ead5d76 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -329,7 +329,7 @@ static int hns_mdio_read(struct mii_bus *bus, int phy_id, int regnum)
}
hns_mdio_cmd_write(mdio_dev, is_c45,
- MDIO_C45_WRITE_ADDR, phy_id, devad);
+ MDIO_C45_READ, phy_id, devad);
}
/* Step 5: waitting for MDIO_COMMAND_REG 's mdio_start==0,*/
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 18/32] net: stmmac: dwmac-rk: fix error handling in rk_gmac_powerup()
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Alexey Khoroshilov, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
[ Upstream commit c69c29a1a0a8f68cd87e98ba4a5a79fb8ef2a58c ]
If phy_power_on() fails in rk_gmac_powerup(), clocks are left enabled.
Found by Linux Driver Verification project (linuxtesting.org).
Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index d80c88bd2bba8..6e61bccc90b3c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -877,8 +877,10 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
}
ret = phy_power_on(bsp_priv, true);
- if (ret)
+ if (ret) {
+ gmac_clk_enable(bsp_priv, false);
return ret;
+ }
ret = gmac_clk_enable(bsp_priv, true);
if (ret)
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 16/32] net: hns: Fix for missing of_node_put() after of_parse_phandle()
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Yonglong Liu, Peng Li, David S . Miller, Sasha Levin, netdev
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: Yonglong Liu <liuyonglong@huawei.com>
[ Upstream commit 263c6d75f9a544a3c2f8f6a26de4f4808d8f59cf ]
In hns enet driver, we use of_parse_handle() to get hold of the
device node related to "ae-handle" but we have missed to put
the node reference using of_node_put() after we are done using
the node. This patch fixes it.
Note:
This problem is stated in Link: https://lkml.org/lkml/2018/12/22/217
Fixes: 48189d6aaf1e ("net: hns: enet specifies a reference to dsaf")
Reported-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: Yonglong Liu <liuyonglong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/hisilicon/hns/hns_enet.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index a2f7d08340715..ad8681cf5ef06 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2078,6 +2078,8 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
out_notify_fail:
(void)cancel_work_sync(&priv->service_task);
out_read_prop_fail:
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
free_netdev(ndev);
return ret;
}
@@ -2107,6 +2109,9 @@ static int hns_nic_dev_remove(struct platform_device *pdev)
set_bit(NIC_STATE_REMOVING, &priv->state);
(void)cancel_work_sync(&priv->service_task);
+ /* safe for ACPI FW */
+ of_node_put(to_of_node(priv->fwnode));
+
free_netdev(ndev);
return 0;
}
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 15/32] net: altera_tse: fix msgdma_tx_completion on non-zero fill_level case
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Tomonori Sakita, Atsushi Nemoto, David S . Miller, Sasha Levin,
netdev
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: Tomonori Sakita <tomonori.sakita@sord.co.jp>
[ Upstream commit 6571ebce112a21ec9be68ef2f53b96fcd41fd81b ]
If fill_level was not zero and status was not BUSY,
result of "tx_prod - tx_cons - inuse" might be zero.
Subtracting 1 unconditionally results invalid negative return value
on this case.
Make sure not to return an negative value.
Signed-off-by: Tomonori Sakita <tomonori.sakita@sord.co.jp>
Signed-off-by: Atsushi Nemoto <atsushi.nemoto@sord.co.jp>
Reviewed-by: Dalon L Westergreen <dalon.westergreen@linux.intel.com>
Acked-by: Thor Thayer <thor.thayer@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
drivers/net/ethernet/altera/altera_msgdma.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/altera/altera_msgdma.c b/drivers/net/ethernet/altera/altera_msgdma.c
index 0fb986ba32905..0ae723f753417 100644
--- a/drivers/net/ethernet/altera/altera_msgdma.c
+++ b/drivers/net/ethernet/altera/altera_msgdma.c
@@ -145,7 +145,8 @@ u32 msgdma_tx_completions(struct altera_tse_private *priv)
& 0xffff;
if (inuse) { /* Tx FIFO is not empty */
- ready = priv->tx_prod - priv->tx_cons - inuse - 1;
+ ready = max_t(int,
+ priv->tx_prod - priv->tx_cons - inuse - 1, 0);
} else {
/* Check for buffered last packet */
status = csrrd32(priv->tx_dma_csr, msgdma_csroffs(status));
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 08/32] ipvs: Fix signed integer overflow when setsockopt timeout
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: ZhangXiaoxu, Pablo Neira Ayuso, Sasha Levin, netdev, lvs-devel,
netfilter-devel, coreteam
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
[ Upstream commit 53ab60baa1ac4f20b080a22c13b77b6373922fd7 ]
There is a UBSAN bug report as below:
UBSAN: Undefined behaviour in net/netfilter/ipvs/ip_vs_ctl.c:2227:21
signed integer overflow:
-2147483647 * 1000 cannot be represented in type 'int'
Reproduce program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/socket.h>
#define IPPROTO_IP 0
#define IPPROTO_RAW 255
#define IP_VS_BASE_CTL (64+1024+64)
#define IP_VS_SO_SET_TIMEOUT (IP_VS_BASE_CTL+10)
/* The argument to IP_VS_SO_GET_TIMEOUT */
struct ipvs_timeout_t {
int tcp_timeout;
int tcp_fin_timeout;
int udp_timeout;
};
int main() {
int ret = -1;
int sockfd = -1;
struct ipvs_timeout_t to;
sockfd = socket(AF_INET, SOCK_RAW, IPPROTO_RAW);
if (sockfd == -1) {
printf("socket init error\n");
return -1;
}
to.tcp_timeout = -2147483647;
to.tcp_fin_timeout = -2147483647;
to.udp_timeout = -2147483647;
ret = setsockopt(sockfd,
IPPROTO_IP,
IP_VS_SO_SET_TIMEOUT,
(char *)(&to),
sizeof(to));
printf("setsockopt return %d\n", ret);
return ret;
}
Return -EINVAL if the timeout value is negative or max than 'INT_MAX / HZ'.
Signed-off-by: ZhangXiaoxu <zhangxiaoxu5@huawei.com>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/netfilter/ipvs/ip_vs_ctl.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 8382b7880b240..8037b25ddb76a 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2258,6 +2258,18 @@ static int ip_vs_set_timeout(struct netns_ipvs *ipvs, struct ip_vs_timeout_user
u->tcp_fin_timeout,
u->udp_timeout);
+#ifdef CONFIG_IP_VS_PROTO_TCP
+ if (u->tcp_timeout < 0 || u->tcp_timeout > (INT_MAX / HZ) ||
+ u->tcp_fin_timeout < 0 || u->tcp_fin_timeout > (INT_MAX / HZ)) {
+ return -EINVAL;
+ }
+#endif
+
+#ifdef CONFIG_IP_VS_PROTO_UDP
+ if (u->udp_timeout < 0 || u->udp_timeout > (INT_MAX / HZ))
+ return -EINVAL;
+#endif
+
#ifdef CONFIG_IP_VS_PROTO_TCP
if (u->tcp_timeout) {
pd = ip_vs_proto_data_get(ipvs, IPPROTO_TCP);
--
2.19.1
^ permalink raw reply related
* [PATCH AUTOSEL 4.9 02/32] xfrm: refine validation of template and selector families
From: Sasha Levin @ 2019-02-23 21:09 UTC (permalink / raw)
To: linux-kernel, stable
Cc: Florian Westphal, Steffen Klassert, Sasha Levin, netdev
In-Reply-To: <20190223210951.202268-1-sashal@kernel.org>
From: Florian Westphal <fw@strlen.de>
[ Upstream commit 35e6103861a3a970de6c84688c6e7a1f65b164ca ]
The check assumes that in transport mode, the first templates family
must match the address family of the policy selector.
Syzkaller managed to build a template using MODE_ROUTEOPTIMIZATION,
with ipv4-in-ipv6 chain, leading to following splat:
BUG: KASAN: stack-out-of-bounds in xfrm_state_find+0x1db/0x1854
Read of size 4 at addr ffff888063e57aa0 by task a.out/2050
xfrm_state_find+0x1db/0x1854
xfrm_tmpl_resolve+0x100/0x1d0
xfrm_resolve_and_create_bundle+0x108/0x1000 [..]
Problem is that addresses point into flowi4 struct, but xfrm_state_find
treats them as being ipv6 because it uses templ->encap_family is used
(AF_INET6 in case of reproducer) rather than family (AF_INET).
This patch inverts the logic: Enforce 'template family must match
selector' EXCEPT for tunnel and BEET mode.
In BEET and Tunnel mode, xfrm_tmpl_resolve_one will have remote/local
address pointers changed to point at the addresses found in the template,
rather than the flowi ones, so no oob read will occur.
Reported-by: 3ntr0py1337@gmail.com
Reported-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
net/xfrm/xfrm_user.c | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 026770884d46b..f6f91c3b2de02 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1408,10 +1408,15 @@ static int validate_tmpl(int nr, struct xfrm_user_tmpl *ut, u16 family)
if (!ut[i].family)
ut[i].family = family;
- if ((ut[i].mode == XFRM_MODE_TRANSPORT) &&
- (ut[i].family != prev_family))
- return -EINVAL;
-
+ switch (ut[i].mode) {
+ case XFRM_MODE_TUNNEL:
+ case XFRM_MODE_BEET:
+ break;
+ default:
+ if (ut[i].family != prev_family)
+ return -EINVAL;
+ break;
+ }
if (ut[i].mode >= XFRM_MODE_MAX)
return -EINVAL;
--
2.19.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox