* [PATCH v2 1/2] net: Added mtu parameter to dev_forward_skb calls
From: Fredrik Markstrom @ 2017-05-11 13:46 UTC (permalink / raw)
To: Eric Dumazet
Cc: Daniel Borkmann, netdev, bridge, linux-kernel, Alexei Starovoitov,
Fredrik Markström, David S. Miller
In-Reply-To: <20170511134629.139528-1-fredrik.markstrom@gmail.com>
From: Fredrik Markström <fredrik.markstrom@gmail.com>
is_skb_forwardable() currently checks if the packet size is <= mtu of
the receiving interface. This is not consistent with most of the hardware
ethernet drivers that happily receives packets larger then MTU.
This patch adds a parameter to dev_forward_skb and is_skb_forwardable so
that the caller can override this packet size limit.
Signed-off-by: Fredrik Markstrom <fredrik.markstrom@gmail.com>
---
drivers/net/ipvlan/ipvlan_core.c | 7 ++++---
drivers/net/macvlan.c | 4 ++--
drivers/net/veth.c | 2 +-
include/linux/netdevice.h | 10 +++++-----
net/bridge/br_forward.c | 4 ++--
net/core/dev.c | 17 +++++++++++------
net/core/filter.c | 4 ++--
net/l2tp/l2tp_eth.c | 2 +-
8 files changed, 28 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 1f3295e274d0..dbbe48ade204 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -234,7 +234,8 @@ void ipvlan_process_multicast(struct work_struct *work)
nskb->pkt_type = pkt_type;
nskb->dev = ipvlan->dev;
if (tx_pkt)
- ret = dev_forward_skb(ipvlan->dev, nskb);
+ ret = dev_forward_skb(ipvlan->dev,
+ nskb, 0);
else
ret = netif_rx(nskb);
}
@@ -301,7 +302,7 @@ static int ipvlan_rcv_frame(struct ipvl_addr *addr, struct sk_buff **pskb,
if (local) {
skb->pkt_type = PACKET_HOST;
- if (dev_forward_skb(ipvlan->dev, skb) == NET_RX_SUCCESS)
+ if (dev_forward_skb(ipvlan->dev, skb, 0) == NET_RX_SUCCESS)
success = true;
} else {
ret = RX_HANDLER_ANOTHER;
@@ -547,7 +548,7 @@ static int ipvlan_xmit_mode_l2(struct sk_buff *skb, struct net_device *dev)
* the skb for the main-dev. At the RX side we just return
* RX_PASS for it to be processed further on the stack.
*/
- return dev_forward_skb(ipvlan->phy_dev, skb);
+ return dev_forward_skb(ipvlan->phy_dev, skb, 0);
} else if (is_multicast_ether_addr(eth->h_dest)) {
ipvlan_skb_crossing_ns(skb, NULL);
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 9261722960a7..4db2876c1e44 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -202,7 +202,7 @@ static int macvlan_broadcast_one(struct sk_buff *skb,
struct net_device *dev = vlan->dev;
if (local)
- return __dev_forward_skb(dev, skb);
+ return __dev_forward_skb(dev, skb, 0);
skb->dev = dev;
if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
@@ -495,7 +495,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
dest = macvlan_hash_lookup(port, eth->h_dest);
if (dest && dest->mode == MACVLAN_MODE_BRIDGE) {
/* send to lowerdev first for its network taps */
- dev_forward_skb(vlan->lowerdev, skb);
+ dev_forward_skb(vlan->lowerdev, skb, 0);
return NET_XMIT_SUCCESS;
}
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 8c39d6d690e5..561da3a63b8a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -116,7 +116,7 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
goto drop;
}
- if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
+ if (likely(dev_forward_skb(rcv, skb, 0) == NET_RX_SUCCESS)) {
struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
u64_stats_update_begin(&stats->syncp);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 97456b2539e4..f207b083ffec 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3282,16 +3282,16 @@ int dev_change_xdp_fd(struct net_device *dev, int fd, u32 flags);
struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev);
struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
struct netdev_queue *txq, int *ret);
-int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
-int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb, int mtu);
+int dev_forward_skb(struct net_device *dev, struct sk_buff *skb, int mtu);
bool is_skb_forwardable(const struct net_device *dev,
- const struct sk_buff *skb);
+ const struct sk_buff *skb, int mtu);
static __always_inline int ____dev_forward_skb(struct net_device *dev,
- struct sk_buff *skb)
+ struct sk_buff *skb, int mtu)
{
if (skb_orphan_frags(skb, GFP_ATOMIC) ||
- unlikely(!is_skb_forwardable(dev, skb))) {
+ unlikely(!is_skb_forwardable(dev, skb, mtu))) {
atomic_long_inc(&dev->rx_dropped);
kfree_skb(skb);
return NET_RX_DROP;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 902af6ba481c..15ab57da5ef1 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -35,7 +35,7 @@ static inline int should_deliver(const struct net_bridge_port *p,
int br_dev_queue_push_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- if (!is_skb_forwardable(skb->dev, skb))
+ if (!is_skb_forwardable(skb->dev, skb, 0))
goto drop;
skb_push(skb, ETH_HLEN);
@@ -96,7 +96,7 @@ static void __br_forward(const struct net_bridge_port *to,
net = dev_net(indev);
} else {
if (unlikely(netpoll_tx_running(to->br->dev))) {
- if (!is_skb_forwardable(skb->dev, skb)) {
+ if (!is_skb_forwardable(skb->dev, skb, 0)) {
kfree_skb(skb);
} else {
skb_push(skb, ETH_HLEN);
diff --git a/net/core/dev.c b/net/core/dev.c
index 533a6d6f6092..f7c53d7c8e26 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1767,14 +1767,18 @@ static inline void net_timestamp_set(struct sk_buff *skb)
__net_timestamp(SKB); \
} \
-bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
+bool is_skb_forwardable(const struct net_device *dev,
+ const struct sk_buff *skb, int mtu)
{
unsigned int len;
if (!(dev->flags & IFF_UP))
return false;
- len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
+ if (mtu == 0)
+ mtu = dev->mtu;
+
+ len = mtu + dev->hard_header_len + VLAN_HLEN;
if (skb->len <= len)
return true;
@@ -1788,9 +1792,9 @@ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(is_skb_forwardable);
-int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb, int mtu)
{
- int ret = ____dev_forward_skb(dev, skb);
+ int ret = ____dev_forward_skb(dev, skb, mtu);
if (likely(!ret)) {
skb->protocol = eth_type_trans(skb, dev);
@@ -1806,6 +1810,7 @@ EXPORT_SYMBOL_GPL(__dev_forward_skb);
*
* @dev: destination network device
* @skb: buffer to forward
+ * @mtu: Maximum size to forward. If 0 dev->mtu is used.
*
* return values:
* NET_RX_SUCCESS (no congestion)
@@ -1819,9 +1824,9 @@ EXPORT_SYMBOL_GPL(__dev_forward_skb);
* we have to clear all information in the skb that could
* impact namespace isolation.
*/
-int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
+int dev_forward_skb(struct net_device *dev, struct sk_buff *skb, int mtu)
{
- return __dev_forward_skb(dev, skb) ?: netif_rx_internal(skb);
+ return __dev_forward_skb(dev, skb, mtu) ?: netif_rx_internal(skb);
}
EXPORT_SYMBOL_GPL(dev_forward_skb);
diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2e46e8..3f3eb26e7ea1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1632,13 +1632,13 @@ static const struct bpf_func_proto bpf_csum_update_proto = {
static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
{
- return dev_forward_skb(dev, skb);
+ return dev_forward_skb(dev, skb, 0);
}
static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
struct sk_buff *skb)
{
- int ret = ____dev_forward_skb(dev, skb);
+ int ret = ____dev_forward_skb(dev, skb, 0);
if (likely(!ret)) {
skb->dev = dev;
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 6fd41d7afe1e..1258555b6578 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -164,7 +164,7 @@ static void l2tp_eth_dev_recv(struct l2tp_session *session, struct sk_buff *skb,
skb_dst_drop(skb);
nf_reset(skb);
- if (dev_forward_skb(dev, skb) == NET_RX_SUCCESS) {
+ if (dev_forward_skb(dev, skb, 0) == NET_RX_SUCCESS) {
atomic_long_inc(&priv->rx_packets);
atomic_long_add(data_len, &priv->rx_bytes);
} else {
--
2.11.0
^ permalink raw reply related
* [PATCH v2 0/2] net: Set maximum receive packet size on veth interfaces
From: Fredrik Markstrom @ 2017-05-11 13:46 UTC (permalink / raw)
To: Eric Dumazet
Cc: Daniel Borkmann, netdev, bridge, linux-kernel, Alexei Starovoitov,
Fredrik Markstrom, David S. Miller
Currently veth drops all packets larger then the mtu set on the receiving
end of the pair. This is inconsistent with most hardware ethernet drivers
that happily receives packets up the the ethernet MTU independent of the
configured MTU.
This patch set adds a new driver attribute to set the maximum size of
received packet to make it possible to create configurations similar to
those possible with (most) hardware ethernet interfaces.
The set consists of two patches. The first one adding a parameter do the
dev_forward_skb functions to specify the maximum packet size, the
second one implents a new attribute (VETH_MRU) in the veth driver.
Fredrik Markstrom (1):
veth: Added attribute to set maximum receive size on veth interfaces
Fredrik Markström (1):
net: Added mtu parameter to dev_forward_skb calls
drivers/net/ipvlan/ipvlan_core.c | 7 ++++---
drivers/net/macvlan.c | 4 ++--
drivers/net/veth.c | 45 +++++++++++++++++++++++++++++++++++++++-
include/linux/netdevice.h | 10 ++++-----
include/uapi/linux/veth.h | 1 +
net/bridge/br_forward.c | 4 ++--
net/core/dev.c | 17 +++++++++------
net/core/filter.c | 4 ++--
net/l2tp/l2tp_eth.c | 2 +-
9 files changed, 72 insertions(+), 22 deletions(-)
v2 - Updated description and fixed compile error in net/bridge/br_forward.c
--
2.11.0
^ permalink raw reply
* Re: [PATCH v3] net/mlx4_core: Use min3 to select number of MSI-X vectors
From: kbuild test robot @ 2017-05-11 13:36 UTC (permalink / raw)
To: Yuval Shaia
Cc: kbuild-all-JC7UmRfGjtg, yishaih-VPRAkNaXOzVWk0Htik3J/w,
netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494499258-17017-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
Hi Yuval,
[auto build test WARNING on net-next/master]
[also build test WARNING on v4.11 next-20170511]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Yuval-Shaia/net-mlx4_core-Use-min3-to-select-number-of-MSI-X-vectors/20170511-184906
reproduce:
# apt-get install sparse
make ARCH=x86_64 allmodconfig
make C=1 CF=-D__CHECK_ENDIAN__
sparse warnings: (new ones prefixed by >>)
include/linux/compiler.h:264:8: sparse: attribute 'no_sanitize_address': unknown attribute
>> drivers/net/ethernet/mellanox/mlx4/main.c:2865:28: sparse: incompatible types in comparison expression (different signedness)
>> drivers/net/ethernet/mellanox/mlx4/main.c:2865:28: sparse: incompatible types in comparison expression (different signedness)
>> drivers/net/ethernet/mellanox/mlx4/main.c:2865:28: sparse: incompatible types in comparison expression (different signedness)
In file included from include/linux/list.h:8:0,
from include/linux/module.h:9,
from drivers/net/ethernet/mellanox/mlx4/main.c:36:
drivers/net/ethernet/mellanox/mlx4/main.c: In function 'mlx4_enable_msi_x':
include/linux/kernel.h:757:16: warning: comparison of distinct pointer types lacks a cast
(void) (&min1 == &min2); \
^
include/linux/kernel.h:755:2: note: in definition of macro '__min'
t1 min1 = (x); \
^~
include/linux/kernel.h:774:23: note: in expansion of macro 'min'
#define min3(x, y, z) min((typeof(x))min(x, y), z)
^~~
include/linux/kernel.h:760:2: note: in expansion of macro '__min'
__min(typeof(x), typeof(y), \
^~~~~
include/linux/kernel.h:774:38: note: in expansion of macro 'min'
#define min3(x, y, z) min((typeof(x))min(x, y), z)
^~~
drivers/net/ethernet/mellanox/mlx4/main.c:2865:14: note: in expansion of macro 'min3'
int nreq = min3(dev->caps.num_ports * num_online_cpus() + 1,
^~~~
include/linux/kernel.h:757:16: warning: comparison of distinct pointer types lacks a cast
(void) (&min1 == &min2); \
^
include/linux/kernel.h:755:13: note: in definition of macro '__min'
t1 min1 = (x); \
^
include/linux/kernel.h:774:23: note: in expansion of macro 'min'
#define min3(x, y, z) min((typeof(x))min(x, y), z)
^~~
include/linux/kernel.h:760:2: note: in expansion of macro '__min'
__min(typeof(x), typeof(y), \
^~~~~
include/linux/kernel.h:774:38: note: in expansion of macro 'min'
#define min3(x, y, z) min((typeof(x))min(x, y), z)
^~~
drivers/net/ethernet/mellanox/mlx4/main.c:2865:14: note: in expansion of macro 'min3'
int nreq = min3(dev->caps.num_ports * num_online_cpus() + 1,
^~~~
include/linux/kernel.h:757:16: warning: comparison of distinct pointer types lacks a cast
(void) (&min1 == &min2); \
^
include/linux/kernel.h:760:2: note: in expansion of macro '__min'
__min(typeof(x), typeof(y), \
^~~~~
include/linux/kernel.h:774:23: note: in expansion of macro 'min'
#define min3(x, y, z) min((typeof(x))min(x, y), z)
^~~
drivers/net/ethernet/mellanox/mlx4/main.c:2865:14: note: in expansion of macro 'min3'
int nreq = min3(dev->caps.num_ports * num_online_cpus() + 1,
^~~~
vim +2865 drivers/net/ethernet/mellanox/mlx4/main.c
2849 if (!zalloc_cpumask_var(&eq->affinity_mask, GFP_KERNEL))
2850 return -ENOMEM;
2851
2852 cpumask_set_cpu(requested_cpu, eq->affinity_mask);
2853
2854 return 0;
2855 }
2856
2857 static void mlx4_enable_msi_x(struct mlx4_dev *dev)
2858 {
2859 struct mlx4_priv *priv = mlx4_priv(dev);
2860 struct msix_entry *entries;
2861 int i;
2862 int port = 0;
2863
2864 if (msi_x) {
> 2865 int nreq = min3(dev->caps.num_ports * num_online_cpus() + 1,
2866 dev->caps.num_eqs - dev->caps.reserved_eqs,
2867 MAX_MSIX);
2868
2869 entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
2870 if (!entries)
2871 goto no_msi;
2872
2873 for (i = 0; i < nreq; ++i)
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] net/mlx4_core: Use min_t instead of if for consistency
From: kbuild test robot @ 2017-05-11 13:35 UTC (permalink / raw)
To: Yuval Shaia
Cc: kbuild-all-JC7UmRfGjtg, yishaih-VPRAkNaXOzVWk0Htik3J/w,
netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494490852-5567-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 1839 bytes --]
Hi Yuval,
[auto build test ERROR on net-next/master]
[also build test ERROR on v4.11 next-20170511]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]
url: https://github.com/0day-ci/linux/commits/Yuval-Shaia/net-mlx4_core-Use-min_t-instead-of-if-for-consistency/20170511-163038
config: powerpc-ppc64_defconfig (attached as .config)
compiler: powerpc64-linux-gnu-gcc (Debian 6.1.1-9) 6.1.1 20160705
reproduce:
wget https://raw.githubusercontent.com/01org/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# save the attached .config to linux build tree
make.cross ARCH=powerpc
All errors (new ones prefixed by >>):
drivers/net/ethernet/mellanox/mlx4/main.c: In function 'mlx4_enable_msi_x':
>> drivers/net/ethernet/mellanox/mlx4/main.c:2869:30: error: macro "min_t" requires 3 arguments, but only 2 given
nreq = min_t(nreq, MAX_MSIX);
^
>> drivers/net/ethernet/mellanox/mlx4/main.c:2869:10: error: 'min_t' undeclared (first use in this function)
nreq = min_t(nreq, MAX_MSIX);
^~~~~
drivers/net/ethernet/mellanox/mlx4/main.c:2869:10: note: each undeclared identifier is reported only once for each function it appears in
vim +/min_t +2869 drivers/net/ethernet/mellanox/mlx4/main.c
2863
2864 if (msi_x) {
2865 int nreq = min_t(int,
2866 dev->caps.num_ports * num_online_cpus() + 1,
2867 dev->caps.num_eqs - dev->caps.reserved_eqs);
2868
> 2869 nreq = min_t(nreq, MAX_MSIX);
2870
2871 entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
2872 if (!entries)
---
0-DAY kernel test infrastructure Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all Intel Corporation
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 23107 bytes --]
^ permalink raw reply
* Re: [PATCH 5/5] bpf: Add verifier test case for alignment.
From: Daniel Borkmann @ 2017-05-11 13:01 UTC (permalink / raw)
To: David Miller, ast; +Cc: alexei.starovoitov, netdev
In-Reply-To: <20170510.151005.805363538289965960.davem@davemloft.net>
On 05/10/2017 09:10 PM, David Miller wrote:
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
Thanks for all the tests! Did you check whether it also allows
to lift some of the F_NEEDS_EFFICIENT_UNALIGNED_ACCESS flagged
tests in test_verifier? I think we should now be able to rework
that a bit, but not subject to this patch set, of course.
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* Re: [PATCH 4/5] bpf: Add bpf_verify_program() to the library.
From: Daniel Borkmann @ 2017-05-11 12:54 UTC (permalink / raw)
To: David Miller, ast; +Cc: alexei.starovoitov, netdev
In-Reply-To: <20170510.151000.1271350336586950089.davem@davemloft.net>
On 05/10/2017 09:10 PM, David Miller wrote:
>
> This allows a test case to load a BPF program and unconditionally
> acquire the verifier log.
>
> It also allows specification of the strict alignment flag.
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* Re: [PATCH 3/5] bpf: Add strict alignment flag for BPF_PROG_LOAD.
From: Daniel Borkmann @ 2017-05-11 12:53 UTC (permalink / raw)
To: David Miller, ast; +Cc: alexei.starovoitov, netdev
In-Reply-To: <20170510.150951.1359250469075249855.davem@davemloft.net>
On 05/10/2017 09:09 PM, David Miller wrote:
>
> Add a new field, "prog_flags", and an initial flag value
> BPF_F_STRCIT_ALIGNMENT.
>
> When set, the verifier will enforce strict pointer alignment
> regardless of the setting of CONFIG_EFFICIENT_UNALIGNED_ACCESS.
>
> The verifier, in this mode, will also use a fixed value of "2" in
> place of NET_IP_ALIGN.
>
> This facilitates test cases that will exercise and validate this part
> of the verifier even when run on architectures where alignment doesn't
> matter.
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
[...]
> @@ -833,10 +838,12 @@ static int check_val_ptr_alignment(const struct bpf_reg_state *reg,
> return 0;
> }
>
> +static bool strict_alignment;
> +
> static int check_ptr_alignment(const struct bpf_reg_state *reg,
> int off, int size)
> {
> - bool strict = false;
> + bool strict = strict_alignment;
>
> if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
> strict = true;
> @@ -3574,6 +3581,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr)
> } else {
> log_level = 0;
> }
> + if (attr->prog_flags & BPF_F_STRICT_ALIGNMENT)
> + strict_alignment = true;
> + else
> + strict_alignment = false;
Just minor nit: Can we move this into struct bpf_verifier_env
here instead of global var? The only change it would need is
in check_ptr_alignment() to pass the env from check_mem_access().
check_ptr_alignment() can then infer this from env.
> ret = replace_map_fd_with_map_ptr(env);
> if (ret < 0)
> @@ -3679,6 +3690,7 @@ int bpf_analyzer(struct bpf_prog *prog, const struct bpf_ext_analyzer_ops *ops,
> mutex_lock(&bpf_verifier_lock);
>
> log_level = 0;
> + strict_alignment = false;
>
> env->explored_states = kcalloc(env->prog->len,
> sizeof(struct bpf_verifier_state_list *),
Rest looks good:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* Re: [PATCH 2/5] bpf: Do per-instruction state dumping in verifier when log_level > 1.
From: Daniel Borkmann @ 2017-05-11 12:42 UTC (permalink / raw)
To: David Miller, ast; +Cc: alexei.starovoitov, netdev
In-Reply-To: <20170510.150947.1771591614496655880.davem@davemloft.net>
On 05/10/2017 09:09 PM, David Miller wrote:
>
> If log_level > 1, do a state dump every instruction and emit it in
> a more compact way (without a leading newline).
>
> This will facilitate more sophisticated test cases which inspect the
> verifier log for register state.
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* Re: [PATCH 1/5] bpf: Track alignment of register values in the verifier.
From: Daniel Borkmann @ 2017-05-11 12:41 UTC (permalink / raw)
To: David Miller, ast; +Cc: alexei.starovoitov, netdev
In-Reply-To: <20170510.150942.1969073633182798014.davem@davemloft.net>
On 05/10/2017 09:09 PM, David Miller wrote:
>
> Currently if we add only constant values to pointers we can fully
> validate the alignment, and properly check if we need to reject the
> program on CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS architectures.
Should say: !CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
> However, once an unknown value is introduced we only allow byte sized
> memory accesses which is too restrictive.
>
> Add logic to track the known minimum alignment of register values,
> and propagate this state into registers containing pointers.
>
> The most common paradigm that makes use of this new logic is computing
> the transport header using the IP header length field. For example:
>
> struct ethhdr *ep = skb->data;
> struct iphdr *iph = (struct iphdr *) (ep + 1);
> struct tcphdr *th;
> ...
> n = iph->ihl;
> th = ((void *)iph + (n * 4));
> port = th->dest;
>
> The existing code will reject the load of th->dport because it cannot
s/th->dport/th->dest/
> validate that the alignment is at least 2 once "n * 4" is added the
> the packet pointer.
>
> In the new code, the register holding "n * 4" will have a reg->min_align
> value of 4, because any value multiplied by 4 will be at least 4 byte
> aligned. (actually, the eBPF code emitted by the compiler in this case
> is most likely to use a shift left by 2, but the end result is identical)
>
> At the critical addition:
>
> th = ((void *)iph + (n * 4));
>
> The register holding 'th' will start with reg->off value of 14. The
> pointer addition will transform that reg into something that looks like:
>
> reg->aux_off = 14
> reg->aux_off_align = 4
>
> Next, the verifier will look at the th->dest load, and it will see
> a load offset of 2, and first check:
>
> if (reg->aux_off_align % size)
>
> which will pass because aux_off_align is 4. reg_off will be computed:
>
> reg_off = reg->off;
> ...
> reg_off += reg->aux_off;
>
> plus we have off==2, and it will thus check:
>
> if ((NET_IP_ALIGN + reg_off + off) % size != 0)
>
> which evaluates to:
>
> if ((NET_IP_ALIGN + 14 + 2) % size != 0)
>
> On strict alignment architectures, NET_IP_ALIGN is 2, thus:
>
> if ((2 + 14 + 2) % size != 0)
>
> which passes.
>
> These pointer transformations and checks work regardless of whether
> the constant offset or the variable with known alignment is added
> first to the pointer register.
>
> Signed-off-by: David S. Miller <davem@davemloft.net>
In adjust_reg_min_max_vals(), don't we also need to call
reset_reg_align() in the 'default' case for the cases where
we use have ALU ops that we don't bother tracking (mod, div,
endianess ops, etc)?
Likewise, for other cases where we do reset_reg_range_values()
which is BPF_LD as class and for the BPF_MOV in check_alu_op(),
which I think, is only relevant when we move reg A to reg B
in 32 bit mode. Perhaps it makes sense to consolidate the reset
on alignment with the reset of min/max values, or do we have
cases where this is undesirable (not that I'm currently aware
of ...)?
But other than that:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
^ permalink raw reply
* [PATCH] qed: fix uninitialized data in aRFS intrastructure
From: Arnd Bergmann @ 2017-05-11 12:15 UTC (permalink / raw)
To: Yuval Mintz, Ariel Elior, everest-linux-l2
Cc: Arnd Bergmann, David S. Miller, Chad Dupuis, Ram Amrani,
Manish Rangankar, Chopra, Manish, netdev, linux-kernel
The new code contains an incredibly elaborate way of setting a 64-bit
register, which went subtly wrong due to the wrong size in a memset():
ethernet/qlogic/qed/qed_init_fw_funcs.c: In function 'qed_set_rfs_mode_disable':
ethernet/qlogic/qed/qed_init_fw_funcs.c:993:3: error: '*((void *)&ramline+4)' is used uninitialized in this function [-Werror=uninitialized]
This removes the silly loop and memset, and instead directly writes
the correct value to the register.
Fixes: d51e4af5c209 ("qed: aRFS infrastructure support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
.../net/ethernet/qlogic/qed/qed_init_fw_funcs.c | 48 +++++-----------------
1 file changed, 11 insertions(+), 37 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index 67200c5498ab..a7c2c147a738 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -966,45 +966,29 @@ void qed_set_geneve_enable(struct qed_hwfn *p_hwfn,
#define PARSER_ETH_CONN_CM_HDR (0x0)
#define CAM_LINE_SIZE sizeof(u32)
#define RAM_LINE_SIZE sizeof(u64)
-#define REG_SIZE sizeof(u32)
+#define CAM_REG(pf_id) (PRS_REG_GFT_CAM + CAM_LINE_SIZE * (pf_id))
+#define RAM_REG(pf_id) (PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * (pf_id))
void qed_set_rfs_mode_disable(struct qed_hwfn *p_hwfn,
struct qed_ptt *p_ptt, u16 pf_id)
{
- union gft_cam_line_union camline;
- struct gft_ram_line ramline;
- u32 *p_ramline, i;
-
- p_ramline = (u32 *)&ramline;
-
/*stop using gft logic */
qed_wr(p_hwfn, p_ptt, PRS_REG_SEARCH_GFT, 0);
qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, 0x0);
- memset(&camline, 0, sizeof(union gft_cam_line_union));
- qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id,
- camline.cam_line_mapped.camline);
- memset(&ramline, 0, sizeof(union gft_cam_line_union));
-
- for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++) {
- u32 hw_addr = PRS_REG_GFT_PROFILE_MASK_RAM;
-
- hw_addr += (RAM_LINE_SIZE * pf_id + i * REG_SIZE);
-
- qed_wr(p_hwfn, p_ptt, hw_addr, *(p_ramline + i));
- }
+ qed_wr(p_hwfn, p_ptt, CAM_REG(pf_id), 0);
+ qed_wr(p_hwfn, p_ptt, RAM_REG(pf_id), 0);
+ qed_wr(p_hwfn, p_ptt, RAM_REG(pf_id) + 4, 0);
}
void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
u16 pf_id, bool tcp, bool udp,
bool ipv4, bool ipv6)
{
- u32 rfs_cm_hdr_event_id, *p_ramline;
+ u32 rfs_cm_hdr_event_id;
union gft_cam_line_union camline;
struct gft_ram_line ramline;
- int i;
rfs_cm_hdr_event_id = qed_rd(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT);
- p_ramline = (u32 *)&ramline;
if (!ipv6 && !ipv4)
DP_NOTICE(p_hwfn,
@@ -1060,8 +1044,7 @@ void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
}
/* write characteristics to cam */
- qed_wr(p_hwfn, p_ptt, PRS_REG_GFT_CAM + CAM_LINE_SIZE * pf_id,
- camline.cam_line_mapped.camline);
+ qed_wr(p_hwfn, p_ptt, CAM_REG(pf_id), camline.cam_line_mapped.camline);
camline.cam_line_mapped.camline = qed_rd(p_hwfn, p_ptt,
PRS_REG_GFT_CAM +
CAM_LINE_SIZE * pf_id);
@@ -1074,19 +1057,10 @@ void qed_set_rfs_mode_enable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
SET_FIELD(ramline.low32bits, GFT_RAM_LINE_SRC_PORT, 1);
SET_FIELD(ramline.low32bits, GFT_RAM_LINE_DST_PORT, 1);
- /* each iteration write to reg */
- for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++)
- qed_wr(p_hwfn, p_ptt,
- PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE * pf_id +
- i * REG_SIZE, *(p_ramline + i));
+ qed_wr(p_hwfn, p_ptt, RAM_REG(pf_id), ramline.low32bits);
+ qed_wr(p_hwfn, p_ptt, RAM_REG(pf_id) + 4, ramline.high32bits);
/* set default profile so that no filter match will happen */
- ramline.low32bits = 0xffff;
- ramline.high32bits = 0xffff;
-
- for (i = 0; i < RAM_LINE_SIZE / REG_SIZE; i++)
- qed_wr(p_hwfn, p_ptt,
- PRS_REG_GFT_PROFILE_MASK_RAM + RAM_LINE_SIZE *
- PRS_GFT_CAM_LINES_NO_MATCH + i * REG_SIZE,
- *(p_ramline + i));
+ qed_wr(p_hwfn, p_ptt, RAM_REG(PRS_GFT_CAM_LINES_NO_MATCH), 0xffff);
+ qed_wr(p_hwfn, p_ptt, RAM_REG(PRS_GFT_CAM_LINES_NO_MATCH) + 4, 0xffff);
}
--
2.9.0
^ permalink raw reply related
* Re: [PATCH] wcn36xx: Close SMD channel on device removal
From: Kalle Valo @ 2017-05-11 12:11 UTC (permalink / raw)
To: Bjorn Andersson
Cc: Arend van Spriel, Eugene Krasnikov, Eyal Ilsar, wcn36xx,
linux-wireless, netdev, linux-kernel, linux-arm-msm
In-Reply-To: <20170510175254.GS15143@minitux>
Bjorn Andersson <bjorn.andersson@linaro.org> writes:
> On Wed 10 May 00:27 PDT 2017, Arend van Spriel wrote:
>
>> On 5/10/2017 1:03 AM, Bjorn Andersson wrote:
>>
>> > AFAICT this never worked, as it seems I did the rework in SMD while we
>> > tried to figure out the dependency issues we had with moving to SMD. So
>> > v4.9 through v4.11 has SMD support - with this bug.
>> >
>> > How do I proceed, do you want me to write up a fix for stable@? Do I
>> > send that out as an ordinary patch?
>>
>> If the patch applies cleanly on branches linux-4.9.y through linux-4.11.y in
>> the stable repository you can go for '--- Option 1 ---' as described in
>> <linux-repo>/Documentation/stable_kernel_rules.txt.
>>
>
> It does not, before v4.12 it's a completely different function to call
> to close the channel.
>
> But "Option 3" describes the situation, thanks for the reference. I'll
> try to find the time to verify the patch on v4.11 and send it to
> stable@.
Great, thanks. This seems to be that serious that better to fix this
also in older releases.
--
Kalle Valo
^ permalink raw reply
* [PATCH v2] xen-netfront: avoid crashing on resume after a failure in talk_to_netback()
From: Vitaly Kuznetsov @ 2017-05-11 11:58 UTC (permalink / raw)
To: xen-devel
Cc: netdev, linux-kernel, Boris Ostrovsky, Juergen Gross,
David Miller
Unavoidable crashes in netfront_resume() and netback_changed() after a
previous fail in talk_to_netback() (e.g. when we fail to read MAC from
xenstore) were discovered. The failure path in talk_to_netback() does
unregister/free for netdev but we don't reset drvdata and we try accessing
it after resume.
Fix the bug by removing the whole xen device completely with
device_unregister(), this guarantees we won't have any calls into netfront
after a failure.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
---
Changes since v1: instead of cleaning drvdata and checking for it in
netfront_resume() and netback_changed() remove the device completely with
device_unregister() [David Miller]
---
drivers/net/xen-netfront.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 6ffc482..7b61adb 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1934,8 +1934,7 @@ static int talk_to_netback(struct xenbus_device *dev,
xennet_disconnect_backend(info);
xennet_destroy_queues(info);
out:
- unregister_netdev(info->netdev);
- xennet_free_netdev(info->netdev);
+ device_unregister(&dev->dev);
return err;
}
--
2.9.3
^ permalink raw reply related
* [PATCH] wlcore: fix 64K page support
From: Arnd Bergmann @ 2017-05-11 11:52 UTC (permalink / raw)
To: Kalle Valo
Cc: Arnd Bergmann, stable, Reizer, Eyal, Tony Lindgren, Wei Yongjun,
linux-wireless, netdev, linux-kernel
In the stable linux-3.16 branch, I ran into a warning in the
wlcore driver:
drivers/net/wireless/ti/wlcore/spi.c: In function 'wl12xx_spi_raw_write':
drivers/net/wireless/ti/wlcore/spi.c:315:1: error: the frame size of 12848 bytes is larger than 2048 bytes [-Werror=frame-larger-than=]
Newer kernels no longer show the warning, but the bug is still there,
as the allocation is based on the CPU page size rather than the
actual capabilities of the hardware.
This replaces the PAGE_SIZE macro with the SZ_4K macro, i.e. 4096 bytes
per buffer.
Cc: stable@vger.kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
drivers/net/wireless/ti/wlcore/spi.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/drivers/net/wireless/ti/wlcore/spi.c b/drivers/net/wireless/ti/wlcore/spi.c
index f949ad2bd898..fa3547e06424 100644
--- a/drivers/net/wireless/ti/wlcore/spi.c
+++ b/drivers/net/wireless/ti/wlcore/spi.c
@@ -70,10 +70,10 @@
#define WSPI_MAX_CHUNK_SIZE 4092
/*
- * wl18xx driver aggregation buffer size is (13 * PAGE_SIZE) compared to
- * (4 * PAGE_SIZE) for wl12xx, so use the larger buffer needed for wl18xx
+ * wl18xx driver aggregation buffer size is (13 * 4K) compared to
+ * (4 * 4K) for wl12xx, so use the larger buffer needed for wl18xx
*/
-#define SPI_AGGR_BUFFER_SIZE (13 * PAGE_SIZE)
+#define SPI_AGGR_BUFFER_SIZE (13 * SZ_4K)
/* Maximum number of SPI write chunks */
#define WSPI_MAX_NUM_OF_CHUNKS \
--
2.9.0
^ permalink raw reply related
* Re: [PATCH v3] net/mlx4_core: Use min3 to select number of MSI-X vectors
From: Leon Romanovsky @ 2017-05-11 10:48 UTC (permalink / raw)
To: Yuval Shaia
Cc: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494499258-17017-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 533 bytes --]
On Thu, May 11, 2017 at 01:40:58PM +0300, Yuval Shaia wrote:
> Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
> ---
> v0 -> v1:
> * s/"min_t("/"min_t(int"
> v1 -> v2:
> * Use min3 instead of min_t twice
> v2 -> v3:
> * Change commit log header message to reflect the changes made in
> v2
> ---
> drivers/net/ethernet/mellanox/mlx4/main.c | 9 +++------
> 1 file changed, 3 insertions(+), 6 deletions(-)
>
Thanks,
Reviewed-by: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [PATCH v2] net/mlx4_core: Use min_t instead of if for consistency
From: Leon Romanovsky @ 2017-05-11 10:42 UTC (permalink / raw)
To: Yuval Shaia
Cc: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494498962-16852-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 444 bytes --]
On Thu, May 11, 2017 at 01:36:02PM +0300, Yuval Shaia wrote:
> Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
> ---
> v0 -> v1:
> * s/"min_t("/"min_t(int"
> v1 -> v2:
> * Use min3 instead of min_t twice
> ---
> drivers/net/ethernet/mellanox/mlx4/main.c | 9 +++------
> 1 file changed, 3 insertions(+), 6 deletions(-)
>
Thanks,
Reviewed-by: Leon Romanovsky <leonro-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* [PATCH v3] net/mlx4_core: Use min3 to select number of MSI-X vectors
From: Yuval Shaia @ 2017-05-11 10:40 UTC (permalink / raw)
To: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
---
v0 -> v1:
* s/"min_t("/"min_t(int"
v1 -> v2:
* Use min3 instead of min_t twice
v2 -> v3:
* Change commit log header message to reflect the changes made in
v2
---
drivers/net/ethernet/mellanox/mlx4/main.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7032054..2afa340 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2862,12 +2862,9 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
int port = 0;
if (msi_x) {
- int nreq = dev->caps.num_ports * num_online_cpus() + 1;
-
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
- if (nreq > MAX_MSIX)
- nreq = MAX_MSIX;
+ int nreq = min3(dev->caps.num_ports * num_online_cpus() + 1,
+ dev->caps.num_eqs - dev->caps.reserved_eqs,
+ MAX_MSIX);
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* [PATCH v2] net/mlx4_core: Use min_t instead of if for consistency
From: Yuval Shaia @ 2017-05-11 10:36 UTC (permalink / raw)
To: yishaih, netdev, linux-rdma
Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
---
v0 -> v1:
* s/"min_t("/"min_t(int"
v1 -> v2:
* Use min3 instead of min_t twice
---
drivers/net/ethernet/mellanox/mlx4/main.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7032054..2afa340 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2862,12 +2862,9 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
int port = 0;
if (msi_x) {
- int nreq = dev->caps.num_ports * num_online_cpus() + 1;
-
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
- if (nreq > MAX_MSIX)
- nreq = MAX_MSIX;
+ int nreq = min3(dev->caps.num_ports * num_online_cpus() + 1,
+ dev->caps.num_eqs - dev->caps.reserved_eqs,
+ MAX_MSIX);
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
--
2.7.4
^ permalink raw reply related
* Re: [PATCH v1] net/mlx4_core: Use min_t instead of if for consistency
From: Yuval Shaia @ 2017-05-11 10:27 UTC (permalink / raw)
To: Leon Romanovsky; +Cc: yishaih, netdev, linux-rdma
In-Reply-To: <20170511102329.GC3616@mtr-leonro.local>
On Thu, May 11, 2017 at 01:23:29PM +0300, Leon Romanovsky wrote:
> On Thu, May 11, 2017 at 11:46:29AM +0300, Yuval Shaia wrote:
> > Signed-off-by: Yuval Shaia <yuval.shaia@oracle.com>
> > ---
> > v0 -> v1:
> > * s/"min_t("/"min_t(int"
> > ---
> > drivers/net/ethernet/mellanox/mlx4/main.c | 9 ++++-----
> > 1 file changed, 4 insertions(+), 5 deletions(-)
> >
> > diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
> > index 7032054..7bb377e 100644
> > --- a/drivers/net/ethernet/mellanox/mlx4/main.c
> > +++ b/drivers/net/ethernet/mellanox/mlx4/main.c
> > @@ -2862,12 +2862,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
> > int port = 0;
> >
> > if (msi_x) {
> > - int nreq = dev->caps.num_ports * num_online_cpus() + 1;
> > + int nreq = min_t(int,
> > + dev->caps.num_ports * num_online_cpus() + 1,
> > + dev->caps.num_eqs - dev->caps.reserved_eqs);
> >
> > - nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
> > - nreq);
> > - if (nreq > MAX_MSIX)
> > - nreq = MAX_MSIX;
> > + nreq = min_t(int, nreq, MAX_MSIX);
>
> You don't need type checking for these variables, they are all int and
> you can use directly min3(..).
Ha ha ha, i can't explain how this macro slipped out from my sight when was
looking for it :).
Hope you can review v2.
>
> Thanks
>
> >
> > entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
> > if (!entries)
> > --
> > 2.7.4
> >
> > --
> > To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> > the body of a message to majordomo@vger.kernel.org
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH v1] net/mlx4_core: Use min_t instead of if for consistency
From: Leon Romanovsky @ 2017-05-11 10:23 UTC (permalink / raw)
To: Yuval Shaia
Cc: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494492389-15040-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 1459 bytes --]
On Thu, May 11, 2017 at 11:46:29AM +0300, Yuval Shaia wrote:
> Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
> ---
> v0 -> v1:
> * s/"min_t("/"min_t(int"
> ---
> drivers/net/ethernet/mellanox/mlx4/main.c | 9 ++++-----
> 1 file changed, 4 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
> index 7032054..7bb377e 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/main.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/main.c
> @@ -2862,12 +2862,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
> int port = 0;
>
> if (msi_x) {
> - int nreq = dev->caps.num_ports * num_online_cpus() + 1;
> + int nreq = min_t(int,
> + dev->caps.num_ports * num_online_cpus() + 1,
> + dev->caps.num_eqs - dev->caps.reserved_eqs);
>
> - nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
> - nreq);
> - if (nreq > MAX_MSIX)
> - nreq = MAX_MSIX;
> + nreq = min_t(int, nreq, MAX_MSIX);
You don't need type checking for these variables, they are all int and
you can use directly min3(..).
Thanks
>
> entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
> if (!entries)
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Implementing Dynamic Rerouting in Kernel
From: Ravish Kumar @ 2017-05-11 9:59 UTC (permalink / raw)
To: Networking, linux-kernel, mst
Hi Experts,
Need expert advice for the one of the requirement Where in VPN
solution we want to dynaically route the packets to different adapter.
We will manage our own DNS cache and , based on DNS to IP lookup, we
can redirect the packet either to Tun device or to a physical adapter.
Please suggest some design what i need to do.
^ permalink raw reply
* Re: arch: arm: bpf: Converting cBPF to eBPF for arm 32 bit
From: Shubham Bansal @ 2017-05-11 9:32 UTC (permalink / raw)
To: Kees Cook
Cc: David Miller, Mircea Gherzan, Network Development,
kernel-hardening, linux-arm-kernel, ast, Daniel Borkmann
In-Reply-To: <CAHgaXdKZ_v+iO7uqEDx7PA7D+xcp1FngGvJ1SRSsGXNQ-iWWDQ@mail.gmail.com>
Hi kees & Daniel,
David suggested following :
"""
eBPF has registers 0 through 10 plus you need to allocate another
temporary register for constant blinding (this is BPF_REG_AX).
I would put all of BPF_REG_0 through BPF_REG_5 in registers if
possible. BPF_REG_FP is the frame pointer which you don't have to
really allocate. That leaves BPF_REG_6 through BPF_REG_9, which
are callee saved, for perhaps stack slot allocation.
You seem to have R0 through R10 on ARM plus a separate frame pointer.
And then I see something called "LR" which is probably the function
return address register.Why can't you just use R0 through R9
for BPF_REG_0 through BPF_REG_9, BPF_REG_10 is just FP and then you
have R10 for BPF_REG_AX?
"""
"""
static const u8 bpf2a32[][2] = {
/* return value from in-kernel function, and exit value from eBPF */
[BPF_REG_0] = {ARM_R1, ARM_R0},
/* arguments from eBPF program to in-kernel function */
[BPF_REG_1] = {ARM_R1, ARM_R0},
[BPF_REG_2] = {ARM_R3, ARM_R2},
/* Stored on stack */
[BPF_REG_3] = {STACK_OFFSET(0), STACK_OFFSET(4)},
[BPF_REG_4] = {STACK_OFFSET(8), STACK_OFFSET(12)},
[BPF_REG_5] = {STACK_OFFSET(16), STACK_OFFSET(20)},
"bpf_jit/* callee saved registers that in-kernel function will preserve */
[BPF_REG_6] = {ARM_R5, ARM_R4},
[BPF_REG_7] = {STACK_OFFSET(24), STACK_OFFSET(28)},
/* Stored on stack */
[BPF_REG_8] = {STACK_OFFSET(32), STACK_OFFSET(36)},
[BPF_REG_9] = {STACK_OFFSET(40), STACK_OFFSET(44)},
/* Read only Frame Pointer to access Stack */
[BPF_REG_FP] = {ARM_FP},
/* Temperory Register for internal BPF JIT, can be used
* for constant blindings and others. */
[TMP_REG_1] = {ARM_R7, ARM_R6},
[TMP_REG_2] = {ARM_R10, ARM_R8},
/* Tail call count. */
[TCALL_CNT] = {STACK_OFFSET(48), STACK_OFFSET(52)},
[BPF_REG_AX] = {STACK_OFFSET(56), STACK_OFFSET(60)},
};
> How register starved are you?
Super Starved.
>
> eBPF has registers 0 through 10 plus you need to allocate another
> temporary register for constant blinding (this is BPF_REG_AX).
I am storing BPF_REG_AX on stack as of now.
>
> I would put all of BPF_REG_0 through BPF_REG_5 in registers if
> possible. BPF_REG_FP is the frame pointer which you don't have to
> really allocate. That leaves BPF_REG_6 through BPF_REG_9, which
> are callee saved, for perhaps stack slot allocation.
>
> You seem to have R0 through R10 on ARM plus a separate frame pointer.
> And then I see something called "LR" which is probably the function
> return address register. Why can't you just use R0 through R9
> for BPF_REG_0 through BPF_REG_9, BPF_REG_10 is just FP and then you
> have R10 for BPF_REG_AX?
I can't do that. BPF registers are 64 bits and ARM registers are 32
bit. So I have to map each BPF register with 2 arm registers.
Also, I need 4 temp registers which I am currently using.
"""
"""
>> I can't do that. BPF registers are 64 bits and ARM registers are 32
>> bit. So I have to map each BPF register with 2 arm registers.
>> Also, I need 4 temp registers which I am currently using.
>
> Ummm, no you don't.
>
> You can do proper data flow analysis on the register values and you
> can just use plain 32-bit registers when that is all that the data
> flow tells you the register is used for.
I don't understand. Can you explain that with example?
>
> This is what the netronome driver does, it is in the same situation
> you are. The NPU cpus on their networking card are 32-bits, and
> they have to do 32-bit value analysis while JIT'ing into their
> device.
As far as I know their ISA is more like cBPF? isn't it?
>
> It is actually rare for full 64-bit values to be used. Those ususally
> come from pointers. But on arm32, pointers will be 32-bits therefore
> any pointer relative value will be 32-bits as well.
Well, in that case I have to rewrite the whole code. I asked what
mapping I should use when I started and nobody replied so I went ahead
and started implementing. :(
>
> When you actually have to fabricate a full 64-bit operation, yeah
> use a stack slot or something like that.
So you are telling me to store the low 32 bit in registers and high 32
bit in scratch memory?
"""
What do you guys suggest i should implement it? I am almost done with
my current implementation but if you think I should change it to the
way David suggested, its better to suggest now before I send the
patch.
Let me know if you have any questions.
Best,
Shubham Bansal
On Thu, May 11, 2017 at 7:23 AM, Shubham Bansal
<illusionist.neo@gmail.com> wrote:
> Okay. My mistake.
>
> -Shubham
>
> On May 11, 2017 7:22 AM, "David Miller" <davem@davemloft.net> wrote:
>>
>>
>> Please keep this discussion on the mailing list.
>>
>> When you drop the CC:, you exclude the entire world from contributing
>> and continuing to help you.
^ permalink raw reply
* [PATCH v1] net/mlx4_core: Use min_t instead of if for consistency
From: Yuval Shaia @ 2017-05-11 8:46 UTC (permalink / raw)
To: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
---
v0 -> v1:
* s/"min_t("/"min_t(int"
---
drivers/net/ethernet/mellanox/mlx4/main.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7032054..7bb377e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2862,12 +2862,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
int port = 0;
if (msi_x) {
- int nreq = dev->caps.num_ports * num_online_cpus() + 1;
+ int nreq = min_t(int,
+ dev->caps.num_ports * num_online_cpus() + 1,
+ dev->caps.num_eqs - dev->caps.reserved_eqs);
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
- if (nreq > MAX_MSIX)
- nreq = MAX_MSIX;
+ nreq = min_t(int, nreq, MAX_MSIX);
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply related
* Re: [PATCH] net/mlx4_core: Use min_t instead of if for consistency
From: Leon Romanovsky @ 2017-05-11 8:28 UTC (permalink / raw)
To: Yuval Shaia
Cc: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494490852-5567-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
[-- Attachment #1: Type: text/plain, Size: 1332 bytes --]
On Thu, May 11, 2017 at 11:20:52AM +0300, Yuval Shaia wrote:
> Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
> ---
> drivers/net/ethernet/mellanox/mlx4/main.c | 9 ++++-----
> 1 file changed, 4 insertions(+), 5 deletions(-)
>
> diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
> index 7032054..a58b15a 100644
> --- a/drivers/net/ethernet/mellanox/mlx4/main.c
> +++ b/drivers/net/ethernet/mellanox/mlx4/main.c
> @@ -2862,12 +2862,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
> int port = 0;
>
> if (msi_x) {
> - int nreq = dev->caps.num_ports * num_online_cpus() + 1;
> + int nreq = min_t(int,
> + dev->caps.num_ports * num_online_cpus() + 1,
> + dev->caps.num_eqs - dev->caps.reserved_eqs);
>
> - nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
> - nreq);
> - if (nreq > MAX_MSIX)
> - nreq = MAX_MSIX;
> + nreq = min_t(nreq, MAX_MSIX);
I don't see min_t (int, ..) here.
>
> entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
> if (!entries)
> --
> 2.7.4
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
> the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 833 bytes --]
^ permalink raw reply
* Re: [PATCH] net/mlx4_core: Use min_t instead of if for consistency
From: Johannes Thumshirn @ 2017-05-11 8:28 UTC (permalink / raw)
To: Yuval Shaia, yishaih-VPRAkNaXOzVWk0Htik3J/w,
netdev-u79uwXL29TY76Z2rM5mHXA, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1494490852-5567-1-git-send-email-yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
On 05/11/2017 10:20 AM, Yuval Shaia wrote:
> + nreq = min_t(nreq, MAX_MSIX);
Ahm...
include/linux/kernel.h +802
#define min_t(type, x, y) \
__min(type, type, \
__UNIQUE_ID(min1_), __UNIQUE_ID(min2_), \
x, y)
Did you compile this patch?
--
Johannes Thumshirn Storage
jthumshirn-l3A5Bk7waGM@public.gmane.org +49 911 74053 689
SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: Felix Imendörffer, Jane Smithard, Graham Norton
HRB 21284 (AG Nürnberg)
Key fingerprint = EC38 9CAB C2C4 F25D 8600 D0D0 0393 969D 2D76 0850
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* [PATCH] net/mlx4_core: Use min_t instead of if for consistency
From: Yuval Shaia @ 2017-05-11 8:20 UTC (permalink / raw)
To: yishaih-VPRAkNaXOzVWk0Htik3J/w, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-rdma-u79uwXL29TY76Z2rM5mHXA
Signed-off-by: Yuval Shaia <yuval.shaia-QHcLZuEGTsvQT0dZR+AlfA@public.gmane.org>
---
drivers/net/ethernet/mellanox/mlx4/main.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 7032054..a58b15a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2862,12 +2862,11 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev)
int port = 0;
if (msi_x) {
- int nreq = dev->caps.num_ports * num_online_cpus() + 1;
+ int nreq = min_t(int,
+ dev->caps.num_ports * num_online_cpus() + 1,
+ dev->caps.num_eqs - dev->caps.reserved_eqs);
- nreq = min_t(int, dev->caps.num_eqs - dev->caps.reserved_eqs,
- nreq);
- if (nreq > MAX_MSIX)
- nreq = MAX_MSIX;
+ nreq = min_t(nreq, MAX_MSIX);
entries = kcalloc(nreq, sizeof *entries, GFP_KERNEL);
if (!entries)
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ 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