* [PATCH v3] ipv4: Early TCP socket demux.
From: David Miller @ 2012-06-20 4:49 UTC (permalink / raw)
To: netdev
Input packet processing for local sockets involves two major demuxes.
One for the route and one for the socket.
But we can optimize this down to one demux for certain kinds of local
sockets.
Currently we only do this for established TCP sockets, but it could
at least in theory be expanded to other kinds of connections.
If a TCP socket is established then it's identity is fully specified.
This means that whatever input route was used during the three-way
handshake must work equally well for the rest of the connection since
the keys will not change.
Once we move to established state, we cache the receive packet's input
route to use later.
Like the existing cached route in sk->sk_dst_cache used for output
packets, we have to check for route invalidations using dst->obsolete
and dst->ops->check().
Early demux occurs outside of a socket locked section, so when a route
invalidation occurs we defer the fixup of sk->sk_rx_dst until we are
actually inside of established state packet processing and thus have
the socket locked.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
This is the final version I pushed into net-next, it's just respun
with the MAX_INET_PROTOS hash masking removed.
include/net/inet_hashtables.h | 4 ++--
include/net/protocol.h | 1 +
include/net/sock.h | 2 ++
include/net/tcp.h | 1 +
net/core/sock.c | 5 +++++
net/ipv4/af_inet.c | 18 +++++++++-------
net/ipv4/ip_input.c | 39 ++++++++++++++++++++++------------
net/ipv4/tcp_input.c | 16 +++++++++++++-
net/ipv4/tcp_ipv4.c | 46 +++++++++++++++++++++++++++++++++++++++++
net/ipv4/tcp_minisocks.c | 2 ++
10 files changed, 110 insertions(+), 24 deletions(-)
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 808fc5f..54be028 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -379,10 +379,10 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
const __be16 sport,
const __be16 dport)
{
- struct sock *sk;
+ struct sock *sk = skb_steal_sock(skb);
const struct iphdr *iph = ip_hdr(skb);
- if (unlikely(sk = skb_steal_sock(skb)))
+ if (sk)
return sk;
else
return __inet_lookup(dev_net(skb_dst(skb)->dev), hashinfo,
diff --git a/include/net/protocol.h b/include/net/protocol.h
index a1b1b53..967b926 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -37,6 +37,7 @@
/* This is used to register protocols. */
struct net_protocol {
+ int (*early_demux)(struct sk_buff *skb);
int (*handler)(struct sk_buff *skb);
void (*err_handler)(struct sk_buff *skb, u32 info);
int (*gso_send_check)(struct sk_buff *skb);
diff --git a/include/net/sock.h b/include/net/sock.h
index 4a45216..87b424a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -319,6 +319,7 @@ struct sock {
unsigned long sk_flags;
struct dst_entry *sk_dst_cache;
spinlock_t sk_dst_lock;
+ struct dst_entry *sk_rx_dst;
atomic_t sk_wmem_alloc;
atomic_t sk_omem_alloc;
int sk_sndbuf;
@@ -1426,6 +1427,7 @@ extern struct sk_buff *sock_rmalloc(struct sock *sk,
gfp_t priority);
extern void sock_wfree(struct sk_buff *skb);
extern void sock_rfree(struct sk_buff *skb);
+extern void sock_edemux(struct sk_buff *skb);
extern int sock_setsockopt(struct socket *sock, int level,
int op, char __user *optval,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9332f34..6660ffc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -325,6 +325,7 @@ extern void tcp_v4_err(struct sk_buff *skb, u32);
extern void tcp_shutdown (struct sock *sk, int how);
+extern int tcp_v4_early_demux(struct sk_buff *skb);
extern int tcp_v4_rcv(struct sk_buff *skb);
extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index 9e5b71f..929bdcc 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1465,6 +1465,11 @@ void sock_rfree(struct sk_buff *skb)
}
EXPORT_SYMBOL(sock_rfree);
+void sock_edemux(struct sk_buff *skb)
+{
+ sock_put(skb->sk);
+}
+EXPORT_SYMBOL(sock_edemux);
int sock_i_uid(struct sock *sk)
{
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 85a3b17..07a02f6 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -157,6 +157,7 @@ void inet_sock_destruct(struct sock *sk)
kfree(rcu_dereference_protected(inet->inet_opt, 1));
dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
+ dst_release(sk->sk_rx_dst);
sk_refcnt_debug_dec(sk);
}
EXPORT_SYMBOL(inet_sock_destruct);
@@ -1518,14 +1519,15 @@ static const struct net_protocol igmp_protocol = {
#endif
static const struct net_protocol tcp_protocol = {
- .handler = tcp_v4_rcv,
- .err_handler = tcp_v4_err,
- .gso_send_check = tcp_v4_gso_send_check,
- .gso_segment = tcp_tso_segment,
- .gro_receive = tcp4_gro_receive,
- .gro_complete = tcp4_gro_complete,
- .no_policy = 1,
- .netns_ok = 1,
+ .early_demux = tcp_v4_early_demux,
+ .handler = tcp_v4_rcv,
+ .err_handler = tcp_v4_err,
+ .gso_send_check = tcp_v4_gso_send_check,
+ .gso_segment = tcp_tso_segment,
+ .gro_receive = tcp4_gro_receive,
+ .gro_complete = tcp4_gro_complete,
+ .no_policy = 1,
+ .netns_ok = 1,
};
static const struct net_protocol udp_protocol = {
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index c4fe1d2..93b092c 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -323,19 +323,32 @@ static int ip_rcv_finish(struct sk_buff *skb)
* how the packet travels inside Linux networking.
*/
if (skb_dst(skb) == NULL) {
- int err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
- iph->tos, skb->dev);
- if (unlikely(err)) {
- if (err == -EHOSTUNREACH)
- IP_INC_STATS_BH(dev_net(skb->dev),
- IPSTATS_MIB_INADDRERRORS);
- else if (err == -ENETUNREACH)
- IP_INC_STATS_BH(dev_net(skb->dev),
- IPSTATS_MIB_INNOROUTES);
- else if (err == -EXDEV)
- NET_INC_STATS_BH(dev_net(skb->dev),
- LINUX_MIB_IPRPFILTER);
- goto drop;
+ const struct net_protocol *ipprot;
+ int protocol = iph->protocol;
+ int err;
+
+ rcu_read_lock();
+ ipprot = rcu_dereference(inet_protos[protocol]);
+ err = -ENOENT;
+ if (ipprot && ipprot->early_demux)
+ err = ipprot->early_demux(skb);
+ rcu_read_unlock();
+
+ if (err) {
+ err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
+ iph->tos, skb->dev);
+ if (unlikely(err)) {
+ if (err == -EHOSTUNREACH)
+ IP_INC_STATS_BH(dev_net(skb->dev),
+ IPSTATS_MIB_INADDRERRORS);
+ else if (err == -ENETUNREACH)
+ IP_INC_STATS_BH(dev_net(skb->dev),
+ IPSTATS_MIB_INNOROUTES);
+ else if (err == -EXDEV)
+ NET_INC_STATS_BH(dev_net(skb->dev),
+ LINUX_MIB_IPRPFILTER);
+ goto drop;
+ }
}
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b224eb8..8416f8a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5518,6 +5518,18 @@ int tcp_rcv_established(struct sock *sk, struct sk_buff *skb,
struct tcp_sock *tp = tcp_sk(sk);
int res;
+ if (sk->sk_rx_dst) {
+ struct dst_entry *dst = sk->sk_rx_dst;
+ if (unlikely(dst->obsolete)) {
+ if (dst->ops->check(dst, 0) == NULL) {
+ dst_release(dst);
+ sk->sk_rx_dst = NULL;
+ }
+ }
+ }
+ if (unlikely(sk->sk_rx_dst == NULL))
+ sk->sk_rx_dst = dst_clone(skb_dst(skb));
+
/*
* Header prediction.
* The code loosely follows the one in the famous
@@ -5729,8 +5741,10 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
tcp_set_state(sk, TCP_ESTABLISHED);
- if (skb != NULL)
+ if (skb != NULL) {
+ sk->sk_rx_dst = dst_clone(skb_dst(skb));
security_inet_conn_established(sk, skb);
+ }
/* Make sure socket is routed, for correct metrics. */
icsk->icsk_af_ops->rebuild_header(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fda2ca1..13857df 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1671,6 +1671,52 @@ csum_err:
}
EXPORT_SYMBOL(tcp_v4_do_rcv);
+int tcp_v4_early_demux(struct sk_buff *skb)
+{
+ struct net *net = dev_net(skb->dev);
+ const struct iphdr *iph;
+ const struct tcphdr *th;
+ struct sock *sk;
+ int err;
+
+ err = -ENOENT;
+ if (skb->pkt_type != PACKET_HOST)
+ goto out_err;
+
+ if (!pskb_may_pull(skb, ip_hdrlen(skb) + sizeof(struct tcphdr)))
+ goto out_err;
+
+ iph = ip_hdr(skb);
+ th = (struct tcphdr *) ((char *)iph + ip_hdrlen(skb));
+
+ if (th->doff < sizeof(struct tcphdr) / 4)
+ goto out_err;
+
+ if (!pskb_may_pull(skb, ip_hdrlen(skb) + th->doff * 4))
+ goto out_err;
+
+ sk = __inet_lookup_established(net, &tcp_hashinfo,
+ iph->saddr, th->source,
+ iph->daddr, th->dest,
+ skb->dev->ifindex);
+ if (sk) {
+ skb->sk = sk;
+ skb->destructor = sock_edemux;
+ if (sk->sk_state != TCP_TIME_WAIT) {
+ struct dst_entry *dst = sk->sk_rx_dst;
+ if (dst)
+ dst = dst_check(dst, 0);
+ if (dst) {
+ skb_dst_set_noref(skb, dst);
+ err = 0;
+ }
+ }
+ }
+
+out_err:
+ return err;
+}
+
/*
* From tcp_input.c
*/
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index cb01531..72b7c63 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -445,6 +445,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_sock *oldtp = tcp_sk(sk);
struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
+ newsk->sk_rx_dst = dst_clone(skb_dst(skb));
+
/* TCP Cookie Transactions require space for the cookie pair,
* as it differs for each connection. There is no need to
* copy any s_data_payload stored at the original socket.
--
1.7.10
^ permalink raw reply related
* Re: [PATCH] net: Update netdev_alloc_frag to work more efficiently with TCP and GRO
From: Eric Dumazet @ 2012-06-20 5:36 UTC (permalink / raw)
To: Alexander Duyck; +Cc: netdev, davem, jeffrey.t.kirsher
In-Reply-To: <20120620004306.17814.58369.stgit@gitlad.jf.intel.com>
On Tue, 2012-06-19 at 17:43 -0700, Alexander Duyck wrote:
> This patch is meant to help improve system performance when
> netdev_alloc_frag is used in scenarios in which buffers are short lived.
> This is accomplished by allowing the page offset to be reset in the event
> that the page count is 1. I also reordered the direction in which we give
> out sections of the page so that we start at the end of the page and end at
> the start. The main motivation being that I preferred to have offset
> represent the amount of page remaining to be used.
>
> My primary test case was using ixgbe in combination with TCP. With this
> patch applied I saw CPU utilization drop from 3.4% to 3.0% for a single
> thread of netperf receiving a TCP stream via ixgbe.
>
> I also tested several scenarios in which the page reuse would not be
> possible such as UDP flows and routing. In both of these scenarios I saw
> no noticeable performance degradation compared to the kernel without this
> patch.
>
> Cc: Eric Dumazet <edumazet@google.com>
> Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
> ---
>
> net/core/skbuff.c | 15 +++++++++++----
> 1 files changed, 11 insertions(+), 4 deletions(-)
>
> diff --git a/net/core/skbuff.c b/net/core/skbuff.c
> index 5b21522..eb3853c 100644
> --- a/net/core/skbuff.c
> +++ b/net/core/skbuff.c
> @@ -317,15 +317,22 @@ void *netdev_alloc_frag(unsigned int fragsz)
> if (unlikely(!nc->page)) {
> refill:
> nc->page = alloc_page(GFP_ATOMIC | __GFP_COLD);
> - nc->offset = 0;
> }
> if (likely(nc->page)) {
> - if (nc->offset + fragsz > PAGE_SIZE) {
> + unsigned int offset = PAGE_SIZE;
> +
> + if (page_count(nc->page) != 1)
> + offset = nc->offset;
> +
> + if (offset < fragsz) {
> put_page(nc->page);
> goto refill;
> }
> - data = page_address(nc->page) + nc->offset;
> - nc->offset += fragsz;
> +
> + offset -= fragsz;
> + nc->offset = offset;
> +
> + data = page_address(nc->page) + offset;
> get_page(nc->page);
> }
> local_irq_restore(flags);
>
I tested this idea one month ago and got not convincing results, because
the branch was taken half of the time.
The cases where page can be reused is probably specific to ixgbe because
it uses a different allocator for the frags themselves.
netdev_alloc_frag() is only used to allocate the skb head.
For typical nics, we allocate frags to populate the RX ring _way_ before
packet is received by the NIC.
Then, I played with using order-2 pages instead of order-0 ones if
PAGE_SIZE < 8192.
No clear win either, but you might try this too.
^ permalink raw reply
* Re: [PATCH v2] ipv4: Early TCP socket demux.
From: Eric Dumazet @ 2012-06-20 5:49 UTC (permalink / raw)
To: David Miller; +Cc: shemminger, netdev
In-Reply-To: <20120619.214657.1345825814176201681.davem@davemloft.net>
On Tue, 2012-06-19 at 21:46 -0700, David Miller wrote:
> From: Stephen Hemminger <shemminger@vyatta.com>
> Date: Tue, 19 Jun 2012 19:35:49 -0700
>
> > Any benchmark numbers?
>
> Measuring the path from ip_rcv_finish() to where we lock the socket in
> tcp_v4_rcv(), on a SPARC-T3, with a pre-warmed routing cache:
>
> Both sk and RT lookup: ~4200 cycles
> Optimized early demux: ~2800 cycles
>
> These numbers can be decreased further, because since we're already
> looking at the TCP header we can pre-cook the TCP control block in the
> SKB and skip much of the stuff that tcp_v4_rcv() does since we've done
> it already in the early demux code.
>
> > I think the number of ref count operations per packet is going to be
> > the next line in the sand.
>
> There is only one, for the socket. We haven't taken a reference on the
> route for years.
Actually this patch makes things probably slower for :
1) routers :
Each incoming tcp packet has to perform lookups
(ESTABLISHED and TIMEWAIT), adding one cache miss
2) small lived tcp sessions
input dst is now dirtied because of the additional
dst_clone()/dst_release()
1) can be solved using a knob as suggested by Changli, possibly using a
JUMP_LABEL shadowing ip_forward ?
^ permalink raw reply
* Re: [PATCH v2] ipv4: Early TCP socket demux.
From: Eric Dumazet @ 2012-06-20 5:51 UTC (permalink / raw)
To: David Miller; +Cc: shemminger, netdev
In-Reply-To: <1340171359.4604.794.camel@edumazet-glaptop>
On Wed, 2012-06-20 at 07:49 +0200, Eric Dumazet wrote:
> 2) small lived tcp sessions
>
> input dst is now dirtied because of the additional
> dst_clone()/dst_release()
Not realy a concern because we dirty cache line anyway
dst_use_noref()
{
dst->__use++;
dst->lastuse = time;
}
^ permalink raw reply
* Re: [PATCH v2] ipv4: Early TCP socket demux.
From: Eric Dumazet @ 2012-06-20 5:59 UTC (permalink / raw)
To: David Miller; +Cc: shemminger, netdev
In-Reply-To: <20120619.214657.1345825814176201681.davem@davemloft.net>
On Tue, 2012-06-19 at 21:46 -0700, David Miller wrote:
> These numbers can be decreased further, because since we're already
> looking at the TCP header we can pre-cook the TCP control block in the
> SKB and skip much of the stuff that tcp_v4_rcv() does since we've done
> it already in the early demux code.
It could be done at GRO level and remove one another demux.
As routers probably have no use of GRO, no need of additional knob.
^ permalink raw reply
* [net-next.git 4/4 (v7)] phy: add the EEE support and the way to access to the MMD registers.
From: Giuseppe CAVALLARO @ 2012-06-20 6:12 UTC (permalink / raw)
To: netdev
Cc: eric.dumazet, bhutchings, rayagond, davem, yuvalmin,
Giuseppe Cavallaro
In-Reply-To: <1340172774-27443-1-git-send-email-peppe.cavallaro@st.com>
This patch adds the support for the Energy-Efficient Ethernet (EEE)
to the Physical Abstraction Layer.
To support the EEE we have to access to the MMD registers 3.20 and
7.60/61. So two new functions have been added to read/write the MMD
registers (clause 45).
An Ethernet driver (I tested the stmmac) can invoke the phy_init_eee to properly
check if the EEE is supported by the PHYs and it can also set the clock
stop enable bit in the 3.0 register.
The phy_get_eee_err can be used for reporting the number of time where
the PHY failed to complete its normal wake sequence.
In the end, this patch also adds the EEE ethtool support implementing:
o phy_ethtool_set_eee
o phy_ethtool_get_eee
v1: initial patch
v2: fixed some errors especially on naming convention
v3: renamed again the mmd read/write functions thank to Ben's feedback
v4: moved file to phy.c and added the ethtool support.
v5: fixed phy_adv_to_eee, phy_eee_to_supported, phy_eee_to_adv return
values according to ethtool API (thanks to Ben's feedback).
Renamed some macros to avoid too long names.
v6: fixed kernel-doc comments to be properly parsed.
Fixed the phy_init_eee function: we need to check which link mode
was autonegotiated and then the corresponding bits in 7.60 and 7.61
registers.
v7: reviewed the way to get the negotiated settings.
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
---
drivers/net/phy/phy.c | 281 +++++++++++++++++++++++++++++++++++++++++++++++++
include/linux/mdio.h | 21 +++-
include/linux/mii.h | 9 ++
include/linux/phy.h | 5 +
4 files changed, 312 insertions(+), 4 deletions(-)
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 2e1c237..e13a30d 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -35,6 +35,7 @@
#include <linux/phy.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
+#include <linux/mdio.h>
#include <linux/atomic.h>
#include <asm/io.h>
@@ -967,3 +968,283 @@ void phy_state_machine(struct work_struct *work)
schedule_delayed_work(&phydev->state_queue, PHY_STATE_TIME * HZ);
}
+
+static inline void mmd_phy_indirect(struct mii_bus *bus, int prtad, int devad,
+ int addr)
+{
+ /* Write the desired MMD Devad */
+ bus->write(bus, addr, MII_MMD_CTRL, devad);
+
+ /* Write the desired MMD register address */
+ bus->write(bus, addr, MII_MMD_DATA, prtad);
+
+ /* Select the Function : DATA with no post increment */
+ bus->write(bus, addr, MII_MMD_CTRL, (devad | MII_MMD_CTRL_NOINCR));
+}
+
+/**
+ * phy_read_mmd_indirect - reads data from the MMD registers
+ * @bus: the target MII bus
+ * @prtad: MMD Address
+ * @devad: MMD DEVAD
+ * @addr: PHY address on the MII bus
+ *
+ * Description: it reads data from the MMD registers (clause 22 to access to
+ * clause 45) of the specified phy address.
+ * To read these register we have:
+ * 1) Write reg 13 // DEVAD
+ * 2) Write reg 14 // MMD Address
+ * 3) Write reg 13 // MMD Data Command for MMD DEVAD
+ * 3) Read reg 14 // Read MMD data
+ */
+static int phy_read_mmd_indirect(struct mii_bus *bus, int prtad, int devad,
+ int addr)
+{
+ u32 ret;
+
+ mmd_phy_indirect(bus, prtad, devad, addr);
+
+ /* Read the content of the MMD's selected register */
+ ret = bus->read(bus, addr, MII_MMD_DATA);
+
+ return ret;
+}
+
+/**
+ * phy_write_mmd_indirect - writes data to the MMD registers
+ * @bus: the target MII bus
+ * @prtad: MMD Address
+ * @devad: MMD DEVAD
+ * @addr: PHY address on the MII bus
+ * @data: data to write in the MMD register
+ *
+ * Description: Write data from the MMD registers of the specified
+ * phy address.
+ * To write these register we have:
+ * 1) Write reg 13 // DEVAD
+ * 2) Write reg 14 // MMD Address
+ * 3) Write reg 13 // MMD Data Command for MMD DEVAD
+ * 3) Write reg 14 // Write MMD data
+ */
+static void phy_write_mmd_indirect(struct mii_bus *bus, int prtad, int devad,
+ int addr, u32 data)
+{
+ mmd_phy_indirect(bus, prtad, devad, addr);
+
+ /* Write the data into MMD's selected register */
+ bus->write(bus, addr, MII_MMD_DATA, data);
+}
+
+static u32 phy_eee_to_adv(u16 eee_adv)
+{
+ u32 adv = 0;
+
+ if (eee_adv & MDIO_EEE_100TX)
+ adv |= ADVERTISED_100baseT_Full;
+ if (eee_adv & MDIO_EEE_1000T)
+ adv |= ADVERTISED_1000baseT_Full;
+ if (eee_adv & MDIO_EEE_10GT)
+ adv |= ADVERTISED_10000baseT_Full;
+ if (eee_adv & MDIO_EEE_1000KX)
+ adv |= ADVERTISED_1000baseKX_Full;
+ if (eee_adv & MDIO_EEE_10GKX4)
+ adv |= ADVERTISED_10000baseKX4_Full;
+ if (eee_adv & MDIO_EEE_10GKR)
+ adv |= ADVERTISED_10000baseKR_Full;
+
+ return adv;
+}
+
+static u32 phy_eee_to_supported(u16 eee_caported)
+{
+ u32 supported = 0;
+
+ if (eee_caported & MDIO_EEE_100TX)
+ supported |= SUPPORTED_100baseT_Full;
+ if (eee_caported & MDIO_EEE_1000T)
+ supported |= SUPPORTED_1000baseT_Full;
+ if (eee_caported & MDIO_EEE_10GT)
+ supported |= SUPPORTED_10000baseT_Full;
+ if (eee_caported & MDIO_EEE_1000KX)
+ supported |= SUPPORTED_1000baseKX_Full;
+ if (eee_caported & MDIO_EEE_10GKX4)
+ supported |= SUPPORTED_10000baseKX4_Full;
+ if (eee_caported & MDIO_EEE_10GKR)
+ supported |= SUPPORTED_10000baseKR_Full;
+
+ return supported;
+}
+
+static u16 phy_adv_to_eee(u32 adv)
+{
+ u16 reg = 0;
+
+ if (adv & ADVERTISED_100baseT_Full)
+ reg |= MDIO_EEE_100TX;
+ if (adv & ADVERTISED_1000baseT_Full)
+ reg |= MDIO_EEE_1000T;
+ if (adv & ADVERTISED_10000baseT_Full)
+ reg |= MDIO_EEE_10GT;
+ if (adv & ADVERTISED_1000baseKX_Full)
+ reg |= MDIO_EEE_1000KX;
+ if (adv & ADVERTISED_10000baseKX4_Full)
+ reg |= MDIO_EEE_10GKX4;
+ if (adv & ADVERTISED_10000baseKR_Full)
+ reg |= MDIO_EEE_10GKR;
+
+ return reg;
+}
+
+/**
+ * phy_init_eee - init and check the EEE feature
+ * @phydev: target phy_device struct
+ * @clk_stop_enable: PHY may stop the clock during LPI
+ *
+ * Description: it checks if the Energy-Efficient Ethernet (EEE)
+ * is supported by looking at the MMD registers 3.20 and 7.60/61
+ * and it programs the MMD register 3.0 setting the "Clock stop enable"
+ * bit if required.
+ */
+int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
+{
+ int ret = -EPROTONOSUPPORT;
+
+ /* According to 802.3az,the EEE is supported only in full duplex-mode.
+ * Also EEE feature is active when core is operating with MII, GMII
+ * or RGMII.
+ */
+ if ((phydev->duplex == DUPLEX_FULL) &&
+ ((phydev->interface == PHY_INTERFACE_MODE_MII) ||
+ (phydev->interface == PHY_INTERFACE_MODE_GMII) ||
+ (phydev->interface == PHY_INTERFACE_MODE_RGMII))) {
+ u16 eee_lp, eee_cap, eee_adv;
+ u32 lp, cap, adv;
+ int idx;
+
+ /* Read phy status to properly get the right settings */
+ ret = phy_read_status(phydev);
+ if (ret)
+ return ret;
+
+ /* First check if the EEE ability is supported */
+ eee_cap = phy_read_mmd_indirect(phydev->bus, MDIO_PCS_EEE_ABLE,
+ MDIO_MMD_PCS, phydev->addr);
+ if (eee_cap < 0)
+ return eee_cap;
+
+ cap = phy_eee_to_supported(eee_cap);
+ if (!cap)
+ goto eee_exit;
+
+ /* Check which link settings negotiated and verify it in
+ * the EEE advertising registers.
+ */
+ eee_lp = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_LPABLE,
+ MDIO_MMD_AN, phydev->addr);
+ if (eee_lp < 0)
+ return eee_lp;
+
+ eee_adv = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_ADV,
+ MDIO_MMD_AN, phydev->addr);
+ if (eee_adv < 0)
+ return eee_adv;
+
+ adv = phy_eee_to_adv(eee_adv);
+ lp = phy_eee_to_adv(eee_lp);
+ idx = phy_find_setting(phydev->speed, phydev->duplex);
+ if ((lp & adv & settings[idx].setting))
+ goto eee_exit;
+
+ if (clk_stop_enable) {
+ /* Configure the PHY to stop receiving xMII
+ * clock while it is signaling LPI.
+ */
+ u32 val = phy_read_mmd_indirect(phydev->bus, MDIO_CTRL1,
+ MDIO_MMD_PCS,
+ phydev->addr);
+ if (val < 0)
+ return val;
+
+ val |= MDIO_PCS_CTRL1_CLKSTOP_EN;
+ phy_write_mmd_indirect(phydev->bus, MDIO_CTRL1,
+ MDIO_MMD_PCS, phydev->addr, val);
+ }
+
+ ret = 0; /* EEE supported */
+ }
+
+eee_exit:
+ return ret;
+}
+EXPORT_SYMBOL(phy_init_eee);
+
+/**
+ * phy_get_eee_err - report the EEE wake error count
+ * @phydev: target phy_device struct
+ *
+ * Description: it is to report the number of time where the PHY
+ * failed to complete its normal wake sequence.
+ */
+int phy_get_eee_err(struct phy_device *phydev)
+{
+ return phy_read_mmd_indirect(phydev->bus, MDIO_PCS_EEE_WK_ERR,
+ MDIO_MMD_PCS, phydev->addr);
+
+}
+EXPORT_SYMBOL(phy_get_eee_err);
+
+/**
+ * phy_ethtool_get_eee - get EEE supported and status
+ * @phydev: target phy_device struct
+ * @data: ethtool_eee data
+ *
+ * Description: it reportes the Supported/Advertisement/LP Advertisement
+ * capabilities.
+ */
+int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data)
+{
+ int val;
+
+ /* Get Supported EEE */
+ val = phy_read_mmd_indirect(phydev->bus, MDIO_PCS_EEE_ABLE,
+ MDIO_MMD_PCS, phydev->addr);
+ if (val < 0)
+ return val;
+ data->supported = phy_eee_to_supported(val);
+
+ /* Get advertisement EEE */
+ val = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_ADV,
+ MDIO_MMD_AN, phydev->addr);
+ if (val < 0)
+ return val;
+ data->advertised = phy_eee_to_adv(val);
+
+ /* Get LP advertisement EEE */
+ val = phy_read_mmd_indirect(phydev->bus, MDIO_AN_EEE_LPABLE,
+ MDIO_MMD_AN, phydev->addr);
+ if (val < 0)
+ return val;
+ data->lp_advertised = phy_eee_to_adv(val);
+
+ return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_get_eee);
+
+/**
+ * phy_ethtool_set_eee - set EEE supported and status
+ * @phydev: target phy_device struct
+ * @data: ethtool_eee data
+ *
+ * Description: it is to program the Advertisement EEE register.
+ */
+int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data)
+{
+ int val;
+
+ val = phy_adv_to_eee(data->advertised);
+ phy_write_mmd_indirect(phydev->bus, MDIO_AN_EEE_ADV, MDIO_MMD_AN,
+ phydev->addr, val);
+
+ return 0;
+}
+EXPORT_SYMBOL(phy_ethtool_set_eee);
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index dfb9479..4ad8f0e 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -43,7 +43,11 @@
#define MDIO_PKGID2 15
#define MDIO_AN_ADVERTISE 16 /* AN advertising (base page) */
#define MDIO_AN_LPA 19 /* AN LP abilities (base page) */
+#define MDIO_PCS_EEE_ABLE 20 /* EEE Capability register */
+#define MDIO_PCS_EEE_WK_ERR 22 /* EEE wake error counter */
#define MDIO_PHYXS_LNSTAT 24 /* PHY XGXS lane state */
+#define MDIO_AN_EEE_ADV 60 /* EEE advertisement */
+#define MDIO_AN_EEE_LPABLE 61 /* EEE link partner ability */
/* Media-dependent registers. */
#define MDIO_PMA_10GBT_SWAPPOL 130 /* 10GBASE-T pair swap & polarity */
@@ -56,7 +60,6 @@
#define MDIO_PCS_10GBRT_STAT2 33 /* 10GBASE-R/-T PCS status 2 */
#define MDIO_AN_10GBT_CTRL 32 /* 10GBASE-T auto-negotiation control */
#define MDIO_AN_10GBT_STAT 33 /* 10GBASE-T auto-negotiation status */
-#define MDIO_AN_EEE_ADV 60 /* EEE advertisement */
/* LASI (Link Alarm Status Interrupt) registers, defined by XENPAK MSA. */
#define MDIO_PMA_LASI_RXCTRL 0x9000 /* RX_ALARM control */
@@ -82,6 +85,7 @@
#define MDIO_AN_CTRL1_RESTART BMCR_ANRESTART
#define MDIO_AN_CTRL1_ENABLE BMCR_ANENABLE
#define MDIO_AN_CTRL1_XNP 0x2000 /* Enable extended next page */
+#define MDIO_PCS_CTRL1_CLKSTOP_EN 0x400 /* Stop the clock during LPI */
/* 10 Gb/s */
#define MDIO_CTRL1_SPEED10G (MDIO_CTRL1_SPEEDSELEXT | 0x00)
@@ -237,9 +241,18 @@
#define MDIO_AN_10GBT_STAT_MS 0x4000 /* Master/slave config */
#define MDIO_AN_10GBT_STAT_MSFLT 0x8000 /* Master/slave config fault */
-/* AN EEE Advertisement register. */
-#define MDIO_AN_EEE_ADV_100TX 0x0002 /* Advertise 100TX EEE cap */
-#define MDIO_AN_EEE_ADV_1000T 0x0004 /* Advertise 1000T EEE cap */
+/* EEE Supported/Advertisement/LP Advertisement registers.
+ *
+ * EEE capability Register (3.20), Advertisement (7.60) and
+ * Link partner ability (7.61) registers have and can use the same identical
+ * bit masks.
+ */
+#define MDIO_EEE_100TX 0x0002 /* 100TX EEE cap */
+#define MDIO_EEE_1000T 0x0004 /* 1000T EEE cap */
+#define MDIO_EEE_10GT 0x0008 /* 10GT EEE cap */
+#define MDIO_EEE_1000KX 0x0010 /* 1000KX EEE cap */
+#define MDIO_EEE_10GKX4 0x0020 /* 10G KX4 EEE cap */
+#define MDIO_EEE_10GKR 0x0040 /* 10G KR EEE cap */
/* LASI RX_ALARM control/status registers. */
#define MDIO_PMA_LASI_RX_PHYXSLFLT 0x0001 /* PHY XS RX local fault */
diff --git a/include/linux/mii.h b/include/linux/mii.h
index 2783eca..8ef3a7a 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -21,6 +21,8 @@
#define MII_EXPANSION 0x06 /* Expansion register */
#define MII_CTRL1000 0x09 /* 1000BASE-T control */
#define MII_STAT1000 0x0a /* 1000BASE-T status */
+#define MII_MMD_CTRL 0x0d /* MMD Access Control Register */
+#define MII_MMD_DATA 0x0e /* MMD Access Data Register */
#define MII_ESTATUS 0x0f /* Extended Status */
#define MII_DCOUNTER 0x12 /* Disconnect counter */
#define MII_FCSCOUNTER 0x13 /* False carrier counter */
@@ -141,6 +143,13 @@
#define FLOW_CTRL_TX 0x01
#define FLOW_CTRL_RX 0x02
+/* MMD Access Control register fields */
+#define MII_MMD_CTRL_DEVAD_MASK 0x1f /* Mask MMD DEVAD*/
+#define MII_MMD_CTRL_ADDR 0x0000 /* Address */
+#define MII_MMD_CTRL_NOINCR 0x4000 /* no post increment */
+#define MII_MMD_CTRL_INCR_RDWT 0x8000 /* post increment on reads & writes */
+#define MII_MMD_CTRL_INCR_ON_WT 0xC000 /* post increment on writes only */
+
/* This structure is used in all SIOCxMIIxxx ioctl calls */
struct mii_ioctl_data {
__u16 phy_id;
diff --git a/include/linux/phy.h b/include/linux/phy.h
index c291cae..97fc4cf 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -532,6 +532,11 @@ int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask,
int (*run)(struct phy_device *));
int phy_scan_fixups(struct phy_device *phydev);
+int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable);
+int phy_get_eee_err(struct phy_device *phydev);
+int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data);
+int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data);
+
int __init mdio_bus_init(void);
void mdio_bus_exit(void);
--
1.7.4.4
^ permalink raw reply related
* [net-next.git 2/4] stmmac: update the driver Documentation and add EEE
From: Giuseppe CAVALLARO @ 2012-06-20 6:12 UTC (permalink / raw)
To: netdev
Cc: eric.dumazet, bhutchings, rayagond, davem, yuvalmin,
Giuseppe Cavallaro
In-Reply-To: <1340172774-27443-1-git-send-email-peppe.cavallaro@st.com>
This patch updates the stmmac's documentation adding
some missing files in the section used to describe the
internal driver's structure.
Also the patch adds a new section to describe the EEE support.
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
---
Documentation/networking/stmmac.txt | 36 +++++++++++++++++++++++++++++-----
1 files changed, 30 insertions(+), 6 deletions(-)
diff --git a/Documentation/networking/stmmac.txt b/Documentation/networking/stmmac.txt
index 5cb9a19..c676b9c 100644
--- a/Documentation/networking/stmmac.txt
+++ b/Documentation/networking/stmmac.txt
@@ -257,9 +257,11 @@ reset procedure etc).
o Makefile
o stmmac_main.c: main network device driver;
o stmmac_mdio.c: mdio functions;
+ o stmmac_pci: PCI driver;
+ o stmmac_platform.c: platform driver
o stmmac_ethtool.c: ethtool support;
o stmmac_timer.[ch]: timer code used for mitigating the driver dma interrupts
- Only tested on ST40 platforms based.
+ (only tested on ST40 platforms based);
o stmmac.h: private driver structure;
o common.h: common definitions and VFTs;
o descs.h: descriptor structure definitions;
@@ -269,9 +271,11 @@ reset procedure etc).
o dwmac100_core: MAC 100 core and dma code;
o dwmac100_dma.c: dma funtions for the MAC chip;
o dwmac1000.h: specific header file for the MAC;
- o dwmac_lib.c: generic DMA functions shared among chips
- o enh_desc.c: functions for handling enhanced descriptors
- o norm_desc.c: functions for handling normal descriptors
+ o dwmac_lib.c: generic DMA functions shared among chips;
+ o enh_desc.c: functions for handling enhanced descriptors;
+ o norm_desc.c: functions for handling normal descriptors;
+ o chain_mode.c/ring_mode.c:: functions to manage RING/CHAINED modes;
+ o mmc_core.c/mmc.h: Management MAC Counters;
5) Debug Information
@@ -304,7 +308,27 @@ All these are only useful during the developing stage
and should never enabled inside the code for general usage.
In fact, these can generate an huge amount of debug messages.
-6) TODO:
+6) Energy Efficient Ethernet
+
+Energy Efficient Ethernet(EEE) enables IEEE 802.3 MAC sublayer along
+with a family of Physical layer to operate in the Low power Idle(LPI)
+mode. The EEE mode supports the IEEE 802.3 MAC operation at 100Mbps,
+1000Mbps & 10Gbps.
+
+The LPI mode allows power saving by switching off parts of the
+communication device functionality when there is no data to be
+transmitted & received. The system on both the side of the link can
+disable some functionalities & save power during the period of low-link
+utilization. The MAC controls whether the system should enter or exit
+the LPI mode & communicate this to PHY.
+
+As soon as the interface is opened, the driver verifies if the EEE can
+be supported. This is done by looking at both the DMA HW capability
+register and the PHY devices MCD registers.
+To enter in Tx LPI mode the driver needs to have a software timer
+that enable and disable the LPI mode when there is nothing to be
+transmitted.
+
+7) TODO:
o XGMAC is not supported.
- o Add the EEE - Energy Efficient Ethernet
o Add the PTP - precision time protocol
--
1.7.4.4
^ permalink raw reply related
* [net-next.git 1/4 (v3)] stmmac: do not use strict_strtoul but kstrtoint
From: Giuseppe CAVALLARO @ 2012-06-20 6:12 UTC (permalink / raw)
To: netdev
Cc: eric.dumazet, bhutchings, rayagond, davem, yuvalmin,
Giuseppe Cavallaro
In-Reply-To: <1340172774-27443-1-git-send-email-peppe.cavallaro@st.com>
This patch replaces the obsolete strict_strtoul with kstrtoint.
v2: also removed casting on kstrtoul.
v3: use kstrtoint instead of kstrtoul due to all vars are integer.
thanks to E. Dumazet.
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
---
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 27 +++++++-------------
1 files changed, 10 insertions(+), 17 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 590e95b..eba49cb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2129,42 +2129,35 @@ static int __init stmmac_cmdline_opt(char *str)
return -EINVAL;
while ((opt = strsep(&str, ",")) != NULL) {
if (!strncmp(opt, "debug:", 6)) {
- if (strict_strtoul(opt + 6, 0, (unsigned long *)&debug))
+ if (kstrtoint(opt + 6, 0, &debug))
goto err;
} else if (!strncmp(opt, "phyaddr:", 8)) {
- if (strict_strtoul(opt + 8, 0,
- (unsigned long *)&phyaddr))
+ if (kstrtoint(opt + 8, 0, &phyaddr))
goto err;
} else if (!strncmp(opt, "dma_txsize:", 11)) {
- if (strict_strtoul(opt + 11, 0,
- (unsigned long *)&dma_txsize))
+ if (kstrtoint(opt + 11, 0, &dma_txsize))
goto err;
} else if (!strncmp(opt, "dma_rxsize:", 11)) {
- if (strict_strtoul(opt + 11, 0,
- (unsigned long *)&dma_rxsize))
+ if (kstrtoint(opt + 11, 0, &dma_rxsize))
goto err;
} else if (!strncmp(opt, "buf_sz:", 7)) {
- if (strict_strtoul(opt + 7, 0,
- (unsigned long *)&buf_sz))
+ if (kstrtoint(opt + 7, 0, &buf_sz))
goto err;
} else if (!strncmp(opt, "tc:", 3)) {
- if (strict_strtoul(opt + 3, 0, (unsigned long *)&tc))
+ if (kstrtoint(opt + 3, 0, &tc))
goto err;
} else if (!strncmp(opt, "watchdog:", 9)) {
- if (strict_strtoul(opt + 9, 0,
- (unsigned long *)&watchdog))
+ if (kstrtoint(opt + 9, 0, &watchdog))
goto err;
} else if (!strncmp(opt, "flow_ctrl:", 10)) {
- if (strict_strtoul(opt + 10, 0,
- (unsigned long *)&flow_ctrl))
+ if (kstrtoint(opt + 10, 0, &flow_ctrl))
goto err;
} else if (!strncmp(opt, "pause:", 6)) {
- if (strict_strtoul(opt + 6, 0, (unsigned long *)&pause))
+ if (kstrtoint(opt + 6, 0, &pause))
goto err;
#ifdef CONFIG_STMMAC_TIMER
} else if (!strncmp(opt, "tmrate:", 7)) {
- if (strict_strtoul(opt + 7, 0,
- (unsigned long *)&tmrate))
+ if (kstrtoint(opt + 7, 0, &tmrate))
goto err;
#endif
}
--
1.7.4.4
^ permalink raw reply related
* [net-next.git 0/4] EEE for PAL and stmmac (V5)
From: Giuseppe CAVALLARO @ 2012-06-20 6:12 UTC (permalink / raw)
To: netdev
Cc: eric.dumazet, bhutchings, rayagond, davem, yuvalmin,
Giuseppe Cavallaro
These patches add the EEE support in the stmmac device driver
restoring an old work I had done some months ago and not
completed in time.
I've tested all on ST STB with the IC+ 101G PHY device that has
this feature.
The initial EEE support for the stmmac has been written by Rayagond
but I have reworked all his code adding new parts and especially
performing tests on a real hardware. Thx Rayagond!
In these patches, we can see that the stmmac supports the EEE
only if the DMA HW capability register says that this
feature is actually available. In that case, the driver can enter
in the Tx LPI mode by using a timer as recommended by Synopsys.
Note that EEE is supported in new chip generations; in particular
I used the 3.61a.
At any rate, further information about how the driver treats the EEE
can be found in the stmmac.txt file (there is a patch for that).
Another patch is for Physical Abstraction Layer now able to
manage the MMD registers (clause 45); it also provides the ethtool
support to manage supported/advertisement/lp adv features.
v3: fixed the "stmmac: do not use strict_strtoul but kstrtoint"
to use the kstrtoint.
v4: fixed the function to enable the EEE and add a check that verifies
if the link auto-negotiated matches with the bits in the adv and lp
registers.
v5: reviewed the way to get the negotiated settings
Giuseppe Cavallaro (4):
stmmac: do not use strict_strtoul but kstrtoint
stmmac: update the driver Documentation and add EEE
stmmac: add the Energy Efficient Ethernet support
phy: add the EEE support and the way to access to the MMD registers.
Documentation/networking/stmmac.txt | 36 ++-
drivers/net/ethernet/stmicro/stmmac/common.h | 31 ++-
drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 20 ++
.../net/ethernet/stmicro/stmmac/dwmac1000_core.c | 101 +++++++-
.../net/ethernet/stmicro/stmmac/dwmac100_core.c | 4 +-
drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 1 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 8 +
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 57 ++++
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 193 ++++++++++++--
.../net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +
drivers/net/phy/phy.c | 281 ++++++++++++++++++++
include/linux/mdio.h | 21 ++-
include/linux/mii.h | 9 +
include/linux/phy.h | 5 +
14 files changed, 724 insertions(+), 45 deletions(-)
--
1.7.4.4
^ permalink raw reply
* [net-next.git 3/4 (v5)] stmmac: add the Energy Efficient Ethernet support
From: Giuseppe CAVALLARO @ 2012-06-20 6:12 UTC (permalink / raw)
To: netdev
Cc: eric.dumazet, bhutchings, rayagond, davem, yuvalmin,
Giuseppe Cavallaro
In-Reply-To: <1340172774-27443-1-git-send-email-peppe.cavallaro@st.com>
This patch adds the Energy Efficient Ethernet support to the stmmac.
Please see the driver's documentation for further details about this support
in the driver.
Thanks also goes to Rayagond Kokatanur for his first implementation.
Note:
to clearly manage and expose the lpi interrupt status and eee ethtool
stats I've had to do some modifications to the driver's design and I
found really useful to move other parts of the code (e.g. mmc irq stat)
in the main directly. So this means that some core has been reworked
to introduce the EEE.
v1: initial patch
v2: fixed some sparse issues (typos)
v3: erroneously sent the v2 renamed as v3
v4:
o Fixed the return value of the stmmac_eee_init as suggested by D.Miller
o Totally reviewed the ethtool support for EEE
o Added a new internal parameter to tune the SW timer for TX LPI.
v5: do not change any eee setting in case of the stmmac_ethtool_op_set_eee fails
(it has to return -EOPNOTSUPP in that case).
Signed-off-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
---
drivers/net/ethernet/stmicro/stmmac/common.h | 31 ++++-
drivers/net/ethernet/stmicro/stmmac/dwmac1000.h | 20 +++
.../net/ethernet/stmicro/stmmac/dwmac1000_core.c | 101 +++++++++++-
.../net/ethernet/stmicro/stmmac/dwmac100_core.c | 4 +-
drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h | 1 +
drivers/net/ethernet/stmicro/stmmac/stmmac.h | 8 +
.../net/ethernet/stmicro/stmmac/stmmac_ethtool.c | 57 +++++++
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 166 +++++++++++++++++++-
.../net/ethernet/stmicro/stmmac/stmmac_platform.c | 2 +
9 files changed, 372 insertions(+), 18 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index bcd54d6..e2d0832 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -95,6 +95,16 @@ struct stmmac_extra_stats {
unsigned long poll_n;
unsigned long sched_timer_n;
unsigned long normal_irq_n;
+ unsigned long mmc_tx_irq_n;
+ unsigned long mmc_rx_irq_n;
+ unsigned long mmc_rx_csum_offload_irq_n;
+ /* EEE */
+ unsigned long irq_receive_pmt_irq_n;
+ unsigned long irq_tx_path_in_lpi_mode_n;
+ unsigned long irq_tx_path_exit_lpi_mode_n;
+ unsigned long irq_rx_path_in_lpi_mode_n;
+ unsigned long irq_rx_path_exit_lpi_mode_n;
+ unsigned long phy_eee_wakeup_error_n;
};
/* CSR Frequency Access Defines*/
@@ -162,6 +172,17 @@ enum tx_dma_irq_status {
handle_tx_rx = 3,
};
+enum core_specific_irq_mask {
+ core_mmc_tx_irq = 1,
+ core_mmc_rx_irq = 2,
+ core_mmc_rx_csum_offload_irq = 4,
+ core_irq_receive_pmt_irq = 8,
+ core_irq_tx_path_in_lpi_mode = 16,
+ core_irq_tx_path_exit_lpi_mode = 32,
+ core_irq_rx_path_in_lpi_mode = 64,
+ core_irq_rx_path_exit_lpi_mode = 128,
+};
+
/* DMA HW capabilities */
struct dma_features {
unsigned int mbps_10_100;
@@ -208,6 +229,10 @@ struct dma_features {
#define MAC_ENABLE_TX 0x00000008 /* Transmitter Enable */
#define MAC_RNABLE_RX 0x00000004 /* Receiver Enable */
+/* Default LPI timers */
+#define STMMAC_DEFAULT_LIT_LS_TIMER 0x3E8
+#define STMMAC_DEFAULT_TWT_LS_TIMER 0x0
+
struct stmmac_desc_ops {
/* DMA RX descriptor ring initialization */
void (*init_rx_desc) (struct dma_desc *p, unsigned int ring_size,
@@ -278,7 +303,7 @@ struct stmmac_ops {
/* Dump MAC registers */
void (*dump_regs) (void __iomem *ioaddr);
/* Handle extra events on specific interrupts hw dependent */
- void (*host_irq_status) (void __iomem *ioaddr);
+ int (*host_irq_status) (void __iomem *ioaddr);
/* Multicast filter setting */
void (*set_filter) (struct net_device *dev, int id);
/* Flow control setting */
@@ -291,6 +316,10 @@ struct stmmac_ops {
unsigned int reg_n);
void (*get_umac_addr) (void __iomem *ioaddr, unsigned char *addr,
unsigned int reg_n);
+ void (*set_eee_mode) (void __iomem *ioaddr);
+ void (*reset_eee_mode) (void __iomem *ioaddr);
+ void (*set_eee_timer) (void __iomem *ioaddr, int ls, int tw);
+ void (*set_eee_pls) (void __iomem *ioaddr, int link);
};
struct mac_link {
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 23478bf..f90fcb5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -36,6 +36,7 @@
#define GMAC_INT_STATUS 0x00000038 /* interrupt status register */
enum dwmac1000_irq_status {
+ lpiis_irq = 0x400,
time_stamp_irq = 0x0200,
mmc_rx_csum_offload_irq = 0x0080,
mmc_tx_irq = 0x0040,
@@ -60,6 +61,25 @@ enum power_event {
power_down = 0x00000001,
};
+/* Energy Efficient Ethernet (EEE)
+ *
+ * LPI status, timer and control register offset
+ */
+#define LPI_CTRL_STATUS 0x0030
+#define LPI_TIMER_CTRL 0x0034
+
+/* LPI control and status defines */
+#define LPI_CTRL_STATUS_LPITXA 0x00080000 /* Enable LPI TX Automate */
+#define LPI_CTRL_STATUS_PLSEN 0x00040000 /* Enable PHY Link Status */
+#define LPI_CTRL_STATUS_PLS 0x00020000 /* PHY Link Status */
+#define LPI_CTRL_STATUS_LPIEN 0x00010000 /* LPI Enable */
+#define LPI_CTRL_STATUS_RLPIST 0x00000200 /* Receive LPI state */
+#define LPI_CTRL_STATUS_TLPIST 0x00000100 /* Transmit LPI state */
+#define LPI_CTRL_STATUS_RLPIEX 0x00000008 /* Receive LPI Exit */
+#define LPI_CTRL_STATUS_RLPIEN 0x00000004 /* Receive LPI Entry */
+#define LPI_CTRL_STATUS_TLPIEX 0x00000002 /* Transmit LPI Exit */
+#define LPI_CTRL_STATUS_TLPIEN 0x00000001 /* Transmit LPI Entry */
+
/* GMAC HW ADDR regs */
#define GMAC_ADDR_HIGH(reg) (((reg > 15) ? 0x00000800 : 0x00000040) + \
(reg * 8))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index b5e4d02..bfe0226 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -194,26 +194,107 @@ static void dwmac1000_pmt(void __iomem *ioaddr, unsigned long mode)
}
-static void dwmac1000_irq_status(void __iomem *ioaddr)
+static int dwmac1000_irq_status(void __iomem *ioaddr)
{
u32 intr_status = readl(ioaddr + GMAC_INT_STATUS);
+ int status = 0;
/* Not used events (e.g. MMC interrupts) are not handled. */
- if ((intr_status & mmc_tx_irq))
- CHIP_DBG(KERN_DEBUG "GMAC: MMC tx interrupt: 0x%08x\n",
+ if ((intr_status & mmc_tx_irq)) {
+ CHIP_DBG(KERN_INFO "GMAC: MMC tx interrupt: 0x%08x\n",
readl(ioaddr + GMAC_MMC_TX_INTR));
- if (unlikely(intr_status & mmc_rx_irq))
- CHIP_DBG(KERN_DEBUG "GMAC: MMC rx interrupt: 0x%08x\n",
+ status |= core_mmc_tx_irq;
+ }
+ if (unlikely(intr_status & mmc_rx_irq)) {
+ CHIP_DBG(KERN_INFO "GMAC: MMC rx interrupt: 0x%08x\n",
readl(ioaddr + GMAC_MMC_RX_INTR));
- if (unlikely(intr_status & mmc_rx_csum_offload_irq))
- CHIP_DBG(KERN_DEBUG "GMAC: MMC rx csum offload: 0x%08x\n",
+ status |= core_mmc_rx_irq;
+ }
+ if (unlikely(intr_status & mmc_rx_csum_offload_irq)) {
+ CHIP_DBG(KERN_INFO "GMAC: MMC rx csum offload: 0x%08x\n",
readl(ioaddr + GMAC_MMC_RX_CSUM_OFFLOAD));
+ status |= core_mmc_rx_csum_offload_irq;
+ }
if (unlikely(intr_status & pmt_irq)) {
- CHIP_DBG(KERN_DEBUG "GMAC: received Magic frame\n");
+ CHIP_DBG(KERN_INFO "GMAC: received Magic frame\n");
/* clear the PMT bits 5 and 6 by reading the PMT
* status register. */
readl(ioaddr + GMAC_PMT);
+ status |= core_irq_receive_pmt_irq;
}
+ /* MAC trx/rx EEE LPI entry/exit interrupts */
+ if (intr_status & lpiis_irq) {
+ /* Clean LPI interrupt by reading the Reg 12 */
+ u32 lpi_status = readl(ioaddr + LPI_CTRL_STATUS);
+
+ if (lpi_status & LPI_CTRL_STATUS_TLPIEN) {
+ CHIP_DBG(KERN_INFO "GMAC TX entered in LPI\n");
+ status |= core_irq_tx_path_in_lpi_mode;
+ }
+ if (lpi_status & LPI_CTRL_STATUS_TLPIEX) {
+ CHIP_DBG(KERN_INFO "GMAC TX exit from LPI\n");
+ status |= core_irq_tx_path_exit_lpi_mode;
+ }
+ if (lpi_status & LPI_CTRL_STATUS_RLPIEN) {
+ CHIP_DBG(KERN_INFO "GMAC RX entered in LPI\n");
+ status |= core_irq_rx_path_in_lpi_mode;
+ }
+ if (lpi_status & LPI_CTRL_STATUS_RLPIEX) {
+ CHIP_DBG(KERN_INFO "GMAC RX exit from LPI\n");
+ status |= core_irq_rx_path_exit_lpi_mode;
+ }
+ }
+
+ return status;
+}
+
+static void dwmac1000_set_eee_mode(void __iomem *ioaddr)
+{
+ u32 value;
+
+ /* Enable the link status receive on RGMII, SGMII ore SMII
+ * receive path and instruct the transmit to enter in LPI
+ * state. */
+ value = readl(ioaddr + LPI_CTRL_STATUS);
+ value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+ writel(value, ioaddr + LPI_CTRL_STATUS);
+}
+
+static void dwmac1000_reset_eee_mode(void __iomem *ioaddr)
+{
+ u32 value;
+
+ value = readl(ioaddr + LPI_CTRL_STATUS);
+ value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA);
+ writel(value, ioaddr + LPI_CTRL_STATUS);
+}
+
+static void dwmac1000_set_eee_pls(void __iomem *ioaddr, int link)
+{
+ u32 value;
+
+ value = readl(ioaddr + LPI_CTRL_STATUS);
+
+ if (link)
+ value |= LPI_CTRL_STATUS_PLS;
+ else
+ value &= ~LPI_CTRL_STATUS_PLS;
+
+ writel(value, ioaddr + LPI_CTRL_STATUS);
+}
+
+static void dwmac1000_set_eee_timer(void __iomem *ioaddr, int ls, int tw)
+{
+ int value = ((tw & 0xffff)) | ((ls & 0x7ff) << 16);
+
+ /* Program the timers in the LPI timer control register:
+ * LS: minimum time (ms) for which the link
+ * status from PHY should be ok before transmitting
+ * the LPI pattern.
+ * TW: minimum time (us) for which the core waits
+ * after it has stopped transmitting the LPI pattern.
+ */
+ writel(value, ioaddr + LPI_TIMER_CTRL);
}
static const struct stmmac_ops dwmac1000_ops = {
@@ -226,6 +307,10 @@ static const struct stmmac_ops dwmac1000_ops = {
.pmt = dwmac1000_pmt,
.set_umac_addr = dwmac1000_set_umac_addr,
.get_umac_addr = dwmac1000_get_umac_addr,
+ .set_eee_mode = dwmac1000_set_eee_mode,
+ .reset_eee_mode = dwmac1000_reset_eee_mode,
+ .set_eee_timer = dwmac1000_set_eee_timer,
+ .set_eee_pls = dwmac1000_set_eee_pls,
};
struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
index 19e0f4e..f83210e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c
@@ -72,9 +72,9 @@ static int dwmac100_rx_ipc_enable(void __iomem *ioaddr)
return 0;
}
-static void dwmac100_irq_status(void __iomem *ioaddr)
+static int dwmac100_irq_status(void __iomem *ioaddr)
{
- return;
+ return 0;
}
static void dwmac100_set_umac_addr(void __iomem *ioaddr, unsigned char *addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
index 6e0360f..e678ce3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac_dma.h
@@ -70,6 +70,7 @@
#define DMA_INTR_DEFAULT_MASK (DMA_INTR_NORMAL | DMA_INTR_ABNORMAL)
/* DMA Status register defines */
+#define DMA_STATUS_GLPII 0x40000000 /* GMAC LPI interrupt */
#define DMA_STATUS_GPI 0x10000000 /* PMT interrupt */
#define DMA_STATUS_GMI 0x08000000 /* MMC interrupt */
#define DMA_STATUS_GLI 0x04000000 /* GMAC Line interface int */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index dc20c56..ab4c376 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -87,6 +87,12 @@ struct stmmac_priv {
#endif
int clk_csr;
int synopsys_id;
+ struct timer_list eee_ctrl_timer;
+ bool tx_path_in_lpi_mode;
+ int lpi_irq;
+ int eee_enabled;
+ int eee_active;
+ int tx_lpi_timer;
};
extern int phyaddr;
@@ -104,6 +110,8 @@ int stmmac_dvr_remove(struct net_device *ndev);
struct stmmac_priv *stmmac_dvr_probe(struct device *device,
struct plat_stmmacenet_data *plat_dat,
void __iomem *addr);
+void stmmac_disable_eee_mode(struct stmmac_priv *priv);
+bool stmmac_eee_init(struct stmmac_priv *priv);
#ifdef CONFIG_HAVE_CLK
static inline int stmmac_clk_enable(struct stmmac_priv *priv)
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
index ce43184..76fd61a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c
@@ -93,6 +93,16 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = {
STMMAC_STAT(poll_n),
STMMAC_STAT(sched_timer_n),
STMMAC_STAT(normal_irq_n),
+ STMMAC_STAT(normal_irq_n),
+ STMMAC_STAT(mmc_tx_irq_n),
+ STMMAC_STAT(mmc_rx_irq_n),
+ STMMAC_STAT(mmc_rx_csum_offload_irq_n),
+ STMMAC_STAT(irq_receive_pmt_irq_n),
+ STMMAC_STAT(irq_tx_path_in_lpi_mode_n),
+ STMMAC_STAT(irq_tx_path_exit_lpi_mode_n),
+ STMMAC_STAT(irq_rx_path_in_lpi_mode_n),
+ STMMAC_STAT(irq_rx_path_exit_lpi_mode_n),
+ STMMAC_STAT(phy_eee_wakeup_error_n),
};
#define STMMAC_STATS_LEN ARRAY_SIZE(stmmac_gstrings_stats)
@@ -366,6 +376,11 @@ static void stmmac_get_ethtool_stats(struct net_device *dev,
(*(u32 *)p);
}
}
+ if (priv->eee_enabled) {
+ int val = phy_get_eee_err(priv->phydev);
+ if (val)
+ priv->xstats.phy_eee_wakeup_error_n = val;
+ }
}
for (i = 0; i < STMMAC_STATS_LEN; i++) {
char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset;
@@ -464,6 +479,46 @@ static int stmmac_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
return 0;
}
+static int stmmac_ethtool_op_get_eee(struct net_device *dev,
+ struct ethtool_eee *edata)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ if (!priv->dma_cap.eee)
+ return -EOPNOTSUPP;
+
+ edata->eee_enabled = priv->eee_enabled;
+ edata->eee_active = priv->eee_active;
+ edata->tx_lpi_timer = priv->tx_lpi_timer;
+
+ return phy_ethtool_get_eee(priv->phydev, edata);
+}
+
+static int stmmac_ethtool_op_set_eee(struct net_device *dev,
+ struct ethtool_eee *edata)
+{
+ struct stmmac_priv *priv = netdev_priv(dev);
+
+ priv->eee_enabled = edata->eee_enabled;
+
+ if (!priv->eee_enabled)
+ stmmac_disable_eee_mode(priv);
+ else {
+ /* We are asking for enabling the EEE but it is safe
+ * to verify all by invoking the eee_init function.
+ * In case of failure it will return an error.
+ */
+ priv->eee_enabled = stmmac_eee_init(priv);
+ if (!priv->eee_enabled)
+ return -EOPNOTSUPP;
+
+ /* Do not change tx_lpi_timer in case of failure */
+ priv->tx_lpi_timer = edata->tx_lpi_timer;
+ }
+
+ return phy_ethtool_set_eee(priv->phydev, edata);
+}
+
static const struct ethtool_ops stmmac_ethtool_ops = {
.begin = stmmac_check_if_running,
.get_drvinfo = stmmac_ethtool_getdrvinfo,
@@ -480,6 +535,8 @@ static const struct ethtool_ops stmmac_ethtool_ops = {
.get_strings = stmmac_get_strings,
.get_wol = stmmac_get_wol,
.set_wol = stmmac_set_wol,
+ .get_eee = stmmac_ethtool_op_get_eee,
+ .set_eee = stmmac_ethtool_op_set_eee,
.get_sset_count = stmmac_get_sset_count,
.get_ts_info = ethtool_op_get_ts_info,
};
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index eba49cb..ea3bc09 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -133,6 +133,12 @@ static const u32 default_msg_level = (NETIF_MSG_DRV | NETIF_MSG_PROBE |
NETIF_MSG_LINK | NETIF_MSG_IFUP |
NETIF_MSG_IFDOWN | NETIF_MSG_TIMER);
+#define STMMAC_DEFAULT_LPI_TIMER 1000
+static int eee_timer = STMMAC_DEFAULT_LPI_TIMER;
+module_param(eee_timer, int, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(eee_timer, "LPI tx expiration time in msec");
+#define STMMAC_LPI_TIMER(x) (jiffies + msecs_to_jiffies(x))
+
static irqreturn_t stmmac_interrupt(int irq, void *dev_id);
#ifdef CONFIG_STMMAC_DEBUG_FS
@@ -161,6 +167,8 @@ static void stmmac_verify_args(void)
flow_ctrl = FLOW_OFF;
if (unlikely((pause < 0) || (pause > 0xffff)))
pause = PAUSE_TIME;
+ if (eee_timer < 0)
+ eee_timer = STMMAC_DEFAULT_LPI_TIMER;
}
static void stmmac_clk_csr_set(struct stmmac_priv *priv)
@@ -229,6 +237,85 @@ static inline void stmmac_hw_fix_mac_speed(struct stmmac_priv *priv)
phydev->speed);
}
+static void stmmac_enable_eee_mode(struct stmmac_priv *priv)
+{
+ /* Check and enter in LPI mode */
+ if ((priv->dirty_tx == priv->cur_tx) &&
+ (priv->tx_path_in_lpi_mode == false))
+ priv->hw->mac->set_eee_mode(priv->ioaddr);
+}
+
+void stmmac_disable_eee_mode(struct stmmac_priv *priv)
+{
+ /* Exit and disable EEE in case of we are are in LPI state. */
+ priv->hw->mac->reset_eee_mode(priv->ioaddr);
+ del_timer_sync(&priv->eee_ctrl_timer);
+ priv->tx_path_in_lpi_mode = false;
+}
+
+/**
+ * stmmac_eee_ctrl_timer
+ * @arg : data hook
+ * Description:
+ * If there is no data transfer and if we are not in LPI state,
+ * then MAC Transmitter can be moved to LPI state.
+ */
+static void stmmac_eee_ctrl_timer(unsigned long arg)
+{
+ struct stmmac_priv *priv = (struct stmmac_priv *)arg;
+
+ stmmac_enable_eee_mode(priv);
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
+}
+
+/**
+ * stmmac_eee_init
+ * @priv: private device pointer
+ * Description:
+ * If the EEE support has been enabled while configuring the driver,
+ * if the GMAC actually supports the EEE (from the HW cap reg) and the
+ * phy can also manage EEE, so enable the LPI state and start the timer
+ * to verify if the tx path can enter in LPI state.
+ */
+bool stmmac_eee_init(struct stmmac_priv *priv)
+{
+ bool ret = false;
+
+ /* MAC core supports the EEE feature. */
+ if (priv->dma_cap.eee) {
+ /* Check if the PHY supports EEE */
+ if (phy_init_eee(priv->phydev, 1))
+ goto out;
+
+ priv->eee_active = 1;
+ init_timer(&priv->eee_ctrl_timer);
+ priv->eee_ctrl_timer.function = stmmac_eee_ctrl_timer;
+ priv->eee_ctrl_timer.data = (unsigned long)priv;
+ priv->eee_ctrl_timer.expires = STMMAC_LPI_TIMER(eee_timer);
+ add_timer(&priv->eee_ctrl_timer);
+
+ priv->hw->mac->set_eee_timer(priv->ioaddr,
+ STMMAC_DEFAULT_LIT_LS_TIMER,
+ priv->tx_lpi_timer);
+
+ pr_info("stmmac: Energy-Efficient Ethernet initialized\n");
+
+ ret = true;
+ }
+out:
+ return ret;
+}
+
+static void stmmac_eee_adjust(struct stmmac_priv *priv)
+{
+ /* When the EEE has been already initialised we have to
+ * modify the PLS bit in the LPI ctrl & status reg according
+ * to the PHY link status. For this reason.
+ */
+ if (priv->eee_enabled)
+ priv->hw->mac->set_eee_pls(priv->ioaddr, priv->phydev->link);
+}
+
/**
* stmmac_adjust_link
* @dev: net device structure
@@ -249,6 +336,7 @@ static void stmmac_adjust_link(struct net_device *dev)
phydev->addr, phydev->link);
spin_lock_irqsave(&priv->lock, flags);
+
if (phydev->link) {
u32 ctrl = readl(priv->ioaddr + MAC_CTRL_REG);
@@ -315,6 +403,8 @@ static void stmmac_adjust_link(struct net_device *dev)
if (new_state && netif_msg_link(priv))
phy_print_status(phydev);
+ stmmac_eee_adjust(priv);
+
spin_unlock_irqrestore(&priv->lock, flags);
DBG(probe, DEBUG, "stmmac_adjust_link: exiting\n");
@@ -332,7 +422,7 @@ static int stmmac_init_phy(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
struct phy_device *phydev;
- char phy_id[MII_BUS_ID_SIZE + 3];
+ char phy_id_fmt[MII_BUS_ID_SIZE + 3];
char bus_id[MII_BUS_ID_SIZE];
int interface = priv->plat->interface;
priv->oldlink = 0;
@@ -346,11 +436,12 @@ static int stmmac_init_phy(struct net_device *dev)
snprintf(bus_id, MII_BUS_ID_SIZE, "stmmac-%x",
priv->plat->bus_id);
- snprintf(phy_id, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
+ snprintf(phy_id_fmt, MII_BUS_ID_SIZE + 3, PHY_ID_FMT, bus_id,
priv->plat->phy_addr);
- pr_debug("stmmac_init_phy: trying to attach to %s\n", phy_id);
+ pr_debug("stmmac_init_phy: trying to attach to %s\n", phy_id_fmt);
- phydev = phy_connect(dev, phy_id, &stmmac_adjust_link, 0, interface);
+ phydev = phy_connect(dev, phy_id_fmt, &stmmac_adjust_link, 0,
+ interface);
if (IS_ERR(phydev)) {
pr_err("%s: Could not attach to PHY\n", dev->name);
@@ -689,6 +780,11 @@ static void stmmac_tx(struct stmmac_priv *priv)
}
netif_tx_unlock(priv->dev);
}
+
+ if ((priv->eee_enabled) && (!priv->tx_path_in_lpi_mode)) {
+ stmmac_enable_eee_mode(priv);
+ mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_TIMER(eee_timer));
+ }
spin_unlock(&priv->tx_lock);
}
@@ -1027,6 +1123,17 @@ static int stmmac_open(struct net_device *dev)
}
}
+ /* Request the IRQ lines */
+ if (priv->lpi_irq != -ENXIO) {
+ ret = request_irq(priv->lpi_irq, stmmac_interrupt, IRQF_SHARED,
+ dev->name, dev);
+ if (unlikely(ret < 0)) {
+ pr_err("%s: ERROR: allocating the LPI IRQ %d (%d)\n",
+ __func__, priv->lpi_irq, ret);
+ goto open_error_lpiirq;
+ }
+ }
+
/* Enable the MAC Rx/Tx */
stmmac_set_mac(priv->ioaddr, true);
@@ -1062,12 +1169,19 @@ static int stmmac_open(struct net_device *dev)
if (priv->phydev)
phy_start(priv->phydev);
+ priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS_TIMER;
+ priv->eee_enabled = stmmac_eee_init(priv);
+
napi_enable(&priv->napi);
skb_queue_head_init(&priv->rx_recycle);
netif_start_queue(dev);
return 0;
+open_error_lpiirq:
+ if (priv->wol_irq != dev->irq)
+ free_irq(priv->wol_irq, dev);
+
open_error_wolirq:
free_irq(dev->irq, dev);
@@ -1093,6 +1207,9 @@ static int stmmac_release(struct net_device *dev)
{
struct stmmac_priv *priv = netdev_priv(dev);
+ if (priv->eee_enabled)
+ del_timer_sync(&priv->eee_ctrl_timer);
+
/* Stop and disconnect the PHY */
if (priv->phydev) {
phy_stop(priv->phydev);
@@ -1115,6 +1232,8 @@ static int stmmac_release(struct net_device *dev)
free_irq(dev->irq, dev);
if (priv->wol_irq != dev->irq)
free_irq(priv->wol_irq, dev);
+ if (priv->lpi_irq != -ENXIO)
+ free_irq(priv->lpi_irq, dev);
/* Stop TX/RX DMA and clear the descriptors */
priv->hw->dma->stop_tx(priv->ioaddr);
@@ -1164,6 +1283,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev)
spin_lock(&priv->tx_lock);
+ if (priv->tx_path_in_lpi_mode)
+ stmmac_disable_eee_mode(priv);
+
entry = priv->cur_tx % txsize;
#ifdef STMMAC_XMIT_DEBUG
@@ -1540,10 +1662,37 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
return IRQ_NONE;
}
- if (priv->plat->has_gmac)
- /* To handle GMAC own interrupts */
- priv->hw->mac->host_irq_status((void __iomem *) dev->base_addr);
+ /* To handle GMAC own interrupts */
+ if (priv->plat->has_gmac) {
+ int status = priv->hw->mac->host_irq_status((void __iomem *)
+ dev->base_addr);
+ if (unlikely(status)) {
+ if (status & core_mmc_tx_irq)
+ priv->xstats.mmc_tx_irq_n++;
+ if (status & core_mmc_rx_irq)
+ priv->xstats.mmc_rx_irq_n++;
+ if (status & core_mmc_rx_csum_offload_irq)
+ priv->xstats.mmc_rx_csum_offload_irq_n++;
+ if (status & core_irq_receive_pmt_irq)
+ priv->xstats.irq_receive_pmt_irq_n++;
+
+ /* For LPI we need to save the tx status */
+ if (status & core_irq_tx_path_in_lpi_mode) {
+ priv->xstats.irq_tx_path_in_lpi_mode_n++;
+ priv->tx_path_in_lpi_mode = true;
+ }
+ if (status & core_irq_tx_path_exit_lpi_mode) {
+ priv->xstats.irq_tx_path_exit_lpi_mode_n++;
+ priv->tx_path_in_lpi_mode = false;
+ }
+ if (status & core_irq_rx_path_in_lpi_mode)
+ priv->xstats.irq_rx_path_in_lpi_mode_n++;
+ if (status & core_irq_rx_path_exit_lpi_mode)
+ priv->xstats.irq_rx_path_exit_lpi_mode_n++;
+ }
+ }
+ /* To handle DMA interrupts */
stmmac_dma_interrupt(priv);
return IRQ_HANDLED;
@@ -2155,6 +2304,9 @@ static int __init stmmac_cmdline_opt(char *str)
} else if (!strncmp(opt, "pause:", 6)) {
if (kstrtoint(opt + 6, 0, &pause))
goto err;
+ } else if (!strncmp(opt, "eee_timer:", 6)) {
+ if (kstrtoint(opt + 10, 0, &eee_timer))
+ goto err;
#ifdef CONFIG_STMMAC_TIMER
} else if (!strncmp(opt, "tmrate:", 7)) {
if (kstrtoint(opt + 7, 0, &tmrate))
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 20eb502..7d36163 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -156,6 +156,8 @@ static int stmmac_pltfr_probe(struct platform_device *pdev)
if (priv->wol_irq == -ENXIO)
priv->wol_irq = priv->dev->irq;
+ priv->lpi_irq = platform_get_irq_byname(pdev, "eth_lpi");
+
platform_set_drvdata(pdev, priv->dev);
pr_debug("STMMAC platform driver registration completed");
--
1.7.4.4
^ permalink raw reply related
* Re: [PATCH v2] ipv4: Early TCP socket demux.
From: David Miller @ 2012-06-20 6:14 UTC (permalink / raw)
To: eric.dumazet; +Cc: shemminger, netdev
In-Reply-To: <1340171489.4604.796.camel@edumazet-glaptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 20 Jun 2012 07:51:29 +0200
> On Wed, 2012-06-20 at 07:49 +0200, Eric Dumazet wrote:
>
>> 2) small lived tcp sessions
>>
>> input dst is now dirtied because of the additional
>> dst_clone()/dst_release()
>
> Not realy a concern because we dirty cache line anyway
>
> dst_use_noref()
> {
> dst->__use++;
> dst->lastuse = time;
> }
Right, the costs probably even out for short TCP flows.
But better to do real tests than to believe what any of
us say. :-)
^ permalink raw reply
* Re: [PATCH v2] ipv4: Early TCP socket demux.
From: David Miller @ 2012-06-20 6:14 UTC (permalink / raw)
To: eric.dumazet; +Cc: shemminger, netdev
In-Reply-To: <1340171940.4604.799.camel@edumazet-glaptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 20 Jun 2012 07:59:00 +0200
> On Tue, 2012-06-19 at 21:46 -0700, David Miller wrote:
>
>> These numbers can be decreased further, because since we're already
>> looking at the TCP header we can pre-cook the TCP control block in the
>> SKB and skip much of the stuff that tcp_v4_rcv() does since we've done
>> it already in the early demux code.
>
> It could be done at GRO level and remove one another demux.
>
> As routers probably have no use of GRO, no need of additional knob.
That's a great idea.
^ permalink raw reply
* Re: [patch net-next 00/19] team: couple of patches
From: Jesper Dangaard Brouer @ 2012-06-20 6:40 UTC (permalink / raw)
To: David Miller; +Cc: jpirko, netdev, eric.dumazet
In-Reply-To: <20120619.150124.1674713634175419404.davem@davemloft.net>
On Tue, 2012-06-19 at 15:01 -0700, David Miller wrote:
> From: Jiri Pirko <jpirko@redhat.com>
> Date: Tue, 19 Jun 2012 17:54:02 +0200
>
> > The main impact is this patchset provides an implementation of userspace driven
> > TX loadbalancing for team driver.
> >
> > Also couple of typos are fixed, minor issues fixes.
>
> Looks good, pushed, thanks Jiri.
Just for the record, I have also reviewed the patch series (before
submission), and ACK the series.
--
Best regards,
Jesper Dangaard Brouer
MSc.CS, Sr. Network Kernel Developer at Red Hat
Author of http://www.iptv-analyzer.org
LinkedIn: http://www.linkedin.com/in/brouer
^ permalink raw reply
* Re: 10GBE performance drop with net.ipv4.tcp_timestamps=0
From: Stefan Priebe - Profihost AG @ 2012-06-20 7:00 UTC (permalink / raw)
To: Eric Dumazet; +Cc: Linux Netdev List
In-Reply-To: <1340141493.4604.773.camel@edumazet-glaptop>
Am 19.06.2012 23:31, schrieb Eric Dumazet:
> On Tue, 2012-06-19 at 23:08 +0200, Stefan Priebe wrote:
>> i'm testing 10GBE speed with tweo servers. One with 3.5-rc3 nd thoe
>> other one whith RHEL 6 (2.6.32 kernel).
>>
>> I noticed that setting
>> net.ipv4.tcp_timestamps=0
>>
>> descreased the performance from 9,7 Full Duplex to 3-4Gb/s.
>>
>> Is this bahviour fine? What should / could i tet?
>>
>
> Really, you should provide more input than that, if you really want us
> to help.
*arg* forgot to add the pastebin links. Sorry. Speed degraded in this
case from 9,88Gbit/s to 2,45Gbit/s. When i turn on timestamps it's
perfect again. Server A has 3.5.0-rc3 and server B has an RHEL6 2.6.32
kernel.
Before:
http://pastebin.com/raw.php?i=1gVraWVc
After:
http://pastebin.com/raw.php?i=NSh8Y29s
Thanks,
Stefan
^ permalink raw reply
* Re: [PATCH v3] ipv4: Early TCP socket demux.
From: Julian Anastasov @ 2012-06-20 7:00 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20120619.214957.1282277480138040899.davem@davemloft.net>
Hello,
On Tue, 19 Jun 2012, David Miller wrote:
> + if (sk->sk_state != TCP_TIME_WAIT) {
> + struct dst_entry *dst = sk->sk_rx_dst;
> + if (dst)
> + dst = dst_check(dst, 0);
What about checking rp_filter here or before dst_check:
rcu_read_lock();
in_dev = __in_dev_get_rcu(dst->dev);
if (skb->dev != dst->dev &&
(!in_dev || IN_DEV_RPFILTER(in_dev)))
dst = NULL;
rcu_read_unlock();
But may be it is a bad idea to return cached dst
that is with different dev. May be it is better a simple
check instead:
if (skb->dev != dst->dev)
dst = NULL;
It will work for the common case of traffic using
same dev.
> + if (dst) {
> + skb_dst_set_noref(skb, dst);
> + err = 0;
> + }
Also, is it a good idea to hide such optimizations
in a bit mask:
sysctl_net_optimizations & 1: optimize for end host
sysctl_net_optimizations & 2: optimize for router
...
Regards
--
Julian Anastasov <ja@ssi.bg>
^ permalink raw reply
* [PATCH -v1 2/3] usbnet: decrease suspend count if returning -EBUSY for runtime suspend
From: Ming Lei @ 2012-06-20 7:15 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman
Cc: Oliver Neukum, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-usb-u79uwXL29TY76Z2rM5mHXA, Ming Lei
In-Reply-To: <1340176553-32225-1-git-send-email-ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
This patch decreases dev->suspend_count in the -EBUSY failure path
of usbnet_suspend. Without the change, the later runtime suspend
will do nothing except for increasing dev->suspend_count.
Signed-off-by: Ming Lei <ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
---
drivers/net/usb/usbnet.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index f06cf9b..9bfa775 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1508,6 +1508,7 @@ int usbnet_suspend (struct usb_interface *intf, pm_message_t message)
spin_lock_irq(&dev->txq.lock);
/* don't autosuspend while transmitting */
if (dev->txq.qlen && PMSG_IS_AUTO(message)) {
+ dev->suspend_count--;
spin_unlock_irq(&dev->txq.lock);
return -EBUSY;
} else {
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" 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 -v1 3/3] usbnet: handle remote wakeup asap
From: Ming Lei @ 2012-06-20 7:15 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman
Cc: Oliver Neukum, netdev-u79uwXL29TY76Z2rM5mHXA,
linux-usb-u79uwXL29TY76Z2rM5mHXA, Ming Lei
In-Reply-To: <1340176553-32225-1-git-send-email-ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
If usbnet is resumed by remote wakeup, generally there are
some packets comming to be handled, so allocate and submit
rx URBs in usbnet_resume to avoid delays introduced by tasklet.
Otherwise, usbnet may have been runtime suspended before the
usbnet_bh is executed to schedule Rx URBs.
Without the patch, usbnet can't recieve any packets from peer
in runtime suspend state if runtime PM is enabled and
autosuspend_delay is set as zero.
Signed-off-by: Ming Lei <ming.lei-Z7WLFzj8eWMS+FvcfC7Uqw@public.gmane.org>
---
drivers/net/usb/usbnet.c | 42 ++++++++++++++++++++++++++----------------
1 file changed, 26 insertions(+), 16 deletions(-)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index 9bfa775..a89d6c5 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1201,6 +1201,21 @@ deferred:
}
EXPORT_SYMBOL_GPL(usbnet_start_xmit);
+static void rx_alloc_submit(struct usbnet *dev, gfp_t flags)
+{
+ struct urb *urb;
+ int i;
+
+ /* don't refill the queue all at once */
+ for (i = 0; i < 10 && dev->rxq.qlen < RX_QLEN(dev); i++) {
+ urb = usb_alloc_urb(0, flags);
+ if (urb != NULL) {
+ if (rx_submit(dev, urb, flags) == -ENOLINK)
+ return;
+ }
+ }
+}
+
/*-------------------------------------------------------------------------*/
// tasklet (work deferred from completions, in_irq) or timer
@@ -1240,26 +1255,14 @@ static void usbnet_bh (unsigned long param)
!timer_pending (&dev->delay) &&
!test_bit (EVENT_RX_HALT, &dev->flags)) {
int temp = dev->rxq.qlen;
- int qlen = RX_QLEN (dev);
-
- if (temp < qlen) {
- struct urb *urb;
- int i;
-
- // don't refill the queue all at once
- for (i = 0; i < 10 && dev->rxq.qlen < qlen; i++) {
- urb = usb_alloc_urb (0, GFP_ATOMIC);
- if (urb != NULL) {
- if (rx_submit (dev, urb, GFP_ATOMIC) ==
- -ENOLINK)
- return;
- }
- }
+
+ if (temp < RX_QLEN(dev)) {
+ rx_alloc_submit(dev, GFP_ATOMIC);
if (temp != dev->rxq.qlen)
netif_dbg(dev, link, dev->net,
"rxqlen %d --> %d\n",
temp, dev->rxq.qlen);
- if (dev->rxq.qlen < qlen)
+ if (dev->rxq.qlen < RX_QLEN(dev))
tasklet_schedule (&dev->bh);
}
if (dev->txq.qlen < TX_QLEN (dev))
@@ -1565,6 +1568,13 @@ int usbnet_resume (struct usb_interface *intf)
spin_unlock_irq(&dev->txq.lock);
if (test_bit(EVENT_DEV_OPEN, &dev->flags)) {
+ /* handle remote wakeup ASAP */
+ if (!dev->wait &&
+ netif_device_present(dev->net) &&
+ !timer_pending(&dev->delay) &&
+ !test_bit(EVENT_RX_HALT, &dev->flags))
+ rx_alloc_submit(dev, GFP_KERNEL);
+
if (!(dev->txq.qlen >= TX_QLEN(dev)))
netif_tx_wake_all_queues(dev->net);
tasklet_schedule (&dev->bh);
--
1.7.9.5
--
To unsubscribe from this list: send the line "unsubscribe linux-usb" 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 -v1 0/3] usbnet: usbnet: PM related fixes
From: Ming Lei @ 2012-06-20 7:15 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman; +Cc: Oliver Neukum, netdev, linux-usb
Hi David,
The 3 patches fix some PM related problems.
v1:
- one line fix in 3/3: GFP_ATOMIC -> flags in rx_alloc_submit
drivers/net/usb/usbnet.c | 47 +++++++++++++++++++++++++++++-----------------
1 file changed, 30 insertions(+), 17 deletions(-)
Thanks,
--
Ming Lei
^ permalink raw reply
* [PATCH -v1 1/3] usbnet: clear OPEN flag in failure path
From: Ming Lei @ 2012-06-20 7:15 UTC (permalink / raw)
To: David S. Miller, Greg Kroah-Hartman
Cc: Oliver Neukum, netdev, linux-usb, Ming Lei
In-Reply-To: <1340176553-32225-1-git-send-email-ming.lei@canonical.com>
Without clearing OPEN flag in failure path, runtime or system resume
may submit interrupt/rx URB and start tx queue mistakenly on a
interface in DOWN state.
Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
drivers/net/usb/usbnet.c | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index ac2e493..f06cf9b 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -793,11 +793,13 @@ int usbnet_open (struct net_device *net)
if (info->manage_power) {
retval = info->manage_power(dev, 1);
if (retval < 0)
- goto done;
+ goto done_manage_power_error;
usb_autopm_put_interface(dev->intf);
}
return retval;
+done_manage_power_error:
+ clear_bit(EVENT_DEV_OPEN, &dev->flags);
done:
usb_autopm_put_interface(dev->intf);
done_nopm:
--
1.7.9.5
^ permalink raw reply related
* Re: 10GBE performance drop with net.ipv4.tcp_timestamps=0
From: Eric Dumazet @ 2012-06-20 7:22 UTC (permalink / raw)
To: Stefan Priebe - Profihost AG; +Cc: Linux Netdev List
In-Reply-To: <4FE17522.5050005@profihost.ag>
On Wed, 2012-06-20 at 09:00 +0200, Stefan Priebe - Profihost AG wrote:
> Am 19.06.2012 23:31, schrieb Eric Dumazet:
> > On Tue, 2012-06-19 at 23:08 +0200, Stefan Priebe wrote:
> >> i'm testing 10GBE speed with tweo servers. One with 3.5-rc3 nd thoe
> >> other one whith RHEL 6 (2.6.32 kernel).
> >>
> >> I noticed that setting
> >> net.ipv4.tcp_timestamps=0
> >>
> >> descreased the performance from 9,7 Full Duplex to 3-4Gb/s.
> >>
> >> Is this bahviour fine? What should / could i tet?
> >>
> >
> > Really, you should provide more input than that, if you really want us
> > to help.
>
> *arg* forgot to add the pastebin links. Sorry. Speed degraded in this
> case from 9,88Gbit/s to 2,45Gbit/s. When i turn on timestamps it's
> perfect again. Server A has 3.5.0-rc3 and server B has an RHEL6 2.6.32
> kernel.
>
> Before:
> http://pastebin.com/raw.php?i=1gVraWVc
>
> After:
> http://pastebin.com/raw.php?i=NSh8Y29s
You have a lot of packet losses
add "tc -s -d qdisc" , "ifconfig -a " and "ethtool -S ethX" outputs for
both servers
^ permalink raw reply
* Warning! Your mailbox is almost full.
From: Publishers Clearing House @ 2012-06-20 7:16 UTC (permalink / raw)
Congratulations, your email address has won ($1,000,000.00USD) in the
on going Publishers Clearing House loto draw that was held today, pls
fill details bellow for claims. Email us back: onlinepch_213@ozledim.net
Name in full:.. Address:... Sex:.. Occupation:.. Present Country:..
!!!Once Again Congratulations!!!
Yours Sincerely,
Mrs.Reyna Cruz
ONLINE CO-ORDINATOR.
----------------------------------------------------------------
This message was sent using IMP, the Internet Messaging Program.
^ permalink raw reply
* [PATCH] netxen: Error return off by one in 'netxen_nic_set_pauseparam()'.
From: santosh nayak @ 2012-06-20 7:27 UTC (permalink / raw)
To: sony.chacko, rajesh.borundia; +Cc: netdev, kernel-janitors, Santosh Nayak
From: Santosh Nayak <santoshprasadnayak@gmail.com>
There are 'NETXEN_NIU_MAX_GBE_PORTS' GBE ports. Port indexing starts
from zero.
Hence we should also return error for "port == NETXEN_NIU_MAX_GBE_PORTS"
Signed-off-by: Santosh Nayak <santoshprasadnayak@gmail.com>
---
Destination tree "linux-next"
.../ethernet/qlogic/netxen/netxen_nic_ethtool.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index 3973040..d4f179f 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -489,7 +489,7 @@ netxen_nic_get_pauseparam(struct net_device *dev,
int port = adapter->physical_port;
if (adapter->ahw.port_type == NETXEN_NIC_GBE) {
- if ((port < 0) || (port > NETXEN_NIU_MAX_GBE_PORTS))
+ if ((port < 0) || (port >= NETXEN_NIU_MAX_GBE_PORTS))
return;
/* get flow control settings */
val = NXRD32(adapter, NETXEN_NIU_GB_MAC_CONFIG_0(port));
@@ -534,7 +534,7 @@ netxen_nic_set_pauseparam(struct net_device *dev,
int port = adapter->physical_port;
/* read mode */
if (adapter->ahw.port_type == NETXEN_NIC_GBE) {
- if ((port < 0) || (port > NETXEN_NIU_MAX_GBE_PORTS))
+ if ((port < 0) || (port >= NETXEN_NIU_MAX_GBE_PORTS))
return -EIO;
/* set flow control */
val = NXRD32(adapter, NETXEN_NIU_GB_MAC_CONFIG_0(port));
--
1.7.4.4
^ permalink raw reply related
* Warning! Your mailbox is almost full.
From: Publishers Clearing House @ 2012-06-20 7:29 UTC (permalink / raw)
Congratulations, your email address has won ($1,000,000.00USD) in the
on going Publishers Clearing House loto draw that was held today, pls
fill details bellow for claims. Email us back: onlinepch_213@ozledim.net
Name in full:.. Address:... Sex:.. Occupation:.. Present Country:..
!!!Once Again Congratulations!!!
Yours Sincerely,
Mrs.Reyna Cruz
ONLINE CO-ORDINATOR.
----------------------------------------------------------------
This message was sent using IMP, the Internet Messaging Program.
^ permalink raw reply
* Re: [PATCH 02.5] mm: sl[au]b: first remove PFMEMALLOC flag then SLAB flag
From: Mel Gorman @ 2012-06-20 7:38 UTC (permalink / raw)
To: Sebastian Andrzej Siewior
Cc: Andrew Morton, Linux-MM, Linux-Netdev, LKML, David Miller,
Neil Brown, Peter Zijlstra, Mike Christie, Eric B Munson
In-Reply-To: <20120615155432.GA5498@breakpoint.cc>
On Fri, Jun 15, 2012 at 05:54:32PM +0200, Sebastian Andrzej Siewior wrote:
> From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
>
> If we first remove the SLAB flag followed by the PFMEMALLOC flag then the
> removal of the latter will trigger the VM_BUG_ON() as it can be seen in
> | kernel BUG at include/linux/page-flags.h:474!
> | invalid opcode: 0000 [#1] PREEMPT SMP
> | Call Trace:
> | [<c10e2d77>] slab_destroy+0x27/0x70
> | [<c10e3285>] drain_freelist+0x55/0x90
> | [<c10e344e>] __cache_shrink+0x6e/0x90
> | [<c14e3211>] ? acpi_sleep_init+0xcf/0xcf
> | [<c10e349d>] kmem_cache_shrink+0x2d/0x40
>
> because the SLAB flag is gone. This patch simply changes the order.
>
> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Grr, yes of course. Thanks very much. I've folded this into patch 2 and
preserved credit.
--
Mel Gorman
SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: [PATCH -v1 1/3] usbnet: clear OPEN flag in failure path
From: Oliver Neukum @ 2012-06-20 7:44 UTC (permalink / raw)
To: Ming Lei; +Cc: David S. Miller, Greg Kroah-Hartman, netdev, linux-usb
In-Reply-To: <1340176553-32225-2-git-send-email-ming.lei@canonical.com>
Am Mittwoch, 20. Juni 2012, 09:15:51 schrieb Ming Lei:
> Without clearing OPEN flag in failure path, runtime or system resume
> may submit interrupt/rx URB and start tx queue mistakenly on a
> interface in DOWN state.
>
> Signed-off-by: Ming Lei <ming.lei@canonical.com>
Acked-by: Oliver Neukum <oneukum@suse.de>
^ permalink raw reply
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