* [PATCH v4 02/10] net/macb: memory barriers cleanup
From: Nicolas Ferre @ 2012-10-31 16:04 UTC (permalink / raw)
To: netdev, davem, havard
Cc: bhutchings, linux-arm-kernel, plagnioj, patrice.vilchez,
linux-kernel, manabian, David.Laight, Nicolas Ferre
In-Reply-To: <cover.1351690694.git.nicolas.ferre@atmel.com>
From: Havard Skinnemoen <havard@skinnemoen.net>
Remove a couple of unneeded barriers and document the remaining ones.
Signed-off-by: Havard Skinnemoen <havard@skinnemoen.net>
[nicolas.ferre@atmel.com: split patch in topics]
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Tested-by: Joachim Eastwood <manabian@gmail.com>
---
drivers/net/ethernet/cadence/macb.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 0931cb7..e7f554d 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -373,7 +373,9 @@ static void macb_tx(struct macb *bp)
BUG_ON(skb == NULL);
+ /* Make hw descriptor updates visible to CPU */
rmb();
+
bufstat = bp->tx_ring[tail].ctrl;
if (!(bufstat & MACB_BIT(TX_USED)))
@@ -416,7 +418,10 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
if (frag == last_frag)
break;
}
+
+ /* Make descriptor updates visible to hardware */
wmb();
+
return 1;
}
@@ -437,12 +442,14 @@ static int macb_rx_frame(struct macb *bp, unsigned int first_frag,
frag_len);
offset += RX_BUFFER_SIZE;
bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
- wmb();
if (frag == last_frag)
break;
}
+ /* Make descriptor updates visible to hardware */
+ wmb();
+
skb->protocol = eth_type_trans(skb, bp->dev);
bp->stats.rx_packets++;
@@ -462,6 +469,8 @@ static void discard_partial_frame(struct macb *bp, unsigned int begin,
for (frag = begin; frag != end; frag = NEXT_RX(frag))
bp->rx_ring[frag].addr &= ~MACB_BIT(RX_USED);
+
+ /* Make descriptor updates visible to hardware */
wmb();
/*
@@ -480,7 +489,9 @@ static int macb_rx(struct macb *bp, int budget)
for (; budget > 0; tail = NEXT_RX(tail)) {
u32 addr, ctrl;
+ /* Make hw descriptor updates visible to CPU */
rmb();
+
addr = bp->rx_ring[tail].addr;
ctrl = bp->rx_ring[tail].ctrl;
@@ -675,6 +686,8 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
bp->tx_ring[entry].addr = mapping;
bp->tx_ring[entry].ctrl = ctrl;
+
+ /* Make newly initialized descriptor visible to hardware */
wmb();
entry = NEXT_TX(entry);
@@ -783,9 +796,6 @@ static void macb_init_rings(struct macb *bp)
static void macb_reset_hw(struct macb *bp)
{
- /* Make sure we have the write buffer for ourselves */
- wmb();
-
/*
* Disable RX and TX (XXX: Should we halt the transmission
* more gracefully?)
--
1.8.0
^ permalink raw reply related
* [PATCH v4 01/10] net/macb: Add support for Gigabit Ethernet mode
From: Nicolas Ferre @ 2012-10-31 16:04 UTC (permalink / raw)
To: netdev, davem, havard
Cc: bhutchings, linux-arm-kernel, plagnioj, patrice.vilchez,
linux-kernel, manabian, David.Laight, Nicolas Ferre
In-Reply-To: <cover.1351690694.git.nicolas.ferre@atmel.com>
From: Patrice Vilchez <patrice.vilchez@atmel.com>
Add Gigabit Ethernet mode to GEM cadence IP and enable RGMII connection.
Signed-off-by: Patrice Vilchez <patrice.vilchez@atmel.com>
Signed-off-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Tested-by: Joachim Eastwood <manabian@gmail.com>
---
drivers/net/ethernet/cadence/macb.c | 15 ++++++++++++---
drivers/net/ethernet/cadence/macb.h | 4 ++++
2 files changed, 16 insertions(+), 3 deletions(-)
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index 6a4f499..0931cb7 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -152,13 +152,17 @@ static void macb_handle_link_change(struct net_device *dev)
reg = macb_readl(bp, NCFGR);
reg &= ~(MACB_BIT(SPD) | MACB_BIT(FD));
+ if (macb_is_gem(bp))
+ reg &= ~GEM_BIT(GBE);
if (phydev->duplex)
reg |= MACB_BIT(FD);
if (phydev->speed == SPEED_100)
reg |= MACB_BIT(SPD);
+ if (phydev->speed == SPEED_1000)
+ reg |= GEM_BIT(GBE);
- macb_writel(bp, NCFGR, reg);
+ macb_or_gem_writel(bp, NCFGR, reg);
bp->speed = phydev->speed;
bp->duplex = phydev->duplex;
@@ -216,7 +220,10 @@ static int macb_mii_probe(struct net_device *dev)
}
/* mask with MAC supported features */
- phydev->supported &= PHY_BASIC_FEATURES;
+ if (macb_is_gem(bp))
+ phydev->supported &= PHY_GBIT_FEATURES;
+ else
+ phydev->supported &= PHY_BASIC_FEATURES;
phydev->advertising = phydev->supported;
@@ -1388,7 +1395,9 @@ static int __init macb_probe(struct platform_device *pdev)
bp->phy_interface = err;
}
- if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
+ if (bp->phy_interface == PHY_INTERFACE_MODE_RGMII)
+ macb_or_gem_writel(bp, USRIO, GEM_BIT(RGMII));
+ else if (bp->phy_interface == PHY_INTERFACE_MODE_RMII)
#if defined(CONFIG_ARCH_AT91)
macb_or_gem_writel(bp, USRIO, (MACB_BIT(RMII) |
MACB_BIT(CLKEN)));
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index a362751..33a050f 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -149,6 +149,8 @@
#define MACB_IRXFCS_SIZE 1
/* GEM specific NCFGR bitfields. */
+#define GEM_GBE_OFFSET 10
+#define GEM_GBE_SIZE 1
#define GEM_CLK_OFFSET 18
#define GEM_CLK_SIZE 3
#define GEM_DBW_OFFSET 21
@@ -252,6 +254,8 @@
/* Bitfields in USRIO (AT91) */
#define MACB_RMII_OFFSET 0
#define MACB_RMII_SIZE 1
+#define GEM_RGMII_OFFSET 0 /* GEM gigabit mode */
+#define GEM_RGMII_SIZE 1
#define MACB_CLKEN_OFFSET 1
#define MACB_CLKEN_SIZE 1
--
1.8.0
^ permalink raw reply related
* [PATCH v4 00/10] net/macb: driver enhancement concerning GEM support, ring logic and cleanup
From: Nicolas Ferre @ 2012-10-31 16:04 UTC (permalink / raw)
To: netdev, davem, havard
Cc: bhutchings, linux-arm-kernel, plagnioj, patrice.vilchez,
linux-kernel, manabian, David.Laight, Nicolas Ferre
This is an enhancement work that began several years ago. I try to catchup with
some performance improvement that has been implemented then by Havard.
The ring index logic and the TX error path modification are the biggest changes
but some cleanup/debugging have been added along the way.
The GEM revision will benefit from the Gigabit support.
Newer pinctrl infrastructure support is added but it is optional.
The series has been tested on several Atmel AT91 SoC with the two MACB/GEM
flavors.
v4: - remove unneeded device tree header includes
- modified the computation of available entries in ring buffer
v3: - rebased on net-next to take into account current effor to merge
at91_ether with macb drivers
- add additional patch to use the new pinctrl infrastructure
v2: - modify the tx error handling: now uses a workqueue
- information provided by ethtool -i were not accurate: removed
Havard Skinnemoen (4):
net/macb: memory barriers cleanup
net/macb: change debugging messages
net/macb: clean up ring buffer logic
net/macb: Offset first RX buffer by two bytes
Jean-Christophe PLAGNIOL-VILLARD (1):
net/macb: add pinctrl consumer support
Nicolas Ferre (4):
net/macb: remove macb_get_drvinfo()
net/macb: tx status is more than 8 bits now
net/macb: ethtool interface: add register dump feature
net/macb: better manage tx errors
Patrice Vilchez (1):
net/macb: Add support for Gigabit Ethernet mode
drivers/net/ethernet/cadence/at91_ether.c | 6 +-
drivers/net/ethernet/cadence/macb.c | 448 +++++++++++++++++++++---------
drivers/net/ethernet/cadence/macb.h | 30 +-
3 files changed, 337 insertions(+), 147 deletions(-)
--
1.8.0
^ permalink raw reply
* [PATCH net-next V3] htb: improved accuracy at high rates
From: Vimalkumar @ 2012-10-31 16:04 UTC (permalink / raw)
To: davem, Jamal Hadi Salim, Eric Dumazet, netdev; +Cc: Vimalkumar
Current HTB (and TBF) uses rate table computed by the "tc"
userspace program, which has the following issue:
The rate table has 256 entries to map packet lengths
to token (time units). With TSO sized packets, the
256 entry granularity leads to loss/gain of rate,
making the token bucket inaccurate.
Thus, instead of relying on rate table, this patch
explicitly computes the time and accounts for packet
transmission times with nanosecond granularity.
This greatly improves accuracy of HTB with a wide
range of packet sizes.
Example:
tc qdisc add dev $dev root handle 1: \
htb default 1
tc class add dev $dev classid 1:1 parent 1: \
rate 5Gbit mtu 64k
Here is an example of inaccuracy:
$ iperf -c host -t 10 -i 1
With old htb:
eth4: 34.76 Mb/s In 5827.98 Mb/s Out - 65836.0 p/s In 481273.0 p/s Out
[SUM] 9.0-10.0 sec 669 MBytes 5.61 Gbits/sec
[SUM] 0.0-10.0 sec 6.50 GBytes 5.58 Gbits/sec
With new htb:
eth4: 28.36 Mb/s In 5208.06 Mb/s Out - 53704.0 p/s In 430076.0 p/s Out
[SUM] 9.0-10.0 sec 594 MBytes 4.98 Gbits/sec
[SUM] 0.0-10.0 sec 5.80 GBytes 4.98 Gbits/sec
The bits per second on the wire is still 5200Mb/s with new HTB
because qdisc accounts for packet length using skb->len, which
is smaller than total bytes on the wire if GSO is used. But
that is for another patch regardless of how time is accounted.
Many thanks to Eric Dumazet for review and feedback.
Signed-off-by: Vimalkumar <j.vimal@gmail.com>
---
net/sched/sch_htb.c | 128 ++++++++++++++++++++++++++++++++++++---------------
1 files changed, 90 insertions(+), 38 deletions(-)
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 9d75b77..32a8097 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -71,6 +71,12 @@ enum htb_cmode {
HTB_CAN_SEND /* class can send */
};
+struct htb_rate_cfg {
+ u64 rate_bps;
+ u32 mult;
+ u32 shift;
+};
+
/* interior & leaf nodes; props specific to leaves are marked L: */
struct htb_class {
struct Qdisc_class_common common;
@@ -118,11 +124,11 @@ struct htb_class {
int filter_cnt;
/* token bucket parameters */
- struct qdisc_rate_table *rate; /* rate table of the class itself */
- struct qdisc_rate_table *ceil; /* ceiling rate (limits borrows too) */
- long buffer, cbuffer; /* token bucket depth/rate */
+ struct htb_rate_cfg rate;
+ struct htb_rate_cfg ceil;
+ s64 buffer, cbuffer; /* token bucket depth/rate */
psched_tdiff_t mbuffer; /* max wait time */
- long tokens, ctokens; /* current number of tokens */
+ s64 tokens, ctokens; /* current number of tokens */
psched_time_t t_c; /* checkpoint time */
};
@@ -162,6 +168,45 @@ struct htb_sched {
struct work_struct work;
};
+static u64 l2t_ns(struct htb_rate_cfg *r, unsigned int len)
+{
+ return ((u64)len * r->mult) >> r->shift;
+}
+
+static void htb_precompute_ratedata(struct htb_rate_cfg *r)
+{
+ u64 factor;
+ u64 mult;
+ int shift;
+
+ r->shift = 0;
+ r->mult = 1;
+ /*
+ * Calibrate mult, shift so that token counting is accurate
+ * for smallest packet size (64 bytes). Token (time in ns) is
+ * computed as (bytes * 8) * NSEC_PER_SEC / rate_bps. It will
+ * work as long as the smallest packet transfer time can be
+ * accurately represented in nanosec.
+ */
+ if (r->rate_bps > 0) {
+ /*
+ * Higher shift gives better accuracy. Find the largest
+ * shift such that mult fits in 32 bits.
+ */
+ for (shift = 0; shift < 16; shift++) {
+ r->shift = shift;
+ factor = 8LLU * NSEC_PER_SEC * (1 << r->shift);
+ mult = div64_u64(factor, r->rate_bps);
+ if (mult > UINT_MAX)
+ break;
+ }
+
+ r->shift = shift - 1;
+ factor = 8LLU * NSEC_PER_SEC * (1 << r->shift);
+ r->mult = div64_u64(factor, r->rate_bps);
+ }
+}
+
/* find class in global hash table using given handle */
static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch)
{
@@ -273,7 +318,7 @@ static void htb_add_to_id_tree(struct rb_root *root,
* already in the queue.
*/
static void htb_add_to_wait_tree(struct htb_sched *q,
- struct htb_class *cl, long delay)
+ struct htb_class *cl, s64 delay)
{
struct rb_node **p = &q->wait_pq[cl->level].rb_node, *parent = NULL;
@@ -441,14 +486,14 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl)
htb_remove_class_from_row(q, cl, mask);
}
-static inline long htb_lowater(const struct htb_class *cl)
+static inline s64 htb_lowater(const struct htb_class *cl)
{
if (htb_hysteresis)
return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0;
else
return 0;
}
-static inline long htb_hiwater(const struct htb_class *cl)
+static inline s64 htb_hiwater(const struct htb_class *cl)
{
if (htb_hysteresis)
return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0;
@@ -469,9 +514,9 @@ static inline long htb_hiwater(const struct htb_class *cl)
* mode transitions per time unit. The speed gain is about 1/6.
*/
static inline enum htb_cmode
-htb_class_mode(struct htb_class *cl, long *diff)
+htb_class_mode(struct htb_class *cl, s64 *diff)
{
- long toks;
+ s64 toks;
if ((toks = (cl->ctokens + *diff)) < htb_lowater(cl)) {
*diff = -toks;
@@ -495,7 +540,7 @@ htb_class_mode(struct htb_class *cl, long *diff)
* to mode other than HTB_CAN_SEND (see htb_add_to_wait_tree).
*/
static void
-htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, long *diff)
+htb_change_class_mode(struct htb_sched *q, struct htb_class *cl, s64 *diff)
{
enum htb_cmode new_mode = htb_class_mode(cl, diff);
@@ -581,26 +626,26 @@ static int htb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
return NET_XMIT_SUCCESS;
}
-static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, long diff)
+static inline void htb_accnt_tokens(struct htb_class *cl, int bytes, s64 diff)
{
- long toks = diff + cl->tokens;
+ s64 toks = diff + cl->tokens;
if (toks > cl->buffer)
toks = cl->buffer;
- toks -= (long) qdisc_l2t(cl->rate, bytes);
+ toks -= (s64) l2t_ns(&cl->rate, bytes);
if (toks <= -cl->mbuffer)
toks = 1 - cl->mbuffer;
cl->tokens = toks;
}
-static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, long diff)
+static inline void htb_accnt_ctokens(struct htb_class *cl, int bytes, s64 diff)
{
- long toks = diff + cl->ctokens;
+ s64 toks = diff + cl->ctokens;
if (toks > cl->cbuffer)
toks = cl->cbuffer;
- toks -= (long) qdisc_l2t(cl->ceil, bytes);
+ toks -= (s64) l2t_ns(&cl->ceil, bytes);
if (toks <= -cl->mbuffer)
toks = 1 - cl->mbuffer;
@@ -623,10 +668,10 @@ static void htb_charge_class(struct htb_sched *q, struct htb_class *cl,
{
int bytes = qdisc_pkt_len(skb);
enum htb_cmode old_mode;
- long diff;
+ s64 diff;
while (cl) {
- diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
+ diff = min_t(s64, q->now - cl->t_c, cl->mbuffer);
if (cl->level >= level) {
if (cl->level == level)
cl->xstats.lends++;
@@ -673,7 +718,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level,
unsigned long stop_at = start + 2;
while (time_before(jiffies, stop_at)) {
struct htb_class *cl;
- long diff;
+ s64 diff;
struct rb_node *p = rb_first(&q->wait_pq[level]);
if (!p)
@@ -684,7 +729,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level,
return cl->pq_key;
htb_safe_rb_erase(p, q->wait_pq + level);
- diff = psched_tdiff_bounded(q->now, cl->t_c, cl->mbuffer);
+ diff = min_t(s64, q->now - cl->t_c, cl->mbuffer);
htb_change_class_mode(q, cl, &diff);
if (cl->cmode != HTB_CAN_SEND)
htb_add_to_wait_tree(q, cl, diff);
@@ -834,7 +879,6 @@ next:
} while (cl != start);
if (likely(skb != NULL)) {
- bstats_update(&cl->bstats, skb);
cl->un.leaf.deficit[level] -= qdisc_pkt_len(skb);
if (cl->un.leaf.deficit[level] < 0) {
cl->un.leaf.deficit[level] += cl->quantum;
@@ -871,10 +915,10 @@ ok:
if (!sch->q.qlen)
goto fin;
- q->now = psched_get_time();
+ q->now = ktime_to_ns(ktime_get());
start_at = jiffies;
- next_event = q->now + 5 * PSCHED_TICKS_PER_SEC;
+ next_event = q->now + 5 * NSEC_PER_SEC;
for (level = 0; level < TC_HTB_MAXDEPTH; level++) {
/* common case optimization - skip event handler quickly */
@@ -884,7 +928,7 @@ ok:
if (q->now >= q->near_ev_cache[level]) {
event = htb_do_events(q, level, start_at);
if (!event)
- event = q->now + PSCHED_TICKS_PER_SEC;
+ event = q->now + NSEC_PER_SEC;
q->near_ev_cache[level] = event;
} else
event = q->near_ev_cache[level];
@@ -903,10 +947,17 @@ ok:
}
}
sch->qstats.overlimits++;
- if (likely(next_event > q->now))
- qdisc_watchdog_schedule(&q->watchdog, next_event);
- else
+ if (likely(next_event > q->now)) {
+ if (!test_bit(__QDISC_STATE_DEACTIVATED,
+ &qdisc_root_sleeping(q->watchdog.qdisc)->state)) {
+ ktime_t time = ns_to_ktime(next_event);
+ qdisc_throttled(q->watchdog.qdisc);
+ hrtimer_start(&q->watchdog.timer, time,
+ HRTIMER_MODE_ABS);
+ }
+ } else {
schedule_work(&q->work);
+ }
fin:
return skb;
}
@@ -1082,9 +1133,9 @@ static int htb_dump_class(struct Qdisc *sch, unsigned long arg,
memset(&opt, 0, sizeof(opt));
- opt.rate = cl->rate->rate;
+ opt.rate.rate = cl->rate.rate_bps >> 3;
opt.buffer = cl->buffer;
- opt.ceil = cl->ceil->rate;
+ opt.ceil.rate = cl->ceil.rate_bps >> 3;
opt.cbuffer = cl->cbuffer;
opt.quantum = cl->quantum;
opt.prio = cl->prio;
@@ -1203,9 +1254,6 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl)
qdisc_destroy(cl->un.leaf.q);
}
gen_kill_estimator(&cl->bstats, &cl->rate_est);
- qdisc_put_rtab(cl->rate);
- qdisc_put_rtab(cl->ceil);
-
tcf_destroy_chain(&cl->filter_list);
kfree(cl);
}
@@ -1460,12 +1508,16 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
cl->buffer = hopt->buffer;
cl->cbuffer = hopt->cbuffer;
- if (cl->rate)
- qdisc_put_rtab(cl->rate);
- cl->rate = rtab;
- if (cl->ceil)
- qdisc_put_rtab(cl->ceil);
- cl->ceil = ctab;
+
+ cl->rate.rate_bps = (u64)rtab->rate.rate << 3;
+ cl->ceil.rate_bps = (u64)ctab->rate.rate << 3;
+
+ htb_precompute_ratedata(&cl->rate);
+ htb_precompute_ratedata(&cl->ceil);
+
+ cl->buffer = hopt->buffer << PSCHED_SHIFT;
+ cl->cbuffer = hopt->buffer << PSCHED_SHIFT;
+
sch_tree_unlock(sch);
qdisc_class_hash_grow(sch, &q->clhash);
--
1.7.5.3
^ permalink raw reply related
* [PATCH/Resend] [trivial] net: sctp: Fix typo in net/sctp
From: Masanari Iida @ 2012-10-31 15:48 UTC (permalink / raw)
To: trivial, linux-kernel, netdev, davem; +Cc: Masanari Iida
Correct spelling typo in net/sctp/socket.c
Signed-off-by: Masanari Iida <standby24x7@gmail.com>
Acked-by: Vlad Yasevich <vyasevich@gmail.com>
---
net/sctp/socket.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 59d16ea..a60d1f8 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -974,7 +974,7 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk,
void *addr_buf;
struct sctp_af *af;
- SCTP_DEBUG_PRINTK("sctp_setsocktopt_bindx: sk %p addrs %p"
+ SCTP_DEBUG_PRINTK("sctp_setsockopt_bindx: sk %p addrs %p"
" addrs_size %d opt %d\n", sk, addrs, addrs_size, op);
if (unlikely(addrs_size <= 0))
--
1.8.0.rc3.16.g8ead1bf
^ permalink raw reply related
* [PATCH net 6/7] bnx2x: Fix no link on 577xx 10G-baseT
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev
Cc: Yaniv Rosner, Barak Witkowski, Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
From: Yaniv Rosner <yanivr@broadcom.com>
Since the Warpcore supports various link types, need to set only the correct
supported modes for XFI which is the serdes interface for the 10G-baseT PHY.
Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 5 +++++
1 files changed, 5 insertions(+), 0 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 679d45e..6dd0dd0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -11528,6 +11528,11 @@ static int bnx2x_populate_int_phy(struct bnx2x *bp, u32 shmem_base, u8 port,
phy->media_type = ETH_PHY_BASE_T;
break;
case PORT_HW_CFG_NET_SERDES_IF_XFI:
+ phy->supported &= (SUPPORTED_1000baseT_Full |
+ SUPPORTED_10000baseT_Full |
+ SUPPORTED_FIBRE |
+ SUPPORTED_Pause |
+ SUPPORTED_Asym_Pause);
phy->media_type = ETH_PHY_XFP_FIBER;
break;
case PORT_HW_CFG_NET_SERDES_IF_SFI:
--
1.7.7.2
^ permalink raw reply related
* [PATCH net 7/7] bnx2x: Disable FCoE for 57840 since not yet supported by FW
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev; +Cc: Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 10 +++++++++-
1 files changed, 9 insertions(+), 1 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index d5648fc..f23e8c0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -11902,7 +11902,15 @@ static int __devinit bnx2x_init_one(struct pci_dev *pdev,
/* disable FCOE L2 queue for E1x */
if (CHIP_IS_E1x(bp))
bp->flags |= NO_FCOE_FLAG;
-
+ /* disable FCOE for 57840 device, until FW supports it */
+ switch (ent->driver_data) {
+ case BCM57840_O:
+ case BCM57840_4_10:
+ case BCM57840_2_20:
+ case BCM57840_MFO:
+ case BCM57840_MF:
+ bp->flags |= NO_FCOE_FLAG;
+ }
#endif
--
1.7.7.2
^ permalink raw reply related
* [PATCH net 5/7] bnx2x: Fix unrecognized SFP+ module after driver is loaded
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev
Cc: Yaniv Rosner, Barak Witkowski, Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
From: Yaniv Rosner <yanivr@broadcom.com>
When SFP+ module is plugged in after driver is already loaded, it may not be
recognized, so set SFP module recognition time up to 300ms, without resetting
the module power in the middle.
Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 22 +++++++++++++++-------
1 files changed, 15 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 308ba42..679d45e 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -7634,7 +7634,7 @@ static void bnx2x_warpcore_power_module(struct link_params *params,
static int bnx2x_warpcore_read_sfp_module_eeprom(struct bnx2x_phy *phy,
struct link_params *params,
u16 addr, u8 byte_cnt,
- u8 *o_buf)
+ u8 *o_buf, u8 is_init)
{
int rc = 0;
u8 i, j = 0, cnt = 0;
@@ -7651,10 +7651,10 @@ static int bnx2x_warpcore_read_sfp_module_eeprom(struct bnx2x_phy *phy,
/* 4 byte aligned address */
addr32 = addr & (~0x3);
do {
- if (cnt == I2C_WA_PWR_ITER) {
+ if ((!is_init) && (cnt == I2C_WA_PWR_ITER)) {
bnx2x_warpcore_power_module(params, phy, 0);
/* Note that 100us are not enough here */
- usleep_range(1000,1000);
+ usleep_range(1000, 2000);
bnx2x_warpcore_power_module(params, phy, 1);
}
rc = bnx2x_bsc_read(params, phy, 0xa0, addr32, 0, byte_cnt,
@@ -7774,7 +7774,7 @@ int bnx2x_read_sfp_module_eeprom(struct bnx2x_phy *phy,
break;
case PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT:
rc = bnx2x_warpcore_read_sfp_module_eeprom(phy, params, addr,
- byte_cnt, o_buf);
+ byte_cnt, o_buf, 0);
break;
}
return rc;
@@ -7978,6 +7978,7 @@ static int bnx2x_wait_for_sfp_module_initialized(struct bnx2x_phy *phy,
{
u8 val;
+ int rc;
struct bnx2x *bp = params->bp;
u16 timeout;
/* Initialization time after hot-plug may take up to 300ms for
@@ -7985,8 +7986,14 @@ static int bnx2x_wait_for_sfp_module_initialized(struct bnx2x_phy *phy,
*/
for (timeout = 0; timeout < 60; timeout++) {
- if (bnx2x_read_sfp_module_eeprom(phy, params, 1, 1, &val)
- == 0) {
+ if (phy->type == PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT)
+ rc = bnx2x_warpcore_read_sfp_module_eeprom(phy,
+ params, 1,
+ 1, &val, 1);
+ else
+ rc = bnx2x_read_sfp_module_eeprom(phy, params, 1, 1,
+ &val);
+ if (rc == 0) {
DP(NETIF_MSG_LINK,
"SFP+ module initialization took %d ms\n",
timeout * 5);
@@ -7994,7 +8001,8 @@ static int bnx2x_wait_for_sfp_module_initialized(struct bnx2x_phy *phy,
}
usleep_range(5000, 10000);
}
- return -EINVAL;
+ rc = bnx2x_read_sfp_module_eeprom(phy, params, 1, 1, &val);
+ return rc;
}
static void bnx2x_8727_power_module(struct bnx2x *bp,
--
1.7.7.2
^ permalink raw reply related
* [PATCH net 3/7] bnx2x: Restore global registers back to default.
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev
Cc: Yaniv Rosner, Barak Witkowski, Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
From: Yaniv Rosner <yanivr@broadcom.com>
Several KR registers were not set correctly back to default after
loopback test, so set those global registers over the global WC lane (zero)
rather than the current lane.
Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 78 ++++++++++++++++------
1 files changed, 56 insertions(+), 22 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index f2436ea..5e8f7b7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3558,13 +3558,11 @@ static void bnx2x_warpcore_set_lpi_passthrough(struct bnx2x_phy *phy,
static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
struct link_params *params,
struct link_vars *vars) {
- u16 val16 = 0, lane, i, cl72_ctrl;
+ u16 lane, i, cl72_ctrl, an_adv = 0;
+ u16 ucode_ver;
struct bnx2x *bp = params->bp;
static struct bnx2x_reg_set reg_set[] = {
{MDIO_WC_DEVAD, MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X2, 0x7},
- {MDIO_AN_DEVAD, MDIO_WC_REG_PAR_DET_10G_CTRL, 0},
- {MDIO_WC_DEVAD, MDIO_WC_REG_XGXSBLK1_LANECTRL0, 0xff},
- {MDIO_WC_DEVAD, MDIO_WC_REG_XGXSBLK1_LANECTRL1, 0x5555},
{MDIO_PMA_DEVAD, MDIO_WC_REG_IEEE0BLK_AUTONEGNP, 0x0},
{MDIO_WC_DEVAD, MDIO_WC_REG_RX66_CONTROL, 0x7415},
{MDIO_WC_DEVAD, MDIO_WC_REG_SERDESDIGITAL_MISC2, 0x6190},
@@ -3589,7 +3587,7 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
(phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_1G)) ||
(vars->line_speed == SPEED_1000)) {
u32 addr = MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X2;
- val16 |= (1<<5);
+ an_adv |= (1<<5);
/* Enable CL37 1G Parallel Detect */
bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD, addr, 0x1);
@@ -3599,11 +3597,14 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
(phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_10G)) ||
(vars->line_speed == SPEED_10000)) {
/* Check adding advertisement for 10G KR */
- val16 |= (1<<7);
+ an_adv |= (1<<7);
/* Enable 10G Parallel Detect */
+ CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
+ MDIO_AER_BLOCK_AER_REG, 0);
+
bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
MDIO_WC_REG_PAR_DET_10G_CTRL, 1);
-
+ bnx2x_set_aer_mmd(params, phy);
DP(NETIF_MSG_LINK, "Advertize 10G\n");
}
@@ -3623,7 +3624,7 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
/* Advertised speeds */
bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
- MDIO_WC_REG_AN_IEEE1BLK_AN_ADVERTISEMENT1, val16);
+ MDIO_WC_REG_AN_IEEE1BLK_AN_ADVERTISEMENT1, an_adv);
/* Advertised and set FEC (Forward Error Correction) */
bnx2x_cl45_write(bp, phy, MDIO_AN_DEVAD,
@@ -3647,9 +3648,10 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
/* Set KR Autoneg Work-Around flag for Warpcore version older than D108
*/
bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
- MDIO_WC_REG_UC_INFO_B1_VERSION, &val16);
- if (val16 < 0xd108) {
- DP(NETIF_MSG_LINK, "Enable AN KR work-around\n");
+ MDIO_WC_REG_UC_INFO_B1_VERSION, &ucode_ver);
+ if (ucode_ver < 0xd108) {
+ DP(NETIF_MSG_LINK, "Enable AN KR work-around. WC ver:0x%x\n",
+ ucode_ver);
vars->rx_tx_asic_rst = MAX_KR_LINK_RETRY;
}
bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
@@ -3670,21 +3672,16 @@ static void bnx2x_warpcore_set_10G_KR(struct bnx2x_phy *phy,
struct link_vars *vars)
{
struct bnx2x *bp = params->bp;
- u16 i;
+ u16 val16, i, lane;
static struct bnx2x_reg_set reg_set[] = {
/* Disable Autoneg */
{MDIO_WC_DEVAD, MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X2, 0x7},
- {MDIO_AN_DEVAD, MDIO_WC_REG_PAR_DET_10G_CTRL, 0},
{MDIO_WC_DEVAD, MDIO_WC_REG_CL72_USERB0_CL72_MISC1_CONTROL,
0x3f00},
{MDIO_AN_DEVAD, MDIO_WC_REG_AN_IEEE1BLK_AN_ADVERTISEMENT1, 0},
{MDIO_AN_DEVAD, MDIO_WC_REG_IEEE0BLK_MIICNTL, 0x0},
{MDIO_WC_DEVAD, MDIO_WC_REG_DIGITAL3_UP1, 0x1},
{MDIO_WC_DEVAD, MDIO_WC_REG_DIGITAL5_MISC7, 0xa},
- /* Disable CL36 PCS Tx */
- {MDIO_WC_DEVAD, MDIO_WC_REG_XGXSBLK1_LANECTRL0, 0x0},
- /* Double Wide Single Data Rate @ pll rate */
- {MDIO_WC_DEVAD, MDIO_WC_REG_XGXSBLK1_LANECTRL1, 0xFFFF},
/* Leave cl72 training enable, needed for KR */
{MDIO_PMA_DEVAD,
MDIO_WC_REG_PMD_IEEE9BLK_TENGBASE_KR_PMD_CONTROL_REGISTER_150,
@@ -3695,11 +3692,24 @@ static void bnx2x_warpcore_set_10G_KR(struct bnx2x_phy *phy,
bnx2x_cl45_write(bp, phy, reg_set[i].devad, reg_set[i].reg,
reg_set[i].val);
- /* Leave CL72 enabled */
- bnx2x_cl45_read_or_write(bp, phy, MDIO_WC_DEVAD,
- MDIO_WC_REG_CL72_USERB0_CL72_MISC1_CONTROL,
- 0x3800);
+ lane = bnx2x_get_warpcore_lane(phy, params);
+ /* Global registers */
+ CL22_WR_OVER_CL45(bp, phy, MDIO_REG_BANK_AER_BLOCK,
+ MDIO_AER_BLOCK_AER_REG, 0);
+ /* Disable CL36 PCS Tx */
+ bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL0, &val16);
+ val16 &= ~(0x0011 << lane);
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL0, val16);
+ bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL1, &val16);
+ val16 |= (0x0303 << (lane << 1));
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL1, val16);
+ /* Restore AER */
+ bnx2x_set_aer_mmd(params, phy);
/* Set speed via PMA/PMD register */
bnx2x_cl45_write(bp, phy, MDIO_PMA_DEVAD,
MDIO_WC_REG_IEEE0BLK_MIICNTL, 0x2040);
@@ -4322,7 +4332,7 @@ static void bnx2x_warpcore_link_reset(struct bnx2x_phy *phy,
struct link_params *params)
{
struct bnx2x *bp = params->bp;
- u16 val16;
+ u16 val16, lane;
bnx2x_sfp_e3_set_transmitter(params, phy, 0);
bnx2x_set_mdio_clk(bp, params->chip_id, params->port);
bnx2x_set_aer_mmd(params, phy);
@@ -4359,6 +4369,30 @@ static void bnx2x_warpcore_link_reset(struct bnx2x_phy *phy,
MDIO_WC_REG_XGXSBLK1_LANECTRL2,
val16 & 0xff00);
+ lane = bnx2x_get_warpcore_lane(phy, params);
+ /* Disable CL36 PCS Tx */
+ bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL0, &val16);
+ val16 |= (0x11 << lane);
+ if (phy->flags & FLAGS_WC_DUAL_MODE)
+ val16 |= (0x22 << lane);
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL0, val16);
+
+ bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL1, &val16);
+ val16 &= ~(0x0303 << (lane << 1));
+ val16 |= (0x0101 << (lane << 1));
+ if (phy->flags & FLAGS_WC_DUAL_MODE) {
+ val16 &= ~(0x0c0c << (lane << 1));
+ val16 |= (0x0404 << (lane << 1));
+ }
+
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_XGXSBLK1_LANECTRL1, val16);
+ /* Restore AER */
+ bnx2x_set_aer_mmd(params, phy);
+
}
static void bnx2x_set_warpcore_loopback(struct bnx2x_phy *phy,
--
1.7.7.2
^ permalink raw reply related
* [PATCH net 2/7] bnx2x: Fix link down in 57712 following LFA
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev
Cc: Yaniv Rosner, Barak Witkowski, Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
From: Yaniv Rosner <yanivr@broadcom.com>
In case of link flap avoidance between PXE boot and bnx2x, set the appropriate
PHY DEVAD even if LFA kicks in.
Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 23 +++++++++++++++++----
1 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 290e12a..f2436ea 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3295,6 +3295,21 @@ static void bnx2x_serdes_deassert(struct bnx2x *bp, u8 port)
DEFAULT_PHY_DEV_ADDR);
}
+static void bnx2x_xgxs_specific_func(struct bnx2x_phy *phy,
+ struct link_params *params,
+ u32 action)
+{
+ struct bnx2x *bp = params->bp;
+ switch (action) {
+ case PHY_INIT:
+ /* Set correct devad */
+ REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_ST + params->port*0x18, 0);
+ REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_DEVAD + params->port*0x18,
+ phy->def_md_devad);
+ break;
+ }
+}
+
static void bnx2x_xgxs_deassert(struct link_params *params)
{
struct bnx2x *bp = params->bp;
@@ -3309,10 +3324,8 @@ static void bnx2x_xgxs_deassert(struct link_params *params)
REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_3_CLEAR, val);
udelay(500);
REG_WR(bp, GRCBASE_MISC + MISC_REGISTERS_RESET_REG_3_SET, val);
-
- REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_ST + port*0x18, 0);
- REG_WR(bp, NIG_REG_XGXS0_CTRL_MD_DEVAD + port*0x18,
- params->phy[INT_PHY].def_md_devad);
+ bnx2x_xgxs_specific_func(¶ms->phy[INT_PHY], params,
+ PHY_INIT);
}
static void bnx2x_calc_ieee_aneg_adv(struct bnx2x_phy *phy,
@@ -10999,7 +11012,7 @@ static struct bnx2x_phy phy_xgxs = {
.format_fw_ver = (format_fw_ver_t)NULL,
.hw_reset = (hw_reset_t)NULL,
.set_link_led = (set_link_led_t)NULL,
- .phy_specific_func = (phy_specific_func_t)NULL
+ .phy_specific_func = (phy_specific_func_t)bnx2x_xgxs_specific_func
};
static struct bnx2x_phy phy_warpcore = {
.type = PORT_HW_CFG_XGXS_EXT_PHY_TYPE_DIRECT,
--
1.7.7.2
^ permalink raw reply related
* [PATCH net 0/7] bnx2x: fixes
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev; +Cc: Dmitry Kravkov
Hi Dave
Please consider applying the series of fixes to net.
Dmitry Kravkov (1):
bnx2x: disable FCoE for 57840 since not yet supported by FW
Yaniv Rosner (6):
bnx2x: Fix 57810 1G-KR link against certain switches.
bnx2x: Fix link down in 57712 following LFA
bnx2x: Restore global registers back to default.
bnx2x: Fix potential incorrect link speed provision
bnx2x: Fix unrecognized SFP+ module after driver is loaded
bnx2x: Fix no link on 577xx 10G-baseT
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 158 +++++++++++++++------
drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 10 ++-
2 files changed, 122 insertions(+), 46 deletions(-)
Thanks,
Dmitry
^ permalink raw reply
* [PATCH net 4/7] bnx2x: Fix potential incorrect link speed provision
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev
Cc: Yaniv Rosner, Barak Witkowski, Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
From: Yaniv Rosner <yanivr@broadcom.com>
Fix possible incorrect link speed provision following rapid link speed change.
Clear link speed mask after each link change, and not only after link down.
Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 22 ++++++++++++----------
1 files changed, 12 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 5e8f7b7..308ba42 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -137,7 +137,16 @@
#define LINK_20GTFD LINK_STATUS_SPEED_AND_DUPLEX_20GTFD
#define LINK_20GXFD LINK_STATUS_SPEED_AND_DUPLEX_20GXFD
-
+#define LINK_UPDATE_MASK \
+ (LINK_STATUS_SPEED_AND_DUPLEX_MASK | \
+ LINK_STATUS_LINK_UP | \
+ LINK_STATUS_PHYSICAL_LINK_FLAG | \
+ LINK_STATUS_AUTO_NEGOTIATE_COMPLETE | \
+ LINK_STATUS_RX_FLOW_CONTROL_FLAG_MASK | \
+ LINK_STATUS_TX_FLOW_CONTROL_FLAG_MASK | \
+ LINK_STATUS_PARALLEL_DETECTION_FLAG_MASK | \
+ LINK_STATUS_LINK_PARTNER_SYMMETRIC_PAUSE | \
+ LINK_STATUS_LINK_PARTNER_ASYMMETRIC_PAUSE)
#define SFP_EEPROM_CON_TYPE_ADDR 0x2
#define SFP_EEPROM_CON_TYPE_VAL_LC 0x7
@@ -6349,15 +6358,7 @@ static int bnx2x_update_link_down(struct link_params *params,
vars->mac_type = MAC_TYPE_NONE;
/* Update shared memory */
- vars->link_status &= ~(LINK_STATUS_SPEED_AND_DUPLEX_MASK |
- LINK_STATUS_LINK_UP |
- LINK_STATUS_PHYSICAL_LINK_FLAG |
- LINK_STATUS_AUTO_NEGOTIATE_COMPLETE |
- LINK_STATUS_RX_FLOW_CONTROL_FLAG_MASK |
- LINK_STATUS_TX_FLOW_CONTROL_FLAG_MASK |
- LINK_STATUS_PARALLEL_DETECTION_FLAG_MASK |
- LINK_STATUS_LINK_PARTNER_SYMMETRIC_PAUSE |
- LINK_STATUS_LINK_PARTNER_ASYMMETRIC_PAUSE);
+ vars->link_status &= ~LINK_UPDATE_MASK;
vars->line_speed = 0;
bnx2x_update_mng(params, vars->link_status);
@@ -6505,6 +6506,7 @@ int bnx2x_link_update(struct link_params *params, struct link_vars *vars)
u16 ext_phy_line_speed = 0, prev_line_speed = vars->line_speed;
u8 active_external_phy = INT_PHY;
vars->phy_flags &= ~PHY_HALF_OPEN_CONN_FLAG;
+ vars->link_status &= ~LINK_UPDATE_MASK;
for (phy_index = INT_PHY; phy_index < params->num_phys;
phy_index++) {
phy_vars[phy_index].flow_ctrl = 0;
--
1.7.7.2
^ permalink raw reply related
* [PATCH net 1/7] bnx2x: Fix 57810 1G-KR link against certain switches.
From: Dmitry Kravkov @ 2012-10-31 15:46 UTC (permalink / raw)
To: ariele, eilong, davem, netdev
Cc: Yaniv Rosner, Barak Witkowski, Dmitry Kravkov
In-Reply-To: <1351698418-10005-1-git-send-email-dmitry@broadcom.com>
From: Yaniv Rosner <yanivr@broadcom.com>
Fix 1G KR link by restoring CL72 misc control register to default value rather
than 0.
Signed-off-by: Yaniv Rosner <yanivr@broadcom.com>
Signed-off-by: Barak Witkowski <barak@broadcom.com>
Signed-off-by: Dmitry Kravkov <dmitry@broadcom.com>
---
drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c | 10 ++++++++--
1 files changed, 8 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index e2e45ee..290e12a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -3545,12 +3545,11 @@ static void bnx2x_warpcore_set_lpi_passthrough(struct bnx2x_phy *phy,
static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
struct link_params *params,
struct link_vars *vars) {
- u16 val16 = 0, lane, i;
+ u16 val16 = 0, lane, i, cl72_ctrl;
struct bnx2x *bp = params->bp;
static struct bnx2x_reg_set reg_set[] = {
{MDIO_WC_DEVAD, MDIO_WC_REG_SERDESDIGITAL_CONTROL1000X2, 0x7},
{MDIO_AN_DEVAD, MDIO_WC_REG_PAR_DET_10G_CTRL, 0},
- {MDIO_WC_DEVAD, MDIO_WC_REG_CL72_USERB0_CL72_MISC1_CONTROL, 0},
{MDIO_WC_DEVAD, MDIO_WC_REG_XGXSBLK1_LANECTRL0, 0xff},
{MDIO_WC_DEVAD, MDIO_WC_REG_XGXSBLK1_LANECTRL1, 0x5555},
{MDIO_PMA_DEVAD, MDIO_WC_REG_IEEE0BLK_AUTONEGNP, 0x0},
@@ -3565,6 +3564,13 @@ static void bnx2x_warpcore_enable_AN_KR(struct bnx2x_phy *phy,
bnx2x_cl45_write(bp, phy, reg_set[i].devad, reg_set[i].reg,
reg_set[i].val);
+ bnx2x_cl45_read(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_CL72_USERB0_CL72_MISC1_CONTROL, &cl72_ctrl);
+ cl72_ctrl &= 0xf8ff;
+ cl72_ctrl |= 0x3800;
+ bnx2x_cl45_write(bp, phy, MDIO_WC_DEVAD,
+ MDIO_WC_REG_CL72_USERB0_CL72_MISC1_CONTROL, cl72_ctrl);
+
/* Check adding advertisement for 1G KX */
if (((vars->line_speed == SPEED_AUTO_NEG) &&
(phy->speed_cap_mask & PORT_HW_CFG_SPEED_CAPABILITY_D0_1G)) ||
--
1.7.7.2
^ permalink raw reply related
* Re: [RFC] back on nf_tables (plus compatibility layer)
From: Pablo Neira Ayuso @ 2012-10-31 15:42 UTC (permalink / raw)
To: Jan Engelhardt
Cc: Netfilter Development Mailing list,
Linux Networking Developer Mailing List
In-Reply-To: <alpine.LNX.2.01.1210311449570.29232@nerf07.vanv.qr>
On Wed, Oct 31, 2012 at 02:50:27PM +0100, Jan Engelhardt wrote:
>
> On Friday 2012-10-26 13:04, Pablo Neira Ayuso wrote:
> >>
> >> Meanwhile, I am on xtables2 that actually reproduces the set of
> >> _really important_ features that currently are in the setsockopt
> >> iptables, like atomic table replace and atomic dump.
> >>
> >> I have updated to the newest tree, and the first set is
> >> available in the git repository at:
> >> git://git.inai.de/linux xt2-20121025
> >
> >If you think this feature is important, checkout nf_tables and think
> >how to integrate this prototype code that provides atomic table
> >replacement to it.
>
> I'd rather tinker with xt2.
You're are free spend your time on your pet project, but I warn you:
it will *extremely hard* to justify its inclusion into mainline.
As said, I don't think it makes sense to add two firewall
engines/interfaces for the same thing. And the compatibility layer
provides an utility with similar syntax and semantics to iptables.
^ permalink raw reply
* Re: [PATCH v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Alan Stern @ 2012-10-31 15:41 UTC (permalink / raw)
To: Ming Lei
Cc: Oliver Neukum, linux-kernel, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <Pine.LNX.4.44L0.1210311117310.1954-100000@iolanthe.rowland.org>
On Wed, 31 Oct 2012, Alan Stern wrote:
> On Wed, 31 Oct 2012, Ming Lei wrote:
>
> > The below idea may help the problem which 'memalloc_noio' flag isn't set during
> > usb_reset_device().
> >
> > - for usb mass storage device, call pm_runtime_set_memalloc_noio(true)
> > inside usb_stor_probe2() and uas_probe(), and call
> > pm_runtime_set_memalloc_noio(false) inside uas_disconnect()
> > and usb_stor_disconnect().
>
> Why would you want to do that? The probe and disconnect routines
> usually -- but not always -- run in the khubd thread. Surely you don't
> want to prevent khubd from using GFP_KERNEL?
>
> And what if probe runs in khubd but disconnect runs in a different
> thread?
Sorry, I misread your message. You are setting the device's flag, not
the thread's flag.
This still doesn't help in this case where CONFIG_PM_RUNTIME is
disabled. I think it will be simpler to set the noio flag during every
device reset.
Alan Stern
--
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 v3 2/6] PM / Runtime: introduce pm_runtime_set[get]_memalloc_noio()
From: Alan Stern @ 2012-10-31 15:20 UTC (permalink / raw)
To: Ming Lei
Cc: Oliver Neukum, linux-kernel, Minchan Kim, Greg Kroah-Hartman,
Rafael J. Wysocki, Jens Axboe, David S. Miller, Andrew Morton,
netdev, linux-usb, linux-pm, linux-mm
In-Reply-To: <CACVXFVNxucCVLS-=EQkmVop3LQMkeXW7RbZq4yfkiq_MUGndvg@mail.gmail.com>
On Wed, 31 Oct 2012, Ming Lei wrote:
> The below idea may help the problem which 'memalloc_noio' flag isn't set during
> usb_reset_device().
>
> - for usb mass storage device, call pm_runtime_set_memalloc_noio(true)
> inside usb_stor_probe2() and uas_probe(), and call
> pm_runtime_set_memalloc_noio(false) inside uas_disconnect()
> and usb_stor_disconnect().
Why would you want to do that? The probe and disconnect routines
usually -- but not always -- run in the khubd thread. Surely you don't
want to prevent khubd from using GFP_KERNEL?
And what if probe runs in khubd but disconnect runs in a different
thread?
Alan Stern
--
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 4/4] arm/dts: am33xx: Add CPSW and MDIO module nodes for AM33XX
From: Benoit Cousson @ 2012-10-31 15:17 UTC (permalink / raw)
To: Vaibhav Hiremath
Cc: netdev, paul, linux-arm-kernel, linux-omap, Mugunthan V N,
Richard Cochran
In-Reply-To: <1351498881-32482-6-git-send-email-hvaibhav@ti.com>
Hi,
On 10/29/2012 09:21 AM, Vaibhav Hiremath wrote:
> From: Mugunthan V N <mugunthanvnm@ti.com>
>
> Add CPSW and MDIO related device tree data for AM33XX.
> Also enable them into board/evm dts files by providing
> respective phy-id.
Is there any bindings documentation for that device?
> Signed-off-by: Mugunthan V N <mugunthanvnm@ti.com>
> Signed-off-by: Vaibhav Hiremath <hvaibhav@ti.com>
> Cc: Richard Cochran <richardcochran@gmail.com>
> Cc: Benoit Cousson <b-cousson@ti.com>
> ---
> arch/arm/boot/dts/am335x-bone.dts | 8 ++++++
> arch/arm/boot/dts/am335x-evm.dts | 8 ++++++
> arch/arm/boot/dts/am33xx.dtsi | 50 +++++++++++++++++++++++++++++++++++++
> 3 files changed, 66 insertions(+), 0 deletions(-)
>
> diff --git a/arch/arm/boot/dts/am335x-bone.dts b/arch/arm/boot/dts/am335x-bone.dts
> index c634f87..e233cfa 100644
> --- a/arch/arm/boot/dts/am335x-bone.dts
> +++ b/arch/arm/boot/dts/am335x-bone.dts
> @@ -78,3 +78,11 @@
> };
> };
> };
> +
> +&cpsw_emac0 {
> + phy_id = "4a101000.mdio:00";
Why are you using that kind of interface? You seem to want a reference
to a device.
Cannot you have something less hard coded like:
phy_id = <&davinci_mdio>, <0>;
> +};
> +
> +&cpsw_emac1 {
> + phy_id = "4a101000.mdio:01";
> +};
> diff --git a/arch/arm/boot/dts/am335x-evm.dts b/arch/arm/boot/dts/am335x-evm.dts
> index 185d632..415c3b3 100644
> --- a/arch/arm/boot/dts/am335x-evm.dts
> +++ b/arch/arm/boot/dts/am335x-evm.dts
> @@ -118,3 +118,11 @@
> };
> };
> };
> +
> +&cpsw_emac0 {
> + phy_id = "4a101000.mdio:00";
> +};
> +
> +&cpsw_emac1 {
> + phy_id = "4a101000.mdio:01";
> +};
> diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
> index bb31bff..f6bea04 100644
> --- a/arch/arm/boot/dts/am33xx.dtsi
> +++ b/arch/arm/boot/dts/am33xx.dtsi
> @@ -210,5 +210,55 @@
> interrupt-parent = <&intc>;
> interrupts = <91>;
> };
> +
> + mac: ethernet@4A100000 {
hexa data should be in lower case.
> + compatible = "ti,cpsw";
> + ti,hwmods = "cpgmac0";
> + cpdma_channels = <8>;
> + host_port_no = <0>;
> + cpdma_reg_ofs = <0x800>;
> + cpdma_sram_ofs = <0xa00>;
> + ale_reg_ofs = <0xd00>;
> + ale_entries = <1024>;
> + host_port_reg_ofs = <0x108>;
> + hw_stats_reg_ofs = <0x900>;
> + bd_ram_ofs = <0x2000>;
> + bd_ram_size = <0x2000>;
> + no_bd_ram = <0>;
> + rx_descs = <64>;
> + mac_control = <0x20>;
Do you have to store all these data in the DTS? Cannot it be in the driver?
Do you expect to have several instance of the same IP with different
parameters here?
> + slaves = <2>;
> + reg = <0x4a100000 0x800
> + 0x4a101200 0x100
> + 0x4a101000 0x100>;
Please align the address.
> + #address-cells = <1>;
> + #size-cells = <1>;
> + interrupt-parent = <&intc>;
> + /* c0_rx_thresh_pend c0_rx_pend c0_tx_pend c0_misc_pend*/
Please use a standard multi-line comment instead of trying to put
everything in one line.
> + interrupts = <40 41 42 43>;
> + ranges;
You should add blank line here for readability.
> + cpsw_emac0: slave@0 {
Mmm, you are using some address later and here some relative number,
that does not looks very consistent.
> + slave_reg_ofs = <0x208>;
Is it an offset from 4a100000? Cannot you use the address for the slave
name?
Something like that: cpsw_emac0: slave@4a100208
> + sliver_reg_ofs = <0xd80>;
> + /* Filled in by U-Boot */
> + mac-address = [ 00 00 00 00 00 00 ];
> + };
You should add blank line here for readability.
> + cpsw_emac1: slave@1 {
> + slave_reg_ofs = <0x308>;
> + sliver_reg_ofs = <0xdc0>;
> + /* Filled in by U-Boot */
> + mac-address = [ 00 00 00 00 00 00 ];
> + };
> +
> + davinci_mdio: mdio@4a101000 {
> + compatible = "ti,davinci_mdio";
> + #address-cells = <1>;
> + #size-cells = <0>;
> + ti,hwmods = "davinci_mdio";
> + bus_freq = <1000000>;
> + reg = <0x4a101000 0x100>;
> + };
> +
Stray change.
Regards,
Benoit
^ permalink raw reply
* [PATCH] bonding: fix off-by-one error
From: Nikolay Aleksandrov @ 2012-10-31 14:42 UTC (permalink / raw)
To: netdev; +Cc: andy, fubar
Fix off-by-one error because IFNAMSIZ == 16 and when this
code gets executed we stick a NULL byte where we should not.
How to reproduce:
with CONFIG_CC_STACKPROTECTOR=y (otherwise it may pass by silently)
modprobe bonding; echo 1 > /sys/class/net/bond0/bonding/mode;
echo "AAAAAAAAAAAAAAAA" > /sys/class/net/bond0/bonding/primary;
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
---
drivers/net/bonding/bond_sysfs.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index dc15d24..238d9b3 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -1060,7 +1060,7 @@ static ssize_t bonding_store_primary(struct device *d,
goto out;
}
- sscanf(buf, "%16s", ifname); /* IFNAMSIZ */
+ sscanf(buf, "%15s", ifname); /* IFNAMSIZ */
/* check to see if we are clearing primary */
if (!strlen(ifname) || buf[0] == '\n') {
--
1.7.11.4
^ permalink raw reply related
* Re: [PATCH net-next 1/8] bridge: bridge port parameters over netlink
From: John Fastabend @ 2012-10-31 14:01 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: davem, netdev
In-Reply-To: <20121030005835.289407930@vyatta.com>
On 10/29/2012 5:57 PM, Stephen Hemminger wrote:
> Expose bridge port parameters over netlink. By switching
> from a single byet to a nested message, this can be used for
> other bridge parameters.
>
> Although, this changes IFLA_PROTINFO attribute from one byte to a full nested
> set of attributes; it is safe for applications because the
> old message used IFLA_PROTINFO and new one uses
> IFLA_PROTINFO | NLA_F_NESTED.
>
> The code still accepts to old format requests, and therefore stays
> compatiable with user mode RSTP daemon. Since the type field
> for nested and unnested attributes are different, and the old
> code in libnetlink doesn't do the mask, it is also safe to use
> with old versions of bridge monitor command.
>
> Note: although mode is only a boolean, treating it as a
> full byte since in the future someone will probably want to add more
> values (like macvlan has).
>
> Signed-off-by: Stephen Hemminger<shemminger@vyatta.com>
>
> ---
Stephen,
Did you see these two patches
http://patchwork.ozlabs.org/patch/193900/
http://patchwork.ozlabs.org/patch/193901/
here I added nested bridge attributes to IFLA_AF_SPEC and pass them down
to the drivers as needed. Should we merge these two sets so that we have
only a single nested set of bridge attributes? Either in IFLA_AF_SPEC or
IFLA_PROTINFO.
The attributes in this patch are port specifics and the one in the
patches listed above are bridge specific so in this sense perhaps
its OK to keep them separate. I'm not sure it matters much either
way but thought I would mention it.
Also I suspect these two series will have conflicts but I haven't tried
yet.
Thanks,
John
^ permalink raw reply
* Re: [RFC] back on nf_tables (plus compatibility layer)
From: Jan Engelhardt @ 2012-10-31 13:50 UTC (permalink / raw)
To: Pablo Neira Ayuso
Cc: Netfilter Development Mailing list,
Linux Networking Developer Mailing List
In-Reply-To: <20121026110419.GA16629@1984>
On Friday 2012-10-26 13:04, Pablo Neira Ayuso wrote:
>>
>> Meanwhile, I am on xtables2 that actually reproduces the set of
>> _really important_ features that currently are in the setsockopt
>> iptables, like atomic table replace and atomic dump.
>>
>> I have updated to the newest tree, and the first set is
>> available in the git repository at:
>> git://git.inai.de/linux xt2-20121025
>
>If you think this feature is important, checkout nf_tables and think
>how to integrate this prototype code that provides atomic table
>replacement to it.
I'd rather tinker with xt2.
^ permalink raw reply
* Re: [uclinux-dist-devel] [PATCH RFC net-next 2/4] bfin_mac: replace sys time stamps with raw ones instead.
From: Richard Cochran @ 2012-10-31 12:46 UTC (permalink / raw)
To: Bob Liu
Cc: netdev, Miroslav Lichvar, John Ronciak, John Stultz, Jeff Kirsher,
device-drivers-devel, Jacob Keller, uclinux-dist-devel,
Patrick Ohly, David Miller
In-Reply-To: <CAA_GA1cQojiaJat8gGmp3XYZVGOtKi2xoFS08hsYTGssdbWcRg@mail.gmail.com>
On Wed, Oct 31, 2012 at 05:00:55PM +0800, Bob Liu wrote:
> On Wed, Oct 31, 2012 at 4:36 PM, Richard Cochran
> <richardcochran@gmail.com> wrote:
> > On Wed, Oct 31, 2012 at 02:29:23PM +0800, Bob Liu wrote:
> >
> >> Any guide how to use ptp4l to sync system time between two machines
> >> over ethernet?
> >
> > You can run ptp4l on two machines like this
> >
> > ptp4l -i eth0 -q -v # master
> > ptp4l -i eth0 -q -v -s # slave
> >
>
> Thank you.
> But i'm still failed to sync system time.
>
> On mater:
> -------------------------------
> root:/> date
> Wed Dec 20 01:31:02 UTC 2006
> root:/>
> root:/> ptp4l -i eth0 -q -v
> ptp4l[33.520]: selected /dev/ptp0 as PTP clock
> ptp4l[33.520]: m
> ptp4l[33.520]: driver rejected most general HWTSTAMP filter
> ptp4l[33.520]: port 1: INITIALIZING to LISTENING on INITIALIZE
> ptp4l[33.524]: port 0: INITIALIZING to LISTENING on INITIALIZE
> ptp4l[39.524]: port 1: LISTENING to MASTER on ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES
> .....
>
> -----------------------------
> On slave:
> root:~> date
> Fri Jan 2 13:16:07 UTC 1970
>
> root:~> ptp4l -i eth0 -q -v -s
> ptp4l[39.624]: selected /dev/ptp0 as PTP clock
> ptp4l[39.628]: m
> ptp4l[39.628]: driver rejected most general HWTSTAMP filter
> ptp4l[39.628]: port 1: INITIALIZING to LISTENING on INITIALIZE
> ptp4l[39.632]: port 0: INITIALIZING to LISTENING on INITIALIZE
> ptp4l[39.664]: port 1: new foreign master 00e022.fffe.fe8529-1
> ptp4l[43.672]: selected best master clock 00e022.fffe.fe8529
> ptp4l[43.676]: port 1: LISTENING to UNCALIBRATED on RS_SLAVE
> ptp4l[44.688]: master offset -7968957480 s0 adj +0 path delay 8120
> ptp4l[45.692]: master offset -7968953124 s0 adj +0 path delay 9076
> ptp4l[46.696]: master offset -7968947340 s0 adj +0 path delay 8860
> ptp4l[47.700]: master offset -7968941884 s1 adj +0 path delay 8860
> ptp4l[48.704]: master offset 4564 s2 adj +4564 path delay 8860
> ptp4l[48.704]: port 1: UNCALIBRATED to SLAVE on MASTER_CLOCK_SELECTED
> ptp4l[49.708]: master offset 5154 s2 adj +6523 path delay 9086
> ptp4l[50.712]: master offset 3686 s2 adj +6601 path delay 9322
> ptp4l[51.716]: master offset 2582 s2 adj +6603 path delay 9322
> ptp4l[52.720]: master offset 1362 s2 adj +6158 path delay 9438
> ptp4l[53.724]: master offset 658 s2 adj +5862 path delay 9438
> ptp4l[54.728]: master offset -85 s2 adj +5317 path delay 9685
> ptp4l[55.732]: master offset -113 s2 adj +5263 path delay 9873
> ptp4l[56.748]: master offset 86 s2 adj +5428 path delay 9930
> ptp4l[57.740]: master offset 166 s2 adj +5534 path delay 9930
> ptp4l[58.744]: master offset -247 s2 adj +5171 path delay 10151
> ptp4l[59.748]: master offset -39 s2 adj +5305 path delay 10151
> ptp4l[60.752]: master offset 217 s2 adj +5549 path delay 10151
> ptp4l[61.756]: master offset 256 s2 adj +5653 path delay 10128
> .....
This looks perfect. Did you fixup the wrong time stamp shift?
>
> root:~> date
> Fri Jan 2 13:16:45 UTC 1970
> root:~>
>
> The system time in slave didn't change.
That is correct. Using RAW time stamping and PHC, the time in the PHC
changes, but not the system time. The system time may be slaved to
the PHC time using the phc2sys program.
Anyhow, it looks like this is working fine to me.
Thanks,
Richard
^ permalink raw reply
* [net PATCH V2] net: fix divide by zero in tcp algorithm illinois
From: Jesper Dangaard Brouer @ 2012-10-31 12:45 UTC (permalink / raw)
To: David S. Miller
Cc: Jesper Dangaard Brouer, netdev, Petr Matousek, Stephen Hemminger,
Eric Dumazet
Reading TCP stats when using TCP Illinois congestion control algorithm
can cause a divide by zero kernel oops.
The division by zero occur in tcp_illinois_info() at:
do_div(t, ca->cnt_rtt);
where ca->cnt_rtt can become zero (when rtt_reset is called)
Steps to Reproduce:
1. Register tcp_illinois:
# sysctl -w net.ipv4.tcp_congestion_control=illinois
2. Monitor internal TCP information via command "ss -i"
# watch -d ss -i
3. Establish new TCP conn to machine
Either it fails at the initial conn, or else it needs to wait
for a loss or a reset.
This is only related to reading stats. The function avg_delay() also
performs the same divide, but is guarded with a (ca->cnt_rtt > 0) at its
calling point in update_params(). Thus, simply fix tcp_illinois_info().
Function tcp_illinois_info() / get_info() is called without
socket lock. Thus, eliminate any race condition on ca->cnt_rtt
by using a local stack variable. Simply reuse info.tcpv_rttcnt,
as its already set to ca->cnt_rtt.
Function avg_delay() is not affected by this race condition, as
its called with the socket lock.
Cc: Petr Matousek <pmatouse@redhat.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
V2:
Address Eric Dumazets input:
- Save 2 bytes of stack, by using info.tcpv_rttcnt.
- Help compiler, and define "u64 t" inside if() lexical scope.
net/ipv4/tcp_illinois.c | 8 +++++---
1 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 813b43a..834857f 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -313,11 +313,13 @@ static void tcp_illinois_info(struct sock *sk, u32 ext,
.tcpv_rttcnt = ca->cnt_rtt,
.tcpv_minrtt = ca->base_rtt,
};
- u64 t = ca->sum_rtt;
- do_div(t, ca->cnt_rtt);
- info.tcpv_rtt = t;
+ if (info.tcpv_rttcnt > 0) {
+ u64 t = ca->sum_rtt;
+ do_div(t, info.tcpv_rttcnt);
+ info.tcpv_rtt = t;
+ }
nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
}
}
^ permalink raw reply related
* Re: [PATCH v2 2/3] pppoatm: fix race condition with destroying of vcc
From: David Woodhouse @ 2012-10-31 11:52 UTC (permalink / raw)
To: Krzysztof Mazur; +Cc: davem, netdev, linux-kernel
In-Reply-To: <20121031113021.GA24093@shrek.podlesie.net>
[-- Attachment #1: Type: text/plain, Size: 1386 bytes --]
On Wed, 2012-10-31 at 12:30 +0100, Krzysztof Mazur wrote:
> Yes, original patch had also the same problem with sock_owned_by_user(),
> so I just incorrectly assumed that we can do "goto nospace" after
> pppoatm_may_send(), but ppooatm_may_send() must be the last test.
>
> So I just moved all other tests earlier and and now pppoatm_may_send()
> is also protected by ATM socket lock as you suggested earlier.
I don't think that's sufficient. When we return zero from
pppoatm_send(), the generic PPP code considers the channel to be
blocked, and it won't send any more data to it, ever, until we call
ppp_output_wakeup(). Which we do from a tasklet, triggered in
pppoatm_pop() *iff* the BLOCKED flag is set.
So we play silly buggers in pppoatm_may_send() to ensure that *if* we're
going to return zero, we make damn sure the BLOCKED flag is set and that
pppoatm_pop() is going to see that it's set. There are extensive
comments in pppoatm_pop() and pppoatm_may_send() which try to explain
this. It works because there's *always* going to be packet in flight if
we say that the sk_wmem is full, so of course there's *always* going to
be a later call to pppoatm_pop() to wake things up.
However, if you're going to return zero from pppoatm_send() when
sock_owned_by_user() is true, what guarantees that ppp_output_wakeup()
will ever be called?
--
dwmw2
[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 6171 bytes --]
^ permalink raw reply
* Re: [PATCH v2 2/3] pppoatm: fix race condition with destroying of vcc
From: Krzysztof Mazur @ 2012-10-31 11:30 UTC (permalink / raw)
To: David Woodhouse; +Cc: davem, netdev, linux-kernel
In-Reply-To: <1351678578.8774.8.camel@shinybook.infradead.org>
On Wed, Oct 31, 2012 at 10:16:18AM +0000, David Woodhouse wrote:
>
> Does this break the pvcc->blocked handling that coordinates with
> pppoatm_pop()?
>
> If we have one packet in flight, so pppoatm_may_send() permits a new one
> to be queued... but they're *large* packets to sk_wmem_alloc doesn't
> permit it. Immediately after the check, pppoatm_pop() runs and leaves
> the queue empty. We return zero, blocking the queue??? which never gets
> woken because we didn't set the BLOCKED flag and thus the tasklet never
> runs.
>
> In fact, I think we need the BLOCKED handling for the
> sock_owned_by_user() case too? When the VCC is actually closed, I
> suppose that's not recoverable and we don't care about waking the queue
> anyway? But any time we end up returning zero from pppoatm_send(), we
> *need* to ensure that a wakeup will happen in future unless the socket
> is actually dead.
>
Yes, original patch had also the same problem with sock_owned_by_user(),
so I just incorrectly assumed that we can do "goto nospace" after
pppoatm_may_send(), but ppooatm_may_send() must be the last test.
So I just moved all other tests earlier and and now pppoatm_may_send()
is also protected by ATM socket lock as you suggested earlier.
Krzysiek
-- >8 --
Subject: [PATCH] pppoatm: fix race condition with destroying of vcc
The pppoatm_send() calls vcc->send() and now also checks for
some vcc flags that indicate destroyed vcc without proper locking.
The vcc_sendmsg() uses lock_sock(sk). This lock is used by
vcc_release(), so vcc_destroy_socket() will not be called between
check and during ->send(). The vcc_release_async() sets ATM_VF_CLOSE,
but it should be safe to call ->send() after it, because
vcc->dev->ops->close() is not called.
The pppoatm_send() is called with BH disabled, so bh_lock_sock()
should be used instead of lock_sock().
Signed-off-by: Krzysztof Mazur <krzysiek@podlesie.net>
---
net/atm/pppoatm.c | 27 +++++++++++++++++++--------
1 file changed, 19 insertions(+), 8 deletions(-)
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index 0dcb5dc..eb76bd3 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -270,11 +270,22 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
{
struct pppoatm_vcc *pvcc = chan_to_pvcc(chan);
struct atm_vcc *vcc;
+ int ret;
ATM_SKB(skb)->vcc = pvcc->atmvcc;
pr_debug("(skb=0x%p, vcc=0x%p)\n", skb, pvcc->atmvcc);
if (skb->data[0] == '\0' && (pvcc->flags & SC_COMP_PROT))
(void) skb_pull(skb, 1);
+
+ vcc = ATM_SKB(skb)->vcc;
+ bh_lock_sock(sk_atm(vcc));
+ if (sock_owned_by_user(sk_atm(vcc)))
+ goto nospace;
+ if (test_bit(ATM_VF_RELEASED, &vcc->flags)
+ || test_bit(ATM_VF_CLOSE, &vcc->flags)
+ || !test_bit(ATM_VF_READY, &vcc->flags))
+ goto nospace;
+
switch (pvcc->encaps) { /* LLC encapsulation needed */
case e_llc:
if (skb_headroom(skb) < LLC_LEN) {
@@ -287,8 +298,10 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
}
consume_skb(skb);
skb = n;
- if (skb == NULL)
+ if (skb == NULL) {
+ bh_unlock_sock(sk_atm(vcc));
return DROP_PACKET;
+ }
} else if (!pppoatm_may_send(pvcc, skb->truesize))
goto nospace;
memcpy(skb_push(skb, LLC_LEN), pppllc, LLC_LEN);
@@ -298,24 +311,22 @@ static int pppoatm_send(struct ppp_channel *chan, struct sk_buff *skb)
goto nospace;
break;
case e_autodetect:
+ bh_unlock_sock(sk_atm(vcc));
pr_debug("Trying to send without setting encaps!\n");
kfree_skb(skb);
return 1;
}
- vcc = ATM_SKB(skb)->vcc;
- if (test_bit(ATM_VF_RELEASED, &vcc->flags)
- || test_bit(ATM_VF_CLOSE, &vcc->flags)
- || !test_bit(ATM_VF_READY, &vcc->flags))
- goto nospace;
-
atomic_add(skb->truesize, &sk_atm(ATM_SKB(skb)->vcc)->sk_wmem_alloc);
ATM_SKB(skb)->atm_options = ATM_SKB(skb)->vcc->atm_options;
pr_debug("atm_skb(%p)->vcc(%p)->dev(%p)\n",
skb, ATM_SKB(skb)->vcc, ATM_SKB(skb)->vcc->dev);
- return ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
+ ret = ATM_SKB(skb)->vcc->send(ATM_SKB(skb)->vcc, skb)
? DROP_PACKET : 1;
+ bh_unlock_sock(sk_atm(vcc));
+ return ret;
nospace:
+ bh_unlock_sock(sk_atm(vcc));
/*
* We don't have space to send this SKB now, but we might have
* already applied SC_COMP_PROT compression, so may need to undo
--
1.8.0.172.g62af90c
^ permalink raw reply related
* [PATCH 4/9] net: openvswitch: use this_cpu_ptr per-cpu helper
From: Shan Wei @ 2012-10-31 11:22 UTC (permalink / raw)
To: jesse-l0M0P4e3n4LQT0dZR+AlfA, dev-yBygre7rU0TnMu66kgdUjQ, NetDev,
Kernel-Maillist, David Miller,
cl-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b
From: Shan Wei <davidshan-1Nz4purKYjRBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: Shan Wei <davidshan-1Nz4purKYjRBDgjK7y7TUQ@public.gmane.org>
---
net/openvswitch/datapath.c | 4 ++--
net/openvswitch/vport.c | 5 ++---
2 files changed, 4 insertions(+), 5 deletions(-)
diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 4c4b62c..77d16a5 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -208,7 +208,7 @@ void ovs_dp_process_received_packet(struct vport *p, struct sk_buff *skb)
int error;
int key_len;
- stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+ stats = this_cpu_ptr(dp->stats_percpu);
/* Extract flow from 'skb' into 'key'. */
error = ovs_flow_extract(skb, p->port_no, &key, &key_len);
@@ -282,7 +282,7 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb,
return 0;
err:
- stats = per_cpu_ptr(dp->stats_percpu, smp_processor_id());
+ stats = this_cpu_ptr(dp->stats_percpu);
u64_stats_update_begin(&stats->sync);
stats->n_lost++;
diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c
index 03779e8..70af0be 100644
--- a/net/openvswitch/vport.c
+++ b/net/openvswitch/vport.c
@@ -333,8 +333,7 @@ void ovs_vport_receive(struct vport *vport, struct sk_buff *skb)
{
struct vport_percpu_stats *stats;
- stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id());
-
+ stats = this_cpu_ptr(vport->percpu_stats);
u64_stats_update_begin(&stats->sync);
stats->rx_packets++;
stats->rx_bytes += skb->len;
@@ -359,7 +358,7 @@ int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
if (likely(sent)) {
struct vport_percpu_stats *stats;
- stats = per_cpu_ptr(vport->percpu_stats, smp_processor_id());
+ stats = this_cpu_ptr(vport->percpu_stats);
u64_stats_update_begin(&stats->sync);
stats->tx_packets++;
--
1.7.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox