* Re: [PATCH] netconsole: queue console messages to send later
From: Flavio Leitner @ 2010-06-08 0:37 UTC (permalink / raw)
To: David Miller
Cc: netdev, amwang, fubar, mpm, gospo, nhorman, jmoyer, shemminger,
linux-kernel, bridge, bonding-devel
In-Reply-To: <20100607.165024.135517125.davem@davemloft.net>
On Mon, Jun 07, 2010 at 04:50:24PM -0700, David Miller wrote:
> From: Flavio Leitner <fleitner@redhat.com>
> Date: Mon, 7 Jun 2010 16:24:52 -0300
>
> > There are some networking drivers that hold a lock in the
> > transmit path. Therefore, if a console message is printed
> > after that, netconsole will push it through the transmit path,
> > resulting in a deadlock.
> >
> > This patch fixes the re-injection problem by queuing the console
> > messages in a preallocated circular buffer and then scheduling a
> > workqueue to send them later with another context.
> >
> > Signed-off-by: Flavio Leitner <fleitner@redhat.com>
>
> You absolutely and positively MUST NOT do this. Otherwise netconsole
> becomes completely useless. Your idea has been proposed several times
> as far back as 6 years ago, it was unacceptable then and it's
> unacceptable now.
>
> The whole point of netconsole is that we may be deep in an interrupt
> or other atomic context, the machine is about to hard hang, and it's
> absolutely essential that we get out any and all kernel logging
> messages that we can, immediately.
Got it. I've never assumed that netconsole would work reliable on
such situations, so I thought as we have better ways now it would
be helpful. See another idea below.
> There may not be another timer or workqueue able to execute after the
> printk() we're trying to emit. We may never get to that point.
What if in the netpoll, before we push the skb to the driver, we check
for a bit saying that it's already pushing another skb. In this case,
queue the new skb inside of netpoll and soon as the first call returns
and try to clear the bit, it will send the next skb?
printk("message 1")
...
netconsole called
netpoll sets the flag bit
pushes to the bonding driver which does another printk("message 2")
netconsole called again
netpoll checks for the flag, queue the message, returns.
so, bonding can finish up to send the first message
netpoll is about to return, checks for new queued messages, and pushes them.
bonding finishes up to send the second message
....
No deadlocks, skbs are ordered and still under the same opportunity
to send something. Does it sound acceptable?
It's off the top of my head, so probably this idea has some problems.
> Fix the locking in the drivers or layers that cause the issue instead
> of breaking netconsole.
Someday, somewhere, I know because I did this before, someone will
use a debugging printk() and will see the entire box hanging with
absolutely no message in any console because of this problem.
I'm not saying that fixing driver isn't the right way to go but
it seems not enough to me.
--
Flavio
^ permalink raw reply
* Re: [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
From: Changli Gao @ 2010-06-08 1:00 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, netdev, Stephen Hemminger, Jarek Poplawski,
Patrick McHardy
In-Reply-To: <1275931108.2545.168.camel@edumazet-laptop>
On Tue, Jun 8, 2010 at 1:18 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
>
> [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
>
> gen_kill_estimator() / gen_new_estimator() is not always called with
> RTNL held.
>
> net/netfilter/xt_RATEEST.c is one user of these API that do not hold
> RTNL, so random corruptions can occur between "tc" and "iptables"
>
> Add a new fine grained lock instead of trying to use RTNL in xt_RATEEST
>
Why not use RTNL in xt_RATEEST? It seems xt_RATEEST misuse the APIs.
and I think gen_replace_estimator is expected to be an atomic operation.
And gen_estimator_active() is also assumed to be called with RTNL locked.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [Patch] infiniband: check local reserved ports
From: Cong Wang @ 2010-06-08 2:23 UTC (permalink / raw)
To: Roland Dreier
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA, Tetsuo Handa,
davem-fT/PcQaiUtIeIZ0/mPfg9Q, linux-rdma-u79uwXL29TY76Z2rM5mHXA,
sean.hefty-ral2JQCrhuEAvxtiuMwx3w
In-Reply-To: <adad3w2onhs.fsf-BjVyx320WGW9gfZ95n9DRSW4+XlvGpQz@public.gmane.org>
On 06/07/10 23:45, Roland Dreier wrote:
> > So this patch looks good for you? :)
>
> Yes, will queue it up, thanks.
Thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [linux-pm] [RFC] pm_qos: get rid of the allocation in pm_qos_add_request()
From: mark gross @ 2010-06-08 3:40 UTC (permalink / raw)
To: James Bottomley
Cc: markgross, Takashi Iwai, netdev, pm list, alsa-devel,
Jaroslav Kysela
In-Reply-To: <1275879019.7227.564.camel@mulgrave.site>
On Sun, Jun 06, 2010 at 10:50:19PM -0400, James Bottomley wrote:
> On Sun, 2010-06-06 at 16:10 -0700, mark gross wrote:
> > On Sat, Jun 05, 2010 at 02:20:14PM -0500, James Bottomley wrote:
> > > [alsa-devel says it's a moderated list, so feel free to drop before
> > > replying]
> > >
> > > Since every caller has to squirrel away the returned pointer anyway,
> > > they might as well supply the memory area. This fixes a bug in a few of
> > > the call sites where the returned pointer was dereferenced without
> > > checking it for NULL (which gets returned if the kzalloc failed).
> > >
> > > I'd like to hear how sound and netdev feels about this: it will add
> > > about two more pointers worth of data to struct netdev and struct
> > > snd_pcm_substream .. but I think it's worth it. If you're OK, I'll add
> > > your acks and send through the pm tree.
> > >
> > > This also looks to me like an android independent clean up (even though
> > > it renders the request_add atomically callable). I also added include
> > > guards to include/linux/pm_qos_params.h
> > >
> > > James
> > >
> > > ---
> > >
> > > drivers/net/e1000e/netdev.c | 17 ++++------
> > > drivers/net/igbvf/netdev.c | 9 ++---
> > > drivers/net/wireless/ipw2x00/ipw2100.c | 12 +++---
> > > include/linux/netdevice.h | 2 +-
> > > include/linux/pm_qos_params.h | 12 +++++--
> > > include/sound/pcm.h | 2 +-
> > > kernel/pm_qos_params.c | 55 ++++++++++++++++---------------
> > > sound/core/pcm_native.c | 12 ++-----
> > > 8 files changed, 60 insertions(+), 61 deletions(-)
> > >
> > > diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c
> > > index 24507f3..47ea62f 100644
> > > --- a/drivers/net/e1000e/netdev.c
> > > +++ b/drivers/net/e1000e/netdev.c
> > > @@ -2901,10 +2901,10 @@ static void e1000_configure_rx(struct e1000_adapter *adapter)
> > > * dropped transactions.
> > > */
> > > pm_qos_update_request(
> > > - adapter->netdev->pm_qos_req, 55);
> > > + &adapter->netdev->pm_qos_req, 55);
> > > } else {
> > > pm_qos_update_request(
> > > - adapter->netdev->pm_qos_req,
> > > + &adapter->netdev->pm_qos_req,
> > > PM_QOS_DEFAULT_VALUE);
> > > }
> > > }
> > > @@ -3196,9 +3196,9 @@ int e1000e_up(struct e1000_adapter *adapter)
> > >
> > > /* DMA latency requirement to workaround early-receive/jumbo issue */
> > > if (adapter->flags & FLAG_HAS_ERT)
> > > - adapter->netdev->pm_qos_req =
> > > - pm_qos_add_request(PM_QOS_CPU_DMA_LATENCY,
> > > - PM_QOS_DEFAULT_VALUE);
> > > + pm_qos_add_request(&adapter->netdev->pm_qos_req,
> > > + PM_QOS_CPU_DMA_LATENCY,
> > > + PM_QOS_DEFAULT_VALUE);
> > >
> > > /* hardware has been reset, we need to reload some things */
> > > e1000_configure(adapter);
> > > @@ -3263,11 +3263,8 @@ void e1000e_down(struct e1000_adapter *adapter)
> > > e1000_clean_tx_ring(adapter);
> > > e1000_clean_rx_ring(adapter);
> > >
> > > - if (adapter->flags & FLAG_HAS_ERT) {
> > > - pm_qos_remove_request(
> > > - adapter->netdev->pm_qos_req);
> > > - adapter->netdev->pm_qos_req = NULL;
> > > - }
> > > + if (adapter->flags & FLAG_HAS_ERT)
> > > + pm_qos_remove_request(&adapter->netdev->pm_qos_req);
> > >
> > > /*
> > > * TODO: for power management, we could drop the link and
> > > diff --git a/drivers/net/igbvf/netdev.c b/drivers/net/igbvf/netdev.c
> > > index 5e2b2a8..5da569f 100644
> > > --- a/drivers/net/igbvf/netdev.c
> > > +++ b/drivers/net/igbvf/netdev.c
> > > @@ -48,7 +48,7 @@
> > > #define DRV_VERSION "1.0.0-k0"
> > > char igbvf_driver_name[] = "igbvf";
> > > const char igbvf_driver_version[] = DRV_VERSION;
> > > -struct pm_qos_request_list *igbvf_driver_pm_qos_req;
> > > +struct pm_qos_request_list igbvf_driver_pm_qos_req;
> > > static const char igbvf_driver_string[] =
> > > "Intel(R) Virtual Function Network Driver";
> > > static const char igbvf_copyright[] = "Copyright (c) 2009 Intel Corporation.";
> > > @@ -2902,8 +2902,8 @@ static int __init igbvf_init_module(void)
> > > printk(KERN_INFO "%s\n", igbvf_copyright);
> > >
> > > ret = pci_register_driver(&igbvf_driver);
> > > - igbvf_driver_pm_qos_req = pm_qos_add_request(PM_QOS_CPU_DMA_LATENCY,
> > > - PM_QOS_DEFAULT_VALUE);
> > > + pm_qos_add_request(igbvf_driver_pm_qos_req, PM_QOS_CPU_DMA_LATENCY,
> > should be:
> >
> > + pm_qos_add_request(&igbvf_driver_pm_qos_req, PM_QOS_CPU_DMA_LATENCY,
>
> Yes, thanks ... must be not compiling this driver for some reason in the
> test case.
>
I think we need to do better with the file gard or fix e100e/netdev.c to
avoid panicking when un-loading the e1000e driver.
I'm on the fence whether to address the e1000e brain damage, or put in
protection from whatever is causing the crash. (which funny enough I
can't get a serial console to that crashing system to share it with
you. but I'm pretty sure an un-initialized netdev->pm_qos_request is
getting passed in (with class==0) resulting in the de-referencing of
NULL in the update_target function.
I'll be other abusers are doing something similar we'll need to guard
again. Would you like me to send an updated patch with some of this
guarding in place?
--mgross
^ permalink raw reply
* Re: 2.6.35-rc2-git1 - include/linux/cgroup.h:534 invoked rcu_dereference_check() without protection!
From: Miles Lane @ 2010-06-08 4:16 UTC (permalink / raw)
To: paulmck
Cc: Vivek Goyal, Eric Paris, Lai Jiangshan, Ingo Molnar,
Peter Zijlstra, LKML, nauman, eric.dumazet, netdev, Jens Axboe,
Gui Jianfeng, Li Zefan, Johannes Berg
In-Reply-To: <20100608001929.GF2387@linux.vnet.ibm.com>
On Mon, Jun 7, 2010 at 8:19 PM, Paul E. McKenney
<paulmck@linux.vnet.ibm.com> wrote:
> On Mon, Jun 07, 2010 at 02:14:25PM -0400, Miles Lane wrote:
>> Hi All,
>>
>> I just reproduced a warning I reported quite a while ago. Is a patch
>> for this in the pipeline?
>
> I proposed a patch, thinking that it was a false positive. Peter Zijlstra
> pointed out that there was a real race, and proposed an alternative patch,
> which may be found at http://lkml.org/lkml/2010/4/22/603.
>
> Could you please test Peter's patch and let us know if it cures the problem?
>
> Thanx, Paul
>
>> [ 0.167267] [ INFO: suspicious rcu_dereference_check() usage. ]
>> [ 0.167396] ---------------------------------------------------
>> [ 0.167526] include/linux/cgroup.h:534 invoked
>> rcu_dereference_check() without protection!
>> [ 0.167728]
>> [ 0.167729] other info that might help us debug this:
>> [ 0.167731]
>> [ 0.168092]
>> [ 0.168093] rcu_scheduler_active = 1, debug_locks = 1
>> [ 0.168337] no locks held by watchdog/0/5.
>> [ 0.168462]
>> [ 0.168463] stack backtrace:
>> [ 0.168704] Pid: 5, comm: watchdog/0 Not tainted 2.6.35-rc2-git1 #8
>> [ 0.168834] Call Trace:
>> [ 0.168965] [<ffffffff81064e9c>] lockdep_rcu_dereference+0x9d/0xa5
>> [ 0.169100] [<ffffffff8102c1ce>] task_subsys_state+0x59/0x70
>> [ 0.169232] [<ffffffff8103189b>] __sched_setscheduler+0x19d/0x2f8
>> [ 0.169365] [<ffffffff8102a5ef>] ? need_resched+0x1e/0x28
>> [ 0.169497] [<ffffffff813c7d01>] ? schedule+0x586/0x619
>> [ 0.169628] [<ffffffff81081c33>] ? watchdog+0x0/0x8c
>> [ 0.169758] [<ffffffff81031a11>] sched_setscheduler+0xe/0x10
>> [ 0.169889] [<ffffffff81081c5d>] watchdog+0x2a/0x8c
>> [ 0.170010] [<ffffffff81081c33>] ? watchdog+0x0/0x8c
>> [ 0.170141] [<ffffffff81054a82>] kthread+0x89/0x91
>> [ 0.170274] [<ffffffff81003054>] kernel_thread_helper+0x4/0x10
>> [ 0.170405] [<ffffffff813ca480>] ? restore_args+0x0/0x30
>> [ 0.170536] [<ffffffff810549f9>] ? kthread+0x0/0x91
>> [ 0.170667] [<ffffffff81003050>] ? kernel_thread_helper+0x0/0x10
>> [ 0.176751] lockdep: fixing up alternatives.
>
With the patch, I get:
[ 0.151274] [ INFO: suspicious rcu_dereference_check() usage. ]
[ 0.151390] ---------------------------------------------------
[ 0.151520] include/linux/cgroup.h:534 invoked
rcu_dereference_check() without protection!
[ 0.151723]
[ 0.151724] other info that might help us debug this:
[ 0.151726]
[ 0.151999]
[ 0.151999] rcu_scheduler_active = 1, debug_locks = 1
[ 0.151999] 2 locks held by kthreadd/10:
[ 0.151999] #0: (key){......}, at: [<ffffffff81036578>] complete+0x1c/0x4e
[ 0.151999] #1: (&rq->lock){-.-...}, at: [<ffffffff81037875>]
select_task_rq_fair+0x21f/0x791
[ 0.151999]
[ 0.151999] stack backtrace:
[ 0.151999] Pid: 10, comm: kthreadd Not tainted 2.6.35-rc2-git1 #11
[ 0.151999] Call Trace:
[ 0.151999] [<ffffffff81070a45>] lockdep_rcu_dereference+0x9d/0xa5
[ 0.151999] [<ffffffff8103675e>] task_subsys_state+0x59/0x70
[ 0.151999] [<ffffffff8103799a>] select_task_rq_fair+0x344/0x791
[ 0.151999] [<ffffffff81037335>] ? task_rq_lock+0x68/0x9d
[ 0.151999] [<ffffffff811d62f3>] ? do_raw_spin_lock+0x79/0x13e
[ 0.151999] [<ffffffff81037335>] ? task_rq_lock+0x68/0x9d
[ 0.151999] [<ffffffff8103ac1e>] select_task_rq+0x13/0x44
[ 0.151999] [<ffffffff810417c3>] try_to_wake_up+0xf2/0x37d
[ 0.151999] [<ffffffff81041a5b>] default_wake_function+0xd/0xf
[ 0.151999] [<ffffffff81034272>] __wake_up_common+0x49/0x7f
[ 0.151999] [<ffffffff81036596>] complete+0x3a/0x4e
[ 0.151999] [<ffffffff8105b598>] ? worker_thread+0x0/0x3a7
[ 0.151999] [<ffffffff8105f7d0>] kthread+0x73/0x91
[ 0.151999] [<ffffffff8100aba4>] kernel_thread_helper+0x4/0x10
[ 0.151999] [<ffffffff813e3694>] ? restore_args+0x0/0x30
[ 0.151999] [<ffffffff8105f75d>] ? kthread+0x0/0x91
[ 0.151999] [<ffffffff8100aba0>] ? kernel_thread_helper+0x0/0x10
^ permalink raw reply
* Re: [PATCHv2 1/2] net: Enable 64-bit net device statistics on 32-bit architectures
From: David Miller @ 2010-06-08 4:18 UTC (permalink / raw)
To: bhutchings; +Cc: shemminger, arnd, netdev, linux-net-drivers
In-Reply-To: <1275689093.2095.36.camel@achroite.uk.solarflarecom.com>
From: Ben Hutchings <bhutchings@solarflare.com>
Date: Fri, 04 Jun 2010 23:04:53 +0100
> +#if BITS_PER_LONG == 64
> +#define NET_DEVICE_STATS_DEFINE(name) u64 name
> +#elif defined(__LITTLE_ENDIAN)
> +#define NET_DEVICE_STATS_DEFINE(name) u32 name, pad_ ## name
> +#else
> +#define NET_DEVICE_STATS_DEFINE(name) u32 pad_ ## name, name
> +#endif
> +
...
> + NET_DEVICE_STATS_DEFINE(rx_packets);
> + NET_DEVICE_STATS_DEFINE(tx_packets);
> + NET_DEVICE_STATS_DEFINE(rx_bytes);
...
> static const char fmt[] = "%30s %12lu\n";
> + static const char fmt64[] = "%30s %12llu\n";
...
> + seq_printf(seq, fmt64, "total frames received", stats->rx_packets);
> + seq_printf(seq, fmt64, "total bytes received", stats->rx_bytes);
> + seq_printf(seq, fmt64, "Broadcast/Multicast Rcvd", stats->multicast);
I guess you only built this on a 64-bit platform that defines u64 as a
long long type.
The rest of the world will receive tons of warnings for these print
statements.
You have basically 3 cases to handle:
1) u64 defined as "unsigned long long"
2) u64 defined as "unsigned long"
3) u32 defined as "unsigned int"
And the whole tree needs to be inspected to make sure there isn't going
to be fallout in areas your patch didn't take care of wrt. printf format
strings and the like.
What was always "unsigned long" is now a variable type, therefore using
a fixed printf format string is impossible unless you always cast these
things when passed in as printf arguments.
^ permalink raw reply
* Re: [PATCH v3] netdev:bfin_mac: reclaim and free tx skb as soon as possible after transfer
From: David Miller @ 2010-06-08 4:22 UTC (permalink / raw)
To: sonic.adi; +Cc: netdev, uclinux-dist-devel
In-Reply-To: <1275907104.9082.1.camel@eight.analog.com>
From: sonic zhang <sonic.adi@gmail.com>
Date: Mon, 7 Jun 2010 18:38:24 +0800
>
> + if (timer_pending(&lp->tx_reclaim_timer))
> + del_timer(&(lp->tx_reclaim_timer));
> +
Please remove the excess parenthesis around lp->tx_reclaim_timer being
passed to del_timer().
Also, you can unconditionally call del_timer(). If the timer isn't running
the call won't do anything.
But you have to do something to make sure you don't race with the code that
enables the timer, f.e. what keeps the timer from being scheduled right
after you make this del_timer() call?
^ permalink raw reply
* Re: [PATCH net-next-2.6] macvlan: use call_rcu for port free
From: David Miller @ 2010-06-08 4:26 UTC (permalink / raw)
To: eric.dumazet; +Cc: jpirko, netdev, kaber
In-Reply-To: <1275912936.2545.48.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 07 Jun 2010 14:15:36 +0200
> Le lundi 07 juin 2010 à 13:36 +0200, Jiri Pirko a écrit :
>> Use call_rcu rather than synchronize_rcu.
>>
>> Signed-off-by: Jiri Pirko <jpirko@redhat.com>
>> ---
>> drivers/net/macvlan.c | 12 ++++++++++--
>> 1 files changed, 10 insertions(+), 2 deletions(-)
>>
>
> Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next-2.6] ip: Router Alert RCU conversion
From: David Miller @ 2010-06-08 4:26 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1275916328.2545.64.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 07 Jun 2010 15:12:08 +0200
> Straightforward conversion to RCU.
>
> One rwlock becomes a spinlock, and is static.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next-2.6] igmp: avoid two atomic ops in igmp_rcv()
From: David Miller @ 2010-06-08 4:26 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1275916630.2545.68.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 07 Jun 2010 15:17:10 +0200
> in_dev_get() -> __in_dev_get_rcu() in a rcu protected function.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next-2.6] ipv4: avoid two atomic ops in ip_rt_redirect()
From: David Miller @ 2010-06-08 4:26 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1275916983.2545.73.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 07 Jun 2010 15:23:03 +0200
> in_dev_get() -> __in_dev_get_rcu() in a rcu protected function.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net-next-2.6] net: avoid two atomic ops in ip_rcv_options()
From: David Miller @ 2010-06-08 4:26 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <1275918886.2545.87.camel@edumazet-laptop>
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Mon, 07 Jun 2010 15:54:46 +0200
> in_dev_get() -> __in_dev_get_rcu() in a rcu protected function.
>
> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Applied.
^ permalink raw reply
* Re: 2.6.35-rc2-git1 - lib/idr.c:605 invoked rcu_dereference_check() without protection!
From: Miles Lane @ 2010-06-08 4:28 UTC (permalink / raw)
To: paulmck
Cc: Vivek Goyal, Eric Paris, David Woodhouse, Lai Jiangshan,
Ingo Molnar, Peter Zijlstra, LKML, nauman, eric.dumazet, netdev,
Jens Axboe, Gui Jianfeng, Li Zefan, Johannes Berg
In-Reply-To: <20100608001234.GE2387@linux.vnet.ibm.com>
On Mon, Jun 7, 2010 at 8:12 PM, Paul E. McKenney
<paulmck@linux.vnet.ibm.com> wrote:
> On Mon, Jun 07, 2010 at 02:23:17PM -0400, Miles Lane wrote:
>> [ 2.677955] [ INFO: suspicious rcu_dereference_check() usage. ]
>> [ 2.679089] ---------------------------------------------------
>> [ 2.680276] lib/idr.c:605 invoked rcu_dereference_check() without protection!
>> [ 2.681499]
>> [ 2.681500] other info that might help us debug this:
>> [ 2.681501]
>> [ 2.685509]
>> [ 2.685510] rcu_scheduler_active = 1, debug_locks = 1
>> [ 2.688221] 1 lock held by swapper/1:
>> [ 2.689587] #0: (mtd_table_mutex){+.+...}, at:
>> [<ffffffff812bea45>] register_mtd_user+0x1a/0x69
>> [ 2.691096]
>> [ 2.691098] stack backtrace:
>> [ 2.694059] Pid: 1, comm: swapper Not tainted 2.6.35-rc2-git1 #8
>> [ 2.695601] Call Trace:
>> [ 2.697243] [<ffffffff81064e9c>] lockdep_rcu_dereference+0x9d/0xa5
>> [ 2.698868] [<ffffffff811b9c86>] idr_get_next+0x60/0x124
>> [ 2.700556] [<ffffffff812be779>] __mtd_next_device+0x1b/0x1d
>> [ 2.702238] [<ffffffff812bea7c>] register_mtd_user+0x51/0x69
>> [ 2.703964] [<ffffffff816cca45>] init_mtdchar+0xb3/0xd3
>> [ 2.705686] [<ffffffff816cc992>] ? init_mtdchar+0x0/0xd3
>> [ 2.707470] [<ffffffff810001ef>] do_one_initcall+0x59/0x14e
>> [ 2.709255] [<ffffffff816a768a>] kernel_init+0x144/0x1ce
>> [ 2.711082] [<ffffffff81003054>] kernel_thread_helper+0x4/0x10
>> [ 2.712862] [<ffffffff813ca480>] ? restore_args+0x0/0x30
>> [ 2.714647] [<ffffffff816a7546>] ? kernel_init+0x0/0x1ce
>> [ 2.716415] [<ffffffff81003050>] ? kernel_thread_helper+0x0/0x10
>
> This looks like a new one! Does the following patch take care of it?
>
> Thanx, Paul
>
> ------------------------------------------------------------------------
>
> commit 2d54a6c31b72c902b09d365e9c66205a5c07e549
> Author: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
> Date: Mon Jun 7 17:09:45 2010 -0700
>
> idr: fix RCU lockdep splat in idr_get_next()
>
> Convert to rcu_dereference_raw() given that many callers may have many
> different locking models.
>
> Located-by: Miles Lane <miles.lane@gmail.com>
> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
>
> diff --git a/lib/idr.c b/lib/idr.c
> index 2eb1dca..f099f25 100644
> --- a/lib/idr.c
> +++ b/lib/idr.c
> @@ -599,7 +599,7 @@ void *idr_get_next(struct idr *idp, int *nextidp)
> /* find first ent */
> n = idp->layers * IDR_BITS;
> max = 1 << n;
> - p = rcu_dereference(idp->top);
> + p = rcu_dereference_raw(idp->top);
> if (!p)
> return NULL;
>
> @@ -607,7 +607,7 @@ void *idr_get_next(struct idr *idp, int *nextidp)
> while (n > 0 && p) {
> n -= IDR_BITS;
> *paa++ = p;
> - p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
> + p = rcu_dereference_raw(p->ary[(id >> n) & IDR_MASK]);
> }
>
> if (p) {
>
Tested. Looks good!
^ permalink raw reply
* Re: [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
From: Eric Dumazet @ 2010-06-08 4:30 UTC (permalink / raw)
To: Changli Gao
Cc: David Miller, netdev, Stephen Hemminger, Jarek Poplawski,
Patrick McHardy
In-Reply-To: <AANLkTik7k__McJk8VCu0WP1RYEDHUfBJA4dyGYQTUmBV@mail.gmail.com>
Le mardi 08 juin 2010 à 09:00 +0800, Changli Gao a écrit :
> On Tue, Jun 8, 2010 at 1:18 AM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> >
> >
> > [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
> >
> > gen_kill_estimator() / gen_new_estimator() is not always called with
> > RTNL held.
> >
> > net/netfilter/xt_RATEEST.c is one user of these API that do not hold
> > RTNL, so random corruptions can occur between "tc" and "iptables"
> >
> > Add a new fine grained lock instead of trying to use RTNL in xt_RATEEST
> >
>
> Why not use RTNL in xt_RATEEST? It seems xt_RATEEST misuse the APIs.
>
> and I think gen_replace_estimator is expected to be an atomic operation.
>
> And gen_estimator_active() is also assumed to be called with RTNL locked.
>
Thank you for asking this question.
Because I want to kill RTNL when possible, I dont even want to try
adding RTNL to xt_RATEEST and solve all lock dependencies it might
raise.
RTNL = Big and Horrible Network LOCK
You never got blocked because of this RTNL thing, dont you ?
I did. And it sucks, because when you hit this, you are in a hurry and
locating the bottleneck takes lot of time.
RTNL is the thing we must hold during device register / unregister.
Its locked for long delays because of all synchronize_rcu() that must be
done, and that is already a big problem on some setups.
Every time someone adds a RTNL requirement, you can be sure another guy
will zap it during following ten years.
Let's do this right now, not later.
For an example of horrible rtnl behavior, take a look at following
construct :
if (!rtnl_trylock())
return restart_syscall();
I saw hundred of udev looping, trying to get rtnl to dump some
information. (Patrick added a rtnl requirement to all dump operations,
and it sucks)
^ permalink raw reply
* Re: [PATCH][RFC] Check sk_buff states
From: Mitchell Erblich @ 2010-06-08 4:46 UTC (permalink / raw)
To: David VomLehn; +Cc: netdev
In-Reply-To: <20100608003055.GA29405@dvomlehn-lnx2.corp.sa.net>
On Jun 7, 2010, at 5:30 PM, David VomLehn wrote:
> This uses the oobparam and callsite infrastructure to implement sk_buff
> state checking and error reporting. Possible states of an sk_buff are:
> SKB_STATE_FREE - Is not currently in use
> SKB_STATE_ALLOCATED - Has been allocated, but is not on a queue
> SKB_STATE_QUEUED - Is allocated and on a queue
> Since there are only three states, two bits suffice to record the state of
> an sk_buff structure, so checking for consistent state is easy. (For you
> weenies, the fourth possible state *is* flagged as an error).
... cut...
Just my two cents,
Just initially thinking of the state names & using only two bits
If a 3rd bit, then it could indicate exclusive or shared (double free then acceptable if shared)
kmem_alloc, malloc, etc actually allocate structs
when something is allocated but not associated with anything, then it has no reference
so then why not?
xxx_STATE_INVALID: both bits unset
xxx_STATE_ALLOCATED: bit 0 set and bit 1 not set
xxx_STATE_REFERENCED : could be exclusive or shared, bit 0 unset & bit 1 set
xxx_STATE_QUEUED: both bits set
Mitchell Erblich
^ permalink raw reply
* Re: [PATCH net-next-2.6] ipv4: avoid two atomic ops in ip_rt_redirect()
From: David Miller @ 2010-06-08 4:51 UTC (permalink / raw)
To: eric.dumazet; +Cc: netdev
In-Reply-To: <20100607.212622.267982352.davem@davemloft.net>
From: David Miller <davem@davemloft.net>
Date: Mon, 07 Jun 2010 21:26:22 -0700 (PDT)
> From: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Mon, 07 Jun 2010 15:23:03 +0200
>
>> in_dev_get() -> __in_dev_get_rcu() in a rcu protected function.
>>
>> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
>
> Applied.
I needed to modify this patch to get it to build.
You left a code label with no code afterwards at the end of
ip_rt_redirect() when CONFIG_IP_ROUTE_VERBOSE is disabled,
which breaks the build.
I fixed it by adding a semicolon.
^ permalink raw reply
* Re: [PATCH net-next-2.6] ipv4: avoid two atomic ops in ip_rt_redirect()
From: Eric Dumazet @ 2010-06-08 4:56 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20100607.215119.176661892.davem@davemloft.net>
Le lundi 07 juin 2010 à 21:51 -0700, David Miller a écrit :
> From: David Miller <davem@davemloft.net>
> Date: Mon, 07 Jun 2010 21:26:22 -0700 (PDT)
>
> > From: Eric Dumazet <eric.dumazet@gmail.com>
> > Date: Mon, 07 Jun 2010 15:23:03 +0200
> >
> >> in_dev_get() -> __in_dev_get_rcu() in a rcu protected function.
> >>
> >> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
> >
> > Applied.
>
> I needed to modify this patch to get it to build.
>
> You left a code label with no code afterwards at the end of
> ip_rt_redirect() when CONFIG_IP_ROUTE_VERBOSE is disabled,
> which breaks the build.
>
> I fixed it by adding a semicolon.
OK, thanks David, I missed this.
^ permalink raw reply
* Re: [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
From: Changli Gao @ 2010-06-08 4:57 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, netdev, Stephen Hemminger, Jarek Poplawski,
Patrick McHardy
In-Reply-To: <1275971457.2775.40.camel@edumazet-laptop>
On Tue, Jun 8, 2010 at 12:30 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
>
> Thank you for asking this question.
>
> Because I want to kill RTNL when possible, I dont even want to try
> adding RTNL to xt_RATEEST and solve all lock dependencies it might
> raise.
>
> RTNL = Big and Horrible Network LOCK
>
It is much like the BKL, and should be killed too. Thanks. :)
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* Re: [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
From: Eric Dumazet @ 2010-06-08 4:58 UTC (permalink / raw)
To: Changli Gao
Cc: David Miller, netdev, Stephen Hemminger, Jarek Poplawski,
Patrick McHardy
In-Reply-To: <AANLkTik7k__McJk8VCu0WP1RYEDHUfBJA4dyGYQTUmBV@mail.gmail.com>
Le mardi 08 juin 2010 à 09:00 +0800, Changli Gao a écrit :
> and I think gen_replace_estimator is expected to be an atomic operation.
>
> And gen_estimator_active() is also assumed to be called with RTNL locked.
>
My patch fixes a bug of new/kill operators, regardless of RTNL being
held or not. Its should be small enough to be included in linux-2.6.35.
If what you say is right, all gen_replace_estimator() /
gen_estimator_active() callers should still holds RTNL.
I didnt change this part.
If you believe one caller doesnt hold RTNL, please submit another patch.
Then, in net-next-2.6, we can probably cleanup this to remove RTNL
requirement if possible for gen_replace_estimator() /
gen_estimator_active()
Yes, it sounds a bit difficult (three patches instead of a single one),
but this is the how things should be done, step by step.
^ permalink raw reply
* cxgb4i_v4.3 submission
From: Rakesh Ranjan @ 2010-06-08 4:59 UTC (permalink / raw)
To: LK-NetDev, LK-SCSIDev, LK-iSCSIDev
Cc: LKML, Karen Xie, David Miller, James Bottomley, Mike Christie,
Anish Bhatt
The following 3 patches add a new iscsi LLD driver cxgb4i to enable iscsi offload
support on Chelsio's new 1G and 10G cards. This is updated version of previous cxgb4i
patch. Please share you commnets after review.
Changes since cxgb4i_v4.2
1. Removed early returns from some functions, which got added for debugging.
[PATCH 1/3] cxgb4i_v4.3 : add build support
[PATCH 2/3] cxgb4i_v4.3 : libcxgbi common library part
[PATCH 3/3] cxgb4i_v4.3 : main driver files
Regards
Rakesh Ranjan
--
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To unsubscribe from this group, send email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
^ permalink raw reply
* [PATCH 1/3] cxgb4i_v4.3 : add build support
From: Rakesh Ranjan @ 2010-06-08 4:59 UTC (permalink / raw)
To: LK-NetDev, LK-SCSIDev, LK-iSCSIDev
Cc: LKML, Karen Xie, David Miller, James Bottomley, Mike Christie,
Anish Bhatt, Rakesh Ranjan
In-Reply-To: <1275973167-8640-1-git-send-email-rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
From: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/scsi/Kconfig | 1 +
drivers/scsi/Makefile | 1 +
drivers/scsi/cxgbi/Kbuild | 5 +++++
drivers/scsi/cxgbi/Kconfig | 7 +++++++
4 files changed, 14 insertions(+), 0 deletions(-)
create mode 100644 drivers/scsi/cxgbi/Kbuild
create mode 100644 drivers/scsi/cxgbi/Kconfig
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 75f2336..70983a8 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -371,6 +371,7 @@ config ISCSI_TCP
http://open-iscsi.org
source "drivers/scsi/cxgb3i/Kconfig"
+source "drivers/scsi/cxgbi/Kconfig"
source "drivers/scsi/bnx2i/Kconfig"
source "drivers/scsi/be2iscsi/Kconfig"
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 1c7ac49..b0873aa 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -133,6 +133,7 @@ obj-$(CONFIG_SCSI_STEX) += stex.o
obj-$(CONFIG_SCSI_MVSAS) += mvsas/
obj-$(CONFIG_PS3_ROM) += ps3rom.o
obj-$(CONFIG_SCSI_CXGB3_ISCSI) += libiscsi.o libiscsi_tcp.o cxgb3i/
+obj-$(CONFIG_SCSI_CXGB4_ISCSI) += libiscsi.o libiscsi_tcp.o cxgbi/
obj-$(CONFIG_SCSI_BNX2_ISCSI) += libiscsi.o bnx2i/
obj-$(CONFIG_BE2ISCSI) += libiscsi.o be2iscsi/
obj-$(CONFIG_SCSI_PMCRAID) += pmcraid.o
diff --git a/drivers/scsi/cxgbi/Kbuild b/drivers/scsi/cxgbi/Kbuild
new file mode 100644
index 0000000..03291c5
--- /dev/null
+++ b/drivers/scsi/cxgbi/Kbuild
@@ -0,0 +1,5 @@
+EXTRA_CFLAGS += -I$(srctree)/drivers/net/cxgb4
+
+obj-$(CONFIG_SCSI_CXGB4_ISCSI) += cxgb4i.o libcxgbi.o
+cxgb4i-y := cxgb4i_init.o cxgb4i_offload.o cxgb4i_ddp.o
+
diff --git a/drivers/scsi/cxgbi/Kconfig b/drivers/scsi/cxgbi/Kconfig
new file mode 100644
index 0000000..3f33dc2
--- /dev/null
+++ b/drivers/scsi/cxgbi/Kconfig
@@ -0,0 +1,7 @@
+config SCSI_CXGB4_ISCSI
+ tristate "Chelsio T4 iSCSI support"
+ depends on CHELSIO_T4_DEPENDS
+ select CHELSIO_T4
+ select SCSI_ISCSI_ATTRS
+ ---help---
+ This driver supports iSCSI offload for the Chelsio T4 series devices.
--
1.6.6.1
--
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To unsubscribe from this group, send email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
^ permalink raw reply related
* [PATCH 2/3] cxgb4i_v4.3 : libcxgbi common library part
From: Rakesh Ranjan @ 2010-06-08 4:59 UTC (permalink / raw)
To: LK-NetDev, LK-SCSIDev, LK-iSCSIDev
Cc: LKML, Karen Xie, David Miller, James Bottomley, Mike Christie,
Anish Bhatt, Rakesh Ranjan
In-Reply-To: <1275973167-8640-2-git-send-email-rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
From: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/scsi/cxgbi/libcxgbi.c | 1518 +++++++++++++++++++++++++++++++++++++++++
drivers/scsi/cxgbi/libcxgbi.h | 556 +++++++++++++++
2 files changed, 2074 insertions(+), 0 deletions(-)
create mode 100644 drivers/scsi/cxgbi/libcxgbi.c
create mode 100644 drivers/scsi/cxgbi/libcxgbi.h
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
new file mode 100644
index 0000000..f6266a0
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -0,0 +1,1518 @@
+/*
+ * libcxgbi.c: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#include <linux/skbuff.h>
+#include <linux/crypto.h>
+#include <linux/scatterlist.h>
+#include <linux/pci.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <linux/if_vlan.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <net/tcp.h>
+
+#include "libcxgbi.h"
+
+MODULE_AUTHOR("Chelsio Communications");
+MODULE_DESCRIPTION("Chelsio libcxgbi common library");
+MODULE_LICENSE("GPL");
+
+static LIST_HEAD(cdev_list);
+static DEFINE_MUTEX(cdev_rwlock);
+
+static void cxgbi_release_itt(struct iscsi_task *, itt_t);
+static int cxgbi_reserve_itt(struct iscsi_task *, itt_t *);
+
+struct cxgbi_device *cxgbi_device_register(unsigned int dd_size,
+ unsigned int nports)
+{
+ struct cxgbi_device *cdev;
+
+ cdev = kzalloc(sizeof(*cdev) + dd_size, GFP_KERNEL);
+ if (!cdev)
+ return NULL;
+
+ cdev->hbas = kzalloc(sizeof(struct cxgbi_hba **) * nports, GFP_KERNEL);
+ if (!cdev->hbas) {
+ kfree(cdev);
+ return NULL;
+ }
+
+ mutex_lock(&cdev_rwlock);
+ list_add_tail(&cdev->list_head, &cdev_list);
+ mutex_unlock(&cdev_rwlock);
+ return cdev;
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_register);
+
+void cxgbi_device_unregister(struct cxgbi_device *cdev)
+{
+ mutex_lock(&cdev_rwlock);
+ list_del(&cdev->list_head);
+ mutex_unlock(&cdev_rwlock);
+
+ kfree(cdev->hbas);
+ kfree(cdev);
+}
+EXPORT_SYMBOL_GPL(cxgbi_device_unregister);
+
+static struct cxgbi_hba *cxgbi_hba_find_by_netdev(struct net_device *dev,
+ struct cxgbi_device *cdev)
+{
+ int i;
+
+ if (dev->priv_flags & IFF_802_1Q_VLAN)
+ dev = vlan_dev_real_dev(dev);
+
+ for (i = 0; i < cdev->nports; i++) {
+ if (cdev->hbas[i]->ndev == dev)
+ return cdev->hbas[i];
+ }
+
+ return NULL;
+}
+
+static struct rtable *find_route(struct net_device *dev,
+ __be32 saddr, __be32 daddr,
+ __be16 sport, __be16 dport,
+ u8 tos)
+{
+ struct rtable *rt;
+ struct flowi fl = {
+ .oif = dev ? dev->ifindex : 0,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = daddr,
+ .saddr = saddr,
+ .tos = tos }
+ },
+ .proto = IPPROTO_TCP,
+ .uli_u = {
+ .ports = {
+ .sport = sport,
+ .dport = dport }
+ }
+ };
+
+ if (ip_route_output_flow(dev ? dev_net(dev) : &init_net,
+ &rt, &fl, NULL, 0))
+ return NULL;
+
+ return rt;
+}
+
+static struct net_device *cxgbi_find_dev(struct net_device *dev,
+ __be32 ipaddr)
+{
+ struct flowi fl;
+ struct rtable *rt;
+ int err;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.nl_u.ip4_u.daddr = ipaddr;
+
+ err = ip_route_output_key(dev ? dev_net(dev) : &init_net, &rt, &fl);
+ if (!err)
+ return (&rt->u.dst)->dev;
+
+ return NULL;
+}
+
+static int is_cxgbi_dev(struct net_device *dev, struct cxgbi_device *cdev)
+{
+ struct net_device *ndev = dev;
+ int i;
+
+ if (dev->priv_flags & IFF_802_1Q_VLAN)
+ ndev = vlan_dev_real_dev(dev);
+
+ for (i = 0; i < cdev->nports; i++) {
+ if (ndev == cdev->ports[i])
+ return 1;
+ }
+ return 0;
+}
+
+static struct net_device *cxgbi_find_egress_dev(struct net_device *root_dev,
+ struct cxgbi_device *cdev)
+{
+ while (root_dev) {
+ if (root_dev->priv_flags & IFF_802_1Q_VLAN)
+ root_dev = vlan_dev_real_dev(root_dev);
+ else if (is_cxgbi_dev(root_dev, cdev))
+ return root_dev;
+ else
+ return NULL;
+ }
+
+ return NULL;
+}
+
+static struct cxgbi_device *cxgbi_find_cdev(struct net_device *dev,
+ __be32 ipaddr)
+{
+ struct flowi fl;
+ struct rtable *rt;
+ struct net_device *sdev = NULL;
+ struct cxgbi_device *cdev = NULL, *tmp;
+ int err, i;
+
+ memset(&fl, 0, sizeof(fl));
+ fl.nl_u.ip4_u.daddr = ipaddr;
+
+ err = ip_route_output_key(dev ? dev_net(dev) : &init_net, &rt, &fl);
+ if (err)
+ goto out;
+
+ sdev = (&rt->u.dst)->dev;
+ mutex_lock(&cdev_rwlock);
+ list_for_each_entry_safe(cdev, tmp, &cdev_list, list_head) {
+ if (cdev) {
+ for (i = 0; i < cdev->nports; i++) {
+ if (sdev == cdev->ports[i]) {
+ mutex_unlock(&cdev_rwlock);
+ return cdev;
+ }
+ }
+ }
+ }
+ mutex_unlock(&cdev_rwlock);
+out: return cdev;
+}
+
+/*
+ * pdu receive, interact with libiscsi_tcp
+ */
+static inline int read_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb,
+ unsigned int offset,
+ int offloaded)
+{
+ int status = 0;
+ int bytes_read;
+
+ bytes_read = iscsi_tcp_recv_skb(conn, skb, offset, offloaded, &status);
+ switch (status) {
+ case ISCSI_TCP_CONN_ERR:
+ return -EIO;
+ case ISCSI_TCP_SUSPENDED:
+ /* no transfer - just have caller flush queue */
+ return bytes_read;
+ case ISCSI_TCP_SKB_DONE:
+ /*
+ * pdus should always fit in the skb and we should get
+ * segment done notifcation.
+ */
+ iscsi_conn_printk(KERN_ERR, conn, "Invalid pdu or skb.");
+ return -EFAULT;
+ case ISCSI_TCP_SEGMENT_DONE:
+ return bytes_read;
+ default:
+ iscsi_conn_printk(KERN_ERR, conn, "Invalid iscsi_tcp_recv_skb "
+ "status %d\n", status);
+ return -EINVAL;
+ }
+}
+
+static int cxgbi_conn_read_bhs_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ int rc;
+
+ cxgbi_rx_debug("conn 0x%p, skb 0x%p, len %u, flag 0x%x.\n",
+ conn, skb, skb->len, cdev->get_skb_ulp_mode(skb));
+
+ if (!iscsi_tcp_recv_segment_is_hdr(tcp_conn)) {
+ iscsi_conn_failure(conn, ISCSI_ERR_PROTO);
+ return -EIO;
+ }
+
+ if (conn->hdrdgst_en && (cdev->get_skb_ulp_mode(skb)
+ & ULP2_FLAG_HCRC_ERROR)) {
+ iscsi_conn_failure(conn, ISCSI_ERR_HDR_DGST);
+ return -EIO;
+ }
+
+ rc = read_pdu_skb(conn, skb, 0, 0);
+ if (rc <= 0)
+ return rc;
+
+ return 0;
+}
+
+static int cxgbi_conn_read_data_pdu_skb(struct iscsi_conn *conn,
+ struct sk_buff *skb)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ bool offloaded = 0;
+ unsigned int offset = 0;
+ int rc;
+
+ cxgbi_rx_debug("conn 0x%p, skb 0x%p, len %u, flag 0x%x.\n",
+ conn, skb, skb->len, cdev->get_skb_ulp_mode(skb));
+
+ if (conn->datadgst_en &&
+ (cdev->get_skb_ulp_mode(skb) & ULP2_FLAG_DCRC_ERROR)) {
+ iscsi_conn_failure(conn, ISCSI_ERR_DATA_DGST);
+ return -EIO;
+ }
+
+ if (iscsi_tcp_recv_segment_is_hdr(tcp_conn))
+ return 0;
+
+ if (conn->hdrdgst_en)
+ offset = ISCSI_DIGEST_SIZE;
+
+ if (cdev->get_skb_ulp_mode(skb) & ULP2_FLAG_DATA_DDPED) {
+ cxgbi_rx_debug("skb 0x%p, opcode 0x%x, data %u, ddp'ed, "
+ "itt 0x%x.\n",
+ skb,
+ tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK,
+ tcp_conn->in.datalen,
+ ntohl(tcp_conn->in.hdr->itt));
+ offloaded = 1;
+ } else {
+ cxgbi_rx_debug("skb 0x%p, opcode 0x%x, data %u, NOT ddp'ed, "
+ "itt 0x%x.\n",
+ skb,
+ tcp_conn->in.hdr->opcode & ISCSI_OPCODE_MASK,
+ tcp_conn->in.datalen,
+ ntohl(tcp_conn->in.hdr->itt));
+ }
+
+ rc = read_pdu_skb(conn, skb, 0, offloaded);
+ if (rc < 0)
+ return rc;
+
+ return 0;
+}
+
+void cxgbi_conn_pdu_ready(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+ unsigned int read = 0;
+ struct iscsi_conn *conn = csk->user_data;
+ int err = 0;
+
+ cxgbi_rx_debug("csk 0x%p.\n", csk);
+
+ read_lock(&csk->callback_lock);
+ if (unlikely(!conn || conn->suspend_rx)) {
+ cxgbi_rx_debug("conn 0x%p, id %d, suspend_rx %lu!\n",
+ conn, conn ? conn->id : 0xFF,
+ conn ? conn->suspend_rx : 0xFF);
+ read_unlock(&csk->callback_lock);
+ return;
+ }
+
+ skb = skb_peek(&csk->receive_queue);
+ while (!err && skb) {
+ __skb_unlink(skb, &csk->receive_queue);
+ read += csk->cdev->get_skb_rx_pdulen(skb);
+ cxgbi_rx_debug("conn 0x%p, csk 0x%p, rx skb 0x%p, pdulen %u\n",
+ conn, csk, skb,
+ csk->cdev->get_skb_rx_pdulen(skb));
+ if (csk->flags & CTPF_MSG_COALESCED) {
+ err = cxgbi_conn_read_bhs_pdu_skb(conn, skb);
+ err = cxgbi_conn_read_data_pdu_skb(conn, skb);
+ } else {
+ if (csk->cdev->get_skb_flags(skb) &
+ CTP_SKCBF_HDR_RCVD)
+ err = cxgbi_conn_read_bhs_pdu_skb(conn, skb);
+ else if (csk->cdev->get_skb_flags(skb) ==
+ CTP_SKCBF_DATA_RCVD)
+ err = cxgbi_conn_read_data_pdu_skb(conn, skb);
+ }
+ __kfree_skb(skb);
+ skb = skb_peek(&csk->receive_queue);
+ }
+ cxgbi_log_debug("read %d\n", read);
+ read_unlock(&csk->callback_lock);
+ csk->copied_seq += read;
+ csk->cdev->sock_rx_credits(csk, read);
+ conn->rxdata_octets += read;
+
+ if (err) {
+ cxgbi_log_info("conn 0x%p rx failed err %d.\n", conn, err);
+ iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_pdu_ready);
+
+static int sgl_seek_offset(struct scatterlist *sgl, unsigned int sgcnt,
+ unsigned int offset, unsigned int *off,
+ struct scatterlist **sgp)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, sgcnt, i) {
+ if (offset < sg->length) {
+ *off = offset;
+ *sgp = sg;
+ return 0;
+ }
+ offset -= sg->length;
+ }
+ return -EFAULT;
+}
+
+static int sgl_read_to_frags(struct scatterlist *sg, unsigned int sgoffset,
+ unsigned int dlen, skb_frag_t *frags,
+ int frag_max)
+{
+ unsigned int datalen = dlen;
+ unsigned int sglen = sg->length - sgoffset;
+ struct page *page = sg_page(sg);
+ int i;
+
+ i = 0;
+ do {
+ unsigned int copy;
+
+ if (!sglen) {
+ sg = sg_next(sg);
+ if (!sg) {
+ cxgbi_log_error("sg NULL, len %u/%u.\n",
+ datalen, dlen);
+ return -EINVAL;
+ }
+ sgoffset = 0;
+ sglen = sg->length;
+ page = sg_page(sg);
+
+ }
+ copy = min(datalen, sglen);
+ if (i && page == frags[i - 1].page &&
+ sgoffset + sg->offset ==
+ frags[i - 1].page_offset + frags[i - 1].size) {
+ frags[i - 1].size += copy;
+ } else {
+ if (i >= frag_max) {
+ cxgbi_log_error("too many pages %u, "
+ "dlen %u.\n", frag_max, dlen);
+ return -EINVAL;
+ }
+
+ frags[i].page = page;
+ frags[i].page_offset = sg->offset + sgoffset;
+ frags[i].size = copy;
+ i++;
+ }
+ datalen -= copy;
+ sgoffset += copy;
+ sglen -= copy;
+ } while (datalen);
+
+ return i;
+}
+
+int cxgbi_conn_alloc_pdu(struct iscsi_task *task, u8 opcode)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = task->dd_data + sizeof(*tcp_task);
+ struct scsi_cmnd *sc = task->sc;
+ int headroom = SKB_TX_PDU_HEADER_LEN;
+
+ tcp_task->dd_data = tdata;
+ task->hdr = NULL;
+
+ /* write command, need to send data pdus */
+ if (cdev->skb_extra_headroom && (opcode == ISCSI_OP_SCSI_DATA_OUT ||
+ (opcode == ISCSI_OP_SCSI_CMD &&
+ (scsi_bidi_cmnd(sc) || sc->sc_data_direction == DMA_TO_DEVICE))))
+ headroom += min(cdev->skb_extra_headroom,
+ conn->max_xmit_dlength);
+
+ tdata->skb = alloc_skb(cdev->skb_tx_headroom + headroom, GFP_ATOMIC);
+ if (!tdata->skb)
+ return -ENOMEM;
+
+ skb_reserve(tdata->skb, cdev->skb_tx_headroom);
+ cxgbi_tx_debug("task 0x%p, opcode 0x%x, skb 0x%p.\n",
+ task, opcode, tdata->skb);
+ task->hdr = (struct iscsi_hdr *)tdata->skb->data;
+ task->hdr_max = SKB_TX_PDU_HEADER_LEN;
+
+ /* data_out uses scsi_cmd's itt */
+ if (opcode != ISCSI_OP_SCSI_DATA_OUT)
+ cxgbi_reserve_itt(task, &task->hdr->itt);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_alloc_pdu);
+
+int cxgbi_conn_init_pdu(struct iscsi_task *task, unsigned int offset,
+ unsigned int count)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = tcp_task->dd_data;
+ struct sk_buff *skb = tdata->skb;
+ unsigned int datalen = count;
+ int i, padlen = iscsi_padding(count);
+ struct page *pg;
+
+ cxgbi_tx_debug("task 0x%p,0x%p, offset %u, count %u, skb 0x%p.\n",
+ task, task->sc, offset, count, skb);
+
+ skb_put(skb, task->hdr_len);
+ cdev->set_skb_txmode(skb, conn->hdrdgst_en,
+ datalen ? conn->datadgst_en : 0);
+ if (!count)
+ return 0;
+
+ if (task->sc) {
+ struct scsi_data_buffer *sdb = scsi_out(task->sc);
+ struct scatterlist *sg = NULL;
+ int err;
+
+ tdata->offset = offset;
+ tdata->count = count;
+ err = sgl_seek_offset(sdb->table.sgl, sdb->table.nents,
+ tdata->offset, &tdata->sgoffset, &sg);
+ if (err < 0) {
+ cxgbi_log_warn("tpdu, sgl %u, bad offset %u/%u.\n",
+ sdb->table.nents, tdata->offset,
+ sdb->length);
+ return err;
+ }
+ err = sgl_read_to_frags(sg, tdata->sgoffset, tdata->count,
+ tdata->frags, MAX_PDU_FRAGS);
+ if (err < 0) {
+ cxgbi_log_warn("tpdu, sgl %u, bad offset %u + %u.\n",
+ sdb->table.nents, tdata->offset,
+ tdata->count);
+ return err;
+ }
+ tdata->nr_frags = err;
+
+ if (tdata->nr_frags > MAX_SKB_FRAGS ||
+ (padlen && tdata->nr_frags == MAX_SKB_FRAGS)) {
+ char *dst = skb->data + task->hdr_len;
+ skb_frag_t *frag = tdata->frags;
+
+ /* data fits in the skb's headroom */
+ for (i = 0; i < tdata->nr_frags; i++, frag++) {
+ char *src = kmap_atomic(frag->page,
+ KM_SOFTIRQ0);
+
+ memcpy(dst, src+frag->page_offset, frag->size);
+ dst += frag->size;
+ kunmap_atomic(src, KM_SOFTIRQ0);
+ }
+ if (padlen) {
+ memset(dst, 0, padlen);
+ padlen = 0;
+ }
+ skb_put(skb, count + padlen);
+ } else {
+ /* data fit into frag_list */
+ for (i = 0; i < tdata->nr_frags; i++)
+ get_page(tdata->frags[i].page);
+
+ memcpy(skb_shinfo(skb)->frags, tdata->frags,
+ sizeof(skb_frag_t) * tdata->nr_frags);
+ skb_shinfo(skb)->nr_frags = tdata->nr_frags;
+ skb->len += count;
+ skb->data_len += count;
+ skb->truesize += count;
+ }
+
+ } else {
+ pg = virt_to_page(task->data);
+
+ get_page(pg);
+ skb_fill_page_desc(skb, 0, pg, offset_in_page(task->data),
+ count);
+ skb->len += count;
+ skb->data_len += count;
+ skb->truesize += count;
+ }
+
+ if (padlen) {
+ i = skb_shinfo(skb)->nr_frags;
+ get_page(cdev->pad_page);
+ skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags,
+ cdev->pad_page, 0, padlen);
+
+ skb->data_len += padlen;
+ skb->truesize += padlen;
+ skb->len += padlen;
+ }
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_init_pdu);
+
+int cxgbi_conn_xmit_pdu(struct iscsi_task *task)
+{
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ struct iscsi_tcp_task *tcp_task = task->dd_data;
+ struct cxgbi_task_data *tdata = tcp_task->dd_data;
+ struct sk_buff *skb = tdata->skb;
+ unsigned int datalen;
+ int err;
+
+ if (!skb)
+ return 0;
+
+ datalen = skb->data_len;
+ tdata->skb = NULL;
+ err = cdev->sock_send_pdus(cconn->cep->csk, skb);
+ if (err > 0) {
+ int pdulen = err;
+
+ cxgbi_tx_debug("task 0x%p, skb 0x%p, len %u/%u, rv %d.\n",
+ task, skb, skb->len, skb->data_len, err);
+
+ if (task->conn->hdrdgst_en)
+ pdulen += ISCSI_DIGEST_SIZE;
+
+ if (datalen && task->conn->datadgst_en)
+ pdulen += ISCSI_DIGEST_SIZE;
+
+ task->conn->txdata_octets += pdulen;
+ return 0;
+ }
+
+ if (err == -EAGAIN || err == -ENOBUFS) {
+ /* reset skb to send when we are called again */
+ tdata->skb = skb;
+ return err;
+ }
+
+ kfree_skb(skb);
+ cxgbi_tx_debug("itt 0x%x, skb 0x%p, len %u/%u, xmit err %d.\n",
+ task->itt, skb, skb->len, skb->data_len, err);
+ iscsi_conn_printk(KERN_ERR, task->conn, "xmit err %d.\n", err);
+ iscsi_conn_failure(task->conn, ISCSI_ERR_XMIT_FAILED);
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_xmit_pdu);
+
+int cxgbi_pdu_init(struct cxgbi_device *cdev)
+{
+ cdev->pad_page = alloc_page(GFP_KERNEL);
+ if (!cdev->pad_page)
+ return -ENOMEM;
+
+ memset(page_address(cdev->pad_page), 0, PAGE_SIZE);
+
+ if (cdev->skb_tx_headroom > (512 * MAX_SKB_FRAGS))
+ cdev->skb_extra_headroom = cdev->skb_tx_headroom;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_pdu_init);
+
+void cxgbi_pdu_cleanup(struct cxgbi_device *cdev)
+{
+ if (cdev->pad_page) {
+ __free_page(cdev->pad_page);
+ cdev->pad_page = NULL;
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_pdu_cleanup);
+
+void cxgbi_conn_tx_open(struct cxgbi_sock *csk)
+{
+ struct iscsi_conn *conn = csk->user_data;
+
+ if (conn) {
+ cxgbi_tx_debug("cn 0x%p, cid %d.\n", csk, conn->id);
+ iscsi_conn_queue_work(conn);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_conn_tx_open);
+
+static int cxgbi_sock_get_port(struct cxgbi_sock *csk)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+ unsigned int start;
+ int idx;
+
+ if (!cdev->pmap)
+ goto error_out;
+
+ if (csk->saddr.sin_port) {
+ cxgbi_log_error("connect, sin_port none ZERO %u\n",
+ ntohs(csk->saddr.sin_port));
+ return -EADDRINUSE;
+ }
+
+ spin_lock_bh(&cdev->pmap->lock);
+ start = idx = cdev->pmap->next;
+
+ do {
+ if (++idx >= cdev->pmap->max_connect)
+ idx = 0;
+ if (!cdev->pmap->port_csk[idx]) {
+ csk->saddr.sin_port =
+ htons(cdev->pmap->sport_base + idx);
+ cdev->pmap->next = idx;
+ cdev->pmap->port_csk[idx] = csk;
+ spin_unlock_bh(&cdev->pmap->lock);
+ cxgbi_conn_debug("reserved port %u\n",
+ cdev->pmap->sport_base + idx);
+ return 0;
+ }
+ } while (idx != start);
+ spin_unlock_bh(&cdev->pmap->lock);
+error_out:
+ return -EADDRNOTAVAIL;
+}
+
+static void cxgbi_sock_put_port(struct cxgbi_sock *csk)
+{
+ struct cxgbi_device *cdev = csk->cdev;
+
+ if (csk->saddr.sin_port) {
+ int idx = ntohs(csk->saddr.sin_port) - cdev->pmap->sport_base;
+
+ csk->saddr.sin_port = 0;
+ if (idx < 0 || idx >= cdev->pmap->max_connect)
+ return;
+
+ spin_lock_bh(&cdev->pmap->lock);
+ cdev->pmap->port_csk[idx] = NULL;
+ spin_unlock_bh(&cdev->pmap->lock);
+ cxgbi_conn_debug("released port %u\n",
+ cdev->pmap->sport_base + idx);
+ }
+}
+
+static struct cxgbi_sock *cxgbi_sock_create(struct cxgbi_device *cdev)
+{
+ struct cxgbi_sock *csk = NULL;
+
+ csk = kzalloc(sizeof(*csk), GFP_NOIO);
+ if (!csk)
+ return NULL;
+
+ if (cdev->alloc_cpl_skbs(csk) < 0)
+ goto free_csk;
+
+ cxgbi_conn_debug("alloc csk: 0x%p\n", csk);
+
+ csk->flags = 0;
+ spin_lock_init(&csk->lock);
+ kref_init(&csk->refcnt);
+ skb_queue_head_init(&csk->receive_queue);
+ skb_queue_head_init(&csk->write_queue);
+ setup_timer(&csk->retry_timer, NULL, (unsigned long)csk);
+ rwlock_init(&csk->callback_lock);
+ csk->cdev = cdev;
+ return csk;
+free_csk:
+ cxgbi_api_debug("csk alloc failed %p, baling out\n", csk);
+ kfree(csk);
+ return NULL;
+}
+
+static int cxgbi_sock_connect(struct net_device *dev, struct cxgbi_sock *csk,
+ struct sockaddr_in *sin)
+{
+ struct rtable *rt;
+ __be32 sipv4 = 0;
+ struct net_device *dstdev;
+ struct cxgbi_hba *chba = NULL;
+ int err;
+
+ cxgbi_conn_debug("csk 0x%p, dev 0x%p\n", csk, dev);
+
+ if (sin->sin_family != AF_INET)
+ return -EAFNOSUPPORT;
+
+ csk->daddr.sin_port = sin->sin_port;
+ csk->daddr.sin_addr.s_addr = sin->sin_addr.s_addr;
+
+ dstdev = cxgbi_find_dev(dev, sin->sin_addr.s_addr);
+ if (!dstdev || !is_cxgbi_dev(dstdev, csk->cdev))
+ return -ENETUNREACH;
+
+ if (dstdev->priv_flags & IFF_802_1Q_VLAN)
+ dev = dstdev;
+
+ rt = find_route(dev, csk->saddr.sin_addr.s_addr,
+ csk->daddr.sin_addr.s_addr,
+ csk->saddr.sin_port,
+ csk->daddr.sin_port,
+ 0);
+ if (rt == NULL) {
+ cxgbi_conn_debug("no route to %pI4, port %u, dev %s, "
+ "snic 0x%p\n",
+ &csk->daddr.sin_addr.s_addr,
+ ntohs(csk->daddr.sin_port),
+ dev ? dev->name : "any",
+ csk->dd_data);
+ return -ENETUNREACH;
+ }
+
+ if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
+ cxgbi_conn_debug("multi-cast route to %pI4, port %u, "
+ "dev %s, snic 0x%p\n",
+ &csk->daddr.sin_addr.s_addr,
+ ntohs(csk->daddr.sin_port),
+ dev ? dev->name : "any",
+ csk->dd_data);
+ ip_rt_put(rt);
+ return -ENETUNREACH;
+ }
+
+ if (!csk->saddr.sin_addr.s_addr)
+ csk->saddr.sin_addr.s_addr = rt->rt_src;
+
+ csk->dst = &rt->u.dst;
+
+ dev = cxgbi_find_egress_dev(csk->dst->dev, csk->cdev);
+ if (dev == NULL) {
+ cxgbi_conn_debug("csk: 0x%p, egress dev NULL\n", csk);
+ return -ENETUNREACH;
+ }
+
+ err = cxgbi_sock_get_port(csk);
+ if (err)
+ return err;
+
+ cxgbi_conn_debug("csk: 0x%p get port: %u\n",
+ csk, ntohs(csk->saddr.sin_port));
+
+ chba = cxgbi_hba_find_by_netdev(csk->dst->dev, csk->cdev);
+
+ sipv4 = cxgbi_get_iscsi_ipv4(chba);
+ if (!sipv4) {
+ cxgbi_conn_debug("csk: 0x%p, iscsi is not configured\n", csk);
+ sipv4 = csk->saddr.sin_addr.s_addr;
+ cxgbi_set_iscsi_ipv4(chba, sipv4);
+ } else
+ csk->saddr.sin_addr.s_addr = sipv4;
+
+ cxgbi_conn_debug("csk: 0x%p, %pI4:[%u], %pI4:[%u] SYN_SENT\n",
+ csk,
+ &csk->saddr.sin_addr.s_addr,
+ ntohs(csk->saddr.sin_port),
+ &csk->daddr.sin_addr.s_addr,
+ ntohs(csk->daddr.sin_port));
+
+ cxgbi_sock_set_state(csk, CTP_CONNECTING);
+
+ if (!csk->cdev->init_act_open(csk, dev))
+ return 0;
+
+ err = -ENOTSUPP;
+ cxgbi_conn_debug("csk 0x%p -> closed\n", csk);
+ cxgbi_sock_set_state(csk, CTP_CLOSED);
+ ip_rt_put(rt);
+ cxgbi_sock_put_port(csk);
+ return err;
+}
+
+void cxgbi_sock_conn_closing(struct cxgbi_sock *csk)
+{
+ struct iscsi_conn *conn = csk->user_data;
+
+ read_lock(&csk->callback_lock);
+ if (conn && csk->state != CTP_ESTABLISHED)
+ iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+ read_unlock(&csk->callback_lock);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_conn_closing);
+
+void cxgbi_sock_closed(struct cxgbi_sock *csk)
+{
+ cxgbi_conn_debug("csk 0x%p, state %u, flags 0x%lx\n",
+ csk, csk->state, csk->flags);
+
+ cxgbi_sock_put_port(csk);
+ csk->cdev->release_offload_resources(csk);
+ cxgbi_sock_set_state(csk, CTP_CLOSED);
+ cxgbi_sock_conn_closing(csk);
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_closed);
+
+static void cxgbi_sock_active_close(struct cxgbi_sock *csk)
+{
+ int data_lost;
+ int close_req = 0;
+
+ cxgbi_conn_debug("csk 0x%p, state %u, flags %lu\n",
+ csk, csk->state, csk->flags);
+ dst_confirm(csk->dst);
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ data_lost = skb_queue_len(&csk->receive_queue);
+ __skb_queue_purge(&csk->receive_queue);
+
+ switch (csk->state) {
+ case CTP_CLOSED:
+ case CTP_ACTIVE_CLOSE:
+ case CTP_CLOSE_WAIT_1:
+ case CTP_CLOSE_WAIT_2:
+ case CTP_ABORTING:
+ break;
+ case CTP_CONNECTING:
+ cxgbi_sock_set_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+ break;
+ case CTP_ESTABLISHED:
+ close_req = 1;
+ cxgbi_sock_set_flag(csk, CTP_ACTIVE_CLOSE);
+ break;
+ case CTP_PASSIVE_CLOSE:
+ close_req = 1;
+ cxgbi_sock_set_flag(csk, CTP_CLOSE_WAIT_2);
+ break;
+ }
+
+ if (close_req) {
+ if (data_lost)
+ csk->cdev->send_abort_req(csk);
+ else
+ csk->cdev->send_close_req(csk);
+ }
+
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+}
+
+static void cxgbi_sock_release(struct cxgbi_sock *csk)
+{
+ cxgbi_conn_debug("csk 0x%p, state %u, flags %lu\n",
+ csk, csk->state, csk->flags);
+ if (unlikely(csk->state == CTP_CONNECTING))
+ cxgbi_sock_set_state(csk, CTPF_ACTIVE_CLOSE_NEEDED);
+ else if (likely(csk->state != CTP_CLOSED))
+ cxgbi_sock_active_close(csk);
+ cxgbi_sock_put(csk);
+}
+
+static unsigned int cxgbi_sock_find_best_mtu(struct cxgbi_sock *csk,
+ unsigned short mtu)
+{
+ int i = 0;
+
+ while (i < csk->cdev->nmtus - 1 && csk->cdev->mtus[i + 1] <= mtu)
+ ++i;
+
+ return i;
+}
+
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *csk, unsigned int pmtu)
+{
+ unsigned int idx;
+ struct dst_entry *dst = csk->dst;
+ u16 advmss = dst_metric(dst, RTAX_ADVMSS);
+
+ if (advmss > pmtu - 40)
+ advmss = pmtu - 40;
+ if (advmss < csk->cdev->mtus[0] - 40)
+ advmss = csk->cdev->mtus[0] - 40;
+ idx = cxgbi_sock_find_best_mtu(csk, advmss + 40);
+
+ return idx;
+}
+EXPORT_SYMBOL_GPL(cxgbi_sock_select_mss);
+
+static void cxgbi_release_itt(struct iscsi_task *task, itt_t hdr_itt)
+{
+ struct scsi_cmnd *sc = task->sc;
+ struct iscsi_tcp_conn *tcp_conn = task->conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_hba *chba = cconn->chba;
+ struct cxgbi_tag_format *tformat = &chba->cdev->tag_format;
+ u32 tag = ntohl((__force u32)hdr_itt);
+
+ cxgbi_tag_debug("release tag 0x%x.\n", tag);
+ if (sc && (scsi_bidi_cmnd(sc) ||
+ sc->sc_data_direction == DMA_FROM_DEVICE) &&
+ cxgbi_is_ddp_tag(tformat, tag))
+ chba->cdev->ddp_tag_release(chba, tag);
+}
+
+static int cxgbi_reserve_itt(struct iscsi_task *task, itt_t *hdr_itt)
+{
+ struct scsi_cmnd *sc = task->sc;
+ struct iscsi_conn *conn = task->conn;
+ struct iscsi_session *sess = conn->session;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_hba *chba = cconn->chba;
+ struct cxgbi_tag_format *tformat = &chba->cdev->tag_format;
+ u32 sw_tag = (sess->age << cconn->task_idx_bits) | task->itt;
+ u32 tag;
+ int err = -EINVAL;
+
+ if (sc && (scsi_bidi_cmnd(sc) ||
+ sc->sc_data_direction == DMA_FROM_DEVICE) &&
+ cxgbi_sw_tag_usable(tformat, sw_tag)) {
+ struct cxgbi_sock *csk = cconn->cep->csk;
+ struct cxgbi_gather_list *gl;
+
+ gl = chba->cdev->ddp_make_gl(scsi_in(sc)->length,
+ scsi_in(sc)->table.sgl,
+ scsi_in(sc)->table.nents,
+ chba->cdev->pdev, GFP_ATOMIC);
+ if (gl) {
+ tag = sw_tag;
+ err = chba->cdev->ddp_tag_reserve(chba, csk->hwtid,
+ tformat, &tag,
+ gl, GFP_ATOMIC);
+ if (err < 0)
+ chba->cdev->ddp_release_gl(gl,
+ chba->cdev->pdev);
+ }
+ }
+ if (err < 0)
+ tag = cxgbi_set_non_ddp_tag(tformat, sw_tag);
+ /* the itt need to sent in big-endian order */
+ *hdr_itt = (__force itt_t)htonl(tag);
+
+ cxgbi_tag_debug("new sc 0x%p tag 0x%x/0x%x (itt 0x%x, age 0x%x).\n",
+ sc, tag, *hdr_itt, task->itt, sess->age);
+ return 0;
+}
+
+void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt,
+ int *idx, int *age)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ u32 tag = ntohl((__force u32) itt);
+ u32 sw_bits;
+
+ sw_bits = cxgbi_tag_nonrsvd_bits(&cdev->tag_format, tag);
+ if (idx)
+ *idx = sw_bits & ((1 << cconn->task_idx_bits) - 1);
+ if (age)
+ *age = (sw_bits >> cconn->task_idx_bits) & ISCSI_AGE_MASK;
+
+ cxgbi_tag_debug("parse tag 0x%x/0x%x, sw 0x%x, itt 0x%x, age 0x%x.\n",
+ tag, itt, sw_bits, idx ? *idx : 0xFFFFF,
+ age ? *age : 0xFF);
+}
+EXPORT_SYMBOL_GPL(cxgbi_parse_pdu_itt);
+
+void cxgbi_cleanup_task(struct iscsi_task *task)
+{
+ struct cxgbi_task_data *tdata = task->dd_data +
+ sizeof(struct iscsi_tcp_task);
+
+ /* never reached the xmit task callout */
+ if (tdata->skb)
+ __kfree_skb(tdata->skb);
+ memset(tdata, 0, sizeof(*tdata));
+
+ cxgbi_release_itt(task, task->hdr_itt);
+ iscsi_tcp_cleanup_task(task);
+}
+EXPORT_SYMBOL_GPL(cxgbi_cleanup_task);
+
+void cxgbi_get_conn_stats(struct iscsi_cls_conn *cls_conn,
+ struct iscsi_stats *stats)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+
+ stats->txdata_octets = conn->txdata_octets;
+ stats->rxdata_octets = conn->rxdata_octets;
+ stats->scsicmd_pdus = conn->scsicmd_pdus_cnt;
+ stats->dataout_pdus = conn->dataout_pdus_cnt;
+ stats->scsirsp_pdus = conn->scsirsp_pdus_cnt;
+ stats->datain_pdus = conn->datain_pdus_cnt;
+ stats->r2t_pdus = conn->r2t_pdus_cnt;
+ stats->tmfcmd_pdus = conn->tmfcmd_pdus_cnt;
+ stats->tmfrsp_pdus = conn->tmfrsp_pdus_cnt;
+ stats->digest_err = 0;
+ stats->timeout_err = 0;
+ stats->custom_length = 1;
+ strcpy(stats->custom[0].desc, "eh_abort_cnt");
+ stats->custom[0].value = conn->eh_abort_cnt;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_conn_stats);
+
+static int cxgbi_conn_max_xmit_dlength(struct iscsi_conn *conn)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_device *cdev = cconn->chba->cdev;
+ unsigned int skb_tx_headroom = cdev->skb_tx_headroom;
+ unsigned int max_def = 512 * MAX_SKB_FRAGS;
+ unsigned int max = max(max_def, skb_tx_headroom);
+
+ max = min(cconn->chba->cdev->tx_max_size, max);
+ if (conn->max_xmit_dlength)
+ conn->max_xmit_dlength = min(conn->max_xmit_dlength, max);
+ else
+ conn->max_xmit_dlength = max;
+ cxgbi_align_pdu_size(conn->max_xmit_dlength);
+ return 0;
+}
+
+static int cxgbi_conn_max_recv_dlength(struct iscsi_conn *conn)
+{
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ unsigned int max = cconn->chba->cdev->rx_max_size;
+
+ cxgbi_align_pdu_size(max);
+
+ if (conn->max_recv_dlength) {
+ if (conn->max_recv_dlength > max) {
+ cxgbi_log_error("MaxRecvDataSegmentLength %u too big."
+ " Need to be <= %u.\n",
+ conn->max_recv_dlength, max);
+ return -EINVAL;
+ }
+ conn->max_recv_dlength = min(conn->max_recv_dlength, max);
+ cxgbi_align_pdu_size(conn->max_recv_dlength);
+ } else
+ conn->max_recv_dlength = max;
+
+ return 0;
+}
+
+int cxgbi_set_conn_param(struct iscsi_cls_conn *cls_conn,
+ enum iscsi_param param, char *buf, int buflen)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_session *session = conn->session;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct cxgbi_sock *csk = cconn->cep->csk;
+ int value, err = 0;
+
+ switch (param) {
+ case ISCSI_PARAM_HDRDGST_EN:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && conn->hdrdgst_en)
+ err = csk->cdev->ddp_setup_conn_digest(csk, csk->hwtid,
+ conn->hdrdgst_en,
+ conn->datadgst_en, 0);
+ break;
+ case ISCSI_PARAM_DATADGST_EN:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && conn->datadgst_en)
+ err = csk->cdev->ddp_setup_conn_digest(csk, csk->hwtid,
+ conn->hdrdgst_en,
+ conn->datadgst_en, 0);
+ break;
+ case ISCSI_PARAM_MAX_R2T:
+ sscanf(buf, "%d", &value);
+ if (value <= 0 || !is_power_of_2(value))
+ return -EINVAL;
+ if (session->max_r2t == value)
+ break;
+ iscsi_tcp_r2tpool_free(session);
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err && iscsi_tcp_r2tpool_alloc(session))
+ return -ENOMEM;
+ case ISCSI_PARAM_MAX_RECV_DLENGTH:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err)
+ err = cxgbi_conn_max_recv_dlength(conn);
+ break;
+ case ISCSI_PARAM_MAX_XMIT_DLENGTH:
+ err = iscsi_set_param(cls_conn, param, buf, buflen);
+ if (!err)
+ err = cxgbi_conn_max_xmit_dlength(conn);
+ break;
+ default:
+ return iscsi_set_param(cls_conn, param, buf, buflen);
+ }
+ return err;
+}
+EXPORT_SYMBOL_GPL(cxgbi_set_conn_param);
+
+int cxgbi_get_conn_param(struct iscsi_cls_conn *cls_conn,
+ enum iscsi_param param, char *buff)
+{
+ struct iscsi_conn *iconn = cls_conn->dd_data;
+ int len;
+
+ switch (param) {
+ case ISCSI_PARAM_CONN_PORT:
+ spin_lock_bh(&iconn->session->lock);
+ len = sprintf(buff, "%hu\n", iconn->portal_port);
+ spin_unlock_bh(&iconn->session->lock);
+ break;
+ case ISCSI_PARAM_CONN_ADDRESS:
+ spin_lock_bh(&iconn->session->lock);
+ len = sprintf(buff, "%s\n", iconn->portal_address);
+ spin_unlock_bh(&iconn->session->lock);
+ break;
+ default:
+ return iscsi_conn_get_param(cls_conn, param, buff);
+ }
+ return len;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_conn_param);
+
+struct iscsi_cls_conn *
+cxgbi_create_conn(struct iscsi_cls_session *cls_session, u32 cid)
+{
+ struct iscsi_cls_conn *cls_conn;
+ struct iscsi_conn *conn;
+ struct iscsi_tcp_conn *tcp_conn;
+ struct cxgbi_conn *cconn;
+
+ cls_conn = iscsi_tcp_conn_setup(cls_session, sizeof(*cconn), cid);
+ if (!cls_conn)
+ return NULL;
+
+ conn = cls_conn->dd_data;
+ tcp_conn = conn->dd_data;
+ cconn = tcp_conn->dd_data;
+ cconn->iconn = conn;
+ return cls_conn;
+}
+EXPORT_SYMBOL_GPL(cxgbi_create_conn);
+
+int cxgbi_bind_conn(struct iscsi_cls_session *cls_session,
+ struct iscsi_cls_conn *cls_conn,
+ u64 transport_eph, int is_leading)
+{
+ struct iscsi_conn *conn = cls_conn->dd_data;
+ struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+ struct cxgbi_conn *cconn = tcp_conn->dd_data;
+ struct iscsi_endpoint *ep;
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_sock *csk;
+ int err;
+
+ ep = iscsi_lookup_endpoint(transport_eph);
+ if (!ep)
+ return -EINVAL;
+
+ /* setup ddp pagesize */
+ cep = ep->dd_data;
+ csk = cep->csk;
+ err = csk->cdev->ddp_setup_conn_host_pgsz(csk, csk->hwtid, 0);
+ if (err < 0)
+ return err;
+
+ err = iscsi_conn_bind(cls_session, cls_conn, is_leading);
+ if (err)
+ return -EINVAL;
+
+ /* calculate the tag idx bits needed for this conn based on cmds_max */
+ cconn->task_idx_bits = (__ilog2_u32(conn->session->cmds_max - 1)) + 1;
+
+ read_lock(&csk->callback_lock);
+ csk->user_data = conn;
+ cconn->chba = cep->chba;
+ cconn->cep = cep;
+ cep->cconn = cconn;
+ read_unlock(&csk->callback_lock);
+
+ cxgbi_conn_max_xmit_dlength(conn);
+ cxgbi_conn_max_recv_dlength(conn);
+
+ spin_lock_bh(&conn->session->lock);
+ sprintf(conn->portal_address, "%pI4", &csk->daddr.sin_addr.s_addr);
+ conn->portal_port = ntohs(csk->daddr.sin_port);
+ spin_unlock_bh(&conn->session->lock);
+
+ /* init recv engine */
+ iscsi_tcp_hdr_recv_prep(tcp_conn);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(cxgbi_bind_conn);
+
+struct iscsi_cls_session *
+cxgbi_create_session(struct iscsi_endpoint *ep, u16 cmds_max, u16 qdepth,
+ u32 initial_cmdsn)
+{
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_hba *chba;
+ struct Scsi_Host *shost;
+ struct iscsi_cls_session *cls_session;
+ struct iscsi_session *session;
+
+ if (!ep) {
+ cxgbi_log_error("missing endpoint\n");
+ return NULL;
+ }
+
+ cep = ep->dd_data;
+ chba = cep->chba;
+ shost = chba->shost;
+
+ BUG_ON(chba != iscsi_host_priv(shost));
+
+ cls_session = iscsi_session_setup(chba->cdev->itp, shost,
+ cmds_max, 0,
+ sizeof(struct iscsi_tcp_task) +
+ sizeof(struct cxgbi_task_data),
+ initial_cmdsn, ISCSI_MAX_TARGET);
+ if (!cls_session)
+ return NULL;
+
+ session = cls_session->dd_data;
+ if (iscsi_tcp_r2tpool_alloc(session))
+ goto remove_session;
+
+ return cls_session;
+
+remove_session:
+ iscsi_session_teardown(cls_session);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_create_session);
+
+void cxgbi_destroy_session(struct iscsi_cls_session *cls_session)
+{
+ iscsi_tcp_r2tpool_free(cls_session->dd_data);
+ iscsi_session_teardown(cls_session);
+}
+EXPORT_SYMBOL_GPL(cxgbi_destroy_session);
+
+int cxgbi_set_host_param(struct Scsi_Host *shost,
+ enum iscsi_host_param param, char *buff, int buflen)
+{
+ struct cxgbi_hba *chba = iscsi_host_priv(shost);
+
+ if (!chba->ndev) {
+ shost_printk(KERN_ERR, shost, "Could not set host param. "
+ "Netdev for host not set\n");
+ return -ENODEV;
+ }
+
+ cxgbi_api_debug("param %d, buff %s\n", param, buff);
+
+ switch (param) {
+ case ISCSI_HOST_PARAM_IPADDRESS:
+ {
+ __be32 addr = in_aton(buff);
+ cxgbi_set_iscsi_ipv4(chba, addr);
+ return 0;
+ }
+ case ISCSI_HOST_PARAM_HWADDRESS:
+ case ISCSI_HOST_PARAM_NETDEV_NAME:
+ return 0;
+ default:
+ return iscsi_host_set_param(shost, param, buff, buflen);
+ }
+}
+EXPORT_SYMBOL_GPL(cxgbi_set_host_param);
+
+int cxgbi_get_host_param(struct Scsi_Host *shost,
+ enum iscsi_host_param param, char *buff)
+{
+ struct cxgbi_hba *chba = iscsi_host_priv(shost);
+ int len = 0;
+
+ if (!chba->ndev) {
+ shost_printk(KERN_ERR, shost, "Could not set host param. "
+ "Netdev for host not set\n");
+ return -ENODEV;
+ }
+
+ cxgbi_api_debug("hba %s, param %d\n", chba->ndev->name, param);
+
+ switch (param) {
+ case ISCSI_HOST_PARAM_HWADDRESS:
+ len = sysfs_format_mac(buff, chba->ndev->dev_addr, 6);
+ break;
+ case ISCSI_HOST_PARAM_NETDEV_NAME:
+ len = sprintf(buff, "%s\n", chba->ndev->name);
+ break;
+ case ISCSI_HOST_PARAM_IPADDRESS:
+ {
+ __be32 addr;
+
+ addr = cxgbi_get_iscsi_ipv4(chba);
+ len = sprintf(buff, "%pI4", &addr);
+ break;
+ }
+ default:
+ return iscsi_host_get_param(shost, param, buff);
+ }
+
+ return len;
+}
+EXPORT_SYMBOL_GPL(cxgbi_get_host_param);
+
+struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *shost,
+ struct sockaddr *dst_addr,
+ int non_blocking)
+{
+ struct iscsi_endpoint *iep;
+ struct cxgbi_endpoint *cep;
+ struct cxgbi_hba *hba = NULL;
+ struct cxgbi_sock *csk = NULL;
+ struct sockaddr_in *sin = (struct sockaddr_in *)dst_addr;
+ struct cxgbi_device *cdev;
+ int err = 0;
+
+ if (shost)
+ hba = iscsi_host_priv(shost);
+
+ cdev = cxgbi_find_cdev(hba ? hba->ndev : NULL,
+ ((struct sockaddr_in *)dst_addr)->sin_addr.s_addr);
+ if (!cdev) {
+ cxgbi_log_info("ep connect no cdev\n");
+ err = -ENOSPC;
+ goto release_conn;
+ }
+
+ csk = cxgbi_sock_create(cdev);
+ if (!csk) {
+ cxgbi_log_info("ep connect OOM\n");
+ err = -ENOMEM;
+ goto release_conn;
+ }
+
+ err = cxgbi_sock_connect(hba ? hba->ndev : NULL, csk, sin);
+ if (err < 0) {
+ cxgbi_log_info("ep connect failed\n");
+ goto release_conn;
+ }
+
+ hba = cxgbi_hba_find_by_netdev(csk->dst->dev, cdev);
+ if (!hba) {
+ err = -ENOSPC;
+ cxgbi_log_info("Not going through cxgb4i device\n");
+ goto release_conn;
+ }
+
+ if (shost && hba != iscsi_host_priv(shost)) {
+ err = -ENOSPC;
+ cxgbi_log_info("Could not connect through request host %u\n",
+ shost->host_no);
+ goto release_conn;
+ }
+
+ if (cxgbi_sock_is_closing(csk)) {
+ err = -ENOSPC;
+ cxgbi_log_info("ep connect unable to connect\n");
+ goto release_conn;
+ }
+
+ iep = iscsi_create_endpoint(sizeof(*cep));
+ if (!iep) {
+ err = -ENOMEM;
+ cxgbi_log_info("iscsi alloc ep, OOM\n");
+ goto release_conn;
+ }
+
+ cep = iep->dd_data;
+ cep->csk = csk;
+ cep->chba = hba;
+ cxgbi_api_debug("iep 0x%p, cep 0x%p, csk 0x%p, hba 0x%p\n",
+ iep, cep, csk, hba);
+ return iep;
+release_conn:
+ cxgbi_api_debug("conn 0x%p failed, release\n", csk);
+ if (csk)
+ cxgbi_sock_release(csk);
+
+ return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_connect);
+
+int cxgbi_ep_poll(struct iscsi_endpoint *ep, int timeout_ms)
+{
+ struct cxgbi_endpoint *cep = ep->dd_data;
+ struct cxgbi_sock *csk = cep->csk;
+
+ if (!cxgbi_sock_is_established(csk))
+ return 0;
+
+ return 1;
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_poll);
+
+void cxgbi_ep_disconnect(struct iscsi_endpoint *ep)
+{
+ struct cxgbi_endpoint *cep = ep->dd_data;
+ struct cxgbi_conn *cconn = cep->cconn;
+
+ if (cconn && cconn->iconn) {
+ iscsi_suspend_tx(cconn->iconn);
+ write_lock_bh(&cep->csk->callback_lock);
+ cep->csk->user_data = NULL;
+ cconn->cep = NULL;
+ write_unlock_bh(&cep->csk->callback_lock);
+ }
+
+ cxgbi_sock_release(cep->csk);
+ iscsi_destroy_endpoint(ep);
+}
+EXPORT_SYMBOL_GPL(cxgbi_ep_disconnect);
+
+struct cxgbi_hba *cxgbi_hba_add(struct cxgbi_device *cdev,
+ unsigned int max_lun,
+ unsigned int max_id,
+ struct scsi_transport_template *stt,
+ struct scsi_host_template *sht,
+ struct net_device *dev)
+{
+ struct cxgbi_hba *chba;
+ struct Scsi_Host *shost;
+ int err;
+
+ shost = iscsi_host_alloc(sht, sizeof(*chba), 1);
+
+ if (!shost) {
+ cxgbi_log_info("cdev 0x%p, ndev 0x%p, host alloc failed\n",
+ cdev, dev);
+ return NULL;
+ }
+
+ shost->transportt = stt;
+ shost->max_lun = max_lun;
+ shost->max_id = max_id;
+ shost->max_channel = 0;
+ shost->max_cmd_len = 16;
+ chba = iscsi_host_priv(shost);
+ cxgbi_log_debug("cdev %p\n", cdev);
+ chba->cdev = cdev;
+ chba->ndev = dev;
+ chba->shost = shost;
+ pci_dev_get(cdev->pdev);
+ err = iscsi_host_add(shost, &cdev->pdev->dev);
+ if (err) {
+ cxgbi_log_info("cdev 0x%p, dev 0x%p, host add failed\n",
+ cdev, dev);
+ goto pci_dev_put;
+ }
+
+ return chba;
+pci_dev_put:
+ pci_dev_put(cdev->pdev);
+ scsi_host_put(shost);
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(cxgbi_hba_add);
+
+void cxgbi_hba_remove(struct cxgbi_hba *chba)
+{
+ iscsi_host_remove(chba->shost);
+ pci_dev_put(chba->cdev->pdev);
+ iscsi_host_free(chba->shost);
+}
+EXPORT_SYMBOL_GPL(cxgbi_hba_remove);
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
new file mode 100644
index 0000000..4e1aa61
--- /dev/null
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -0,0 +1,556 @@
+/*
+ * libcxgbi.h: Chelsio common library for T3/T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#ifndef __LIBCXGBI_H__
+#define __LIBCXGBI_H__
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+#include <scsi/libiscsi_tcp.h>
+
+
+#define cxgbi_log_error(fmt...) printk(KERN_ERR "cxgbi: ERR! " fmt)
+#define cxgbi_log_warn(fmt...) printk(KERN_WARNING "cxgbi: WARN! " fmt)
+#define cxgbi_log_info(fmt...) printk(KERN_INFO "cxgbi: " fmt)
+#define cxgbi_debug_log(fmt, args...) \
+ printk(KERN_INFO "cxgbi: %s - " fmt, __func__ , ## args)
+
+#ifdef __DEBUG_CXGBI__
+#define cxgbi_log_debug cxgbi_debug_log
+#else
+#define cxgbi_log_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_TAG__
+#define cxgbi_tag_debug cxgbi_log_debug
+#else
+#define cxgbi_tag_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_API__
+#define cxgbi_api_debug cxgbi_log_debug
+#else
+#define cxgbi_api_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_CONN__
+#define cxgbi_conn_debug cxgbi_log_debug
+#else
+#define cxgbi_conn_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_TX__
+#define cxgbi_tx_debug cxgbi_log_debug
+#else
+#define cxgbi_tx_debug(fmt...)
+#endif
+
+#ifdef __DEBUG_CXGBI_RX__
+#define cxgbi_rx_debug cxgbi_log_debug
+#else
+#define cxgbi_rx_debug(fmt...)
+#endif
+
+/* always allocate rooms for AHS */
+#define SKB_TX_PDU_HEADER_LEN \
+ (sizeof(struct iscsi_hdr) + ISCSI_MAX_AHS_SIZE)
+
+#define ISCSI_PDU_NONPAYLOAD_LEN 312 /* bhs(48) + ahs(256) + digest(8)*/
+#define ULP2_MAX_PKT_SIZE 16224
+#define ULP2_MAX_PDU_PAYLOAD \
+ (ULP2_MAX_PKT_SIZE - ISCSI_PDU_NONPAYLOAD_LEN)
+
+#define PPOD_PAGES_MAX 4
+#define PPOD_PAGES_SHIFT 2 /* 4 pages per pod */
+
+/*
+ * align pdu size to multiple of 512 for better performance
+ */
+#define cxgbi_align_pdu_size(n) do { n = (n) & (~511); } while (0)
+
+/*
+ * struct pagepod_hdr, pagepod - pagepod format
+ */
+struct pagepod_hdr {
+ unsigned int vld_tid;
+ unsigned int pgsz_tag_clr;
+ unsigned int max_offset;
+ unsigned int page_offset;
+ unsigned long long rsvd;
+};
+
+struct pagepod {
+ struct pagepod_hdr hdr;
+ unsigned long long addr[PPOD_PAGES_MAX + 1];
+};
+
+struct cxgbi_tag_format {
+ unsigned char sw_bits;
+ unsigned char rsvd_bits;
+ unsigned char rsvd_shift;
+ unsigned char filler[1];
+ unsigned int rsvd_mask;
+};
+
+struct cxgbi_gather_list {
+ unsigned int tag;
+ unsigned int length;
+ unsigned int offset;
+ unsigned int nelem;
+ struct page **pages;
+ dma_addr_t phys_addr[0];
+};
+
+/*
+ * sge_opaque_hdr -
+ * Opaque version of structure the SGE stores at skb->head of TX_DATA packets
+ * and for which we must reserve space.
+ */
+struct sge_opaque_hdr {
+ void *dev;
+ dma_addr_t addr[MAX_SKB_FRAGS + 1];
+};
+
+struct cxgbi_sock {
+ struct cxgbi_device *cdev;
+
+ unsigned long flags;
+ unsigned short rss_qid;
+ unsigned short txq_idx;
+ unsigned int hwtid;
+ unsigned int atid;
+ unsigned int tx_chan;
+ unsigned int rx_chan;
+ unsigned int mss_idx;
+ unsigned int smac_idx;
+ unsigned char port_id;
+ int wr_max_cred;
+ int wr_cred;
+ int wr_una_cred;
+ unsigned char hcrc_len;
+ unsigned char dcrc_len;
+
+ void *l2t;
+ struct sk_buff *wr_pending_head;
+ struct sk_buff *wr_pending_tail;
+ struct sk_buff *cpl_close;
+ struct sk_buff *cpl_abort_req;
+ struct sk_buff *cpl_abort_rpl;
+ struct sk_buff *skb_ulp_lhdr;
+ spinlock_t lock;
+ struct kref refcnt;
+ unsigned int state;
+ struct sockaddr_in saddr;
+ struct sockaddr_in daddr;
+ struct dst_entry *dst;
+ struct sk_buff_head receive_queue;
+ struct sk_buff_head write_queue;
+ struct timer_list retry_timer;
+ int err;
+ rwlock_t callback_lock;
+ void *user_data;
+
+ u32 rcv_nxt;
+ u32 copied_seq;
+ u32 rcv_wup;
+ u32 snd_nxt;
+ u32 snd_una;
+ u32 write_seq;
+};
+
+enum cxgbi_sock_states{
+ CTP_CONNECTING = 1,
+ CTP_ESTABLISHED,
+ CTP_ACTIVE_CLOSE,
+ CTP_PASSIVE_CLOSE,
+ CTP_CLOSE_WAIT_1,
+ CTP_CLOSE_WAIT_2,
+ CTP_ABORTING,
+ CTP_CLOSED,
+};
+
+enum cxgbi_sock_flags {
+ CTPF_ABORT_RPL_RCVD = 1,/*received one ABORT_RPL_RSS message */
+ CTPF_ABORT_REQ_RCVD, /*received one ABORT_REQ_RSS message */
+ CTPF_ABORT_RPL_PENDING, /* expecting an abort reply */
+ CTPF_TX_DATA_SENT, /* already sent a TX_DATA WR */
+ CTPF_ACTIVE_CLOSE_NEEDED, /* need to be closed */
+ CTPF_MSG_COALESCED,
+ CTPF_OFFLOAD_DOWN, /* offload function off */
+};
+
+enum cxgbi_skcb_flags {
+ CTP_SKCBF_NEED_HDR = 1 << 0, /* packet needs a header */
+ CTP_SKCBF_NO_APPEND = 1 << 1, /* don't grow this skb */
+ CTP_SKCBF_COMPL = 1 << 2, /* request WR completion */
+ CTP_SKCBF_HDR_RCVD = 1 << 3, /* recieved header pdu */
+ CTP_SKCBF_DATA_RCVD = 1 << 4, /* recieved data pdu */
+ CTP_SKCBF_STATUS_RCVD = 1 << 5, /* recieved ddp status */
+};
+
+static inline void cxgbi_sock_set_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ __set_bit(flag, &csk->flags);
+ cxgbi_conn_debug("csk 0x%p, set %d, state %u, flags 0x%lu\n",
+ csk, flag, csk->state, csk->flags);
+}
+
+static inline void cxgbi_sock_clear_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ __clear_bit(flag, &csk->flags);
+ cxgbi_conn_debug("csk 0x%p, clear %d, state %u, flags 0x%lu\n",
+ csk, flag, csk->state, csk->flags);
+}
+
+static inline int cxgbi_sock_flag(struct cxgbi_sock *csk,
+ enum cxgbi_sock_flags flag)
+{
+ if (csk == NULL)
+ return 0;
+
+ return test_bit(flag, &csk->flags);
+}
+
+static inline void cxgbi_sock_set_state(struct cxgbi_sock *csk, int state)
+{
+ csk->state = state;
+}
+
+static inline void cxgbi_sock_hold(struct cxgbi_sock *csk)
+{
+ kref_get(&csk->refcnt);
+}
+
+static inline void cxgbi_clean_sock(struct kref *kref)
+{
+ struct cxgbi_sock *csk = container_of(kref,
+ struct cxgbi_sock,
+ refcnt);
+ if (csk) {
+ cxgbi_log_debug("free csk 0x%p, state %u, flags 0x%lx\n",
+ csk, csk->state, csk->flags);
+ kfree(csk);
+ }
+}
+
+static inline void cxgbi_sock_put(struct cxgbi_sock *csk)
+{
+ if (csk)
+ kref_put(&csk->refcnt, cxgbi_clean_sock);
+}
+
+static inline unsigned int cxgbi_sock_is_closing(const struct cxgbi_sock *csk)
+{
+ return csk->state >= CTP_ACTIVE_CLOSE;
+}
+
+static inline unsigned int cxgbi_sock_is_established(
+ const struct cxgbi_sock *csk)
+{
+ return csk->state == CTP_ESTABLISHED;
+}
+
+static inline void cxgbi_sock_purge_write_queue(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+
+ while ((skb = __skb_dequeue(&csk->write_queue)))
+ __kfree_skb(skb);
+}
+
+static inline int cxgbi_sock_compute_wscale(int win)
+{
+ int wscale = 0;
+ while (wscale < 14 && (65535 << wscale) < win)
+ wscale++;
+ return wscale;
+}
+
+void cxgbi_sock_conn_closing(struct cxgbi_sock *);
+void cxgbi_sock_closed(struct cxgbi_sock *);
+unsigned int cxgbi_sock_select_mss(struct cxgbi_sock *, unsigned int);
+
+struct cxgbi_hba {
+ struct net_device *ndev;
+ struct Scsi_Host *shost;
+ struct cxgbi_device *cdev;
+ __be32 ipv4addr;
+ unsigned short txq_idx;
+ unsigned char port_id;
+};
+
+struct cxgbi_ports_map {
+ unsigned int max_connect;
+ unsigned short sport_base;
+ spinlock_t lock;
+ unsigned int next;
+ struct cxgbi_sock *port_csk[0];
+};
+
+struct cxgbi_device {
+ struct list_head list_head;
+ char *name;
+ struct net_device **ports;
+ struct cxgbi_hba **hbas;
+ const unsigned short *mtus;
+ unsigned char nmtus;
+ unsigned char nports;
+ struct pci_dev *pdev;
+
+ unsigned int skb_tx_headroom;
+ unsigned int skb_extra_headroom;
+ unsigned int tx_max_size;
+ unsigned int rx_max_size;
+ struct page *pad_page;
+ struct cxgbi_ports_map *pmap;
+ struct iscsi_transport *itp;
+ struct cxgbi_tag_format tag_format;
+
+ int (*ddp_tag_reserve)(struct cxgbi_hba *, unsigned int,
+ struct cxgbi_tag_format *, u32 *,
+ struct cxgbi_gather_list *, gfp_t);
+ void (*ddp_tag_release)(struct cxgbi_hba *, u32);
+ struct cxgbi_gather_list* (*ddp_make_gl)(unsigned int,
+ struct scatterlist *,
+ unsigned int,
+ struct pci_dev *,
+ gfp_t);
+ void (*ddp_release_gl)(struct cxgbi_gather_list *, struct pci_dev *);
+ int (*ddp_setup_conn_digest)(struct cxgbi_sock *,
+ unsigned int, int, int, int);
+ int (*ddp_setup_conn_host_pgsz)(struct cxgbi_sock *,
+ unsigned int, int);
+ __u16 (*get_skb_ulp_mode)(struct sk_buff *);
+ __u16 (*get_skb_flags)(struct sk_buff *);
+ __u32 (*get_skb_tcp_seq)(struct sk_buff *);
+ __u32 (*get_skb_rx_pdulen)(struct sk_buff *);
+ void (*set_skb_txmode)(struct sk_buff *, int, int);
+
+ void (*release_offload_resources)(struct cxgbi_sock *);
+ int (*sock_send_pdus)(struct cxgbi_sock *, struct sk_buff *);
+ void (*sock_rx_credits)(struct cxgbi_sock *, int);
+ void (*send_abort_req)(struct cxgbi_sock *);
+ void (*send_close_req)(struct cxgbi_sock *);
+ int (*alloc_cpl_skbs)(struct cxgbi_sock *);
+ int (*init_act_open)(struct cxgbi_sock *, struct net_device *);
+
+ unsigned long dd_data[0];
+};
+
+static inline void *cxgbi_cdev_priv(struct cxgbi_device *cdev)
+{
+ return (void *)cdev->dd_data;
+}
+
+struct cxgbi_device *cxgbi_device_register(unsigned int, unsigned int);
+void cxgbi_device_unregister(struct cxgbi_device *);
+
+struct cxgbi_conn {
+ struct cxgbi_endpoint *cep;
+ struct iscsi_conn *iconn;
+ struct cxgbi_hba *chba;
+ u32 task_idx_bits;
+};
+
+struct cxgbi_endpoint {
+ struct cxgbi_conn *cconn;
+ struct cxgbi_hba *chba;
+ struct cxgbi_sock *csk;
+};
+
+#define MAX_PDU_FRAGS ((ULP2_MAX_PDU_PAYLOAD + 512 - 1) / 512)
+struct cxgbi_task_data {
+ unsigned short nr_frags;
+ skb_frag_t frags[MAX_PDU_FRAGS];
+ struct sk_buff *skb;
+ unsigned int offset;
+ unsigned int count;
+ unsigned int sgoffset;
+};
+
+static inline int cxgbi_is_ddp_tag(struct cxgbi_tag_format *tformat, u32 tag)
+{
+ return !(tag & (1 << (tformat->rsvd_bits + tformat->rsvd_shift - 1)));
+}
+
+static inline int cxgbi_sw_tag_usable(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ sw_tag >>= (32 - tformat->rsvd_bits);
+ return !sw_tag;
+}
+
+static inline u32 cxgbi_set_non_ddp_tag(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+
+ u32 mask = (1 << shift) - 1;
+
+ if (sw_tag && (sw_tag & ~mask)) {
+ u32 v1 = sw_tag & ((1 << shift) - 1);
+ u32 v2 = (sw_tag >> (shift - 1)) << shift;
+
+ return v2 | v1 | 1 << shift;
+ }
+
+ return sw_tag | 1 << shift;
+}
+
+static inline u32 cxgbi_ddp_tag_base(struct cxgbi_tag_format *tformat,
+ u32 sw_tag)
+{
+ u32 mask = (1 << tformat->rsvd_shift) - 1;
+
+ if (sw_tag && (sw_tag & ~mask)) {
+ u32 v1 = sw_tag & mask;
+ u32 v2 = sw_tag >> tformat->rsvd_shift;
+
+ v2 <<= tformat->rsvd_bits + tformat->rsvd_shift;
+
+ return v2 | v1;
+ }
+
+ return sw_tag;
+}
+
+static inline u32 cxgbi_tag_rsvd_bits(struct cxgbi_tag_format *tformat,
+ u32 tag)
+{
+ if (cxgbi_is_ddp_tag(tformat, tag))
+ return (tag >> tformat->rsvd_shift) & tformat->rsvd_mask;
+
+ return 0;
+}
+
+static inline u32 cxgbi_tag_nonrsvd_bits(struct cxgbi_tag_format *tformat,
+ u32 tag)
+{
+ unsigned char shift = tformat->rsvd_bits + tformat->rsvd_shift - 1;
+ u32 v1, v2;
+
+ if (cxgbi_is_ddp_tag(tformat, tag)) {
+ v1 = tag & ((1 << tformat->rsvd_shift) - 1);
+ v2 = (tag >> (shift + 1)) << tformat->rsvd_shift;
+ } else {
+ u32 mask = (1 << shift) - 1;
+ tag &= ~(1 << shift);
+ v1 = tag & mask;
+ v2 = (tag >> 1) & ~mask;
+ }
+ return v1 | v2;
+}
+
+static inline void *cxgbi_alloc_big_mem(unsigned int size,
+ gfp_t gfp)
+{
+ void *p = kmalloc(size, gfp);
+ if (!p)
+ p = vmalloc(size);
+ if (p)
+ memset(p, 0, size);
+ return p;
+}
+
+static inline void cxgbi_free_big_mem(void *addr)
+{
+ if (is_vmalloc_addr(addr))
+ vfree(addr);
+ else
+ kfree(addr);
+}
+
+#define RX_DDP_STATUS_IPP_SHIFT 27 /* invalid pagepod */
+#define RX_DDP_STATUS_TID_SHIFT 26 /* tid mismatch */
+#define RX_DDP_STATUS_COLOR_SHIFT 25 /* color mismatch */
+#define RX_DDP_STATUS_OFFSET_SHIFT 24 /* offset mismatch */
+#define RX_DDP_STATUS_ULIMIT_SHIFT 23 /* ulimit error */
+#define RX_DDP_STATUS_TAG_SHIFT 22 /* tag mismatch */
+#define RX_DDP_STATUS_DCRC_SHIFT 21 /* dcrc error */
+#define RX_DDP_STATUS_HCRC_SHIFT 20 /* hcrc error */
+#define RX_DDP_STATUS_PAD_SHIFT 19 /* pad error */
+#define RX_DDP_STATUS_PPP_SHIFT 18 /* pagepod parity error */
+#define RX_DDP_STATUS_LLIMIT_SHIFT 17 /* llimit error */
+#define RX_DDP_STATUS_DDP_SHIFT 16 /* ddp'able */
+#define RX_DDP_STATUS_PMM_SHIFT 15 /* pagepod mismatch */
+
+
+#define ULP2_FLAG_DATA_READY 0x1
+#define ULP2_FLAG_DATA_DDPED 0x2
+#define ULP2_FLAG_HCRC_ERROR 0x4
+#define ULP2_FLAG_DCRC_ERROR 0x8
+#define ULP2_FLAG_PAD_ERROR 0x10
+
+struct cxgbi_hba *cxgbi_hba_add(struct cxgbi_device *,
+ unsigned int, unsigned int,
+ struct scsi_transport_template *,
+ struct scsi_host_template *,
+ struct net_device *);
+void cxgbi_hba_remove(struct cxgbi_hba *);
+
+
+void cxgbi_parse_pdu_itt(struct iscsi_conn *conn, itt_t itt,
+ int *idx, int *age);
+void cxgbi_cleanup_task(struct iscsi_task *task);
+
+void cxgbi_conn_pdu_ready(struct cxgbi_sock *);
+void cxgbi_conn_tx_open(struct cxgbi_sock *);
+int cxgbi_conn_init_pdu(struct iscsi_task *, unsigned int , unsigned int);
+int cxgbi_conn_alloc_pdu(struct iscsi_task *, u8);
+int cxgbi_conn_xmit_pdu(struct iscsi_task *);
+void cxgbi_get_conn_stats(struct iscsi_cls_conn *, struct iscsi_stats *);
+int cxgbi_set_conn_param(struct iscsi_cls_conn *,
+ enum iscsi_param, char *, int);
+int cxgbi_get_conn_param(struct iscsi_cls_conn *, enum iscsi_param, char *);
+struct iscsi_cls_conn *cxgbi_create_conn(struct iscsi_cls_session *, u32);
+int cxgbi_bind_conn(struct iscsi_cls_session *,
+ struct iscsi_cls_conn *, u64, int);
+void cxgbi_destroy_session(struct iscsi_cls_session *);
+struct iscsi_cls_session *cxgbi_create_session(struct iscsi_endpoint *,
+ u16, u16, u32);
+int cxgbi_set_host_param(struct Scsi_Host *,
+ enum iscsi_host_param, char *, int);
+int cxgbi_get_host_param(struct Scsi_Host *, enum iscsi_host_param, char *);
+
+
+int cxgbi_pdu_init(struct cxgbi_device *);
+void cxgbi_pdu_cleanup(struct cxgbi_device *);
+
+struct iscsi_endpoint *cxgbi_ep_connect(struct Scsi_Host *,
+ struct sockaddr *, int);
+int cxgbi_ep_poll(struct iscsi_endpoint *, int);
+void cxgbi_ep_disconnect(struct iscsi_endpoint *);
+
+static inline void cxgbi_set_iscsi_ipv4(struct cxgbi_hba *chba, __be32 ipaddr)
+{
+ chba->ipv4addr = ipaddr;
+}
+
+static inline __be32 cxgbi_get_iscsi_ipv4(struct cxgbi_hba *chba)
+{
+ return chba->ipv4addr;
+}
+
+struct cxgbi_device *cxgbi_device_alloc(unsigned int dd_size);
+void cxgbi_device_free(struct cxgbi_device *cdev);
+void cxgbi_device_add(struct list_head *list_head);
+void cxgbi_device_remove(struct cxgbi_device *cdev);
+
+#endif /*__LIBCXGBI_H__*/
--
1.6.6.1
--
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To unsubscribe from this group, send email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
^ permalink raw reply related
* [PATCH 3/3] cxgb4i_v4.3 : main driver files
From: Rakesh Ranjan @ 2010-06-08 4:59 UTC (permalink / raw)
To: LK-NetDev, LK-SCSIDev, LK-iSCSIDev
Cc: LKML, Karen Xie, David Miller, James Bottomley, Mike Christie,
Anish Bhatt, Rakesh Ranjan
In-Reply-To: <1275973167-8640-3-git-send-email-rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
From: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
Signed-off-by: Rakesh Ranjan <rakesh-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org>
---
drivers/scsi/cxgbi/cxgb4i.h | 175 +++++
drivers/scsi/cxgbi/cxgb4i_ddp.c | 653 ++++++++++++++++
drivers/scsi/cxgbi/cxgb4i_init.c | 317 ++++++++
drivers/scsi/cxgbi/cxgb4i_offload.c | 1409 +++++++++++++++++++++++++++++++++++
4 files changed, 2554 insertions(+), 0 deletions(-)
create mode 100644 drivers/scsi/cxgbi/cxgb4i.h
create mode 100644 drivers/scsi/cxgbi/cxgb4i_ddp.c
create mode 100644 drivers/scsi/cxgbi/cxgb4i_init.c
create mode 100644 drivers/scsi/cxgbi/cxgb4i_offload.c
diff --git a/drivers/scsi/cxgbi/cxgb4i.h b/drivers/scsi/cxgbi/cxgb4i.h
new file mode 100644
index 0000000..41b0a25
--- /dev/null
+++ b/drivers/scsi/cxgbi/cxgb4i.h
@@ -0,0 +1,175 @@
+/*
+ * cxgb4i.h: Chelsio T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#ifndef __CXGB4I_H__
+#define __CXGB4I_H__
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/scatterlist.h>
+#include <linux/skbuff.h>
+#include <scsi/libiscsi_tcp.h>
+
+#include "t4fw_api.h"
+#include "t4_msg.h"
+#include "l2t.h"
+#include "cxgb4.h"
+#include "cxgb4_uld.h"
+#include "libcxgbi.h"
+
+#define CXGB4I_MAX_CONN 16384
+#define CXGB4I_SCSI_HOST_QDEPTH 1024
+#define CXGB4I_MAX_TARGET CXGB4I_MAX_CONN
+#define CXGB4I_MAX_LUN 0x1000
+
+struct cxgb4i_snic;
+typedef int (*cxgb4i_cplhandler_func)(struct cxgb4i_snic *, struct sk_buff *);
+
+struct cxgb4i_snic {
+ struct cxgb4_lld_info lldi;
+ struct cxgb4i_ddp_info *ddp;
+ cxgb4i_cplhandler_func *handlers;
+};
+
+enum {
+ CPL_RET_BUF_DONE = 1,
+ CPL_RET_BAD_MSG = 2,
+ CPL_RET_UNKNOWN_TID = 4
+};
+
+struct cxgb4i_skb_rx_cb {
+ __u32 ddigest;
+ __u32 pdulen;
+};
+
+struct cxgb4i_skb_tx_cb {
+ struct l2t_skb_cb l2t;
+ struct sk_buff *wr_next;
+};
+
+struct cxgb4i_skb_cb {
+ __u16 flags;
+ __u16 ulp_mode;
+ __u32 seq;
+
+ union {
+ struct cxgb4i_skb_rx_cb rx;
+ struct cxgb4i_skb_tx_cb tx;
+ };
+};
+
+#define CXGB4I_SKB_CB(skb) ((struct cxgb4i_skb_cb *)&((skb)->cb[0]))
+#define cxgb4i_skb_flags(skb) (CXGB4I_SKB_CB(skb)->flags)
+#define cxgb4i_skb_ulp_mode(skb) (CXGB4I_SKB_CB(skb)->ulp_mode)
+#define cxgb4i_skb_tcp_seq(skb) (CXGB4I_SKB_CB(skb)->seq)
+#define cxgb4i_skb_rx_ddigest(skb) (CXGB4I_SKB_CB(skb)->rx.ddigest)
+#define cxgb4i_skb_rx_pdulen(skb) (CXGB4I_SKB_CB(skb)->rx.pdulen)
+#define cxgb4i_skb_tx_wr_next(skb) (CXGB4I_SKB_CB(skb)->tx.wr_next)
+
+/* for TX: a skb must have a headroom of at least TX_HEADER_LEN bytes */
+#define CXGB4I_TX_HEADER_LEN \
+ (sizeof(struct fw_ofld_tx_data_wr) + sizeof(struct sge_opaque_hdr))
+
+int cxgb4i_ofld_init(struct cxgbi_device *);
+void cxgb4i_ofld_cleanup(struct cxgbi_device *);
+
+struct cxgb4i_ddp_info {
+ struct kref refcnt;
+ struct cxgb4i_snic *snic;
+ struct pci_dev *pdev;
+ unsigned int max_txsz;
+ unsigned int max_rxsz;
+ unsigned int llimit;
+ unsigned int ulimit;
+ unsigned int nppods;
+ unsigned int idx_last;
+ unsigned char idx_bits;
+ unsigned char filler[3];
+ unsigned int idx_mask;
+ unsigned int rsvd_tag_mask;
+ spinlock_t map_lock;
+ struct cxgbi_gather_list **gl_map;
+};
+
+struct cpl_rx_data_ddp {
+ union opcode_tid ot;
+ __be16 urg;
+ __be16 len;
+ __be32 seq;
+ union {
+ __be32 nxt_seq;
+ __be32 ddp_report;
+ };
+ __be32 ulp_crc;
+ __be32 ddpvld;
+};
+
+#define PPOD_SIZE sizeof(struct pagepod) /* 64 */
+#define PPOD_SIZE_SHIFT 6
+
+#define ULPMEM_DSGL_MAX_NPPODS 16 /* 1024/PPOD_SIZE */
+#define ULPMEM_IDATA_MAX_NPPODS 4 /* 256/PPOD_SIZE */
+#define PCIE_MEMWIN_MAX_NPPODS 16 /* 1024/PPOD_SIZE */
+
+#define PPOD_COLOR_SHIFT 0
+#define PPOD_COLOR_MASK 0x3F
+#define PPOD_COLOR_SIZE 6
+#define PPOD_COLOR(x) ((x) << PPOD_COLOR_SHIFT)
+
+#define PPOD_TAG_SHIFT 6
+#define PPOD_TAG_MASK 0xFFFFFF
+#define PPOD_TAG(x) ((x) << PPOD_TAG_SHIFT)
+
+#define PPOD_PGSZ_SHIFT 30
+#define PPOD_PGSZ_MASK 0x3
+#define PPOD_PGSZ(x) ((x) << PPOD_PGSZ_SHIFT)
+
+#define PPOD_TID_SHIFT 32
+#define PPOD_TID_MASK 0xFFFFFF
+#define PPOD_TID(x) ((__u64)(x) << PPOD_TID_SHIFT)
+
+#define PPOD_VALID_SHIFT 56
+#define PPOD_VALID(x) ((__u64)(x) << PPOD_VALID_SHIFT)
+#define PPOD_VALID_FLAG PPOD_VALID(1ULL)
+
+#define PPOD_LEN_SHIFT 32
+#define PPOD_LEN_MASK 0xFFFFFFFF
+#define PPOD_LEN(x) ((__u64)(x) << PPOD_LEN_SHIFT)
+
+#define PPOD_OFST_SHIFT 0
+#define PPOD_OFST_MASK 0xFFFFFFFF
+#define PPOD_OFST(x) ((x) << PPOD_OFST_SHIFT)
+
+#define PPOD_IDX_SHIFT PPOD_COLOR_SIZE
+#define PPOD_IDX_MAX_SIZE 24
+
+#define W_TCB_ULP_TYPE 0
+#define TCB_ULP_TYPE_SHIFT 0
+#define TCB_ULP_TYPE_MASK 0xfULL
+#define TCB_ULP_TYPE(x) ((x) << TCB_ULP_TYPE_SHIFT)
+
+#define W_TCB_ULP_RAW 0
+#define TCB_ULP_RAW_SHIFT 4
+#define TCB_ULP_RAW_MASK 0xffULL
+#define TCB_ULP_RAW(x) ((x) << TCB_ULP_RAW_SHIFT)
+
+int cxgb4i_ddp_init(struct cxgbi_device *);
+void cxgb4i_ddp_cleanup(struct cxgbi_device *);
+
+#endif /* __CXGB4I_H__ */
+
diff --git a/drivers/scsi/cxgbi/cxgb4i_ddp.c b/drivers/scsi/cxgbi/cxgb4i_ddp.c
new file mode 100644
index 0000000..24debcf
--- /dev/null
+++ b/drivers/scsi/cxgbi/cxgb4i_ddp.c
@@ -0,0 +1,653 @@
+/*
+ * cxgb4i_ddp.c: Chelsio T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#include <linux/skbuff.h>
+#include <linux/scatterlist.h>
+
+#include "libcxgbi.h"
+#include "cxgb4i.h"
+
+#define DDP_PGIDX_MAX 4
+#define DDP_THRESHOLD 2048
+
+static unsigned char ddp_page_order[DDP_PGIDX_MAX] = {0, 1, 2, 4};
+static unsigned char ddp_page_shift[DDP_PGIDX_MAX] = {12, 13, 14, 16};
+static unsigned char page_idx = DDP_PGIDX_MAX;
+static unsigned char sw_tag_idx_bits;
+static unsigned char sw_tag_age_bits;
+
+static inline void cxgb4i_ddp_ppod_set(struct pagepod *ppod,
+ struct pagepod_hdr *hdr,
+ struct cxgbi_gather_list *gl,
+ unsigned int pidx)
+{
+ int i;
+
+ memcpy(ppod, hdr, sizeof(*hdr));
+ for (i = 0; i < (PPOD_PAGES_MAX + 1); i++, pidx++) {
+ ppod->addr[i] = pidx < gl->nelem ?
+ cpu_to_be64(gl->phys_addr[pidx]) : 0ULL;
+ }
+}
+
+static inline void cxgb4i_ddp_ppod_clear(struct pagepod *ppod)
+{
+ memset(ppod, 0, sizeof(*ppod));
+}
+
+static inline void cxgb4i_ddp_ulp_mem_io_set_hdr(struct ulp_mem_io *req,
+ unsigned int wr_len,
+ unsigned int dlen,
+ unsigned int pm_addr)
+{
+ struct ulptx_sgl *sgl;
+
+ INIT_ULPTX_WR(req, wr_len, 0, 0);
+ req->cmd = htonl(ULPTX_CMD(ULP_TX_MEM_WRITE));
+ req->dlen = htonl(ULP_MEMIO_DATA_LEN(dlen >> 5));
+ req->len16 = htonl(DIV_ROUND_UP(wr_len - sizeof(req->wr), 16));
+ req->lock_addr = htonl(ULP_MEMIO_ADDR(pm_addr >> 5));
+ sgl = (struct ulptx_sgl *)(req + 1);
+ sgl->cmd_nsge = htonl(ULPTX_CMD(ULP_TX_SC_DSGL) | ULPTX_NSGE(1));
+ sgl->len0 = htonl(dlen);
+}
+
+static int cxgb4i_ddp_ppod_write_sgl(struct cxgbi_hba *chba,
+ struct cxgb4i_ddp_info *ddp,
+ struct pagepod_hdr *hdr,
+ unsigned int idx,
+ unsigned int npods,
+ struct cxgbi_gather_list *gl,
+ unsigned int gl_pidx)
+{
+ unsigned int dlen, pm_addr, wr_len;
+ struct sk_buff *skb;
+ struct ulp_mem_io *req;
+ struct ulptx_sgl *sgl;
+ struct pagepod *ppod;
+ unsigned int i;
+
+ dlen = PPOD_SIZE * npods;
+ pm_addr = idx * PPOD_SIZE + ddp->llimit;
+ wr_len = roundup(sizeof(struct ulp_mem_io) +
+ sizeof(struct ulptx_sgl), 16);
+
+ skb = alloc_skb(wr_len + dlen, GFP_ATOMIC);
+ if (!skb) {
+ cxgbi_log_error("snic 0x%p, idx %u, npods %u, OOM\n",
+ ddp->snic, idx, npods);
+ return -ENOMEM;
+ }
+
+ memset(skb->data, 0, wr_len + dlen);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, chba->txq_idx);
+ req = (struct ulp_mem_io *)__skb_put(skb, wr_len);
+ cxgb4i_ddp_ulp_mem_io_set_hdr(req, wr_len, dlen, pm_addr);
+ sgl = (struct ulptx_sgl *)(req + 1);
+ ppod = (struct pagepod *)(sgl + 1);
+ sgl->addr0 = cpu_to_be64(virt_to_phys(ppod));
+
+ for (i = 0; i < npods; i++, ppod++, gl_pidx += PPOD_PAGES_MAX) {
+ if (!hdr && !gl)
+ cxgb4i_ddp_ppod_clear(ppod);
+ else
+ cxgb4i_ddp_ppod_set(ppod, hdr, gl, gl_pidx);
+
+ }
+
+ cxgb4_ofld_send(chba->cdev->ports[chba->port_id], skb);
+ return 0;
+}
+
+static int cxgb4i_ddp_set_map(struct cxgbi_hba *chba,
+ struct cxgb4i_ddp_info *ddp,
+ struct pagepod_hdr *hdr,
+ unsigned int idx,
+ unsigned int npods,
+ struct cxgbi_gather_list *gl)
+{
+ unsigned int pidx, w_npods, cnt;
+ int err = 0;
+
+ for (w_npods = 0, pidx = 0; w_npods < npods;
+ idx += cnt, w_npods += cnt, pidx += PPOD_PAGES_MAX) {
+ cnt = npods - w_npods;
+ if (cnt > ULPMEM_DSGL_MAX_NPPODS)
+ cnt = ULPMEM_DSGL_MAX_NPPODS;
+ err = cxgb4i_ddp_ppod_write_sgl(chba, ddp, hdr, idx, cnt, gl,
+ pidx);
+ if (err < 0)
+ break;
+ }
+ return err;
+}
+
+static void cxgb4i_ddp_clear_map(struct cxgbi_hba *chba,
+ struct cxgb4i_ddp_info *ddp,
+ unsigned int tag,
+ unsigned int idx,
+ unsigned int npods)
+{
+ int err;
+ unsigned int w_npods, cnt;
+
+ for (w_npods = 0; w_npods < npods; idx += cnt, w_npods += cnt) {
+ cnt = npods - w_npods;
+
+ if (cnt > ULPMEM_DSGL_MAX_NPPODS)
+ cnt = ULPMEM_DSGL_MAX_NPPODS;
+ err = cxgb4i_ddp_ppod_write_sgl(chba, ddp, NULL, idx, cnt,
+ NULL, 0);
+ if (err < 0)
+ break;
+ }
+}
+
+static inline int cxgb4i_ddp_find_unused_entries(struct cxgb4i_ddp_info *ddp,
+ unsigned int start, unsigned int max,
+ unsigned int count,
+ struct cxgbi_gather_list *gl)
+{
+ unsigned int i, j, k;
+
+ /* not enough entries */
+ if ((max - start) < count)
+ return -EBUSY;
+
+ max -= count;
+ spin_lock(&ddp->map_lock);
+ for (i = start; i < max;) {
+ for (j = 0, k = i; j < count; j++, k++) {
+ if (ddp->gl_map[k])
+ break;
+ }
+ if (j == count) {
+ for (j = 0, k = i; j < count; j++, k++)
+ ddp->gl_map[k] = gl;
+ spin_unlock(&ddp->map_lock);
+ return i;
+ }
+ i += j + 1;
+ }
+ spin_unlock(&ddp->map_lock);
+ return -EBUSY;
+}
+
+static inline void cxgb4i_ddp_unmark_entries(struct cxgb4i_ddp_info *ddp,
+ int start, int count)
+{
+ spin_lock(&ddp->map_lock);
+ memset(&ddp->gl_map[start], 0,
+ count * sizeof(struct cxgbi_gather_list *));
+ spin_unlock(&ddp->map_lock);
+}
+
+static int cxgb4i_ddp_find_page_index(unsigned long pgsz)
+{
+ int i;
+
+ for (i = 0; i < DDP_PGIDX_MAX; i++) {
+ if (pgsz == (1UL << ddp_page_shift[i]))
+ return i;
+ }
+ cxgbi_log_debug("ddp page size 0x%lx not supported\n", pgsz);
+ return DDP_PGIDX_MAX;
+}
+
+static int cxgb4i_ddp_adjust_page_table(void)
+{
+ int i;
+ unsigned int base_order, order;
+
+ if (PAGE_SIZE < (1UL << ddp_page_shift[0])) {
+ cxgbi_log_info("PAGE_SIZE 0x%lx too small, min 0x%lx\n",
+ PAGE_SIZE, 1UL << ddp_page_shift[0]);
+ return -EINVAL;
+ }
+
+ base_order = get_order(1UL << ddp_page_shift[0]);
+ order = get_order(1UL << PAGE_SHIFT);
+
+ for (i = 0; i < DDP_PGIDX_MAX; i++) {
+ /* first is the kernel page size,
+ * then just doubling the size */
+ ddp_page_order[i] = order - base_order + i;
+ ddp_page_shift[i] = PAGE_SHIFT + i;
+ }
+ return 0;
+}
+
+static inline void cxgb4i_ddp_gl_unmap(struct pci_dev *pdev,
+ struct cxgbi_gather_list *gl)
+{
+ int i;
+
+ for (i = 0; i < gl->nelem; i++)
+ dma_unmap_page(&pdev->dev, gl->phys_addr[i], PAGE_SIZE,
+ PCI_DMA_FROMDEVICE);
+}
+
+static inline int cxgb4i_ddp_gl_map(struct pci_dev *pdev,
+ struct cxgbi_gather_list *gl)
+{
+ int i;
+
+ for (i = 0; i < gl->nelem; i++) {
+ gl->phys_addr[i] = dma_map_page(&pdev->dev, gl->pages[i], 0,
+ PAGE_SIZE,
+ PCI_DMA_FROMDEVICE);
+ if (unlikely(dma_mapping_error(&pdev->dev, gl->phys_addr[i])))
+ goto unmap;
+ }
+ return i;
+unmap:
+ if (i) {
+ unsigned int nelem = gl->nelem;
+
+ gl->nelem = i;
+ cxgb4i_ddp_gl_unmap(pdev, gl);
+ gl->nelem = nelem;
+ }
+ return -ENOMEM;
+}
+
+static void cxgb4i_ddp_release_gl(struct cxgbi_gather_list *gl,
+ struct pci_dev *pdev)
+{
+ cxgb4i_ddp_gl_unmap(pdev, gl);
+ kfree(gl);
+}
+
+static struct cxgbi_gather_list *cxgb4i_ddp_make_gl(unsigned int xferlen,
+ struct scatterlist *sgl,
+ unsigned int sgcnt,
+ struct pci_dev *pdev,
+ gfp_t gfp)
+{
+ struct cxgbi_gather_list *gl;
+ struct scatterlist *sg = sgl;
+ struct page *sgpage = sg_page(sg);
+ unsigned int sglen = sg->length;
+ unsigned int sgoffset = sg->offset;
+ unsigned int npages = (xferlen + sgoffset + PAGE_SIZE - 1) >>
+ PAGE_SHIFT;
+ int i = 1, j = 0;
+
+ if (xferlen < DDP_THRESHOLD) {
+ cxgbi_log_debug("xfer %u < threshold %u, no ddp.\n",
+ xferlen, DDP_THRESHOLD);
+ return NULL;
+ }
+
+ gl = kzalloc(sizeof(struct cxgbi_gather_list) +
+ npages * (sizeof(dma_addr_t) +
+ sizeof(struct page *)), gfp);
+ if (!gl)
+ return NULL;
+
+ gl->pages = (struct page **)&gl->phys_addr[npages];
+ gl->length = xferlen;
+ gl->offset = sgoffset;
+ gl->pages[0] = sgpage;
+ sg = sg_next(sg);
+
+ while (sg) {
+ struct page *page = sg_page(sg);
+
+ if (sgpage == page && sg->offset == sgoffset + sglen)
+ sglen += sg->length;
+ else {
+ /* make sure the sgl is fit for ddp:
+ * each has the same page size, and
+ * all of the middle pages are used completely
+ */
+ if ((j && sgoffset) || ((i != sgcnt - 1) &&
+ ((sglen + sgoffset) & ~PAGE_MASK)))
+ goto error_out;
+
+ j++;
+ if (j == gl->nelem || sg->offset)
+ goto error_out;
+ gl->pages[j] = page;
+ sglen = sg->length;
+ sgoffset = sg->offset;
+ sgpage = page;
+ }
+ i++;
+ sg = sg_next(sg);
+ }
+ gl->nelem = ++j;
+
+ if (cxgb4i_ddp_gl_map(pdev, gl) < 0)
+ goto error_out;
+ return gl;
+error_out:
+ kfree(gl);
+ return NULL;
+}
+
+static void cxgb4i_ddp_tag_release(struct cxgbi_hba *chba, u32 tag)
+{
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(chba->cdev);
+ struct cxgb4i_ddp_info *ddp = snic->ddp;
+ u32 idx;
+
+ if (!ddp) {
+ cxgbi_log_error("release ddp tag 0x%x, ddp NULL.\n", tag);
+ return;
+ }
+
+ idx = (tag >> PPOD_IDX_SHIFT) & ddp->idx_mask;
+ if (idx < ddp->nppods) {
+ struct cxgbi_gather_list *gl = ddp->gl_map[idx];
+ unsigned int npods;
+
+ if (!gl || !gl->nelem) {
+ cxgbi_log_error("rel 0x%x, idx 0x%x, gl 0x%p, %u\n",
+ tag, idx, gl, gl ? gl->nelem : 0);
+ return;
+ }
+ npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+ cxgbi_log_debug("ddp tag 0x%x, release idx 0x%x, npods %u.\n",
+ tag, idx, npods);
+ cxgb4i_ddp_clear_map(chba, ddp, tag, idx, npods);
+ cxgb4i_ddp_unmark_entries(ddp, idx, npods);
+ cxgb4i_ddp_release_gl(gl, ddp->pdev);
+ } else
+ cxgbi_log_error("ddp tag 0x%x, idx 0x%x > max 0x%x.\n",
+ tag, idx, ddp->nppods);
+}
+
+static int cxgb4i_ddp_tag_reserve(struct cxgbi_hba *chba,
+ unsigned int tid,
+ struct cxgbi_tag_format *tformat,
+ u32 *tagp,
+ struct cxgbi_gather_list *gl,
+ gfp_t gfp)
+{
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(chba->cdev);
+ struct cxgb4i_ddp_info *ddp = snic->ddp;
+ struct pagepod_hdr hdr;
+ unsigned int npods;
+ int idx = -1;
+ int err = -ENOMEM;
+ u32 sw_tag = *tagp;
+ u32 tag;
+
+ if (page_idx >= DDP_PGIDX_MAX || !ddp || !gl || !gl->nelem ||
+ gl->length < DDP_THRESHOLD) {
+ cxgbi_log_debug("pgidx %u, xfer %u/%u, NO ddp.\n",
+ page_idx, gl->length, DDP_THRESHOLD);
+ return -EINVAL;
+ }
+
+ npods = (gl->nelem + PPOD_PAGES_MAX - 1) >> PPOD_PAGES_SHIFT;
+
+ if (ddp->idx_last == ddp->nppods)
+ idx = cxgb4i_ddp_find_unused_entries(ddp, 0, ddp->nppods,
+ npods, gl);
+ else {
+ idx = cxgb4i_ddp_find_unused_entries(ddp, ddp->idx_last + 1,
+ ddp->nppods, npods,
+ gl);
+ if (idx < 0 && ddp->idx_last >= npods) {
+ idx = cxgb4i_ddp_find_unused_entries(ddp, 0,
+ min(ddp->idx_last + npods, ddp->nppods),
+ npods, gl);
+ }
+ }
+ if (idx < 0) {
+ cxgbi_log_debug("xferlen %u, gl %u, npods %u NO DDP.\n",
+ gl->length, gl->nelem, npods);
+ return idx;
+ }
+
+ tag = cxgbi_ddp_tag_base(tformat, sw_tag);
+ tag |= idx << PPOD_IDX_SHIFT;
+
+ hdr.rsvd = 0;
+ hdr.vld_tid = htonl(PPOD_VALID_FLAG | PPOD_TID(tid));
+ hdr.pgsz_tag_clr = htonl(tag & ddp->rsvd_tag_mask);
+ hdr.max_offset = htonl(gl->length);
+ hdr.page_offset = htonl(gl->offset);
+
+ err = cxgb4i_ddp_set_map(chba, ddp, &hdr, idx, npods, gl);
+ if (err < 0)
+ goto unmark_entries;
+
+ ddp->idx_last = idx;
+ cxgbi_log_debug("xfer %u, gl %u,%u, tid 0x%x, 0x%x -> 0x%x(%u,%u).\n",
+ gl->length, gl->nelem, gl->offset, tid, sw_tag, tag,
+ idx, npods);
+ *tagp = tag;
+ return 0;
+unmark_entries:
+ cxgb4i_ddp_unmark_entries(ddp, idx, npods);
+ return err;
+}
+
+static int cxgb4i_ddp_setup_conn_pgidx(struct cxgbi_sock *csk,
+ unsigned int tid,
+ int pg_idx,
+ bool reply)
+{
+ struct sk_buff *skb;
+ struct cpl_set_tcb_field *req;
+ u64 val = pg_idx < DDP_PGIDX_MAX ? pg_idx : 0;
+
+ skb = alloc_skb(sizeof(*req), GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ /* set up ulp submode and page size */
+ val = (val & 0x03) << 2;
+ val |= TCB_ULP_TYPE(ULP_MODE_ISCSI);
+ req = (struct cpl_set_tcb_field *)skb_put(skb, sizeof(*req));
+ INIT_TP_WR(req, tid);
+ OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, csk->hwtid));
+ req->reply_ctrl = htons(NO_REPLY(reply) | QUEUENO(csk->rss_qid));
+ req->word_cookie = htons(TCB_WORD(W_TCB_ULP_RAW));
+ req->mask = cpu_to_be64(TCB_ULP_TYPE(TCB_ULP_TYPE_MASK));
+ req->val = cpu_to_be64(val);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->txq_idx);
+ cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+ return 0;
+}
+
+static int cxgb4i_ddp_setup_conn_host_pagesize(struct cxgbi_sock *csk,
+ unsigned int tid, int reply)
+{
+ return cxgb4i_ddp_setup_conn_pgidx(csk, tid, page_idx, reply);
+}
+
+static int cxgb4i_ddp_setup_conn_digest(struct cxgbi_sock *csk,
+ unsigned int tid, int hcrc,
+ int dcrc, int reply)
+{
+ struct sk_buff *skb;
+ struct cpl_set_tcb_field *req;
+ u64 val = (hcrc ? ULP_CRC_HEADER : 0) | (dcrc ? ULP_CRC_DATA : 0);
+
+ val = TCB_ULP_RAW(val);
+ val |= TCB_ULP_TYPE(ULP_MODE_ISCSI);
+
+ skb = alloc_skb(sizeof(*req), GFP_KERNEL);
+ if (!skb)
+ return -ENOMEM;
+
+ csk->hcrc_len = (hcrc ? 4 : 0);
+ csk->dcrc_len = (dcrc ? 4 : 0);
+ /* set up ulp submode and page size */
+ req = (struct cpl_set_tcb_field *)skb_put(skb, sizeof(*req));
+ INIT_TP_WR(req, tid);
+ OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SET_TCB_FIELD, tid));
+ req->reply_ctrl = htons(NO_REPLY(reply) | QUEUENO(csk->rss_qid));
+ req->word_cookie = htons(TCB_WORD(W_TCB_ULP_RAW));
+ req->mask = cpu_to_be64(TCB_ULP_RAW(TCB_ULP_RAW_MASK));
+ req->val = cpu_to_be64(val);
+ set_wr_txq(skb, CPL_PRIORITY_CONTROL, csk->txq_idx);
+ cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+ return 0;
+}
+
+static void __cxgb4i_ddp_cleanup(struct kref *kref)
+{
+ int i = 0;
+ struct cxgb4i_ddp_info *ddp = container_of(kref,
+ struct cxgb4i_ddp_info,
+ refcnt);
+
+ cxgbi_log_info("kref release ddp 0x%p, snic 0x%p\n", ddp, ddp->snic);
+ ddp->snic->ddp = NULL;
+
+ while (i < ddp->nppods) {
+ struct cxgbi_gather_list *gl = ddp->gl_map[i];
+
+ if (gl) {
+ int npods = (gl->nelem + PPOD_PAGES_MAX - 1) >>
+ PPOD_PAGES_SHIFT;
+ cxgbi_log_info("snic 0x%p, ddp %d + %d\n",
+ ddp->snic, i, npods);
+ kfree(gl);
+ i += npods;
+ } else
+ i++;
+ }
+ cxgbi_free_big_mem(ddp);
+}
+
+static int __cxgb4i_ddp_init(struct cxgbi_device *cdev)
+{
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(cdev);
+ struct cxgb4i_ddp_info *ddp = snic->ddp;
+ unsigned int ppmax, bits, tagmask, pgsz_factor[4];
+ int i;
+
+ if (ddp) {
+ kref_get(&ddp->refcnt);
+ cxgbi_log_warn("snic 0x%p, ddp 0x%p already set up\n",
+ snic, snic->ddp);
+ return -EALREADY;
+ }
+ sw_tag_idx_bits = (__ilog2_u32(ISCSI_ITT_MASK)) + 1;
+ sw_tag_age_bits = (__ilog2_u32(ISCSI_AGE_MASK)) + 1;
+ cdev->tag_format.sw_bits = sw_tag_idx_bits + sw_tag_age_bits;
+ cxgbi_log_info("tag itt 0x%x, %u bits, age 0x%x, %u bits\n",
+ ISCSI_ITT_MASK, sw_tag_idx_bits,
+ ISCSI_AGE_MASK, sw_tag_age_bits);
+ ppmax = (snic->lldi.vr->iscsi.size >> PPOD_SIZE_SHIFT);
+ bits = __ilog2_u32(ppmax) + 1;
+ if (bits > PPOD_IDX_MAX_SIZE)
+ bits = PPOD_IDX_MAX_SIZE;
+ ppmax = (1 << (bits - 1)) - 1;
+ ddp = cxgbi_alloc_big_mem(sizeof(struct cxgb4i_ddp_info) +
+ ppmax * (sizeof(struct cxgbi_gather_list *) +
+ sizeof(struct sk_buff *)),
+ GFP_KERNEL);
+ if (!ddp) {
+ cxgbi_log_warn("snic 0x%p unable to alloc ddp 0x%d, "
+ "ddp disabled\n", snic, ppmax);
+ return -ENOMEM;
+ }
+ ddp->gl_map = (struct cxgbi_gather_list **)(ddp + 1);
+ spin_lock_init(&ddp->map_lock);
+ kref_init(&ddp->refcnt);
+ ddp->snic = snic;
+ ddp->pdev = snic->lldi.pdev;
+ ddp->max_txsz = min_t(unsigned int,
+ snic->lldi.iscsi_iolen,
+ ULP2_MAX_PKT_SIZE);
+ ddp->max_rxsz = min_t(unsigned int,
+ snic->lldi.iscsi_iolen,
+ ULP2_MAX_PKT_SIZE);
+ ddp->llimit = snic->lldi.vr->iscsi.start;
+ ddp->ulimit = ddp->llimit + snic->lldi.vr->iscsi.size - 1;
+ ddp->nppods = ppmax;
+ ddp->idx_last = ppmax;
+ ddp->idx_bits = bits;
+ ddp->idx_mask = (1 << bits) - 1;
+ ddp->rsvd_tag_mask = (1 << (bits + PPOD_IDX_SHIFT)) - 1;
+ tagmask = ddp->idx_mask << PPOD_IDX_SHIFT;
+ for (i = 0; i < DDP_PGIDX_MAX; i++)
+ pgsz_factor[i] = ddp_page_order[i];
+ cxgb4_iscsi_init(snic->lldi.ports[0], tagmask, pgsz_factor);
+ snic->ddp = ddp;
+ cdev->tag_format.rsvd_bits = ddp->idx_bits;
+ cdev->tag_format.rsvd_shift = PPOD_IDX_SHIFT;
+ cdev->tag_format.rsvd_mask =
+ ((1 << cdev->tag_format.rsvd_bits) - 1);
+ cxgbi_log_info("tag format: sw %u, rsvd %u,%u, mask 0x%x.\n",
+ cdev->tag_format.sw_bits,
+ cdev->tag_format.rsvd_bits,
+ cdev->tag_format.rsvd_shift,
+ cdev->tag_format.rsvd_mask);
+ cdev->tx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+ ddp->max_txsz - ISCSI_PDU_NONPAYLOAD_LEN);
+ cdev->rx_max_size = min_t(unsigned int, ULP2_MAX_PDU_PAYLOAD,
+ ddp->max_rxsz - ISCSI_PDU_NONPAYLOAD_LEN);
+ cxgbi_log_info("max payload size: %u/%u, %u/%u.\n",
+ cdev->tx_max_size, ddp->max_txsz,
+ cdev->rx_max_size, ddp->max_rxsz);
+ cxgbi_log_info("snic 0x%p, nppods %u, bits %u, mask 0x%x,0x%x "
+ "pkt %u/%u, %u/%u\n",
+ snic, ppmax, ddp->idx_bits, ddp->idx_mask,
+ ddp->rsvd_tag_mask, ddp->max_txsz,
+ snic->lldi.iscsi_iolen,
+ ddp->max_rxsz, snic->lldi.iscsi_iolen);
+ return 0;
+}
+
+int cxgb4i_ddp_init(struct cxgbi_device *cdev)
+{
+ int rc = 0;
+
+ if (page_idx == DDP_PGIDX_MAX) {
+ page_idx = cxgb4i_ddp_find_page_index(PAGE_SIZE);
+
+ if (page_idx == DDP_PGIDX_MAX) {
+ cxgbi_log_info("system PAGE_SIZE %lu, update hw\n",
+ PAGE_SIZE);
+ rc = cxgb4i_ddp_adjust_page_table();
+ if (rc) {
+ cxgbi_log_info("PAGE_SIZE %lu, ddp disabled\n",
+ PAGE_SIZE);
+ return rc;
+ }
+ page_idx = cxgb4i_ddp_find_page_index(PAGE_SIZE);
+ }
+ cxgbi_log_info("system PAGE_SIZE %lu, ddp idx %u\n",
+ PAGE_SIZE, page_idx);
+ }
+ rc = __cxgb4i_ddp_init(cdev);
+ if (rc)
+ return rc;
+
+ cdev->ddp_make_gl = cxgb4i_ddp_make_gl;
+ cdev->ddp_release_gl = cxgb4i_ddp_release_gl;
+ cdev->ddp_tag_reserve = cxgb4i_ddp_tag_reserve;
+ cdev->ddp_tag_release = cxgb4i_ddp_tag_release;
+ cdev->ddp_setup_conn_digest = cxgb4i_ddp_setup_conn_digest;
+ cdev->ddp_setup_conn_host_pgsz = cxgb4i_ddp_setup_conn_host_pagesize;
+ return 0;
+}
+
+void cxgb4i_ddp_cleanup(struct cxgbi_device *cdev)
+{
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(cdev);
+ struct cxgb4i_ddp_info *ddp = snic->ddp;
+
+ cxgbi_log_info("snic 0x%p, release ddp 0x%p\n", cdev, ddp);
+ if (ddp)
+ kref_put(&ddp->refcnt, __cxgb4i_ddp_cleanup);
+}
+
diff --git a/drivers/scsi/cxgbi/cxgb4i_init.c b/drivers/scsi/cxgbi/cxgb4i_init.c
new file mode 100644
index 0000000..31da683
--- /dev/null
+++ b/drivers/scsi/cxgbi/cxgb4i_init.c
@@ -0,0 +1,317 @@
+/*
+ * cxgb4i_init.c: Chelsio T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#include <net/route.h>
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_device.h>
+#include <scsi/scsi_eh.h>
+#include <scsi/scsi_host.h>
+#include <scsi/scsi.h>
+#include <scsi/iscsi_proto.h>
+#include <scsi/libiscsi.h>
+#include <scsi/scsi_transport_iscsi.h>
+
+#include "cxgb4i.h"
+
+#define DRV_MODULE_NAME "cxgb4i"
+#define DRV_MODULE_VERSION "0.90"
+#define DRV_MODULE_RELDATE "05/04/2010"
+
+static char version[] =
+ "Chelsio T4 iSCSI driver " DRV_MODULE_NAME
+ " v" DRV_MODULE_VERSION " (" DRV_MODULE_RELDATE ")\n";
+
+MODULE_AUTHOR("Chelsio Communications");
+MODULE_DESCRIPTION("Chelsio T4 iSCSI driver");
+MODULE_LICENSE("GPL");
+MODULE_VERSION(DRV_MODULE_VERSION);
+
+#define RX_PULL_LEN 128
+
+static struct scsi_transport_template *cxgb4i_scsi_transport;
+static struct scsi_host_template cxgb4i_host_template;
+static struct iscsi_transport cxgb4i_iscsi_transport;
+static struct cxgbi_device *cxgb4i_cdev;
+
+static void *cxgb4i_uld_add(const struct cxgb4_lld_info *linfo);
+static int cxgb4i_uld_rx_handler(void *handle, const __be64 *rsp,
+ const struct pkt_gl *pgl);
+static int cxgb4i_uld_state_change(void *handle, enum cxgb4_state state);
+static int cxgb4i_iscsi_init(struct cxgbi_device *);
+static void cxgb4i_iscsi_cleanup(struct cxgbi_device *);
+
+const static struct cxgb4_uld_info cxgb4i_uld_info = {
+ .name = "cxgb4i",
+ .add = cxgb4i_uld_add,
+ .rx_handler = cxgb4i_uld_rx_handler,
+ .state_change = cxgb4i_uld_state_change,
+};
+
+static struct cxgbi_device *cxgb4i_uld_init(const struct cxgb4_lld_info *linfo)
+{
+ struct cxgbi_device *cdev;
+ struct cxgb4i_snic *snic;
+ struct port_info *pi;
+ int i, offs, rc;
+
+ cdev = cxgbi_device_register(sizeof(*snic), linfo->nports);
+ if (!cdev) {
+ cxgbi_log_debug("error cxgbi_device_alloc\n");
+ return NULL;
+ }
+ cxgb4i_cdev = cdev;
+ snic = cxgbi_cdev_priv(cxgb4i_cdev);
+ snic->lldi = *linfo;
+ cdev->ports = snic->lldi.ports;
+ cdev->nports = snic->lldi.nports;
+ cdev->pdev = snic->lldi.pdev;
+ cdev->mtus = snic->lldi.mtus;
+ cdev->nmtus = NMTUS;
+ cdev->skb_tx_headroom = SKB_MAX_HEAD(CXGB4I_TX_HEADER_LEN);
+ rc = cxgb4i_iscsi_init(cdev);
+ if (rc) {
+ cxgbi_log_info("cxgb4i_iscsi_init failed\n");
+ goto free_cdev;
+ }
+ rc = cxgbi_pdu_init(cdev);
+ if (rc) {
+ cxgbi_log_info("cxgbi_pdu_init failed\n");
+ goto clean_iscsi;
+ }
+ rc = cxgb4i_ddp_init(cdev);
+ if (rc) {
+ cxgbi_log_info("cxgb4i_ddp_init failed\n");
+ goto clean_pdu;
+ }
+ rc = cxgb4i_ofld_init(cdev);
+ if (rc) {
+ cxgbi_log_info("cxgb4i_ofld_init failed\n");
+ goto clean_ddp;
+ }
+
+ for (i = 0; i < cdev->nports; i++) {
+ cdev->hbas[i] = cxgbi_hba_add(cdev,
+ CXGB4I_MAX_LUN,
+ CXGB4I_MAX_CONN,
+ cxgb4i_scsi_transport,
+ &cxgb4i_host_template,
+ snic->lldi.ports[i]);
+ if (!cdev->hbas[i])
+ goto clean_iscsi;
+
+ pi = netdev_priv(snic->lldi.ports[i]);
+ offs = snic->lldi.ntxq / snic->lldi.nchan;
+ cdev->hbas[i]->txq_idx = pi->port_id * offs;
+ cdev->hbas[i]->port_id = pi->port_id;
+ }
+ return cdev;
+clean_iscsi:
+ cxgb4i_iscsi_cleanup(cdev);
+clean_pdu:
+ cxgbi_pdu_cleanup(cdev);
+clean_ddp:
+ cxgb4i_ddp_cleanup(cdev);
+free_cdev:
+ cxgbi_device_unregister(cdev);
+ cdev = ERR_PTR(-ENOMEM);
+ return cdev;
+}
+
+static void cxgb4i_uld_cleanup(void *handle)
+{
+ struct cxgbi_device *cdev = handle;
+ int i;
+
+ if (!cdev)
+ return;
+
+ for (i = 0; i < cdev->nports; i++) {
+ if (cdev->hbas[i]) {
+ cxgbi_hba_remove(cdev->hbas[i]);
+ cdev->hbas[i] = NULL;
+ }
+ }
+ cxgb4i_ofld_cleanup(cdev);
+ cxgb4i_ddp_cleanup(cdev);
+ cxgbi_pdu_cleanup(cdev);
+ cxgbi_log_info("snic 0x%p, %u scsi hosts removed.\n",
+ cdev, cdev->nports);
+ cxgb4i_iscsi_cleanup(cdev);
+ cxgbi_device_unregister(cdev);
+}
+
+static void *cxgb4i_uld_add(const struct cxgb4_lld_info *linfo)
+{
+ cxgbi_log_info("%s", version);
+ return cxgb4i_uld_init(linfo);
+}
+
+static int cxgb4i_uld_rx_handler(void *handle, const __be64 *rsp,
+ const struct pkt_gl *pgl)
+{
+ const struct cpl_act_establish *rpl;
+ struct sk_buff *skb;
+ unsigned int opc;
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(handle);
+
+ if (pgl == NULL) {
+ unsigned int len = 64 - sizeof(struct rsp_ctrl) - 8;
+
+ skb = alloc_skb(len, GFP_ATOMIC);
+ if (!skb)
+ goto nomem;
+ __skb_put(skb, len);
+ skb_copy_to_linear_data(skb, &rsp[1], len);
+ } else {
+ skb = cxgb4_pktgl_to_skb(pgl, RX_PULL_LEN, RX_PULL_LEN);
+ if (unlikely(!skb))
+ goto nomem;
+ }
+
+ rpl = (struct cpl_act_establish *)skb->data;
+ opc = rpl->ot.opcode;
+ cxgbi_log_debug("snic %p, opcode 0x%x, skb %p\n", snic, opc, skb);
+ BUG_ON(!snic->handlers[opc]);
+
+ if (snic->handlers[opc])
+ snic->handlers[opc](snic, skb);
+ else
+ cxgbi_log_error("No handler for opcode 0x%x\n", opc);
+ return 0;
+nomem:
+ cxgbi_api_debug("OOM bailing out\n");
+ return 1;
+}
+
+static int cxgb4i_uld_state_change(void *handle, enum cxgb4_state state)
+{
+ return 0;
+}
+
+static struct scsi_host_template cxgb4i_host_template = {
+ .module = THIS_MODULE,
+ .name = "Chelsio T4 iSCSI initiator",
+ .proc_name = "cxgb4i",
+ .queuecommand = iscsi_queuecommand,
+ .change_queue_depth = iscsi_change_queue_depth,
+ .can_queue = CXGB4I_SCSI_HOST_QDEPTH,
+ .sg_tablesize = SG_ALL,
+ .max_sectors = 0xFFFF,
+ .cmd_per_lun = ISCSI_DEF_CMD_PER_LUN,
+ .eh_abort_handler = iscsi_eh_abort,
+ .eh_device_reset_handler = iscsi_eh_device_reset,
+ .eh_target_reset_handler = iscsi_eh_recover_target,
+ .target_alloc = iscsi_target_alloc,
+ .use_clustering = DISABLE_CLUSTERING,
+ .this_id = -1,
+};
+
+#define CXGB4I_CAPS (CAP_RECOVERY_L0 | CAP_MULTI_R2T | \
+ CAP_HDRDGST | CAP_DATADGST | \
+ CAP_DIGEST_OFFLOAD | CAP_PADDING_OFFLOAD)
+#define CXGB4I_PMASK (ISCSI_MAX_RECV_DLENGTH | ISCSI_MAX_XMIT_DLENGTH | \
+ ISCSI_HDRDGST_EN | ISCSI_DATADGST_EN | \
+ ISCSI_INITIAL_R2T_EN | ISCSI_MAX_R2T | \
+ ISCSI_IMM_DATA_EN | ISCSI_FIRST_BURST | \
+ ISCSI_MAX_BURST | ISCSI_PDU_INORDER_EN | \
+ ISCSI_DATASEQ_INORDER_EN | ISCSI_ERL | \
+ ISCSI_CONN_PORT | ISCSI_CONN_ADDRESS | \
+ ISCSI_EXP_STATSN | ISCSI_PERSISTENT_PORT | \
+ ISCSI_PERSISTENT_ADDRESS | ISCSI_TARGET_NAME | \
+ ISCSI_TPGT | ISCSI_USERNAME | \
+ ISCSI_PASSWORD | ISCSI_USERNAME_IN | \
+ ISCSI_PASSWORD_IN | ISCSI_FAST_ABORT | \
+ ISCSI_ABORT_TMO | ISCSI_LU_RESET_TMO | \
+ ISCSI_TGT_RESET_TMO | ISCSI_PING_TMO | \
+ ISCSI_RECV_TMO | ISCSI_IFACE_NAME | \
+ ISCSI_INITIATOR_NAME)
+#define CXGB4I_HPMASK (ISCSI_HOST_HWADDRESS | ISCSI_HOST_IPADDRESS | \
+ ISCSI_HOST_INITIATOR_NAME | ISCSI_HOST_INITIATOR_NAME)
+
+static struct iscsi_transport cxgb4i_iscsi_transport = {
+ .owner = THIS_MODULE,
+ .name = "cxgb4i",
+ .caps = CXGB4I_CAPS,
+ .param_mask = CXGB4I_PMASK,
+ .host_param_mask = CXGB4I_HPMASK,
+ .get_host_param = cxgbi_get_host_param,
+ .set_host_param = cxgbi_set_host_param,
+
+ .create_session = cxgbi_create_session,
+ .destroy_session = cxgbi_destroy_session,
+ .get_session_param = iscsi_session_get_param,
+
+ .create_conn = cxgbi_create_conn,
+ .bind_conn = cxgbi_bind_conn,
+ .destroy_conn = iscsi_tcp_conn_teardown,
+ .start_conn = iscsi_conn_start,
+ .stop_conn = iscsi_conn_stop,
+ .get_conn_param = cxgbi_get_conn_param,
+ .set_param = cxgbi_set_conn_param,
+ .get_stats = cxgbi_get_conn_stats,
+
+ .send_pdu = iscsi_conn_send_pdu,
+
+ .init_task = iscsi_tcp_task_init,
+ .xmit_task = iscsi_tcp_task_xmit,
+ .cleanup_task = cxgbi_cleanup_task,
+
+ .alloc_pdu = cxgbi_conn_alloc_pdu,
+ .init_pdu = cxgbi_conn_init_pdu,
+ .xmit_pdu = cxgbi_conn_xmit_pdu,
+ .parse_pdu_itt = cxgbi_parse_pdu_itt,
+
+ .ep_connect = cxgbi_ep_connect,
+ .ep_poll = cxgbi_ep_poll,
+ .ep_disconnect = cxgbi_ep_disconnect,
+
+ .session_recovery_timedout = iscsi_session_recovery_timedout,
+};
+
+static int cxgb4i_iscsi_init(struct cxgbi_device *cdev)
+{
+ cxgb4i_scsi_transport = iscsi_register_transport(
+ &cxgb4i_iscsi_transport);
+ if (!cxgb4i_scsi_transport) {
+ cxgbi_log_error("Could not register cxgb4i transport\n");
+ return -ENODATA;
+ }
+
+ cdev->itp = &cxgb4i_iscsi_transport;
+ return 0;
+}
+
+static void cxgb4i_iscsi_cleanup(struct cxgbi_device *cdev)
+{
+ if (cxgb4i_scsi_transport) {
+ cxgbi_api_debug("cxgb4i transport 0x%p removed\n",
+ cxgb4i_scsi_transport);
+ iscsi_unregister_transport(&cxgb4i_iscsi_transport);
+ }
+}
+
+
+static int __init cxgb4i_init_module(void)
+{
+ cxgb4_register_uld(CXGB4_ULD_ISCSI, &cxgb4i_uld_info);
+ return 0;
+}
+
+static void __exit cxgb4i_exit_module(void)
+{
+ cxgb4_unregister_uld(CXGB4_ULD_ISCSI);
+ cxgb4i_uld_cleanup(cxgb4i_cdev);
+}
+
+module_init(cxgb4i_init_module);
+module_exit(cxgb4i_exit_module);
diff --git a/drivers/scsi/cxgbi/cxgb4i_offload.c b/drivers/scsi/cxgbi/cxgb4i_offload.c
new file mode 100644
index 0000000..bc7296c
--- /dev/null
+++ b/drivers/scsi/cxgbi/cxgb4i_offload.c
@@ -0,0 +1,1409 @@
+/*
+ * cxgb4i_offload.c: Chelsio T4 iSCSI driver.
+ *
+ * Copyright (c) 2010 Chelsio Communications, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * Written by: Karen Xie (kxie-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ * Written by: Rakesh Ranjan (rranjan-ut6Up61K2wZBDgjK7y7TUQ@public.gmane.org)
+ */
+
+#include <linux/if_vlan.h>
+#include <net/dst.h>
+#include <net/route.h>
+#include <net/tcp.h>
+
+#include "libcxgbi.h"
+#include "cxgb4i.h"
+
+static int cxgb4i_rcv_win = 256 * 1024;
+module_param(cxgb4i_rcv_win, int, 0644);
+MODULE_PARM_DESC(cxgb4i_rcv_win, "TCP reveive window in bytes");
+
+static int cxgb4i_snd_win = 128 * 1024;
+module_param(cxgb4i_snd_win, int, 0644);
+MODULE_PARM_DESC(cxgb4i_snd_win, "TCP send window in bytes");
+
+static int cxgb4i_rx_credit_thres = 10 * 1024;
+module_param(cxgb4i_rx_credit_thres, int, 0644);
+MODULE_PARM_DESC(cxgb4i_rx_credit_thres,
+ "RX credits return threshold in bytes (default=10KB)");
+
+static unsigned int cxgb4i_max_connect = (8 * 1024);
+module_param(cxgb4i_max_connect, uint, 0644);
+MODULE_PARM_DESC(cxgb4i_max_connect, "Maximum number of connections");
+
+static unsigned short cxgb4i_sport_base = 20000;
+module_param(cxgb4i_sport_base, ushort, 0644);
+MODULE_PARM_DESC(cxgb4i_sport_base, "Starting port number (default 20000)");
+
+#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
+#define RCV_BUFSIZ_MASK 0x3FFU
+#define MAX_IMM_TX_PKT_LEN 128
+
+static int cxgb4i_sock_push_tx_frames(struct cxgbi_sock *, int);
+
+/*
+ * is_ofld_imm - check whether a packet can be sent as immediate data
+ * @skb: the packet
+ *
+ * Returns true if a packet can be sent as an offload WR with immediate
+ * data. We currently use the same limit as for Ethernet packets.
+ */
+static inline int is_ofld_imm(const struct sk_buff *skb)
+{
+ return skb->len <= (MAX_IMM_TX_PKT_LEN -
+ sizeof(struct fw_ofld_tx_data_wr));
+}
+
+static void cxgb4i_sock_make_act_open_req(struct cxgbi_sock *csk,
+ struct sk_buff *skb,
+ unsigned int qid_atid,
+ struct l2t_entry *e)
+{
+ struct cpl_act_open_req *req;
+ unsigned long long opt0;
+ unsigned int opt2;
+ int wscale;
+
+ cxgbi_conn_debug("csk 0x%p, atid 0x%x\n", csk, qid_atid);
+
+ wscale = cxgbi_sock_compute_wscale(csk->mss_idx);
+ opt0 = KEEP_ALIVE(1) |
+ WND_SCALE(wscale) |
+ MSS_IDX(csk->mss_idx) |
+ L2T_IDX(((struct l2t_entry *)csk->l2t)->idx) |
+ TX_CHAN(csk->tx_chan) |
+ SMAC_SEL(csk->smac_idx) |
+ RCV_BUFSIZ(cxgb4i_rcv_win >> 10);
+ opt2 = RX_CHANNEL(0) |
+ RSS_QUEUE_VALID |
+ RSS_QUEUE(csk->rss_qid);
+ set_wr_txq(skb, CPL_PRIORITY_SETUP, csk->txq_idx);
+ req = (struct cpl_act_open_req *)__skb_put(skb, sizeof(*req));
+ INIT_TP_WR(req, 0);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ACT_OPEN_REQ,
+ qid_atid));
+ req->local_port = csk->saddr.sin_port;
+ req->peer_port = csk->daddr.sin_port;
+ req->local_ip = csk->saddr.sin_addr.s_addr;
+ req->peer_ip = csk->daddr.sin_addr.s_addr;
+ req->opt0 = cpu_to_be64(opt0);
+ req->params = 0;
+ req->opt2 = cpu_to_be32(opt2);
+}
+
+static void cxgb4i_fail_act_open(struct cxgbi_sock *csk, int errno)
+{
+ cxgbi_conn_debug("csk 0%p, state %u, flag 0x%lx\n", csk,
+ csk->state, csk->flags);
+ csk->err = errno;
+ cxgbi_sock_closed(csk);
+}
+
+static void cxgb4i_act_open_req_arp_failure(void *handle, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk = (struct cxgbi_sock *)skb->sk;
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ if (csk->state == CTP_CONNECTING)
+ cxgb4i_fail_act_open(csk, -EHOSTUNREACH);
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ __kfree_skb(skb);
+}
+
+static void cxgb4i_sock_skb_entail(struct cxgbi_sock *csk,
+ struct sk_buff *skb,
+ int flags)
+{
+ cxgb4i_skb_tcp_seq(skb) = csk->write_seq;
+ cxgb4i_skb_flags(skb) = flags;
+ __skb_queue_tail(&csk->write_queue, skb);
+}
+
+static void cxgb4i_sock_send_close_req(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb = csk->cpl_close;
+ struct cpl_close_con_req *req = (struct cpl_close_con_req *)skb->head;
+ unsigned int tid = csk->hwtid;
+
+ csk->cpl_close = NULL;
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ INIT_TP_WR(req, tid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid));
+ req->rsvd = 0;
+ cxgb4i_sock_skb_entail(csk, skb, CTP_SKCBF_NO_APPEND);
+ if (csk->state != CTP_CONNECTING)
+ cxgb4i_sock_push_tx_frames(csk, 1);
+}
+
+static void cxgb4i_sock_abort_arp_failure(void *handle, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk = (struct cxgbi_sock *)handle;
+ struct cpl_abort_req *req;
+
+ req = (struct cpl_abort_req *)skb->data;
+ req->cmd = CPL_ABORT_NO_RST;
+ cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+}
+
+static void cxgb4i_sock_send_abort_req(struct cxgbi_sock *csk)
+{
+ struct cpl_abort_req *req;
+ struct sk_buff *skb = csk->cpl_abort_req;
+
+ if (unlikely(csk->state == CTP_ABORTING) || !skb || !csk->cdev)
+ return;
+ cxgbi_sock_set_state(csk, CTP_ABORTING);
+ cxgbi_conn_debug("csk 0x%p, flag ABORT_RPL + ABORT_SHUT\n", csk);
+ cxgbi_sock_set_state(csk, CTPF_ABORT_RPL_PENDING);
+ cxgbi_sock_purge_write_queue(csk);
+ csk->cpl_abort_req = NULL;
+ req = (struct cpl_abort_req *)skb->head;
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ t4_set_arp_err_handler(skb, csk, cxgb4i_sock_abort_arp_failure);
+ INIT_TP_WR(req, csk->hwtid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, csk->hwtid));
+ req->rsvd0 = htonl(csk->snd_nxt);
+ req->rsvd1 = !cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT);
+ req->cmd = CPL_ABORT_SEND_RST;
+ cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
+}
+
+static void cxgb4i_sock_send_abort_rpl(struct cxgbi_sock *csk, int rst_status)
+{
+ struct sk_buff *skb = csk->cpl_abort_rpl;
+ struct cpl_abort_rpl *rpl = (struct cpl_abort_rpl *)skb->head;
+
+ csk->cpl_abort_rpl = NULL;
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ INIT_TP_WR(rpl, csk->hwtid);
+ OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, csk->hwtid));
+ rpl->cmd = rst_status;
+ cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+}
+
+static u32 cxgb4i_csk_send_rx_credits(struct cxgbi_sock *csk, u32 credits)
+{
+ struct sk_buff *skb;
+ struct cpl_rx_data_ack *req;
+ int wrlen = roundup(sizeof(*req), 16);
+
+ skb = alloc_skb(wrlen, GFP_ATOMIC);
+ if (!skb)
+ return 0;
+ req = (struct cpl_rx_data_ack *)__skb_put(skb, wrlen);
+ memset(req, 0, wrlen);
+ set_wr_txq(skb, CPL_PRIORITY_ACK, csk->txq_idx);
+ INIT_TP_WR(req, csk->hwtid);
+ OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK,
+ csk->hwtid));
+ req->credit_dack = cpu_to_be32(RX_CREDITS(credits) | RX_FORCE_ACK(1));
+ cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+ return credits;
+}
+
+#define SKB_WR_LIST_SIZE (MAX_SKB_FRAGS + 2)
+static const unsigned int cxgb4i_ulp_extra_len[] = { 0, 4, 4, 8 };
+
+static inline unsigned int ulp_extra_len(const struct sk_buff *skb)
+{
+ return cxgb4i_ulp_extra_len[cxgb4i_skb_ulp_mode(skb) & 3];
+}
+
+static inline void cxgb4i_sock_reset_wr_list(struct cxgbi_sock *csk)
+{
+ csk->wr_pending_head = csk->wr_pending_tail = NULL;
+}
+
+static inline void cxgb4i_sock_enqueue_wr(struct cxgbi_sock *csk,
+ struct sk_buff *skb)
+{
+ cxgb4i_skb_tx_wr_next(skb) = NULL;
+ /*
+ * We want to take an extra reference since both us and the driver
+ * need to free the packet before it's really freed. We know there's
+ * just one user currently so we use atomic_set rather than skb_get
+ * to avoid the atomic op.
+ */
+ atomic_set(&skb->users, 2);
+
+ if (!csk->wr_pending_head)
+ csk->wr_pending_head = skb;
+ else
+ cxgb4i_skb_tx_wr_next(csk->wr_pending_tail) = skb;
+ csk->wr_pending_tail = skb;
+}
+
+static int cxgb4i_sock_count_pending_wrs(const struct cxgbi_sock *csk)
+{
+ int n = 0;
+ const struct sk_buff *skb = csk->wr_pending_head;
+
+ while (skb) {
+ n += skb->csum;
+ skb = cxgb4i_skb_tx_wr_next(skb);
+ }
+ return n;
+}
+
+static inline struct sk_buff *cxgb4i_sock_peek_wr(const struct cxgbi_sock *csk)
+{
+ return csk->wr_pending_head;
+}
+
+static inline struct sk_buff *cxgb4i_sock_dequeue_wr(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb = csk->wr_pending_head;
+
+ if (likely(skb)) {
+ csk->wr_pending_head = cxgb4i_skb_tx_wr_next(skb);
+ cxgb4i_skb_tx_wr_next(skb) = NULL;
+ }
+ return skb;
+}
+
+static void cxgb4i_sock_purge_wr_queue(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+
+ while ((skb = cxgb4i_sock_dequeue_wr(csk)) != NULL)
+ kfree_skb(skb);
+}
+
+/*
+ * sgl_len - calculates the size of an SGL of the given capacity
+ * @n: the number of SGL entries
+ * Calculates the number of flits needed for a scatter/gather list that
+ * can hold the given number of entries.
+ */
+static inline unsigned int sgl_len(unsigned int n)
+{
+ n--;
+ return (3 * n) / 2 + (n & 1) + 2;
+}
+
+/*
+ * calc_tx_flits_ofld - calculate # of flits for an offload packet
+ * @skb: the packet
+ *
+ * Returns the number of flits needed for the given offload packet.
+ * These packets are already fully constructed and no additional headers
+ * will be added.
+ */
+static inline unsigned int calc_tx_flits_ofld(const struct sk_buff *skb)
+{
+ unsigned int flits, cnt;
+
+ if (is_ofld_imm(skb))
+ return DIV_ROUND_UP(skb->len, 8);
+ flits = skb_transport_offset(skb) / 8;
+ cnt = skb_shinfo(skb)->nr_frags;
+ if (skb->tail != skb->transport_header)
+ cnt++;
+ return flits + sgl_len(cnt);
+}
+
+static inline void cxgb4i_sock_send_tx_flowc_wr(struct cxgbi_sock *csk)
+{
+ struct sk_buff *skb;
+ struct fw_flowc_wr *flowc;
+ int flowclen, i;
+
+ flowclen = 80;
+ skb = alloc_skb(flowclen, GFP_ATOMIC);
+ flowc = (struct fw_flowc_wr *)__skb_put(skb, flowclen);
+ flowc->op_to_nparams =
+ htonl(FW_WR_OP(FW_FLOWC_WR) | FW_FLOWC_WR_NPARAMS(8));
+ flowc->flowid_len16 =
+ htonl(FW_WR_LEN16(DIV_ROUND_UP(72, 16)) |
+ FW_WR_FLOWID(csk->hwtid));
+ flowc->mnemval[0].mnemonic = FW_FLOWC_MNEM_PFNVFN;
+ flowc->mnemval[0].val = htonl(0);
+ flowc->mnemval[1].mnemonic = FW_FLOWC_MNEM_CH;
+ flowc->mnemval[1].val = htonl(csk->tx_chan);
+ flowc->mnemval[2].mnemonic = FW_FLOWC_MNEM_PORT;
+ flowc->mnemval[2].val = htonl(csk->tx_chan);
+ flowc->mnemval[3].mnemonic = FW_FLOWC_MNEM_IQID;
+ flowc->mnemval[3].val = htonl(csk->rss_qid);
+ flowc->mnemval[4].mnemonic = FW_FLOWC_MNEM_SNDNXT;
+ flowc->mnemval[4].val = htonl(csk->snd_nxt);
+ flowc->mnemval[5].mnemonic = FW_FLOWC_MNEM_RCVNXT;
+ flowc->mnemval[5].val = htonl(csk->rcv_nxt);
+ flowc->mnemval[6].mnemonic = FW_FLOWC_MNEM_SNDBUF;
+ flowc->mnemval[6].val = htonl(cxgb4i_snd_win);
+ flowc->mnemval[7].mnemonic = FW_FLOWC_MNEM_MSS;
+ flowc->mnemval[7].val = htonl(csk->mss_idx);
+ flowc->mnemval[8].mnemonic = 0;
+ flowc->mnemval[8].val = 0;
+ for (i = 0; i < 9; i++) {
+ flowc->mnemval[i].r4[0] = 0;
+ flowc->mnemval[i].r4[1] = 0;
+ flowc->mnemval[i].r4[2] = 0;
+ }
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ cxgb4_ofld_send(csk->cdev->ports[csk->port_id], skb);
+}
+
+static inline void cxgb4i_sock_make_tx_data_wr(struct cxgbi_sock *csk,
+ struct sk_buff *skb, int dlen,
+ int len, u32 credits,
+ int req_completion)
+{
+ struct fw_ofld_tx_data_wr *req;
+ unsigned int wr_ulp_mode;
+
+ if (is_ofld_imm(skb)) {
+ req = (struct fw_ofld_tx_data_wr *)
+ __skb_push(skb, sizeof(*req));
+ req->op_to_immdlen =
+ cpu_to_be32(FW_WR_OP(FW_OFLD_TX_DATA_WR) |
+ FW_WR_COMPL(req_completion) |
+ FW_WR_IMMDLEN(dlen));
+ req->flowid_len16 =
+ cpu_to_be32(FW_WR_FLOWID(csk->hwtid) |
+ FW_WR_LEN16(credits));
+ } else {
+ req = (struct fw_ofld_tx_data_wr *)
+ __skb_push(skb, sizeof(*req));
+ req->op_to_immdlen =
+ cpu_to_be32(FW_WR_OP(FW_OFLD_TX_DATA_WR) |
+ FW_WR_COMPL(req_completion) |
+ FW_WR_IMMDLEN(0));
+ req->flowid_len16 =
+ cpu_to_be32(FW_WR_FLOWID(csk->hwtid) |
+ FW_WR_LEN16(credits));
+ }
+ wr_ulp_mode =
+ FW_OFLD_TX_DATA_WR_ULPMODE(cxgb4i_skb_ulp_mode(skb) >> 4) |
+ FW_OFLD_TX_DATA_WR_ULPSUBMODE(cxgb4i_skb_ulp_mode(skb) & 3);
+ req->tunnel_to_proxy = cpu_to_be32(wr_ulp_mode) |
+ FW_OFLD_TX_DATA_WR_SHOVE(skb_peek(&csk->write_queue) ? 0 : 1);
+ req->plen = cpu_to_be32(len);
+ if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT))
+ cxgbi_sock_set_flag(csk, CTPF_TX_DATA_SENT);
+}
+
+static void cxgb4i_sock_arp_failure_discard(void *handle, struct sk_buff *skb)
+{
+ kfree_skb(skb);
+}
+
+static int cxgb4i_sock_push_tx_frames(struct cxgbi_sock *csk,
+ int req_completion)
+{
+ int total_size = 0;
+ struct sk_buff *skb;
+ struct cxgb4i_snic *snic;
+
+ if (unlikely(csk->state == CTP_CONNECTING ||
+ csk->state == CTP_CLOSE_WAIT_1 ||
+ csk->state >= CTP_ABORTING)) {
+ cxgbi_tx_debug("csk 0x%p, in closing state %u.\n",
+ csk, csk->state);
+ return 0;
+ }
+
+ snic = cxgbi_cdev_priv(csk->cdev);
+ while (csk->wr_cred && (skb = skb_peek(&csk->write_queue)) != NULL) {
+ int dlen;
+ int len;
+ unsigned int credits_needed;
+
+ dlen = len = skb->len;
+ skb_reset_transport_header(skb);
+ if (is_ofld_imm(skb))
+ credits_needed = DIV_ROUND_UP(dlen +
+ sizeof(struct fw_ofld_tx_data_wr), 16);
+ else
+ credits_needed = DIV_ROUND_UP(8 *
+ calc_tx_flits_ofld(skb)+
+ sizeof(struct fw_ofld_tx_data_wr), 16);
+ if (csk->wr_cred < credits_needed) {
+ cxgbi_tx_debug("csk 0x%p, skb len %u/%u, "
+ "wr %d < %u.\n",
+ csk, skb->len, skb->data_len,
+ credits_needed, csk->wr_cred);
+ break;
+ }
+ __skb_unlink(skb, &csk->write_queue);
+ set_wr_txq(skb, CPL_PRIORITY_DATA, csk->txq_idx);
+ skb->csum = credits_needed;
+ csk->wr_cred -= credits_needed;
+ csk->wr_una_cred += credits_needed;
+ cxgb4i_sock_enqueue_wr(csk, skb);
+ cxgbi_tx_debug("csk 0x%p, enqueue, skb len %u/%u, "
+ "wr %d, left %u, unack %u.\n",
+ csk, skb->len, skb->data_len,
+ credits_needed, csk->wr_cred,
+ csk->wr_una_cred);
+ if (likely(cxgb4i_skb_flags(skb) & CTP_SKCBF_NEED_HDR)) {
+ len += ulp_extra_len(skb);
+ if (!cxgbi_sock_flag(csk, CTPF_TX_DATA_SENT)) {
+ cxgb4i_sock_send_tx_flowc_wr(csk);
+ skb->csum += 5;
+ csk->wr_cred -= 5;
+ csk->wr_una_cred += 5;
+ }
+ if ((req_completion &&
+ csk->wr_una_cred == credits_needed) ||
+ (cxgb4i_skb_flags(skb) & CTP_SKCBF_COMPL) ||
+ csk->wr_una_cred >= csk->wr_max_cred >> 1) {
+ req_completion = 1;
+ csk->wr_una_cred = 0;
+ }
+ cxgb4i_sock_make_tx_data_wr(csk, skb, dlen, len,
+ credits_needed,
+ req_completion);
+ csk->snd_nxt += len;
+ if (req_completion)
+ cxgb4i_skb_flags(skb) &= ~CTP_SKCBF_NEED_HDR;
+ }
+ total_size += skb->truesize;
+ t4_set_arp_err_handler(skb, csk,
+ cxgb4i_sock_arp_failure_discard);
+ cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
+ }
+ return total_size;
+}
+
+static inline void cxgb4i_sock_free_atid(struct cxgbi_sock *csk)
+{
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(csk->cdev);
+
+ cxgb4_free_atid(snic->lldi.tids, csk->atid);
+ cxgbi_sock_put(csk);
+}
+
+static void cxgb4i_sock_established(struct cxgbi_sock *csk, u32 snd_isn,
+ unsigned int opt)
+{
+ cxgbi_conn_debug("csk 0x%p, state %u.\n", csk, csk->state);
+
+ csk->write_seq = csk->snd_nxt = csk->snd_una = snd_isn;
+ /*
+ * Causes the first RX_DATA_ACK to supply any Rx credits we couldn't
+ * pass through opt0.
+ */
+ if (cxgb4i_rcv_win > (RCV_BUFSIZ_MASK << 10))
+ csk->rcv_wup -= cxgb4i_rcv_win - (RCV_BUFSIZ_MASK << 10);
+ dst_confirm(csk->dst);
+ smp_mb();
+ cxgbi_sock_set_state(csk, CTP_ESTABLISHED);
+}
+
+static int cxgb4i_cpl_act_establish(struct cxgb4i_snic *snic,
+ struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_act_establish *req = (struct cpl_act_establish *)skb->data;
+ unsigned int hwtid = GET_TID(req);
+ unsigned int atid = GET_TID_TID(ntohl(req->tos_atid));
+ struct tid_info *t = snic->lldi.tids;
+ u32 rcv_isn = be32_to_cpu(req->rcv_isn);
+
+ csk = lookup_atid(t, atid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+ cxgbi_conn_debug("csk 0x%p, state %u, flag 0x%lx\n",
+ csk, csk->state, csk->flags);
+ csk->hwtid = hwtid;
+ cxgbi_sock_hold(csk);
+ cxgb4_insert_tid(snic->lldi.tids, csk, hwtid);
+ cxgb4i_sock_free_atid(csk);
+ spin_lock_bh(&csk->lock);
+
+ if (unlikely(csk->state != CTP_CONNECTING))
+ cxgbi_log_error("TID %u expected SYN_SENT, got EST., s %u\n",
+ csk->hwtid, csk->state);
+ csk->copied_seq = csk->rcv_wup = csk->rcv_nxt = rcv_isn;
+ cxgb4i_sock_established(csk, ntohl(req->snd_isn), ntohs(req->tcp_opt));
+ __kfree_skb(skb);
+
+ if (unlikely(cxgbi_sock_flag(csk, CTPF_ACTIVE_CLOSE_NEEDED)))
+ cxgb4i_sock_send_abort_req(csk);
+ else {
+ if (skb_queue_len(&csk->write_queue))
+ cxgb4i_sock_push_tx_frames(csk, 1);
+ cxgbi_conn_tx_open(csk);
+ }
+
+ if (csk->retry_timer.function) {
+ del_timer(&csk->retry_timer);
+ csk->retry_timer.function = NULL;
+ }
+ spin_unlock_bh(&csk->lock);
+ return 0;
+}
+
+static int act_open_rpl_status_to_errno(int status)
+{
+ switch (status) {
+ case CPL_ERR_CONN_RESET:
+ return -ECONNREFUSED;
+ case CPL_ERR_ARP_MISS:
+ return -EHOSTUNREACH;
+ case CPL_ERR_CONN_TIMEDOUT:
+ return -ETIMEDOUT;
+ case CPL_ERR_TCAM_FULL:
+ return -ENOMEM;
+ case CPL_ERR_CONN_EXIST:
+ cxgbi_log_error("ACTIVE_OPEN_RPL: 4-tuple in use\n");
+ return -EADDRINUSE;
+ default:
+ return -EIO;
+ }
+}
+
+/*
+ * Return whether a failed active open has allocated a TID
+ */
+static inline int act_open_has_tid(int status)
+{
+ return status != CPL_ERR_TCAM_FULL && status != CPL_ERR_CONN_EXIST &&
+ status != CPL_ERR_ARP_MISS;
+}
+
+static void cxgb4i_sock_act_open_retry_timer(unsigned long data)
+{
+ struct sk_buff *skb;
+ struct cxgbi_sock *csk = (struct cxgbi_sock *)data;
+
+ cxgbi_conn_debug("csk 0x%p, state %u.\n", csk, csk->state);
+ spin_lock_bh(&csk->lock);
+ skb = alloc_skb(sizeof(struct cpl_act_open_req), GFP_ATOMIC);
+ if (!skb)
+ cxgb4i_fail_act_open(csk, -ENOMEM);
+ else {
+ unsigned int qid_atid = csk->rss_qid << 14;
+ qid_atid |= (unsigned int)csk->atid;
+ skb->sk = (struct sock *)csk;
+ t4_set_arp_err_handler(skb, csk,
+ cxgb4i_act_open_req_arp_failure);
+ cxgb4i_sock_make_act_open_req(csk, skb, qid_atid, csk->l2t);
+ cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
+ }
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+}
+
+static int cxgb4i_cpl_act_open_rpl(struct cxgb4i_snic *snic,
+ struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_act_open_rpl *rpl = (struct cpl_act_open_rpl *)skb->data;
+ unsigned int atid =
+ GET_TID_TID(GET_AOPEN_ATID(be32_to_cpu(rpl->atid_status)));
+ struct tid_info *t = snic->lldi.tids;
+ unsigned int status = GET_AOPEN_STATUS(be32_to_cpu(rpl->atid_status));
+
+ csk = lookup_atid(t, atid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", atid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ cxgbi_conn_debug("rcv, status 0x%x, csk 0x%p, csk->state %u, "
+ "csk->flag 0x%lx, csk->atid %u.\n",
+ status, csk, csk->state, csk->flags, csk->hwtid);
+
+ if (status & act_open_has_tid(status))
+ cxgb4_remove_tid(snic->lldi.tids, csk->port_id, GET_TID(rpl));
+
+ if (status == CPL_ERR_CONN_EXIST &&
+ csk->retry_timer.function != cxgb4i_sock_act_open_retry_timer) {
+ csk->retry_timer.function = cxgb4i_sock_act_open_retry_timer;
+ if (!mod_timer(&csk->retry_timer, jiffies + HZ / 2))
+ cxgbi_sock_hold(csk);
+ } else
+ cxgb4i_fail_act_open(csk,
+ act_open_rpl_status_to_errno(status));
+
+ __kfree_skb(skb);
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ return 0;
+}
+
+static int cxgb4i_cpl_peer_close(struct cxgb4i_snic *snic, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_peer_close *req = (struct cpl_peer_close *)skb->data;
+ unsigned int hwtid = GET_TID(req);
+ struct tid_info *t = snic->lldi.tids;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING))
+ goto out;
+
+ switch (csk->state) {
+ case CTP_ESTABLISHED:
+ cxgbi_sock_set_state(csk, CTP_PASSIVE_CLOSE);
+ break;
+ case CTP_ACTIVE_CLOSE:
+ cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_2);
+ break;
+ case CTP_CLOSE_WAIT_1:
+ cxgbi_sock_closed(csk);
+ break;
+ case CTP_ABORTING:
+ break;
+ default:
+ cxgbi_log_error("peer close, TID %u in bad state %u\n",
+ csk->hwtid, csk->state);
+ }
+
+ cxgbi_sock_conn_closing(csk);
+out:
+ __kfree_skb(skb);
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ return 0;
+}
+
+static int cxgb4i_cpl_close_con_rpl(struct cxgb4i_snic *snic,
+ struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_close_con_rpl *rpl = (struct cpl_close_con_rpl *)skb->data;
+ unsigned int hwtid = GET_TID(rpl);
+ struct tid_info *t = snic->lldi.tids;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ cxgbi_conn_debug("csk 0x%p, state %u, flag 0x%lx.\n",
+ csk, csk->state, csk->flags);
+ csk->snd_una = ntohl(rpl->snd_nxt) - 1;
+
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING))
+ goto out;
+
+ switch (csk->state) {
+ case CTP_ACTIVE_CLOSE:
+ cxgbi_sock_set_state(csk, CTP_CLOSE_WAIT_1);
+ break;
+ case CTP_CLOSE_WAIT_1:
+ case CTP_CLOSE_WAIT_2:
+ cxgbi_sock_closed(csk);
+ break;
+ case CTP_ABORTING:
+ break;
+ default:
+ cxgbi_log_error("close_rpl, TID %u in bad state %u\n",
+ csk->hwtid, csk->state);
+ }
+out:
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ kfree_skb(skb);
+ return 0;
+}
+
+static int abort_status_to_errno(struct cxgbi_sock *csk, int abort_reason,
+ int *need_rst)
+{
+ switch (abort_reason) {
+ case CPL_ERR_BAD_SYN: /* fall through */
+ case CPL_ERR_CONN_RESET:
+ return csk->state > CTP_ESTABLISHED ?
+ -EPIPE : -ECONNRESET;
+ case CPL_ERR_XMIT_TIMEDOUT:
+ case CPL_ERR_PERSIST_TIMEDOUT:
+ case CPL_ERR_FINWAIT2_TIMEDOUT:
+ case CPL_ERR_KEEPALIVE_TIMEDOUT:
+ return -ETIMEDOUT;
+ default:
+ return -EIO;
+ }
+}
+
+/*
+ * Returns whether an ABORT_REQ_RSS message is a negative advice.
+ */
+static inline int is_neg_adv_abort(unsigned int status)
+{
+ return status == CPL_ERR_RTX_NEG_ADVICE ||
+ status == CPL_ERR_PERSIST_NEG_ADVICE;
+}
+
+static int cxgb4i_cpl_abort_req_rss(struct cxgb4i_snic *snic,
+ struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_abort_req_rss *req = (struct cpl_abort_req_rss *)skb->data;
+ unsigned int hwtid = GET_TID(req);
+ struct tid_info *t = snic->lldi.tids;
+ int rst_status = CPL_ABORT_NO_RST;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ if (is_neg_adv_abort(req->status)) {
+ __kfree_skb(skb);
+ return 0;
+ }
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+
+ if (!cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD)) {
+ cxgbi_sock_set_flag(csk, CTPF_ABORT_REQ_RCVD);
+ cxgbi_sock_set_state(csk, CTP_ABORTING);
+ __kfree_skb(skb);
+ goto out;
+ }
+
+ cxgbi_sock_clear_flag(csk, CTPF_ABORT_REQ_RCVD);
+ cxgb4i_sock_send_abort_rpl(csk, rst_status);
+
+ if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) {
+ csk->err = abort_status_to_errno(csk, req->status,
+ &rst_status);
+ cxgbi_sock_closed(csk);
+ }
+out:
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ return 0;
+}
+
+static int cxgb4i_cpl_abort_rpl_rss(struct cxgb4i_snic *snic,
+ struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_abort_rpl_rss *rpl = (struct cpl_abort_rpl_rss *)skb->data;
+ unsigned int hwtid = GET_TID(rpl);
+ struct tid_info *t = snic->lldi.tids;
+
+ if (rpl->status == CPL_ERR_ABORT_FAILED)
+ goto out;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ goto out;
+ }
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_RPL_PENDING)) {
+ if (!cxgbi_sock_flag(csk, CTPF_ABORT_RPL_RCVD))
+ cxgbi_sock_set_flag(csk, CTPF_ABORT_RPL_RCVD);
+ else {
+ cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_RCVD);
+ cxgbi_sock_clear_flag(csk, CTPF_ABORT_RPL_PENDING);
+
+ if (cxgbi_sock_flag(csk, CTPF_ABORT_REQ_RCVD))
+ cxgbi_log_error("tid %u, ABORT_RPL_RSS\n",
+ csk->hwtid);
+
+ cxgbi_sock_closed(csk);
+ }
+ }
+
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+out:
+ __kfree_skb(skb);
+ return 0;
+}
+
+static int cxgb4i_cpl_iscsi_hdr(struct cxgb4i_snic *snic, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_iscsi_hdr *cpl = (struct cpl_iscsi_hdr *)skb->data;
+ unsigned int hwtid = GET_TID(cpl);
+ struct tid_info *t = snic->lldi.tids;
+ struct sk_buff *lskb;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ spin_lock_bh(&csk->lock);
+
+ if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
+ if (csk->state != CTP_ABORTING)
+ goto abort_conn;
+ }
+
+ cxgb4i_skb_tcp_seq(skb) = ntohl(cpl->seq);
+ skb_reset_transport_header(skb);
+ __skb_pull(skb, sizeof(*cpl));
+ __pskb_trim(skb, ntohs(cpl->len));
+
+ if (!csk->skb_ulp_lhdr) {
+ unsigned char *bhs;
+ unsigned int hlen, dlen;
+
+ csk->skb_ulp_lhdr = skb;
+ lskb = csk->skb_ulp_lhdr;
+ cxgb4i_skb_flags(lskb) = CTP_SKCBF_HDR_RCVD;
+
+ if (cxgb4i_skb_tcp_seq(lskb) != csk->rcv_nxt) {
+ cxgbi_log_error("tid 0x%x, CPL_ISCSI_HDR, bad seq got "
+ "0x%x, exp 0x%x\n",
+ csk->hwtid,
+ cxgb4i_skb_tcp_seq(lskb),
+ csk->rcv_nxt);
+ goto abort_conn;
+ }
+
+ bhs = lskb->data;
+ hlen = ntohs(cpl->len);
+ dlen = ntohl(*(unsigned int *)(bhs + 4)) & 0xFFFFFF;
+
+ if ((hlen + dlen) != ntohs(cpl->pdu_len_ddp) - 40) {
+ cxgbi_log_error("tid 0x%x, CPL_ISCSI_HDR, pdu len "
+ "mismatch %u != %u + %u, seq 0x%x\n",
+ csk->hwtid,
+ ntohs(cpl->pdu_len_ddp) - 40,
+ hlen, dlen, cxgb4i_skb_tcp_seq(skb));
+ }
+ cxgb4i_skb_rx_pdulen(skb) = hlen + dlen;
+ if (dlen)
+ cxgb4i_skb_rx_pdulen(skb) += csk->dcrc_len;
+ cxgb4i_skb_rx_pdulen(skb) =
+ ((cxgb4i_skb_rx_pdulen(skb) + 3) & (~3));
+ csk->rcv_nxt += cxgb4i_skb_rx_pdulen(skb);
+ } else {
+ lskb = csk->skb_ulp_lhdr;
+ cxgb4i_skb_flags(lskb) |= CTP_SKCBF_DATA_RCVD;
+ cxgb4i_skb_flags(skb) = CTP_SKCBF_DATA_RCVD;
+ cxgbi_log_debug("csk 0x%p, tid 0x%x skb 0x%p, pdu data, "
+ " header 0x%p.\n",
+ csk, csk->hwtid, skb, lskb);
+ }
+
+ __skb_queue_tail(&csk->receive_queue, skb);
+ spin_unlock_bh(&csk->lock);
+ return 0;
+abort_conn:
+ cxgb4i_sock_send_abort_req(csk);
+ __kfree_skb(skb);
+ spin_unlock_bh(&csk->lock);
+ return -EINVAL;
+}
+
+static int cxgb4i_cpl_rx_data_ddp(struct cxgb4i_snic *snic, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct sk_buff *lskb;
+ struct cpl_rx_data_ddp *rpl = (struct cpl_rx_data_ddp *)skb->data;
+ unsigned int hwtid = GET_TID(rpl);
+ struct tid_info *t = snic->lldi.tids;
+ unsigned int status;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ spin_lock_bh(&csk->lock);
+
+ if (unlikely(csk->state >= CTP_PASSIVE_CLOSE)) {
+ if (csk->state != CTP_ABORTING)
+ goto abort_conn;
+ }
+
+ if (!csk->skb_ulp_lhdr) {
+ cxgbi_log_error("tid 0x%x, rcv RX_DATA_DDP w/o pdu header\n",
+ csk->hwtid);
+ goto abort_conn;
+ }
+
+ lskb = csk->skb_ulp_lhdr;
+ cxgb4i_skb_flags(lskb) |= CTP_SKCBF_STATUS_RCVD;
+
+ if (ntohs(rpl->len) != cxgb4i_skb_rx_pdulen(lskb)) {
+ cxgbi_log_error("tid 0x%x, RX_DATA_DDP pdulen %u != %u.\n",
+ csk->hwtid, ntohs(rpl->len),
+ cxgb4i_skb_rx_pdulen(lskb));
+ }
+
+ cxgb4i_skb_rx_ddigest(lskb) = ntohl(rpl->ulp_crc);
+ status = ntohl(rpl->ddpvld);
+
+ if (status & (1 << RX_DDP_STATUS_HCRC_SHIFT)) {
+ cxgbi_log_info("ULP2_FLAG_HCRC_ERROR set\n");
+ cxgb4i_skb_ulp_mode(skb) |= ULP2_FLAG_HCRC_ERROR;
+ }
+ if (status & (1 << RX_DDP_STATUS_DCRC_SHIFT)) {
+ cxgbi_log_info("ULP2_FLAG_DCRC_ERROR set\n");
+ cxgb4i_skb_ulp_mode(skb) |= ULP2_FLAG_DCRC_ERROR;
+ }
+ if (status & (1 << RX_DDP_STATUS_PAD_SHIFT)) {
+ cxgbi_log_info("ULP2_FLAG_PAD_ERROR set\n");
+ cxgb4i_skb_ulp_mode(skb) |= ULP2_FLAG_PAD_ERROR;
+ }
+ if ((cxgb4i_skb_flags(lskb) & ULP2_FLAG_DATA_READY)) {
+ cxgbi_log_info("ULP2_FLAG_DATA_DDPED set\n");
+ cxgb4i_skb_ulp_mode(skb) |= ULP2_FLAG_DATA_DDPED;
+ }
+
+ csk->skb_ulp_lhdr = NULL;
+ __kfree_skb(skb);
+ cxgbi_conn_pdu_ready(csk);
+ spin_unlock_bh(&csk->lock);
+ return 0;
+abort_conn:
+ cxgb4i_sock_send_abort_req(csk);
+ __kfree_skb(skb);
+ spin_unlock_bh(&csk->lock);
+ return -EINVAL;
+}
+
+static void check_wr_invariants(const struct cxgbi_sock *csk)
+{
+ int pending = cxgb4i_sock_count_pending_wrs(csk);
+
+ if (unlikely(csk->wr_cred + pending != csk->wr_max_cred))
+ printk(KERN_ERR "TID %u: credit imbalance: avail %u, "
+ "pending %u, total should be %u\n",
+ csk->hwtid,
+ csk->wr_cred,
+ pending,
+ csk->wr_max_cred);
+}
+
+static int cxgb4i_cpl_fw4_ack(struct cxgb4i_snic *snic, struct sk_buff *skb)
+{
+ struct cxgbi_sock *csk;
+ struct cpl_fw4_ack *rpl = (struct cpl_fw4_ack *)skb->data;
+ unsigned int hwtid = GET_TID(rpl);
+ struct tid_info *t = snic->lldi.tids;
+ unsigned char credits;
+ unsigned int snd_una;
+
+ csk = lookup_tid(t, hwtid);
+ if (unlikely(!csk)) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ kfree_skb(skb);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ credits = rpl->credits;
+ snd_una = be32_to_cpu(rpl->snd_una);
+ cxgbi_tx_debug("%u WR credits, avail %u, unack %u, TID %u, state %u\n",
+ credits, csk->wr_cred, csk->wr_una_cred,
+ csk->hwtid, csk->state);
+ csk->wr_cred += credits;
+
+ if (csk->wr_una_cred > csk->wr_max_cred - csk->wr_cred)
+ csk->wr_una_cred = csk->wr_max_cred - csk->wr_cred;
+
+ while (credits) {
+ struct sk_buff *p = cxgb4i_sock_peek_wr(csk);
+
+ if (unlikely(!p)) {
+ cxgbi_log_error("%u WR_ACK credits for TID %u with "
+ "nothing pending, state %u\n",
+ credits, csk->hwtid, csk->state);
+ break;
+ }
+
+ if (unlikely(credits < p->csum))
+ p->csum -= credits;
+ else {
+ cxgb4i_sock_dequeue_wr(csk);
+ credits -= p->csum;
+ kfree_skb(p);
+ }
+ }
+
+ check_wr_invariants(csk);
+
+ if (rpl->seq_vld) {
+ if (unlikely(before(snd_una, csk->snd_una))) {
+ cxgbi_log_error("TID %u, unexpected sequence # %u "
+ "in WR_ACK snd_una %u\n",
+ csk->hwtid, snd_una, csk->snd_una);
+ goto out_free;
+ }
+ }
+
+ if (csk->snd_una != snd_una) {
+ csk->snd_una = snd_una;
+ dst_confirm(csk->dst);
+ }
+
+ if (skb_queue_len(&csk->write_queue)) {
+ if (cxgb4i_sock_push_tx_frames(csk, 0))
+ cxgbi_conn_tx_open(csk);
+ } else
+ cxgbi_conn_tx_open(csk);
+
+ goto out;
+out_free:
+ __kfree_skb(skb);
+out:
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ return 0;
+}
+
+static int cxgb4i_cpl_set_tcb_rpl(struct cxgb4i_snic *snic, struct sk_buff *skb)
+{
+ struct cpl_set_tcb_rpl *rpl = (struct cpl_set_tcb_rpl *)skb->data;
+ unsigned int hwtid = GET_TID(rpl);
+ struct tid_info *t = snic->lldi.tids;
+ struct cxgbi_sock *csk;
+
+ csk = lookup_tid(t, hwtid);
+ if (!csk) {
+ cxgbi_log_error("can't find connection for tid %u\n", hwtid);
+ __kfree_skb(skb);
+ return CPL_RET_UNKNOWN_TID;
+ }
+
+ spin_lock_bh(&csk->lock);
+
+ if (rpl->status != CPL_ERR_NONE) {
+ cxgbi_log_error("Unexpected SET_TCB_RPL status %u "
+ "for tid %u\n", rpl->status, GET_TID(rpl));
+ }
+
+ __kfree_skb(skb);
+ spin_unlock_bh(&csk->lock);
+ return 0;
+}
+
+static void cxgb4i_sock_free_cpl_skbs(struct cxgbi_sock *csk)
+{
+ if (csk->cpl_close)
+ kfree_skb(csk->cpl_close);
+ if (csk->cpl_abort_req)
+ kfree_skb(csk->cpl_abort_req);
+ if (csk->cpl_abort_rpl)
+ kfree_skb(csk->cpl_abort_rpl);
+}
+
+static int cxgb4i_alloc_cpl_skbs(struct cxgbi_sock *csk)
+{
+ int wrlen;
+
+ wrlen = roundup(sizeof(struct cpl_close_con_req), 16);
+ csk->cpl_close = alloc_skb(wrlen, GFP_NOIO);
+ if (!csk->cpl_close)
+ return -ENOMEM;
+ skb_put(csk->cpl_close, wrlen);
+
+ wrlen = roundup(sizeof(struct cpl_abort_req), 16);
+ csk->cpl_abort_req = alloc_skb(wrlen, GFP_NOIO);
+ if (!csk->cpl_abort_req)
+ goto free_cpl_skbs;
+ skb_put(csk->cpl_abort_req, wrlen);
+
+ wrlen = roundup(sizeof(struct cpl_abort_rpl), 16);
+ csk->cpl_abort_rpl = alloc_skb(wrlen, GFP_NOIO);
+ if (!csk->cpl_abort_rpl)
+ goto free_cpl_skbs;
+ skb_put(csk->cpl_abort_rpl, wrlen);
+ return 0;
+free_cpl_skbs:
+ cxgb4i_sock_free_cpl_skbs(csk);
+ return -ENOMEM;
+}
+
+static void cxgb4i_sock_release_offload_resources(struct cxgbi_sock *csk)
+{
+
+ cxgb4i_sock_free_cpl_skbs(csk);
+
+ if (csk->wr_cred != csk->wr_max_cred) {
+ cxgb4i_sock_purge_wr_queue(csk);
+ cxgb4i_sock_reset_wr_list(csk);
+ }
+
+ if (csk->l2t) {
+ cxgb4_l2t_release(csk->l2t);
+ csk->l2t = NULL;
+ }
+
+ if (csk->state == CTP_CONNECTING)
+ cxgb4i_sock_free_atid(csk);
+ else {
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(csk->cdev);
+ cxgb4_remove_tid(snic->lldi.tids, 0, csk->hwtid);
+ cxgbi_sock_put(csk);
+ }
+
+ csk->dst = NULL;
+ csk->cdev = NULL;
+}
+
+static int cxgb4i_init_act_open(struct cxgbi_sock *csk,
+ struct net_device *dev)
+{
+ struct dst_entry *dst = csk->dst;
+ struct sk_buff *skb;
+ struct port_info *pi = netdev_priv(dev);
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(csk->cdev);
+ int offs;
+
+ cxgbi_conn_debug("csk 0x%p, state %u, flags 0x%lx\n",
+ csk, csk->state, csk->flags);
+
+ csk->atid = cxgb4_alloc_atid(snic->lldi.tids, csk);
+ if (csk->atid == -1) {
+ cxgbi_log_error("cannot alloc atid\n");
+ goto out_err;
+ }
+
+ csk->l2t = cxgb4_l2t_get(snic->lldi.l2t, csk->dst->neighbour, dev, 0);
+ if (!csk->l2t) {
+ cxgbi_log_error("cannot alloc l2t\n");
+ goto free_atid;
+ }
+
+ skb = alloc_skb(sizeof(struct cpl_act_open_req), GFP_NOIO);
+ if (!skb)
+ goto free_l2t;
+
+ skb->sk = (struct sock *)csk;
+ t4_set_arp_err_handler(skb, csk, cxgb4i_act_open_req_arp_failure);
+ cxgbi_sock_hold(csk);
+ offs = snic->lldi.ntxq / snic->lldi.nchan;
+ csk->txq_idx = pi->port_id * offs;
+ cxgbi_log_debug("csk->txq_idx : %d\n", csk->txq_idx);
+ offs = snic->lldi.nrxq / snic->lldi.nchan;
+ csk->rss_qid = snic->lldi.rxq_ids[pi->port_id * offs];
+ cxgbi_log_debug("csk->rss_qid : %d\n", csk->rss_qid);
+ csk->wr_max_cred = csk->wr_cred = snic->lldi.wr_cred;
+ csk->port_id = pi->port_id;
+ csk->tx_chan = cxgb4_port_chan(dev);
+ csk->smac_idx = csk->tx_chan << 1;
+ csk->wr_una_cred = 0;
+ csk->mss_idx = cxgbi_sock_select_mss(csk, dst_mtu(dst));
+ csk->err = 0;
+ cxgb4i_sock_reset_wr_list(csk);
+ cxgb4i_sock_make_act_open_req(csk, skb,
+ ((csk->rss_qid << 14) |
+ (csk->atid)), csk->l2t);
+ cxgb4_l2t_send(csk->cdev->ports[csk->port_id], skb, csk->l2t);
+ return 0;
+free_l2t:
+ cxgb4_l2t_release(csk->l2t);
+free_atid:
+ cxgb4i_sock_free_atid(csk);
+out_err:
+ return -EINVAL;;
+}
+
+static void cxgb4i_sock_rx_credits(struct cxgbi_sock *csk, int copied)
+{
+ int must_send;
+ u32 credits;
+
+ if (csk->state != CTP_ESTABLISHED)
+ return;
+
+ credits = csk->copied_seq - csk->rcv_wup;
+ if (unlikely(!credits))
+ return;
+
+ if (unlikely(cxgb4i_rx_credit_thres == 0))
+ return;
+
+ must_send = credits + 16384 >= cxgb4i_rcv_win;
+
+ if (must_send || credits >= cxgb4i_rx_credit_thres)
+ csk->rcv_wup += cxgb4i_csk_send_rx_credits(csk, credits);
+}
+
+static int cxgb4i_sock_send_pdus(struct cxgbi_sock *csk, struct sk_buff *skb)
+{
+ struct sk_buff *next;
+ int err, copied = 0;
+
+ spin_lock_bh(&csk->lock);
+
+ if (csk->state != CTP_ESTABLISHED) {
+ cxgbi_tx_debug("csk 0x%p, not in est. state %u.\n",
+ csk, csk->state);
+ err = -EAGAIN;
+ goto out_err;
+ }
+
+ if (csk->err) {
+ cxgbi_tx_debug("csk 0x%p, err %d.\n", csk, csk->err);
+ err = -EPIPE;
+ goto out_err;
+ }
+
+ if (csk->write_seq - csk->snd_una >= cxgb4i_snd_win) {
+ cxgbi_tx_debug("csk 0x%p, snd %u - %u > %u.\n",
+ csk, csk->write_seq, csk->snd_una,
+ cxgb4i_snd_win);
+ err = -ENOBUFS;
+ goto out_err;
+ }
+
+ while (skb) {
+ int frags = skb_shinfo(skb)->nr_frags +
+ (skb->len != skb->data_len);
+
+ if (unlikely(skb_headroom(skb) < CXGB4I_TX_HEADER_LEN)) {
+ cxgbi_tx_debug("csk 0x%p, skb head.\n", csk);
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ if (frags >= SKB_WR_LIST_SIZE) {
+ cxgbi_log_error("csk 0x%p, tx frags %d, len %u,%u.\n",
+ csk, skb_shinfo(skb)->nr_frags,
+ skb->len, skb->data_len);
+ err = -EINVAL;
+ goto out_err;
+ }
+
+ next = skb->next;
+ skb->next = NULL;
+ cxgb4i_sock_skb_entail(csk, skb, CTP_SKCBF_NO_APPEND |
+ CTP_SKCBF_NEED_HDR);
+ copied += skb->len;
+ csk->write_seq += skb->len + ulp_extra_len(skb);
+ skb = next;
+ }
+done:
+ if (likely(skb_queue_len(&csk->write_queue)))
+ cxgb4i_sock_push_tx_frames(csk, 1);
+ spin_unlock_bh(&csk->lock);
+ return copied;
+out_err:
+ if (copied == 0 && err == -EPIPE)
+ copied = csk->err ? csk->err : -EPIPE;
+ else
+ copied = err;
+ goto done;
+}
+
+static void tx_skb_setmode(struct sk_buff *skb, int hcrc, int dcrc)
+{
+ u8 submode = 0;
+
+ if (hcrc)
+ submode |= 1;
+ if (dcrc)
+ submode |= 2;
+ cxgb4i_skb_ulp_mode(skb) = (ULP_MODE_ISCSI << 4) | submode;
+}
+
+static inline __u16 get_skb_ulp_mode(struct sk_buff *skb)
+{
+ return cxgb4i_skb_ulp_mode(skb);
+}
+
+static inline __u16 get_skb_flags(struct sk_buff *skb)
+{
+ return cxgb4i_skb_flags(skb);
+}
+
+static inline __u32 get_skb_tcp_seq(struct sk_buff *skb)
+{
+ return cxgb4i_skb_tcp_seq(skb);
+}
+
+static inline __u32 get_skb_rx_pdulen(struct sk_buff *skb)
+{
+ return cxgb4i_skb_rx_pdulen(skb);
+}
+
+static cxgb4i_cplhandler_func cxgb4i_cplhandlers[NUM_CPL_CMDS] = {
+ [CPL_ACT_ESTABLISH] = cxgb4i_cpl_act_establish,
+ [CPL_ACT_OPEN_RPL] = cxgb4i_cpl_act_open_rpl,
+ [CPL_PEER_CLOSE] = cxgb4i_cpl_peer_close,
+ [CPL_ABORT_REQ_RSS] = cxgb4i_cpl_abort_req_rss,
+ [CPL_ABORT_RPL_RSS] = cxgb4i_cpl_abort_rpl_rss,
+ [CPL_CLOSE_CON_RPL] = cxgb4i_cpl_close_con_rpl,
+ [CPL_FW4_ACK] = cxgb4i_cpl_fw4_ack,
+ [CPL_ISCSI_HDR] = cxgb4i_cpl_iscsi_hdr,
+ [CPL_SET_TCB_RPL] = cxgb4i_cpl_set_tcb_rpl,
+ [CPL_RX_DATA_DDP] = cxgb4i_cpl_rx_data_ddp
+};
+
+int cxgb4i_ofld_init(struct cxgbi_device *cdev)
+{
+ struct cxgb4i_snic *snic = cxgbi_cdev_priv(cdev);
+ struct cxgbi_ports_map *ports;
+ int mapsize;
+
+ if (cxgb4i_max_connect > CXGB4I_MAX_CONN)
+ cxgb4i_max_connect = CXGB4I_MAX_CONN;
+
+ mapsize = (cxgb4i_max_connect * sizeof(struct cxgbi_sock));
+ ports = cxgbi_alloc_big_mem(sizeof(*ports) + mapsize, GFP_KERNEL);
+ if (!ports)
+ return -ENOMEM;
+
+ spin_lock_init(&ports->lock);
+ cdev->pmap = ports;
+ cdev->pmap->max_connect = cxgb4i_max_connect;
+ cdev->pmap->sport_base = cxgb4i_sport_base;
+ cdev->set_skb_txmode = tx_skb_setmode;
+ cdev->get_skb_ulp_mode = get_skb_ulp_mode;
+ cdev->get_skb_flags = get_skb_flags;
+ cdev->get_skb_tcp_seq = get_skb_tcp_seq;
+ cdev->get_skb_rx_pdulen = get_skb_rx_pdulen;
+ cdev->release_offload_resources = cxgb4i_sock_release_offload_resources;
+ cdev->sock_send_pdus = cxgb4i_sock_send_pdus;
+ cdev->send_abort_req = cxgb4i_sock_send_abort_req;
+ cdev->send_close_req = cxgb4i_sock_send_close_req;
+ cdev->sock_rx_credits = cxgb4i_sock_rx_credits;
+ cdev->alloc_cpl_skbs = cxgb4i_alloc_cpl_skbs;
+ cdev->init_act_open = cxgb4i_init_act_open;
+ snic->handlers = cxgb4i_cplhandlers;
+ return 0;
+}
+
+void cxgb4i_ofld_cleanup(struct cxgbi_device *cdev)
+{
+ struct cxgbi_sock *csk;
+ int i;
+
+ for (i = 0; i < cdev->pmap->max_connect; i++) {
+ if (cdev->pmap->port_csk[i]) {
+ csk = cdev->pmap->port_csk[i];
+ cdev->pmap->port_csk[i] = NULL;
+
+ cxgbi_sock_hold(csk);
+ spin_lock_bh(&csk->lock);
+ cxgbi_sock_closed(csk);
+ spin_unlock_bh(&csk->lock);
+ cxgbi_sock_put(csk);
+ }
+ }
+ cxgbi_free_big_mem(cdev->pmap);
+}
--
1.6.6.1
--
You received this message because you are subscribed to the Google Groups "open-iscsi" group.
To post to this group, send email to open-iscsi-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
To unsubscribe from this group, send email to open-iscsi+unsubscribe-/JYPxA39Uh5TLH3MbocFF+G/Ez6ZCGd0@public.gmane.org
For more options, visit this group at http://groups.google.com/group/open-iscsi?hl=en.
^ permalink raw reply related
* Re: [PATCH net-2.6] pkt_sched: gen_estimator: add a new lock
From: Changli Gao @ 2010-06-08 5:20 UTC (permalink / raw)
To: Eric Dumazet
Cc: David Miller, netdev, Stephen Hemminger, Jarek Poplawski,
Patrick McHardy
In-Reply-To: <1275973091.2775.51.camel@edumazet-laptop>
On Tue, Jun 8, 2010 at 12:58 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> Le mardi 08 juin 2010 à 09:00 +0800, Changli Gao a écrit :
>
>> and I think gen_replace_estimator is expected to be an atomic operation.
>>
>> And gen_estimator_active() is also assumed to be called with RTNL locked.
>>
>
> My patch fixes a bug of new/kill operators, regardless of RTNL being
> held or not. Its should be small enough to be included in linux-2.6.35.
>
> If what you say is right, all gen_replace_estimator() /
> gen_estimator_active() callers should still holds RTNL.
> I didnt change this part.
> If you believe one caller doesnt hold RTNL, please submit another patch.
>
> Then, in net-next-2.6, we can probably cleanup this to remove RTNL
> requirement if possible for gen_replace_estimator() /
> gen_estimator_active()
>
> Yes, it sounds a bit difficult (three patches instead of a single one),
> but this is the how things should be done, step by step.
>
IMO, this bug should be fixed by adding rtnl_lock to xt_RATEEST.c.
Killing rtnl should be done in separated patches. They are different
things. Your patch introduces another locks, and it is extra overhead
for other users.
--
Regards,
Changli Gao(xiaosuo@gmail.com)
^ permalink raw reply
* [RFC PATCH 0/5] netdev: show a process of packets
From: Koki Sanagi @ 2010-06-08 5:25 UTC (permalink / raw)
To: netdev; +Cc: davem, kaneshige.kenji, izumi.taku
These patch-set adds tracepoints to show us a process of packets.
Using these tracepoints and existing points, we can get the time when
packet passes through some points in transmit or receive sequence.
For example, this is an output of perf script which is attached by patch 5/5.
79074.756672832sec cpu=1
irq_entry(+0.000000msec,irq=77:eth3)
|------------softirq_raise(+0.001277msec)
irq_exit (+0.002278msec) |
|
softirq_entry(+0.003562msec)
|
|---netif_receive_skb(+0.006279msec,len=100)
| |
| skb_copy_datagram_iovec(+0.038778msec, 2285:sshd)
|
napi_poll_exit(+0.017160msec, eth3)
|
softirq_exit(+0.018248msec)
The above is a receive side. Like this, it can show receive sequence from
interrupt(irq_entry) to application(skb_copy_datagram_iovec). There are 8
tracepoints in this side. All events except for skb_copy_datagram_iovec can be
associated with each other by CPU number. skb_copy_datagram_iovec can be
associated with netif_receive_skb by skbaddr.
This script shows one NET_RX softirq and events related to it. All relative
time bases on first irq_entry which raise NET_RX softirq.
dev len dev_queue_xmit|----------|dev_hard_start_xmit|-----|free_skb
| | |
eth3 114 79044.417123332sec 0.005242msec 0.103843msec
eth3 114 79044.580090422sec 0.002306msec 0.103632msec
eth3 114 79044.719078251sec 0.002288msec 0.104093msec
The above is a transmit side. There are three tracepoints in this side.
Point1 is before putting a packet to Qdisc. point2 is after ndo_start_xmit in
dev_hard_start_xmit. It indicates finishing putting a packet to driver.
point3 is in consume_skb and dev_kfree_skb_irq. It indicates freeing a
transmitted packet.
Values of this script are, from left, device name, length of a packet, a time of
point1, an interval time between point1 and point2 and an interval time between
point2 and point3.
These times are useful to analyze a performance or to detect a point where
packet delays. For example,
- NET_RX softirq calling is late.
- Application is late to take a packet.
- It takes much time to put a transmitting packet to driver
(It may be caused by packed queue)
And also, these tracepoint help us to investigate a network driver's trouble
from memory dump because ftrace records it to memory. And ftrace is so light
even if always trace on. So, in a case investigating a problem which doesn't
reproduce, it is useful.
Thanks,
Koki Sanagi.
^ 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