* [PATCH 4/4] [CCID3]: Redundant debugging output / documentation
From: Gerrit Renker @ 2007-12-10 13:11 UTC (permalink / raw)
To: acme; +Cc: dccp, netdev, Gerrit Renker
In-Reply-To: <1197292318-29659-4-git-send-email-gerrit@erg.abdn.ac.uk>
Each time feedback is sent two lines are printed:
ccid3_hc_rx_send_feedback: client ... - entry
ccid3_hc_rx_send_feedback: Interval ...usec, X_recv=..., 1/p=...
The first line is redundant and thus removed.
Further, documentation of ccid3_hc_rx_sock (capitalisation) is made consistent.
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
---
net/dccp/ccids/ccid3.c | 2 --
net/dccp/ccids/ccid3.h | 4 ++--
2 files changed, 2 insertions(+), 4 deletions(-)
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 60fcb31..b92069b 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -685,8 +685,6 @@ static void ccid3_hc_rx_send_feedback(struct sock *sk,
ktime_t now;
s64 delta = 0;
- ccid3_pr_debug("%s(%p) - entry \n", dccp_role(sk), sk);
-
if (unlikely(hcrx->ccid3hcrx_state == TFRC_RSTATE_TERM))
return;
diff --git a/net/dccp/ccids/ccid3.h b/net/dccp/ccids/ccid3.h
index 3c33dc6..6ceeb80 100644
--- a/net/dccp/ccids/ccid3.h
+++ b/net/dccp/ccids/ccid3.h
@@ -135,9 +135,9 @@ enum ccid3_hc_rx_states {
*
* @ccid3hcrx_x_recv - Receiver estimate of send rate (RFC 3448 4.3)
* @ccid3hcrx_rtt - Receiver estimate of rtt (non-standard)
- * @ccid3hcrx_p - current loss event rate (RFC 3448 5.4)
+ * @ccid3hcrx_p - Current loss event rate (RFC 3448 5.4)
* @ccid3hcrx_last_counter - Tracks window counter (RFC 4342, 8.1)
- * @ccid3hcrx_state - receiver state, one of %ccid3_hc_rx_states
+ * @ccid3hcrx_state - Receiver state, one of %ccid3_hc_rx_states
* @ccid3hcrx_bytes_recv - Total sum of DCCP payload bytes
* @ccid3hcrx_tstamp_last_feedback - Time at which last feedback was sent
* @ccid3hcrx_tstamp_last_ack - Time at which last feedback was sent
--
1.5.3.GIT
^ permalink raw reply related
* [PATCH 2/4] [PATCH v2] [TFRC]: Loss interval code needs the macros/inlines that were moved
From: Gerrit Renker @ 2007-12-10 13:11 UTC (permalink / raw)
To: acme; +Cc: dccp, netdev, Gerrit Renker
In-Reply-To: <1197292318-29659-2-git-send-email-gerrit@erg.abdn.ac.uk>
This moves the inlines (which were previously declared as macros) back into packet_history.h since
the loss detection code needs to be able to read entries from the RX history in order to create the
relevant loss entries: it needs at least tfrc_rx_hist_loss_prev() and tfrc_rx_hist_last_rcv(), which
in turn require the definition of the other inlines (macros).
Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk>
---
net/dccp/ccids/lib/packet_history.c | 35 -----------------------------------
net/dccp/ccids/lib/packet_history.h | 35 +++++++++++++++++++++++++++++++++++
2 files changed, 35 insertions(+), 35 deletions(-)
diff --git a/net/dccp/ccids/lib/packet_history.c b/net/dccp/ccids/lib/packet_history.c
index 1346045..22114c6 100644
--- a/net/dccp/ccids/lib/packet_history.c
+++ b/net/dccp/ccids/lib/packet_history.c
@@ -151,41 +151,6 @@ void tfrc_rx_packet_history_exit(void)
}
}
-/**
- * tfrc_rx_hist_index - index to reach n-th entry after loss_start
- */
-static inline u8 tfrc_rx_hist_index(const struct tfrc_rx_hist *h, const u8 n)
-{
- return (h->loss_start + n) & TFRC_NDUPACK;
-}
-
-/**
- * tfrc_rx_hist_last_rcv - entry with highest-received-seqno so far
- */
-static inline struct tfrc_rx_hist_entry *
- tfrc_rx_hist_last_rcv(const struct tfrc_rx_hist *h)
-{
- return h->ring[tfrc_rx_hist_index(h, h->loss_count)];
-}
-
-/**
- * tfrc_rx_hist_entry - return the n-th history entry after loss_start
- */
-static inline struct tfrc_rx_hist_entry *
- tfrc_rx_hist_entry(const struct tfrc_rx_hist *h, const u8 n)
-{
- return h->ring[tfrc_rx_hist_index(h, n)];
-}
-
-/**
- * tfrc_rx_hist_loss_prev - entry with highest-received-seqno before loss was detected
- */
-static inline struct tfrc_rx_hist_entry *
- tfrc_rx_hist_loss_prev(const struct tfrc_rx_hist *h)
-{
- return h->ring[h->loss_start];
-}
-
/* has the packet contained in skb been seen before? */
int tfrc_rx_hist_duplicate(struct tfrc_rx_hist *h, struct sk_buff *skb)
{
diff --git a/net/dccp/ccids/lib/packet_history.h b/net/dccp/ccids/lib/packet_history.h
index 3dfd182..e58b0fc 100644
--- a/net/dccp/ccids/lib/packet_history.h
+++ b/net/dccp/ccids/lib/packet_history.h
@@ -84,6 +84,41 @@ struct tfrc_rx_hist {
#define rtt_sample_prev loss_start
};
+/**
+ * tfrc_rx_hist_index - index to reach n-th entry after loss_start
+ */
+static inline u8 tfrc_rx_hist_index(const struct tfrc_rx_hist *h, const u8 n)
+{
+ return (h->loss_start + n) & TFRC_NDUPACK;
+}
+
+/**
+ * tfrc_rx_hist_last_rcv - entry with highest-received-seqno so far
+ */
+static inline struct tfrc_rx_hist_entry *
+ tfrc_rx_hist_last_rcv(const struct tfrc_rx_hist *h)
+{
+ return h->ring[tfrc_rx_hist_index(h, h->loss_count)];
+}
+
+/**
+ * tfrc_rx_hist_entry - return the n-th history entry after loss_start
+ */
+static inline struct tfrc_rx_hist_entry *
+ tfrc_rx_hist_entry(const struct tfrc_rx_hist *h, const u8 n)
+{
+ return h->ring[tfrc_rx_hist_index(h, n)];
+}
+
+/**
+ * tfrc_rx_hist_loss_prev - entry with highest-received-seqno before loss was detected
+ */
+static inline struct tfrc_rx_hist_entry *
+ tfrc_rx_hist_loss_prev(const struct tfrc_rx_hist *h)
+{
+ return h->ring[h->loss_start];
+}
+
extern void tfrc_rx_hist_add_packet(struct tfrc_rx_hist *h,
const struct sk_buff *skb, const u32 ndp);
--
1.5.3.GIT
^ permalink raw reply related
* [PATCH 0/4] [TFRC]: Revised Loss Intervals Patches (macro-less, new swap function)
From: Gerrit Renker @ 2007-12-10 13:11 UTC (permalink / raw)
To: acme; +Cc: dccp, netdev
This revision updates earlier patches, following discussion,
and adds one additional cleanup patch at the end.
Patch #1: Revision of initialisation patch; fixed calling __exit function
from __init function - identified by Arnaldo.
Patch #2: Revision - re-converted tfrc_rx_hist_entry() back to inline,
following discussion with Arnaldo.
Patch #3: Reworked - loss intervals database. Individual changes:
- replaced tfrc_rx_hist_swap() with routine suggested by Arnaldo;
- replaced all access macros with inlines or in-place(s);
- replaced LIH_INDEX also with inline instead of macro.
Patch #4: Removes redundant debugging output from syslog.
^ permalink raw reply
* Re: [1/4] DST: Distributed storage documentation.
From: Evgeniy Polyakov @ 2007-12-10 12:58 UTC (permalink / raw)
To: Kay Sievers; +Cc: lkml, netdev, linux-fsdevel, Greg KH
In-Reply-To: <3ae72650712100451h6a84d6cfs9b3a2954c13c4612@mail.gmail.com>
On Mon, Dec 10, 2007 at 01:51:43PM +0100, Kay Sievers (kay.sievers@vrfy.org) wrote:
> On Dec 10, 2007 12:47 PM, Evgeniy Polyakov <johnpol@2ka.mipt.ru> wrote:
> > diff --git a/Documentation/dst/sysfs.txt b/Documentation/dst/sysfs.txt
> > new file mode 100644
> > index 0000000..79d79dc
> > --- /dev/null
> > +++ b/Documentation/dst/sysfs.txt
> > @@ -0,0 +1,30 @@
> > +This file describes sysfs files created for each storage.
> > +
> > +1. Per-storage files.
> > +Each storage has its own dir /sysfs/devices/$storage_name,
>
> It's always /sys/devices/.
I meant that for each new device, it will be placed into
/sys/devices/its_name, but it can also be accessed via
/sys/bus/dst/devices/
> > +which contains following files:
> > +
> > +alg - contains name of the algorithm used to created given storage
> > +name - name of the storage
> > +nodes - map of the storage (list of nodes and their sizes and starts)
> > +remove_all_nodes - writable file which allows to remove all nodes from given
> > + storage
> > +n-$start-$cookie - per node directory, where
> > + $start - start of the given node in sectors,
> > + $cookie - unique node's id used by DST
> > +
> > +2. Per-node files.
> > +Node's files are located in /sysfs/devices/$storage_name/n-$start-$cookie
> > +directory, described above.
>
> To which class or bus do the devices you create belong? Care to show a
> "tree" or "ls -la" of the device?
It is 'dst' bus.
uganda:~/codes# ls -la /sys/devices/staorge/
total 0
drwxr-xr-x 4 root root 0 2007-12-10 11:46 .
drwxr-xr-x 9 root root 0 2007-12-10 11:46 ..
-r--r--r-- 1 root root 4096 2007-12-10 11:46 alg
lrwxrwxrwx 1 root root 0 2007-12-10 11:46 bus -> ../../bus/dst
drwxr-xr-x 3 root root 0 2007-12-10 11:46 n-0-ffff81003e24117
-r--r--r-- 1 root root 4096 2007-12-10 11:46 name
-r--r--r-- 1 root root 4096 2007-12-10 11:46 nodes
drwxr-xr-x 2 root root 0 2007-12-10 11:46 power
-rw-r--r-- 1 root root 4096 2007-12-10 11:46 remove_all_nodes
lrwxrwxrwx 1 root root 0 2007-12-10 11:46 subsystem -> ../../bus/dst
-rw-r--r-- 1 root root 4096 2007-12-10 11:46 uevent
uganda:~/codes# ls -l /sys/bus/dst/
total 0
drwxr-xr-x 2 root root 0 2007-12-10 09:52 devices
drwxr-xr-x 2 root root 0 2007-12-10 09:52 drivers
-rw-r--r-- 1 root root 4096 2007-12-10 11:46 drivers_autoprobe
--w------- 1 root root 4096 2007-12-10 11:46 drivers_probe
> Kay
--
Evgeniy Polyakov
^ permalink raw reply
* Re: [1/4] DST: Distributed storage documentation.
From: Kay Sievers @ 2007-12-10 12:51 UTC (permalink / raw)
To: Evgeniy Polyakov; +Cc: lkml, netdev, linux-fsdevel, Greg KH
In-Reply-To: <11972872501664@2ka.mipt.ru>
On Dec 10, 2007 12:47 PM, Evgeniy Polyakov <johnpol@2ka.mipt.ru> wrote:
> diff --git a/Documentation/dst/sysfs.txt b/Documentation/dst/sysfs.txt
> new file mode 100644
> index 0000000..79d79dc
> --- /dev/null
> +++ b/Documentation/dst/sysfs.txt
> @@ -0,0 +1,30 @@
> +This file describes sysfs files created for each storage.
> +
> +1. Per-storage files.
> +Each storage has its own dir /sysfs/devices/$storage_name,
It's always /sys/devices/.
> +which contains following files:
> +
> +alg - contains name of the algorithm used to created given storage
> +name - name of the storage
> +nodes - map of the storage (list of nodes and their sizes and starts)
> +remove_all_nodes - writable file which allows to remove all nodes from given
> + storage
> +n-$start-$cookie - per node directory, where
> + $start - start of the given node in sectors,
> + $cookie - unique node's id used by DST
> +
> +2. Per-node files.
> +Node's files are located in /sysfs/devices/$storage_name/n-$start-$cookie
> +directory, described above.
To which class or bus do the devices you create belong? Care to show a
"tree" or "ls -la" of the device?
Kay
^ permalink raw reply
* Re: [PATCH] [TCP]: Bind fackets_out state to highest_sack more tightly
From: Ilpo Järvinen @ 2007-12-10 12:39 UTC (permalink / raw)
To: David Miller; +Cc: Netdev
In-Reply-To: <20071210.043127.60066660.davem@davemloft.net>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 722 bytes --]
On Mon, 10 Dec 2007, David Miller wrote:
> From: "Ilpo_Järvinen" <ilpo.jarvinen@helsinki.fi>
> Date: Mon, 10 Dec 2007 14:27:24 +0200 (EET)
>
> > Added checks will catch most of the errors if the current
> > complex fack_count counting logic is flawed somewhere.
> >
> > Fackets_out should always be advancable if highest_sack is too
> > because the fackets_out is nowadays accurate (and obviously it
> > must be smaller than packets_out).
> >
> > Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
>
> Applied to net-2.6.25, thanks!
Please get the fack_count fix as well from the mm1 thread before my
mailbox gets filled with stacktraces :-) :
http://marc.info/?l=linux-netdev&m=119728952018975&w=2
--
i.
^ permalink raw reply
* Re: [PATCH] [TCP]: Bind fackets_out state to highest_sack more tightly
From: David Miller @ 2007-12-10 12:31 UTC (permalink / raw)
To: ilpo.jarvinen; +Cc: netdev
In-Reply-To: <Pine.LNX.4.64.0712101426010.18529@kivilampi-30.cs.helsinki.fi>
From: "Ilpo_Järvinen" <ilpo.jarvinen@helsinki.fi>
Date: Mon, 10 Dec 2007 14:27:24 +0200 (EET)
> Added checks will catch most of the errors if the current
> complex fack_count counting logic is flawed somewhere.
>
> Fackets_out should always be advancable if highest_sack is too
> because the fackets_out is nowadays accurate (and obviously it
> must be smaller than packets_out).
>
> Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
Applied to net-2.6.25, thanks!
^ permalink raw reply
* [PATCH] [TCP]: Bind fackets_out state to highest_sack more tightly
From: Ilpo Järvinen @ 2007-12-10 12:27 UTC (permalink / raw)
To: David Miller; +Cc: Netdev
[-- Attachment #1: Type: TEXT/PLAIN, Size: 1679 bytes --]
Added checks will catch most of the errors if the current
complex fack_count counting logic is flawed somewhere.
Fackets_out should always be advancable if highest_sack is too
because the fackets_out is nowadays accurate (and obviously it
must be smaller than packets_out).
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
---
net/ipv4/tcp_input.c | 14 +++++++++-----
1 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9499a12..23b2a34 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1270,24 +1270,28 @@ static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk,
}
}
- if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
+ fack_count += tcp_skb_pcount(skb);
+ if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) {
+ WARN_ON((fack_count <= tp->fackets_out) ||
+ (fack_count > tp->packets_out));
+
tcp_advance_highest_sack(sk, skb);
+ tp->fackets_out = fack_count;
+ } else
+ WARN_ON(fack_count > tp->fackets_out);
+
tcp_write_queue_requeue(skb, sk, TCP_WQ_SACKED);
TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED;
flag |= FLAG_DATA_SACKED;
tp->sacked_out += tcp_skb_pcount(skb);
- fack_count += tcp_skb_pcount(skb);
-
/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) &&
before(TCP_SKB_CB(skb)->seq,
TCP_SKB_CB(tp->lost_skb_hint)->seq))
tp->lost_cnt_hint += tcp_skb_pcount(skb);
- if (fack_count > tp->fackets_out)
- tp->fackets_out = fack_count;
}
/* D-SACK. We can detect redundant retransmission in S|R and plain R
--
1.5.0.6
^ permalink raw reply related
* Re: 2.6.24-rc4-mm1
From: Ilpo Järvinen @ 2007-12-10 12:24 UTC (permalink / raw)
To: Andrew Morton, Reuben Farrelly, David Miller
Cc: LKML, Linux Netdev List, Auke Kok
In-Reply-To: <20071205233504.67366c5b.akpm@linux-foundation.org>
[-- Attachment #1: Type: TEXT/PLAIN, Size: 3239 bytes --]
On Wed, 5 Dec 2007, Andrew Morton wrote:
> On Thu, 06 Dec 2007 17:59:37 +1100 Reuben Farrelly <reuben-linuxkernel@reub.net> wrote:
>
> > This non fatal oops which I have just noticed may be related to this change then
> > - certainly looks networking related.
>
> yep, but it isn't e1000. It's core TCP.
>
> > WARNING: at net/ipv4/tcp_input.c:2518 tcp_fastretrans_alert()
> > Pid: 0, comm: swapper Not tainted 2.6.24-rc4-mm1 #1
>
> Ilpo, Reuben's kernel is talking to you ;)
...Please try the patch below. Andrew, this probably fixes your problem
(the packets <= tp->packets_out) as well.
Dave, please include this one to net-2.6.25.
--
i.
--
[PATCH] [TCP]: Fix fack_count miscountings (multiple places)
1) Fack_count is set incorrectly if the highest sent skb is
already sacked (the skb->prev won't return it because it's on
the other list already). These manifest as fackets_out counting
error later on, the second-order effects are very hard to track,
so it may fix all out-standing TCP bug reports.
2) Prev == NULL check was wrong way around
3) Last skb's fack count was incorrectly skipped while() {} loop
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi>
---
include/net/tcp.h | 22 ++++++++++++++++------
1 files changed, 16 insertions(+), 6 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 9dbed0b..11a7e3e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1337,10 +1337,20 @@ static inline struct sk_buff *tcp_send_head(struct sock *sk)
static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *prev = tcp_write_queue_prev(sk, skb);
+ unsigned int fc = 0;
+
+ if (prev == (struct sk_buff *)&sk->sk_write_queue)
+ prev = NULL;
+ else if (!tcp_skb_adjacent(sk, prev, skb))
+ prev = NULL;
- if (prev != (struct sk_buff *)&sk->sk_write_queue)
- TCP_SKB_CB(skb)->fack_count = TCP_SKB_CB(prev)->fack_count +
- tcp_skb_pcount(prev);
+ if ((prev == NULL) && !__tcp_write_queue_empty(sk, TCP_WQ_SACKED))
+ prev = __tcp_write_queue_tail(sk, TCP_WQ_SACKED);
+
+ if (prev != NULL)
+ fc = TCP_SKB_CB(prev)->fack_count + tcp_skb_pcount(prev);
+
+ TCP_SKB_CB(skb)->fack_count = fc;
sk->sk_send_head = tcp_write_queue_next(sk, skb);
if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue)
@@ -1464,7 +1474,7 @@ static inline struct sk_buff *__tcp_reset_fack_counts(struct sock *sk,
{
unsigned int fc = 0;
- if (prev == NULL)
+ if (prev != NULL)
fc = TCP_SKB_CB(*prev)->fack_count + tcp_skb_pcount(*prev);
BUG_ON((*prev != NULL) && !tcp_skb_adjacent(sk, *prev, skb));
@@ -1521,7 +1531,7 @@ static inline void tcp_reset_fack_counts(struct sock *sk, struct sk_buff *inskb)
skb[otherq] = prev->next;
}
- while (skb[queue] != __tcp_write_queue_tail(sk, queue)) {
+ do {
/* Lazy find for the other queue */
if (skb[queue] == NULL) {
skb[queue] = tcp_write_queue_find(sk, TCP_SKB_CB(prev)->seq,
@@ -1535,7 +1545,7 @@ static inline void tcp_reset_fack_counts(struct sock *sk, struct sk_buff *inskb)
break;
queue ^= TCP_WQ_SACKED;
- }
+ } while (skb[queue] != __tcp_write_queue_tail(sk, queue));
}
static inline void __tcp_insert_write_queue_after(struct sk_buff *skb,
--
1.5.0.6
^ permalink raw reply related
* [PATCH 3/3] Modified Documentation to explain dts entries for UCC TDM driver.
From: Poonam_Aggrwal-b10812 @ 2007-12-10 12:13 UTC (permalink / raw)
To: rubini, kumar.gala, linux-kernel, netdev, linuxppc-dev
Cc: michael.barkowski, kim.phillips, ashish.kalra, rich.cutler
From: Poonam Aggrwal <b10812@freescale.com>
Modified Documentation to explain new properties introduced for UCC TDM
driver. Also two new nodes have been added "brg" and "clocks" to configure
a BRG from device tree.
Signed-off-by: Poonam Aggrwal <b10812@freescale.com>
Signed-off-by: Ashish Kalra <ashish.kalra@freescale.com>
Signed-off-by: Kim Phillips <Kim.Phillips@freescale.com>
Signed-off-by: Michael Barkowski <michael.barkowski@freescale.com>
---
Documentation/powerpc/booting-without-of.txt | 96 +++++++++++++++++++++++++-
1 files changed, 94 insertions(+), 2 deletions(-)
diff --git a/Documentation/powerpc/booting-without-of.txt b/Documentation/powerpc/booting-without-of.txt
index e9a3cb1..94a6b4b 100644
--- a/Documentation/powerpc/booting-without-of.txt
+++ b/Documentation/powerpc/booting-without-of.txt
@@ -1613,8 +1613,8 @@ platforms are moved over to use the flattened-device-tree model.
Required properties:
- device_type : should be "network", "hldc", "uart", "transparent"
- "bisync" or "atm".
- - compatible : could be "ucc_geth" or "fsl_atm" and so on.
+ "bisync", "atm" or "tdm".
+ - compatible : could be "ucc_geth", "fsl_atm" or "fsl,ucc_tdm" and so on.
- model : should be "UCC".
- device-id : the ucc number(1-8), corresponding to UCCx in UM.
- reg : Offset and length of the register set for the device
@@ -1666,7 +1666,44 @@ platforms are moved over to use the flattened-device-tree model.
pio-handle = <140001>;
};
+ Required properties for tdm device_type:
+ - instead of tx-clock and rx-clock following clock properties are
+ required:
+ - fsl,tdm-tx-clk : This property selects the TX clock source for TDM
+ from a bank of clocks.
+ - fsl,tdm-rx-clk : This property selects the RX clock source for TDM
+ from a bank of clocks.
+ - fsl,tdm-tx-sync : This property selects the TX Frame sync source
+ for TDM from a bank of clocks.
+ - fsl,tdm-rx-sync : This property selects the TX Frame sync source
+ for TDM from a bank of clocks.
+
+ All the above mentioned properties are string type with possible
+ values
+ "CLK1", "CLK2", "CLK3"..."CLK24" and so on
+ "BRG1", "BRG2", "BRG3"..."BRG16" and so on
+
+ - fsl,tdm-num : TDM to be used (1,2,3 or 4 for TDMA TDMB TDMC TDMD)
+ - fsl,si-num : Serial Interface to be used.
+ Example:
+ ucc@2000 {
+ device_type = "tdm";
+ compatible = "fsl,ucc-tdm";
+ model = "UCC";
+ device-id = <1>;
+ fsl,tdm-num = <1>;
+ fsl,si-num = <1>;
+ fsl,tdm-tx-clk = "CLK1";
+ fsl,tdm-rx-clk = "CLK1";
+ fsl,tdm-tx-sync = "BRG9";
+ fsl,tdm-rx-sync = "BRG9";
+ reg = <2000 200>;
+ interrupts = <20>;
+ interrupt-parent = <&qeic>;
+ pio-handle = <&ucc1pio>;
+ };
+
v) Parallel I/O Ports
This node configures Parallel I/O ports for CPUs with QE support.
@@ -1772,6 +1809,61 @@ platforms are moved over to use the flattened-device-tree model.
};
};
+ viii) Clocks (clocks)
+ This node specifies the frequency values for all the external clocks
+ viz CLK1 to CLK24 in Hz.
+
+ Required Properties:
+ - compatible : should be "fsl,cpm-clocks".
+ - #clock-cells : It specifies the number of cells occupied by clock-frequency
+ property. Currently #clock-cells = 1 is only supported and implemented.
+ This property is kept for future in case we need frequencies higher than
+ 4 GHz.
+ - clock-frequency : It is a list of u32 values to represent the frequency
+ of each external clock(CLK1 to CLK24) in Hz.Each entry occupies
+ number of cells specified by #clock-cells property(1 for now).
+
+ Example:
+
+ clocks {
+ compatible = "fsl,cpm-clocks";
+ #clock-cells = <1>;
+ /* clock freqs in Hz(for CLK1~CLK24).
+ * CLK11 is 1024KHz,
+ * all other clocks unused
+ */
+ clock-frequency = <0 0 0 0 0 0
+ 0 0 0 0 0 d#1024000 0
+ 0 0 0 0 0 0
+ 0 0 0 0 0 0>;
+ };
+
+ ix) Baud Rate Generator (BRG)
+
+ Required properties:
+ - compatible : shpuld be "fsl,cpm-brg"
+ - fsl,brg-sources : define the input clock for all 16 BRGs. The input
+ clock source could be 1 to 24 for CLK1 to CLK24. Zero means that the
+ particular BRG will be driven by QE clock(BRGCLK).
+ - reg : This property defines the address and size of the memory-mapped
+ registers of the BRG.
+
+ Example:
+
+ brg@640 {
+ compatible = "fsl,qe-brg";
+ /* input clock sources for all the 16 BRGs.
+ * 1-24 for CLK1 to CLK24.
+ * BRG9 uses CLK11 others use
+ * the QE clock.
+ */
+ fsl,brg-sources = <0 0 0 0 0 0 0 0
+ b 0 0 0 0 0 0 0>;
+ reg = <640 7f>;
+ };
+
+ In the above entry, for BRG9 the input clock is 0xb(decimal 11) ie QE_CLK11.
+
j) CFI or JEDEC memory-mapped NOR flash
Flash chips (Memory Technology Devices) are often used for solid state
--
1.5.2.4
^ permalink raw reply related
* [PATCH 2/3] arch/ : Platform changes for UCC TDM driver for MPC8323ERDB.Also includes related QE changes.
From: Poonam_Aggrwal-b10812 @ 2007-12-10 12:09 UTC (permalink / raw)
To: rubini, linux-kernel, netdev, kumar.gala, linuxppc-dev
Cc: michael.barkowski, kim.phillips, ashish.kalra, rich.cutler
From: Poonam Aggrwal <b10812@freescale.com>
This patch makes necessary changes in the QE and UCC framework to support
TDM. It also adds support to configure the BRG properly through device
tree entries. Includes the device tree changes for UCC TDM driver as well.
It also includes device tree entries for UCC TDM driver.
Tested on MPC8323ERDB platform.
Signed-off-by: Poonam Aggrwal <b10812@freescale.com>
Signed-off-by: Ashish Kalra <ashish.kalra@freescale.com>
Signed-off-by: Kim Phillips <Kim.Phillips@freescale.com>
Signed-off-by: Michael Barkowski <michael.barkowski@freescale.com>
---
arch/powerpc/boot/dts/mpc832x_rdb.dts | 58 +++++++
arch/powerpc/sysdev/qe_lib/qe.c | 128 ++++++++++++++--
arch/powerpc/sysdev/qe_lib/ucc.c | 265 +++++++++++++++++++++++++++++++++
arch/powerpc/sysdev/qe_lib/ucc_fast.c | 37 +++++
include/asm-powerpc/qe.h | 8 +
include/asm-powerpc/ucc.h | 4 +
include/asm-powerpc/ucc_fast.h | 4 +
7 files changed, 492 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/boot/dts/mpc832x_rdb.dts b/arch/powerpc/boot/dts/mpc832x_rdb.dts
index 388c8a7..333408c 100644
--- a/arch/powerpc/boot/dts/mpc832x_rdb.dts
+++ b/arch/powerpc/boot/dts/mpc832x_rdb.dts
@@ -105,6 +105,17 @@
device_type = "par_io";
num-ports = <7>;
+ ucc1pio:ucc_pin@01 {
+ pio-map = <
+ /* port pin dir open_drain assignment has_irq */
+ 0 e 2 0 1 0 /* CLK11 */
+ 3 16 1 0 2 0 /* BRG9 */
+ 3 1b 1 0 2 0 /* BRG3 */
+ 0 0 3 0 2 0 /* TDMATxD0 */
+ 0 4 3 0 2 0 /* TDMARxD0 */
+ 3 1b 2 0 1 0>; /* CLK1 */
+ };
+
ucc2pio:ucc_pin@02 {
pio-map = <
/* port pin dir open_drain assignment has_irq */
@@ -169,6 +180,36 @@
};
};
+ clocks {
+ compatible = "fsl,cpm-clocks";
+ /* clock freqs in Hz(for CLK1~CLK24).
+ * CLK11 is 1024KHz,
+ * all other clocks unused
+ * #clock-cells define number of cells
+ * used by the clock-frequency.
+ * right now only #clock cells=1 is
+ * implemented. Provision is there to
+ * handle frequencies >4Gig
+ */
+ #clock-cells = <1>;
+ clock-frequency = <0 0 0 0 0 0
+ 0 0 0 0 d#1024000 0
+ 0 0 0 0 0 0
+ 0 0 0 0 0 0>;
+ };
+
+ brg@640 {
+ compatible = "fsl,cpm-brg";
+ /* input clock sources for all the 16 BRGs.
+ * 1-24 for CLK1 to CLK24.
+ * BRG9 uses CLK11,BRG1 and BRG2-8 use
+ * the QE clock.
+ */
+ fsl,brg-sources = <0 0 0 0 0 0 0 0
+ b 0 0 0 0 0 0 0>;
+ reg = <640 7f>;
+ };
+
spi@4c0 {
device_type = "spi";
compatible = "fsl_spi";
@@ -187,6 +228,23 @@
mode = "cpu";
};
+ ucc@2000 {
+ device_type = "tdm";
+ compatible = "fsl,ucc-tdm";
+ model = "UCC";
+ device-id = <1>;
+ fsl,tdm-num = <1>;
+ fsl,si-num = <1>;
+ fsl,tdm-tx-clk = "CLK1";
+ fsl,tdm-rx-clk = "CLK1";
+ fsl,tdm-tx-sync = "BRG9";
+ fsl,tdm-rx-sync = "BRG9";
+ reg = <2000 200>;
+ interrupts = <20>;
+ interrupt-parent = <&qeic>;
+ pio-handle = <&ucc1pio>;
+ };
+
ucc@3000 {
device_type = "network";
compatible = "ucc_geth";
diff --git a/arch/powerpc/sysdev/qe_lib/qe.c b/arch/powerpc/sysdev/qe_lib/qe.c
index 1df3b4a..abcf0b4 100644
--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@@ -149,22 +149,116 @@ EXPORT_SYMBOL(qe_issue_cmd);
*/
static unsigned int brg_clk = 0;
-unsigned int get_brg_clk(void)
+u32 get_brg_clk(enum qe_clock brgclk, enum qe_clock *brg_source)
{
- struct device_node *qe;
- if (brg_clk)
- return brg_clk;
+ struct device_node *qe, *brg, *clocks;
+ enum qe_clock brg_src;
+ u32 brg_input_freq = 0;
+ u32 brg_num;
+ const unsigned int *prop;
- qe = of_find_node_by_type(NULL, "qe");
- if (qe) {
+ *brg_source = 0;
+
+ brg_num = brgclk - QE_BRG1;
+ brg = of_find_compatible_node(NULL, NULL, "fsl,cpm-brg");
+ if (brg) {
unsigned int size;
- const u32 *prop = of_get_property(qe, "brg-frequency", &size);
- brg_clk = *prop;
- of_node_put(qe);
- };
+ prop = of_get_property(brg,
+ "fsl,brg-sources", &size);
+
+ brg_src = *(prop + brg_num);
+ if (brg_src == 0) {
+ *brg_source = 0;
+ if (brg_clk > 0) {
+ of_node_put(brg);
+ return brg_clk;
+ }
+ qe = of_find_node_by_type(NULL, "qe");
+ if (qe) {
+ unsigned int size;
+ prop = of_get_property
+ (qe, "brg-frequency", &size);
+ of_node_put(qe);
+ of_node_put(brg);
+ return *prop;
+ }
+ } else {
+ *brg_source = brg_src + QE_CLK1 - 1;
+ clocks = of_find_compatible_node(NULL, NULL,
+ "fsl,cpm-clocks");
+ prop = of_get_property(clocks,
+ "#clock-cells", &size);
+ /*
+ * clock-cells = 1 only supported right now.
+ */
+ if (*prop != 1)
+ return 0;
+ prop = of_get_property(clocks,
+ "clock-frequency", &size);
+
+ brg_input_freq = *(prop+(brg_src - 1));
+ of_node_put(clocks);
+ of_node_put(brg);
+ return brg_input_freq;
+ }
+ }
return brg_clk;
}
+u32 qe_brg_src(int brg_num, enum qe_clock brg_src)
+{
+ u32 clock_bits, shift;
+
+ clock_bits = 0;
+
+ switch (brg_num) {
+ case 1:
+ case 2:
+ case 5:
+ case 6:
+ switch (brg_src) {
+ case QE_CLK3: clock_bits = 1; break;
+ case QE_CLK5: clock_bits = 2; break;
+ default: break;
+ }
+ break;
+ case 3:
+ case 4:
+ case 7:
+ case 8:
+ switch (brg_src) {
+ case QE_CLK9: clock_bits = 1; break;
+ case QE_CLK15: clock_bits = 2; break;
+ default: break;
+ }
+ break;
+ case 9:
+ case 10:
+ switch (brg_src) {
+ case QE_CLK11: clock_bits = 1; break;
+ default: break;
+ }
+ break;
+ case 11:
+ case 15:
+ case 16:
+ switch (brg_src) {
+ case QE_CLK13: clock_bits = 1; break;
+ default: break;
+ }
+ break;
+ default: clock_bits = 0; break;
+ }
+ shift = 14;
+
+ if (!clock_bits)
+ return -ENOENT;
+
+ clock_bits <<= shift;
+
+ return clock_bits;
+}
+
/* Program the BRG to the given sampling rate and multiplier
*
* @brg: the BRG, QE_BRG1 - QE_BRG16
@@ -177,11 +271,18 @@ int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier)
{
u32 divisor, tempval;
u32 div16 = 0;
+ u32 brg_clock;
+ enum qe_clock brgsrc;
+ u32 src_bits = 0;
if ((brg < QE_BRG1) || (brg > QE_BRG16))
return -EINVAL;
- divisor = get_brg_clk() / (rate * multiplier);
+ brg_clock = get_brg_clk(brg, &brgsrc);
+ if (!brg_clock)
+ return -EINVAL;
+
+ divisor = brg_clock / (rate * multiplier);
if (divisor > QE_BRGC_DIVISOR_MAX + 1) {
div16 = QE_BRGC_DIV16;
@@ -194,8 +295,11 @@ int qe_setbrg(enum qe_clock brg, unsigned int rate, unsigned int multiplier)
if (!div16 && (divisor & 1))
divisor++;
+ if (brgsrc > 0)
+ src_bits = qe_brg_src(brg - QE_BRG1 + 1, brgsrc);
+
tempval = ((divisor - 1) << QE_BRGC_DIVISOR_SHIFT) |
- QE_BRGC_ENABLE | div16;
+ QE_BRGC_ENABLE | div16 | src_bits;
out_be32(&qe_immr->brg.brgc[brg - QE_BRG1], tempval);
diff --git a/arch/powerpc/sysdev/qe_lib/ucc.c b/arch/powerpc/sysdev/qe_lib/ucc.c
index 0e348d9..f2de0ed 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc.c
@@ -213,3 +213,268 @@ int ucc_set_qe_mux_rxtx(unsigned int ucc_num, enum qe_clock clock,
return 0;
}
+
+int ucc_set_tdm_rxtx_clk(int tdm_num, char *clk_src, enum comm_dir mode)
+{
+ enum qe_clock clock;
+ u32 clock_bits, shift;
+ struct qe_mux *qe_mux_reg = NULL;
+
+ clock_bits = 0;
+ qe_mux_reg = &qe_immr->qmx;
+
+ if ((tdm_num > 3 || tdm_num < 0))
+ return -EINVAL;
+
+ /* The communications direction must be RX or TX */
+ if (!((mode == COMM_DIR_RX) || (mode == COMM_DIR_TX)))
+ return -EINVAL;
+
+ clock = qe_clock_source(clk_src);
+ switch (mode) {
+ case COMM_DIR_RX:
+ switch (tdm_num) {
+ case 0:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK3: clock_bits = 6; break;
+ case QE_CLK8: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 28;
+ break;
+ case 1:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK5: clock_bits = 6; break;
+ case QE_CLK10: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 24;
+ break;
+ case 2:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK7: clock_bits = 6; break;
+ case QE_CLK12: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 20;
+ break;
+ case 3:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK9: clock_bits = 6; break;
+ case QE_CLK14: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 16;
+ break;
+ default:
+ break;
+ }
+ break;
+ case COMM_DIR_TX:
+ switch (tdm_num) {
+ case 0:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK4: clock_bits = 6; break;
+ case QE_CLK9: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 12;
+ break;
+ case 1:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK6: clock_bits = 6; break;
+ case QE_CLK11: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 8;
+ break;
+ case 2:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK8: clock_bits = 6; break;
+ case QE_CLK13: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 4;
+ break;
+ case 3:
+ switch (clock) {
+ case QE_BRG3: clock_bits = 1; break;
+ case QE_BRG4: clock_bits = 2; break;
+ case QE_CLK1: clock_bits = 4; break;
+ case QE_CLK2: clock_bits = 5; break;
+ case QE_CLK10: clock_bits = 6; break;
+ case QE_CLK15: clock_bits = 7; break;
+ default: break;
+ }
+ shift = 0;
+ break;
+ default:
+ break;
+ }
+ break;
+ default:
+ break;
+ }
+
+ if (!clock_bits)
+ return -ENOENT;
+
+ clock_bits <<= shift;
+
+ qe_mux_reg->cmxsi1cr_l |= clock_bits;
+
+ return 0;
+}
+
+int ucc_set_tdm_rxtx_sync(int tdm_num, char *sync_src, enum comm_dir mode)
+{
+ enum qe_clock clock;
+ u32 shift, clock_bits;
+ struct qe_mux *qe_mux_reg = NULL;
+ int source;
+
+ source = -1;
+ qe_mux_reg = &qe_immr->qmx;
+
+ if ((tdm_num > 3 || tdm_num < 0))
+ return -EINVAL;
+
+ /* The communications direction must be RX or TX */
+ if (!((mode == COMM_DIR_RX) || (mode == COMM_DIR_TX)))
+ return -EINVAL;
+
+ switch (mode) {
+ case COMM_DIR_RX:
+ if (strcasecmp("RSYNC", sync_src) == 0) {
+ source = 0;
+ shift = 0;
+ break;
+ }
+ clock = qe_clock_source(sync_src);
+ switch (tdm_num) {
+ case 0:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG10: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 30;
+ break;
+ case 1:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG10: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 28;
+ break;
+ case 2:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG11: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 26;
+ break;
+ case 3:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG11: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 24;
+ break;
+ default:
+ source = -1;
+ break;
+ }
+ break;
+ case COMM_DIR_TX:
+ if (strcasecmp("TSYNC", sync_src) == 0) {
+ source = 0;
+ shift = 0;
+ break;
+ }
+ clock = qe_clock_source(sync_src);
+ switch (tdm_num) {
+ case 0:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG10: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 14;
+ break;
+ case 1:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG10: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 12;
+ break;
+ case 2:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG11: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 10;
+ break;
+ case 3:
+ switch (clock) {
+ case QE_BRG9: source = 1; break;
+ case QE_BRG11: source = 2; break;
+ default: source = -1; break;
+ }
+ shift = 8;
+ break;
+ default:
+ source = -1;
+ break;
+ }
+ break;
+ default:
+ source = -1;
+ break;
+ }
+
+ if (source == -1)
+ return -ENOENT;
+
+ clock_bits = (u32) source;
+ clock_bits <<= shift;
+
+
+ qe_mux_reg->cmxsi1syr |= clock_bits;
+
+ return 0;
+}
diff --git a/arch/powerpc/sysdev/qe_lib/ucc_fast.c b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
index 3223acb..9c8559f 100644
--- a/arch/powerpc/sysdev/qe_lib/ucc_fast.c
+++ b/arch/powerpc/sysdev/qe_lib/ucc_fast.c
@@ -327,6 +327,43 @@ int ucc_fast_init(struct ucc_fast_info * uf_info, struct ucc_fast_private ** ucc
ucc_fast_free(uccf);
return -EINVAL;
}
+ } else {
+ /* TDM Rx clock routing */
+ if ((uf_info->tdm_rx_clk != NULL) &&
+ ucc_set_tdm_rxtx_clk(uf_info->ucc_num,
+ uf_info->tdm_rx_clk, COMM_DIR_RX)) {
+ printk(KERN_ERR "%s: illegal value for TDM RX clock",
+ __FUNCTION__);
+ ucc_fast_free(uccf);
+ return -EINVAL;
+ }
+ /* TDM Tx clock routing */
+ if ((uf_info->tdm_tx_clk != NULL) &&
+ ucc_set_tdm_rxtx_clk(uf_info->ucc_num,
+ uf_info->tdm_tx_clk, COMM_DIR_TX)) {
+ printk(KERN_ERR "%s: illegal value for TDM TX clock",
+ __FUNCTION__);
+ ucc_fast_free(uccf);
+ return -EINVAL;
+ }
+ /* TDM Rx sync routing */
+ if ((uf_info->tdm_rx_sync != NULL) &&
+ ucc_set_tdm_rxtx_sync(uf_info->ucc_num,
+ uf_info->tdm_rx_sync, COMM_DIR_RX)) {
+ printk(KERN_ERR "%s: illegal value for TDM RX"
+ "Frame sync", __FUNCTION__);
+ ucc_fast_free(uccf);
+ return -EINVAL;
+ }
+ /* TDM Tx sync routing */
+ if ((uf_info->tdm_tx_sync != NULL) &&
+ ucc_set_tdm_rxtx_sync(uf_info->ucc_num,
+ uf_info->tdm_tx_sync, COMM_DIR_TX)) {
+ printk(KERN_ERR "%s: illegal value for TDM TX"
+ "Frame sync", __FUNCTION__);
+ ucc_fast_free(uccf);
+ return -EINVAL;
+ }
}
/* Set interrupt mask register at UCC level. */
diff --git a/include/asm-powerpc/qe.h b/include/asm-powerpc/qe.h
index bcf60be..51de236 100644
--- a/include/asm-powerpc/qe.h
+++ b/include/asm-powerpc/qe.h
@@ -497,6 +497,14 @@ struct ucc_slow_pram {
#define UCC_GETH_UCCE_RXF1 0x00000002
#define UCC_GETH_UCCE_RXF0 0x00000001
+/* Transparent UCC Event Register (UCCE) */
+#define UCC_TRANS_UCCE_GRA 0x0080
+#define UCC_TRANS_UCCE_TXE 0x0010
+#define UCC_TRANS_UCCE_RXF 0x0008
+#define UCC_TRANS_UCCE_BSY 0x0004
+#define UCC_TRANS_UCCE_TXB 0x0002
+#define UCC_TRANS_UCCE_RXB 0x0001
+
/* UPSMR, when used as a UART */
#define UCC_UART_UPSMR_FLC 0x8000
#define UCC_UART_UPSMR_SL 0x4000
diff --git a/include/asm-powerpc/ucc.h b/include/asm-powerpc/ucc.h
index 46b09ba..153db97 100644
--- a/include/asm-powerpc/ucc.h
+++ b/include/asm-powerpc/ucc.h
@@ -42,6 +42,10 @@ int ucc_set_qe_mux_mii_mng(unsigned int ucc_num);
int ucc_set_qe_mux_rxtx(unsigned int ucc_num, enum qe_clock clock,
enum comm_dir mode);
+int ucc_set_tdm_rxtx_clk(int tdm_num, char *clk_src, enum comm_dir mode);
+
+int ucc_set_tdm_rxtx_sync(int tdm_num, char *clk_src, enum comm_dir mode);
+
int ucc_mux_set_grant_tsa_bkpt(unsigned int ucc_num, int set, u32 mask);
/* QE MUX clock routing for UCC
diff --git a/include/asm-powerpc/ucc_fast.h b/include/asm-powerpc/ucc_fast.h
index f529f70..d267983 100644
--- a/include/asm-powerpc/ucc_fast.h
+++ b/include/asm-powerpc/ucc_fast.h
@@ -152,6 +152,10 @@ struct ucc_fast_info {
enum ucc_fast_rx_decoding_method renc;
enum ucc_fast_transparent_tcrc tcrc;
enum ucc_fast_sync_len synl;
+ char *tdm_rx_clk;
+ char *tdm_tx_clk;
+ char *tdm_rx_sync;
+ char *tdm_tx_sync;
};
struct ucc_fast_private {
--
1.5.2.4
^ permalink raw reply related
* [PATCH 1/3] drivers/misc :UCC based TDM driver for MPC83xx platforms.
From: Poonam_Aggrwal-b10812 @ 2007-12-10 12:04 UTC (permalink / raw)
To: rubini, linux-kernel, linuxppc-dev, netdev, kumar.gala
Cc: michael.barkowski, kim.phillips, ashish.kalra, rich.cutler
From: Poonam Aggrwal <b10812@freescale.com>
The UCC TDM driver basically multiplexes and demultiplexes data from
different channels. It can interface with for example SLIC kind of devices
to receive TDM data demultiplex it and send to upper applications. At the
transmit end it receives data for different channels multiplexes it and
sends them on the TDM channel. It internally uses TSA( Time Slot Assigner)
which does multiplexing and demultiplexing, UCC to perform SDMA between
host buffers and the TSA, CMX to connect TSA to UCC.
This driver will run on MPC8323E-RDB platforms.
Signed-off-by: Poonam Aggrwal <b10812@freescale.com>
Signed-off-by: Ashish Kalra <ashish.kalra@freescale.com>
Signed-off-by: Kim Phillips <Kim.Phillips@freescale.com>
Signed-off-by: Michael Barkowski <michael.barkowski@freescale.com>
---
drivers/misc/Kconfig | 21 +
drivers/misc/Makefile | 1 +
drivers/misc/ucc_tdm.c | 1068 ++++++++++++++++++++++++++++++++++++++++++++++++
drivers/misc/ucc_tdm.h | 227 ++++++++++
4 files changed, 1317 insertions(+), 0 deletions(-)
create mode 100644 drivers/misc/ucc_tdm.c
create mode 100644 drivers/misc/ucc_tdm.h
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index b5e67c0..698a72c 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -219,6 +219,27 @@ config THINKPAD_ACPI_BAY
If you are not sure, say Y here.
+config UCC_TDM
+ bool "Freescale UCC TDM Driver"
+ depends on QUICC_ENGINE && UCC_FAST
+ default n
+ ---help---
+ The TDM driver is for UCC based TDM devices for example, TDM device on
+ MPC832x RDB. Select it to run PowerVoIP on MPC832x RDB board.
+ The TDM driver can interface with SLIC kind of devices to transmit
+ and receive TDM samples. The TDM driver receives Time Division
+ multiplexed samples(for different channels) from the SLIC device,
+ demutiplexes them and sends them to the upper layers. At the transmit
+ end the TDM drivers receives samples for different channels, it
+ multiplexes them and sends them to the SLIC device.
+
+config TDM_LINEAR_PCM
+ bool "Linear PCM mode"
+ depends on UCC_TDM
+ ---help---
+ This mode should be selected if the TDM driver interface with the
+ SLIC device is linear PCM(e.g. 16 bit samples). If not selected the
+ interface will be 8 bit u-law.
config ATMEL_SSC
tristate "Device driver for Atmel SSC peripheral"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 87f2685..6f0c49d 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_SONY_LAPTOP) += sony-laptop.o
obj-$(CONFIG_THINKPAD_ACPI) += thinkpad_acpi.o
obj-$(CONFIG_FUJITSU_LAPTOP) += fujitsu-laptop.o
obj-$(CONFIG_EEPROM_93CX6) += eeprom_93cx6.o
+obj-$(CONFIG_UCC_TDM) += ucc_tdm.o
diff --git a/drivers/misc/ucc_tdm.c b/drivers/misc/ucc_tdm.c
new file mode 100644
index 0000000..232d537
--- /dev/null
+++ b/drivers/misc/ucc_tdm.c
@@ -0,0 +1,1068 @@
+/*
+ * drivers/misc/ucc_tdm.c
+ *
+ * UCC Based Linux TDM Driver
+ * This driver is designed to support UCC based TDM for PowerPC processors.
+ * This driver can interface with SLIC device to run VOIP kind of
+ * applications.
+ *
+ * Author: Ashish Kalra & Poonam Aggrwal
+ *
+ * Copyright (c) 2007 Freescale Semiconductor, 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; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/autoconf.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/skbuff.h>
+#include <linux/proc_fs.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/string.h>
+#include <linux/irq.h>
+#include <linux/of_platform.h>
+#include <linux/io.h>
+#include <linux/wait.h>
+#include <linux/timer.h>
+
+#include <asm/immap_qe.h>
+#include <asm/qe.h>
+#include <asm/ucc.h>
+#include <asm/ucc_fast.h>
+#include <asm/ucc_slow.h>
+
+#include "ucc_tdm.h"
+#define DRV_DESC "Freescale QE UCC TDM Driver"
+#define DRV_NAME "ucc_tdm"
+
+/*
+ * define the following #define if snooping or hardware-based cache coherency
+ * is disabled on the UCC transparent controller.This flag enables
+ * software-based cache-coherency support by explicitly flushing data cache
+ * contents after setting up the TDM output buffer(s) and invalidating the
+ * data cache contents before the TDM input buffer(s) are read.
+ */
+#undef UCC_CACHE_SNOOPING_DISABLED
+
+#define MAX_NUM_TDM_DEVICES 8
+
+static struct tdm_ctrl *tdm_ctrl[MAX_NUM_TDM_DEVICES];
+
+static int num_tdm_devices;
+static int num_tdm_clients;
+
+#define PREV_PHASE(x) ((x == 0) ? MAX_PHASE : (x - 1))
+#define NEXT_PHASE(x) (((x + 1) > MAX_PHASE) ? 0 : (x + 1))
+
+static struct ucc_tdm_info utdm_primary_info = {
+ .uf_info = {
+ .tsa = 1,
+ .cdp = 1,
+ .cds = 1,
+ .ctsp = 1,
+ .ctss = 1,
+ .revd = 1,
+ .urfs = 0x128,
+ .utfs = 0x128,
+ .utfet = 0,
+ .utftt = 0x128,
+ .ufpt = 256,
+ .ttx_trx = UCC_FAST_GUMR_TRANSPARENT_TTX_TRX_TRANSPARENT,
+ .tenc = UCC_FAST_TX_ENCODING_NRZ,
+ .renc = UCC_FAST_RX_ENCODING_NRZ,
+ .tcrc = UCC_FAST_16_BIT_CRC,
+ .synl = UCC_FAST_SYNC_LEN_NOT_USED,
+ },
+ .ucc_busy = 0,
+};
+
+static struct ucc_tdm_info utdm_info[8];
+
+static void dump_siram(struct tdm_ctrl *tdm_c)
+{
+#if defined(DEBUG)
+ int i;
+ u16 phy_num_ts;
+
+ phy_num_ts = tdm_c->physical_num_ts;
+
+ pr_debug("SI TxRAM dump\n");
+ /* each slot entry in SI RAM is of 2 bytes */
+ for (i = 0; i < phy_num_ts * 2; i++)
+ pr_debug("%x ", in_8(&qe_immr->sir.tx[i]));
+ pr_debug("\nSI RxRAM dump\n");
+ for (i = 0; i < phy_num_ts * 2; i++)
+ pr_debug("%x ", in_8(&qe_immr->sir.rx[i]));
+ pr_debug("\n");
+#endif
+}
+
+static void dump_ucc(struct tdm_ctrl *tdm_c)
+{
+#if defined(DEBUG)
+ struct ucc_transparent_pram *ucc_pram;
+
+ ucc_pram = tdm_c->ucc_pram;
+
+ pr_debug("%s Dumping UCC Registers\n", __FUNCTION__);
+ ucc_fast_dump_regs(tdm_c->uf_private);
+ pr_debug("%s Dumping UCC Parameter RAM\n", __FUNCTION__);
+ pr_debug("rbase = 0x%x\n", in_be32(&ucc_pram->rbase));
+ pr_debug("rbptr = 0x%x\n", in_be32(&ucc_pram->rbptr));
+ pr_debug("mrblr = 0x%x\n", in_be16(&ucc_pram->mrblr));
+ pr_debug("rbdlen = 0x%x\n", in_be16(&ucc_pram->rbdlen));
+ pr_debug("rbdstat = 0x%x\n", in_be16(&ucc_pram->rbdstat));
+ pr_debug("rstate = 0x%x\n", in_be32(&ucc_pram->rstate));
+ pr_debug("rdptr = 0x%x\n", in_be32(&ucc_pram->rdptr));
+ pr_debug("tbase = 0x%x\n", in_be32(&ucc_pram->tbase));
+ pr_debug("tbptr = 0x%x\n", in_be32(&ucc_pram->tbptr));
+ pr_debug("tbdlen = 0x%x\n", in_be16(&ucc_pram->tbdlen));
+ pr_debug("tbdstat = 0x%x\n", in_be16(&ucc_pram->tbdstat));
+ pr_debug("tstate = 0x%x\n", in_be32(&ucc_pram->tstate));
+ pr_debug("tdptr = 0x%x\n", in_be32(&ucc_pram->tdptr));
+#endif
+}
+/*
+ * converts u-law compressed samples to linear PCM
+ * If the CONFIG_TDM_LINEAR_PCM flag is not set the
+ * TDM driver receives u-law compressed data from the
+ * SLIC device. This function converts the compressed
+ * data to linear PCM and sends it to upper layers.
+ */
+static inline int ulaw2int(unsigned char log)
+{
+ u32 sign, segment, temp, quant;
+ int val;
+
+ temp = log ^ 0xFF;
+ sign = (temp & 0x80) >> 7;
+ segment = (temp & 0x70) >> 4;
+ quant = temp & 0x0F;
+ quant <<= 1;
+ quant += 33;
+ quant <<= segment;
+ if (sign)
+ val = 33 - quant;
+ else
+ val = quant - 33;
+
+ val *= 4;
+ return val;
+}
+
+/*
+ * converts linear PCM samples to u-law compressed format.
+ * If the CONFIG_TDM_LINEAR_PCM flag is not set the
+ * TDM driver calls this function to convert the PCM samples
+ * to u-law compressed format before sending them to SLIC
+ * device.
+ */
+static inline u8 int2ulaw(short linear)
+{
+ u8 quant, ret;
+ u16 output, absol, temp;
+ u32 i, sign;
+ char segment;
+
+ ret = 0;
+ if (linear >= 0)
+ linear = (linear >> 2);
+ else
+ linear = (0xc000 | (linear >> 2));
+
+ absol = abs(linear) + 33;
+ temp = absol;
+ sign = (linear >= 0) ? 1 : 0;
+ for (i = 0; i < 16; i++) {
+ output = temp & 0x8000;
+ if (output)
+ break;
+ temp <<= 1;
+ }
+ segment = 11 - i;
+ quant = (absol >> segment) & 0x0F;
+ segment--;
+ segment <<= 4;
+ output = segment + quant;
+ if (absol > 8191)
+ output = 0x7F;
+ if (sign)
+ ret ^= 0xFF;
+ else
+ ret ^= 0x7F;
+ return ret;
+}
+
+/*
+ * For use when a framing bit is not present
+ * Program current-route SI ram
+ * Set SIxRAM TDMx
+ * Entries must be in units of 8.
+ * SIR_UCC -> Channel Select
+ * SIR_CNT -> Number of bits or bytes
+ * SIR_BYTE -> Byte or Bit resolution
+ * SIR_LAST -> Indicates last entry in SIxRAM
+ * SIR_IDLE -> The Tx data pin is Tri-stated and the Rx data pin is
+ * ignored
+ */
+static void set_siram(struct tdm_ctrl *tdm_c, enum comm_dir dir)
+{
+ const u16 *mask;
+ u16 temp_mask = 1;
+ u16 siram_code = 0;
+ u32 i, j, k;
+ u32 ucc;
+ u32 phy_num_ts;
+
+ phy_num_ts = tdm_c->physical_num_ts;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+
+ if (dir == COMM_DIR_RX)
+ mask = tdm_c->rx_mask;
+ else
+ mask = tdm_c->tx_mask;
+ k = 0;
+ j = 0;
+ for (i = 0; i < phy_num_ts; i++) {
+ if ((mask[k] & temp_mask) == temp_mask)
+ siram_code = SIR_UCC(ucc) | SIR_CNT(0) | SIR_BYTE;
+ else
+ siram_code = SIR_IDLE | SIR_CNT(0) | SIR_BYTE;
+ if (dir == COMM_DIR_RX)
+ SET_RX_SI_RAM(i, siram_code);
+ else
+ SET_TX_SI_RAM(i, siram_code);
+ temp_mask = temp_mask << 1;
+ j++;
+ if (j >= 16) {
+ j = 0;
+ temp_mask = 0x0001;
+ k++;
+ }
+ }
+ siram_code = siram_code | SIR_LAST;
+
+ if (dir == COMM_DIR_RX)
+ SET_RX_SI_RAM(phy_num_ts - 1, siram_code);
+ else
+ SET_TX_SI_RAM(phy_num_ts - 1, siram_code);
+}
+
+static void config_si(struct tdm_ctrl *tdm_c)
+{
+ u8 rxsyncdelay, txsyncdelay, tdm_port;
+ u16 sixmr_val = 0;
+ u32 tdma_mode_off;
+ u16 *si1_tdm_mode_reg;
+
+ tdm_port = tdm_c->tdm_port;
+
+ set_siram(tdm_c, COMM_DIR_RX);
+
+ set_siram(tdm_c, COMM_DIR_TX);
+
+ rxsyncdelay = tdm_c->cfg_ctrl.rx_fr_sync_delay;
+ txsyncdelay = tdm_c->cfg_ctrl.tx_fr_sync_delay;
+ if (tdm_c->cfg_ctrl.com_pin)
+ sixmr_val |= SIMODE_CRT;
+ if (tdm_c->cfg_ctrl.fr_sync_level == 1)
+ sixmr_val |= SIMODE_SL;
+ if (tdm_c->cfg_ctrl.clk_edge == 1)
+ sixmr_val |= SIMODE_CE;
+ if (tdm_c->cfg_ctrl.fr_sync_edge == 1)
+ sixmr_val |= SIMODE_FE;
+ sixmr_val |= (SIMODE_TFSD(txsyncdelay) | SIMODE_RFSD(rxsyncdelay));
+
+ tdma_mode_off = SI_TDM_MODE_REGISTER_OFFSET * tdm_c->tdm_port;
+
+ si1_tdm_mode_reg = (u8 *)&qe_immr->si1 + tdma_mode_off;
+ out_be16(si1_tdm_mode_reg, sixmr_val);
+
+ dump_siram(tdm_c);
+}
+
+static int tdm_init(struct tdm_ctrl *tdm_c)
+{
+ u32 tdm_port, ucc, act_num_ts;
+ int ret, i, err;
+ u32 cecr_subblock;
+ u32 pram_offset;
+ u32 rxbdt_offset;
+ u32 txbdt_offset;
+ u32 rx_ucode_buf_offset, tx_ucode_buf_offset;
+ u16 bd_status, bd_len;
+ enum qe_clock clock;
+ struct qe_bd __iomem *rx_bd, *tx_bd;
+
+ tdm_port = tdm_c->tdm_port;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+ act_num_ts = tdm_c->cfg_ctrl.active_num_ts;
+
+ /*
+ * TDM Tx and Rx CLKs = 2048 KHz.
+ */
+ if (strstr(tdm_c->ut_info->uf_info.tdm_tx_clk, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_tx_clk);
+ err = qe_setbrg(clock, 2048000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_tx_clk);
+ return err;
+ }
+ }
+ if (strstr(tdm_c->ut_info->uf_info.tdm_rx_clk, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_rx_clk);
+ err = qe_setbrg(clock, 2048000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_rx_clk);
+ return err;
+ }
+ }
+ /*
+ * TDM FSyncs = 4 KHz.
+ */
+ if (strstr(tdm_c->ut_info->uf_info.tdm_tx_sync, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_tx_sync);
+ err = qe_setbrg(clock, 4000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_tx_sync);
+ return err;
+ }
+ }
+ if (strstr(tdm_c->ut_info->uf_info.tdm_rx_sync, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_rx_sync);
+ err = qe_setbrg(clock, 4000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_rx_sync);
+ return err;
+ }
+ }
+
+ tdm_c->ut_info->uf_info.uccm_mask = (u32)
+ ((UCC_TRANS_UCCE_RXB | UCC_TRANS_UCCE_BSY) << 16);
+
+ if (ucc_fast_init(&(tdm_c->ut_info->uf_info), &tdm_c->uf_private)) {
+ printk(KERN_ERR "%s: Failed to init uccf\n", __FUNCTION__);
+ return -ENOMEM;
+ }
+
+ ucc_fast_disable(tdm_c->uf_private, COMM_DIR_RX | COMM_DIR_TX);
+
+ /* Write to QE CECR, UCCx channel to Stop Transmission */
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+ pram_offset = qe_muram_alloc(UCC_TRANSPARENT_PRAM_SIZE,
+ ALIGNMENT_OF_UCC_SLOW_PRAM);
+ if (IS_ERR_VALUE(pram_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM memory for"
+ " transparent UCC\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto pram_alloc_error;
+ }
+
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+ QE_CR_PROTOCOL_UNSPECIFIED, pram_offset);
+
+ tdm_c->ucc_pram = qe_muram_addr(pram_offset);
+ tdm_c->ucc_pram_offset = pram_offset;
+
+ /*
+ * zero-out pram, this will also ensure RSTATE, TSTATE are cleared, also
+ * DISFC & CRCEC counters will be initialized.
+ */
+ memset(tdm_c->ucc_pram, 0, sizeof(struct ucc_transparent_pram));
+
+ /* rbase, tbase alignment is 8. */
+ rxbdt_offset = qe_muram_alloc(NR_BUFS * sizeof(struct qe_bd),
+ QE_ALIGNMENT_OF_BD);
+ if (IS_ERR_VALUE(rxbdt_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM memory for RxBDs\n",
+ __FUNCTION__);
+ ret = -ENOMEM;
+ goto rxbd_alloc_error;
+ }
+ txbdt_offset = qe_muram_alloc(NR_BUFS * sizeof(struct qe_bd),
+ QE_ALIGNMENT_OF_BD);
+ if (IS_ERR_VALUE(txbdt_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM memory for TxBDs\n",
+ __FUNCTION__);
+ ret = -ENOMEM;
+ goto txbd_alloc_error;
+ }
+ tdm_c->tx_bd = qe_muram_addr(txbdt_offset);
+ tdm_c->rx_bd = qe_muram_addr(rxbdt_offset);
+
+ tdm_c->tx_bd_offset = txbdt_offset;
+ tdm_c->rx_bd_offset = rxbdt_offset;
+
+ rx_bd = tdm_c->rx_bd;
+ tx_bd = tdm_c->tx_bd;
+
+ out_be32(&tdm_c->ucc_pram->rbase, (u32) immrbar_virt_to_phys(rx_bd));
+ out_be32(&tdm_c->ucc_pram->tbase, (u32) immrbar_virt_to_phys(tx_bd));
+
+ for (i = 0; i < NR_BUFS - 1; i++) {
+ bd_status = (u16) ((R_E | R_CM | R_I) >> 16);
+ bd_len = 0;
+ out_be16(&rx_bd->length, bd_len);
+ out_be16(&rx_bd->status, bd_status);
+ out_be32(&rx_bd->buf,
+ tdm_c->dma_input_addr + i * SAMPLE_DEPTH * act_num_ts);
+ rx_bd += 1;
+
+ bd_status = (u16) ((T_R | T_CM) >> 16);
+ bd_len = SAMPLE_DEPTH * act_num_ts;
+ out_be16(&tx_bd->length, bd_len);
+ out_be16(&tx_bd->status, bd_status);
+ out_be32(&tx_bd->buf,
+ tdm_c->dma_output_addr + i * SAMPLE_DEPTH * act_num_ts);
+ tx_bd += 1;
+ }
+
+ bd_status = (u16) ((R_E | R_CM | R_I | R_W) >> 16);
+ bd_len = 0;
+ out_be16(&rx_bd->length, bd_len);
+ out_be16(&rx_bd->status, bd_status);
+ out_be32(&rx_bd->buf,
+ tdm_c->dma_input_addr + i * SAMPLE_DEPTH * act_num_ts);
+
+ bd_status = (u16) ((T_R | T_CM | T_W) >> 16);
+ bd_len = SAMPLE_DEPTH * act_num_ts;
+ out_be16(&tx_bd->length, bd_len);
+ out_be16(&tx_bd->status, bd_status);
+ out_be32(&tx_bd->buf,
+ tdm_c->dma_output_addr + i * SAMPLE_DEPTH * act_num_ts);
+
+ config_si(tdm_c);
+
+ setbits32(&qe_immr->ic.qimr, (0x80000000 >> ucc));
+
+ rx_ucode_buf_offset = qe_muram_alloc(32, 32);
+ if (IS_ERR_VALUE(rx_ucode_buf_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM mem for Rx"
+ " ucode buf\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto rxucode_buf_alloc_error;
+ }
+
+ tx_ucode_buf_offset = qe_muram_alloc(32, 32);
+ if (IS_ERR_VALUE(tx_ucode_buf_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM mem for Tx"
+ " ucode buf\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto txucode_buf_alloc_error;
+ }
+ out_be16(&tdm_c->ucc_pram->riptr, (u16) rx_ucode_buf_offset);
+ out_be16(&tdm_c->ucc_pram->tiptr, (u16) tx_ucode_buf_offset);
+
+ tdm_c->rx_ucode_buf_offset = rx_ucode_buf_offset;
+ tdm_c->tx_ucode_buf_offset = tx_ucode_buf_offset;
+
+ /*
+ * set the receive buffer descriptor maximum size to be
+ * SAMPLE_DEPTH * number of active RX channels
+ */
+ out_be16(&tdm_c->ucc_pram->mrblr, (u16) SAMPLE_DEPTH * act_num_ts);
+
+ /*
+ * enable snooping and BE byte ordering on the UCC pram's
+ * tstate & rstate registers.
+ */
+ out_be32(&tdm_c->ucc_pram->tstate, 0x30000000);
+ out_be32(&tdm_c->ucc_pram->rstate, 0x30000000);
+
+ /*Put UCC transparent controller into serial interface mode. */
+ out_be32(&tdm_c->uf_regs->upsmr, 0);
+
+ /* Reset TX and RX for UCCx */
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_INIT_TX_RX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+ return 0;
+
+txucode_buf_alloc_error:
+ qe_muram_free(rx_ucode_buf_offset);
+rxucode_buf_alloc_error:
+ qe_muram_free(txbdt_offset);
+txbd_alloc_error:
+ qe_muram_free(rxbdt_offset);
+rxbd_alloc_error:
+ qe_muram_free(pram_offset);
+pram_alloc_error:
+ ucc_fast_free(tdm_c->uf_private);
+ return ret;
+}
+
+static void tdm_deinit(struct tdm_ctrl *tdm_c)
+{
+ qe_muram_free(tdm_c->rx_ucode_buf_offset);
+ qe_muram_free(tdm_c->tx_ucode_buf_offset);
+
+ if (tdm_c->rx_bd_offset) {
+ qe_muram_free(tdm_c->rx_bd_offset);
+ tdm_c->rx_bd = NULL;
+ tdm_c->rx_bd_offset = 0;
+ }
+ if (tdm_c->tx_bd_offset) {
+ qe_muram_free(tdm_c->tx_bd_offset);
+ tdm_c->tx_bd = NULL;
+ tdm_c->tx_bd_offset = 0;
+ }
+ if (tdm_c->ucc_pram_offset) {
+ qe_muram_free(tdm_c->ucc_pram_offset);
+ tdm_c->ucc_pram = NULL;
+ tdm_c->ucc_pram_offset = 0;
+ }
+}
+
+
+static irqreturn_t tdm_isr(int irq, void *dev_id)
+{
+ u8 *input_tdm_buffer, *output_tdm_buffer;
+ u32 txb, rxb;
+ u32 ucc;
+ register u32 ucce = 0;
+ struct tdm_ctrl *tdm_c;
+ tdm_c = (struct tdm_ctrl *)dev_id;
+
+ tdm_c->tdm_icnt++;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+ input_tdm_buffer = tdm_c->tdm_input_data;
+ output_tdm_buffer = tdm_c->tdm_output_data;
+
+ if (in_be32(tdm_c->uf_private->p_ucce) &
+ (UCC_TRANS_UCCE_BSY << 16)) {
+ out_be32(tdm_c->uf_private->p_ucce,
+ (UCC_TRANS_UCCE_BSY << 16));
+ pr_info("%s: From tdm isr busy interrupt\n",
+ __FUNCTION__);
+ dump_ucc(tdm_c);
+
+ return IRQ_HANDLED;
+ }
+
+ if (tdm_c->tdm_flag == 1) {
+ /* track phases for Rx/Tx */
+ tdm_c->phase_rx = NEXT_PHASE(tdm_c->phase_rx);
+ tdm_c->phase_tx = NEXT_PHASE(tdm_c->phase_tx);
+#if defined(CONFIG_TDM_HW_LB_TSA_SLIC)
+ {
+ u32 temp_rx, temp_tx, phase_tx, phase_rx;
+ int i;
+ phase_rx = tdm_c->phase_rx;
+ phase_tx = tdm_c->phase_tx;
+ phase_rx = PREV_PHASE(phase_rx);
+ phase_tx = PREV_PHASE(phase_tx);
+ temp_rx = phase_rx * SAMPLE_DEPTH * ACTIVE_CH;
+ temp_tx = phase_tx * SAMPLE_DEPTH * ACTIVE_CH;
+
+ /*check if loopback received data on TS0 is correct. */
+ pr_debug("%s: check if loopback received data on TS0"
+ " is correct\n", __FUNCTION__);
+ pr_debug("%d,%d ", phase_rx, phase_tx);
+ for (i = 0; i < 8; i++)
+ pr_debug("%1d,%1d ",
+ input_tdm_buffer[temp_rx + i],
+ output_tdm_buffer[temp_tx + i]);
+ pr_debug("\n");
+ }
+#endif
+
+ /* schedule BH */
+ wake_up_interruptible(&tdm_c->wakeup_event);
+ } else {
+ if (tdm_c->tdm_icnt == STUTTER_INT_CNT) {
+ txb = in_be32(&tdm_c->ucc_pram->tbptr) -
+ in_be32(&tdm_c->ucc_pram->tbase);
+ rxb = in_be32(&tdm_c->ucc_pram->rbptr) -
+ in_be32(&tdm_c->ucc_pram->rbase);
+ tdm_c->phase_tx = txb / sizeof(struct qe_bd);
+ tdm_c->phase_rx = rxb / sizeof(struct qe_bd);
+
+#if defined(CONFIG_TDM_HW_LB_TSA_SLIC)
+ tdm_c->phase_tx = tdm_c->phase_rx;
+#endif
+
+ /* signal "stuttering" period is over */
+ tdm_c->tdm_flag = 1;
+
+ pr_debug("%s: stuttering period is over\n",
+ __FUNCTION__);
+
+ if (in_be32(tdm_c->uf_private->p_ucce) &
+ (UCC_TRANS_UCCE_TXE << 16)) {
+ u32 cecr_subblock;
+ out_be32(tdm_c->uf_private->p_ucce,
+ (UCC_TRANS_UCCE_TXE << 16));
+ pr_debug("%s: From tdm isr txe interrupt\n",
+ __FUNCTION__);
+
+ cecr_subblock =
+ ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_RESTART_TX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED,
+ 0);
+ }
+ }
+ }
+
+ ucce = (in_be32(tdm_c->uf_private->p_ucce)
+ & in_be32(tdm_c->uf_private->p_uccm));
+
+ out_be32(tdm_c->uf_private->p_ucce, ucce);
+
+ return IRQ_HANDLED;
+}
+
+static int tdm_start(struct tdm_ctrl *tdm_c)
+{
+ if (request_irq(tdm_c->ut_info->uf_info.irq, tdm_isr,
+ 0, "tdm", tdm_c)) {
+ printk(KERN_ERR "%s: request_irq for tdm_isr failed\n",
+ __FUNCTION__);
+ return -ENODEV;
+ }
+
+ ucc_fast_enable(tdm_c->uf_private, COMM_DIR_RX | COMM_DIR_TX);
+
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ pr_info("%s 8-bit u-law compressed mode active\n", __FUNCTION__);
+#else
+ pr_info("%s 16-bit linear pcm mode active with"
+ " slots 0 & 2\n", __FUNCTION__);
+#endif
+
+ dump_siram(tdm_c);
+ dump_ucc(tdm_c);
+
+ setbits8(&(qe_immr->si1.siglmr1_h), (0x1 << tdm_c->tdm_port));
+ pr_info("%s UCC based TDM enabled\n", __FUNCTION__);
+
+ return 0;
+}
+
+static void tdm_stop(struct tdm_ctrl *tdm_c)
+{
+ u32 port, si;
+ u32 ucc;
+ u32 cecr_subblock;
+
+ port = tdm_c->tdm_port;
+ si = tdm_c->si;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+
+ qe_issue_cmd(QE_GRACEFUL_STOP_TX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+ qe_issue_cmd(QE_CLOSE_RX_BD, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+ clrbits8(&qe_immr->si1.siglmr1_h, (0x1 << port));
+ ucc_fast_disable(tdm_c->uf_private, COMM_DIR_RX);
+ ucc_fast_disable(tdm_c->uf_private, COMM_DIR_TX);
+ free_irq(tdm_c->ut_info->uf_info.irq, tdm_c);
+}
+
+
+static void config_tdm(struct tdm_ctrl *tdm_c)
+{
+ u32 i, j, k;
+
+ j = 0;
+ k = 0;
+
+ /* Set Mask Bits */
+ for (i = 0; i < ACTIVE_CH; i++) {
+ tdm_c->tx_mask[k] |= (1 << j);
+ tdm_c->rx_mask[k] |= (1 << j);
+ j++;
+ if (j >= 16) {
+ j = 0;
+ k++;
+ }
+ }
+ /* physical number of slots in a frame */
+ tdm_c->physical_num_ts = NUM_TS;
+
+ /* common receive and transmit pins */
+ tdm_c->cfg_ctrl.com_pin = 1;
+
+ /* L1R/TSYNC active logic "1" */
+ tdm_c->cfg_ctrl.fr_sync_level = 0;
+
+ /*
+ * TX data on rising edge of clock
+ * RX data on falling edge
+ */
+ tdm_c->cfg_ctrl.clk_edge = 0;
+
+ /* Frame sync sampled on falling edge */
+ tdm_c->cfg_ctrl.fr_sync_edge = 0;
+
+ /* no bit delay */
+ tdm_c->cfg_ctrl.rx_fr_sync_delay = 0;
+
+ /* no bit delay */
+ tdm_c->cfg_ctrl.tx_fr_sync_delay = 0;
+
+#if !defined(CONFIG_TDM_HW_LB_TSA_SLIC)
+ if (tdm_c->leg_slic) {
+ /* Need 1 bit delay for Legrity SLIC */
+ tdm_c->cfg_ctrl.rx_fr_sync_delay = 1;
+ tdm_c->cfg_ctrl.tx_fr_sync_delay = 1;
+ pr_info("%s Delay for Legerity!\n", __FUNCTION__);
+ }
+#endif
+
+ tdm_c->cfg_ctrl.active_num_ts = ACTIVE_CH;
+}
+
+static void tdm_read(u32 driver_handle, short chn_id, short *pcm_buffer,
+ short len)
+{
+ int i;
+ u32 phase_rx;
+ /* point to where to start for the current phase data processing */
+ u32 temp_rx;
+
+ struct tdm_ctrl *tdm_c = (struct tdm_ctrl *)(driver_handle);
+
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ u8 *input_tdm_buffer = tdm_c->tdm_input_data;
+
+#else
+ u16 *input_tdm_buffer =
+ (u16 *)tdm_c->tdm_input_data;
+
+#endif
+ phase_rx = tdm_c->phase_rx;
+ phase_rx = PREV_PHASE(phase_rx);
+
+ temp_rx = phase_rx * SAMPLE_DEPTH * EFF_ACTIVE_CH;
+
+#if defined(UCC_CACHE_SNOOPING_DISABLED)
+ flush_dcache_range((size_t) &input_tdm_buffer[temp_rx],
+ (size_t) &input_tdm_buffer[temp_rx +
+ SAMPLE_DEPTH * ACTIVE_CH]);
+#endif
+ for (i = 0; i < len; i++) {
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ pcm_buffer[i] =
+ ulaw2int(input_tdm_buffer[i * EFF_ACTIVE_CH +
+ temp_rx + chn_id]);
+#else
+ pcm_buffer[i] =
+ input_tdm_buffer[i * EFF_ACTIVE_CH + temp_rx + chn_id];
+#endif
+
+ }
+
+}
+
+static void tdm_write(u32 driver_handle, short chn_id, short *pcm_buffer,
+ short len)
+{
+ int i;
+ int phase_tx;
+ u32 txb;
+ /* point to where to start for the current phase data processing */
+ int temp_tx;
+ struct tdm_ctrl *tdm_c = (struct tdm_ctrl *)(driver_handle);
+
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ u8 *output_tdm_buffer;
+ output_tdm_buffer = tdm_c->tdm_output_data;
+#else
+ u16 *output_tdm_buffer;
+ output_tdm_buffer = (u16 *)tdm_c->tdm_output_data;
+#endif
+ txb = in_be32(&tdm_c->ucc_pram->tbptr) -
+ in_be32(&tdm_c->ucc_pram->tbase);
+ phase_tx = txb / sizeof(struct qe_bd);
+
+ phase_tx = PREV_PHASE(phase_tx);
+
+ temp_tx = phase_tx * SAMPLE_DEPTH * EFF_ACTIVE_CH;
+
+ for (i = 0; i < len; i++) {
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ output_tdm_buffer[i * EFF_ACTIVE_CH + temp_tx + chn_id] =
+ int2ulaw(pcm_buffer[i]);
+#else
+ output_tdm_buffer[i * EFF_ACTIVE_CH + temp_tx + chn_id] =
+ pcm_buffer[i];
+#endif
+ }
+
+#if defined(UCC_CACHE_SNOOPING_DISABLED)
+ flush_dcache_range((size_t) &output_tdm_buffer[temp_tx],
+ (size_t) &output_tdm_buffer[temp_tx + SAMPLE_DEPTH *
+ ACTIVE_CH]);
+#endif
+}
+
+
+static int tdm_register_client(struct tdm_client *tdm_client)
+{
+ if (num_tdm_clients == num_tdm_devices) {
+ printk(KERN_ERR "all TDM devices busy\n");
+ return -EBUSY;
+ }
+
+ num_tdm_clients++;
+ tdm_client->driver_handle = (u32)(tdm_ctrl[num_tdm_clients - 1]);
+ tdm_client->tdm_read = tdm_read;
+ tdm_client->tdm_write = tdm_write;
+ tdm_client->wakeup_event =
+ &(tdm_ctrl[num_tdm_clients - 1]->wakeup_event);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tdm_register_client);
+
+static int tdm_deregister_client(struct tdm_client *tdm_client)
+{
+ num_tdm_clients--;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tdm_deregister_client);
+
+static int ucc_tdm_probe(struct of_device *ofdev,
+ const struct of_device_id *match)
+{
+ struct device_node *np = ofdev->node;
+ struct resource res;
+ const unsigned int *prop;
+ u32 ucc_num, device_num, err, ret = 0;
+ struct device_node *np_tmp = NULL;
+ dma_addr_t physaddr;
+ void *tdm_buff;
+ struct ucc_tdm_info *ut_info;
+
+ prop = of_get_property(np, "device-id", NULL);
+ ucc_num = *prop - 1;
+ if ((ucc_num < 0) || (ucc_num > 7))
+ return -ENODEV;
+
+ ut_info = &utdm_info[ucc_num];
+ if (ut_info == NULL) {
+ printk(KERN_ERR "additional data missing\n");
+ return -ENODEV;
+ }
+ if (ut_info->ucc_busy) {
+ printk(KERN_ERR "UCC in use by another TDM driver instance\n");
+ return -EBUSY;
+ }
+
+ ut_info->ucc_busy = 1;
+ tdm_ctrl[num_tdm_devices++] =
+ kzalloc(sizeof(struct tdm_ctrl), GFP_KERNEL);
+ if (!tdm_ctrl[num_tdm_devices - 1]) {
+ printk(KERN_ERR "%s: no memory to allocate for"
+ " tdm control structure\n", __FUNCTION__);
+ num_tdm_devices--;
+ return -ENOMEM;
+ }
+ device_num = num_tdm_devices - 1;
+
+ tdm_ctrl[device_num]->device = &ofdev->dev;
+ tdm_ctrl[device_num]->ut_info = ut_info;
+
+ tdm_ctrl[device_num]->ut_info->uf_info.ucc_num = ucc_num;
+
+ prop = of_get_property(np, "fsl,tdm-num", NULL);
+ if (prop == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->tdm_port = *prop - 1;
+
+ if (tdm_ctrl[device_num]->tdm_port > 3) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ prop = of_get_property(np, "fsl,si-num", NULL);
+ if (prop == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->si = *prop - 1;
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_clk =
+ (char *) of_get_property(np, "fsl,tdm-tx-clk", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_clk == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_clk =
+ (char *) of_get_property(np, "fsl,tdm-rx-clk", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_clk == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_sync =
+ (char *) of_get_property(np, "fsl,tdm-tx-sync", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_sync == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_sync =
+ (char *) of_get_property(np, "fsl,tdm-rx-sync", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_sync == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.irq =
+ irq_of_parse_and_map(np, 0);
+ err = of_address_to_resource(np, 0, &res);
+ if (err) {
+ ret = EINVAL;
+ goto get_property_error;
+ }
+ tdm_ctrl[device_num]->ut_info->uf_info.regs = res.start;
+ tdm_ctrl[device_num]->uf_regs = of_iomap(np, 0);
+
+ np_tmp = of_find_compatible_node(np_tmp, "slic", "legerity-slic");
+ if (np_tmp != NULL)
+ tdm_ctrl[device_num]->leg_slic = 1;
+ else
+ tdm_ctrl[device_num]->leg_slic = 0;
+
+ config_tdm(tdm_ctrl[device_num]);
+
+ tdm_buff = dma_alloc_coherent(NULL, 2 * NR_BUFS * SAMPLE_DEPTH *
+ tdm_ctrl[device_num]->cfg_ctrl.active_num_ts,
+ &physaddr, GFP_KERNEL);
+ if (!tdm_buff) {
+ printk(KERN_ERR "ucc-tdm: could not allocate buffer"
+ "descriptors\n");
+ ret = -ENOMEM;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->tdm_input_data = tdm_buff;
+ tdm_ctrl[device_num]->dma_input_addr = physaddr;
+
+ tdm_ctrl[device_num]->tdm_output_data = tdm_buff + NR_BUFS *
+ SAMPLE_DEPTH * tdm_ctrl[device_num]->cfg_ctrl.active_num_ts;
+ tdm_ctrl[device_num]->dma_output_addr = physaddr + NR_BUFS *
+ SAMPLE_DEPTH * tdm_ctrl[device_num]->cfg_ctrl.active_num_ts;
+
+ init_waitqueue_head(&(tdm_ctrl[device_num]->wakeup_event));
+
+ ret = tdm_init(tdm_ctrl[device_num]);
+ if (ret != 0)
+ goto tdm_init_error;
+
+ ret = tdm_start(tdm_ctrl[device_num]);
+ if (ret != 0)
+ goto tdm_start_error;
+
+ dev_set_drvdata(&(ofdev->dev), tdm_ctrl[device_num]);
+
+ pr_info("%s UCC based tdm module installed\n", __FUNCTION__);
+ return 0;
+
+tdm_start_error:
+ tdm_deinit(tdm_ctrl[device_num]);
+tdm_init_error:
+ dma_free_coherent(NULL, 2 * NR_BUFS * SAMPLE_DEPTH *
+ tdm_ctrl[device_num]->cfg_ctrl.active_num_ts,
+ tdm_ctrl[device_num]->tdm_input_data,
+ tdm_ctrl[device_num]->dma_input_addr);
+
+get_property_error:
+ kfree(tdm_ctrl[device_num]);
+ return ret;
+}
+
+static int ucc_tdm_remove(struct of_device *ofdev)
+{
+ struct tdm_ctrl *tdm_c;
+ struct ucc_tdm_info *ut_info;
+ u32 ucc_num;
+
+ tdm_c = dev_get_drvdata(&(ofdev->dev));
+ ucc_num = tdm_c->ut_info->uf_info.ucc_num;
+ ut_info = &utdm_info[ucc_num];
+ tdm_stop(tdm_c);
+ tdm_deinit(tdm_c);
+
+ ucc_fast_free(tdm_c->uf_private);
+
+ dma_free_coherent(NULL, 2 * NR_BUFS * SAMPLE_DEPTH *
+ tdm_c->cfg_ctrl.active_num_ts,
+ tdm_c->tdm_input_data,
+ tdm_c->dma_input_addr);
+
+ num_tdm_devices--;
+ kfree(tdm_c);
+
+ ut_info->ucc_busy = 0;
+
+ pr_info("%s UCC based tdm module uninstalled\n", __FUNCTION__);
+ return 0;
+}
+
+static struct of_device_id ucc_tdm_match[] = {
+ {
+ .type = "tdm",
+ .compatible = "fsl,ucc-tdm",
+ }, {},
+};
+
+MODULE_DEVICE_TABLE(of, ucc_tdm_match);
+
+static struct of_platform_driver ucc_tdm_driver = {
+ .name = DRV_NAME,
+ .match_table = ucc_tdm_match,
+ .probe = ucc_tdm_probe,
+ .remove = ucc_tdm_remove,
+};
+
+static int __init ucc_tdm_init(void)
+{
+ u32 i;
+
+ pr_info("ucc_tdm: " DRV_DESC "\n");
+ for (i = 0; i < 8; i++)
+ memcpy(&(utdm_info[i]), &utdm_primary_info,
+ sizeof(utdm_primary_info));
+
+ return of_register_platform_driver(&ucc_tdm_driver);
+}
+
+static void __exit ucc_tdm_exit(void)
+{
+ of_unregister_platform_driver(&ucc_tdm_driver);
+}
+
+module_init(ucc_tdm_init);
+module_exit(ucc_tdm_exit);
+MODULE_AUTHOR("Freescale Semiconductor, Inc");
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/ucc_tdm.h b/drivers/misc/ucc_tdm.h
new file mode 100644
index 0000000..d0f376b
--- /dev/null
+++ b/drivers/misc/ucc_tdm.h
@@ -0,0 +1,227 @@
+/*
+ * drivers/misc/ucc_tdm.h
+ *
+ * UCC Based Linux TDM Driver
+ * This driver is designed to support UCC based TDM for PowerPC processors.
+ * This driver can interface with SLIC device to run VOIP kind of
+ * applications.
+ *
+ * Author: Ashish Kalra & Poonam Aggrwal
+ *
+ * Copyright (c) 2007 Freescale Semiconductor, 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; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef TDM_H
+#define TDM_H
+
+#define NUM_TS 8
+#define ACTIVE_CH 8
+
+/* SAMPLE_DEPTH is the sample depth is the number of frames before
+ * an interrupt. Must be a multiple of 4
+ */
+#define SAMPLE_DEPTH 80
+
+/* define the number of Rx interrupts to go by for initial stuttering */
+#define STUTTER_INT_CNT 1
+
+/* BMRx Field Descriptions to specify tstate and rstate in UCC parameter RAM*/
+#define EN_BUS_SNOOPING 0x20
+#define BE_BO 0x10
+
+/* UPSMR Register for Transparent UCC controller Bit definitions*/
+#define NBO 0x00000000 /* Normal Mode 1 bit of data per clock */
+
+/* SI Mode register bit definitions */
+#define NORMAL_OPERATION 0x0000
+#define AUTO_ECHO 0x0400
+#define INTERNAL_LB 0x0800
+#define CONTROL_LB 0x0c00
+#define SIMODE_CRT (0x8000 >> 9)
+#define SIMODE_SL (0x8000 >> 10)
+#define SIMODE_CE (0x8000 >> 11)
+#define SIMODE_FE (0x8000 >> 12)
+#define SIMODE_GM (0x8000 >> 13)
+#define SIMODE_TFSD(val) (val)
+#define SIMODE_RFSD(val) ((val) << 8)
+
+#define SI_TDM_MODE_REGISTER_OFFSET 0
+
+#define R_CM 0x02000000
+#define T_CM 0x02000000
+
+#define SET_RX_SI_RAM(n, val) \
+ out_be16((u16 *)&qe_immr->sir.rx[(n)*2], (u16)(val))
+
+#define SET_TX_SI_RAM(n, val) \
+ out_be16((u16 *)&qe_immr->sir.tx[(n)*2], (u16)(val))
+
+/* SI RAM entries */
+#define SIR_LAST 0x0001
+#define SIR_CNT(n) ((n) << 2)
+#define SIR_BYTE 0x0002
+#define SIR_BIT 0x0000
+#define SIR_IDLE 0
+#define SIR_UCC(uccx) (((uccx+9)) << 5)
+
+/* BRGC Register Bit definitions */
+#define BRGC_RESET (0x1<<17)
+#define BRGC_EN (0x1<<16)
+#define BRGC_EXTC_QE (0x00<<14)
+#define BRGC_EXTC_CLK3 (0x01<<14)
+#define BRGC_EXTC_CLK5 (0x01<<15)
+#define BRGC_EXTC_CLK9 (0x01<<14)
+#define BRGC_EXTC_CLK11 (0x01<<14)
+#define BRGC_EXTC_CLK13 (0x01<<14)
+#define BRGC_EXTC_CLK15 (0x01<<15)
+#define BRGC_ATB (0x1<<13)
+#define BRGC_DIV16 (0x1)
+
+/* structure representing UCC transparent parameter RAM */
+struct ucc_transparent_pram {
+ __be16 riptr;
+ __be16 tiptr;
+ __be16 res0;
+ __be16 mrblr;
+ __be32 rstate;
+ __be32 rbase;
+ __be16 rbdstat;
+ __be16 rbdlen;
+ __be32 rdptr;
+ __be32 tstate;
+ __be32 tbase;
+ __be16 tbdstat;
+ __be16 tbdlen;
+ __be32 tdptr;
+ __be32 rbptr;
+ __be32 tbptr;
+ __be32 rcrc;
+ __be32 res1;
+ __be32 tcrc;
+ __be32 res2;
+ __be32 res3;
+ __be32 c_mask;
+ __be32 c_pres;
+ __be16 disfc;
+ __be16 crcec;
+ __be32 res4[4];
+ __be16 ts_tmp;
+ __be16 tmp_mb;
+};
+
+#define UCC_TRANSPARENT_PRAM_SIZE 0x100
+
+struct tdm_cfg {
+ u8 com_pin; /* Common receive and transmit pins
+ * 0 = separate pins
+ * 1 = common pins
+ */
+
+ u8 fr_sync_level; /* SLx bit Frame Sync Polarity
+ * 0 = L1R/TSYNC active logic "1"
+ * 1 = L1R/TSYNC active logic "0"
+ */
+
+ u8 clk_edge; /* CEx bit Tx Rx Clock Edge
+ * 0 = TX data on rising edge of clock
+ * RX data on falling edge
+ * 1 = TX data on falling edge of clock
+ * RX data on rising edge
+ */
+
+ u8 fr_sync_edge; /* FEx bit Frame sync edge
+ * Determine when the sync pulses are sampled
+ * 0 = Falling edge
+ * 1 = Rising edge
+ */
+
+ u8 rx_fr_sync_delay; /* TFSDx/RFSDx bits Frame Sync Delay
+ * 00 = no bit delay
+ * 01 = 1 bit delay
+ * 10 = 2 bit delay
+ * 11 = 3 bit delay
+ */
+
+ u8 tx_fr_sync_delay; /* TFSDx/RFSDx bits Frame Sync Delay
+ * 00 = no bit delay
+ * 01 = 1 bit delay
+ * 10 = 2 bit delay
+ * 11 = 3 bit delay
+ */
+
+ u8 active_num_ts; /* Number of active time slots in TDM
+ * assume same active Rx/Tx time slots
+ */
+};
+
+struct ucc_tdm_info {
+ struct ucc_fast_info uf_info;
+ u32 ucc_busy;
+};
+
+struct tdm_ctrl {
+ struct device *device;
+ struct ucc_fast_private *uf_private;
+ struct ucc_tdm_info *ut_info;
+ u32 tdm_port; /* port for this tdm:TDMA,TDMB,TDMC,TDMD */
+ u32 si; /* serial interface: 0 or 1 */
+ struct ucc_fast __iomem *uf_regs; /* UCC Fast registers */
+ u16 rx_mask[8]; /* Active Receive channels LSB is ch0 */
+ u16 tx_mask[8]; /* Active Transmit channels LSB is ch0 */
+ /* Only channels less than the number of FRAME_SIZE are implemented */
+ struct tdm_cfg cfg_ctrl; /* Signaling controls configuration */
+ u8 *tdm_input_data; /* buffer used for Rx by the tdm */
+ u8 *tdm_output_data; /* buffer used for Tx by the tdm */
+
+ dma_addr_t dma_input_addr; /* dma mapped buffer for TDM Rx */
+ dma_addr_t dma_output_addr; /* dma mapped buffer for TDM Tx */
+ u16 physical_num_ts; /* physical number of timeslots in the tdm
+ frame */
+ u32 phase_rx; /* cycles through 0, 1, 2 */
+ u32 phase_tx; /* cycles through 0, 1, 2 */
+ /*
+ * the following two variables are for dealing with "stutter" problem
+ * "stutter" period is about 20 frames or so, varies depending active
+ * channel num depending on the sample depth, the code should let a
+ * few Rx interrupts go by
+ */
+ u32 tdm_icnt;
+ u32 tdm_flag;
+ struct ucc_transparent_pram __iomem *ucc_pram;
+ struct qe_bd __iomem *tx_bd;
+ struct qe_bd __iomem *rx_bd;
+ u32 ucc_pram_offset;
+ u32 tx_bd_offset;
+ u32 rx_bd_offset;
+ u32 rx_ucode_buf_offset;
+ u32 tx_ucode_buf_offset;
+ bool leg_slic;
+ wait_queue_head_t wakeup_event;
+};
+
+struct tdm_client {
+ u32 driver_handle;
+ void (*tdm_read)(u32 driver_handle, short chn_id,
+ short *pcm_buffer, short len);
+ void (*tdm_write)(u32 driver_handle, short chn_id,
+ short *pcm_buffer, short len);
+ wait_queue_head_t *wakeup_event;
+ };
+
+
+#ifndef CONFIG_TDM_LINEAR_PCM
+ #define MAX_PHASE 2
+ #define NR_BUFS 3
+ #define EFF_ACTIVE_CH ACTIVE_CH
+#else
+ #define MAX_PHASE 1
+ #define NR_BUFS 2
+ #define EFF_ACTIVE_CH ACTIVE_CH / 2
+#endif
+
+#endif
--
1.5.2.4
^ permalink raw reply related
* [PATCH 0/3] UCC TDM driver for MPC83xx platforms
From: Aggrwal Poonam @ 2007-12-10 11:53 UTC (permalink / raw)
To: rubini, linux-ppcdev, netdev, linux-kernel, Gala Kumar
Cc: Barkowski Michael, Phillips Kim, Kalra Ashish, Cutler Richard
There are three patches
[PATCH 1/3] drivers/misc : UCC TDM driver for mpc83xx platforms. This
driver is usable in VoIP iind of applications to interface with SLIC
kind of devices to exchange TDM voice samples.
[PATCH 2/3] arch/ : Platform changes
- device tree entries for UCC TDM driver for MPC8323ERDB platform.
- QE changes related to TDM , like,
1) Modified ucc_fast_init so that it can be used by fast UCC
based TDM driver. Mainly changes have been made to configure TDM clocks
and Fsyncs.
2) Modified get_brg_clk so that it can return the input frequncy
and input source of any BRG by reading the corresponding entries from
device tree.
3) Added new nodes brg and clocks in the device tree which
represent input clocks for different BRGs.
4) Modified qe_setbrg accordingly.
- new device tree entries added for "clocks" and "brg"
[PATCH 3/3] Documentation
- Modified Documentation to explain the device tree entries related to
UCC TDM driver and the new nodes added("clocks" and "brg")
The patch applies over a merge of galak's for-2.6.25 plus for-2.6.24
plus of_doc_update branches.
In brief the steps were
git clone
git://git.kernel.org/pub/scm/linux/kernel/git/galak/powerpc.git
powerpc-galak git checkout -b for-2.6.25 origin/for-2.6.25 git checkout
-b for-2.6.24 origin/for-2.6.24 git checkout -b of_doc_update
origin/of_doc_update
git pull . for-2.6.24 # merge the other two
git pull . for-2.6.25
git checkout -b tdm # clean slate for tdm rebase work
Also after applying the patches changes have to be made corresponding to
Tabi's patch "qe: add function qe_clock_source".
The driver has been tested with a VoIP stack and application on
MPC8323ERDB.
With Regards
Poonam
^ permalink raw reply
* Re: [PATCH 5/8] [TFRC]: Loss interval code needs the macros/inlines that were moved
From: Arnaldo Carvalho de Melo @ 2007-12-10 11:48 UTC (permalink / raw)
To: Gerrit Renker, dccp, netdev
In-Reply-To: <20071210113153.GB4688@gerrit.erg.abdn.ac.uk>
Em Mon, Dec 10, 2007 at 11:31:53AM +0000, Gerrit Renker escreveu:
> | >
> | > distcc[24516] ERROR: compile /root/.ccache/packet_his.tmp.aspire.home.net.24512.i on _tiptop failed
> | > /usr/src/davem-2.6/net/dccp/ccids/lib/packet_history.c: In function '__one_after_loss':
> | > /usr/src/davem-2.6/net/dccp/ccids/lib/packet_history.c:266: error: lvalue required as unary '&' operand
> <snip>
> |
> | Because you do it this way:
> |
> | tfrc_rx_hist_swap(&TFRC_RX_HIST_ENTRY(h, 0), &TFRC_RX_HIST_ENTRY(h, 3));
> |
> | I checked and at least in this patch series all uses are of this type,
> | so why not do it using just the indexes, which would be simpler:
> |
> | tfrc_rx_hist_swap(h, 0, 3);
> |
> | With this implementation:
> |
> | static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const int a, const int b)
> | {
> | const int idx_a = tfrc_rx_hist_index(h, a),
> | int idx_b = tfrc_rx_hist_index(h, b);
> | struct tfrc_rx_hist_entry *tmp = h->ring[idx_a];
> |
> | h->ring[idx_a] = h->ring[idx_b];
> | h->ring[idx_b] = tmp;
> | }
> |
> Agreed, that is useful in the present case, since then everything uses
> inlines. The only suggestion I'd like to make is to use `u8' instead of
> `int' since the indices will have very low values.
Agreed.
> There is a related point: you will probably have noticed that loss_interval.c
> also uses macros. I don't know if you are planning to convert these also into
> inlines. I think that there would be less benefit in converting these, since
> they are locl to loss_interval.c and mostly serve to improve readability.
In general I'm against using macros for functions, so please always
consider doing things as inlines.
I'll read some more patches today and provide comments as to if I think
it is ok for now to keep it as macros.
> As I have at least one other patch to revise (plus another minor one),
> I'll rework this according to the above.
Thank you.
- Arnaldo
^ permalink raw reply
* [4/4] DST: Algorithms used in distributed storage.
From: Evgeniy Polyakov @ 2007-12-10 11:47 UTC (permalink / raw)
To: lkml; +Cc: netdev, linux-fsdevel
In-Reply-To: <11972872511269@2ka.mipt.ru>
Algorithms used in distributed storage.
Mirror and linear mapping code.
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
diff --git a/drivers/block/dst/alg_linear.c b/drivers/block/dst/alg_linear.c
new file mode 100644
index 0000000..9dc0976
--- /dev/null
+++ b/drivers/block/dst/alg_linear.c
@@ -0,0 +1,105 @@
+/*
+ * 2007+ Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * All rights reserved.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/dst.h>
+
+static struct dst_alg *alg_linear;
+
+/*
+ * This callback is invoked when node is removed from storage.
+ */
+static void dst_linear_del_node(struct dst_node *n)
+{
+}
+
+/*
+ * This callback is invoked when node is added to storage.
+ */
+static int dst_linear_add_node(struct dst_node *n)
+{
+ struct dst_storage *st = n->st;
+
+ dprintk("%s: disk_size: %llu, node_size: %llu.\n",
+ __func__, st->disk_size, n->size);
+
+ mutex_lock(&st->tree_lock);
+ n->start = st->disk_size;
+ st->disk_size += n->size;
+ set_capacity(st->disk, st->disk_size);
+ mutex_unlock(&st->tree_lock);
+
+ return 0;
+}
+
+static int dst_linear_remap(struct dst_request *req)
+{
+ int err;
+
+ if (req->node->bdev) {
+ generic_make_request(req->bio);
+ return 0;
+ }
+
+ err = kst_check_permissions(req->state, req->bio);
+ if (err)
+ return err;
+
+ return req->state->ops->push(req);
+}
+
+/*
+ * Failover callback - it is invoked each time error happens during
+ * request processing.
+ */
+static int dst_linear_error(struct kst_state *st, int err)
+{
+ if (err)
+ set_bit(DST_NODE_FROZEN, &st->node->flags);
+ else
+ clear_bit(DST_NODE_FROZEN, &st->node->flags);
+ return 0;
+}
+
+static struct dst_alg_ops alg_linear_ops = {
+ .remap = dst_linear_remap,
+ .add_node = dst_linear_add_node,
+ .del_node = dst_linear_del_node,
+ .error = dst_linear_error,
+ .owner = THIS_MODULE,
+};
+
+static int __devinit alg_linear_init(void)
+{
+ alg_linear = dst_alloc_alg("alg_linear", &alg_linear_ops);
+ if (!alg_linear)
+ return -ENOMEM;
+
+ return 0;
+}
+
+static void __devexit alg_linear_exit(void)
+{
+ dst_remove_alg(alg_linear);
+}
+
+module_init(alg_linear_init);
+module_exit(alg_linear_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Evgeniy Polyakov <johnpol@2ka.mipt.ru>");
+MODULE_DESCRIPTION("Linear distributed algorithm.");
diff --git a/drivers/block/dst/alg_mirror.c b/drivers/block/dst/alg_mirror.c
new file mode 100644
index 0000000..3c457ff
--- /dev/null
+++ b/drivers/block/dst/alg_mirror.c
@@ -0,0 +1,1128 @@
+/*
+ * 2007+ Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * All rights reserved.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/poll.h>
+#include <linux/dst.h>
+
+struct dst_mirror_node_data
+{
+ u64 age;
+};
+
+struct dst_mirror_priv
+{
+ unsigned int chunk_num;
+
+ u64 last_start;
+
+ spinlock_t backlog_lock;
+ struct list_head backlog_list;
+
+ struct dst_mirror_node_data old_data, new_data;
+
+ unsigned long *chunk;
+};
+
+static struct dst_alg *alg_mirror;
+static struct bio_set *dst_mirror_bio_set;
+
+static int dst_mirror_resync(struct dst_node *n, int ndp);
+
+static void dst_mirror_mark_sync(struct dst_node *n)
+{
+ if (test_bit(DST_NODE_NOTSYNC, &n->flags)) {
+ struct dst_mirror_priv *priv = n->priv;
+
+ clear_bit(DST_NODE_NOTSYNC, &n->flags);
+ dprintk("%s: node: %p, %llu:%llu synchronization "
+ "has been completed.\n",
+ __func__, n, n->start, n->size);
+ priv->old_data.age = 0;
+ }
+}
+
+static void dst_mirror_mark_notsync(struct dst_node *n)
+{
+ if (!test_bit(DST_NODE_NOTSYNC, &n->flags)) {
+ set_bit(DST_NODE_NOTSYNC, &n->flags);
+ dprintk("%s: not synced node n: %p.\n", __func__, n);
+ }
+}
+
+static void dst_mirror_mark_node_notsync(struct dst_node *n)
+{
+ struct dst_mirror_priv *p = n->priv;
+
+ memset(p->chunk, 0xff, DIV_ROUND_UP(p->chunk_num, BITS_PER_LONG)*sizeof(long));
+ dst_mirror_mark_notsync(n);
+ dst_mirror_resync(n, 0);
+}
+
+static void dst_mirror_mark_node_sync(struct dst_node *n)
+{
+ struct dst_mirror_priv *p = n->priv;
+
+ memset(p->chunk, 0x0, DIV_ROUND_UP(p->chunk_num, BITS_PER_LONG)*sizeof(long));
+ dst_mirror_mark_sync(n);
+}
+
+static ssize_t dst_mirror_mark_dirty(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct dst_node *n = container_of(dev, struct dst_node, device);
+
+ dst_mirror_mark_node_notsync(n);
+ return count;
+}
+
+static ssize_t dst_mirror_mark_clean(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct dst_node *n = container_of(dev, struct dst_node, device);
+
+ dst_mirror_mark_node_sync(n);
+ return count;
+}
+
+static ssize_t dst_mirror_chunk_mask_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_node *n = container_of(dev, struct dst_node, device);
+ struct dst_mirror_priv *priv = n->priv;
+ unsigned int i;
+ int rest = PAGE_SIZE, rest_bits = priv->chunk_num;
+
+ for (i = 0; i < DIV_ROUND_UP(priv->chunk_num, BITS_PER_LONG); ++i) {
+ int bit, j;
+
+ for (j = 0; j < min(BITS_PER_LONG, rest_bits); ++j) {
+ bit = (priv->chunk[i] >> j) & 1;
+ sprintf(buf, "%c", (bit)?'+':'-');
+ buf++;
+ }
+
+ rest_bits -= j;
+ rest -= j;
+
+ if (rest < BITS_PER_LONG || rest_bits <= 0)
+ break;
+ }
+
+ return PAGE_SIZE - rest;
+}
+
+static struct device_attribute dst_mirror_attrs[] = {
+ __ATTR(chunks, S_IRUGO, dst_mirror_chunk_mask_show, NULL),
+ __ATTR(dirty, S_IWUSR, NULL, dst_mirror_mark_dirty),
+ __ATTR(clean, S_IWUSR, NULL, dst_mirror_mark_clean),
+};
+
+/*
+ * This callback is invoked when node is removed from storage.
+ */
+static void dst_mirror_del_node(struct dst_node *n)
+{
+ struct dst_mirror_priv *priv = n->priv;
+ struct dst_request *req, *tmp;
+
+ list_for_each_entry_safe(req, tmp, &priv->backlog_list, request_list_entry) {
+ kst_del_req(req);
+ kst_complete_req(req, -ENODEV);
+ }
+
+ if (priv) {
+ vfree(priv->chunk);
+ kfree(priv);
+ n->priv = NULL;
+ }
+
+ if (n->device.parent == &n->st->device) {
+ int i;
+
+ for (i=0; i<ARRAY_SIZE(dst_mirror_attrs); ++i)
+ device_remove_file(&n->device, &dst_mirror_attrs[i]);
+ }
+}
+
+static void dst_mirror_handle_priv(struct dst_node *n)
+{
+ if (n->priv) {
+ int err, i;
+
+ for (i=0; i<ARRAY_SIZE(dst_mirror_attrs); ++i)
+ err = device_create_file(&n->device,
+ &dst_mirror_attrs[i]);
+ }
+}
+
+static void dst_mirror_destructor(struct bio *bio)
+{
+ dprintk("%s: bio: %p.\n", __func__, bio);
+ bio_free(bio, dst_mirror_bio_set);
+}
+
+/*
+ * This function copies node's private on-disk data from first node
+ * to the new one.
+ */
+static int dst_mirror_get_node_data(struct dst_node *n,
+ struct dst_mirror_node_data *ndata, int old)
+{
+ struct dst_node *first;
+ struct dst_mirror_priv *p;
+
+ mutex_lock(&n->st->tree_lock);
+ first = dst_storage_tree_search(n->st, n->start);
+ mutex_unlock(&n->st->tree_lock);
+ if (!first) {
+ dprintk("%s: there are no nodes in the storage.\n", __func__);
+ return -ENODEV;
+ }
+
+ p = first->priv;
+ memcpy(ndata, (old)?&p->old_data:&p->new_data, sizeof(struct dst_mirror_node_data));
+
+ dst_node_put(first);
+ return 0;
+}
+
+struct dst_mirror_ndp
+{
+ int err;
+ struct page *page;
+ struct completion complete;
+};
+
+static void dst_mirror_ndb_complete(struct dst_mirror_ndp *cmp, int err)
+{
+ cmp->err = err;
+ dprintk("%s: completing request: cmp: %p, err: %d.\n",
+ __func__, cmp, err);
+ complete(&cmp->complete);
+}
+
+static void dst_mirror_ndp_bio_endio(struct dst_request *req, int err)
+{
+ struct dst_mirror_ndp *cmp = req->bio->bi_private;
+
+ dst_mirror_ndb_complete(cmp, err);
+}
+
+static int dst_mirror_ndp_end_io(struct bio *bio, unsigned int size, int err)
+{
+ struct dst_mirror_ndp *cmp = bio->bi_private;
+
+ if (bio->bi_size)
+ return 0;
+
+ dst_mirror_ndb_complete(cmp, err);
+ return 0;
+}
+
+/*
+ * This function reads or writes node's private data from underlying media.
+ */
+static int dst_mirror_process_node_data(struct dst_node *n,
+ struct dst_mirror_node_data *ndata, int op)
+{
+ struct bio *bio;
+ int err = -ENOMEM;
+ struct dst_mirror_ndp *cmp;
+ void *addr;
+
+ cmp = kzalloc(sizeof(struct dst_mirror_ndp), GFP_KERNEL);
+ if (!cmp)
+ goto err_out_exit;
+
+ cmp->page = alloc_page(GFP_NOIO);
+ if (!cmp->page)
+ goto err_out_free_cmp;
+
+ addr = kmap(cmp->page);
+
+ init_completion(&cmp->complete);
+
+ if (op == WRITE)
+ memcpy(addr, ndata, sizeof(struct dst_mirror_node_data));
+
+ bio = bio_alloc_bioset(GFP_NOIO, 1, dst_mirror_bio_set);
+ if (!bio)
+ goto err_out_free_page;
+
+ bio->bi_rw = op;
+ bio->bi_private = cmp;
+ bio->bi_sector = n->size;
+ bio->bi_bdev = n->bdev;
+ bio->bi_destructor = dst_mirror_destructor;
+ bio->bi_end_io = dst_mirror_ndp_end_io;
+
+ err = bio_add_pc_page(n->st->queue, bio, cmp->page, 512, 0);
+ if (err <= 0)
+ goto err_out_free_bio;
+
+ if (n->bdev) {
+ generic_make_request(bio);
+ } else {
+ struct dst_request req;
+
+ memset(&req, 0, sizeof(struct dst_request));
+
+ req.node = n;
+ req.state = n->state;
+ req.start = bio->bi_sector;
+ req.size = req.orig_size = bio->bi_size;
+ req.bio = bio;
+ req.idx = bio->bi_idx;
+ req.num = bio->bi_vcnt;
+ req.flags = 0;
+ req.offset = 0;
+ req.bio_endio = &dst_mirror_ndp_bio_endio;
+ req.callback = &kst_data_callback;
+
+ err = req.state->ops->push(&req);
+ if (err)
+ req.bio_endio(&req, err);
+ }
+
+ dprintk("%s: waiting for completion: bio: %p, cmp: %p.\n",
+ __func__, bio, cmp);
+
+ wait_for_completion(&cmp->complete);
+
+ err = cmp->err;
+
+ if (!err && (op != WRITE))
+ memcpy(ndata, addr, sizeof(struct dst_mirror_node_data));
+
+ kunmap(cmp->page);
+
+ dprintk("%s: freeing bio: %p, err: %d.\n", __func__, bio, err);
+
+err_out_free_bio:
+ bio_put(bio);
+err_out_free_page:
+ __free_page(cmp->page);
+err_out_free_cmp:
+ kfree(cmp);
+err_out_exit:
+ return err;
+}
+
+/*
+ * This function reads node's private data from underlying media.
+ */
+static int dst_mirror_read_node_data(struct dst_node *n,
+ struct dst_mirror_node_data *ndata)
+{
+ return dst_mirror_process_node_data(n, ndata, READ);
+}
+
+/*
+ * This function writes node's private data from underlying media.
+ */
+static int dst_mirror_write_node_data(struct dst_node *n,
+ struct dst_mirror_node_data *ndata)
+{
+ dprintk("%s: writing new age: %llx, node: %p %llu-%llu.\n",
+ __func__, ndata->age, n, n->start, n->size);
+ return dst_mirror_process_node_data(n, ndata, WRITE);
+}
+
+static int dst_mirror_ndp_setup(struct dst_node *n, int first_node, int clean_on_sync)
+{
+ struct dst_mirror_priv *p = n->priv;
+ int sync = 1, err;
+
+ err = dst_mirror_read_node_data(n, &p->old_data);
+ if (err)
+ return err;
+
+ if (first_node) {
+ p->new_data.age = *(u64 *)&n->st;
+
+ dprintk("%s: first age: %llx -> %llx. "
+ "Old will be set to new for the first node.\n",
+ __func__, p->old_data.age, p->new_data.age);
+
+ err = dst_mirror_write_node_data(n, &p->new_data);
+ if (err)
+ return err;
+ p->old_data.age = p->new_data.age;
+ } else {
+ err = dst_mirror_get_node_data(n, &p->new_data, 1);
+ if (err)
+ return err;
+
+ if (p->new_data.age != p->old_data.age) {
+ sync = 0;
+ dprintk("%s: node %llu:%llu is not synced with the first "
+ "node (old != new): %llx != %llx.\n",
+ __func__, n->start, n->start+n->size,
+ p->old_data.age, p->new_data.age);
+ err = dst_mirror_get_node_data(n, &p->new_data, 0);
+ if (err)
+ return err;
+ } else {
+ err = dst_mirror_get_node_data(n, &p->new_data, 0);
+ if (err)
+ return err;
+
+ err = dst_mirror_write_node_data(n, &p->new_data);
+ if (err)
+ return err;
+
+ dprintk("%s: node %llu:%llu is in sync with the first node.\n",
+ __func__, n->start, n->start+n->size);
+ }
+ }
+
+ if (!sync)
+ dst_mirror_mark_node_notsync(n);
+ else if (clean_on_sync)
+ dst_mirror_mark_node_sync(n);
+
+ dprintk("%s: age: old: %llx, new: %llx.\n", __func__, p->old_data.age, p->new_data.age);
+
+ return 0;
+}
+
+/*
+ * This callback is invoked when node is added to storage.
+ */
+static int dst_mirror_add_node(struct dst_node *n)
+{
+ struct dst_storage *st = n->st;
+ struct dst_mirror_priv *priv;
+ int err = -ENOMEM, first_node = 0;
+ u64 disk_size;
+
+ n->size--; /* A sector size actually. */
+
+ mutex_lock(&st->tree_lock);
+ disk_size = st->disk_size;
+ if (st->disk_size) {
+ st->disk_size = min(n->size, st->disk_size);
+ } else {
+ st->disk_size = n->size;
+ first_node = 1;
+ }
+ mutex_unlock(&st->tree_lock);
+
+ priv = kzalloc(sizeof(struct dst_mirror_priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->chunk_num = st->disk_size;
+
+ priv->chunk = vmalloc(DIV_ROUND_UP(priv->chunk_num, BITS_PER_LONG) * sizeof(long));
+ if (!priv->chunk)
+ goto err_out_free;
+
+ spin_lock_init(&priv->backlog_lock);
+ INIT_LIST_HEAD(&priv->backlog_list);
+
+ dprintk("%s: %llu:%llu, chunk_num: %u, disk_size: %llu.\n\n",
+ __func__, n->start, n->size,
+ priv->chunk_num, st->disk_size);
+
+ n->priv_callback = &dst_mirror_handle_priv;
+ n->priv = priv;
+
+ err = dst_mirror_ndp_setup(n, first_node, 1);
+ if (err)
+ goto err_out_free_chunk;
+
+ return 0;
+
+err_out_free_chunk:
+ vfree(priv->chunk);
+err_out_free:
+ kfree(priv);
+ n->priv = NULL;
+
+ mutex_lock(&st->tree_lock);
+ st->disk_size = disk_size;
+ mutex_unlock(&st->tree_lock);
+ return err;
+}
+
+static void dst_mirror_sync_destructor(struct bio *bio)
+{
+ struct bio_vec *bv;
+ int i;
+
+ bio_for_each_segment(bv, bio, i)
+ __free_page(bv->bv_page);
+ bio_free(bio, dst_mirror_bio_set);
+}
+
+/*
+ * Without errors it is always called under node's request lock,
+ * so it is safe to requeue them.
+ */
+static void dst_mirror_bio_error(struct dst_request *req, int err)
+{
+ int i;
+ struct dst_mirror_priv *priv = req->node->priv;
+ unsigned int num, idx;
+ u64 start = req->start - to_sector(req->orig_size - req->size);
+
+ if (err)
+ dst_mirror_mark_notsync(req->node);
+
+ priv->last_start = req->start;
+
+ idx = start;
+ num = to_sector(req->orig_size);
+
+ dprintk("%s: %llu:%llu start: %llu, size: %llu, "
+ "chunk_num: %u, idx: %d, num: %d, err: %d, node: %p.\n",
+ __func__, req->node->start, req->node->size,
+ start, req->orig_size, priv->chunk_num,
+ idx, num, err, req->node);
+
+ if (unlikely(idx >= priv->chunk_num || idx + num > priv->chunk_num)) {
+ dprintk("%s: %llu:%llu req: %p, start: %llu, orig_size: %llu, "
+ "req_start: %llu, req_size: %llu, "
+ "chunk_num: %u, idx: %d, num: %d, err: %d.\n",
+ __func__, req->node->start, req->node->size, req,
+ start, req->orig_size,
+ req->start, req->size,
+ priv->chunk_num, idx, num, err);
+ return;
+ }
+
+ if (err) {
+ for (i=0; i<num; ++i)
+ __set_bit(idx+i, priv->chunk);
+ } else {
+ for (i=0; i<num; ++i)
+ __clear_bit(idx+i, priv->chunk);
+ }
+}
+
+static void dst_mirror_sync_req_endio(struct dst_request *req, int err)
+{
+ struct dst_node *n = req->node;
+ struct dst_mirror_priv *p = req->node->priv;
+ int i;
+ unsigned long notsync = 0;
+
+ dst_mirror_bio_error(req, err);
+
+ dprintk("%s: freeing bio: %p, bi_size: %u, "
+ "orig_size: %llu, req: %p, node: %p.\n",
+ __func__, req->bio, req->bio->bi_size, req->orig_size, req,
+ req->node);
+
+ bio_put(req->bio);
+
+ if (!test_bit(DST_NODE_NOTSYNC, &n->flags))
+ return;
+
+ for (i = 0; i < DIV_ROUND_UP(p->chunk_num, BITS_PER_LONG); ++i) {
+ notsync = p->chunk[i];
+ if (notsync)
+ break;
+ }
+
+ if (notsync) {
+ dprintk("%s: %d/%d sync: %lx, ffs: %lu, chunk_num (modulo %u): %d.\n",
+ __func__, i, DIV_ROUND_UP(p->chunk_num, BITS_PER_LONG),
+ notsync, __ffs(notsync), BITS_PER_LONG,
+ p->chunk_num%BITS_PER_LONG);
+ if (i != DIV_ROUND_UP(p->chunk_num, BITS_PER_LONG) - 1)
+ return;
+
+ if (__ffs(notsync) != (p->chunk_num%BITS_PER_LONG))
+ return;
+ }
+
+ dst_mirror_mark_sync(n);
+}
+
+static int dst_mirror_sync_endio(struct bio *bio, unsigned int size, int err)
+{
+ struct dst_request *req = bio->bi_private;
+ struct dst_node *n = req->node;
+ struct dst_mirror_priv *priv = n->priv;
+ unsigned long flags;
+
+ dprintk("%s: bio: %p, err: %d, size: %u, req: %p.\n",
+ __func__, bio, err, bio->bi_size, req);
+
+ if (bio->bi_size)
+ return 1;
+
+ bio->bi_rw = WRITE;
+ bio->bi_size = req->orig_size;
+ bio->bi_sector = req->start;
+
+ if (!err) {
+ spin_lock_irqsave(&priv->backlog_lock, flags);
+ list_add_tail(&req->request_list_entry, &priv->backlog_list);
+ spin_unlock_irqrestore(&priv->backlog_lock, flags);
+ kst_wake(req->state);
+ } else {
+ req->bio_endio(req, err);
+ dst_free_request(req);
+ }
+ return 0;
+}
+
+static int dst_mirror_sync_block(struct dst_node *n,
+ int bit_start, int bit_num)
+{
+ u64 start = to_bytes(bit_start);
+ u32 size = to_bytes(bit_num);
+ struct bio *bio;
+ unsigned int nr_pages = DIV_ROUND_UP(size, PAGE_SIZE), i;
+ struct page *page;
+ int err = -ENOMEM;
+ struct dst_request *req;
+
+ dprintk("%s: bit_start: %d, bit_num: %d, start: %llu, nr_pages: %u, "
+ "disk_size: %llu.\n",
+ __func__, bit_start, bit_num, start, nr_pages,
+ n->st->disk_size);
+
+ while (nr_pages) {
+ req = dst_clone_request(NULL, n->w->req_pool);
+ if (!req)
+ return -ENOMEM;
+
+ bio = bio_alloc_bioset(GFP_NOIO, nr_pages, dst_mirror_bio_set);
+ if (!bio)
+ goto err_out_free_req;
+
+ bio->bi_rw = READ;
+ bio->bi_private = req;
+ bio->bi_sector = to_sector(start);
+ bio->bi_bdev = NULL;
+ bio->bi_destructor = dst_mirror_sync_destructor;
+ bio->bi_end_io = dst_mirror_sync_endio;
+
+ for (i = 0; i < nr_pages; ++i) {
+ err = -ENOMEM;
+
+ page = alloc_page(GFP_NOIO);
+ if (!page)
+ break;
+
+ err = bio_add_pc_page(n->st->queue, bio, page,
+ min_t(u32, PAGE_SIZE, size), 0);
+ if (err <= 0)
+ break;
+ size -= err;
+ err = 0;
+ }
+
+ if (err && !bio->bi_vcnt)
+ goto err_out_put_bio;
+
+ req->node = n;
+ req->state = n->state;
+ req->start = bio->bi_sector;
+ req->size = req->orig_size = bio->bi_size;
+ req->bio = bio;
+ req->idx = bio->bi_idx;
+ req->num = bio->bi_vcnt;
+ req->flags = DST_REQ_CHECK_QUEUE;
+ req->offset = 0;
+ req->bio_endio = &dst_mirror_sync_req_endio;
+ req->callback = &kst_data_callback;
+
+ dprintk("%s: start: %llu, size: %llu/%u, bio: %p, req: %p, "
+ "node: %p.\n",
+ __func__, req->start, req->size, nr_pages, bio,
+ req, req->node);
+
+ err = n->st->queue->make_request_fn(n->st->queue, bio);
+ if (err)
+ goto err_out_put_bio;
+
+ nr_pages -= bio->bi_vcnt;
+ start += bio->bi_size;
+ }
+
+ return 0;
+
+err_out_put_bio:
+ bio_put(bio);
+err_out_free_req:
+ dst_free_request(req);
+ return err;
+}
+
+/*
+ * Resync logic.
+ *
+ * System allocates and queues requests for number of regions.
+ * Each request initially is reading from the one of the nodes.
+ * When it is completed, system checks if given region was already
+ * written to, and in such case just drops read request, otherwise
+ * it writes it to the node being updated. Any write clears not-uptodate
+ * bit, which is used as a flag that region must be synchronized or not.
+ * Reading is never performed from the node under resync.
+ */
+static int dst_mirror_resync(struct dst_node *n, int ndp)
+{
+ struct dst_mirror_priv *priv = n->priv;
+ int err = 0, sync = 1, total = priv->chunk_num;
+ unsigned int i;
+
+ dprintk("%s: node: %p, %llu:%llu synchronization has been started.\n",
+ __func__, n, n->start, n->size);
+
+ if (ndp) {
+ err = dst_mirror_ndp_setup(n, 0, 0);
+ if (err)
+ return err;
+ }
+
+ for (i = 0; i < DIV_ROUND_UP(priv->chunk_num, BITS_PER_LONG); ++i) {
+ int bit, num, start;
+ unsigned long word = priv->chunk[i];
+
+ if (!word)
+ continue;
+
+ num = 0;
+ start = -1;
+ while (word && num < BITS_PER_LONG) {
+ bit = __ffs(word);
+ if (start == -1)
+ start = bit;
+ num++;
+ word >>= (bit+1);
+
+ if (--total == 0)
+ break;
+ }
+
+ if (start != -1) {
+ err = dst_mirror_sync_block(n, start + i*BITS_PER_LONG,
+ num);
+ if (err)
+ break;
+ sync = 0;
+ }
+
+ if (total == 0)
+ break;
+ }
+
+ return err;
+}
+
+static int dst_mirror_end_io(struct bio *bio, unsigned int size, int err)
+{
+ struct dst_request *req = bio->bi_private;
+
+ if (bio->bi_size)
+ return 0;
+
+ dprintk("%s: req: %p, bio: %p, req->bio: %p, err: %d.\n",
+ __func__, req, bio, req->bio, err);
+ req->bio_endio(req, err);
+ bio_put(bio);
+ return 0;
+}
+
+static void dst_mirror_read_endio(struct dst_request *req, int err)
+{
+ dst_mirror_bio_error(req, err);
+
+ if (err && req->state)
+ kst_wake(req->state);
+
+ if (!err || req->callback)
+ kst_bio_endio(req, err);
+}
+
+static void dst_mirror_write_endio(struct dst_request *req, int err)
+{
+ dst_mirror_bio_error(req, err);
+
+ if (err && req->state)
+ kst_wake(req->state);
+
+ req = req->priv;
+
+ dprintk("%s: req: %p, priv: %p err: %d, bio: %p, "
+ "cnt: %d, orig_size: %llu.\n",
+ __func__, req, req->priv, err, req->bio,
+ atomic_read(&req->refcnt), req->orig_size);
+
+ if (atomic_dec_and_test(&req->refcnt)) {
+ bio_endio(req->bio, req->orig_size, 0);
+ dst_free_request(req);
+ }
+}
+
+static int dst_mirror_process_request_nosync(struct dst_request *req,
+ struct dst_node *n)
+{
+ int err = 0;
+
+ /*
+ * Block layer requires to clone a bio.
+ */
+ if (n->bdev) {
+ struct bio *clone = bio_alloc_bioset(GFP_NOIO,
+ req->bio->bi_max_vecs, dst_mirror_bio_set);
+
+ __bio_clone(clone, req->bio);
+
+ clone->bi_bdev = n->bdev;
+ clone->bi_destructor = dst_mirror_destructor;
+ clone->bi_private = req;
+ clone->bi_end_io = &dst_mirror_end_io;
+
+ dprintk("%s: clone: %p, bio: %p, req: %p.\n",
+ __func__, clone, req->bio, req);
+
+ generic_make_request(clone);
+ } else {
+ struct dst_request nr;
+ /*
+ * Network state processing engine will clone request
+ * by itself if needed. We can not use the same structure
+ * here, since number of its fields will be modified.
+ */
+ memcpy(&nr, req, sizeof(struct dst_request));
+
+ nr.node = n;
+ nr.state = n->state;
+ nr.priv = req;
+
+ err = kst_check_permissions(n->state, req->bio);
+ if (!err)
+ err = n->state->ops->push(&nr);
+ }
+
+ dprintk("%s: req: %p, n: %p, bdev: %p, err: %d.\n",
+ __func__, req, n, n->bdev, err);
+
+ return err;
+}
+
+static void dst_mirror_sync_requeue(struct dst_node *n)
+{
+ struct dst_mirror_priv *p = n->priv;
+ struct dst_request *req;
+ unsigned int num, idx, i;
+ u64 start;
+ unsigned long flags;
+ int err;
+
+ while (!list_empty(&p->backlog_list)) {
+ req = NULL;
+ spin_lock_irqsave(&p->backlog_lock, flags);
+ if (!list_empty(&p->backlog_list)) {
+ req = list_entry(p->backlog_list.next,
+ struct dst_request,
+ request_list_entry);
+ list_del_init(&req->request_list_entry);
+ }
+ spin_unlock_irqrestore(&p->backlog_lock, flags);
+
+ if (!req)
+ break;
+
+ start = req->start - to_sector(req->orig_size - req->size);
+
+ idx = start;
+ num = to_sector(req->orig_size);
+
+ for (i=0; i<num; ++i)
+ if (test_bit(idx+i, p->chunk))
+ break;
+
+ dprintk("%s: idx: %u, num: %u, i: %u, req: %p, "
+ "start: %llu, size: %llu.\n",
+ __func__, idx, num, i, req,
+ req->start, req->orig_size);
+
+ err = -1;
+ if (i != num) {
+ err = dst_mirror_process_request_nosync(req, n);
+ if (!err)
+ dst_free_request(req);
+ }
+
+ if (err)
+ kst_complete_req(req, err);
+ }
+
+ if (!test_bit(DST_NODE_NOTSYNC, &n->flags) &&
+ p->old_data.age != p->new_data.age) {
+ dst_mirror_write_node_data(n, &p->new_data);
+ p->old_data.age = p->new_data.age;
+ }
+}
+
+static int dst_mirror_process_request(struct dst_request *req,
+ struct dst_node *n)
+{
+ dst_mirror_sync_requeue(n);
+ return dst_mirror_process_request_nosync(req, n);
+}
+
+static int dst_mirror_write(struct dst_request *oreq)
+{
+ struct dst_node *n, *node = oreq->node;
+ struct dst_request *req;
+ int num, err = 0, err_num = 0, orig_num;
+
+ req = dst_clone_request(oreq, oreq->node->w->req_pool);
+ if (!req) {
+ err = -ENOMEM;
+ goto err_out_exit;
+ }
+
+ req->priv = req;
+
+ /*
+ * This logic is pretty simple - req->bio_endio will not
+ * call bio_endio() until all mirror devices completed
+ * processing of the request (no matter with or without error).
+ * Mirror's req->bio_endio callback will take care of that.
+ */
+ orig_num = num = atomic_read(&req->node->shared_num) + 1;
+ atomic_set(&req->refcnt, num);
+
+ req->bio_endio = &dst_mirror_write_endio;
+
+ dprintk("\n%s: req: %p, mirror to %d nodes.\n",
+ __func__, req, num);
+
+ err = dst_mirror_process_request(req, node);
+ if (err)
+ err_num++;
+
+ if (--num) {
+ list_for_each_entry(n, &node->shared, shared) {
+ dprintk("\n%s: req: %p, start: %llu, size: %llu, "
+ "num: %d, n: %p, state: %p.\n",
+ __func__, req, req->start,
+ req->size, num, n, n->state);
+
+ err = dst_mirror_process_request(req, n);
+ if (err)
+ err_num++;
+
+ if (--num <= 0)
+ break;
+ }
+ }
+
+ if (err_num == orig_num) {
+ dprintk("%s: req: %p, num: %d, err: %d.\n",
+ __func__, req, num, err);
+ err = -ENODEV;
+ goto err_out_exit;
+ }
+
+ return 0;
+
+err_out_exit:
+ return err;
+}
+
+static int dst_mirror_read(struct dst_request *req)
+{
+ struct dst_node *node = req->node, *n, *min_dist_node;
+ struct dst_mirror_priv *priv = node->priv;
+ u64 dist, d;
+ int err;
+
+ req->bio_endio = &dst_mirror_read_endio;
+
+ do {
+ err = -ENODEV;
+ min_dist_node = NULL;
+ dist = -1ULL;
+
+ /*
+ * Reading is never performed from the node under resync.
+ * If this will cause any troubles (like all nodes must be
+ * resynced between each other), this check can be removed
+ * and per-chunk dirty bit can be tested instead.
+ */
+
+ if (!test_bit(DST_NODE_NOTSYNC, &node->flags)) {
+ priv = node->priv;
+ if (req->start > priv->last_start)
+ dist = req->start - priv->last_start;
+ else
+ dist = priv->last_start - req->start;
+ min_dist_node = req->node;
+ }
+
+ list_for_each_entry(n, &node->shared, shared) {
+ if (test_bit(DST_NODE_NOTSYNC, &n->flags))
+ continue;
+
+ priv = n->priv;
+
+ if (req->start > priv->last_start)
+ d = req->start - priv->last_start;
+ else
+ d = priv->last_start - req->start;
+
+ if (d < dist)
+ min_dist_node = n;
+ }
+
+ if (!min_dist_node)
+ break;
+
+ req->node = min_dist_node;
+ req->state = req->node->state;
+
+ if (req->node->bdev) {
+ req->bio->bi_bdev = req->node->bdev;
+ generic_make_request(req->bio);
+ err = 0;
+ break;
+ }
+
+ err = req->state->ops->push(req);
+ if (err) {
+ dprintk("%s: req: %p, bio: %p, node: %p, err: %d.\n",
+ __func__, req, req->bio, min_dist_node, err);
+ dst_mirror_mark_notsync(req->node);
+ }
+ } while (err && min_dist_node);
+
+ if (err || !min_dist_node) {
+ dprintk("%s: req: %p, bio: %p, node: %p, err: %d.\n",
+ __func__, req, req->bio, min_dist_node, err);
+ if (!err)
+ err = -ENODEV;
+ }
+ dprintk("%s: req: %p, err: %d.\n", __func__, req, err);
+ return err;
+}
+
+/*
+ * This callback is invoked from block layer request processing function,
+ * its task is to remap block request to different nodes.
+ */
+static int dst_mirror_remap(struct dst_request *req)
+{
+ int (*remap[])(struct dst_request *) =
+ {&dst_mirror_read, &dst_mirror_write};
+
+ return remap[bio_rw(req->bio) == WRITE](req);
+}
+
+static int dst_mirror_error(struct kst_state *st, int err)
+{
+ struct dst_request *req, *tmp;
+ unsigned int revents = st->socket->ops->poll(NULL, st->socket, NULL);
+
+ dprintk("%s: err: %d, revents: %x, notsync: %d.\n",
+ __func__, err, revents,
+ test_bit(DST_NODE_NOTSYNC, &st->node->flags));
+
+ if (err == -EEXIST)
+ return err;
+
+ if (!(revents & (POLLERR | POLLHUP)) &&
+ (err == -EPIPE || err == -ECONNRESET)) {
+ if (test_bit(DST_NODE_NOTSYNC, &st->node->flags)) {
+ return dst_mirror_resync(st->node, 1);
+ }
+ return 0;
+ }
+
+ if (atomic_read(&st->node->shared_num) == 0 &&
+ !st->node->shared_head) {
+ dprintk("%s: this node is the only one in the mirror, "
+ "can not mark it notsync.\n", __func__);
+ return err;
+ }
+
+ dst_mirror_mark_notsync(st->node);
+
+ mutex_lock(&st->request_lock);
+ list_for_each_entry_safe(req, tmp, &st->request_list,
+ request_list_entry) {
+ kst_del_req(req);
+ dprintk("%s: requeue [%c], start: %llu, idx: %d,"
+ " num: %d, size: %llu, offset: %u, err: %d.\n",
+ __func__, (bio_rw(req->bio) == WRITE)?'W':'R',
+ req->start, req->idx, req->num, req->size,
+ req->offset, err);
+
+ if (bio_rw(req->bio) != WRITE) {
+ req->start -= to_sector(req->orig_size - req->size);
+ req->size = req->orig_size;
+ req->flags &= ~(DST_REQ_HEADER_SENT | DST_REQ_CHEKSUM_RECV);
+ req->idx = 0;
+ if (dst_mirror_read(req))
+ dst_free_request(req);
+ } else {
+ kst_complete_req(req, err);
+ }
+ }
+ mutex_unlock(&st->request_lock);
+ return err;
+}
+
+static struct dst_alg_ops alg_mirror_ops = {
+ .remap = dst_mirror_remap,
+ .add_node = dst_mirror_add_node,
+ .del_node = dst_mirror_del_node,
+ .error = dst_mirror_error,
+ .owner = THIS_MODULE,
+};
+
+static int __devinit alg_mirror_init(void)
+{
+ int err = -ENOMEM;
+
+ dst_mirror_bio_set = bioset_create(256, 256);
+ if (!dst_mirror_bio_set)
+ return -ENOMEM;
+
+ alg_mirror = dst_alloc_alg("alg_mirror", &alg_mirror_ops);
+ if (!alg_mirror)
+ goto err_out;
+
+ return 0;
+
+err_out:
+ bioset_free(dst_mirror_bio_set);
+ return err;
+}
+
+static void __devexit alg_mirror_exit(void)
+{
+ dst_remove_alg(alg_mirror);
+ bioset_free(dst_mirror_bio_set);
+}
+
+module_init(alg_mirror_init);
+module_exit(alg_mirror_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Evgeniy Polyakov <johnpol@2ka.mipt.ru>");
+MODULE_DESCRIPTION("Mirror distributed algorithm.");
^ permalink raw reply related
* [3/4] DST: Network state machine.
From: Evgeniy Polyakov @ 2007-12-10 11:47 UTC (permalink / raw)
To: lkml; +Cc: netdev, linux-fsdevel
In-Reply-To: <1197287250388@2ka.mipt.ru>
Network state machine.
Includes network async processing state machine and related tasks.
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
diff --git a/drivers/block/dst/kst.c b/drivers/block/dst/kst.c
new file mode 100644
index 0000000..8fa3387
--- /dev/null
+++ b/drivers/block/dst/kst.c
@@ -0,0 +1,1513 @@
+/*
+ * 2007+ Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * All rights reserved.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/kthread.h>
+#include <linux/net.h>
+#include <linux/in.h>
+#include <linux/poll.h>
+#include <linux/bio.h>
+#include <linux/dst.h>
+
+#include <net/sock.h>
+
+struct kst_poll_helper
+{
+ poll_table pt;
+ struct kst_state *st;
+};
+
+static LIST_HEAD(kst_worker_list);
+static DEFINE_MUTEX(kst_worker_mutex);
+
+/*
+ * This function creates bound socket for local export node.
+ */
+static int kst_sock_create(struct kst_state *st, struct saddr *addr,
+ int type, int proto, int backlog)
+{
+ int err;
+
+ err = sock_create(addr->sa_family, type, proto, &st->socket);
+ if (err)
+ goto err_out_exit;
+
+ err = st->socket->ops->bind(st->socket, (struct sockaddr *)addr,
+ addr->sa_data_len);
+
+ err = st->socket->ops->listen(st->socket, backlog);
+ if (err)
+ goto err_out_release;
+
+ st->socket->sk->sk_allocation = GFP_NOIO;
+
+ return 0;
+
+err_out_release:
+ sock_release(st->socket);
+err_out_exit:
+ return err;
+}
+
+static void kst_sock_release(struct kst_state *st)
+{
+ if (st->socket) {
+ sock_release(st->socket);
+ st->socket = NULL;
+ }
+}
+
+void kst_wake(struct kst_state *st)
+{
+ if (st) {
+ struct kst_worker *w = st->node->w;
+ unsigned long flags;
+
+ spin_lock_irqsave(&w->ready_lock, flags);
+ if (list_empty(&st->ready_entry))
+ list_add_tail(&st->ready_entry, &w->ready_list);
+ spin_unlock_irqrestore(&w->ready_lock, flags);
+
+ wake_up(&w->wait);
+ }
+}
+EXPORT_SYMBOL_GPL(kst_wake);
+
+/*
+ * Polling machinery.
+ */
+static int kst_state_wake_callback(wait_queue_t *wait, unsigned mode,
+ int sync, void *key)
+{
+ struct kst_state *st = container_of(wait, struct kst_state, wait);
+ kst_wake(st);
+ return 1;
+}
+
+static void kst_queue_func(struct file *file, wait_queue_head_t *whead,
+ poll_table *pt)
+{
+ struct kst_state *st = container_of(pt, struct kst_poll_helper, pt)->st;
+
+ st->whead = whead;
+ init_waitqueue_func_entry(&st->wait, kst_state_wake_callback);
+ add_wait_queue(whead, &st->wait);
+}
+
+static void kst_poll_exit(struct kst_state *st)
+{
+ if (st->whead) {
+ remove_wait_queue(st->whead, &st->wait);
+ st->whead = NULL;
+ }
+}
+
+/*
+ * This function removes request from state tree and ordering list.
+ */
+void kst_del_req(struct dst_request *req)
+{
+ list_del_init(&req->request_list_entry);
+}
+EXPORT_SYMBOL_GPL(kst_del_req);
+
+static struct dst_request *kst_req_first(struct kst_state *st)
+{
+ struct dst_request *req = NULL;
+
+ if (!list_empty(&st->request_list))
+ req = list_entry(st->request_list.next, struct dst_request,
+ request_list_entry);
+ return req;
+}
+
+/*
+ * This function dequeues first request from the queue and tree.
+ */
+static struct dst_request *kst_dequeue_req(struct kst_state *st)
+{
+ struct dst_request *req;
+
+ mutex_lock(&st->request_lock);
+ req = kst_req_first(st);
+ if (req)
+ kst_del_req(req);
+ mutex_unlock(&st->request_lock);
+ return req;
+}
+
+/*
+ * This function enqueues request into tree, indexed by start of the request,
+ * and also puts request into ordered queue.
+ */
+int kst_enqueue_req(struct kst_state *st, struct dst_request *req)
+{
+ if (unlikely(req->flags & DST_REQ_CHECK_QUEUE)) {
+ struct dst_request *r;
+
+ list_for_each_entry(r, &st->request_list, request_list_entry) {
+ if (bio_rw(r->bio) != bio_rw(req->bio))
+ continue;
+
+ if (r->start >= req->start + req->size)
+ continue;
+
+ if (r->start + r->size <= req->start)
+ continue;
+
+ return -EEXIST;
+ }
+ }
+
+ list_add_tail(&req->request_list_entry, &st->request_list);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(kst_enqueue_req);
+
+/*
+ * BIOs for local exporting node are freed via this function.
+ */
+static void kst_export_put_bio(struct bio *bio)
+{
+ int i;
+ struct bio_vec *bv;
+
+ dprintk("%s: bio: %p, size: %u, idx: %d, num: %d, req: %p.\n",
+ __func__, bio, bio->bi_size, bio->bi_idx,
+ bio->bi_vcnt, bio->bi_private);
+
+ bio_for_each_segment(bv, bio, i)
+ __free_page(bv->bv_page);
+ bio_put(bio);
+}
+
+/*
+ * This is a generic request completion function for requests,
+ * queued for async processing.
+ * If it is local export node, state machine is different,
+ * see details below.
+ */
+void kst_complete_req(struct dst_request *req, int err)
+{
+ dprintk("%s: bio: %p, req: %p, size: %llu, orig_size: %llu, "
+ "bi_size: %u, err: %d, flags: %u.\n",
+ __func__, req->bio, req, req->size, req->orig_size,
+ req->bio->bi_size, err, req->flags);
+
+ if (req->flags & DST_REQ_EXPORT) {
+ if (err || !(req->flags & DST_REQ_EXPORT_WRITE)) {
+ req->bio_endio(req, err);
+ goto out;
+ }
+
+ req->bio->bi_rw = WRITE;
+ generic_make_request(req->bio);
+ } else {
+ req->bio_endio(req, err);
+ }
+out:
+ dst_free_request(req);
+}
+EXPORT_SYMBOL_GPL(kst_complete_req);
+
+static void kst_flush_requests(struct kst_state *st)
+{
+ struct dst_request *req;
+
+ while ((req = kst_dequeue_req(st)) != NULL)
+ kst_complete_req(req, -EIO);
+}
+
+static int kst_poll_init(struct kst_state *st)
+{
+ struct kst_poll_helper ph;
+
+ ph.st = st;
+ init_poll_funcptr(&ph.pt, &kst_queue_func);
+
+ st->socket->ops->poll(NULL, st->socket, &ph.pt);
+ return 0;
+}
+
+/*
+ * Main state creation function.
+ * It creates new state according to given operations
+ * and links it into worker structure and node.
+ */
+static struct kst_state *kst_state_init(struct dst_node *node,
+ unsigned int permissions,
+ struct kst_state_ops *ops, void *data)
+{
+ struct kst_state *st;
+ int err;
+
+ st = kzalloc(sizeof(struct kst_state), GFP_KERNEL);
+ if (!st)
+ return ERR_PTR(-ENOMEM);
+
+ st->permissions = permissions;
+ st->node = node;
+ st->ops = ops;
+ INIT_LIST_HEAD(&st->ready_entry);
+ INIT_LIST_HEAD(&st->entry);
+ INIT_LIST_HEAD(&st->request_list);
+ mutex_init(&st->request_lock);
+
+ err = st->ops->init(st, data);
+ if (err)
+ goto err_out_free;
+ mutex_lock(&node->w->state_mutex);
+ list_add_tail(&st->entry, &node->w->state_list);
+ mutex_unlock(&node->w->state_mutex);
+
+ kst_wake(st);
+
+ return st;
+
+err_out_free:
+ kfree(st);
+ return ERR_PTR(err);
+}
+
+/*
+ * This function is called when node is removed,
+ * or when state is destroyed for connected to local exporting
+ * node client.
+ */
+void kst_state_exit(struct kst_state *st)
+{
+ struct kst_worker *w = st->node->w;
+
+ mutex_lock(&w->state_mutex);
+ list_del_init(&st->entry);
+ mutex_unlock(&w->state_mutex);
+
+ st->ops->exit(st);
+
+ if (st == st->node->state)
+ st->node->state = NULL;
+
+ kfree(st);
+}
+
+static int kst_error(struct kst_state *st, int err)
+{
+ if ((err == -ECONNRESET || err == -EPIPE) && st->ops->recovery)
+ err = st->ops->recovery(st, err);
+
+ return st->node->st->alg->ops->error(st, err);
+}
+
+/*
+ * This is main state processing function.
+ * It tries to complete request and invoke appropriate
+ * callbacks in case of errors or successfull operation finish.
+ */
+static int kst_thread_process_state(struct kst_state *st)
+{
+ int err, empty;
+ unsigned int revents;
+ struct dst_request *req, *tmp;
+
+ mutex_lock(&st->request_lock);
+ if (st->ops->ready) {
+ err = st->ops->ready(st);
+ if (err) {
+ mutex_unlock(&st->request_lock);
+ if (err < 0)
+ kst_state_exit(st);
+ return err;
+ }
+ }
+
+ err = 0;
+ empty = 1;
+ req = NULL;
+ list_for_each_entry_safe(req, tmp, &st->request_list, request_list_entry) {
+ empty = 0;
+ revents = st->socket->ops->poll(st->socket->file,
+ st->socket, NULL);
+ if (!revents)
+ break;
+ err = req->callback(req, revents);
+ if (req->size && !err)
+ err = 1;
+
+ if (err < 0 || !req->size) {
+ if (!req->size)
+ err = 0;
+ kst_del_req(req);
+ kst_complete_req(req, err);
+ }
+
+ if (err)
+ break;
+ }
+
+ dprintk("%s: broke the loop: err: %d, list_empty: %d.\n",
+ __func__, err, list_empty(&st->request_list));
+ mutex_unlock(&st->request_lock);
+
+ if (err < 0) {
+ dprintk("%s: req: %p, err: %d, st: %p, node->state: %p.\n",
+ __func__, req, err, st, st->node->state);
+
+ if (st != st->node->state) {
+ /*
+ * Accepted client has state not related to storage
+ * node, so it must be freed explicitely.
+ * We do not try to fix clients connections to local
+ * export nodes, just drop the client.
+ */
+
+ kst_state_exit(st);
+ return err;
+ }
+
+ err = kst_error(st, err);
+ if (err)
+ return err;
+
+ kst_wake(st);
+ }
+
+ if (list_empty(&st->request_list) && !empty)
+ kst_wake(st);
+
+ return err;
+}
+
+/*
+ * Main worker thread - one per storage.
+ */
+static int kst_thread_func(void *data)
+{
+ struct kst_worker *w = data;
+ struct kst_state *st;
+ unsigned long flags;
+ int err = 0;
+
+ while (!kthread_should_stop()) {
+ wait_event_interruptible_timeout(w->wait,
+ !list_empty(&w->ready_list) ||
+ kthread_should_stop(),
+ HZ);
+
+ st = NULL;
+ spin_lock_irqsave(&w->ready_lock, flags);
+ if (!list_empty(&w->ready_list)) {
+ st = list_entry(w->ready_list.next, struct kst_state,
+ ready_entry);
+ list_del_init(&st->ready_entry);
+ }
+ spin_unlock_irqrestore(&w->ready_lock, flags);
+
+ if (!st)
+ continue;
+
+ err = kst_thread_process_state(st);
+ }
+
+ return err;
+}
+
+/*
+ * Worker initialization - this object will host andprocess all states,
+ * which in turn host requests for remote targets.
+ */
+struct kst_worker *kst_worker_init(int id)
+{
+ struct kst_worker *w;
+ int err;
+
+ w = kzalloc(sizeof(struct kst_worker), GFP_KERNEL);
+ if (!w)
+ return ERR_PTR(-ENOMEM);
+
+ w->id = id;
+ init_waitqueue_head(&w->wait);
+ spin_lock_init(&w->ready_lock);
+ mutex_init(&w->state_mutex);
+
+ INIT_LIST_HEAD(&w->ready_list);
+ INIT_LIST_HEAD(&w->state_list);
+
+ w->req_pool = mempool_create_slab_pool(256, dst_request_cache);
+ if (!w->req_pool) {
+ err = -ENOMEM;
+ goto err_out_free;
+ }
+
+ w->thread = kthread_run(&kst_thread_func, w, "kst%d", w->id);
+ if (IS_ERR(w->thread)) {
+ err = PTR_ERR(w->thread);
+ goto err_out_destroy;
+ }
+
+ mutex_lock(&kst_worker_mutex);
+ list_add_tail(&w->entry, &kst_worker_list);
+ mutex_unlock(&kst_worker_mutex);
+
+ return w;
+
+err_out_destroy:
+ mempool_destroy(w->req_pool);
+err_out_free:
+ kfree(w);
+ return ERR_PTR(err);
+}
+
+void kst_worker_exit(struct kst_worker *w)
+{
+ struct kst_state *st, *n;
+
+ mutex_lock(&kst_worker_mutex);
+ list_del(&w->entry);
+ mutex_unlock(&kst_worker_mutex);
+
+ kthread_stop(w->thread);
+
+ list_for_each_entry_safe(st, n, &w->state_list, entry) {
+ kst_state_exit(st);
+ }
+
+ mempool_destroy(w->req_pool);
+ kfree(w);
+}
+
+/*
+ * Common state exit callback.
+ * Removes itself from worker's list of states,
+ * releases socket and flushes all requests.
+ */
+static void kst_common_exit(struct kst_state *st)
+{
+ unsigned long flags;
+
+ kst_poll_exit(st);
+
+ spin_lock_irqsave(&st->node->w->ready_lock, flags);
+ list_del_init(&st->ready_entry);
+ spin_unlock_irqrestore(&st->node->w->ready_lock, flags);
+
+ kst_flush_requests(st);
+ kst_sock_release(st);
+}
+
+/*
+ * Listen socket contains security attributes in request_list,
+ * so it can not be flushed via usual way.
+ */
+static void kst_listen_flush(struct kst_state *st)
+{
+ struct dst_secure *s, *tmp;
+
+ list_for_each_entry_safe(s, tmp, &st->request_list, sec_entry) {
+ list_del(&s->sec_entry);
+ kfree(s);
+ }
+}
+
+static void kst_listen_exit(struct kst_state *st)
+{
+ kst_listen_flush(st);
+ kst_common_exit(st);
+}
+
+/*
+ * BIO vector receiving function - does not block, but may sleep because
+ * of scheduling policy.
+ */
+static int kst_data_recv_bio_vec(struct kst_state *st, struct bio_vec *bv,
+ unsigned int offset, unsigned int size)
+{
+ struct msghdr msg;
+ struct kvec iov;
+ void *kaddr;
+ int err;
+
+ kaddr = kmap(bv->bv_page);
+
+ iov.iov_base = kaddr + bv->bv_offset + offset;
+ iov.iov_len = size;
+
+ msg.msg_iov = (struct iovec *)&iov;
+ msg.msg_iovlen = 1;
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
+
+ err = kernel_recvmsg(st->socket, &msg, &iov, 1, iov.iov_len,
+ msg.msg_flags);
+ kunmap(bv->bv_page);
+
+ return err;
+}
+
+/*
+ * BIO vector sending function - does not block, but may sleep because
+ * of scheduling policy.
+ */
+static int kst_data_send_bio_vec(struct kst_state *st, struct bio_vec *bv,
+ unsigned int offset, unsigned int size)
+{
+ return kernel_sendpage(st->socket, bv->bv_page,
+ bv->bv_offset + offset, size,
+ MSG_DONTWAIT | MSG_NOSIGNAL);
+}
+
+static int kst_data_send_bio_vec_slow(struct kst_state *st, struct bio_vec *bv,
+ unsigned int offset, unsigned int size)
+{
+ struct msghdr msg;
+ struct kvec iov;
+ void *addr;
+ int err;
+
+ addr = kmap(bv->bv_page);
+ iov.iov_base = addr + bv->bv_offset + offset;
+ iov.iov_len = size;
+
+ msg.msg_iov = (struct iovec *)&iov;
+ msg.msg_iovlen = 1;
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL;
+
+ err = kernel_sendmsg(st->socket, &msg, &iov, 1, iov.iov_len);
+ kunmap(bv->bv_page);
+
+ return err;
+}
+
+static u32 dst_csum_bvec(struct bio_vec *bv, unsigned int offset, unsigned int size)
+{
+ void *addr;
+ u32 csum;
+
+ addr = kmap_atomic(bv->bv_page, KM_USER0);
+ csum = dst_csum_data(addr + bv->bv_offset + offset, size);
+ kunmap_atomic(addr, KM_USER0);
+
+ return csum;
+}
+
+typedef int (*kst_data_process_bio_vec_t)(struct kst_state *st,
+ struct bio_vec *bv, unsigned int offset, unsigned int size);
+
+/*
+ * @req: processing request.
+ * Contains BIO and all related to its processing info.
+ *
+ * This function sends or receives requested number of pages from given BIO.
+ *
+ * In case of errors negative value is returned and @size,
+ * @index and @off are set to the:
+ * - number of bytes not yet processed (i.e. the rest of the bytes to be
+ * processed).
+ * - index of the last bio_vec started to be processed (header sent).
+ * - offset of the first byte to be processed in the bio_vec.
+ *
+ * If there are no errors, zero is returned.
+ * -EAGAIN is not an error and is transformed into zero return value,
+ * called must check if @size is zero, in that case whole BIO is processed
+ * and thus req->bio_endio() can be called, othervise new request must be allocated
+ * to be processed later.
+ */
+static int kst_data_process_bio(struct dst_request *req)
+{
+ int err = -ENOSPC;
+ struct dst_remote_request r;
+ kst_data_process_bio_vec_t func;
+ unsigned int cur_size;
+ int use_csum = test_bit(DST_NODE_USE_CSUM, &req->node->flags);
+
+ if (bio_rw(req->bio) == WRITE) {
+ int i;
+
+ func = kst_data_send_bio_vec;
+ for (i=req->idx; i<req->num; ++i) {
+ struct bio_vec *bv = bio_iovec_idx(req->bio, i);
+
+ if (PageSlab(bv->bv_page)) {
+ func = kst_data_send_bio_vec_slow;
+ break;
+ }
+ }
+ r.cmd = cpu_to_be32(DST_WRITE);
+ } else {
+ r.cmd = cpu_to_be32(DST_READ);
+ func = kst_data_recv_bio_vec;
+ }
+
+ dprintk("%s: start: [%c], start: %llu, idx: %d, num: %d, "
+ "size: %llu, offset: %u, flags: %x, use_csum: %d.\n",
+ __func__, (bio_rw(req->bio) == WRITE)?'W':'R',
+ req->start, req->idx, req->num, req->size, req->offset,
+ req->flags, use_csum);
+
+ while (req->idx < req->num) {
+ struct bio_vec *bv = bio_iovec_idx(req->bio, req->idx);
+
+ cur_size = min_t(u64, bv->bv_len - req->offset, req->size);
+
+ dprintk("%s: page: %p, slab: %d, count: %d, max: %d, off: %u, len: %u, req->offset: %u, "
+ "req->size: %llu, cur_size: %u, flags: %x, "
+ "use_csum: %d, req->csum: %x.\n",
+ __func__, bv->bv_page, PageSlab(bv->bv_page),
+ atomic_read(&bv->bv_page->_count), req->bio->bi_vcnt,
+ bv->bv_offset, bv->bv_len,
+ req->offset, req->size, cur_size,
+ req->flags, use_csum, req->tmp_csum);
+
+ if (cur_size == 0) {
+ printk(KERN_ERR "%s: %d/%d: start: %llu, "
+ "bv_offset: %u, bv_len: %u, "
+ "req_offset: %u, req_size: %llu, "
+ "req: %p, bio: %p, err: %d.\n",
+ __func__, req->idx, req->num, req->start,
+ bv->bv_offset, bv->bv_len,
+ req->offset, req->size,
+ req, req->bio, err);
+ BUG();
+ }
+
+ if (!(req->flags & DST_REQ_HEADER_SENT)) {
+ r.sector = cpu_to_be64(req->start);
+ r.offset = cpu_to_be32(bv->bv_offset + req->offset);
+ r.size = cpu_to_be32(cur_size);
+ r.csum = 0;
+
+ if (use_csum && bio_rw(req->bio) == WRITE &&
+ !req->tmp_offset) {
+ req->tmp_offset = req->offset;
+ r.csum = cpu_to_be32(dst_csum_bvec(bv,
+ req->offset, cur_size));
+ }
+
+ err = dst_data_send_header(req->state->socket, &r);
+ dprintk("%s: %d/%d: sending header: cmd: %u, start: %llu, "
+ "bv_offset: %u, bv_len: %u, "
+ "a offset: %u, offset: %u, "
+ "cur_size: %u, err: %d.\n",
+ __func__, req->idx, req->num, be32_to_cpu(r.cmd),
+ req->start, bv->bv_offset, bv->bv_len,
+ bv->bv_offset + req->offset,
+ req->offset, cur_size, err);
+
+ if (err != sizeof(struct dst_remote_request)) {
+ if (err >= 0)
+ err = -EINVAL;
+ break;
+ }
+
+ req->flags |= DST_REQ_HEADER_SENT;
+ }
+
+ if (use_csum && (bio_rw(req->bio) != WRITE) &&
+ !(req->flags & DST_REQ_CHEKSUM_RECV)) {
+ struct dst_remote_request tmp_req;
+
+ err = dst_data_recv_header(req->state->socket, &tmp_req, 0);
+ dprintk("%s: %d/%d: receiving header: start: %llu, "
+ "bv_offset: %u, bv_len: %u, "
+ "a offset: %u, offset: %u, "
+ "cur_size: %u, err: %d.\n",
+ __func__, req->idx, req->num,
+ req->start, bv->bv_offset, bv->bv_len,
+ bv->bv_offset + req->offset,
+ req->offset, cur_size, err);
+
+ if (err != sizeof(struct dst_remote_request)) {
+ if (err >= 0)
+ err = -EINVAL;
+ break;
+ }
+
+ if (req->tmp_csum) {
+ printk("%s: req: %p, old csum: %x, new: %x.\n",
+ __func__, req, req->tmp_csum,
+ be32_to_cpu(tmp_req.csum));
+ BUG_ON(1);
+ }
+
+ dprintk("%s: req: %p, old csum: %x, new: %x.\n",
+ __func__, req, req->tmp_csum,
+ be32_to_cpu(tmp_req.csum));
+ req->tmp_csum = be32_to_cpu(tmp_req.csum);
+
+ req->flags |= DST_REQ_CHEKSUM_RECV;
+ }
+
+ err = func(req->state, bv, req->offset, cur_size);
+ if (err <= 0)
+ break;
+
+ req->offset += err;
+ req->size -= err;
+
+ if (req->offset != bv->bv_len) {
+ dprintk("%s: %d/%d: this: start: %llu, bv_offset: %u, "
+ "bv_len: %u, offset: %u, "
+ "cur_size: %u, err: %d.\n",
+ __func__, req->idx, req->num, req->start,
+ bv->bv_offset, bv->bv_len,
+ req->offset, cur_size, err);
+ err = -EAGAIN;
+ break;
+ }
+
+ if (use_csum && bio_rw(req->bio) != WRITE) {
+ u32 csum = dst_csum_bvec(bv, req->tmp_offset,
+ bv->bv_len - req->tmp_offset);
+
+ dprintk("%s: req: %p, csum: %x, received csum: %x.\n",
+ __func__, req, csum, req->tmp_csum);
+
+ if (csum != req->tmp_csum) {
+ printk("%s: %d/%d: broken checksum: start: %llu, "
+ "bv_offset: %u, bv_len: %u, "
+ "a offset: %u, offset: %u, "
+ "cur_size: %u, orig_size: %llu.\n",
+ __func__, req->idx, req->num,
+ req->start, bv->bv_offset, bv->bv_len,
+ bv->bv_offset + req->offset,
+ req->offset, cur_size, req->orig_size);
+ printk("%s: broken checksum: req: %p, csum: %x, "
+ "should be: %x, flags: %x, "
+ "req->tmp_offset: %u, rw: %lu.\n",
+ __func__, req, csum, req->tmp_csum,
+ req->flags, req->tmp_offset, bio_rw(req->bio));
+
+ req->offset -= err;
+ req->size += err;
+
+ err = -EREMOTEIO;
+ break;
+ }
+ }
+
+ req->offset = 0;
+ req->idx++;
+ req->flags &= ~(DST_REQ_HEADER_SENT | DST_REQ_CHEKSUM_RECV);
+ req->tmp_csum = 0;
+ req->start += to_sector(bv->bv_len);
+ }
+
+ if (err <= 0 && err != -EAGAIN) {
+ if (err == 0)
+ err = -ECONNRESET;
+ } else
+ err = 0;
+
+ if (err < 0 || (req->idx == req->num && req->size)) {
+ dprintk("%s: return: idx: %d, num: %d, offset: %u, "
+ "size: %llu, err: %d.\n",
+ __func__, req->idx, req->num, req->offset,
+ req->size, err);
+ }
+ dprintk("%s: end: start: %llu, idx: %d, num: %d, "
+ "size: %llu, offset: %u.\n",
+ __func__, req->start, req->idx, req->num,
+ req->size, req->offset);
+
+ return err;
+}
+
+void kst_bio_endio(struct dst_request *req, int err)
+{
+ if (err && printk_ratelimit())
+ printk("%s: freeing bio: %p, bi_size: %u, "
+ "orig_size: %llu, req: %p, err: %d.\n",
+ __func__, req->bio, req->bio->bi_size, req->orig_size,
+ req, err);
+ bio_endio(req->bio, req->orig_size, err);
+}
+EXPORT_SYMBOL_GPL(kst_bio_endio);
+
+/*
+ * This callback is invoked by worker thread to process given request.
+ */
+int kst_data_callback(struct dst_request *req, unsigned int revents)
+{
+ int err;
+
+ dprintk("%s: req: %p, num: %d, idx: %d, bio: %p, "
+ "revents: %x, flags: %x.\n",
+ __func__, req, req->num, req->idx, req->bio,
+ revents, req->flags);
+
+ if (req->flags & DST_REQ_EXPORT_READ)
+ return 1;
+
+ err = kst_data_process_bio(req);
+
+ if (revents & (POLLERR | POLLHUP | POLLRDHUP))
+ err = -EPIPE;
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(kst_data_callback);
+
+struct dst_request *dst_clone_request(struct dst_request *req, mempool_t *pool)
+{
+ struct dst_request *new_req;
+
+ new_req = mempool_alloc(pool, GFP_NOIO);
+ if (!new_req)
+ return NULL;
+
+ memset(new_req, 0, sizeof(struct dst_request));
+
+ dprintk("%s: req: %p, new_req: %p.\n", __func__, req, new_req);
+
+ if (req) {
+ new_req->bio = req->bio;
+ new_req->state = req->state;
+ new_req->node = req->node;
+ new_req->idx = req->idx;
+ new_req->num = req->num;
+ new_req->size = req->size;
+ new_req->orig_size = req->orig_size;
+ new_req->offset = req->offset;
+ new_req->tmp_offset = req->tmp_offset;
+ new_req->tmp_csum = req->tmp_csum;
+ new_req->start = req->start;
+ new_req->flags = req->flags;
+ new_req->bio_endio = req->bio_endio;
+ new_req->priv = req->priv;
+ }
+
+ return new_req;
+}
+EXPORT_SYMBOL_GPL(dst_clone_request);
+
+void dst_free_request(struct dst_request *req)
+{
+ dprintk("%s: free req: %p, pool: %p, bio: %p, state: %p, node: %p.\n",
+ __func__, req, req->node->w->req_pool,
+ req->bio, req->state, req->node);
+ mempool_free(req, req->node->w->req_pool);
+}
+EXPORT_SYMBOL_GPL(dst_free_request);
+
+/*
+ * This is main data processing function, eventually invoked from block layer.
+ * It tries to complte request, but if it is about to block, it allocates
+ * new request and queues it to main worker to be processed when events allow.
+ */
+static int kst_data_push(struct dst_request *req)
+{
+ struct kst_state *st = req->state;
+ struct dst_request *new_req;
+ unsigned int revents;
+ int err, locked = 0;
+
+ dprintk("%s: start: %llu, size: %llu, bio: %p.\n",
+ __func__, req->start, req->size, req->bio);
+
+ if (!list_empty(&st->request_list) || (req->flags & DST_REQ_ALWAYS_QUEUE))
+ goto alloc_new_req;
+
+ if (mutex_trylock(&st->request_lock)) {
+ locked = 1;
+
+ if (!list_empty(&st->request_list))
+ goto alloc_new_req;
+
+ revents = st->socket->ops->poll(NULL, st->socket, NULL);
+ if (revents & POLLOUT) {
+ err = kst_data_process_bio(req);
+ if (err < 0)
+ goto out_unlock;
+
+ if (!req->size)
+ goto out_bio_endio;
+ }
+ }
+
+alloc_new_req:
+ err = -ENOMEM;
+ new_req = dst_clone_request(req, req->node->w->req_pool);
+ if (!new_req)
+ goto out_unlock;
+
+ new_req->callback = &kst_data_callback;
+
+ if (!locked)
+ mutex_lock(&st->request_lock);
+
+ locked = 1;
+
+ err = kst_enqueue_req(st, new_req);
+ if (err)
+ goto out_unlock;
+ mutex_unlock(&st->request_lock);
+
+ err = 0;
+ goto out;
+
+out_bio_endio:
+ req->bio_endio(req, err);
+out_unlock:
+ if (locked)
+ mutex_unlock(&st->request_lock);
+ locked = 0;
+
+ if (err) {
+ err = kst_error(st, err);
+ if (!err)
+ goto alloc_new_req;
+ }
+
+ if (err && printk_ratelimit()) {
+ printk("%s: error [%c], start: %llu, idx: %d, num: %d, "
+ "size: %llu, offset: %u, err: %d.\n",
+ __func__, (bio_rw(req->bio) == WRITE)?'W':'R',
+ req->start, req->idx, req->num, req->size,
+ req->offset, err);
+ }
+
+out:
+
+ kst_wake(st);
+ return err;
+}
+
+/*
+ * Remote node initialization callback.
+ */
+static int kst_data_init(struct kst_state *st, void *data)
+{
+ int err;
+
+ st->socket = data;
+ st->socket->sk->sk_allocation = GFP_NOIO;
+ /*
+ * Why not?
+ */
+ st->socket->sk->sk_sndbuf = st->socket->sk->sk_sndbuf = 1024*1024*10;
+
+ err = kst_poll_init(st);
+ if (err)
+ return err;
+
+ return 0;
+}
+
+/*
+ * Remote node recovery function - tries to reconnect to given target.
+ */
+static int kst_data_recovery(struct kst_state *st, int err)
+{
+ struct socket *sock;
+ struct sockaddr addr;
+ int addrlen;
+ struct dst_request *req;
+
+ if (err != -ECONNRESET && err != -EPIPE) {
+ dprintk("%s: state %p does not know how "
+ "to recover from error %d.\n",
+ __func__, st, err);
+ return err;
+ }
+
+ err = sock_create(st->socket->ops->family, st->socket->type,
+ st->socket->sk->sk_protocol, &sock);
+ if (err < 0)
+ goto err_out_exit;
+
+ sock->sk->sk_sndtimeo = sock->sk->sk_rcvtimeo =
+ msecs_to_jiffies(DST_DEFAULT_TIMEO);
+
+ err = sock->ops->getname(st->socket, &addr, &addrlen, 2);
+ if (err)
+ goto err_out_destroy;
+
+ err = sock->ops->connect(sock, &addr, addrlen, 0);
+ if (err)
+ goto err_out_destroy;
+
+ kst_poll_exit(st);
+ kst_sock_release(st);
+
+ mutex_lock(&st->request_lock);
+ err = st->ops->init(st, sock);
+ if (!err) {
+ /*
+ * After reconnection is completed all requests
+ * must be resent from the state they were finished previously,
+ * but with new headers.
+ */
+ list_for_each_entry(req, &st->request_list, request_list_entry)
+ req->flags &= ~(DST_REQ_HEADER_SENT | DST_REQ_CHEKSUM_RECV);
+ }
+ mutex_unlock(&st->request_lock);
+ if (err < 0)
+ goto err_out_destroy;
+
+ kst_wake(st);
+ dprintk("%s: reconnected.\n", __func__);
+
+ return 0;
+
+err_out_destroy:
+ sock_release(sock);
+err_out_exit:
+ dprintk("%s: revovery failed: st: %p, err: %d.\n", __func__, st, err);
+ return err;
+}
+
+/*
+ * Local exporting node end IO callbacks.
+ */
+static int kst_export_write_end_io(struct bio *bio, unsigned int size, int err)
+{
+ dprintk("%s: bio: %p, size: %u, idx: %d, num: %d, err: %d.\n",
+ __func__, bio, bio->bi_size, bio->bi_idx, bio->bi_vcnt, err);
+
+ if (bio->bi_size)
+ return 1;
+
+ kst_export_put_bio(bio);
+ return 0;
+}
+
+static int kst_export_read_end_io(struct bio *bio, unsigned int size, int err)
+{
+ struct dst_request *req = bio->bi_private;
+ struct kst_state *st = req->state;
+ int use_csum = test_bit(DST_NODE_USE_CSUM, &req->node->flags);
+
+ dprintk("%s: bio: %p, req: %p, size: %u, idx: %d, num: %d, err: %d.\n",
+ __func__, bio, req, bio->bi_size, bio->bi_idx,
+ bio->bi_vcnt, err);
+
+ if (bio->bi_size)
+ return 1;
+
+ if (err) {
+ kst_export_put_bio(bio);
+ return 0;
+ }
+
+ bio->bi_size = req->size = req->orig_size;
+ bio->bi_rw = WRITE;
+ if (use_csum)
+ req->flags &= ~(DST_REQ_HEADER_SENT | DST_REQ_CHEKSUM_RECV);
+
+ /*
+ * This is a race with kst_data_callback(), which checks
+ * this bit to determine if it can or can not process given
+ * request. This does not harm actually, since subsequent
+ * state wakeup will call it again and thus will pick
+ * given request in time.
+ */
+ req->flags &= ~DST_REQ_EXPORT_READ;
+ kst_wake(st);
+ return 0;
+}
+
+/*
+ * This callback is invoked each time new request from remote
+ * node to given local export node is received.
+ * It allocates new block IO request and queues it for processing.
+ */
+static int kst_export_ready(struct kst_state *st)
+{
+ struct dst_remote_request r;
+ struct bio *bio;
+ int err, nr, i;
+ struct dst_request *req;
+ unsigned int revents = st->socket->ops->poll(NULL, st->socket, NULL);
+
+ if (revents & (POLLERR | POLLHUP)) {
+ err = -EPIPE;
+ goto err_out_exit;
+ }
+
+ if (!(revents & POLLIN) || !list_empty(&st->request_list))
+ return 0;
+
+ err = dst_data_recv_header(st->socket, &r, 1);
+ if (err != sizeof(struct dst_remote_request)) {
+ err = -ECONNRESET;
+ goto err_out_exit;
+ }
+
+ kst_convert_header(&r);
+
+ dprintk("\n%s: st: %p, cmd: %u, sector: %llu, size: %u, "
+ "csum: %x, offset: %u.\n",
+ __func__, st, r.cmd, r.sector,
+ r.size, r.csum, r.offset);
+
+ err = -EINVAL;
+ if (r.cmd != DST_READ && r.cmd != DST_WRITE && r.cmd != DST_REMOTE_CFG)
+ goto err_out_exit;
+
+ if ((s64)(r.sector + to_sector(r.size)) < 0 ||
+ (r.sector + to_sector(r.size)) > st->node->size ||
+ r.offset >= PAGE_SIZE)
+ goto err_out_exit;
+
+ if (r.cmd == DST_REMOTE_CFG) {
+ r.sector = st->node->size;
+
+ if (test_bit(DST_NODE_USE_CSUM, &st->node->flags))
+ r.csum = 1;
+
+ kst_convert_header(&r);
+
+ err = dst_data_send_header(st->socket, &r);
+ if (err != sizeof(struct dst_remote_request)) {
+ err = -EINVAL;
+ goto err_out_exit;
+ }
+ kst_wake(st);
+ return 0;
+ }
+
+ nr = DIV_ROUND_UP(r.size, PAGE_SIZE);
+
+ while (r.size) {
+ int nr_pages = min(BIO_MAX_PAGES, nr);
+ unsigned int size;
+ struct page *page;
+
+ err = -ENOMEM;
+ req = dst_clone_request(NULL, st->node->w->req_pool);
+ if (!req)
+ goto err_out_exit;
+
+ bio = bio_alloc(GFP_NOIO, nr_pages);
+ if (!bio)
+ goto err_out_free_req;
+
+ req->flags = DST_REQ_EXPORT | DST_REQ_HEADER_SENT |
+ DST_REQ_CHEKSUM_RECV;
+ req->bio = bio;
+ req->state = st;
+ req->node = st->node;
+ req->callback = &kst_data_callback;
+ req->bio_endio = &kst_bio_endio;
+
+ req->tmp_offset = 0;
+ req->tmp_csum = r.csum;
+
+ /*
+ * Yes, looks a bit weird.
+ * Logic is simple - for local exporting node all operations
+ * are reversed compared to usual nodes, since usual nodes
+ * process remote data and local export node process remote
+ * requests, so that writing data means sending data to
+ * remote node and receiving on the local export one.
+ *
+ * So, to process writing to the exported node we need first
+ * to receive data from the net (i.e. to perform READ
+ * operationin terms of usual node), and then put it to the
+ * storage (WRITE command, so it will be changed before
+ * calling generic_make_request()).
+ *
+ * To process read request from the exported node we need
+ * first to read it from storage (READ command for BIO)
+ * and then send it over the net (perform WRITE operation
+ * in terms of network).
+ */
+ if (r.cmd == DST_WRITE) {
+ req->flags |= DST_REQ_EXPORT_WRITE;
+ bio->bi_end_io = kst_export_write_end_io;
+ } else {
+ req->flags |= DST_REQ_EXPORT_READ;
+ bio->bi_end_io = kst_export_read_end_io;
+ }
+ bio->bi_rw = READ;
+ bio->bi_private = req;
+ bio->bi_sector = r.sector;
+ bio->bi_bdev = st->node->bdev;
+
+ for (i = 0; i < nr_pages; ++i) {
+ page = alloc_page(GFP_NOIO);
+ if (!page)
+ break;
+
+ size = min_t(u32, PAGE_SIZE - r.offset, r.size);
+
+ err = bio_add_page(bio, page, size, 0);
+ dprintk("%s: %d/%d: page: %p, size: %u, "
+ "offset: %u (used zero), err: %d.\n",
+ __func__, i, nr_pages, page, size,
+ r.offset, err);
+ if (err <= 0)
+ break;
+
+ if (err == size)
+ nr--;
+
+ r.size -= err;
+ r.sector += to_sector(err);
+
+ if (!r.size)
+ break;
+ }
+
+ if (!bio->bi_vcnt) {
+ err = -ENOMEM;
+ goto err_out_put;
+ }
+
+ req->size = req->orig_size = bio->bi_size;
+ req->start = bio->bi_sector;
+ req->idx = 0;
+ req->num = bio->bi_vcnt;
+
+ dprintk("%s: submitting: bio: %p, req: %p, start: %llu, "
+ "size: %llu, idx: %d, num: %d, offset: %u, csum: %x.\n",
+ __func__, bio, req, req->start, req->size,
+ req->idx, req->num, req->offset, req->tmp_csum);
+
+ err = kst_enqueue_req(st, req);
+ if (err)
+ goto err_out_put;
+
+ if (r.cmd == DST_READ) {
+ generic_make_request(bio);
+ }
+ }
+
+ kst_wake(st);
+ return 0;
+
+err_out_put:
+ bio_put(bio);
+err_out_free_req:
+ dst_free_request(req);
+err_out_exit:
+ return err;
+}
+
+static void kst_export_exit(struct kst_state *st)
+{
+ struct dst_node *n = st->node;
+
+ kst_common_exit(st);
+ dst_node_put(n);
+}
+
+static struct kst_state_ops kst_data_export_ops = {
+ .init = &kst_data_init,
+ .push = &kst_data_push,
+ .exit = &kst_export_exit,
+ .ready = &kst_export_ready,
+};
+
+/*
+ * This callback is invoked each time listening socket for
+ * given local export node becomes ready.
+ * It creates new state for connected client and queues for processing.
+ */
+static int kst_listen_ready(struct kst_state *st)
+{
+ struct socket *newsock;
+ struct saddr addr;
+ struct kst_state *newst;
+ int err;
+ unsigned int revents, permissions = 0;
+ struct dst_secure *s;
+
+ revents = st->socket->ops->poll(NULL, st->socket, NULL);
+ if (!(revents & POLLIN))
+ return 1;
+
+ err = sock_create(st->socket->ops->family, st->socket->type,
+ st->socket->sk->sk_protocol, &newsock);
+ if (err)
+ goto err_out_exit;
+
+ err = st->socket->ops->accept(st->socket, newsock, 0);
+ if (err)
+ goto err_out_put;
+
+ if (newsock->ops->getname(newsock, (struct sockaddr *)&addr,
+ (int *)&addr.sa_data_len, 2) < 0) {
+ err = -ECONNABORTED;
+ goto err_out_put;
+ }
+
+ list_for_each_entry(s, &st->request_list, sec_entry) {
+ void *sec_addr, *new_addr;
+
+ sec_addr = ((void *)&s->sec.addr) + s->sec.check_offset;
+ new_addr = ((void *)&addr) + s->sec.check_offset;
+
+ if (!memcmp(sec_addr, new_addr,
+ addr.sa_data_len - s->sec.check_offset)) {
+ permissions = s->sec.permissions;
+ break;
+ }
+ }
+
+ /*
+ * So far only reading and writing are supported.
+ * Block device does not know about anything else,
+ * but as far as I recall, there was a prognosis,
+ * that computer will never require more than 640kb of RAM.
+ */
+ if (permissions == 0) {
+ err = -EPERM;
+ goto err_out_put;
+ }
+
+ if (st->socket->ops->family == AF_INET) {
+ struct sockaddr_in *sin = (struct sockaddr_in *)&addr;
+ printk(KERN_INFO "%s: Client: %u.%u.%u.%u:%d.\n", __func__,
+ NIPQUAD(sin->sin_addr.s_addr), ntohs(sin->sin_port));
+ } else if (st->socket->ops->family == AF_INET6) {
+ struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr;
+ printk(KERN_INFO "%s: Client: "
+ "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%d",
+ __func__,
+ NIP6(sin->sin6_addr), ntohs(sin->sin6_port));
+ }
+
+ dst_node_get(st->node);
+ newst = kst_state_init(st->node, permissions,
+ &kst_data_export_ops, newsock);
+ if (IS_ERR(newst)) {
+ err = PTR_ERR(newst);
+ goto err_out_put;
+ }
+
+ /*
+ * Negative return value means error, positive - stop this state
+ * processing. Zero allows to check state for pending requests.
+ * Listening socket contains security objects in request list,
+ * since it does not have any requests.
+ */
+ return 1;
+
+err_out_put:
+ sock_release(newsock);
+err_out_exit:
+ return 1;
+}
+
+static int kst_listen_init(struct kst_state *st, void *data)
+{
+ int err = -ENOMEM, i;
+ struct dst_le_template *tmp = data;
+ struct dst_secure *s;
+
+ for (i=0; i<tmp->le->secure_attr_num; ++i) {
+ s = kmalloc(sizeof(struct dst_secure), GFP_KERNEL);
+ if (!s)
+ goto err_out_exit;
+
+ memcpy(&s->sec, tmp->data, sizeof(struct dst_secure_user));
+
+ list_add_tail(&s->sec_entry, &st->request_list);
+ tmp->data += sizeof(struct dst_secure_user);
+
+ if (s->sec.addr.sa_family == AF_INET) {
+ struct sockaddr_in *sin =
+ (struct sockaddr_in *)&s->sec.addr;
+ printk(KERN_INFO "%s: Client: %u.%u.%u.%u:%d, "
+ "permissions: %x.\n",
+ __func__, NIPQUAD(sin->sin_addr.s_addr),
+ ntohs(sin->sin_port), s->sec.permissions);
+ } else if (s->sec.addr.sa_family == AF_INET6) {
+ struct sockaddr_in6 *sin =
+ (struct sockaddr_in6 *)&s->sec.addr;
+ printk(KERN_INFO "%s: Client: "
+ "%04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%d, "
+ "permissions: %x.\n",
+ __func__, NIP6(sin->sin6_addr),
+ ntohs(sin->sin6_port), s->sec.permissions);
+ }
+ }
+
+ err = kst_sock_create(st, &tmp->le->rctl.addr, tmp->le->rctl.type,
+ tmp->le->rctl.proto, tmp->le->backlog);
+ if (err)
+ goto err_out_exit;
+
+ err = kst_poll_init(st);
+ if (err)
+ goto err_out_release;
+
+ return 0;
+
+err_out_release:
+ kst_sock_release(st);
+err_out_exit:
+ kst_listen_flush(st);
+ return err;
+}
+
+/*
+ * Operations for different types of states.
+ * There are three:
+ * data state - created for remote node, when distributed storage connects
+ * to remote node, which contain data.
+ * listen state - created for local export node, when remote distributed
+ * storage's node connects to given node to get/put data.
+ * data export state - created for each client connected to above listen
+ * state.
+ */
+static struct kst_state_ops kst_listen_ops = {
+ .init = &kst_listen_init,
+ .exit = &kst_listen_exit,
+ .ready = &kst_listen_ready,
+};
+static struct kst_state_ops kst_data_ops = {
+ .init = &kst_data_init,
+ .push = &kst_data_push,
+ .exit = &kst_common_exit,
+ .recovery = &kst_data_recovery,
+};
+
+struct kst_state *kst_listener_state_init(struct dst_node *node,
+ struct dst_le_template *tmp)
+{
+ return kst_state_init(node, DST_PERM_READ | DST_PERM_WRITE,
+ &kst_listen_ops, tmp);
+}
+
+struct kst_state *kst_data_state_init(struct dst_node *node,
+ struct socket *newsock)
+{
+ return kst_state_init(node, DST_PERM_READ | DST_PERM_WRITE,
+ &kst_data_ops, newsock);
+}
+
+/*
+ * Remove all workers and associated states.
+ */
+void kst_exit_all(void)
+{
+ struct kst_worker *w, *n;
+
+ list_for_each_entry_safe(w, n, &kst_worker_list, entry) {
+ kst_worker_exit(w);
+ }
+}
^ permalink raw reply related
* [2/4] DST: Core distributed storage files.
From: Evgeniy Polyakov @ 2007-12-10 11:47 UTC (permalink / raw)
To: lkml; +Cc: netdev, linux-fsdevel
In-Reply-To: <11972872501664@2ka.mipt.ru>
Core distributed storage files.
Include userspace interfaces, initialization,
block layer bindings and other core functionality.
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index b4c8319..ca6592d 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -451,6 +451,8 @@ config ATA_OVER_ETH
This driver provides Support for ATA over Ethernet block
devices like the Coraid EtherDrive (R) Storage Blade.
+source "drivers/block/dst/Kconfig"
+
source "drivers/s390/block/Kconfig"
endmenu
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index dd88e33..fcf042d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -29,3 +29,4 @@ obj-$(CONFIG_VIODASD) += viodasd.o
obj-$(CONFIG_BLK_DEV_SX8) += sx8.o
obj-$(CONFIG_BLK_DEV_UB) += ub.o
+obj-$(CONFIG_DST) += dst/
diff --git a/drivers/block/dst/Kconfig b/drivers/block/dst/Kconfig
new file mode 100644
index 0000000..e91f8ed
--- /dev/null
+++ b/drivers/block/dst/Kconfig
@@ -0,0 +1,28 @@
+config DST
+ tristate "Distributed storage"
+ depends on NET
+ select CONNECTOR
+ select LIBCRC32C
+ ---help---
+ This driver allows to create a distributed storage.
+
+config DST_DEBUG
+ bool "DST debug"
+ depends on DST
+ ---help---
+ This option will turn HEAVY debugging of the DST.
+ Turn it on ONLY if you have to debug some really obscure problem.
+
+config DST_ALG_LINEAR
+ tristate "Linear distribution algorithm"
+ depends on DST
+ ---help---
+ This module allows to create linear mapping of the nodes
+ in the distributed storage.
+
+config DST_ALG_MIRROR
+ tristate "Mirror distribution algorithm"
+ depends on DST
+ ---help---
+ This module allows to create a mirror of the noes in the
+ distributed storage.
diff --git a/drivers/block/dst/Makefile b/drivers/block/dst/Makefile
new file mode 100644
index 0000000..1400e94
--- /dev/null
+++ b/drivers/block/dst/Makefile
@@ -0,0 +1,6 @@
+obj-$(CONFIG_DST) += dst.o
+
+dst-y := dcore.o kst.o
+
+obj-$(CONFIG_DST_ALG_LINEAR) += alg_linear.o
+obj-$(CONFIG_DST_ALG_MIRROR) += alg_mirror.o
diff --git a/drivers/block/dst/dcore.c b/drivers/block/dst/dcore.c
new file mode 100644
index 0000000..17a5e61
--- /dev/null
+++ b/drivers/block/dst/dcore.c
@@ -0,0 +1,1631 @@
+/*
+ * 2007+ Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * All rights reserved.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/slab.h>
+#include <linux/connector.h>
+#include <linux/socket.h>
+#include <linux/dst.h>
+#include <linux/device.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/buffer_head.h>
+
+#include <net/sock.h>
+
+static LIST_HEAD(dst_storage_list);
+static LIST_HEAD(dst_alg_list);
+static DEFINE_MUTEX(dst_storage_lock);
+static DEFINE_MUTEX(dst_alg_lock);
+static int dst_major;
+static struct kst_worker *kst_main_worker;
+static struct cb_id cn_dst_id = { CN_DST_IDX, CN_DST_VAL };
+
+struct kmem_cache *dst_request_cache;
+
+static char dst_name[] = "Gamardjoba, genacvale!";
+
+/*
+ * DST sysfs tree. For device called 'storage' which is formed
+ * on top of two nodes this looks like this:
+ *
+ * /sys/devices/storage/
+ * /sys/devices/storage/alg : alg_linear
+ * /sys/devices/storage/n-800/type : R: 192.168.4.80:1025
+ * /sys/devices/storage/n-800/size : 800
+ * /sys/devices/storage/n-800/start : 800
+ * /sys/devices/storage/n-800/clean
+ * /sys/devices/storage/n-800/dirty
+ * /sys/devices/storage/n-0/type : R: 192.168.4.81:1025
+ * /sys/devices/storage/n-0/size : 800
+ * /sys/devices/storage/n-0/start : 0
+ * /sys/devices/storage/n-0/clean
+ * /sys/devices/storage/n-0/dirty
+ * /sys/devices/storage/remove_all_nodes
+ * /sys/devices/storage/nodes : sectors (start [size]): 0 [800] | 800 [800]
+ * /sys/devices/storage/name : storage
+ */
+
+static int dst_dev_match(struct device *dev, struct device_driver *drv)
+{
+ return 1;
+}
+
+static void dst_dev_release(struct device *dev)
+{
+}
+
+static struct bus_type dst_dev_bus_type = {
+ .name = "dst",
+ .match = &dst_dev_match,
+};
+
+static struct device dst_dev = {
+ .bus = &dst_dev_bus_type,
+ .release = &dst_dev_release
+};
+
+static void dst_node_release(struct device *dev)
+{
+}
+
+static struct device dst_node_dev = {
+ .release = &dst_node_release
+};
+
+static void dst_free_alg(struct dst_alg *alg)
+{
+ kfree(alg);
+}
+
+/*
+ * Algorithm is never freed directly,
+ * since its module reference counter is increased
+ * by storage when it is created - just like network protocols.
+ */
+static inline void dst_put_alg(struct dst_alg *alg)
+{
+ module_put(alg->ops->owner);
+ if (atomic_dec_and_test(&alg->refcnt))
+ dst_free_alg(alg);
+}
+
+static void dst_remove_disk(struct dst_storage *st)
+{
+ put_disk(st->disk);
+ blk_cleanup_queue(st->queue);
+}
+
+static void dst_free_storage(struct dst_storage *st)
+{
+ BUG_ON(rb_first(&st->tree_root) != NULL);
+
+ dst_remove_disk(st);
+ dst_put_alg(st->alg);
+ kfree(st);
+}
+
+static inline void dst_put_storage(struct dst_storage *st)
+{
+ if (atomic_dec_and_test(&st->refcnt))
+ dst_free_storage(st);
+}
+
+static struct bio_set *dst_bio_set;
+
+static void dst_destructor(struct bio *bio)
+{
+ bio_free(bio, dst_bio_set);
+}
+
+/*
+ * Internal callback for local requests (i.e. for local disk),
+ * which are splitted between nodes (part with local node destination
+ * ends up with this ->bi_end_io() callback).
+ */
+static int dst_end_io(struct bio *bio, unsigned int size, int err)
+{
+ struct bio *orig_bio = bio->bi_private;
+
+ if (bio->bi_size)
+ return 0;
+
+ dprintk("%s: bio: %p, orig_bio: %p, size: %u, orig_size: %u.\n",
+ __func__, bio, orig_bio, size, orig_bio->bi_size);
+
+ bio_endio(orig_bio, size, 0);
+ bio_put(bio);
+ return 0;
+}
+
+/*
+ * This function sends processing request down to block layer (for local node)
+ * or to network state machine (for remote node).
+ */
+static int dst_node_push(struct dst_request *req)
+{
+ int err = 0;
+ struct dst_node *n = req->node;
+
+ if (n->bdev) {
+ struct bio *bio = req->bio;
+
+ dprintk("%s: start: %llu, num: %d, idx: %d, offset: %u, "
+ "size: %llu, bi_idx: %d, bi_vcnt: %d.\n",
+ __func__, req->start, req->num, req->idx,
+ req->offset, req->size, bio->bi_idx, bio->bi_vcnt);
+
+ if (likely(bio->bi_idx == req->idx &&
+ bio->bi_vcnt == req->num)) {
+ bio->bi_bdev = n->bdev;
+ bio->bi_sector = req->start;
+ } else {
+ struct bio *clone = bio_alloc_bioset(GFP_NOIO,
+ bio->bi_max_vecs, dst_bio_set);
+ struct bio_vec *bv;
+
+ err = -ENOMEM;
+ if (!clone)
+ goto out_put;
+
+ __bio_clone(clone, bio);
+
+ bv = bio_iovec_idx(clone, req->idx);
+ bv->bv_offset += req->offset;
+ clone->bi_idx = req->idx;
+ clone->bi_vcnt = req->num;
+ clone->bi_bdev = n->bdev;
+ clone->bi_sector = req->start;
+ clone->bi_destructor = dst_destructor;
+ clone->bi_private = bio;
+ clone->bi_size = req->orig_size;
+ clone->bi_end_io = &dst_end_io;
+ req->bio = clone;
+
+ dprintk("%s: start: %llu, num: %d, idx: %d, "
+ "offset: %u, size: %llu, "
+ "bi_idx: %d, bi_vcnt: %d, req: %p, bio: %p.\n",
+ __func__, req->start, req->num, req->idx,
+ req->offset, req->size,
+ clone->bi_idx, clone->bi_vcnt, req, req->bio);
+
+ }
+ }
+
+ err = n->st->alg->ops->remap(req);
+
+out_put:
+ dst_node_put(n);
+ return err;
+}
+
+/*
+ * This function is invoked from block layer request processing function,
+ * its task is to remap block request to different nodes.
+ */
+static int dst_remap(struct dst_storage *st, struct bio *bio)
+{
+ struct dst_node *n;
+ int err = -EINVAL, i, cnt;
+ unsigned int bio_sectors = bio->bi_size>>9;
+ struct bio_vec *bv;
+ struct dst_request req;
+ u64 rest_in_node, start, total_size;
+
+ mutex_lock(&st->tree_lock);
+ n = dst_storage_tree_search(st, bio->bi_sector);
+ mutex_unlock(&st->tree_lock);
+
+ if (!n) {
+ dprintk("%s: failed to find a node for bio: %p, "
+ "sector: %llu.\n",
+ __func__, bio, (u64)bio->bi_sector);
+ return -ENODEV;
+ }
+
+ dprintk("%s: bio: %llu-%llu, dev: %llu-%llu, in sectors.\n",
+ __func__, (u64)bio->bi_sector, (u64)bio->bi_sector+bio_sectors,
+ n->start, n->start+n->size);
+
+ memset(&req, 0, sizeof(struct dst_request));
+
+ start = bio->bi_sector;
+ total_size = bio->bi_size;
+
+ req.flags = (test_bit(DST_NODE_FROZEN, &n->flags))?
+ DST_REQ_ALWAYS_QUEUE:0;
+ req.start = start - n->start;
+ req.offset = 0;
+ req.state = n->state;
+ req.node = n;
+ req.bio = bio;
+
+ req.size = bio->bi_size;
+ req.orig_size = bio->bi_size;
+ req.idx = bio->bi_idx;
+ req.num = bio->bi_vcnt;
+
+ req.bio_endio = &kst_bio_endio;
+
+ /*
+ * Common fast path - block request does not cross
+ * boundaries between nodes.
+ */
+ if (likely(bio->bi_sector + bio_sectors <= n->start + n->size))
+ return dst_node_push(&req);
+
+ req.size = 0;
+ req.idx = 0;
+ req.num = 1;
+
+ cnt = bio->bi_vcnt;
+
+ rest_in_node = to_bytes(n->size - req.start);
+
+ for (i = 0; i < cnt; ++i) {
+ bv = bio_iovec_idx(bio, i);
+
+ if (req.size + bv->bv_len >= rest_in_node) {
+ unsigned int diff = req.size + bv->bv_len -
+ rest_in_node;
+
+ req.size += bv->bv_len - diff;
+ req.start = start - n->start;
+ req.orig_size = req.size;
+ req.bio = bio;
+ req.bio_endio = &kst_bio_endio;
+
+ dprintk("%s: split: start: %llu/%llu, size: %llu, "
+ "total_size: %llu, diff: %u, idx: %d, "
+ "num: %d, bv_len: %u, bv_offset: %u.\n",
+ __func__, start, req.start, req.size,
+ total_size, diff, req.idx, req.num,
+ bv->bv_len, bv->bv_offset);
+
+ err = dst_node_push(&req);
+ if (err)
+ break;
+
+ total_size -= req.orig_size;
+
+ if (!total_size)
+ break;
+
+ start += to_sector(req.orig_size);
+
+ req.flags = (test_bit(DST_NODE_FROZEN, &n->flags))?
+ DST_REQ_ALWAYS_QUEUE:0;
+ req.orig_size = req.size = diff;
+
+ if (diff) {
+ req.offset = bv->bv_len - diff;
+ req.idx = req.num - 1;
+ } else {
+ req.idx = req.num;
+ req.offset = 0;
+ }
+
+ dprintk("%s: next: start: %llu, size: %llu, "
+ "total_size: %llu, diff: %u, idx: %d, "
+ "num: %d, offset: %u, bv_len: %u, "
+ "bv_offset: %u.\n",
+ __func__, start, req.size, total_size, diff,
+ req.idx, req.num, req.offset,
+ bv->bv_len, bv->bv_offset);
+
+ mutex_lock(&st->tree_lock);
+ n = dst_storage_tree_search(st, start);
+ mutex_unlock(&st->tree_lock);
+
+ if (!n) {
+ err = -ENODEV;
+ dprintk("%s: failed to find a split node for "
+ "bio: %p, sector: %llu, start: %llu.\n",
+ __func__, bio, (u64)bio->bi_sector,
+ req.start);
+ break;
+ }
+
+ req.state = n->state;
+ req.node = n;
+ req.start = start - n->start;
+ rest_in_node = to_bytes(n->size - req.start);
+
+ dprintk("%s: req.start: %llu, start: %llu, "
+ "dev_start: %llu, dev_size: %llu, "
+ "rest_in_node: %llu.\n",
+ __func__, req.start, start, n->start,
+ n->size, rest_in_node);
+ } else {
+ req.size += bv->bv_len;
+ req.num++;
+ }
+ }
+
+ dprintk("%s: last request: start: %llu, size: %llu, "
+ "total_size: %llu.\n", __func__,
+ req.start, req.size, total_size);
+ if (total_size) {
+ req.orig_size = req.size;
+ req.bio = bio;
+ req.bio_endio = &kst_bio_endio;
+
+ dprintk("%s: last: start: %llu/%llu, size: %llu, "
+ "total_size: %llu, idx: %d, num: %d.\n",
+ __func__, start, req.start, req.size,
+ total_size, req.idx, req.num);
+
+ err = dst_node_push(&req);
+ if (!err) {
+ total_size -= req.orig_size;
+
+ BUG_ON(total_size != 0);
+ }
+ }
+
+ dprintk("%s: end bio: %p, err: %d.\n", __func__, bio, err);
+ return err;
+}
+
+/*
+ * Distributed storage erquest processing function.
+ * It calls algorithm spcific remapping code only.
+ */
+static int dst_request(request_queue_t *q, struct bio *bio)
+{
+ struct dst_storage *st = q->queuedata;
+ int err;
+
+ dprintk("\n%s: start: st: %p, bio: %p, cnt: %u.\n",
+ __func__, st, bio, bio->bi_vcnt);
+
+ err = dst_remap(st, bio);
+ if (err)
+ bio_endio(bio, bio->bi_size, err);
+
+ dprintk("%s: end: st: %p, bio: %p, err: %d.\n",
+ __func__, st, bio, err);
+ return 0;
+}
+
+static void dst_unplug(request_queue_t *q)
+{
+}
+
+static int dst_flush(request_queue_t *q, struct gendisk *disk, sector_t *sec)
+{
+ return 0;
+}
+
+static int dst_blk_open(struct inode *inode, struct file *file)
+{
+ struct dst_storage *st = inode->i_bdev->bd_disk->private_data;
+
+ dprintk("%s: storage: %p.\n", __func__, st);
+ atomic_inc(&st->refcnt);
+ return 0;
+}
+
+static int dst_blk_release(struct inode *inode, struct file *file)
+{
+ struct dst_storage *st = inode->i_bdev->bd_disk->private_data;
+
+ dprintk("%s: storage: %p.\n", __func__, st);
+ dst_put_storage(st);
+ return 0;
+}
+
+static struct block_device_operations dst_blk_ops = {
+ .open = &dst_blk_open,
+ .release = &dst_blk_release,
+ .owner = THIS_MODULE,
+};
+
+/*
+ * Block layer binding - disk is created when array is fully configured
+ * by userspace request.
+ */
+static int dst_create_disk(struct dst_storage *st)
+{
+ int err = -ENOMEM;
+
+ st->queue = blk_alloc_queue(GFP_KERNEL);
+ if (!st->queue)
+ goto err_out_exit;
+
+ st->queue->queuedata = st;
+ blk_queue_make_request(st->queue, dst_request);
+ blk_queue_bounce_limit(st->queue, BLK_BOUNCE_ANY);
+ st->queue->unplug_fn = dst_unplug;
+ st->queue->issue_flush_fn = dst_flush;
+
+ err = -EINVAL;
+ st->disk = alloc_disk(1);
+ if (!st->disk)
+ goto err_out_free_queue;
+
+ st->disk->major = dst_major;
+ st->disk->first_minor = (((unsigned long)st->disk) ^
+ (((unsigned long)st->disk) >> 31)) & 0xff;
+ st->disk->fops = &dst_blk_ops;
+ st->disk->queue = st->queue;
+ st->disk->private_data = st;
+ snprintf(st->disk->disk_name, sizeof(st->disk->disk_name),
+ "dst-%s-%d", st->name, st->disk->first_minor);
+
+ return 0;
+
+err_out_free_queue:
+ blk_cleanup_queue(st->queue);
+err_out_exit:
+ return err;
+}
+
+/*
+ * Shows node name in sysfs.
+ */
+static ssize_t dst_name_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_storage *st = container_of(dev, struct dst_storage, device);
+
+ return sprintf(buf, "%s\n", st->name);
+}
+
+static void dst_remove_all_nodes(struct dst_storage *st)
+{
+ struct dst_node *n, *node, *tmp;
+ struct rb_node *rb_node;
+
+ mutex_lock(&st->tree_lock);
+ while ((rb_node = rb_first(&st->tree_root)) != NULL) {
+ n = rb_entry(rb_node, struct dst_node, tree_node);
+ dprintk("%s: n: %p, start: %llu, size: %llu.\n",
+ __func__, n, n->start, n->size);
+ rb_erase(&n->tree_node, &st->tree_root);
+ if (!n->shared_head && atomic_read(&n->shared_num)) {
+ list_for_each_entry_safe(node, tmp, &n->shared, shared) {
+ list_del(&node->shared);
+ atomic_dec(&node->shared_head->refcnt);
+ node->shared_head = NULL;
+ dst_node_put(node);
+ }
+ }
+ dst_node_put(n);
+ }
+ mutex_unlock(&st->tree_lock);
+}
+
+/*
+ * Shows node layout in syfs.
+ */
+static ssize_t dst_nodes_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_storage *st = container_of(dev, struct dst_storage, device);
+ int size = PAGE_CACHE_SIZE, sz;
+ struct dst_node *n;
+ struct rb_node *rb_node;
+
+ sz = sprintf(buf, "sectors (start [size]): ");
+ size -= sz;
+ buf += sz;
+
+ mutex_lock(&st->tree_lock);
+ for (rb_node = rb_first(&st->tree_root); rb_node;
+ rb_node = rb_next(rb_node)) {
+ n = rb_entry(rb_node, struct dst_node, tree_node);
+ if (size < 32)
+ break;
+ sz = sprintf(buf, "%llu [%llu]", n->start, n->size);
+ buf += sz;
+ size -= sz;
+
+ if (!rb_next(rb_node))
+ break;
+
+ sz = sprintf(buf, " | ");
+ buf += sz;
+ size -= sz;
+ }
+ mutex_unlock(&st->tree_lock);
+ size -= sprintf(buf, "\n");
+ return PAGE_CACHE_SIZE - size;
+}
+
+/*
+ * Algorithm currently being used by given storage.
+ */
+static ssize_t dst_alg_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_storage *st = container_of(dev, struct dst_storage, device);
+ return sprintf(buf, "%s\n", st->alg->name);
+}
+
+/*
+ * Writing to this sysfs file allows to remove all nodes
+ * and storage itself automatically.
+ */
+static ssize_t dst_remove_nodes(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct dst_storage *st = container_of(dev, struct dst_storage, device);
+ dst_remove_all_nodes(st);
+ return count;
+}
+
+static DEVICE_ATTR(name, 0444, dst_name_show, NULL);
+static DEVICE_ATTR(nodes, 0444, dst_nodes_show, NULL);
+static DEVICE_ATTR(alg, 0444, dst_alg_show, NULL);
+static DEVICE_ATTR(remove_all_nodes, 0644, NULL, dst_remove_nodes);
+
+static int dst_create_storage_attributes(struct dst_storage *st)
+{
+ int err;
+
+ err = device_create_file(&st->device, &dev_attr_name);
+ err = device_create_file(&st->device, &dev_attr_nodes);
+ err = device_create_file(&st->device, &dev_attr_alg);
+ err = device_create_file(&st->device, &dev_attr_remove_all_nodes);
+ return 0;
+}
+
+static void dst_remove_storage_attributes(struct dst_storage *st)
+{
+ device_remove_file(&st->device, &dev_attr_name);
+ device_remove_file(&st->device, &dev_attr_nodes);
+ device_remove_file(&st->device, &dev_attr_alg);
+ device_remove_file(&st->device, &dev_attr_remove_all_nodes);
+}
+
+static void dst_storage_sysfs_exit(struct dst_storage *st)
+{
+ dst_remove_storage_attributes(st);
+ device_unregister(&st->device);
+}
+
+static int dst_storage_sysfs_init(struct dst_storage *st)
+{
+ int err;
+
+ memcpy(&st->device, &dst_dev, sizeof(struct device));
+ snprintf(st->device.bus_id, sizeof(st->device.bus_id), "%s", st->name);
+
+ err = device_register(&st->device);
+ if (err) {
+ dprintk(KERN_ERR "Failed to register dst device %s, err: %d.\n",
+ st->name, err);
+ goto err_out_exit;
+ }
+
+ dst_create_storage_attributes(st);
+
+ return 0;
+
+err_out_exit:
+ return err;
+}
+
+/*
+ * This functions shows size and start of the appropriate node.
+ * Both are in sectors.
+ */
+static ssize_t dst_show_start(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_node *n = container_of(dev, struct dst_node, device);
+
+ return sprintf(buf, "%llu\n", n->start);
+}
+
+static ssize_t dst_show_size(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_node *n = container_of(dev, struct dst_node, device);
+
+ return sprintf(buf, "%llu\n", n->size);
+}
+
+/*
+ * Shows type of the remote node - device major/minor number
+ * for local nodes and address (af_inet ipv4/ipv6 only) for remote nodes.
+ */
+static ssize_t dst_show_type(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct dst_node *n = container_of(dev, struct dst_node, device);
+ struct sockaddr addr;
+ struct socket *sock;
+ int addrlen;
+
+ if (!n->state && !n->bdev)
+ return 0;
+
+ if (n->bdev)
+ return sprintf(buf, "L: %d:%d\n",
+ MAJOR(n->bdev->bd_dev), MINOR(n->bdev->bd_dev));
+
+ sock = n->state->socket;
+ if (sock->ops->getname(sock, &addr, &addrlen, 2))
+ return 0;
+
+ if (sock->ops->family == AF_INET) {
+ struct sockaddr_in *sin = (struct sockaddr_in *)&addr;
+ return sprintf(buf, "R: %u.%u.%u.%u:%d\n",
+ NIPQUAD(sin->sin_addr.s_addr), ntohs(sin->sin_port));
+ } else if (sock->ops->family == AF_INET6) {
+ struct sockaddr_in6 *sin = (struct sockaddr_in6 *)&addr;
+ return sprintf(buf,
+ "R: %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x:%d\n",
+ NIP6(sin->sin6_addr), ntohs(sin->sin6_port));
+ }
+ return 0;
+}
+
+static DEVICE_ATTR(start, 0444, dst_show_start, NULL);
+static DEVICE_ATTR(size, 0444, dst_show_size, NULL);
+static DEVICE_ATTR(type, 0444, dst_show_type, NULL);
+
+static int dst_create_node_attributes(struct dst_node *n)
+{
+ int err;
+
+ err = device_create_file(&n->device, &dev_attr_start);
+ err = device_create_file(&n->device, &dev_attr_size);
+ err = device_create_file(&n->device, &dev_attr_type);
+ return 0;
+}
+
+static void dst_remove_node_attributes(struct dst_node *n)
+{
+ device_remove_file(&n->device, &dev_attr_start);
+ device_remove_file(&n->device, &dev_attr_size);
+ device_remove_file(&n->device, &dev_attr_type);
+}
+
+static void dst_node_sysfs_exit(struct dst_node *n)
+{
+ if (n->device.parent == &n->st->device) {
+ dst_remove_node_attributes(n);
+ device_unregister(&n->device);
+ n->device.parent = NULL;
+ }
+}
+
+static int dst_node_sysfs_init(struct dst_node *n)
+{
+ int err;
+
+ memcpy(&n->device, &dst_node_dev, sizeof(struct device));
+
+ n->device.parent = &n->st->device;
+
+ snprintf(n->device.bus_id, sizeof(n->device.bus_id),
+ "n-%llu-%p", n->start, n);
+ err = device_register(&n->device);
+ if (err) {
+ dprintk(KERN_ERR "Failed to register node, err: %d.\n", err);
+ goto err_out_exit;
+ }
+
+ dst_create_node_attributes(n);
+
+ return 0;
+
+err_out_exit:
+ n->device.parent = NULL;
+ return err;
+}
+
+/*
+ * Gets a reference for given storage, if
+ * storage with given name and algorithm being used
+ * does not exist it is created.
+ */
+static struct dst_storage *dst_get_storage(char *name, char *aname, int alloc)
+{
+ struct dst_storage *st, *rst = NULL;
+ int err;
+ struct dst_alg *alg;
+
+ mutex_lock(&dst_storage_lock);
+ list_for_each_entry(st, &dst_storage_list, entry) {
+ if (!strcmp(name, st->name) && !strcmp(st->alg->name, aname)) {
+ rst = st;
+ atomic_inc(&st->refcnt);
+ break;
+ }
+ }
+
+ if (rst || !alloc) {
+ mutex_unlock(&dst_storage_lock);
+ return rst;
+ }
+
+ st = kzalloc(sizeof(struct dst_storage), GFP_KERNEL);
+ if (!st) {
+ mutex_unlock(&dst_storage_lock);
+ return NULL;
+ }
+
+ mutex_init(&st->tree_lock);
+ /*
+ * One for storage itself,
+ * another one for attached node below.
+ */
+ atomic_set(&st->refcnt, 2);
+ snprintf(st->name, DST_NAMELEN, "%s", name);
+ st->tree_root.rb_node = NULL;
+
+ err = dst_storage_sysfs_init(st);
+ if (err)
+ goto err_out_free;
+
+ err = dst_create_disk(st);
+ if (err)
+ goto err_out_sysfs_exit;
+
+ mutex_lock(&dst_alg_lock);
+ list_for_each_entry(alg, &dst_alg_list, entry) {
+ if (!strcmp(alg->name, aname)) {
+ atomic_inc(&alg->refcnt);
+ try_module_get(alg->ops->owner);
+ st->alg = alg;
+ break;
+ }
+ }
+ mutex_unlock(&dst_alg_lock);
+
+ if (!st->alg)
+ goto err_out_disk_remove;
+
+ list_add_tail(&st->entry, &dst_storage_list);
+ mutex_unlock(&dst_storage_lock);
+
+ return st;
+
+err_out_disk_remove:
+ dst_remove_disk(st);
+err_out_sysfs_exit:
+ dst_storage_sysfs_exit(st);
+err_out_free:
+ mutex_unlock(&dst_storage_lock);
+ kfree(st);
+ return NULL;
+}
+
+/*
+ * Allows to allocate and add new algorithm by external modules.
+ */
+struct dst_alg *dst_alloc_alg(char *name, struct dst_alg_ops *ops)
+{
+ struct dst_alg *alg;
+
+ alg = kzalloc(sizeof(struct dst_alg), GFP_KERNEL);
+ if (!alg)
+ return NULL;
+ snprintf(alg->name, DST_NAMELEN, "%s", name);
+ atomic_set(&alg->refcnt, 1);
+ alg->ops = ops;
+
+ mutex_lock(&dst_alg_lock);
+ list_add_tail(&alg->entry, &dst_alg_list);
+ mutex_unlock(&dst_alg_lock);
+
+ return alg;
+}
+EXPORT_SYMBOL_GPL(dst_alloc_alg);
+
+/*
+ * Removing algorithm from main list of supported algorithms.
+ */
+void dst_remove_alg(struct dst_alg *alg)
+{
+ mutex_lock(&dst_alg_lock);
+ list_del_init(&alg->entry);
+ mutex_unlock(&dst_alg_lock);
+
+ dst_put_alg(alg);
+}
+EXPORT_SYMBOL_GPL(dst_remove_alg);
+
+static void dst_cleanup_node(struct dst_node *n)
+{
+ struct dst_storage *st = n->st;
+
+ dprintk("%s: node: %p.\n", __func__, n);
+
+ if (n->shared_head) {
+ mutex_lock(&st->tree_lock);
+ list_del(&n->shared);
+ mutex_unlock(&st->tree_lock);
+
+ atomic_dec(&n->shared_head->refcnt);
+ dst_node_put(n->shared_head);
+ n->shared_head = NULL;
+ }
+
+ if (n->cleanup)
+ n->cleanup(n);
+ dst_node_sysfs_exit(n);
+ n->st->alg->ops->del_node(n);
+ kfree(n);
+}
+
+/*
+ * This can deadlock if called under st->tree_lock being held,
+ * so take care to only call this when reference counter can not
+ * hit zero and thus start node freeing.
+ */
+void dst_node_put(struct dst_node *n)
+{
+ dprintk("%s: node: %p, start: %llu, size: %llu, refcnt: %d.\n",
+ __func__, n, n->start, n->size,
+ atomic_read(&n->refcnt));
+
+ if (atomic_dec_and_test(&n->refcnt)) {
+ struct dst_storage *st = n->st;
+
+ dprintk("%s: freeing node: %p, start: %llu, size: %llu, "
+ "refcnt: %d.\n",
+ __func__, n, n->start, n->size,
+ atomic_read(&n->refcnt));
+
+ dst_cleanup_node(n);
+ dst_put_storage(st);
+ }
+}
+EXPORT_SYMBOL_GPL(dst_node_put);
+
+static inline int dst_compare_id(struct dst_node *old, u64 new)
+{
+ if (old->start + old->size <= new)
+ return 1;
+ if (old->start > new)
+ return -1;
+ return 0;
+}
+
+/*
+ * Tree of of the nodes, which form the storage.
+ * Tree is indexed via start of the node and its size.
+ * Comparison function above.
+ */
+struct dst_node *dst_storage_tree_search(struct dst_storage *st, u64 start)
+{
+ struct rb_node *n = st->tree_root.rb_node;
+ struct dst_node *dn;
+ int cmp;
+
+ while (n) {
+ dn = rb_entry(n, struct dst_node, tree_node);
+
+ cmp = dst_compare_id(dn, start);
+ dprintk("%s: tree: %llu-%llu, new: %llu.\n",
+ __func__, dn->start, dn->start+dn->size, start);
+ if (cmp < 0)
+ n = n->rb_left;
+ else if (cmp > 0)
+ n = n->rb_right;
+ else {
+ return dst_node_get(dn);
+ }
+ }
+ return NULL;
+}
+EXPORT_SYMBOL_GPL(dst_storage_tree_search);
+
+/*
+ * This function allows to remove a node with given start address
+ * from the storage.
+ */
+static struct dst_node *dst_storage_tree_del(struct dst_storage *st, u64 start)
+{
+ struct dst_node *n = dst_storage_tree_search(st, start);
+
+ if (!n)
+ return NULL;
+
+ rb_erase(&n->tree_node, &st->tree_root);
+ dst_node_put(n);
+ return n;
+}
+
+/*
+ * This function allows to add given node to the storage.
+ * Returns -EEXIST if the same area is already covered by another node.
+ * This is return must be checked for redundancy algorithms.
+ */
+static struct dst_node *dst_storage_tree_add(struct dst_node *new,
+ struct dst_storage *st)
+{
+ struct rb_node **n = &st->tree_root.rb_node, *parent = NULL;
+ struct dst_node *dn;
+ int cmp;
+
+ while (*n) {
+ parent = *n;
+ dn = rb_entry(parent, struct dst_node, tree_node);
+
+ cmp = dst_compare_id(dn, new->start);
+ dprintk("%s: tree: %llu-%llu, new: %llu.\n",
+ __func__, dn->start, dn->start+dn->size,
+ new->start);
+ if (cmp < 0)
+ n = &parent->rb_left;
+ else if (cmp > 0)
+ n = &parent->rb_right;
+ else {
+ return dn;
+ }
+ }
+
+ rb_link_node(&new->tree_node, parent, n);
+ rb_insert_color(&new->tree_node, &st->tree_root);
+
+ return NULL;
+}
+
+/*
+ * This function finds devices major/minor numbers for given pathname.
+ */
+static int dst_lookup_device(const char *path, dev_t *dev)
+{
+ int err;
+ struct nameidata nd;
+ struct inode *inode;
+
+ err = path_lookup(path, LOOKUP_FOLLOW, &nd);
+ if (err)
+ return err;
+
+ inode = nd.dentry->d_inode;
+ if (!inode) {
+ err = -ENOENT;
+ goto out;
+ }
+
+ if (!S_ISBLK(inode->i_mode)) {
+ err = -ENOTBLK;
+ goto out;
+ }
+
+ *dev = inode->i_rdev;
+
+out:
+ path_release(&nd);
+ return err;
+}
+
+/*
+ * Cleanup routings for local, local exporting and remote nodes.
+ */
+static void dst_cleanup_remote(struct dst_node *n)
+{
+ if (n->state) {
+ kst_state_exit(n->state);
+ n->state = NULL;
+ }
+}
+
+static void dst_cleanup_local(struct dst_node *n)
+{
+ if (n->bdev) {
+ sync_blockdev(n->bdev);
+ blkdev_put(n->bdev);
+ n->bdev = NULL;
+ }
+}
+
+static void dst_cleanup_local_export(struct dst_node *n)
+{
+ dst_cleanup_local(n);
+ dst_cleanup_remote(n);
+}
+
+/*
+ * Header receiving function - may block.
+ */
+int dst_data_recv_header(struct socket *sock,
+ struct dst_remote_request *r, int block)
+{
+ struct msghdr msg;
+ struct kvec iov;
+
+ iov.iov_base = r;
+ iov.iov_len = sizeof(struct dst_remote_request);
+
+ msg.msg_iov = (struct iovec *)&iov;
+ msg.msg_iovlen = 1;
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = (block)?MSG_WAITALL:MSG_DONTWAIT | MSG_NOSIGNAL;
+
+ return kernel_recvmsg(sock, &msg, &iov, 1, iov.iov_len,
+ msg.msg_flags);
+}
+
+/*
+ * Header sending function - may block.
+ */
+int dst_data_send_header(struct socket *sock,
+ struct dst_remote_request *r)
+{
+ struct msghdr msg;
+ struct kvec iov;
+
+ iov.iov_base = r;
+ iov.iov_len = sizeof(struct dst_remote_request);
+
+ msg.msg_iov = (struct iovec *)&iov;
+ msg.msg_iovlen = 1;
+ msg.msg_name = NULL;
+ msg.msg_namelen = 0;
+ msg.msg_control = NULL;
+ msg.msg_controllen = 0;
+ msg.msg_flags = MSG_WAITALL | MSG_NOSIGNAL;
+
+ return kernel_sendmsg(sock, &msg, &iov, 1, iov.iov_len);
+}
+
+static inline void dst_node_set_size(struct dst_node *n, u64 size)
+{
+ if (n->size)
+ n->size = min(size, n->size);
+ else
+ n->size = size;
+}
+
+/*
+ * Setup routings for local, local exporting and remote nodes.
+ */
+static int dst_setup_local(struct dst_node *n, struct dst_ctl *ctl,
+ struct dst_local_ctl *l)
+{
+ dev_t dev;
+ int err;
+
+ err = dst_lookup_device(l->name, &dev);
+ if (err)
+ return err;
+
+ n->bdev = open_by_devnum(dev, FMODE_READ|FMODE_WRITE);
+ if (!n->bdev)
+ return -ENODEV;
+
+ dst_node_set_size(n, to_sector(n->bdev->bd_inode->i_size));
+
+ return 0;
+}
+
+static int dst_setup_local_export(struct dst_node *n, struct dst_ctl *ctl,
+ struct dst_le_template *tmp)
+{
+ int err;
+
+ err = dst_setup_local(n, ctl, &tmp->le->lctl);
+ if (err)
+ goto err_out_exit;
+
+ n->state = kst_listener_state_init(n, tmp);
+ if (IS_ERR(n->state)) {
+ err = PTR_ERR(n->state);
+ goto err_out_cleanup;
+ }
+
+ return 0;
+
+err_out_cleanup:
+ dst_cleanup_local(n);
+err_out_exit:
+ return err;
+}
+
+static int dst_request_remote_config(struct dst_node *n, struct socket *sock)
+{
+ struct dst_remote_request cfg;
+ int err = -EINVAL;
+
+ memset(&cfg, 0, sizeof(struct dst_remote_request));
+ cfg.cmd = cpu_to_be32(DST_REMOTE_CFG);
+
+ dprintk("%s: sending header.\n", __func__);
+ err = dst_data_send_header(sock, &cfg);
+ if (err != sizeof(struct dst_remote_request))
+ goto out;
+
+ dprintk("%s: receiving header.\n", __func__);
+ err = dst_data_recv_header(sock, &cfg, 1);
+ if (err != sizeof(struct dst_remote_request))
+ goto out;
+
+ err = -EINVAL;
+ dprintk("%s: checking result: cmd: %d, size reported: %llu, csum is supported: %u.\n",
+ __func__, be32_to_cpu(cfg.cmd), be64_to_cpu(cfg.sector), !!cfg.csum);
+ if (be32_to_cpu(cfg.cmd) != DST_REMOTE_CFG)
+ goto out;
+
+ err = 0;
+ dst_node_set_size(n, be64_to_cpu(cfg.sector));
+
+ if (cfg.csum)
+ __set_bit(DST_NODE_USE_CSUM, &n->flags);
+ else
+ __clear_bit(DST_NODE_USE_CSUM, &n->flags);
+
+out:
+ dprintk("%s: n: %p, err: %d.\n", __func__, n, err);
+ return err;
+}
+
+static int dst_setup_remote(struct dst_node *n, struct dst_ctl *ctl,
+ struct dst_remote_ctl *r)
+{
+ int err;
+ struct socket *sock;
+
+ err = sock_create(r->addr.sa_family, r->type, r->proto, &sock);
+ if (err < 0)
+ goto err_out_exit;
+
+ sock->sk->sk_sndtimeo = sock->sk->sk_rcvtimeo =
+ msecs_to_jiffies(DST_DEFAULT_TIMEO);
+
+ err = sock->ops->connect(sock, (struct sockaddr *)&r->addr,
+ r->addr.sa_data_len, 0);
+ if (err)
+ goto err_out_destroy;
+
+ err = dst_request_remote_config(n, sock);
+ if (err)
+ goto err_out_destroy;
+
+ n->state = kst_data_state_init(n, sock);
+ if (IS_ERR(n->state)) {
+ err = PTR_ERR(n->state);
+ goto err_out_destroy;
+ }
+
+ return 0;
+
+err_out_destroy:
+ sock_release(sock);
+err_out_exit:
+
+ dprintk("%s: n: %p, err: %d.\n", __func__, n, err);
+ return err;
+}
+
+/*
+ * This function inserts node into storage.
+ */
+static int dst_insert_node(struct dst_node *n)
+{
+ int err;
+ struct dst_storage *st = n->st;
+ struct dst_node *dn;
+
+ err = st->alg->ops->add_node(n);
+ if (err)
+ goto err_out_exit;
+
+ err = dst_node_sysfs_init(n);
+ if (err)
+ goto err_out_remove_node;
+
+ mutex_lock(&st->tree_lock);
+ dn = dst_storage_tree_add(n, st);
+ if (dn) {
+ err = -EINVAL;
+ dn->size = st->disk_size;
+ if (dn->start == n->start) {
+ err = 0;
+ n->shared_head = dst_node_get(dn);
+ atomic_inc(&dn->shared_num);
+ list_add_tail(&n->shared, &dn->shared);
+ }
+ }
+ mutex_unlock(&st->tree_lock);
+ if (err)
+ goto err_out_sysfs_exit;
+
+ if (n->priv_callback)
+ n->priv_callback(n);
+
+ return 0;
+
+err_out_sysfs_exit:
+ dst_node_sysfs_exit(n);
+err_out_remove_node:
+ st->alg->ops->del_node(n);
+err_out_exit:
+ return err;
+}
+
+static struct dst_node *dst_alloc_node(struct dst_ctl *ctl,
+ void (*cleanup)(struct dst_node *))
+{
+ struct dst_storage *st;
+ struct dst_node *n;
+
+ st = dst_get_storage(ctl->st, ctl->alg, 1);
+ if (!st)
+ goto err_out_exit;
+
+ n = kzalloc(sizeof(struct dst_node), GFP_KERNEL);
+ if (!n)
+ goto err_out_put_storage;
+
+ if (ctl->flags & DST_CTL_USE_CSUM)
+ __set_bit(DST_NODE_USE_CSUM, &n->flags);
+
+ n->w = kst_main_worker;
+ n->st = st;
+ n->cleanup = cleanup;
+ n->start = ctl->start;
+ n->size = ctl->size;
+ INIT_LIST_HEAD(&n->shared);
+ n->shared_head = NULL;
+ atomic_set(&n->shared_num, 0);
+ atomic_set(&n->refcnt, 1);
+
+ return n;
+
+err_out_put_storage:
+ mutex_lock(&dst_storage_lock);
+ list_del_init(&st->entry);
+ mutex_unlock(&dst_storage_lock);
+
+ dst_put_storage(st);
+err_out_exit:
+ return NULL;
+}
+
+/*
+ * Control callback for userspace commands to setup
+ * different nodes and start/stop array.
+ */
+static int dst_add_remote(struct dst_ctl *ctl, void *data, unsigned int len)
+{
+ struct dst_node *n;
+ int err;
+ struct dst_remote_ctl *rctl = data;
+
+ if (len != sizeof(struct dst_remote_ctl))
+ return -EINVAL;
+
+ n = dst_alloc_node(ctl, &dst_cleanup_remote);
+ if (!n)
+ return -ENOMEM;
+
+ err = dst_setup_remote(n, ctl, rctl);
+ if (err < 0)
+ goto err_out_free;
+
+ err = dst_insert_node(n);
+ if (err)
+ goto err_out_cleanup;
+
+ return 0;
+
+err_out_cleanup:
+ if (n->cleanup)
+ n->cleanup(n);
+err_out_free:
+ dst_put_storage(n->st);
+ kfree(n);
+ return err;
+}
+
+static int dst_add_local_export(struct dst_ctl *ctl, void *data, unsigned int len)
+{
+ struct dst_node *n;
+ int err;
+ struct dst_le_template tmp;
+
+ if (len < sizeof(struct dst_local_export_ctl))
+ return -EINVAL;
+
+ tmp.le = data;
+
+ len -= sizeof(struct dst_local_export_ctl);
+ data += sizeof(struct dst_local_export_ctl);
+
+ if (len != tmp.le->secure_attr_num * sizeof(struct dst_secure_user))
+ return -EINVAL;
+
+ tmp.data = data;
+
+ n = dst_alloc_node(ctl, &dst_cleanup_local_export);
+ if (!n)
+ return -EINVAL;
+
+ err = dst_setup_local_export(n, ctl, &tmp);
+ if (err < 0)
+ goto err_out_free;
+
+ err = dst_insert_node(n);
+ if (err)
+ goto err_out_cleanup;
+
+ return 0;
+
+err_out_cleanup:
+ if (n->cleanup)
+ n->cleanup(n);
+err_out_free:
+ dst_put_storage(n->st);
+ kfree(n);
+ return err;
+}
+
+static int dst_add_local(struct dst_ctl *ctl, void *data, unsigned int len)
+{
+ struct dst_node *n;
+ int err;
+ struct dst_local_ctl *lctl = data;
+
+ if (len != sizeof(struct dst_local_ctl))
+ return -EINVAL;
+
+ n = dst_alloc_node(ctl, &dst_cleanup_local);
+ if (!n)
+ return -EINVAL;
+
+ err = dst_setup_local(n, ctl, lctl);
+ if (err < 0)
+ goto err_out_free;
+
+ err = dst_insert_node(n);
+ if (err)
+ goto err_out_cleanup;
+
+ return 0;
+
+err_out_cleanup:
+ if (n->cleanup)
+ n->cleanup(n);
+err_out_free:
+ dst_put_storage(n->st);
+ kfree(n);
+ return err;
+}
+
+static int dst_del_node(struct dst_ctl *ctl, void *data, unsigned int len)
+{
+ struct dst_node *n;
+ struct dst_storage *st;
+ int err = -ENODEV;
+
+ if (len)
+ return -EINVAL;
+
+ st = dst_get_storage(ctl->st, ctl->alg, 0);
+ if (!st)
+ goto err_out_exit;
+
+ mutex_lock(&st->tree_lock);
+ n = dst_storage_tree_del(st, ctl->start);
+ mutex_unlock(&st->tree_lock);
+ if (!n)
+ goto err_out_put;
+
+ dst_node_put(n);
+ dst_put_storage(st);
+
+ return 0;
+
+err_out_put:
+ dst_put_storage(st);
+err_out_exit:
+ return err;
+}
+
+static int dst_start_storage(struct dst_ctl *ctl, void *data, unsigned int len)
+{
+ struct dst_storage *st;
+ int err = -ENXIO;
+
+ if (len)
+ return -EINVAL;
+
+ st = dst_get_storage(ctl->st, ctl->alg, 0);
+ if (!st)
+ return -ENODEV;
+
+ mutex_lock(&st->tree_lock);
+ if (!(st->flags & DST_ST_STARTED) && st->disk_size) {
+ set_capacity(st->disk, st->disk_size);
+ add_disk(st->disk);
+ st->flags |= DST_ST_STARTED;
+ dprintk("%s: STARTED name: '%s', st: %p, disk_size: %llu.\n",
+ __func__, st->name, st, st->disk_size);
+ err = 0;
+ }
+ mutex_unlock(&st->tree_lock);
+
+ dst_put_storage(st);
+
+ return err;
+}
+
+static int dst_stop_storage(struct dst_ctl *ctl, void *data, unsigned int len)
+{
+ struct dst_storage *st;
+
+ if (len)
+ return -EINVAL;
+
+ st = dst_get_storage(ctl->st, ctl->alg, 0);
+ if (!st)
+ return -ENODEV;
+
+ dprintk("%s: STOPPED storage: %s.\n", __func__, st->name);
+
+ dst_storage_sysfs_exit(st);
+
+ mutex_lock(&dst_storage_lock);
+ list_del_init(&st->entry);
+ mutex_unlock(&dst_storage_lock);
+
+ if (st->flags & DST_ST_STARTED)
+ del_gendisk(st->disk);
+
+ dst_remove_all_nodes(st);
+ dst_put_storage(st); /* One reference got above */
+ dst_put_storage(st); /* Another reference set during initialization */
+
+ return 0;
+}
+
+typedef int (*dst_command_func)(struct dst_ctl *ctl, void *data, unsigned int len);
+
+/*
+ * List of userspace commands.
+ */
+static dst_command_func dst_commands[] = {
+ [DST_ADD_REMOTE] = &dst_add_remote,
+ [DST_ADD_LOCAL] = &dst_add_local,
+ [DST_ADD_LOCAL_EXPORT] = &dst_add_local_export,
+ [DST_DEL_NODE] = &dst_del_node,
+ [DST_START_STORAGE] = &dst_start_storage,
+ [DST_STOP_STORAGE] = &dst_stop_storage,
+};
+
+/*
+ * Configuration parser.
+ */
+static void cn_dst_callback(void *data)
+{
+ struct dst_ctl *ctl;
+ struct cn_msg *msg = data;
+ int err;
+ struct dst_ctl_ack *ack;
+
+ if (msg->len < sizeof(struct dst_ctl)) {
+ err = -EBADMSG;
+ goto out;
+ }
+
+ ctl = (struct dst_ctl *)msg->data;
+
+ if (ctl->cmd >= DST_CMD_MAX) {
+ err = -EINVAL;
+ goto out;
+ }
+
+ err = dst_commands[ctl->cmd](ctl, msg->data + sizeof(struct dst_ctl),
+ msg->len - sizeof(struct dst_ctl));
+
+out:
+ ack = kmalloc(sizeof(struct dst_ctl_ack), GFP_KERNEL);
+ if (!ack)
+ return;
+
+ memcpy(&ack->msg, msg, sizeof(struct cn_msg));
+
+ ack->msg.ack = msg->ack + 1;
+ ack->msg.len = sizeof(struct dst_ctl_ack) - sizeof(struct cn_msg);
+
+ ack->error = err;
+
+ cn_netlink_send(&ack->msg, 0, GFP_KERNEL);
+ kfree(ack);
+}
+
+static int dst_sysfs_init(void)
+{
+ return bus_register(&dst_dev_bus_type);
+}
+
+static void dst_sysfs_exit(void)
+{
+ bus_unregister(&dst_dev_bus_type);
+}
+
+static int __init dst_sys_init(void)
+{
+ int err = -ENOMEM;
+
+ dst_request_cache = kmem_cache_create("dst", sizeof(struct dst_request),
+ 0, 0, NULL, NULL);
+ if (!dst_request_cache)
+ return -ENOMEM;
+
+ dst_bio_set = bioset_create(32, 32);
+ if (!dst_bio_set)
+ goto err_out_destroy;
+
+ err = register_blkdev(dst_major, DST_NAME);
+ if (err < 0)
+ goto err_out_destroy_bioset;
+ if (err)
+ dst_major = err;
+
+ err = dst_sysfs_init();
+ if (err)
+ goto err_out_unregister;
+
+ kst_main_worker = kst_worker_init(0);
+ if (IS_ERR(kst_main_worker)) {
+ err = PTR_ERR(kst_main_worker);
+ goto err_out_sysfs_exit;
+ }
+
+ err = cn_add_callback(&cn_dst_id, "DST", cn_dst_callback);
+ if (err)
+ goto err_out_worker_exit;
+
+ printk(KERN_INFO "Distributed storage, '%s' release.\n", dst_name);
+
+ return 0;
+
+err_out_worker_exit:
+ kst_worker_exit(kst_main_worker);
+err_out_sysfs_exit:
+ dst_sysfs_exit();
+err_out_unregister:
+ unregister_blkdev(dst_major, DST_NAME);
+err_out_destroy_bioset:
+ bioset_free(dst_bio_set);
+err_out_destroy:
+ kmem_cache_destroy(dst_request_cache);
+ return err;
+}
+
+static void __exit dst_sys_exit(void)
+{
+ cn_del_callback(&cn_dst_id);
+ dst_sysfs_exit();
+ unregister_blkdev(dst_major, DST_NAME);
+ kst_exit_all();
+ bioset_free(dst_bio_set);
+ kmem_cache_destroy(dst_request_cache);
+}
+
+module_init(dst_sys_init);
+module_exit(dst_sys_exit);
+
+MODULE_DESCRIPTION("Distributed storage");
+MODULE_AUTHOR("Evgeniy Polyakov <johnpol@2ka.mipt.ru>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 10eb56b..9e67d58 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -36,9 +36,11 @@
#define CN_VAL_CIFS 0x1
#define CN_W1_IDX 0x3 /* w1 communication */
#define CN_W1_VAL 0x1
+#define CN_DST_IDX 0x4 /* Distributed storage */
+#define CN_DST_VAL 0x1
-#define CN_NETLINK_USERS 4
+#define CN_NETLINK_USERS 5
/*
* Maximum connector's message size.
diff --git a/include/linux/dst.h b/include/linux/dst.h
new file mode 100644
index 0000000..1cf5a1d
--- /dev/null
+++ b/include/linux/dst.h
@@ -0,0 +1,385 @@
+/*
+ * 2007+ Copyright (c) Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+ * All rights reserved.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DST_H
+#define __DST_H
+
+#include <linux/types.h>
+#include <linux/connector.h>
+
+#define DST_NAMELEN 32
+#define DST_NAME "dst"
+#define DST_IOCTL 0xba
+
+enum {
+ DST_DEL_NODE = 0, /* Remove node with given id from storage */
+ DST_ADD_REMOTE, /* Add remote node with given id to the storage */
+ DST_ADD_LOCAL, /* Add local node with given id to the storage */
+ DST_ADD_LOCAL_EXPORT, /* Add local node with given id to the storage to be exported and used by remote peers */
+ DST_START_STORAGE, /* Array is ready and storage can be started, if there will be new nodes
+ * added to the storage, they will be checked against existing size and
+ * probably be dropped (for example in mirror format when new node has smaller
+ * size than array created) or inserted.
+ */
+ DST_STOP_STORAGE, /* Remove array and all nodes. */
+ DST_CMD_MAX
+};
+
+#define DST_CTL_FLAGS_REMOTE (1<<0)
+#define DST_CTL_FLAGS_EXPORT (1<<1)
+#define DST_CTL_USE_CSUM (1<<2)
+
+struct dst_ctl
+{
+ char st[DST_NAMELEN];
+ char alg[DST_NAMELEN];
+ __u32 flags, cmd;
+ __u64 start, size;
+};
+
+struct dst_ctl_ack
+{
+ struct cn_msg msg;
+ int error;
+ int unused[3];
+};
+
+struct dst_local_ctl
+{
+ char name[DST_NAMELEN];
+};
+
+#define SADDR_MAX_DATA 128
+
+struct saddr {
+ unsigned short sa_family; /* address family, AF_xxx */
+ char sa_data[SADDR_MAX_DATA]; /* 14 bytes of protocol address */
+ unsigned short sa_data_len; /* Number of bytes used in sa_data */
+};
+
+struct dst_remote_ctl
+{
+ __u16 type;
+ __u16 proto;
+ struct saddr addr;
+};
+
+#define DST_PERM_READ (1<<0)
+#define DST_PERM_WRITE (1<<1)
+
+/*
+ * Right now it is simple model, where each remote address
+ * is assigned to set of permissions it is allowed to perform.
+ * In real world block device does not know anything but
+ * reading and writing, so it should be more than enough.
+ */
+struct dst_secure_user
+{
+ unsigned int permissions;
+ unsigned short check_offset;
+ struct saddr addr;
+};
+
+struct dst_local_export_ctl
+{
+ __u32 backlog;
+ int secure_attr_num;
+ struct dst_local_ctl lctl;
+ struct dst_remote_ctl rctl;
+};
+
+enum {
+ DST_REMOTE_CFG = 1, /* Request remote configuration */
+ DST_WRITE, /* Writing */
+ DST_READ, /* Reading */
+ DST_NCMD_MAX,
+};
+
+struct dst_remote_request
+{
+ __u32 cmd;
+ __u32 csum;
+ __u32 size;
+ __u32 offset;
+ __u64 sector;
+};
+
+#ifdef __KERNEL__
+
+#include <linux/rbtree.h>
+#include <linux/net.h>
+#include <linux/blkdev.h>
+#include <linux/bio.h>
+#include <linux/mempool.h>
+#include <linux/device.h>
+#include <linux/crc32c.h>
+
+//#define CONFIG_DST_DEBUG
+
+#ifdef CONFIG_DST_DEBUG
+#define dprintk(f, a...) printk(KERN_NOTICE f, ##a)
+#else
+static inline void __attribute__ ((format (printf, 1, 2))) dprintk(const char * fmt, ...) {}
+#endif
+
+struct kst_worker
+{
+ struct list_head entry;
+
+ struct list_head state_list;
+ struct mutex state_mutex;
+
+ struct list_head ready_list;
+ spinlock_t ready_lock;
+
+ mempool_t *req_pool;
+
+ struct task_struct *thread;
+
+ wait_queue_head_t wait;
+
+ int id;
+};
+
+struct kst_state;
+struct dst_node;
+
+#define DST_REQ_HEADER_SENT (1<<0)
+#define DST_REQ_EXPORT (1<<1)
+#define DST_REQ_EXPORT_WRITE (1<<2)
+#define DST_REQ_EXPORT_READ (1<<3)
+#define DST_REQ_ALWAYS_QUEUE (1<<4)
+#define DST_REQ_CHEKSUM_RECV (1<<5)
+#define DST_REQ_CHECK_QUEUE (1<<6)
+
+struct dst_request
+{
+ struct list_head request_list_entry;
+ struct bio *bio;
+ struct kst_state *state;
+ struct dst_node *node;
+
+ u32 tmp_csum, tmp_offset;
+
+ u32 flags;
+
+ u32 offset;
+ int idx, num;
+
+ int (*callback)(struct dst_request *dst,
+ unsigned int revents);
+ void (*bio_endio)(struct dst_request *dst,
+ int err);
+
+ atomic_t refcnt;
+ void *priv;
+
+ u64 size, orig_size, start;
+};
+
+struct kst_state_ops
+{
+ int (*init)(struct kst_state *, void *);
+ int (*push)(struct dst_request *req);
+ int (*ready)(struct kst_state *);
+ int (*recovery)(struct kst_state *, int err);
+ void (*exit)(struct kst_state *);
+};
+
+struct kst_state
+{
+ struct list_head entry;
+ struct list_head ready_entry;
+
+ wait_queue_t wait;
+ wait_queue_head_t *whead;
+
+ struct dst_node *node;
+ struct socket *socket;
+
+ u32 permissions;
+
+ struct mutex request_lock;
+ struct list_head request_list;
+
+ struct kst_state_ops *ops;
+};
+
+#define DST_DEFAULT_TIMEO 2000
+
+struct dst_storage;
+
+struct dst_alg_ops
+{
+ int (*add_node)(struct dst_node *n);
+ void (*del_node)(struct dst_node *n);
+ int (*remap)(struct dst_request *req);
+ int (*error)(struct kst_state *state, int err);
+ struct module *owner;
+};
+
+struct dst_alg
+{
+ struct list_head entry;
+ char name[DST_NAMELEN];
+ atomic_t refcnt;
+ struct dst_alg_ops *ops;
+};
+
+#define DST_ST_STARTED (1<<0)
+
+struct dst_storage
+{
+ struct list_head entry;
+ char name[DST_NAMELEN];
+ struct dst_alg *alg;
+ atomic_t refcnt;
+ struct mutex tree_lock;
+ struct rb_root tree_root;
+
+ request_queue_t *queue;
+ struct gendisk *disk;
+
+ long flags;
+ u64 disk_size;
+
+ struct device device;
+};
+
+#define DST_NODE_FROZEN 0
+#define DST_NODE_NOTSYNC 1
+#define DST_NODE_USE_CSUM 2
+
+struct dst_node
+{
+ struct rb_node tree_node;
+
+ struct list_head shared;
+ struct dst_node *shared_head;
+
+ struct block_device *bdev;
+ struct dst_storage *st;
+ struct kst_state *state;
+ struct kst_worker *w;
+
+ atomic_t refcnt;
+ atomic_t shared_num;
+
+ void (*cleanup)(struct dst_node *);
+
+ long flags;
+
+ u64 start, size;
+
+ void (*priv_callback)(struct dst_node *);
+ void *priv;
+
+ struct device device;
+};
+
+struct dst_le_template
+{
+ struct dst_local_export_ctl *le;
+ void *data;
+};
+
+struct dst_secure
+{
+ struct list_head sec_entry;
+ struct dst_secure_user sec;
+};
+
+void kst_state_exit(struct kst_state *st);
+
+struct kst_worker *kst_worker_init(int id);
+void kst_worker_exit(struct kst_worker *w);
+
+struct kst_state *kst_listener_state_init(struct dst_node *node,
+ struct dst_le_template *tmp);
+struct kst_state *kst_data_state_init(struct dst_node *node,
+ struct socket *newsock);
+
+void kst_wake(struct kst_state *st);
+
+void kst_exit_all(void);
+
+struct dst_alg *dst_alloc_alg(char *name, struct dst_alg_ops *ops);
+void dst_remove_alg(struct dst_alg *alg);
+
+struct dst_node *dst_storage_tree_search(struct dst_storage *st, u64 start);
+
+void dst_node_put(struct dst_node *n);
+
+static inline struct dst_node *dst_node_get(struct dst_node *n)
+{
+ atomic_inc(&n->refcnt);
+ return n;
+}
+
+struct dst_request *dst_clone_request(struct dst_request *req, mempool_t *pool);
+void dst_free_request(struct dst_request *req);
+
+void kst_complete_req(struct dst_request *req, int err);
+void kst_bio_endio(struct dst_request *req, int err);
+void kst_del_req(struct dst_request *req);
+int kst_enqueue_req(struct kst_state *st, struct dst_request *req);
+
+int kst_data_callback(struct dst_request *req, unsigned int revents);
+
+extern struct kmem_cache *dst_request_cache;
+
+static inline sector_t to_sector(unsigned long long n)
+{
+ return (n >> 9);
+}
+
+static inline unsigned long to_bytes(sector_t n)
+{
+ return (n << 9);
+}
+
+/*
+ * Checks state's permissions.
+ * Returns -EPERM if check failed.
+ */
+static inline int kst_check_permissions(struct kst_state *st, struct bio *bio)
+{
+ if ((bio_rw(bio) == WRITE) && !(st->permissions & DST_PERM_WRITE))
+ return -EPERM;
+
+ return 0;
+}
+
+static inline __u32 dst_csum_data(unsigned char *d, unsigned int size)
+{
+ return crc32c_le(0, d, size);
+}
+
+static inline void kst_convert_header(struct dst_remote_request *r)
+{
+ r->cmd = be32_to_cpu(r->cmd);
+ r->sector = be64_to_cpu(r->sector);
+ r->offset = be32_to_cpu(r->offset);
+ r->size = be32_to_cpu(r->size);
+ r->csum = be32_to_cpu(r->csum);
+}
+
+extern int dst_data_send_header(struct socket *sock,
+ struct dst_remote_request *r);
+extern int dst_data_recv_header(struct socket *sock,
+ struct dst_remote_request *r, int block);
+
+#endif /* __KERNEL__ */
+#endif /* __DST_H */
^ permalink raw reply related
* [1/4] DST: Distributed storage documentation.
From: Evgeniy Polyakov @ 2007-12-10 11:47 UTC (permalink / raw)
To: lkml; +Cc: netdev, linux-fsdevel
In-Reply-To: <11972872493977@2ka.mipt.ru>
Distributed storage documentation.
Algorithms used in the system, userspace interfaces
(sysfs dirs and files), design and implementation details
are described here.
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
diff --git a/Documentation/dst/algorithms.txt b/Documentation/dst/algorithms.txt
new file mode 100644
index 0000000..1437a6a
--- /dev/null
+++ b/Documentation/dst/algorithms.txt
@@ -0,0 +1,115 @@
+Each storage by itself is just a set of contiguous logical blocks, with
+allowed number of operations. Nodes, each of which has own start and size,
+are placed into storage by appropriate algorithm, which remaps
+logical sector number into real node's sector. One can create
+own algorithms, since DST has pluggable interface for that.
+Currently mirrored and linear algorithms are supported.
+
+Let's briefly describe how they work.
+
+Linear algorithm.
+Simple approach of concatenating storages into single device with
+increased size is used in this algorithm. Essentially new device
+has size equal to sum of sizes of underlying nodes and nodes are
+placed one after another.
+
+ /----- Node 1 ---\ /------ Node 3 ----\
+start end start end
+ |==================|========================|==================|
+ | start end |
+ | \------- Node 2 ---------/ |
+ | |
+start end
+ \-------------------------- DST storage ----------------------/
+
+ /\
+ ||
+ ||
+
+ IO operations
+
+ Figure 1.
+ 3 nodes combined into single storage using linear algorithm.
+
+Mirror algorithm.
+In this algorithms nodes are placed under each other, so when
+operation comes to the first one, it can be mirrored to all
+underlying nodes. In case of reading, actual data is obtained from
+the nearest node - algoritm keeps track of previous operation
+and knows where it was stopped, so that subsequent seek to the
+start of the new request will take the shortest time.
+Writing is always mirrored to all underlying nodes.
+
+ IO operations
+ ||
+ ||
+ \/
+
+|---------------- DST storage -------------------|
+| prev position |
+|-------|------------ Node 1 --------------------|
+| prev pos |
+|-------------------- Node 2 -----|--------------|
+|prev pos |
+|---|---------------- Node 3 --------------------|
+
+ Figure 2.
+ 3 nodes combined into single storage using mirror algorithm.
+
+Each algorithm must implement number of callbacks,
+which must be registered during initialization time.
+
+struct dst_alg_ops
+{
+ int (*add_node)(struct dst_node *n);
+ void (*del_node)(struct dst_node *n);
+ int (*remap)(struct dst_request *req);
+ int (*error)(struct kst_state *state, int err);
+ struct module *owner;
+};
+
+@add_node.
+This callback is invoked when new node is being added into the storage,
+but before node is actually added into the storage, so that it could
+be accessed from it. When it is called, all appropriate initialization
+of the underlying device is already completed (system has been connected
+to remote node or got a reference to the local block device). At this
+stage algorithm can add node into private map.
+It must return zero on success or negative value otherwise.
+
+@del_node.
+This callback is invoked when node is being deleted from the storage,
+i.e. when its reference counter hits zero. It is called before
+any cleaning is performed.
+It must return zero on success or negative value otherwise.
+
+@remap.
+This callback is invoked each time new bio hits the storage.
+Request structure contains BIO itself, pointer to the node, which originally
+stores the whole region under given IO request, and various parameters
+used by storage core to process this block request.
+It must return zero on success or negative value otherwise. It is upto
+this method to call all cleaning if remapping failed, for example it must
+call kst_bio_endio() for given callback in case of error, which in turn
+will call bio_endio(). Note, that dst_request structure provided in this
+callback is allocated on stack, so if there is a need to use it outside
+of the given function, it must be cloned (it will happen automatically
+in state's push callback, but that copy will not be shared by any other
+user).
+
+@error.
+This callback is invoked for each error, which happend when processed
+requests for remote nodes or when talking to remote size
+of the local export node (state contains data related to data
+transfers over the network).
+If this function has fixed given error, it must return 0 or negative
+error value otherwise.
+
+@owner.
+This is module reference counter updated automatically by DST core.
+
+Algorithm must provide its name and above structure to the
+dst_alloc_alg() function, which will return a reference to the newly
+created algorithm.
+To remove it, one needs to call dst_remove_alg() with given algorithm
+pointer.
diff --git a/Documentation/dst/dst.txt b/Documentation/dst/dst.txt
new file mode 100644
index 0000000..a6ea126
--- /dev/null
+++ b/Documentation/dst/dst.txt
@@ -0,0 +1,69 @@
+Distributed storage. Design and implementation.
+http://tservice.net.ru/~s0mbre/old/?section=projects&item=dst
+
+ Evgeniy Polyakov
+
+This document is intended to briefly describe design and
+implementation details of the distributed storage project,
+aimed to create ability to group physically and/or logically
+distributed storages into single device.
+
+Main operational unit in the storage is node. Node can represent
+either remote storage, connected to local machine, or local
+device, or storage exported to the outside of the system.
+Here goes small explaination of basic therms.
+
+Local node.
+This node is just a logical link between block device (with given
+major and minor numbers) and structure in the DST hierarchy,
+which represents number of sectors on the area, corresponding to given
+block device. it can be a disk, a device mapper node or stacked
+block device on top of another underlying DST nodes.
+
+Local export node.
+Essentially the same as local node, but it allows to access
+to its data via network. Remote clients can connect to given local
+export node and read or write blocks according to its size.
+Blocks are then forwarded to underlying local node and processed
+there accordingly to the nature of the local node.
+
+Remote node.
+This type of nodes contain remotely accessible devices. One can think
+about remote nodes as remote disks, which can be connected to
+local system and combined into single storage. Remote nodes
+are presented as number of sectors accessed over the network
+by the local machine, where distributed storage is being formed.
+Remote node allows autoconfiguration - size of the storage and
+checksumming will be requested during node initialization (if remote
+node supports checksumming it will be turned on).
+
+
+Each node or set of them can be formed into single array, which
+in turn becomes a local node, which can be exported further by stacking
+a local export node on top of it.
+
+Each storage by itself is just a set of contiguous logical blocks, with
+allowed number of operations. Nodes, each of which has own start and size,
+are placed into storage by appropriate algorithm, which remaps
+logical sector number into real node's sector. One can create
+own algorithms, since DST has pluggable interface for that.
+Currently mirrored and linear algorithms are supported.
+One can find more details in Documentation/dst/algorithms.txt file.
+
+Main goal of the distributed storage is to combine remote nodes into
+single device, so each block IO request is being sent over the network
+(contrary requests for local nodes are handled by the gneric block
+layer features). Each network connection has number of variables which
+describe it (socket, list of requests, error handling and so on),
+which form kst_state structure. This network state is added into per-socket
+polling state machine, and can be processed by dedicated thread when
+becomes ready. This system forms asynchronous IO for given block
+requests. If block request can be processed without blocking, then
+no new structures are allocated and async part of the state is not used.
+
+When connection to the remote peer breaks, DST core tries to reconnect
+to failed node and no requests are marked as errorneous, instead
+they live in the queue until reconnectin is established.
+
+Userspace code, setup documentation and examples can be found on project's
+homepage above.
diff --git a/Documentation/dst/sysfs.txt b/Documentation/dst/sysfs.txt
new file mode 100644
index 0000000..79d79dc
--- /dev/null
+++ b/Documentation/dst/sysfs.txt
@@ -0,0 +1,30 @@
+This file describes sysfs files created for each storage.
+
+1. Per-storage files.
+Each storage has its own dir /sysfs/devices/$storage_name,
+which contains following files:
+
+alg - contains name of the algorithm used to created given storage
+name - name of the storage
+nodes - map of the storage (list of nodes and their sizes and starts)
+remove_all_nodes - writable file which allows to remove all nodes from given
+ storage
+n-$start-$cookie - per node directory, where
+ $start - start of the given node in sectors,
+ $cookie - unique node's id used by DST
+
+2. Per-node files.
+Node's files are located in /sysfs/devices/$storage_name/n-$start-$cookie
+directory, described above.
+
+chunks - private file for mirroring algorithm, contains map of update/dirty
+ sectors of the node, '-' means update, '+' is dirty and has to be
+ resynced sector
+clean - writable file, writing leads to marking node as clean (in sync)
+dirty - writable file, writing leads to marking node as dirty (not in sync)
+size - size of the given node in sectors
+start - start of the given node in the storage in sectors
+type - contains type of the node in the following format: $type: $dev
+ where $type is either 'L' or 'R' - local or remote acordingly,
+ and $dev is device name for local node (/dev/sda1 for example)
+ or address of the remote node (192.168.4.81:1025 for example)
^ permalink raw reply related
* [0/4] DST: Distributed storage.
From: Evgeniy Polyakov @ 2007-12-10 11:47 UTC (permalink / raw)
To: lkml; +Cc: netdev, linux-fsdevel
In-Reply-To: <11qqqasdzxczc036@2ka.mipt.ru>
Distributed storage.
I'm pleased to announce the 11'th release of the distributed
storage subsystem (DST). This is a maintenance release and includes
bug fixes and simple feature extensions only.
DST allows to form a storage on top of local and remote nodes
and combine them into linear or mirroring setup, which in
turn can be exported to remote nodes.
Short changelog:
* wakeup state when mirror detected error to seedup reconnect
* if connecting in csum mode to no-csum server, do not enable csums
* do not clean queue until all users are removed
* allow to increase size of the storage in linear add callback
(with this change it is possible to add nodes into linear array
in real time without stopping storage. Filesystem has to be prepared
for the case when underlying device has changed its size.
Real-time addon of mirror nodes is also supported)
* allow to delete gendisk only after device was started
* dst debug config option
* Name: Gamardjoba, genacvale! ('Hi friend' in georgian)
Great thanks to Matthew Hodgson <matthew@mxtelecom.com> for debugging!
Overall list of features of the DST can be found on project's homepage:
http://tservice.net.ru/~s0mbre/old/?section=projects&item=dst
Thank you.
Signed-off-by: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
^ permalink raw reply
* [PATCH 1/3] UCC based TDM driver for MPC83xx platforms.
From: Poonam_Aggrwal-b10812 @ 2007-12-10 11:40 UTC (permalink / raw)
To: rubini, linux-kernel, netdev, kumar.gala
Cc: michael.barkowski, kim.phillips, ashish.kalra, rich.cutler
From: Poonam Agarwal-b10812 <b10812@freescale.com>
The UCC TDM driver basically multiplexes and demultiplexes data from
different channels. It can interface with for example SLIC kind of devices
to receive TDM data demultiplex it and send to upper applications. At the
transmit end it receives data for different channels multiplexes it and
sends them on the TDM channel. It internally uses TSA( Time Slot Assigner)
which does multiplexing and demultiplexing, UCC to perform SDMA between
host buffers and the TSA, CMX to connect TSA to UCC.
This driver will run on MPC8323E-RDB platforms.
Signed-off-by: Poonam Aggrwal <b10812@freescale.com>
Signed-off-by: Ashish Kalra <ashish.kalra@freescale.com>
Signed-off-by: Kim Phillips <Kim.Phillips@freescale.com>
Signed-off-by: Michael Barkowski <michael.barkowski@freescale.com>
---
drivers/misc/Kconfig | 21 +
drivers/misc/Makefile | 1 +
drivers/misc/ucc_tdm.c | 1068 ++++++++++++++++++++++++++++++++++++++++++++++++
drivers/misc/ucc_tdm.h | 227 ++++++++++
4 files changed, 1317 insertions(+), 0 deletions(-)
create mode 100644 drivers/misc/ucc_tdm.c
create mode 100644 drivers/misc/ucc_tdm.h
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index b5e67c0..698a72c 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -219,6 +219,27 @@ config THINKPAD_ACPI_BAY
If you are not sure, say Y here.
+config UCC_TDM
+ bool "Freescale UCC TDM Driver"
+ depends on QUICC_ENGINE && UCC_FAST
+ default n
+ ---help---
+ The TDM driver is for UCC based TDM devices for example, TDM device on
+ MPC832x RDB. Select it to run PowerVoIP on MPC832x RDB board.
+ The TDM driver can interface with SLIC kind of devices to transmit
+ and receive TDM samples. The TDM driver receives Time Division
+ multiplexed samples(for different channels) from the SLIC device,
+ demutiplexes them and sends them to the upper layers. At the transmit
+ end the TDM drivers receives samples for different channels, it
+ multiplexes them and sends them to the SLIC device.
+
+config TDM_LINEAR_PCM
+ bool "Linear PCM mode"
+ depends on UCC_TDM
+ ---help---
+ This mode should be selected if the TDM driver interface with the
+ SLIC device is linear PCM(e.g. 16 bit samples). If not selected the
+ interface will be 8 bit u-law.
config ATMEL_SSC
tristate "Device driver for Atmel SSC peripheral"
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 87f2685..6f0c49d 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -17,3 +17,4 @@ obj-$(CONFIG_SONY_LAPTOP) += sony-laptop.o
obj-$(CONFIG_THINKPAD_ACPI) += thinkpad_acpi.o
obj-$(CONFIG_FUJITSU_LAPTOP) += fujitsu-laptop.o
obj-$(CONFIG_EEPROM_93CX6) += eeprom_93cx6.o
+obj-$(CONFIG_UCC_TDM) += ucc_tdm.o
diff --git a/drivers/misc/ucc_tdm.c b/drivers/misc/ucc_tdm.c
new file mode 100644
index 0000000..232d537
--- /dev/null
+++ b/drivers/misc/ucc_tdm.c
@@ -0,0 +1,1068 @@
+/*
+ * drivers/misc/ucc_tdm.c
+ *
+ * UCC Based Linux TDM Driver
+ * This driver is designed to support UCC based TDM for PowerPC processors.
+ * This driver can interface with SLIC device to run VOIP kind of
+ * applications.
+ *
+ * Author: Ashish Kalra & Poonam Aggrwal
+ *
+ * Copyright (c) 2007 Freescale Semiconductor, 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; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/autoconf.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/time.h>
+#include <linux/skbuff.h>
+#include <linux/proc_fs.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/string.h>
+#include <linux/irq.h>
+#include <linux/of_platform.h>
+#include <linux/io.h>
+#include <linux/wait.h>
+#include <linux/timer.h>
+
+#include <asm/immap_qe.h>
+#include <asm/qe.h>
+#include <asm/ucc.h>
+#include <asm/ucc_fast.h>
+#include <asm/ucc_slow.h>
+
+#include "ucc_tdm.h"
+#define DRV_DESC "Freescale QE UCC TDM Driver"
+#define DRV_NAME "ucc_tdm"
+
+/*
+ * define the following #define if snooping or hardware-based cache coherency
+ * is disabled on the UCC transparent controller.This flag enables
+ * software-based cache-coherency support by explicitly flushing data cache
+ * contents after setting up the TDM output buffer(s) and invalidating the
+ * data cache contents before the TDM input buffer(s) are read.
+ */
+#undef UCC_CACHE_SNOOPING_DISABLED
+
+#define MAX_NUM_TDM_DEVICES 8
+
+static struct tdm_ctrl *tdm_ctrl[MAX_NUM_TDM_DEVICES];
+
+static int num_tdm_devices;
+static int num_tdm_clients;
+
+#define PREV_PHASE(x) ((x == 0) ? MAX_PHASE : (x - 1))
+#define NEXT_PHASE(x) (((x + 1) > MAX_PHASE) ? 0 : (x + 1))
+
+static struct ucc_tdm_info utdm_primary_info = {
+ .uf_info = {
+ .tsa = 1,
+ .cdp = 1,
+ .cds = 1,
+ .ctsp = 1,
+ .ctss = 1,
+ .revd = 1,
+ .urfs = 0x128,
+ .utfs = 0x128,
+ .utfet = 0,
+ .utftt = 0x128,
+ .ufpt = 256,
+ .ttx_trx = UCC_FAST_GUMR_TRANSPARENT_TTX_TRX_TRANSPARENT,
+ .tenc = UCC_FAST_TX_ENCODING_NRZ,
+ .renc = UCC_FAST_RX_ENCODING_NRZ,
+ .tcrc = UCC_FAST_16_BIT_CRC,
+ .synl = UCC_FAST_SYNC_LEN_NOT_USED,
+ },
+ .ucc_busy = 0,
+};
+
+static struct ucc_tdm_info utdm_info[8];
+
+static void dump_siram(struct tdm_ctrl *tdm_c)
+{
+#if defined(DEBUG)
+ int i;
+ u16 phy_num_ts;
+
+ phy_num_ts = tdm_c->physical_num_ts;
+
+ pr_debug("SI TxRAM dump\n");
+ /* each slot entry in SI RAM is of 2 bytes */
+ for (i = 0; i < phy_num_ts * 2; i++)
+ pr_debug("%x ", in_8(&qe_immr->sir.tx[i]));
+ pr_debug("\nSI RxRAM dump\n");
+ for (i = 0; i < phy_num_ts * 2; i++)
+ pr_debug("%x ", in_8(&qe_immr->sir.rx[i]));
+ pr_debug("\n");
+#endif
+}
+
+static void dump_ucc(struct tdm_ctrl *tdm_c)
+{
+#if defined(DEBUG)
+ struct ucc_transparent_pram *ucc_pram;
+
+ ucc_pram = tdm_c->ucc_pram;
+
+ pr_debug("%s Dumping UCC Registers\n", __FUNCTION__);
+ ucc_fast_dump_regs(tdm_c->uf_private);
+ pr_debug("%s Dumping UCC Parameter RAM\n", __FUNCTION__);
+ pr_debug("rbase = 0x%x\n", in_be32(&ucc_pram->rbase));
+ pr_debug("rbptr = 0x%x\n", in_be32(&ucc_pram->rbptr));
+ pr_debug("mrblr = 0x%x\n", in_be16(&ucc_pram->mrblr));
+ pr_debug("rbdlen = 0x%x\n", in_be16(&ucc_pram->rbdlen));
+ pr_debug("rbdstat = 0x%x\n", in_be16(&ucc_pram->rbdstat));
+ pr_debug("rstate = 0x%x\n", in_be32(&ucc_pram->rstate));
+ pr_debug("rdptr = 0x%x\n", in_be32(&ucc_pram->rdptr));
+ pr_debug("tbase = 0x%x\n", in_be32(&ucc_pram->tbase));
+ pr_debug("tbptr = 0x%x\n", in_be32(&ucc_pram->tbptr));
+ pr_debug("tbdlen = 0x%x\n", in_be16(&ucc_pram->tbdlen));
+ pr_debug("tbdstat = 0x%x\n", in_be16(&ucc_pram->tbdstat));
+ pr_debug("tstate = 0x%x\n", in_be32(&ucc_pram->tstate));
+ pr_debug("tdptr = 0x%x\n", in_be32(&ucc_pram->tdptr));
+#endif
+}
+/*
+ * converts u-law compressed samples to linear PCM
+ * If the CONFIG_TDM_LINEAR_PCM flag is not set the
+ * TDM driver receives u-law compressed data from the
+ * SLIC device. This function converts the compressed
+ * data to linear PCM and sends it to upper layers.
+ */
+static inline int ulaw2int(unsigned char log)
+{
+ u32 sign, segment, temp, quant;
+ int val;
+
+ temp = log ^ 0xFF;
+ sign = (temp & 0x80) >> 7;
+ segment = (temp & 0x70) >> 4;
+ quant = temp & 0x0F;
+ quant <<= 1;
+ quant += 33;
+ quant <<= segment;
+ if (sign)
+ val = 33 - quant;
+ else
+ val = quant - 33;
+
+ val *= 4;
+ return val;
+}
+
+/*
+ * converts linear PCM samples to u-law compressed format.
+ * If the CONFIG_TDM_LINEAR_PCM flag is not set the
+ * TDM driver calls this function to convert the PCM samples
+ * to u-law compressed format before sending them to SLIC
+ * device.
+ */
+static inline u8 int2ulaw(short linear)
+{
+ u8 quant, ret;
+ u16 output, absol, temp;
+ u32 i, sign;
+ char segment;
+
+ ret = 0;
+ if (linear >= 0)
+ linear = (linear >> 2);
+ else
+ linear = (0xc000 | (linear >> 2));
+
+ absol = abs(linear) + 33;
+ temp = absol;
+ sign = (linear >= 0) ? 1 : 0;
+ for (i = 0; i < 16; i++) {
+ output = temp & 0x8000;
+ if (output)
+ break;
+ temp <<= 1;
+ }
+ segment = 11 - i;
+ quant = (absol >> segment) & 0x0F;
+ segment--;
+ segment <<= 4;
+ output = segment + quant;
+ if (absol > 8191)
+ output = 0x7F;
+ if (sign)
+ ret ^= 0xFF;
+ else
+ ret ^= 0x7F;
+ return ret;
+}
+
+/*
+ * For use when a framing bit is not present
+ * Program current-route SI ram
+ * Set SIxRAM TDMx
+ * Entries must be in units of 8.
+ * SIR_UCC -> Channel Select
+ * SIR_CNT -> Number of bits or bytes
+ * SIR_BYTE -> Byte or Bit resolution
+ * SIR_LAST -> Indicates last entry in SIxRAM
+ * SIR_IDLE -> The Tx data pin is Tri-stated and the Rx data pin is
+ * ignored
+ */
+static void set_siram(struct tdm_ctrl *tdm_c, enum comm_dir dir)
+{
+ const u16 *mask;
+ u16 temp_mask = 1;
+ u16 siram_code = 0;
+ u32 i, j, k;
+ u32 ucc;
+ u32 phy_num_ts;
+
+ phy_num_ts = tdm_c->physical_num_ts;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+
+ if (dir == COMM_DIR_RX)
+ mask = tdm_c->rx_mask;
+ else
+ mask = tdm_c->tx_mask;
+ k = 0;
+ j = 0;
+ for (i = 0; i < phy_num_ts; i++) {
+ if ((mask[k] & temp_mask) == temp_mask)
+ siram_code = SIR_UCC(ucc) | SIR_CNT(0) | SIR_BYTE;
+ else
+ siram_code = SIR_IDLE | SIR_CNT(0) | SIR_BYTE;
+ if (dir == COMM_DIR_RX)
+ SET_RX_SI_RAM(i, siram_code);
+ else
+ SET_TX_SI_RAM(i, siram_code);
+ temp_mask = temp_mask << 1;
+ j++;
+ if (j >= 16) {
+ j = 0;
+ temp_mask = 0x0001;
+ k++;
+ }
+ }
+ siram_code = siram_code | SIR_LAST;
+
+ if (dir == COMM_DIR_RX)
+ SET_RX_SI_RAM(phy_num_ts - 1, siram_code);
+ else
+ SET_TX_SI_RAM(phy_num_ts - 1, siram_code);
+}
+
+static void config_si(struct tdm_ctrl *tdm_c)
+{
+ u8 rxsyncdelay, txsyncdelay, tdm_port;
+ u16 sixmr_val = 0;
+ u32 tdma_mode_off;
+ u16 *si1_tdm_mode_reg;
+
+ tdm_port = tdm_c->tdm_port;
+
+ set_siram(tdm_c, COMM_DIR_RX);
+
+ set_siram(tdm_c, COMM_DIR_TX);
+
+ rxsyncdelay = tdm_c->cfg_ctrl.rx_fr_sync_delay;
+ txsyncdelay = tdm_c->cfg_ctrl.tx_fr_sync_delay;
+ if (tdm_c->cfg_ctrl.com_pin)
+ sixmr_val |= SIMODE_CRT;
+ if (tdm_c->cfg_ctrl.fr_sync_level == 1)
+ sixmr_val |= SIMODE_SL;
+ if (tdm_c->cfg_ctrl.clk_edge == 1)
+ sixmr_val |= SIMODE_CE;
+ if (tdm_c->cfg_ctrl.fr_sync_edge == 1)
+ sixmr_val |= SIMODE_FE;
+ sixmr_val |= (SIMODE_TFSD(txsyncdelay) | SIMODE_RFSD(rxsyncdelay));
+
+ tdma_mode_off = SI_TDM_MODE_REGISTER_OFFSET * tdm_c->tdm_port;
+
+ si1_tdm_mode_reg = (u8 *)&qe_immr->si1 + tdma_mode_off;
+ out_be16(si1_tdm_mode_reg, sixmr_val);
+
+ dump_siram(tdm_c);
+}
+
+static int tdm_init(struct tdm_ctrl *tdm_c)
+{
+ u32 tdm_port, ucc, act_num_ts;
+ int ret, i, err;
+ u32 cecr_subblock;
+ u32 pram_offset;
+ u32 rxbdt_offset;
+ u32 txbdt_offset;
+ u32 rx_ucode_buf_offset, tx_ucode_buf_offset;
+ u16 bd_status, bd_len;
+ enum qe_clock clock;
+ struct qe_bd __iomem *rx_bd, *tx_bd;
+
+ tdm_port = tdm_c->tdm_port;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+ act_num_ts = tdm_c->cfg_ctrl.active_num_ts;
+
+ /*
+ * TDM Tx and Rx CLKs = 2048 KHz.
+ */
+ if (strstr(tdm_c->ut_info->uf_info.tdm_tx_clk, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_tx_clk);
+ err = qe_setbrg(clock, 2048000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_tx_clk);
+ return err;
+ }
+ }
+ if (strstr(tdm_c->ut_info->uf_info.tdm_rx_clk, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_rx_clk);
+ err = qe_setbrg(clock, 2048000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_rx_clk);
+ return err;
+ }
+ }
+ /*
+ * TDM FSyncs = 4 KHz.
+ */
+ if (strstr(tdm_c->ut_info->uf_info.tdm_tx_sync, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_tx_sync);
+ err = qe_setbrg(clock, 4000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_tx_sync);
+ return err;
+ }
+ }
+ if (strstr(tdm_c->ut_info->uf_info.tdm_rx_sync, "BRG")) {
+ clock = qe_clock_source(tdm_c->ut_info->uf_info.tdm_rx_sync);
+ err = qe_setbrg(clock, 4000, 1);
+ if (err < 0) {
+ printk(KERN_ERR "%s: Failed to set %s\n", __FUNCTION__,
+ tdm_c->ut_info->uf_info.tdm_rx_sync);
+ return err;
+ }
+ }
+
+ tdm_c->ut_info->uf_info.uccm_mask = (u32)
+ ((UCC_TRANS_UCCE_RXB | UCC_TRANS_UCCE_BSY) << 16);
+
+ if (ucc_fast_init(&(tdm_c->ut_info->uf_info), &tdm_c->uf_private)) {
+ printk(KERN_ERR "%s: Failed to init uccf\n", __FUNCTION__);
+ return -ENOMEM;
+ }
+
+ ucc_fast_disable(tdm_c->uf_private, COMM_DIR_RX | COMM_DIR_TX);
+
+ /* Write to QE CECR, UCCx channel to Stop Transmission */
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_STOP_TX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+ pram_offset = qe_muram_alloc(UCC_TRANSPARENT_PRAM_SIZE,
+ ALIGNMENT_OF_UCC_SLOW_PRAM);
+ if (IS_ERR_VALUE(pram_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM memory for"
+ " transparent UCC\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto pram_alloc_error;
+ }
+
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_ASSIGN_PAGE_TO_DEVICE, cecr_subblock,
+ QE_CR_PROTOCOL_UNSPECIFIED, pram_offset);
+
+ tdm_c->ucc_pram = qe_muram_addr(pram_offset);
+ tdm_c->ucc_pram_offset = pram_offset;
+
+ /*
+ * zero-out pram, this will also ensure RSTATE, TSTATE are cleared, also
+ * DISFC & CRCEC counters will be initialized.
+ */
+ memset(tdm_c->ucc_pram, 0, sizeof(struct ucc_transparent_pram));
+
+ /* rbase, tbase alignment is 8. */
+ rxbdt_offset = qe_muram_alloc(NR_BUFS * sizeof(struct qe_bd),
+ QE_ALIGNMENT_OF_BD);
+ if (IS_ERR_VALUE(rxbdt_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM memory for RxBDs\n",
+ __FUNCTION__);
+ ret = -ENOMEM;
+ goto rxbd_alloc_error;
+ }
+ txbdt_offset = qe_muram_alloc(NR_BUFS * sizeof(struct qe_bd),
+ QE_ALIGNMENT_OF_BD);
+ if (IS_ERR_VALUE(txbdt_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM memory for TxBDs\n",
+ __FUNCTION__);
+ ret = -ENOMEM;
+ goto txbd_alloc_error;
+ }
+ tdm_c->tx_bd = qe_muram_addr(txbdt_offset);
+ tdm_c->rx_bd = qe_muram_addr(rxbdt_offset);
+
+ tdm_c->tx_bd_offset = txbdt_offset;
+ tdm_c->rx_bd_offset = rxbdt_offset;
+
+ rx_bd = tdm_c->rx_bd;
+ tx_bd = tdm_c->tx_bd;
+
+ out_be32(&tdm_c->ucc_pram->rbase, (u32) immrbar_virt_to_phys(rx_bd));
+ out_be32(&tdm_c->ucc_pram->tbase, (u32) immrbar_virt_to_phys(tx_bd));
+
+ for (i = 0; i < NR_BUFS - 1; i++) {
+ bd_status = (u16) ((R_E | R_CM | R_I) >> 16);
+ bd_len = 0;
+ out_be16(&rx_bd->length, bd_len);
+ out_be16(&rx_bd->status, bd_status);
+ out_be32(&rx_bd->buf,
+ tdm_c->dma_input_addr + i * SAMPLE_DEPTH * act_num_ts);
+ rx_bd += 1;
+
+ bd_status = (u16) ((T_R | T_CM) >> 16);
+ bd_len = SAMPLE_DEPTH * act_num_ts;
+ out_be16(&tx_bd->length, bd_len);
+ out_be16(&tx_bd->status, bd_status);
+ out_be32(&tx_bd->buf,
+ tdm_c->dma_output_addr + i * SAMPLE_DEPTH * act_num_ts);
+ tx_bd += 1;
+ }
+
+ bd_status = (u16) ((R_E | R_CM | R_I | R_W) >> 16);
+ bd_len = 0;
+ out_be16(&rx_bd->length, bd_len);
+ out_be16(&rx_bd->status, bd_status);
+ out_be32(&rx_bd->buf,
+ tdm_c->dma_input_addr + i * SAMPLE_DEPTH * act_num_ts);
+
+ bd_status = (u16) ((T_R | T_CM | T_W) >> 16);
+ bd_len = SAMPLE_DEPTH * act_num_ts;
+ out_be16(&tx_bd->length, bd_len);
+ out_be16(&tx_bd->status, bd_status);
+ out_be32(&tx_bd->buf,
+ tdm_c->dma_output_addr + i * SAMPLE_DEPTH * act_num_ts);
+
+ config_si(tdm_c);
+
+ setbits32(&qe_immr->ic.qimr, (0x80000000 >> ucc));
+
+ rx_ucode_buf_offset = qe_muram_alloc(32, 32);
+ if (IS_ERR_VALUE(rx_ucode_buf_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM mem for Rx"
+ " ucode buf\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto rxucode_buf_alloc_error;
+ }
+
+ tx_ucode_buf_offset = qe_muram_alloc(32, 32);
+ if (IS_ERR_VALUE(tx_ucode_buf_offset)) {
+ printk(KERN_ERR "%s: Cannot allocate MURAM mem for Tx"
+ " ucode buf\n", __FUNCTION__);
+ ret = -ENOMEM;
+ goto txucode_buf_alloc_error;
+ }
+ out_be16(&tdm_c->ucc_pram->riptr, (u16) rx_ucode_buf_offset);
+ out_be16(&tdm_c->ucc_pram->tiptr, (u16) tx_ucode_buf_offset);
+
+ tdm_c->rx_ucode_buf_offset = rx_ucode_buf_offset;
+ tdm_c->tx_ucode_buf_offset = tx_ucode_buf_offset;
+
+ /*
+ * set the receive buffer descriptor maximum size to be
+ * SAMPLE_DEPTH * number of active RX channels
+ */
+ out_be16(&tdm_c->ucc_pram->mrblr, (u16) SAMPLE_DEPTH * act_num_ts);
+
+ /*
+ * enable snooping and BE byte ordering on the UCC pram's
+ * tstate & rstate registers.
+ */
+ out_be32(&tdm_c->ucc_pram->tstate, 0x30000000);
+ out_be32(&tdm_c->ucc_pram->rstate, 0x30000000);
+
+ /*Put UCC transparent controller into serial interface mode. */
+ out_be32(&tdm_c->uf_regs->upsmr, 0);
+
+ /* Reset TX and RX for UCCx */
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_INIT_TX_RX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+ return 0;
+
+txucode_buf_alloc_error:
+ qe_muram_free(rx_ucode_buf_offset);
+rxucode_buf_alloc_error:
+ qe_muram_free(txbdt_offset);
+txbd_alloc_error:
+ qe_muram_free(rxbdt_offset);
+rxbd_alloc_error:
+ qe_muram_free(pram_offset);
+pram_alloc_error:
+ ucc_fast_free(tdm_c->uf_private);
+ return ret;
+}
+
+static void tdm_deinit(struct tdm_ctrl *tdm_c)
+{
+ qe_muram_free(tdm_c->rx_ucode_buf_offset);
+ qe_muram_free(tdm_c->tx_ucode_buf_offset);
+
+ if (tdm_c->rx_bd_offset) {
+ qe_muram_free(tdm_c->rx_bd_offset);
+ tdm_c->rx_bd = NULL;
+ tdm_c->rx_bd_offset = 0;
+ }
+ if (tdm_c->tx_bd_offset) {
+ qe_muram_free(tdm_c->tx_bd_offset);
+ tdm_c->tx_bd = NULL;
+ tdm_c->tx_bd_offset = 0;
+ }
+ if (tdm_c->ucc_pram_offset) {
+ qe_muram_free(tdm_c->ucc_pram_offset);
+ tdm_c->ucc_pram = NULL;
+ tdm_c->ucc_pram_offset = 0;
+ }
+}
+
+
+static irqreturn_t tdm_isr(int irq, void *dev_id)
+{
+ u8 *input_tdm_buffer, *output_tdm_buffer;
+ u32 txb, rxb;
+ u32 ucc;
+ register u32 ucce = 0;
+ struct tdm_ctrl *tdm_c;
+ tdm_c = (struct tdm_ctrl *)dev_id;
+
+ tdm_c->tdm_icnt++;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+ input_tdm_buffer = tdm_c->tdm_input_data;
+ output_tdm_buffer = tdm_c->tdm_output_data;
+
+ if (in_be32(tdm_c->uf_private->p_ucce) &
+ (UCC_TRANS_UCCE_BSY << 16)) {
+ out_be32(tdm_c->uf_private->p_ucce,
+ (UCC_TRANS_UCCE_BSY << 16));
+ pr_info("%s: From tdm isr busy interrupt\n",
+ __FUNCTION__);
+ dump_ucc(tdm_c);
+
+ return IRQ_HANDLED;
+ }
+
+ if (tdm_c->tdm_flag == 1) {
+ /* track phases for Rx/Tx */
+ tdm_c->phase_rx = NEXT_PHASE(tdm_c->phase_rx);
+ tdm_c->phase_tx = NEXT_PHASE(tdm_c->phase_tx);
+#if defined(CONFIG_TDM_HW_LB_TSA_SLIC)
+ {
+ u32 temp_rx, temp_tx, phase_tx, phase_rx;
+ int i;
+ phase_rx = tdm_c->phase_rx;
+ phase_tx = tdm_c->phase_tx;
+ phase_rx = PREV_PHASE(phase_rx);
+ phase_tx = PREV_PHASE(phase_tx);
+ temp_rx = phase_rx * SAMPLE_DEPTH * ACTIVE_CH;
+ temp_tx = phase_tx * SAMPLE_DEPTH * ACTIVE_CH;
+
+ /*check if loopback received data on TS0 is correct. */
+ pr_debug("%s: check if loopback received data on TS0"
+ " is correct\n", __FUNCTION__);
+ pr_debug("%d,%d ", phase_rx, phase_tx);
+ for (i = 0; i < 8; i++)
+ pr_debug("%1d,%1d ",
+ input_tdm_buffer[temp_rx + i],
+ output_tdm_buffer[temp_tx + i]);
+ pr_debug("\n");
+ }
+#endif
+
+ /* schedule BH */
+ wake_up_interruptible(&tdm_c->wakeup_event);
+ } else {
+ if (tdm_c->tdm_icnt == STUTTER_INT_CNT) {
+ txb = in_be32(&tdm_c->ucc_pram->tbptr) -
+ in_be32(&tdm_c->ucc_pram->tbase);
+ rxb = in_be32(&tdm_c->ucc_pram->rbptr) -
+ in_be32(&tdm_c->ucc_pram->rbase);
+ tdm_c->phase_tx = txb / sizeof(struct qe_bd);
+ tdm_c->phase_rx = rxb / sizeof(struct qe_bd);
+
+#if defined(CONFIG_TDM_HW_LB_TSA_SLIC)
+ tdm_c->phase_tx = tdm_c->phase_rx;
+#endif
+
+ /* signal "stuttering" period is over */
+ tdm_c->tdm_flag = 1;
+
+ pr_debug("%s: stuttering period is over\n",
+ __FUNCTION__);
+
+ if (in_be32(tdm_c->uf_private->p_ucce) &
+ (UCC_TRANS_UCCE_TXE << 16)) {
+ u32 cecr_subblock;
+ out_be32(tdm_c->uf_private->p_ucce,
+ (UCC_TRANS_UCCE_TXE << 16));
+ pr_debug("%s: From tdm isr txe interrupt\n",
+ __FUNCTION__);
+
+ cecr_subblock =
+ ucc_fast_get_qe_cr_subblock(ucc);
+ qe_issue_cmd(QE_RESTART_TX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED,
+ 0);
+ }
+ }
+ }
+
+ ucce = (in_be32(tdm_c->uf_private->p_ucce)
+ & in_be32(tdm_c->uf_private->p_uccm));
+
+ out_be32(tdm_c->uf_private->p_ucce, ucce);
+
+ return IRQ_HANDLED;
+}
+
+static int tdm_start(struct tdm_ctrl *tdm_c)
+{
+ if (request_irq(tdm_c->ut_info->uf_info.irq, tdm_isr,
+ 0, "tdm", tdm_c)) {
+ printk(KERN_ERR "%s: request_irq for tdm_isr failed\n",
+ __FUNCTION__);
+ return -ENODEV;
+ }
+
+ ucc_fast_enable(tdm_c->uf_private, COMM_DIR_RX | COMM_DIR_TX);
+
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ pr_info("%s 8-bit u-law compressed mode active\n", __FUNCTION__);
+#else
+ pr_info("%s 16-bit linear pcm mode active with"
+ " slots 0 & 2\n", __FUNCTION__);
+#endif
+
+ dump_siram(tdm_c);
+ dump_ucc(tdm_c);
+
+ setbits8(&(qe_immr->si1.siglmr1_h), (0x1 << tdm_c->tdm_port));
+ pr_info("%s UCC based TDM enabled\n", __FUNCTION__);
+
+ return 0;
+}
+
+static void tdm_stop(struct tdm_ctrl *tdm_c)
+{
+ u32 port, si;
+ u32 ucc;
+ u32 cecr_subblock;
+
+ port = tdm_c->tdm_port;
+ si = tdm_c->si;
+ ucc = tdm_c->ut_info->uf_info.ucc_num;
+ cecr_subblock = ucc_fast_get_qe_cr_subblock(ucc);
+
+ qe_issue_cmd(QE_GRACEFUL_STOP_TX, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+ qe_issue_cmd(QE_CLOSE_RX_BD, cecr_subblock,
+ (u8) QE_CR_PROTOCOL_UNSPECIFIED, 0);
+
+ clrbits8(&qe_immr->si1.siglmr1_h, (0x1 << port));
+ ucc_fast_disable(tdm_c->uf_private, COMM_DIR_RX);
+ ucc_fast_disable(tdm_c->uf_private, COMM_DIR_TX);
+ free_irq(tdm_c->ut_info->uf_info.irq, tdm_c);
+}
+
+
+static void config_tdm(struct tdm_ctrl *tdm_c)
+{
+ u32 i, j, k;
+
+ j = 0;
+ k = 0;
+
+ /* Set Mask Bits */
+ for (i = 0; i < ACTIVE_CH; i++) {
+ tdm_c->tx_mask[k] |= (1 << j);
+ tdm_c->rx_mask[k] |= (1 << j);
+ j++;
+ if (j >= 16) {
+ j = 0;
+ k++;
+ }
+ }
+ /* physical number of slots in a frame */
+ tdm_c->physical_num_ts = NUM_TS;
+
+ /* common receive and transmit pins */
+ tdm_c->cfg_ctrl.com_pin = 1;
+
+ /* L1R/TSYNC active logic "1" */
+ tdm_c->cfg_ctrl.fr_sync_level = 0;
+
+ /*
+ * TX data on rising edge of clock
+ * RX data on falling edge
+ */
+ tdm_c->cfg_ctrl.clk_edge = 0;
+
+ /* Frame sync sampled on falling edge */
+ tdm_c->cfg_ctrl.fr_sync_edge = 0;
+
+ /* no bit delay */
+ tdm_c->cfg_ctrl.rx_fr_sync_delay = 0;
+
+ /* no bit delay */
+ tdm_c->cfg_ctrl.tx_fr_sync_delay = 0;
+
+#if !defined(CONFIG_TDM_HW_LB_TSA_SLIC)
+ if (tdm_c->leg_slic) {
+ /* Need 1 bit delay for Legrity SLIC */
+ tdm_c->cfg_ctrl.rx_fr_sync_delay = 1;
+ tdm_c->cfg_ctrl.tx_fr_sync_delay = 1;
+ pr_info("%s Delay for Legerity!\n", __FUNCTION__);
+ }
+#endif
+
+ tdm_c->cfg_ctrl.active_num_ts = ACTIVE_CH;
+}
+
+static void tdm_read(u32 driver_handle, short chn_id, short *pcm_buffer,
+ short len)
+{
+ int i;
+ u32 phase_rx;
+ /* point to where to start for the current phase data processing */
+ u32 temp_rx;
+
+ struct tdm_ctrl *tdm_c = (struct tdm_ctrl *)(driver_handle);
+
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ u8 *input_tdm_buffer = tdm_c->tdm_input_data;
+
+#else
+ u16 *input_tdm_buffer =
+ (u16 *)tdm_c->tdm_input_data;
+
+#endif
+ phase_rx = tdm_c->phase_rx;
+ phase_rx = PREV_PHASE(phase_rx);
+
+ temp_rx = phase_rx * SAMPLE_DEPTH * EFF_ACTIVE_CH;
+
+#if defined(UCC_CACHE_SNOOPING_DISABLED)
+ flush_dcache_range((size_t) &input_tdm_buffer[temp_rx],
+ (size_t) &input_tdm_buffer[temp_rx +
+ SAMPLE_DEPTH * ACTIVE_CH]);
+#endif
+ for (i = 0; i < len; i++) {
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ pcm_buffer[i] =
+ ulaw2int(input_tdm_buffer[i * EFF_ACTIVE_CH +
+ temp_rx + chn_id]);
+#else
+ pcm_buffer[i] =
+ input_tdm_buffer[i * EFF_ACTIVE_CH + temp_rx + chn_id];
+#endif
+
+ }
+
+}
+
+static void tdm_write(u32 driver_handle, short chn_id, short *pcm_buffer,
+ short len)
+{
+ int i;
+ int phase_tx;
+ u32 txb;
+ /* point to where to start for the current phase data processing */
+ int temp_tx;
+ struct tdm_ctrl *tdm_c = (struct tdm_ctrl *)(driver_handle);
+
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ u8 *output_tdm_buffer;
+ output_tdm_buffer = tdm_c->tdm_output_data;
+#else
+ u16 *output_tdm_buffer;
+ output_tdm_buffer = (u16 *)tdm_c->tdm_output_data;
+#endif
+ txb = in_be32(&tdm_c->ucc_pram->tbptr) -
+ in_be32(&tdm_c->ucc_pram->tbase);
+ phase_tx = txb / sizeof(struct qe_bd);
+
+ phase_tx = PREV_PHASE(phase_tx);
+
+ temp_tx = phase_tx * SAMPLE_DEPTH * EFF_ACTIVE_CH;
+
+ for (i = 0; i < len; i++) {
+#if !defined(CONFIG_TDM_LINEAR_PCM)
+ output_tdm_buffer[i * EFF_ACTIVE_CH + temp_tx + chn_id] =
+ int2ulaw(pcm_buffer[i]);
+#else
+ output_tdm_buffer[i * EFF_ACTIVE_CH + temp_tx + chn_id] =
+ pcm_buffer[i];
+#endif
+ }
+
+#if defined(UCC_CACHE_SNOOPING_DISABLED)
+ flush_dcache_range((size_t) &output_tdm_buffer[temp_tx],
+ (size_t) &output_tdm_buffer[temp_tx + SAMPLE_DEPTH *
+ ACTIVE_CH]);
+#endif
+}
+
+
+static int tdm_register_client(struct tdm_client *tdm_client)
+{
+ if (num_tdm_clients == num_tdm_devices) {
+ printk(KERN_ERR "all TDM devices busy\n");
+ return -EBUSY;
+ }
+
+ num_tdm_clients++;
+ tdm_client->driver_handle = (u32)(tdm_ctrl[num_tdm_clients - 1]);
+ tdm_client->tdm_read = tdm_read;
+ tdm_client->tdm_write = tdm_write;
+ tdm_client->wakeup_event =
+ &(tdm_ctrl[num_tdm_clients - 1]->wakeup_event);
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tdm_register_client);
+
+static int tdm_deregister_client(struct tdm_client *tdm_client)
+{
+ num_tdm_clients--;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tdm_deregister_client);
+
+static int ucc_tdm_probe(struct of_device *ofdev,
+ const struct of_device_id *match)
+{
+ struct device_node *np = ofdev->node;
+ struct resource res;
+ const unsigned int *prop;
+ u32 ucc_num, device_num, err, ret = 0;
+ struct device_node *np_tmp = NULL;
+ dma_addr_t physaddr;
+ void *tdm_buff;
+ struct ucc_tdm_info *ut_info;
+
+ prop = of_get_property(np, "device-id", NULL);
+ ucc_num = *prop - 1;
+ if ((ucc_num < 0) || (ucc_num > 7))
+ return -ENODEV;
+
+ ut_info = &utdm_info[ucc_num];
+ if (ut_info == NULL) {
+ printk(KERN_ERR "additional data missing\n");
+ return -ENODEV;
+ }
+ if (ut_info->ucc_busy) {
+ printk(KERN_ERR "UCC in use by another TDM driver instance\n");
+ return -EBUSY;
+ }
+
+ ut_info->ucc_busy = 1;
+ tdm_ctrl[num_tdm_devices++] =
+ kzalloc(sizeof(struct tdm_ctrl), GFP_KERNEL);
+ if (!tdm_ctrl[num_tdm_devices - 1]) {
+ printk(KERN_ERR "%s: no memory to allocate for"
+ " tdm control structure\n", __FUNCTION__);
+ num_tdm_devices--;
+ return -ENOMEM;
+ }
+ device_num = num_tdm_devices - 1;
+
+ tdm_ctrl[device_num]->device = &ofdev->dev;
+ tdm_ctrl[device_num]->ut_info = ut_info;
+
+ tdm_ctrl[device_num]->ut_info->uf_info.ucc_num = ucc_num;
+
+ prop = of_get_property(np, "fsl,tdm-num", NULL);
+ if (prop == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->tdm_port = *prop - 1;
+
+ if (tdm_ctrl[device_num]->tdm_port > 3) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ prop = of_get_property(np, "fsl,si-num", NULL);
+ if (prop == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->si = *prop - 1;
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_clk =
+ (char *) of_get_property(np, "fsl,tdm-tx-clk", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_clk == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_clk =
+ (char *) of_get_property(np, "fsl,tdm-rx-clk", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_clk == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_sync =
+ (char *) of_get_property(np, "fsl,tdm-tx-sync", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_tx_sync == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_sync =
+ (char *) of_get_property(np, "fsl,tdm-rx-sync", NULL);
+ if (tdm_ctrl[device_num]->ut_info->uf_info.tdm_rx_sync == NULL) {
+ ret = -EINVAL;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->ut_info->uf_info.irq =
+ irq_of_parse_and_map(np, 0);
+ err = of_address_to_resource(np, 0, &res);
+ if (err) {
+ ret = EINVAL;
+ goto get_property_error;
+ }
+ tdm_ctrl[device_num]->ut_info->uf_info.regs = res.start;
+ tdm_ctrl[device_num]->uf_regs = of_iomap(np, 0);
+
+ np_tmp = of_find_compatible_node(np_tmp, "slic", "legerity-slic");
+ if (np_tmp != NULL)
+ tdm_ctrl[device_num]->leg_slic = 1;
+ else
+ tdm_ctrl[device_num]->leg_slic = 0;
+
+ config_tdm(tdm_ctrl[device_num]);
+
+ tdm_buff = dma_alloc_coherent(NULL, 2 * NR_BUFS * SAMPLE_DEPTH *
+ tdm_ctrl[device_num]->cfg_ctrl.active_num_ts,
+ &physaddr, GFP_KERNEL);
+ if (!tdm_buff) {
+ printk(KERN_ERR "ucc-tdm: could not allocate buffer"
+ "descriptors\n");
+ ret = -ENOMEM;
+ goto get_property_error;
+ }
+
+ tdm_ctrl[device_num]->tdm_input_data = tdm_buff;
+ tdm_ctrl[device_num]->dma_input_addr = physaddr;
+
+ tdm_ctrl[device_num]->tdm_output_data = tdm_buff + NR_BUFS *
+ SAMPLE_DEPTH * tdm_ctrl[device_num]->cfg_ctrl.active_num_ts;
+ tdm_ctrl[device_num]->dma_output_addr = physaddr + NR_BUFS *
+ SAMPLE_DEPTH * tdm_ctrl[device_num]->cfg_ctrl.active_num_ts;
+
+ init_waitqueue_head(&(tdm_ctrl[device_num]->wakeup_event));
+
+ ret = tdm_init(tdm_ctrl[device_num]);
+ if (ret != 0)
+ goto tdm_init_error;
+
+ ret = tdm_start(tdm_ctrl[device_num]);
+ if (ret != 0)
+ goto tdm_start_error;
+
+ dev_set_drvdata(&(ofdev->dev), tdm_ctrl[device_num]);
+
+ pr_info("%s UCC based tdm module installed\n", __FUNCTION__);
+ return 0;
+
+tdm_start_error:
+ tdm_deinit(tdm_ctrl[device_num]);
+tdm_init_error:
+ dma_free_coherent(NULL, 2 * NR_BUFS * SAMPLE_DEPTH *
+ tdm_ctrl[device_num]->cfg_ctrl.active_num_ts,
+ tdm_ctrl[device_num]->tdm_input_data,
+ tdm_ctrl[device_num]->dma_input_addr);
+
+get_property_error:
+ kfree(tdm_ctrl[device_num]);
+ return ret;
+}
+
+static int ucc_tdm_remove(struct of_device *ofdev)
+{
+ struct tdm_ctrl *tdm_c;
+ struct ucc_tdm_info *ut_info;
+ u32 ucc_num;
+
+ tdm_c = dev_get_drvdata(&(ofdev->dev));
+ ucc_num = tdm_c->ut_info->uf_info.ucc_num;
+ ut_info = &utdm_info[ucc_num];
+ tdm_stop(tdm_c);
+ tdm_deinit(tdm_c);
+
+ ucc_fast_free(tdm_c->uf_private);
+
+ dma_free_coherent(NULL, 2 * NR_BUFS * SAMPLE_DEPTH *
+ tdm_c->cfg_ctrl.active_num_ts,
+ tdm_c->tdm_input_data,
+ tdm_c->dma_input_addr);
+
+ num_tdm_devices--;
+ kfree(tdm_c);
+
+ ut_info->ucc_busy = 0;
+
+ pr_info("%s UCC based tdm module uninstalled\n", __FUNCTION__);
+ return 0;
+}
+
+static struct of_device_id ucc_tdm_match[] = {
+ {
+ .type = "tdm",
+ .compatible = "fsl,ucc-tdm",
+ }, {},
+};
+
+MODULE_DEVICE_TABLE(of, ucc_tdm_match);
+
+static struct of_platform_driver ucc_tdm_driver = {
+ .name = DRV_NAME,
+ .match_table = ucc_tdm_match,
+ .probe = ucc_tdm_probe,
+ .remove = ucc_tdm_remove,
+};
+
+static int __init ucc_tdm_init(void)
+{
+ u32 i;
+
+ pr_info("ucc_tdm: " DRV_DESC "\n");
+ for (i = 0; i < 8; i++)
+ memcpy(&(utdm_info[i]), &utdm_primary_info,
+ sizeof(utdm_primary_info));
+
+ return of_register_platform_driver(&ucc_tdm_driver);
+}
+
+static void __exit ucc_tdm_exit(void)
+{
+ of_unregister_platform_driver(&ucc_tdm_driver);
+}
+
+module_init(ucc_tdm_init);
+module_exit(ucc_tdm_exit);
+MODULE_AUTHOR("Freescale Semiconductor, Inc");
+MODULE_DESCRIPTION(DRV_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/misc/ucc_tdm.h b/drivers/misc/ucc_tdm.h
new file mode 100644
index 0000000..d0f376b
--- /dev/null
+++ b/drivers/misc/ucc_tdm.h
@@ -0,0 +1,227 @@
+/*
+ * drivers/misc/ucc_tdm.h
+ *
+ * UCC Based Linux TDM Driver
+ * This driver is designed to support UCC based TDM for PowerPC processors.
+ * This driver can interface with SLIC device to run VOIP kind of
+ * applications.
+ *
+ * Author: Ashish Kalra & Poonam Aggrwal
+ *
+ * Copyright (c) 2007 Freescale Semiconductor, 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; either version 2 of the License, or (at your
+ * option) any later version.
+ */
+
+#ifndef TDM_H
+#define TDM_H
+
+#define NUM_TS 8
+#define ACTIVE_CH 8
+
+/* SAMPLE_DEPTH is the sample depth is the number of frames before
+ * an interrupt. Must be a multiple of 4
+ */
+#define SAMPLE_DEPTH 80
+
+/* define the number of Rx interrupts to go by for initial stuttering */
+#define STUTTER_INT_CNT 1
+
+/* BMRx Field Descriptions to specify tstate and rstate in UCC parameter RAM*/
+#define EN_BUS_SNOOPING 0x20
+#define BE_BO 0x10
+
+/* UPSMR Register for Transparent UCC controller Bit definitions*/
+#define NBO 0x00000000 /* Normal Mode 1 bit of data per clock */
+
+/* SI Mode register bit definitions */
+#define NORMAL_OPERATION 0x0000
+#define AUTO_ECHO 0x0400
+#define INTERNAL_LB 0x0800
+#define CONTROL_LB 0x0c00
+#define SIMODE_CRT (0x8000 >> 9)
+#define SIMODE_SL (0x8000 >> 10)
+#define SIMODE_CE (0x8000 >> 11)
+#define SIMODE_FE (0x8000 >> 12)
+#define SIMODE_GM (0x8000 >> 13)
+#define SIMODE_TFSD(val) (val)
+#define SIMODE_RFSD(val) ((val) << 8)
+
+#define SI_TDM_MODE_REGISTER_OFFSET 0
+
+#define R_CM 0x02000000
+#define T_CM 0x02000000
+
+#define SET_RX_SI_RAM(n, val) \
+ out_be16((u16 *)&qe_immr->sir.rx[(n)*2], (u16)(val))
+
+#define SET_TX_SI_RAM(n, val) \
+ out_be16((u16 *)&qe_immr->sir.tx[(n)*2], (u16)(val))
+
+/* SI RAM entries */
+#define SIR_LAST 0x0001
+#define SIR_CNT(n) ((n) << 2)
+#define SIR_BYTE 0x0002
+#define SIR_BIT 0x0000
+#define SIR_IDLE 0
+#define SIR_UCC(uccx) (((uccx+9)) << 5)
+
+/* BRGC Register Bit definitions */
+#define BRGC_RESET (0x1<<17)
+#define BRGC_EN (0x1<<16)
+#define BRGC_EXTC_QE (0x00<<14)
+#define BRGC_EXTC_CLK3 (0x01<<14)
+#define BRGC_EXTC_CLK5 (0x01<<15)
+#define BRGC_EXTC_CLK9 (0x01<<14)
+#define BRGC_EXTC_CLK11 (0x01<<14)
+#define BRGC_EXTC_CLK13 (0x01<<14)
+#define BRGC_EXTC_CLK15 (0x01<<15)
+#define BRGC_ATB (0x1<<13)
+#define BRGC_DIV16 (0x1)
+
+/* structure representing UCC transparent parameter RAM */
+struct ucc_transparent_pram {
+ __be16 riptr;
+ __be16 tiptr;
+ __be16 res0;
+ __be16 mrblr;
+ __be32 rstate;
+ __be32 rbase;
+ __be16 rbdstat;
+ __be16 rbdlen;
+ __be32 rdptr;
+ __be32 tstate;
+ __be32 tbase;
+ __be16 tbdstat;
+ __be16 tbdlen;
+ __be32 tdptr;
+ __be32 rbptr;
+ __be32 tbptr;
+ __be32 rcrc;
+ __be32 res1;
+ __be32 tcrc;
+ __be32 res2;
+ __be32 res3;
+ __be32 c_mask;
+ __be32 c_pres;
+ __be16 disfc;
+ __be16 crcec;
+ __be32 res4[4];
+ __be16 ts_tmp;
+ __be16 tmp_mb;
+};
+
+#define UCC_TRANSPARENT_PRAM_SIZE 0x100
+
+struct tdm_cfg {
+ u8 com_pin; /* Common receive and transmit pins
+ * 0 = separate pins
+ * 1 = common pins
+ */
+
+ u8 fr_sync_level; /* SLx bit Frame Sync Polarity
+ * 0 = L1R/TSYNC active logic "1"
+ * 1 = L1R/TSYNC active logic "0"
+ */
+
+ u8 clk_edge; /* CEx bit Tx Rx Clock Edge
+ * 0 = TX data on rising edge of clock
+ * RX data on falling edge
+ * 1 = TX data on falling edge of clock
+ * RX data on rising edge
+ */
+
+ u8 fr_sync_edge; /* FEx bit Frame sync edge
+ * Determine when the sync pulses are sampled
+ * 0 = Falling edge
+ * 1 = Rising edge
+ */
+
+ u8 rx_fr_sync_delay; /* TFSDx/RFSDx bits Frame Sync Delay
+ * 00 = no bit delay
+ * 01 = 1 bit delay
+ * 10 = 2 bit delay
+ * 11 = 3 bit delay
+ */
+
+ u8 tx_fr_sync_delay; /* TFSDx/RFSDx bits Frame Sync Delay
+ * 00 = no bit delay
+ * 01 = 1 bit delay
+ * 10 = 2 bit delay
+ * 11 = 3 bit delay
+ */
+
+ u8 active_num_ts; /* Number of active time slots in TDM
+ * assume same active Rx/Tx time slots
+ */
+};
+
+struct ucc_tdm_info {
+ struct ucc_fast_info uf_info;
+ u32 ucc_busy;
+};
+
+struct tdm_ctrl {
+ struct device *device;
+ struct ucc_fast_private *uf_private;
+ struct ucc_tdm_info *ut_info;
+ u32 tdm_port; /* port for this tdm:TDMA,TDMB,TDMC,TDMD */
+ u32 si; /* serial interface: 0 or 1 */
+ struct ucc_fast __iomem *uf_regs; /* UCC Fast registers */
+ u16 rx_mask[8]; /* Active Receive channels LSB is ch0 */
+ u16 tx_mask[8]; /* Active Transmit channels LSB is ch0 */
+ /* Only channels less than the number of FRAME_SIZE are implemented */
+ struct tdm_cfg cfg_ctrl; /* Signaling controls configuration */
+ u8 *tdm_input_data; /* buffer used for Rx by the tdm */
+ u8 *tdm_output_data; /* buffer used for Tx by the tdm */
+
+ dma_addr_t dma_input_addr; /* dma mapped buffer for TDM Rx */
+ dma_addr_t dma_output_addr; /* dma mapped buffer for TDM Tx */
+ u16 physical_num_ts; /* physical number of timeslots in the tdm
+ frame */
+ u32 phase_rx; /* cycles through 0, 1, 2 */
+ u32 phase_tx; /* cycles through 0, 1, 2 */
+ /*
+ * the following two variables are for dealing with "stutter" problem
+ * "stutter" period is about 20 frames or so, varies depending active
+ * channel num depending on the sample depth, the code should let a
+ * few Rx interrupts go by
+ */
+ u32 tdm_icnt;
+ u32 tdm_flag;
+ struct ucc_transparent_pram __iomem *ucc_pram;
+ struct qe_bd __iomem *tx_bd;
+ struct qe_bd __iomem *rx_bd;
+ u32 ucc_pram_offset;
+ u32 tx_bd_offset;
+ u32 rx_bd_offset;
+ u32 rx_ucode_buf_offset;
+ u32 tx_ucode_buf_offset;
+ bool leg_slic;
+ wait_queue_head_t wakeup_event;
+};
+
+struct tdm_client {
+ u32 driver_handle;
+ void (*tdm_read)(u32 driver_handle, short chn_id,
+ short *pcm_buffer, short len);
+ void (*tdm_write)(u32 driver_handle, short chn_id,
+ short *pcm_buffer, short len);
+ wait_queue_head_t *wakeup_event;
+ };
+
+
+#ifndef CONFIG_TDM_LINEAR_PCM
+ #define MAX_PHASE 2
+ #define NR_BUFS 3
+ #define EFF_ACTIVE_CH ACTIVE_CH
+#else
+ #define MAX_PHASE 1
+ #define NR_BUFS 2
+ #define EFF_ACTIVE_CH ACTIVE_CH / 2
+#endif
+
+#endif
--
1.5.2.4
^ permalink raw reply related
* [PATCH 0/3] UCC TDM driver for MPC83xx platforms
From: Aggrwal Poonam @ 2007-12-10 11:40 UTC (permalink / raw)
To: rubini, linux-kernel, netdev, Gala Kumar
Cc: Barkowski Michael, Phillips Kim, Kalra Ashish, Cutler Richard
There are three patches
[PATCH 1/3] drivers/misc : UCC TDM driver for mpc83xx platforms. This
driver is usable in VoIP iind of applications to interface with SLIC
kind of devices to exchange TDM voice samples.
[PATCH 2/3] arch/ : Platform changes
- device tree entries for UCC TDM driver for MPC8323ERDB platform.
- QE changes related to TDM , like,
1) Modified ucc_fast_init so that it can be used by fast UCC
based TDM driver. Mainly changes have been made to configure TDM clocks
and Fsyncs.
2) Modified get_brg_clk so that it can return the input frequncy
and input source of any BRG by reading the corresponding entries from
device tree.
3) Added new nodes brg and clocks in the device tree which
represent input clocks for different BRGs.
4) Modified qe_setbrg accordingly.
- new device tree entries added for "clocks" and "brg"
[PATCH 3/3] Documentation
- Modified Documentation to explain the device tree entries related to
UCC TDM driver and the new nodes added("clocks" and "brg")
The patch applies over a merge of galak's for-2.6.25 plus for-2.6.24
plus of_doc_update branches.
In brief the steps were
git clone
git://git.kernel.org/pub/scm/linux/kernel/git/galak/powerpc.git
powerpc-galak
git checkout -b for-2.6.25 origin/for-2.6.25
git checkout -b for-2.6.24 origin/for-2.6.24
git checkout -b of_doc_update origin/of_doc_update
git pull . for-2.6.24 # merge the other two
git pull . for-2.6.25
git checkout -b tdm # clean slate for tdm rebase work
Also after applying the patches changes have to be made corresponding to
Tabi's patch "qe: add function qe_clock_source".
The driver has been tested with a VoIP stack and application on
MPC8323ERDB.
With Regards
Poonam
^ permalink raw reply
* Re: [PATCH 5/8] [TFRC]: Loss interval code needs the macros/inlines that were moved
From: Gerrit Renker @ 2007-12-10 11:31 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, dccp, netdev
In-Reply-To: <20071208184711.GF3180@ghostprotocols.net>
| >
| > distcc[24516] ERROR: compile /root/.ccache/packet_his.tmp.aspire.home.net.24512.i on _tiptop failed
| > /usr/src/davem-2.6/net/dccp/ccids/lib/packet_history.c: In function '__one_after_loss':
| > /usr/src/davem-2.6/net/dccp/ccids/lib/packet_history.c:266: error: lvalue required as unary '&' operand
<snip>
|
| Because you do it this way:
|
| tfrc_rx_hist_swap(&TFRC_RX_HIST_ENTRY(h, 0), &TFRC_RX_HIST_ENTRY(h, 3));
|
| I checked and at least in this patch series all uses are of this type,
| so why not do it using just the indexes, which would be simpler:
|
| tfrc_rx_hist_swap(h, 0, 3);
|
| With this implementation:
|
| static void tfrc_rx_hist_swap(struct tfrc_rx_hist *h, const int a, const int b)
| {
| const int idx_a = tfrc_rx_hist_index(h, a),
| int idx_b = tfrc_rx_hist_index(h, b);
| struct tfrc_rx_hist_entry *tmp = h->ring[idx_a];
|
| h->ring[idx_a] = h->ring[idx_b];
| h->ring[idx_b] = tmp;
| }
|
Agreed, that is useful in the present case, since then everything uses
inlines. The only suggestion I'd like to make is to use `u8' instead of
`int' since the indices will have very low values.
There is a related point: you will probably have noticed that loss_interval.c
also uses macros. I don't know if you are planning to convert these also into
inlines. I think that there would be less benefit in converting these, since
they are locl to loss_interval.c and mostly serve to improve readability.
As I have at least one other patch to revise (plus another minor one),
I'll rework this according to the above.
^ permalink raw reply
* Re: [PATCH 2/8] [TFRC]: Put RX/TX initialisation into tfrc.c
From: Gerrit Renker @ 2007-12-10 10:56 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo, dccp, netdev
In-Reply-To: <20071208171317.GC3180@ghostprotocols.net>
| > This separates RX/TX initialisation and puts all packet history / loss intervals
| > initialisation into tfrc.c.
| > The organisation is uniform: slab declaration -> {rx,tx}_init() -> {rx,tx}_exit()
|
| NAK, you can't call a __exit marked routine from a __init marked
| routine.
|
Ok thanks, will fix that in revision 2.
^ permalink raw reply
* routing policy based on u32 classifier
From: Marco Berizzi @ 2007-12-10 9:22 UTC (permalink / raw)
To: netdev
Hello everybody.
Kindly, I would like to know if the is any plan
to add this feature to a future kernel release.
I know that fwmark is able to do this, but there
is the limitation in source ip address selection.
TIA
^ permalink raw reply
* Re: [PATCH 4/4] udp: memory accounting in IPv4
From: Herbert Xu @ 2007-12-10 9:22 UTC (permalink / raw)
To: Hideo AOKI
Cc: netdev, David Miller, Eric Dumazet, Satoshi Oshima, Bill Fink,
Andi Kleen, Evgeniy Polyakov, Stephen Hemminger, yoshfuji,
Yumiko Sugita
In-Reply-To: <47577A72.10205@redhat.com>
On Wed, Dec 05, 2007 at 11:28:34PM -0500, Hideo AOKI wrote:
>
> 1. Using sk_forward_alloc and adding socket lock
>
> UDP already uses a socket lock to send message. However, it doesn't
> use the lock to receive message. I wonder if we can also use the
> lock when sk_forward_alloc is updated in receive processing.
> I understand performance issue might occur, but ...
Having discussed this with Dave we've agreed that this is the
best way to go.
Thanks,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ 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