* [PATCH v3] 9p: Add refcount to p9_req_t
From: Dominique Martinet @ 2018-08-29 4:59 UTC (permalink / raw)
To: Tomas Bortoli, Eric Van Hensbergen, Latchesar Ionkov
Cc: v9fs-developer, netdev, linux-kernel, syzkaller,
Dominique Martinet
From: Tomas Bortoli <tomasbortoli@gmail.com>
To avoid use-after-free(s), use a refcount to keep track of the
usable references to any instantiated struct p9_req_t.
This commit adds p9_req_put(), p9_req_get() and p9_req_try_get() as
wrappers to kref_put(), kref_get() and kref_get_unless_zero().
These are used by the client and the transports to keep track of
valid requests' references.
p9_free_req() is added back and used as callback by kref_put().
Add SLAB_TYPESAFE_BY_RCU as it ensures that the memory freed by
kmem_cache_free() will not be reused for another type until the rcu
synchronisation period is over, so an address gotten under rcu read
lock is safe to inc_ref() without corrupting random memory while
the lock is held.
Co-developed-by: Dominique Martinet <dominique.martinet@cea.fr>
Signed-off-by: Tomas Bortoli <tomasbortoli@gmail.com>
Reported-by: syzbot+467050c1ce275af2a5b8@syzkaller.appspotmail.com
Signed-off-by: Dominique Martinet <dominique.martinet@cea.fr>
---
include/net/9p/client.h | 14 ++++++++++
net/9p/client.c | 59 ++++++++++++++++++++++++++++++++++++-----
net/9p/trans_fd.c | 11 +++++++-
net/9p/trans_rdma.c | 2 ++
net/9p/trans_virtio.c | 18 ++++++++++---
5 files changed, 92 insertions(+), 12 deletions(-)
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 735f3979d559..947a570307a6 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -94,6 +94,7 @@ enum p9_req_status_t {
struct p9_req_t {
int status;
int t_err;
+ struct kref refcount;
wait_queue_head_t wq;
struct p9_fcall tc;
struct p9_fcall rc;
@@ -233,6 +234,19 @@ int p9_client_lock_dotl(struct p9_fid *fid, struct p9_flock *flock, u8 *status);
int p9_client_getlock_dotl(struct p9_fid *fid, struct p9_getlock *fl);
void p9_fcall_fini(struct p9_fcall *fc);
struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
+
+static inline void p9_req_get(struct p9_req_t *r)
+{
+ kref_get(&r->refcount);
+}
+
+static inline int p9_req_try_get(struct p9_req_t *r)
+{
+ return kref_get_unless_zero(&r->refcount);
+}
+
+int p9_req_put(struct p9_req_t *r);
+
void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status);
int p9_parse_header(struct p9_fcall *, int32_t *, int8_t *, int16_t *, int);
diff --git a/net/9p/client.c b/net/9p/client.c
index 7942c0bfcc5b..4cf11adad819 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -310,6 +310,18 @@ p9_tag_alloc(struct p9_client *c, int8_t type, unsigned int max_size)
if (tag < 0)
goto free;
+ /* Init ref to two because in the general case there is one ref
+ * that is put asynchronously by a writer thread, one ref
+ * temporarily given by p9_tag_lookup and put by p9_client_cb
+ * in the recv thread, and one ref put by p9_tag_remove in the
+ * main thread. The only exception is virtio that does not use
+ * p9_tag_lookup but does not have a writer thread either
+ * (the write happens synchronously in the request/zc_request
+ * callback), so p9_client_cb eats the second ref there
+ * as the pointer is duplicated directly by virtqueue_add_sgs()
+ */
+ refcount_set(&req->refcount.refcount, 2);
+
return req;
free:
@@ -333,10 +345,21 @@ struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag)
struct p9_req_t *req;
rcu_read_lock();
+again:
req = idr_find(&c->reqs, tag);
- /* There's no refcount on the req; a malicious server could cause
- * us to dereference a NULL pointer
- */
+ if (req) {
+ /* We have to be careful with the req found under rcu_read_lock
+ * Thanks to SLAB_TYPESAFE_BY_RCU we can safely try to get the
+ * ref again without corrupting other data, then check again
+ * that the tag matches once we have the ref
+ */
+ if (!p9_req_try_get(req))
+ goto again;
+ if (req->tc.tag != tag) {
+ p9_req_put(req);
+ goto again;
+ }
+ }
rcu_read_unlock();
return req;
@@ -350,7 +373,7 @@ EXPORT_SYMBOL(p9_tag_lookup);
*
* Context: Any context.
*/
-static void p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
+static int p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
{
unsigned long flags;
u16 tag = r->tc.tag;
@@ -359,11 +382,23 @@ static void p9_tag_remove(struct p9_client *c, struct p9_req_t *r)
spin_lock_irqsave(&c->lock, flags);
idr_remove(&c->reqs, tag);
spin_unlock_irqrestore(&c->lock, flags);
+ return p9_req_put(r);
+}
+
+static void p9_req_free(struct kref *ref)
+{
+ struct p9_req_t *r = container_of(ref, struct p9_req_t, refcount);
p9_fcall_fini(&r->tc);
p9_fcall_fini(&r->rc);
kmem_cache_free(p9_req_cache, r);
}
+int p9_req_put(struct p9_req_t *r)
+{
+ return kref_put(&r->refcount, p9_req_free);
+}
+EXPORT_SYMBOL(p9_req_put);
+
/**
* p9_tag_cleanup - cleans up tags structure and reclaims resources
* @c: v9fs client struct
@@ -379,7 +414,9 @@ static void p9_tag_cleanup(struct p9_client *c)
rcu_read_lock();
idr_for_each_entry(&c->reqs, req, id) {
pr_info("Tag %d still in use\n", id);
- p9_tag_remove(c, req);
+ if (p9_tag_remove(c, req) == 0)
+ pr_warn("Packet with tag %d has still references",
+ req->tc.tag);
}
rcu_read_unlock();
}
@@ -403,6 +440,7 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req, int status)
wake_up(&req->wq);
p9_debug(P9_DEBUG_MUX, "wakeup: %d\n", req->tc.tag);
+ p9_req_put(req);
}
EXPORT_SYMBOL(p9_client_cb);
@@ -643,9 +681,12 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
* if we haven't received a response for oldreq,
* remove it from the list
*/
- if (oldreq->status == REQ_STATUS_SENT)
+ if (oldreq->status == REQ_STATUS_SENT) {
if (c->trans_mod->cancelled)
c->trans_mod->cancelled(c, oldreq);
+ else
+ p9_req_put(oldreq);
+ }
p9_tag_remove(c, req);
return 0;
@@ -682,6 +723,8 @@ static struct p9_req_t *p9_client_prepare_req(struct p9_client *c,
return req;
reterr:
p9_tag_remove(c, req);
+ /* We have to put also the 2nd reference as it won't be used */
+ p9_req_put(req);
return ERR_PTR(err);
}
@@ -716,6 +759,8 @@ p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
err = c->trans_mod->request(c, req);
if (err < 0) {
+ /* write won't happen */
+ p9_req_put(req);
if (err != -ERESTARTSYS && err != -EFAULT)
c->status = Disconnected;
goto recalc_sigpending;
@@ -2241,7 +2286,7 @@ EXPORT_SYMBOL(p9_client_readlink);
int __init p9_client_init(void)
{
- p9_req_cache = KMEM_CACHE(p9_req_t, 0);
+ p9_req_cache = KMEM_CACHE(p9_req_t, SLAB_TYPESAFE_BY_RCU);
return p9_req_cache ? 0 : -ENOMEM;
}
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 20f46f13fe83..686e24e355d0 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -132,6 +132,7 @@ struct p9_conn {
struct list_head req_list;
struct list_head unsent_req_list;
struct p9_req_t *req;
+ struct p9_req_t *wreq;
char tmp_buf[7];
struct p9_fcall rc;
int wpos;
@@ -383,6 +384,7 @@ static void p9_read_work(struct work_struct *work)
m->rc.sdata = NULL;
m->rc.offset = 0;
m->rc.capacity = 0;
+ p9_req_put(m->req);
m->req = NULL;
}
@@ -472,6 +474,8 @@ static void p9_write_work(struct work_struct *work)
m->wbuf = req->tc.sdata;
m->wsize = req->tc.size;
m->wpos = 0;
+ p9_req_get(req);
+ m->wreq = req;
spin_unlock(&m->client->lock);
}
@@ -492,8 +496,11 @@ static void p9_write_work(struct work_struct *work)
}
m->wpos += err;
- if (m->wpos == m->wsize)
+ if (m->wpos == m->wsize) {
m->wpos = m->wsize = 0;
+ p9_req_put(m->wreq);
+ m->wreq = NULL;
+ }
end_clear:
clear_bit(Wworksched, &m->wsched);
@@ -694,6 +701,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
if (req->status == REQ_STATUS_UNSENT) {
list_del(&req->req_list);
req->status = REQ_STATUS_FLSHD;
+ p9_req_put(req);
ret = 0;
}
spin_unlock(&client->lock);
@@ -711,6 +719,7 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req)
spin_lock(&client->lock);
list_del(&req->req_list);
spin_unlock(&client->lock);
+ p9_req_put(req);
return 0;
}
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 5b0cda1aaa7a..9ea9e2eb318e 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -365,6 +365,7 @@ send_done(struct ib_cq *cq, struct ib_wc *wc)
c->busa, c->req->tc.size,
DMA_TO_DEVICE);
up(&rdma->sq_sem);
+ p9_req_put(c->req);
kfree(c);
}
@@ -611,6 +612,7 @@ static int rdma_cancelled(struct p9_client *client, struct p9_req_t *req)
{
struct p9_trans_rdma *rdma = client->trans;
atomic_inc(&rdma->excess_rc);
+ p9_req_put(req);
return 0;
}
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 3dd6ce1c0f2d..c7aaea74cdc1 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -404,6 +404,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
struct scatterlist *sgs[4];
size_t offs;
int need_drop = 0;
+ int kicked = 0;
p9_debug(P9_DEBUG_TRANS, "virtio request\n");
@@ -411,8 +412,10 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
__le32 sz;
int n = p9_get_mapped_pages(chan, &out_pages, uodata,
outlen, &offs, &need_drop);
- if (n < 0)
- return n;
+ if (n < 0) {
+ err = n;
+ goto err_out;
+ }
out_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
if (n != outlen) {
__le32 v = cpu_to_le32(n);
@@ -428,8 +431,10 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
} else if (uidata) {
int n = p9_get_mapped_pages(chan, &in_pages, uidata,
inlen, &offs, &need_drop);
- if (n < 0)
- return n;
+ if (n < 0) {
+ err = n;
+ goto err_out;
+ }
in_nr_pages = DIV_ROUND_UP(n + offs, PAGE_SIZE);
if (n != inlen) {
__le32 v = cpu_to_le32(n);
@@ -498,6 +503,7 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
}
virtqueue_kick(chan->vq);
spin_unlock_irqrestore(&chan->lock, flags);
+ kicked = 1;
p9_debug(P9_DEBUG_TRANS, "virtio request kicked\n");
err = wait_event_killable(req->wq, req->status >= REQ_STATUS_RCVD);
/*
@@ -518,6 +524,10 @@ p9_virtio_zc_request(struct p9_client *client, struct p9_req_t *req,
}
kvfree(in_pages);
kvfree(out_pages);
+ if (!kicked) {
+ /* reply won't come */
+ p9_req_put(req);
+ }
return err;
}
--
2.17.1
^ permalink raw reply related
* Re: [PATCH v2 15/17] zinc: Curve25519 ARM implementation
From: Jason A. Donenfeld @ 2018-08-29 5:06 UTC (permalink / raw)
To: Ard Biesheuvel
Cc: LKML, Netdev, David Miller, Andrew Lutomirski, Greg Kroah-Hartman,
Samuel Neves, Daniel J . Bernstein, Jean-Philippe Aumasson,
Russell King - ARM Linux, linux-arm-kernel,
Linux Crypto Mailing List
In-Reply-To: <CAKv+Gu-WVOBZ1sQwOKo29P_jWL86wOnzd1-sB_6mTbPX1Lz0NQ@mail.gmail.com>
Hey Ard,
Thanks for the thorough review. Very much appreciated. I've
incorporated nearly all of your suggestions into my development tree:
https://git.kernel.org/pub/scm/linux/kernel/git/zx2c4/linux.git/tree/lib/zinc/curve25519/curve25519-arm.S?h=jd/wireguard
These changes will be part of v3.
Regards,
Jason
^ permalink raw reply
* [PATCH can-next] can: ucan: remove duplicated include from ucan.c
From: YueHaibing @ 2018-08-29 1:25 UTC (permalink / raw)
To: Wolfgang Grandegger, Marc Kleine-Budde, David S. Miller,
Martin Elshuber, Jakob Unterwurzacher, Philipp Tomsich
Cc: YueHaibing, linux-can, netdev, kernel-janitors
Remove duplicated include.
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/can/usb/ucan.c | 4 ----
1 file changed, 4 deletions(-)
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index 0678a38..c6f4b41 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -35,10 +35,6 @@
#include <linux/slab.h>
#include <linux/usb.h>
-#include <linux/can.h>
-#include <linux/can/dev.h>
-#include <linux/can/error.h>
-
#define UCAN_DRIVER_NAME "ucan"
#define UCAN_MAX_RX_URBS 8
/* the CAN controller needs a while to enable/disable the bus */
^ permalink raw reply related
* Re: [PATCH v2 iproute2-next 2/5] bridge: colorize output and use JSON print library
From: Roopa Prabhu @ 2018-08-29 1:17 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev, Stephen Hemminger, Julien Fortin, David Ahern
In-Reply-To: <CAJieiUi3BZPmaEJP6AK14zUwo20ssTNMz6eUfjFS0ZExizK9ng@mail.gmail.com>
On Sat, Jul 14, 2018 at 6:41 PM, Roopa Prabhu <roopa@cumulusnetworks.com> wrote:
> On Tue, Feb 20, 2018 at 11:24 AM, Stephen Hemminger
> <stephen@networkplumber.org> wrote:
>> From: Stephen Hemminger <sthemmin@microsoft.com>
>>
>> Use new functions from json_print to simplify code.
>> Provide standard flag for colorizing output.
>>
>> The shortened -c flag is ambiguous it could mean color or
>> compressvlan; it is now changed to mean color for consistency
>> with other iproute2 commands.
>>
>> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
>> ---
[snip]
>
> Stephen, this seems to have broken both json and non-json output.
>
> Here is some output before and after the patch (same thing for tunnelshow):
>
> before:
> $bridge vlan show
> port vlan ids
> hostbond4 1000
> 1001 PVID Egress Untagged
> 1002
> 1003
> 1004
>
> hostbond3 1000 PVID Egress Untagged
> 1001
> 1002
> 1003
> 1004
>
> bridge 1 PVID Egress Untagged
> 1000
> 1001
> 1002
> 1003
> 1004
>
> vxlan0 1 PVID Egress Untagged
> 1000
> 1001
> 1002
> 1003
> 1004
>
>
> $ bridge -j -c vlan show
> {
> "hostbond4": [{
> "vlan": 1000
> },{
> "vlan": 1001,
> "flags": ["PVID","Egress Untagged"
> ]
> },{
> "vlan": 1002,
> "vlanEnd": 1004
> }
> ],
> "hostbond3": [{
> "vlan": 1000,
> "flags": ["PVID","Egress Untagged"
> ]
> },{
> "vlan": 1001,
> "vlanEnd": 1004
> }
> ],
> "bridge": [{
> "vlan": 1,
> "flags": ["PVID","Egress Untagged"
> ]
> },{
> "vlan": 1000,
> "vlanEnd": 1004
> }
> ],
> "vxlan0": [{
> "vlan": 1,
> "flags": ["PVID","Egress Untagged"
> ]
> },{
> "vlan": 1000,
> "vlanEnd": 1004
> }
> ]
> }
>
>
> after:
> ====
>
> $bridge vlan show
> port vlan ids
> hostbond4
> 1000 1001 PVID untagged 1002 1003 1004
> hostbond3
> 1000 PVID untagged 1001 1002 1003 1004
> bridge
> 1 PVID untagged 1000 1001 1002 1003 1004
> vxlan0
> 1 PVID untagged 1000 1001 1002 1003 1004
>
> $bridge -j -c vlan show
> ["hostbond4","vlan":[{"vlan":1000},{"vlan":1001,"pvid":null,"untagged":null},{"vlan":1002},{"vlan":1003},{"vlan":1004}],"hostbond3","vlan":[{"vlan":1000,"pvid":null,"untagged":null},{"vlan":1001},{"vlan":1002},{"vlan":1003},{"vlan":1004}],"bridge","vlan":[{"vlan":1,"pvid":null,"untagged":null},{"vlan":1000},{"vlan":1001},{"vlan":1002},{"vlan":1003},{"vlan":1004}],"vxlan0","vlan":[{"vlan":1,"pvid":null,"untagged":null},{"vlan":1000},{"vlan":1001},{"vlan":1002},{"vlan":1003},{"vlan":1004}]]
Stephen, ping again...
I was trying to fix it ...but its not trivial enough for the time I
have right now.
If this cannot be fixed soon, I request you to please revert the patch
as it has broken the json output completely.
Thanks.
^ permalink raw reply
* Wohltätigkeitsspende in Höhe von € 2.000.000,00
From: ines_valdiviezo @ 2018-08-28 22:34 UTC (permalink / raw)
To: Recipients
Lieber Freund,
Ich bin Herr Tayeb Souami, New Jersey, Vereinigte Staaten von Amerika, der Mega-Gewinner von $ 315million In Mega Millions Jackpot, spende ich an 5 zufällige Personen, wenn Sie diese E-Mail erhalten, dann wurde Ihre E-Mail nach einem Spinball ausgewählt.Ich habe den größten Teil meines Vermögens auf eine Reihe von Wohltätigkeitsorganisationen und Organisationen verteilt.Ich habe mich freiwillig dazu entschieden, die Summe von € 2.000.000,00 an Sie als eine der ausgewählten 5 zu spenden, um meine Gewinne zu überprüfen, sehen Sie bitte meine You Tube Seite unten.
UHR MICH HIER: https://www.youtube.com/watch?v=Z6ui8ZDQ6Ks
Das ist dein Spendencode: [DFC530342018]
Antworten Sie mit dem SPENDE-CODE an diese E-Mail: financialfundingcompany09@gmail.com
Ich hoffe, Sie und Ihre Familie glücklich zu machen.
Grüße
Herr Tayeb Souami
^ permalink raw reply
* [PATCH can-next] can: ucan: remove set but not used variable 'udev'
From: YueHaibing @ 2018-08-29 1:46 UTC (permalink / raw)
To: Wolfgang Grandegger, Marc Kleine-Budde, David S. Miller,
Martin Elshuber, Jakob Unterwurzacher, Philipp Tomsich
Cc: YueHaibing, linux-can, netdev, kernel-janitors
Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/can/usb/ucan.c: In function 'ucan_disconnect':
drivers/net/can/usb/ucan.c:1578:21: warning:
variable 'udev' set but not used [-Wunused-but-set-variable]
struct usb_device *udev;
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
---
drivers/net/can/usb/ucan.c | 3 ---
1 file changed, 3 deletions(-)
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index 0678a38..c9fd83e 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -1575,11 +1575,8 @@ static int ucan_probe(struct usb_interface *intf,
/* disconnect the device */
static void ucan_disconnect(struct usb_interface *intf)
{
- struct usb_device *udev;
struct ucan_priv *up = usb_get_intfdata(intf);
- udev = interface_to_usbdev(intf);
-
usb_set_intfdata(intf, NULL);
if (up) {
^ permalink raw reply related
* [PATCH net-next 0/4] liquidio: improve soft command/response handling
From: Felix Manlunas @ 2018-08-29 1:50 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, weilin.chang
From: Weilin Chang <weilin.chang@cavium.com>
Change soft command handling to fix the possible race condition when the
process handles a response of a soft command that was already freed by an
application which got timeout for this request.
Weilin Chang (4):
liquidio: improve soft command handling
liquidio: make soft command calls synchronous
liquidio: change octnic_ctrl_pkt to do synchronous soft commands
liquidio: remove obsolete functions and data structures
drivers/net/ethernet/cavium/liquidio/lio_core.c | 232 ++++------------
drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 256 ++++++-----------
drivers/net/ethernet/cavium/liquidio/lio_main.c | 307 +++++++++------------
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 194 ++++++-------
drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c | 47 ++--
.../net/ethernet/cavium/liquidio/octeon_config.h | 3 +-
drivers/net/ethernet/cavium/liquidio/octeon_iq.h | 12 +-
drivers/net/ethernet/cavium/liquidio/octeon_main.h | 94 ++++---
.../net/ethernet/cavium/liquidio/octeon_network.h | 16 --
drivers/net/ethernet/cavium/liquidio/octeon_nic.c | 59 ++--
drivers/net/ethernet/cavium/liquidio/octeon_nic.h | 9 +-
.../net/ethernet/cavium/liquidio/request_manager.c | 114 ++++++--
.../ethernet/cavium/liquidio/response_manager.c | 82 +++++-
.../ethernet/cavium/liquidio/response_manager.h | 4 +-
14 files changed, 627 insertions(+), 802 deletions(-)
--
2.9.0
^ permalink raw reply
* [PATCH net-next 3/4] liquidio: change octnic_ctrl_pkt to do synchronous soft commands
From: Felix Manlunas @ 2018-08-29 1:51 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, weilin.chang
In-Reply-To: <20180829015058.GA7898@felix-thinkpad.cavium.com>
1. Change struct octnic_ctrl_pkt to support synchronous operation.
2. Change code which use structure octnic_ctrl_pkt to send sc's
synchronously.
Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/lio_core.c | 15 ++---
drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 21 ++++---
drivers/net/ethernet/cavium/liquidio/lio_main.c | 69 ++++++++++++++--------
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 38 ++++--------
drivers/net/ethernet/cavium/liquidio/octeon_nic.c | 56 ++++++++----------
drivers/net/ethernet/cavium/liquidio/octeon_nic.h | 9 +--
6 files changed, 98 insertions(+), 110 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 822ce0f..27b3655 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -198,14 +198,15 @@ int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1)
nctrl.ncmd.s.cmd = cmd;
nctrl.ncmd.s.param1 = param1;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "Feature change failed in core (ret: 0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
@@ -285,15 +286,7 @@ void liquidio_link_ctrl_cmd_completion(void *nctrl_ptr)
struct octeon_device *oct = lio->oct_dev;
u8 *mac;
- if (nctrl->completion && nctrl->response_code) {
- /* Signal whoever is interested that the response code from the
- * firmware has arrived.
- */
- WRITE_ONCE(*nctrl->response_code, nctrl->status);
- complete(nctrl->completion);
- }
-
- if (nctrl->status)
+ if (nctrl->sc_status)
return;
switch (nctrl->ncmd.s.cmd) {
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 8e05afd..d374c44 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -472,12 +472,11 @@ lio_send_queue_count_update(struct net_device *netdev, uint32_t num_queues)
nctrl.ncmd.s.param1 = num_queues;
nctrl.ncmd.s.param2 = num_queues;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "Failed to send Queue reset command (ret: 0x%x)\n",
ret);
return -1;
@@ -708,13 +707,13 @@ static int octnet_gpio_access(struct net_device *netdev, int addr, int val)
nctrl.ncmd.s.param1 = addr;
nctrl.ncmd.s.param2 = val;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
- dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n");
+ if (ret) {
+ dev_err(&oct->pci_dev->dev,
+ "Failed to configure gpio value, ret=%d\n", ret);
return -EINVAL;
}
@@ -734,13 +733,13 @@ static int octnet_id_active(struct net_device *netdev, int val)
nctrl.ncmd.s.cmd = OCTNET_CMD_ID_ACTIVE;
nctrl.ncmd.s.param1 = val;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
- dev_err(&oct->pci_dev->dev, "Failed to configure gpio value\n");
+ if (ret) {
+ dev_err(&oct->pci_dev->dev,
+ "Failed to configure gpio value, ret=%d\n", ret);
return -EINVAL;
}
@@ -1412,7 +1411,6 @@ lio_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
nctrl.ncmd.u64 = 0;
nctrl.ncmd.s.cmd = OCTNET_CMD_SET_FLOW_CTL;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
@@ -1433,8 +1431,9 @@ lio_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause)
}
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
- dev_err(&oct->pci_dev->dev, "Failed to set pause parameter\n");
+ if (ret) {
+ dev_err(&oct->pci_dev->dev,
+ "Failed to set pause parameter, ret=%d\n", ret);
return -EINVAL;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8ddc191..9c5a53d 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2039,10 +2039,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
/* Apparently, any activity in this call from the kernel has to
* be atomic. So we won't wait for response.
*/
- nctrl.wait_time = 0;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n",
ret);
}
@@ -2071,8 +2070,6 @@ static int liquidio_set_mac(struct net_device *netdev, void *p)
nctrl.ncmd.s.more = 1;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
nctrl.netpndev = (u64)netdev;
- nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
- nctrl.wait_time = 100;
nctrl.udd[0] = 0;
/* The MAC Address is presented in network byte order. */
@@ -2083,6 +2080,14 @@ static int liquidio_set_mac(struct net_device *netdev, void *p)
dev_err(&oct->pci_dev->dev, "MAC Address change failed\n");
return -ENOMEM;
}
+
+ if (nctrl.sc_status) {
+ dev_err(&oct->pci_dev->dev,
+ "%s: MAC Address change failed. sc return=%x\n",
+ __func__, nctrl.sc_status);
+ return -EIO;
+ }
+
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
memcpy(((u8 *)&lio->linfo.hw_addr) + 2, addr->sa_data, ETH_ALEN);
@@ -2623,14 +2628,15 @@ static int liquidio_vlan_rx_add_vid(struct net_device *netdev,
nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER;
nctrl.ncmd.s.param1 = vid;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
@@ -2651,14 +2657,15 @@ static int liquidio_vlan_rx_kill_vid(struct net_device *netdev,
nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER;
nctrl.ncmd.s.param1 = vid;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
@@ -2684,15 +2691,16 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
nctrl.ncmd.s.cmd = command;
nctrl.ncmd.s.param1 = rx_cmd;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev,
"DEVFLAGS RXCSUM change failed in core(ret:0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
@@ -2720,15 +2728,16 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
nctrl.ncmd.s.more = vxlan_cmd_bit;
nctrl.ncmd.s.param1 = vxlan_port;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev,
"VxLAN port add/delete failed in core (ret:0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
@@ -2851,6 +2860,7 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
struct octnic_ctrl_pkt nctrl;
+ int ret = 0;
if (!is_valid_ether_addr(mac))
return -EINVAL;
@@ -2864,12 +2874,13 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
nctrl.ncmd.s.cmd = OCTNET_CMD_CHANGE_MACADDR;
/* vfidx is 0 based, but vf_num (param1) is 1 based */
nctrl.ncmd.s.param1 = vfidx + 1;
- nctrl.ncmd.s.param2 = (is_admin_assigned ? 1 : 0);
nctrl.ncmd.s.more = 1;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
nctrl.netpndev = (u64)netdev;
- nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
- nctrl.wait_time = LIO_CMD_WAIT_TM;
+ if (is_admin_assigned) {
+ nctrl.ncmd.s.param2 = true;
+ nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
+ }
nctrl.udd[0] = 0;
/* The MAC Address is presented in network byte order. */
@@ -2877,9 +2888,11 @@ static int __liquidio_set_vf_mac(struct net_device *netdev, int vfidx,
oct->sriov_info.vf_macaddr[vfidx] = nctrl.udd[0];
- octnet_send_nic_ctrl_pkt(oct, &nctrl);
+ ret = octnet_send_nic_ctrl_pkt(oct, &nctrl);
+ if (ret > 0)
+ ret = -EIO;
- return 0;
+ return ret;
}
static int liquidio_set_vf_mac(struct net_device *netdev, int vfidx, u8 *mac)
@@ -2905,6 +2918,7 @@ static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx,
struct octeon_device *oct = lio->oct_dev;
struct octnic_ctrl_pkt nctrl;
u16 vlantci;
+ int ret = 0;
if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced)
return -EINVAL;
@@ -2936,13 +2950,17 @@ static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx,
nctrl.ncmd.s.more = 0;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
nctrl.cb_fn = NULL;
- nctrl.wait_time = LIO_CMD_WAIT_TM;
- octnet_send_nic_ctrl_pkt(oct, &nctrl);
+ ret = octnet_send_nic_ctrl_pkt(oct, &nctrl);
+ if (ret) {
+ if (ret > 0)
+ ret = -EIO;
+ return ret;
+ }
oct->sriov_info.vf_vlantci[vfidx] = vlantci;
- return 0;
+ return ret;
}
static int liquidio_get_vf_config(struct net_device *netdev, int vfidx,
@@ -3063,6 +3081,7 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
struct octnic_ctrl_pkt nctrl;
+ int ret = 0;
if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced)
return -EINVAL;
@@ -3078,13 +3097,15 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
nctrl.ncmd.s.more = 0;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
nctrl.cb_fn = NULL;
- nctrl.wait_time = LIO_CMD_WAIT_TM;
- octnet_send_nic_ctrl_pkt(oct, &nctrl);
+ ret = octnet_send_nic_ctrl_pkt(oct, &nctrl);
- oct->sriov_info.vf_linkstate[vfidx] = linkstate;
+ if (!ret)
+ oct->sriov_info.vf_linkstate[vfidx] = linkstate;
+ else if (ret > 0)
+ ret = -EIO;
- return 0;
+ return ret;
}
static int
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 59c2dd9..f6bed6e 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -1119,10 +1119,9 @@ static void liquidio_set_mcast_list(struct net_device *netdev)
/* Apparently, any activity in this call from the kernel has to
* be atomic. So we won't wait for response.
*/
- nctrl.wait_time = 0;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "DEVFLAGS change failed in core (ret: 0x%x)\n",
ret);
}
@@ -1159,8 +1158,6 @@ static int liquidio_set_mac(struct net_device *netdev, void *p)
nctrl.ncmd.s.more = 1;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
nctrl.netpndev = (u64)netdev;
- nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
- nctrl.wait_time = 100;
nctrl.udd[0] = 0;
/* The MAC Address is presented in network byte order. */
@@ -1171,6 +1168,7 @@ static int liquidio_set_mac(struct net_device *netdev, void *p)
dev_err(&oct->pci_dev->dev, "MAC Address change failed\n");
return -ENOMEM;
}
+
memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
ether_addr_copy(((u8 *)&lio->linfo.hw_addr) + 2, addr->sa_data);
@@ -1664,8 +1662,6 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev,
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
struct octnic_ctrl_pkt nctrl;
- struct completion compl;
- u16 response_code;
int ret = 0;
memset(&nctrl, 0, sizeof(struct octnic_ctrl_pkt));
@@ -1674,26 +1670,15 @@ liquidio_vlan_rx_add_vid(struct net_device *netdev,
nctrl.ncmd.s.cmd = OCTNET_CMD_ADD_VLAN_FILTER;
nctrl.ncmd.s.param1 = vid;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
- init_completion(&compl);
- nctrl.completion = &compl;
- nctrl.response_code = &response_code;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
ret);
- return -EIO;
- }
-
- if (!wait_for_completion_timeout(&compl,
- msecs_to_jiffies(nctrl.wait_time)))
- return -EPERM;
-
- if (READ_ONCE(response_code))
return -EPERM;
+ }
return 0;
}
@@ -1713,14 +1698,15 @@ liquidio_vlan_rx_kill_vid(struct net_device *netdev,
nctrl.ncmd.s.cmd = OCTNET_CMD_DEL_VLAN_FILTER;
nctrl.ncmd.s.param1 = vid;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
@@ -1746,14 +1732,15 @@ static int liquidio_set_rxcsum_command(struct net_device *netdev, int command,
nctrl.ncmd.s.cmd = command;
nctrl.ncmd.s.param1 = rx_cmd;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev, "DEVFLAGS RXCSUM change failed in core (ret:0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
@@ -1781,15 +1768,16 @@ static int liquidio_vxlan_port_command(struct net_device *netdev, int command,
nctrl.ncmd.s.more = vxlan_cmd_bit;
nctrl.ncmd.s.param1 = vxlan_port;
nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
- nctrl.wait_time = 100;
nctrl.netpndev = (u64)netdev;
nctrl.cb_fn = liquidio_link_ctrl_cmd_completion;
ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
- if (ret < 0) {
+ if (ret) {
dev_err(&oct->pci_dev->dev,
"DEVFLAGS VxLAN port add/delete failed in core (ret : 0x%x)\n",
ret);
+ if (ret > 0)
+ ret = -EIO;
}
return ret;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index b7364bb..676fe0b 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -91,29 +91,6 @@ int octnet_send_nic_data_pkt(struct octeon_device *oct,
ndata->reqtype);
}
-static void octnet_link_ctrl_callback(struct octeon_device *oct,
- u32 status,
- void *sc_ptr)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)sc_ptr;
- struct octnic_ctrl_pkt *nctrl;
-
- nctrl = (struct octnic_ctrl_pkt *)sc->ctxptr;
-
- /* Call the callback function if status is zero (meaning OK) or status
- * contains a firmware status code bigger than zero (meaning the
- * firmware is reporting an error).
- * If no response was expected, status is OK if the command was posted
- * successfully.
- */
- if ((!status || status > FIRMWARE_STATUS_CODE(0)) && nctrl->cb_fn) {
- nctrl->status = status;
- nctrl->cb_fn(nctrl);
- }
-
- octeon_free_soft_command(oct, sc);
-}
-
static inline struct octeon_soft_command
*octnic_alloc_ctrl_pkt_sc(struct octeon_device *oct,
struct octnic_ctrl_pkt *nctrl)
@@ -126,17 +103,14 @@ static inline struct octeon_soft_command
uddsize = (u32)(nctrl->ncmd.s.more * 8);
datasize = OCTNET_CMD_SIZE + uddsize;
- rdatasize = (nctrl->wait_time) ? 16 : 0;
+ rdatasize = 16;
sc = (struct octeon_soft_command *)
- octeon_alloc_soft_command(oct, datasize, rdatasize,
- sizeof(struct octnic_ctrl_pkt));
+ octeon_alloc_soft_command(oct, datasize, rdatasize, 0);
if (!sc)
return NULL;
- memcpy(sc->ctxptr, nctrl, sizeof(struct octnic_ctrl_pkt));
-
data = (u8 *)sc->virtdptr;
memcpy(data, &nctrl->ncmd, OCTNET_CMD_SIZE);
@@ -153,9 +127,8 @@ static inline struct octeon_soft_command
octeon_prepare_soft_command(oct, sc, OPCODE_NIC, OPCODE_NIC_CMD,
0, 0, 0);
- sc->callback = octnet_link_ctrl_callback;
- sc->callback_arg = sc;
- sc->wait_time = nctrl->wait_time;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
return sc;
}
@@ -198,5 +171,26 @@ octnet_send_nic_ctrl_pkt(struct octeon_device *oct,
}
spin_unlock_bh(&oct->cmd_resp_wqlock);
+
+ switch (nctrl->ncmd.s.cmd) {
+ /* caller holds lock, can not sleep */
+ case OCTNET_CMD_CHANGE_DEVFLAGS:
+ case OCTNET_CMD_SET_MULTI_LIST:
+ case OCTNET_CMD_SET_UC_LIST:
+ WRITE_ONCE(sc->caller_is_done, true);
+ return retval;
+ }
+
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
+ return (retval);
+
+ nctrl->sc_status = sc->sc_status;
+ retval = nctrl->sc_status;
+ if (nctrl->cb_fn)
+ nctrl->cb_fn(nctrl);
+
+ WRITE_ONCE(sc->caller_is_done, true);
+
return retval;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
index de4130d..87dd6f8 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.h
@@ -52,20 +52,13 @@ struct octnic_ctrl_pkt {
/** Input queue to use to send this command. */
u64 iq_no;
- /** Time to wait for Octeon software to respond to this control command.
- * If wait_time is 0, OSI assumes no response is expected.
- */
- size_t wait_time;
-
/** The network device that issued the control command. */
u64 netpndev;
/** Callback function called when the command has been fetched */
octnic_ctrl_pkt_cb_fn_t cb_fn;
- u32 status;
- u16 *response_code;
- struct completion *completion;
+ u32 sc_status;
};
#define MAX_UDD_SIZE(nctrl) (sizeof((nctrl)->udd))
--
2.9.0
^ permalink raw reply related
* [PATCH net-next 4/4] liquidio: remove obsolete functions and data structures
From: Felix Manlunas @ 2018-08-29 1:51 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, weilin.chang
In-Reply-To: <20180829015058.GA7898@felix-thinkpad.cavium.com>
1. Remove unused functions and data structures.
2. Change the sending of the remaining soft commands to synchronous.
Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/lio_core.c | 83 +-------
drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 235 ++++++---------------
drivers/net/ethernet/cavium/liquidio/lio_main.c | 165 +++++----------
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 122 ++++-------
drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c | 5 +-
.../net/ethernet/cavium/liquidio/octeon_config.h | 1 +
drivers/net/ethernet/cavium/liquidio/octeon_iq.h | 3 -
drivers/net/ethernet/cavium/liquidio/octeon_main.h | 42 ----
.../net/ethernet/cavium/liquidio/octeon_network.h | 10 -
9 files changed, 176 insertions(+), 490 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 27b3655..30b4a60 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -32,38 +32,6 @@
#define OCTNIC_MAX_SG MAX_SKB_FRAGS
/**
- * \brief Callback for getting interface configuration
- * @param status status of request
- * @param buf pointer to resp structure
- */
-void lio_if_cfg_callback(struct octeon_device *oct,
- u32 status __attribute__((unused)), void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
- struct liquidio_if_cfg_context *ctx;
- struct liquidio_if_cfg_resp *resp;
-
- resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
-
- oct = lio_get_device(ctx->octeon_id);
- if (resp->status)
- dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n",
- CVM_CAST64(resp->status));
- WRITE_ONCE(ctx->cond, 1);
-
- snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s",
- resp->cfg_info.liquidio_firmware_version);
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
-/**
* \brief Delete gather lists
* @param lio per-network private data
*/
@@ -1211,30 +1179,6 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs)
return 0;
}
-static void liquidio_change_mtu_completion(struct octeon_device *oct,
- u32 status, void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
- struct liquidio_if_cfg_context *ctx;
-
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
-
- if (status) {
- dev_err(&oct->pci_dev->dev, "MTU change failed. Status: %llx\n",
- CVM_CAST64(status));
- WRITE_ONCE(ctx->cond, LIO_CHANGE_MTU_FAIL);
- } else {
- WRITE_ONCE(ctx->cond, LIO_CHANGE_MTU_SUCCESS);
- }
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
/**
* \brief Net device change_mtu
* @param netdev network device
@@ -1243,22 +1187,17 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
{
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct = lio->oct_dev;
- struct liquidio_if_cfg_context *ctx;
struct octeon_soft_command *sc;
union octnet_cmd *ncmd;
- int ctx_size;
int ret = 0;
- ctx_size = sizeof(struct liquidio_if_cfg_context);
sc = (struct octeon_soft_command *)
- octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, 16, ctx_size);
+ octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, 16, 0);
ncmd = (union octnet_cmd *)sc->virtdptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(oct);
- init_waitqueue_head(&ctx->wc);
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
ncmd->u64 = 0;
ncmd->s.cmd = OCTNET_CMD_CHANGE_MTU;
@@ -1271,28 +1210,28 @@ int liquidio_change_mtu(struct net_device *netdev, int new_mtu)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_CMD, 0, 0, 0);
- sc->callback = liquidio_change_mtu_completion;
- sc->callback_arg = sc;
- sc->wait_time = 100;
-
ret = octeon_send_soft_command(oct, sc);
if (ret == IQ_SEND_FAILED) {
netif_info(lio, rx_err, lio->netdev, "Failed to change MTU\n");
+ octeon_free_soft_command(oct, sc);
return -EINVAL;
}
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR ||
- ctx->cond == LIO_CHANGE_MTU_FAIL) {
- octeon_free_soft_command(oct, sc);
+ ret = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (ret)
+ return ret;
+
+ if (sc->sc_status) {
+ WRITE_ONCE(sc->caller_is_done, true);
return -EINVAL;
}
netdev->mtu = new_mtu;
lio->mtu = new_mtu;
- octeon_free_soft_command(oct, sc);
+ WRITE_ONCE(sc->caller_is_done, true);
return 0;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index d374c44..46d8379 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -33,25 +33,12 @@
static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs);
-struct oct_intrmod_context {
- int octeon_id;
- wait_queue_head_t wc;
- int cond;
- int status;
-};
-
struct oct_intrmod_resp {
u64 rh;
struct oct_intrmod_cfg intrmod;
u64 status;
};
-struct oct_mdio_cmd_context {
- int octeon_id;
- wait_queue_head_t wc;
- int cond;
-};
-
struct oct_mdio_cmd_resp {
u64 rh;
struct oct_mdio_cmd resp;
@@ -746,28 +733,6 @@ static int octnet_id_active(struct net_device *netdev, int val)
return 0;
}
-/* Callback for when mdio command response arrives
- */
-static void octnet_mdio_resp_callback(struct octeon_device *oct,
- u32 status,
- void *buf)
-{
- struct oct_mdio_cmd_context *mdio_cmd_ctx;
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
-
- mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr;
-
- oct = lio_get_device(mdio_cmd_ctx->octeon_id);
- if (status) {
- dev_err(&oct->pci_dev->dev, "MIDO instruction failed. Status: %llx\n",
- CVM_CAST64(status));
- WRITE_ONCE(mdio_cmd_ctx->cond, -1);
- } else {
- WRITE_ONCE(mdio_cmd_ctx->cond, 1);
- }
- wake_up_interruptible(&mdio_cmd_ctx->wc);
-}
-
/* This routine provides PHY access routines for
* mdio clause45 .
*/
@@ -777,25 +742,20 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value)
struct octeon_device *oct_dev = lio->oct_dev;
struct octeon_soft_command *sc;
struct oct_mdio_cmd_resp *mdio_cmd_rsp;
- struct oct_mdio_cmd_context *mdio_cmd_ctx;
struct oct_mdio_cmd *mdio_cmd;
int retval = 0;
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct_dev,
sizeof(struct oct_mdio_cmd),
- sizeof(struct oct_mdio_cmd_resp),
- sizeof(struct oct_mdio_cmd_context));
+ sizeof(struct oct_mdio_cmd_resp), 0);
if (!sc)
return -ENOMEM;
- mdio_cmd_ctx = (struct oct_mdio_cmd_context *)sc->ctxptr;
mdio_cmd_rsp = (struct oct_mdio_cmd_resp *)sc->virtrptr;
mdio_cmd = (struct oct_mdio_cmd *)sc->virtdptr;
- WRITE_ONCE(mdio_cmd_ctx->cond, 0);
- mdio_cmd_ctx->octeon_id = lio_get_device_id(oct_dev);
mdio_cmd->op = op;
mdio_cmd->mdio_addr = loc;
if (op)
@@ -807,42 +767,40 @@ octnet_mdio45_access(struct lio *lio, int op, int loc, int *value)
octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, OPCODE_NIC_MDIO45,
0, 0, 0);
- sc->wait_time = 1000;
- sc->callback = octnet_mdio_resp_callback;
- sc->callback_arg = sc;
-
- init_waitqueue_head(&mdio_cmd_ctx->wc);
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct_dev, sc);
-
if (retval == IQ_SEND_FAILED) {
dev_err(&oct_dev->pci_dev->dev,
"octnet_mdio45_access instruction failed status: %x\n",
retval);
- retval = -EBUSY;
+ octeon_free_soft_command(oct_dev, sc);
+ return -EBUSY;
} else {
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived
*/
- sleep_cond(&mdio_cmd_ctx->wc, &mdio_cmd_ctx->cond);
+ retval = wait_for_sc_completion_timeout(oct_dev, sc, 0);
+ if (retval)
+ return retval;
+
retval = mdio_cmd_rsp->status;
if (retval) {
- dev_err(&oct_dev->pci_dev->dev, "octnet mdio45 access failed\n");
- retval = -EBUSY;
- } else {
- octeon_swap_8B_data((u64 *)(&mdio_cmd_rsp->resp),
- sizeof(struct oct_mdio_cmd) / 8);
-
- if (READ_ONCE(mdio_cmd_ctx->cond) == 1) {
- if (!op)
- *value = mdio_cmd_rsp->resp.value1;
- } else {
- retval = -EINVAL;
- }
+ dev_err(&oct_dev->pci_dev->dev,
+ "octnet mdio45 access failed: %x\n", retval);
+ WRITE_ONCE(sc->caller_is_done, true);
+ return -EBUSY;
}
- }
- octeon_free_soft_command(oct_dev, sc);
+ octeon_swap_8B_data((u64 *)(&mdio_cmd_rsp->resp),
+ sizeof(struct oct_mdio_cmd) / 8);
+
+ if (!op)
+ *value = mdio_cmd_rsp->resp.value1;
+
+ WRITE_ONCE(sc->caller_is_done, true);
+ }
return retval;
}
@@ -1006,8 +964,7 @@ lio_ethtool_get_ringparam(struct net_device *netdev,
static int lio_23xx_reconfigure_queue_count(struct lio *lio)
{
struct octeon_device *oct = lio->oct_dev;
- struct liquidio_if_cfg_context *ctx;
- u32 resp_size, ctx_size, data_size;
+ u32 resp_size, data_size;
struct liquidio_if_cfg_resp *resp;
struct octeon_soft_command *sc;
union oct_nic_if_cfg if_cfg;
@@ -1017,11 +974,10 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio)
int j;
resp_size = sizeof(struct liquidio_if_cfg_resp);
- ctx_size = sizeof(struct liquidio_if_cfg_context);
data_size = sizeof(struct lio_version);
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct, data_size,
- resp_size, ctx_size);
+ resp_size, 0);
if (!sc) {
dev_err(&oct->pci_dev->dev, "%s: Failed to allocate soft command\n",
__func__);
@@ -1029,7 +985,6 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio)
}
resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
vdata = (struct lio_version *)sc->virtdptr;
vdata->major = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MAJOR_VERSION);
@@ -1037,9 +992,6 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio)
vdata->micro = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MICRO_VERSION);
ifidx_or_pfnum = oct->pf_num;
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(oct);
- init_waitqueue_head(&ctx->wc);
if_cfg.u64 = 0;
if_cfg.s.num_iqueues = oct->sriov_info.num_pf_rings;
@@ -1051,27 +1003,29 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_QCOUNT_UPDATE, 0,
if_cfg.u64, 0);
- sc->callback = lio_if_cfg_callback;
- sc->callback_arg = sc;
- sc->wait_time = LIO_IFCFG_WAIT_TIME;
+
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct, sc);
if (retval == IQ_SEND_FAILED) {
dev_err(&oct->pci_dev->dev,
- "iq/oq config failed status: %x\n",
+ "Sending iq/oq config failed status: %x\n",
retval);
- goto qcount_update_fail;
+ octeon_free_soft_command(oct, sc);
+ return -EIO;
}
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
- dev_err(&oct->pci_dev->dev, "Wait interrupted\n");
- return -1;
- }
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
+ return retval;
retval = resp->status;
if (retval) {
- dev_err(&oct->pci_dev->dev, "iq/oq config failed\n");
- goto qcount_update_fail;
+ dev_err(&oct->pci_dev->dev,
+ "iq/oq config failed: %x\n", retval);
+ WRITE_ONCE(sc->caller_is_done, true);
+ return -1;
}
octeon_swap_8B_data((u64 *)(&resp->cfg_info),
@@ -1096,16 +1050,12 @@ static int lio_23xx_reconfigure_queue_count(struct lio *lio)
lio->txq = lio->linfo.txpciq[0].s.q_no;
lio->rxq = lio->linfo.rxpciq[0].s.q_no;
- octeon_free_soft_command(oct, sc);
dev_info(&oct->pci_dev->dev, "Queue count updated to %d\n",
lio->linfo.num_rxpciq);
- return 0;
-
-qcount_update_fail:
- octeon_free_soft_command(oct, sc);
+ WRITE_ONCE(sc->caller_is_done, true);
- return -1;
+ return 0;
}
static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs)
@@ -2012,34 +1962,11 @@ static int lio_vf_get_sset_count(struct net_device *netdev, int sset)
}
}
-/* Callback function for intrmod */
-static void octnet_intrmod_callback(struct octeon_device *oct_dev,
- u32 status,
- void *ptr)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
- struct oct_intrmod_context *ctx;
-
- ctx = (struct oct_intrmod_context *)sc->ctxptr;
-
- ctx->status = status;
-
- WRITE_ONCE(ctx->cond, 1);
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
/* get interrupt moderation parameters */
static int octnet_get_intrmod_cfg(struct lio *lio,
struct oct_intrmod_cfg *intr_cfg)
{
struct octeon_soft_command *sc;
- struct oct_intrmod_context *ctx;
struct oct_intrmod_resp *resp;
int retval;
struct octeon_device *oct_dev = lio->oct_dev;
@@ -2048,8 +1975,7 @@ static int octnet_get_intrmod_cfg(struct lio *lio,
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct_dev,
0,
- sizeof(struct oct_intrmod_resp),
- sizeof(struct oct_intrmod_context));
+ sizeof(struct oct_intrmod_resp), 0);
if (!sc)
return -ENOMEM;
@@ -2057,20 +1983,13 @@ static int octnet_get_intrmod_cfg(struct lio *lio,
resp = (struct oct_intrmod_resp *)sc->virtrptr;
memset(resp, 0, sizeof(struct oct_intrmod_resp));
- ctx = (struct oct_intrmod_context *)sc->ctxptr;
- memset(ctx, 0, sizeof(struct oct_intrmod_context));
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(oct_dev);
- init_waitqueue_head(&ctx->wc);
-
sc->iq_no = lio->linfo.txpciq[0].s.q_no;
octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
OPCODE_NIC_INTRMOD_PARAMS, 0, 0, 0);
- sc->callback = octnet_intrmod_callback;
- sc->callback_arg = sc;
- sc->wait_time = 1000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct_dev, sc);
if (retval == IQ_SEND_FAILED) {
@@ -2081,32 +2000,23 @@ static int octnet_get_intrmod_cfg(struct lio *lio,
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
- dev_err(&oct_dev->pci_dev->dev, "Wait interrupted\n");
- goto intrmod_info_wait_intr;
- }
+ retval = wait_for_sc_completion_timeout(oct_dev, sc, 0);
+ if (retval)
+ return -ENODEV;
- retval = ctx->status || resp->status;
- if (retval) {
+ if (resp->status) {
dev_err(&oct_dev->pci_dev->dev,
"Get interrupt moderation parameters failed\n");
- goto intrmod_info_wait_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ return -ENODEV;
}
octeon_swap_8B_data((u64 *)&resp->intrmod,
(sizeof(struct oct_intrmod_cfg)) / 8);
memcpy(intr_cfg, &resp->intrmod, sizeof(struct oct_intrmod_cfg));
- octeon_free_soft_command(oct_dev, sc);
+ WRITE_ONCE(sc->caller_is_done, true);
return 0;
-
-intrmod_info_wait_fail:
-
- octeon_free_soft_command(oct_dev, sc);
-
-intrmod_info_wait_intr:
-
- return -ENODEV;
}
/* Configure interrupt moderation parameters */
@@ -2114,7 +2024,6 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
struct oct_intrmod_cfg *intr_cfg)
{
struct octeon_soft_command *sc;
- struct oct_intrmod_context *ctx;
struct oct_intrmod_cfg *cfg;
int retval;
struct octeon_device *oct_dev = lio->oct_dev;
@@ -2123,18 +2032,11 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct_dev,
sizeof(struct oct_intrmod_cfg),
- 0,
- sizeof(struct oct_intrmod_context));
+ 16, 0);
if (!sc)
return -ENOMEM;
- ctx = (struct oct_intrmod_context *)sc->ctxptr;
-
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(oct_dev);
- init_waitqueue_head(&ctx->wc);
-
cfg = (struct oct_intrmod_cfg *)sc->virtdptr;
memcpy(cfg, intr_cfg, sizeof(struct oct_intrmod_cfg));
@@ -2145,9 +2047,8 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
OPCODE_NIC_INTRMOD_CFG, 0, 0, 0);
- sc->callback = octnet_intrmod_callback;
- sc->callback_arg = sc;
- sc->wait_time = 1000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct_dev, sc);
if (retval == IQ_SEND_FAILED) {
@@ -2158,26 +2059,24 @@ static int octnet_set_intrmod_cfg(struct lio *lio,
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) != -EINTR) {
- retval = ctx->status;
- if (retval)
- dev_err(&oct_dev->pci_dev->dev,
- "intrmod config failed. Status: %llx\n",
- CVM_CAST64(retval));
- else
- dev_info(&oct_dev->pci_dev->dev,
- "Rx-Adaptive Interrupt moderation %s\n",
- (intr_cfg->rx_enable) ?
- "enabled" : "disabled");
-
- octeon_free_soft_command(oct_dev, sc);
-
- return ((retval) ? -ENODEV : 0);
+ retval = wait_for_sc_completion_timeout(oct_dev, sc, 0);
+ if (retval)
+ return retval;
+
+ retval = sc->sc_status;
+ if (retval == 0) {
+ dev_info(&oct_dev->pci_dev->dev,
+ "Rx-Adaptive Interrupt moderation %s\n",
+ (intr_cfg->rx_enable) ?
+ "enabled" : "disabled");
+ WRITE_ONCE(sc->caller_is_done, true);
+ return 0;
}
- dev_err(&oct_dev->pci_dev->dev, "iq/oq config failed\n");
-
- return -EINTR;
+ dev_err(&oct_dev->pci_dev->dev,
+ "intrmod config failed. Status: %x\n", retval);
+ WRITE_ONCE(sc->caller_is_done, true);
+ return -ENODEV;
}
static int lio_get_intr_coalesce(struct net_device *netdev,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 9c5a53d..ed5fc6e 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -99,14 +99,6 @@ struct lio_trusted_vf_ctx {
int status;
};
-struct liquidio_rx_ctl_context {
- int octeon_id;
-
- wait_queue_head_t wc;
-
- int cond;
-};
-
struct oct_link_status_resp {
u64 rh;
struct oct_link_info link_info;
@@ -642,26 +634,6 @@ static inline void update_link_status(struct net_device *netdev,
}
/**
- * lio_sync_octeon_time_cb - callback that is invoked when soft command
- * sent by lio_sync_octeon_time() has completed successfully or failed
- *
- * @oct - octeon device structure
- * @status - indicates success or failure
- * @buf - pointer to the command that was sent to firmware
- **/
-static void lio_sync_octeon_time_cb(struct octeon_device *oct,
- u32 status, void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
-
- if (status)
- dev_err(&oct->pci_dev->dev,
- "Failed to sync time to octeon; error=%d\n", status);
-
- octeon_free_soft_command(oct, sc);
-}
-
-/**
* lio_sync_octeon_time - send latest localtime to octeon firmware so that
* firmware will correct it's time, in case there is a time skew
*
@@ -677,7 +649,7 @@ static void lio_sync_octeon_time(struct work_struct *work)
struct lio_time *lt;
int ret;
- sc = octeon_alloc_soft_command(oct, sizeof(struct lio_time), 0, 0);
+ sc = octeon_alloc_soft_command(oct, sizeof(struct lio_time), 16, 0);
if (!sc) {
dev_err(&oct->pci_dev->dev,
"Failed to sync time to octeon: soft command allocation failed\n");
@@ -696,15 +668,16 @@ static void lio_sync_octeon_time(struct work_struct *work)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_SYNC_OCTEON_TIME, 0, 0, 0);
- sc->callback = lio_sync_octeon_time_cb;
- sc->callback_arg = sc;
- sc->wait_time = 1000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
ret = octeon_send_soft_command(oct, sc);
if (ret == IQ_SEND_FAILED) {
dev_err(&oct->pci_dev->dev,
"Failed to sync time to octeon: failed to send soft command\n");
octeon_free_soft_command(oct, sc);
+ } else {
+ WRITE_ONCE(sc->caller_is_done, true);
}
queue_delayed_work(lio->sync_octeon_time_wq.wq,
@@ -1203,34 +1176,6 @@ static void octeon_destroy_resources(struct octeon_device *oct)
}
/**
- * \brief Callback for rx ctrl
- * @param status status of request
- * @param buf pointer to resp structure
- */
-static void rx_ctl_callback(struct octeon_device *oct,
- u32 status,
- void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
- struct liquidio_rx_ctl_context *ctx;
-
- ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr;
-
- oct = lio_get_device(ctx->octeon_id);
- if (status)
- dev_err(&oct->pci_dev->dev, "rx ctl instruction failed. Status: %llx\n",
- CVM_CAST64(status));
- WRITE_ONCE(ctx->cond, 1);
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
-/**
* \brief Send Rx control command
* @param lio per-network private data
* @param start_stop whether to start or stop
@@ -1238,9 +1183,7 @@ static void rx_ctl_callback(struct octeon_device *oct,
static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
{
struct octeon_soft_command *sc;
- struct liquidio_rx_ctl_context *ctx;
union octnet_cmd *ncmd;
- int ctx_size = sizeof(struct liquidio_rx_ctl_context);
struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
int retval;
@@ -1249,14 +1192,9 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
- 16, ctx_size);
+ 16, 0);
ncmd = (union octnet_cmd *)sc->virtdptr;
- ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr;
-
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(oct);
- init_waitqueue_head(&ctx->wc);
ncmd->u64 = 0;
ncmd->s.cmd = OCTNET_CMD_RX_CTL;
@@ -1269,23 +1207,25 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_CMD, 0, 0, 0);
- sc->callback = rx_ctl_callback;
- sc->callback_arg = sc;
- sc->wait_time = 5000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct, sc);
if (retval == IQ_SEND_FAILED) {
netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n");
+ octeon_free_soft_command(oct, sc);
+ return;
} else {
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR)
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
return;
+
oct->props[lio->ifidx].rx_on = start_stop;
+ WRITE_ONCE(sc->caller_is_done, true);
}
-
- octeon_free_soft_command(oct, sc);
}
/**
@@ -3336,7 +3276,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
unsigned long micro;
u32 cur_ver;
struct octeon_soft_command *sc;
- struct liquidio_if_cfg_context *ctx;
struct liquidio_if_cfg_resp *resp;
struct octdev_props *props;
int retval, num_iqueues, num_oqueues;
@@ -3344,7 +3283,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
union oct_nic_if_cfg if_cfg;
unsigned int base_queue;
unsigned int gmx_port_id;
- u32 resp_size, ctx_size, data_size;
+ u32 resp_size, data_size;
u32 ifidx_or_pfnum;
struct lio_version *vdata;
struct devlink *devlink;
@@ -3369,13 +3308,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
for (i = 0; i < octeon_dev->ifcount; i++) {
resp_size = sizeof(struct liquidio_if_cfg_resp);
- ctx_size = sizeof(struct liquidio_if_cfg_context);
data_size = sizeof(struct lio_version);
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(octeon_dev, data_size,
- resp_size, ctx_size);
+ resp_size, 0);
resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
vdata = (struct lio_version *)sc->virtdptr;
*((u64 *)vdata) = 0;
@@ -3405,9 +3342,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
dev_dbg(&octeon_dev->pci_dev->dev,
"requesting config for interface %d, iqs %d, oqs %d\n",
ifidx_or_pfnum, num_iqueues, num_oqueues);
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(octeon_dev);
- init_waitqueue_head(&ctx->wc);
if_cfg.u64 = 0;
if_cfg.s.num_iqueues = num_iqueues;
@@ -3421,9 +3355,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
OPCODE_NIC_IF_CFG, 0,
if_cfg.u64, 0);
- sc->callback = lio_if_cfg_callback;
- sc->callback_arg = sc;
- sc->wait_time = LIO_IFCFG_WAIT_TIME;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(octeon_dev, sc);
if (retval == IQ_SEND_FAILED) {
@@ -3431,22 +3364,26 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
"iq/oq config failed status: %x\n",
retval);
/* Soft instr is freed by driver in case of failure. */
- goto setup_nic_dev_fail;
+ octeon_free_soft_command(octeon_dev, sc);
+ return(-EIO);
}
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
- dev_err(&octeon_dev->pci_dev->dev, "Wait interrupted\n");
- goto setup_nic_wait_intr;
- }
+ retval = wait_for_sc_completion_timeout(octeon_dev, sc, 0);
+ if (retval)
+ return retval;
retval = resp->status;
if (retval) {
dev_err(&octeon_dev->pci_dev->dev, "iq/oq config failed\n");
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_done;
}
+ snprintf(octeon_dev->fw_info.liquidio_firmware_version,
+ 32, "%s",
+ resp->cfg_info.liquidio_firmware_version);
/* Verify f/w version (in case of 'auto' loading from flash) */
fw_ver = octeon_dev->fw_info.liquidio_firmware_version;
@@ -3456,7 +3393,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
dev_err(&octeon_dev->pci_dev->dev,
"Unmatched firmware version. Expected %s.x, got %s.\n",
LIQUIDIO_BASE_VERSION, fw_ver);
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_done;
} else if (atomic_read(octeon_dev->adapter_fw_state) ==
FW_IS_PRELOADED) {
dev_info(&octeon_dev->pci_dev->dev,
@@ -3483,7 +3421,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
"Got bad iqueues (%016llx) or oqueues (%016llx) from firmware.\n",
resp->cfg_info.iqmask,
resp->cfg_info.oqmask);
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_done;
}
if (OCTEON_CN6XXX(octeon_dev)) {
@@ -3502,7 +3441,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (!netdev) {
dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n");
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_done;
}
SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev);
@@ -3517,14 +3457,16 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (retval) {
dev_err(&octeon_dev->pci_dev->dev,
"setting real number rx failed\n");
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_free;
}
retval = netif_set_real_num_tx_queues(netdev, num_iqueues);
if (retval) {
dev_err(&octeon_dev->pci_dev->dev,
"setting real number tx failed\n");
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_free;
}
lio = GET_LIO(netdev);
@@ -3551,6 +3493,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
lio->linfo.gmxport = resp->cfg_info.linfo.gmxport;
lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64;
+ WRITE_ONCE(sc->caller_is_done, true);
+
lio->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
if (OCTEON_CN23XX_PF(octeon_dev) ||
@@ -3617,7 +3561,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
dev_err(&octeon_dev->pci_dev->dev,
"Error setting VF%d MAC address\n",
j);
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
}
@@ -3639,7 +3583,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
lio->linfo.num_txpciq,
lio->linfo.num_rxpciq)) {
dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n");
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
ifstate_set(lio, LIO_IFSTATE_DROQ_OPS);
@@ -3650,7 +3594,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (lio_setup_glists(octeon_dev, lio, num_iqueues)) {
dev_err(&octeon_dev->pci_dev->dev,
"Gather list allocation failed\n");
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
/* Register ethtool support */
@@ -3672,20 +3616,20 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
OCTNET_CMD_VERBOSE_ENABLE, 0);
if (setup_link_status_change_wq(netdev))
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
if ((octeon_dev->fw_info.app_cap_flags &
LIQUIDIO_TIME_SYNC_CAP) &&
setup_sync_octeon_time_wq(netdev))
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
if (setup_rx_oom_poll_fn(netdev))
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
/* Register the network device with the OS */
if (register_netdev(netdev)) {
dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
dev_dbg(&octeon_dev->pci_dev->dev,
@@ -3708,8 +3652,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
dev_dbg(&octeon_dev->pci_dev->dev,
"NIC ifidx:%d Setup successful\n", i);
- octeon_free_soft_command(octeon_dev, sc);
-
if (octeon_dev->subsystem_id ==
OCTEON_CN2350_25GB_SUBSYS_ID ||
octeon_dev->subsystem_id ==
@@ -3743,7 +3685,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
sizeof(struct lio_devlink_priv));
if (!devlink) {
dev_err(&octeon_dev->pci_dev->dev, "devlink alloc failed\n");
- goto setup_nic_wait_intr;
+ goto setup_nic_dev_free;
}
lio_devlink = devlink_priv(devlink);
@@ -3753,7 +3695,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
devlink_free(devlink);
dev_err(&octeon_dev->pci_dev->dev,
"devlink registration failed\n");
- goto setup_nic_wait_intr;
+ goto setup_nic_dev_free;
}
octeon_dev->devlink = devlink;
@@ -3761,17 +3703,16 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
return 0;
-setup_nic_dev_fail:
-
- octeon_free_soft_command(octeon_dev, sc);
-
-setup_nic_wait_intr:
+setup_nic_dev_free:
while (i--) {
dev_err(&octeon_dev->pci_dev->dev,
"NIC ifidx:%d Setup failed\n", i);
liquidio_destroy_nic_device(octeon_dev, i);
}
+
+setup_nic_dev_done:
+
return -ENODEV;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index f6bed6e..9c267b4c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -40,14 +40,6 @@ MODULE_PARM_DESC(debug, "NETIF_MSG debug bits");
#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
-struct liquidio_rx_ctl_context {
- int octeon_id;
-
- wait_queue_head_t wc;
-
- int cond;
-};
-
struct oct_timestamp_resp {
u64 rh;
u64 timestamp;
@@ -598,33 +590,6 @@ static void octeon_destroy_resources(struct octeon_device *oct)
}
/**
- * \brief Callback for rx ctrl
- * @param status status of request
- * @param buf pointer to resp structure
- */
-static void rx_ctl_callback(struct octeon_device *oct,
- u32 status, void *buf)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)buf;
- struct liquidio_rx_ctl_context *ctx;
-
- ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr;
-
- oct = lio_get_device(ctx->octeon_id);
- if (status)
- dev_err(&oct->pci_dev->dev, "rx ctl instruction failed. Status: %llx\n",
- CVM_CAST64(status));
- WRITE_ONCE(ctx->cond, 1);
-
- /* This barrier is required to be sure that the response has been
- * written fully before waking up the handler
- */
- wmb();
-
- wake_up_interruptible(&ctx->wc);
-}
-
-/**
* \brief Send Rx control command
* @param lio per-network private data
* @param start_stop whether to start or stop
@@ -632,8 +597,6 @@ static void rx_ctl_callback(struct octeon_device *oct,
static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
{
struct octeon_device *oct = (struct octeon_device *)lio->oct_dev;
- int ctx_size = sizeof(struct liquidio_rx_ctl_context);
- struct liquidio_rx_ctl_context *ctx;
struct octeon_soft_command *sc;
union octnet_cmd *ncmd;
int retval;
@@ -643,14 +606,9 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
- 16, ctx_size);
+ 16, 0);
ncmd = (union octnet_cmd *)sc->virtdptr;
- ctx = (struct liquidio_rx_ctl_context *)sc->ctxptr;
-
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(oct);
- init_waitqueue_head(&ctx->wc);
ncmd->u64 = 0;
ncmd->s.cmd = OCTNET_CMD_RX_CTL;
@@ -663,23 +621,24 @@ static void send_rx_ctrl_cmd(struct lio *lio, int start_stop)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_CMD, 0, 0, 0);
- sc->callback = rx_ctl_callback;
- sc->callback_arg = sc;
- sc->wait_time = 5000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct, sc);
if (retval == IQ_SEND_FAILED) {
netif_info(lio, rx_err, lio->netdev, "Failed to send RX Control message\n");
+ octeon_free_soft_command(oct, sc);
} else {
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR)
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
return;
+
oct->props[lio->ifidx].rx_on = start_stop;
+ WRITE_ONCE(sc->caller_is_done, true);
}
-
- octeon_free_soft_command(oct, sc);
}
/**
@@ -1938,8 +1897,7 @@ static int lio_nic_info(struct octeon_recv_info *recv_info, void *buf)
static int setup_nic_devices(struct octeon_device *octeon_dev)
{
int retval, num_iqueues, num_oqueues;
- struct liquidio_if_cfg_context *ctx;
- u32 resp_size, ctx_size, data_size;
+ u32 resp_size, data_size;
struct liquidio_if_cfg_resp *resp;
struct octeon_soft_command *sc;
union oct_nic_if_cfg if_cfg;
@@ -1970,13 +1928,11 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
for (i = 0; i < octeon_dev->ifcount; i++) {
resp_size = sizeof(struct liquidio_if_cfg_resp);
- ctx_size = sizeof(struct liquidio_if_cfg_context);
data_size = sizeof(struct lio_version);
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(octeon_dev, data_size,
- resp_size, ctx_size);
+ resp_size, 0);
resp = (struct liquidio_if_cfg_resp *)sc->virtrptr;
- ctx = (struct liquidio_if_cfg_context *)sc->ctxptr;
vdata = (struct lio_version *)sc->virtdptr;
*((u64 *)vdata) = 0;
@@ -1984,10 +1940,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
vdata->minor = cpu_to_be16(LIQUIDIO_BASE_MINOR_VERSION);
vdata->micro = cpu_to_be16(LIQUIDIO_BASE_MICRO_VERSION);
- WRITE_ONCE(ctx->cond, 0);
- ctx->octeon_id = lio_get_device_id(octeon_dev);
- init_waitqueue_head(&ctx->wc);
-
if_cfg.u64 = 0;
if_cfg.s.num_iqueues = octeon_dev->sriov_info.rings_per_vf;
@@ -2000,32 +1952,37 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
OPCODE_NIC_IF_CFG, 0, if_cfg.u64,
0);
- sc->callback = lio_if_cfg_callback;
- sc->callback_arg = sc;
- sc->wait_time = 5000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(octeon_dev, sc);
if (retval == IQ_SEND_FAILED) {
dev_err(&octeon_dev->pci_dev->dev,
"iq/oq config failed status: %x\n", retval);
/* Soft instr is freed by driver in case of failure. */
- goto setup_nic_dev_fail;
+ octeon_free_soft_command(octeon_dev, sc);
+ return(-EIO);
}
/* Sleep on a wait queue till the cond flag indicates that the
* response arrived or timed-out.
*/
- if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) {
- dev_err(&octeon_dev->pci_dev->dev, "Wait interrupted\n");
- goto setup_nic_wait_intr;
- }
+ retval = wait_for_sc_completion_timeout(octeon_dev, sc, 0);
+ if (retval)
+ return retval;
retval = resp->status;
if (retval) {
- dev_err(&octeon_dev->pci_dev->dev, "iq/oq config failed\n");
- goto setup_nic_dev_fail;
+ dev_err(&octeon_dev->pci_dev->dev,
+ "iq/oq config failed, retval = %d\n", retval);
+ WRITE_ONCE(sc->caller_is_done, true);
+ return -EIO;
}
+ snprintf(octeon_dev->fw_info.liquidio_firmware_version,
+ 32, "%s",
+ resp->cfg_info.liquidio_firmware_version);
+
octeon_swap_8B_data((u64 *)(&resp->cfg_info),
(sizeof(struct liquidio_if_cfg_info)) >> 3);
@@ -2036,7 +1993,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
dev_err(&octeon_dev->pci_dev->dev,
"Got bad iqueues (%016llx) or oqueues (%016llx) from firmware.\n",
resp->cfg_info.iqmask, resp->cfg_info.oqmask);
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_done;
}
dev_dbg(&octeon_dev->pci_dev->dev,
"interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d\n",
@@ -2047,7 +2005,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (!netdev) {
dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n");
- goto setup_nic_dev_fail;
+ WRITE_ONCE(sc->caller_is_done, true);
+ goto setup_nic_dev_done;
}
SET_NETDEV_DEV(netdev, &octeon_dev->pci_dev->dev);
@@ -2123,6 +2082,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
netdev->min_mtu = LIO_MIN_MTU_SIZE;
netdev->max_mtu = LIO_MAX_MTU_SIZE;
+ WRITE_ONCE(sc->caller_is_done, true);
+
/* Point to the properties for octeon device to which this
* interface belongs.
*/
@@ -2146,7 +2107,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
lio->linfo.num_txpciq,
lio->linfo.num_rxpciq)) {
dev_err(&octeon_dev->pci_dev->dev, "I/O queues creation failed\n");
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
ifstate_set(lio, LIO_IFSTATE_DROQ_OPS);
@@ -2169,7 +2130,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
if (lio_setup_glists(octeon_dev, lio, num_iqueues)) {
dev_err(&octeon_dev->pci_dev->dev,
"Gather list allocation failed\n");
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
/* Register ethtool support */
@@ -2184,15 +2145,15 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
OCTNIC_LROIPV4 | OCTNIC_LROIPV6);
if (setup_link_status_change_wq(netdev))
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
if (setup_rx_oom_poll_fn(netdev))
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
/* Register the network device with the OS */
if (register_netdev(netdev)) {
dev_err(&octeon_dev->pci_dev->dev, "Device registration failed\n");
- goto setup_nic_dev_fail;
+ goto setup_nic_dev_free;
}
dev_dbg(&octeon_dev->pci_dev->dev,
@@ -2215,24 +2176,21 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
dev_dbg(&octeon_dev->pci_dev->dev,
"NIC ifidx:%d Setup successful\n", i);
- octeon_free_soft_command(octeon_dev, sc);
-
octeon_dev->no_speed_setting = 1;
}
return 0;
-setup_nic_dev_fail:
-
- octeon_free_soft_command(octeon_dev, sc);
-
-setup_nic_wait_intr:
+setup_nic_dev_free:
while (i--) {
dev_err(&octeon_dev->pci_dev->dev,
"NIC ifidx:%d Setup failed\n", i);
liquidio_destroy_nic_device(octeon_dev, i);
}
+
+setup_nic_dev_done:
+
return -ENODEV;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
index dfd4d10..a9306164 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -386,7 +386,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev)
}
sc = (struct octeon_soft_command *)
- octeon_alloc_soft_command(oct, 0, 0, 0);
+ octeon_alloc_soft_command(oct, 0, 16, 0);
if (!sc) {
dev_err(&oct->pci_dev->dev, "VF rep: Soft command alloc failed\n");
goto xmit_failed;
@@ -395,6 +395,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev)
/* Multiple buffers are not used for vf_rep packets. */
if (skb_shinfo(skb)->nr_frags != 0) {
dev_err(&oct->pci_dev->dev, "VF rep: nr_frags != 0. Dropping packet\n");
+ octeon_free_soft_command(oct, sc);
goto xmit_failed;
}
@@ -402,6 +403,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev)
skb->data, skb->len, DMA_TO_DEVICE);
if (dma_mapping_error(&oct->pci_dev->dev, sc->dmadptr)) {
dev_err(&oct->pci_dev->dev, "VF rep: DMA mapping failed\n");
+ octeon_free_soft_command(oct, sc);
goto xmit_failed;
}
@@ -422,6 +424,7 @@ lio_vf_rep_pkt_xmit(struct sk_buff *skb, struct net_device *ndev)
if (status == IQ_SEND_FAILED) {
dma_unmap_single(&oct->pci_dev->dev, sc->dmadptr,
sc->datasize, DMA_TO_DEVICE);
+ octeon_free_soft_command(oct, sc);
goto xmit_failed;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index 056dceb..24c2120 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -438,6 +438,7 @@ struct octeon_config {
#define MAX_BAR1_IOREMAP_SIZE (16 * OCTEON_BAR1_ENTRY_SIZE)
/* Response lists - 1 ordered, 1 unordered-blocking, 1 unordered-nonblocking
+ * 1 process done list, 1 zombie lists(timeouted sc list)
* NoResponse Lists are now maintained with each IQ. (Dec' 2007).
*/
#define MAX_RESPONSE_LISTS 6
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 3437d7f..a04f36a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -292,10 +292,7 @@ struct octeon_soft_command {
u32 ctxsize;
/** Time out and callback */
- size_t wait_time;
- size_t timeout;
size_t expiry_time;
-
u32 iq_no;
void (*callback)(struct octeon_device *, u32, void *);
void *callback_arg;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index de2a229..38c055f 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -146,48 +146,6 @@ static inline int octeon_map_pci_barx(struct octeon_device *oct,
return 1;
}
-static inline int
-sleep_cond(wait_queue_head_t *wait_queue, int *condition)
-{
- int errno = 0;
- wait_queue_entry_t we;
-
- init_waitqueue_entry(&we, current);
- add_wait_queue(wait_queue, &we);
- while (!(READ_ONCE(*condition))) {
- set_current_state(TASK_INTERRUPTIBLE);
- if (signal_pending(current)) {
- errno = -EINTR;
- goto out;
- }
- schedule();
- }
-out:
- set_current_state(TASK_RUNNING);
- remove_wait_queue(wait_queue, &we);
- return errno;
-}
-
-/* Gives up the CPU for a timeout period.
- * Check that the condition is not true before we go to sleep for a
- * timeout period.
- */
-static inline void
-sleep_timeout_cond(wait_queue_head_t *wait_queue,
- int *condition,
- int timeout)
-{
- wait_queue_entry_t we;
-
- init_waitqueue_entry(&we, current);
- add_wait_queue(wait_queue, &we);
- set_current_state(TASK_INTERRUPTIBLE);
- if (!(*condition))
- schedule_timeout(timeout);
- set_current_state(TASK_RUNNING);
- remove_wait_queue(wait_queue, &we);
-}
-
/* input parameter:
* sc: pointer to a soft request
* timeout: milli sec which an application wants to wait for the
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index a62826a..807266e 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -35,12 +35,6 @@
#define LIO_IFSTATE_RX_TIMESTAMP_ENABLED 0x08
#define LIO_IFSTATE_RESETTING 0x10
-struct liquidio_if_cfg_context {
- u32 octeon_id;
- wait_queue_head_t wc;
- int cond;
-};
-
struct liquidio_if_cfg_resp {
u64 rh;
struct liquidio_if_cfg_info cfg_info;
@@ -228,10 +222,6 @@ int lio_wait_for_clean_oq(struct octeon_device *oct);
*/
void liquidio_set_ethtool_ops(struct net_device *netdev);
-void lio_if_cfg_callback(struct octeon_device *oct,
- u32 status __attribute__((unused)),
- void *buf);
-
void lio_delete_glists(struct lio *lio);
int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_qs);
--
2.9.0
^ permalink raw reply related
* [PATCH net-next 2/4] liquidio: make soft command calls synchronous
From: Felix Manlunas @ 2018-08-29 1:51 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, weilin.chang
In-Reply-To: <20180829015058.GA7898@felix-thinkpad.cavium.com>
1. Add wait_for_sc_completion_timeout() for waiting the response and
handling common response errors
2. Send sc's synchronously: remove unused callback function,
and context structure; use wait_for_sc_completion_timeout() to wait
its response.
Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/lio_core.c | 134 ++++++---------------
drivers/net/ethernet/cavium/liquidio/lio_main.c | 42 ++-----
drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c | 42 ++-----
drivers/net/ethernet/cavium/liquidio/octeon_main.h | 66 ++++++++++
.../net/ethernet/cavium/liquidio/octeon_network.h | 6 -
5 files changed, 129 insertions(+), 161 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c
index 8093c5e..822ce0f 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_core.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c
@@ -1333,8 +1333,6 @@ octnet_nic_stats_callback(struct octeon_device *oct_dev,
struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
struct oct_nic_stats_resp *resp =
(struct oct_nic_stats_resp *)sc->virtrptr;
- struct oct_nic_stats_ctrl *ctrl =
- (struct oct_nic_stats_ctrl *)sc->ctxptr;
struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire;
struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost;
struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire;
@@ -1424,7 +1422,6 @@ octnet_nic_stats_callback(struct octeon_device *oct_dev,
} else {
resp->status = -1;
}
- complete(&ctrl->complete);
}
int octnet_get_link_stats(struct net_device *netdev)
@@ -1432,7 +1429,6 @@ int octnet_get_link_stats(struct net_device *netdev)
struct lio *lio = GET_LIO(netdev);
struct octeon_device *oct_dev = lio->oct_dev;
struct octeon_soft_command *sc;
- struct oct_nic_stats_ctrl *ctrl;
struct oct_nic_stats_resp *resp;
int retval;
@@ -1441,7 +1437,7 @@ int octnet_get_link_stats(struct net_device *netdev)
octeon_alloc_soft_command(oct_dev,
0,
sizeof(struct oct_nic_stats_resp),
- sizeof(struct octnic_ctrl_pkt));
+ 0);
if (!sc)
return -ENOMEM;
@@ -1449,66 +1445,39 @@ int octnet_get_link_stats(struct net_device *netdev)
resp = (struct oct_nic_stats_resp *)sc->virtrptr;
memset(resp, 0, sizeof(struct oct_nic_stats_resp));
- ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr;
- memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl));
- ctrl->netdev = netdev;
- init_completion(&ctrl->complete);
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
sc->iq_no = lio->linfo.txpciq[0].s.q_no;
octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC,
OPCODE_NIC_PORT_STATS, 0, 0, 0);
- sc->callback = octnet_nic_stats_callback;
- sc->callback_arg = sc;
- sc->wait_time = 500; /*in milli seconds*/
-
retval = octeon_send_soft_command(oct_dev, sc);
if (retval == IQ_SEND_FAILED) {
octeon_free_soft_command(oct_dev, sc);
return -EINVAL;
}
- wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000));
-
- if (resp->status != 1) {
- octeon_free_soft_command(oct_dev, sc);
-
- return -EINVAL;
+ retval = wait_for_sc_completion_timeout(oct_dev, sc,
+ (2 * LIO_SC_MAX_TMO_MS));
+ if (retval) {
+ dev_err(&oct_dev->pci_dev->dev, "sc OPCODE_NIC_PORT_STATS command failed\n");
+ return retval;
}
- octeon_free_soft_command(oct_dev, sc);
+ octnet_nic_stats_callback(oct_dev, sc->sc_status, sc);
+ WRITE_ONCE(sc->caller_is_done, true);
return 0;
}
-static void liquidio_nic_seapi_ctl_callback(struct octeon_device *oct,
- u32 status,
- void *buf)
-{
- struct liquidio_nic_seapi_ctl_context *ctx;
- struct octeon_soft_command *sc = buf;
-
- ctx = sc->ctxptr;
-
- oct = lio_get_device(ctx->octeon_id);
- if (status) {
- dev_err(&oct->pci_dev->dev, "%s: instruction failed. Status: %llx\n",
- __func__,
- CVM_CAST64(status));
- }
- ctx->status = status;
- complete(&ctx->complete);
-}
-
int liquidio_set_speed(struct lio *lio, int speed)
{
- struct liquidio_nic_seapi_ctl_context *ctx;
struct octeon_device *oct = lio->oct_dev;
struct oct_nic_seapi_resp *resp;
struct octeon_soft_command *sc;
union octnet_cmd *ncmd;
- u32 ctx_size;
int retval;
u32 var;
@@ -1521,21 +1490,18 @@ int liquidio_set_speed(struct lio *lio, int speed)
return -EOPNOTSUPP;
}
- ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context);
sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
sizeof(struct oct_nic_seapi_resp),
- ctx_size);
+ 0);
if (!sc)
return -ENOMEM;
ncmd = sc->virtdptr;
- ctx = sc->ctxptr;
resp = sc->virtrptr;
memset(resp, 0, sizeof(struct oct_nic_seapi_resp));
- ctx->octeon_id = lio_get_device_id(oct);
- ctx->status = 0;
- init_completion(&ctx->complete);
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
ncmd->u64 = 0;
ncmd->s.cmd = SEAPI_CMD_SPEED_SET;
@@ -1548,30 +1514,24 @@ int liquidio_set_speed(struct lio *lio, int speed)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_UBOOT_CTL, 0, 0, 0);
- sc->callback = liquidio_nic_seapi_ctl_callback;
- sc->callback_arg = sc;
- sc->wait_time = 5000;
-
retval = octeon_send_soft_command(oct, sc);
if (retval == IQ_SEND_FAILED) {
dev_info(&oct->pci_dev->dev, "Failed to send soft command\n");
+ octeon_free_soft_command(oct, sc);
retval = -EBUSY;
} else {
/* Wait for response or timeout */
- if (wait_for_completion_timeout(&ctx->complete,
- msecs_to_jiffies(10000)) == 0) {
- dev_err(&oct->pci_dev->dev, "%s: sc timeout\n",
- __func__);
- octeon_free_soft_command(oct, sc);
- return -EINTR;
- }
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
+ return retval;
retval = resp->status;
if (retval) {
dev_err(&oct->pci_dev->dev, "%s failed, retval=%d\n",
__func__, retval);
- octeon_free_soft_command(oct, sc);
+ WRITE_ONCE(sc->caller_is_done, true);
+
return -EIO;
}
@@ -1583,38 +1543,32 @@ int liquidio_set_speed(struct lio *lio, int speed)
}
oct->speed_setting = var;
+ WRITE_ONCE(sc->caller_is_done, true);
}
- octeon_free_soft_command(oct, sc);
-
return retval;
}
int liquidio_get_speed(struct lio *lio)
{
- struct liquidio_nic_seapi_ctl_context *ctx;
struct octeon_device *oct = lio->oct_dev;
struct oct_nic_seapi_resp *resp;
struct octeon_soft_command *sc;
union octnet_cmd *ncmd;
- u32 ctx_size;
int retval;
- ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context);
sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE,
sizeof(struct oct_nic_seapi_resp),
- ctx_size);
+ 0);
if (!sc)
return -ENOMEM;
ncmd = sc->virtdptr;
- ctx = sc->ctxptr;
resp = sc->virtrptr;
memset(resp, 0, sizeof(struct oct_nic_seapi_resp));
- ctx->octeon_id = lio_get_device_id(oct);
- ctx->status = 0;
- init_completion(&ctx->complete);
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
ncmd->u64 = 0;
ncmd->s.cmd = SEAPI_CMD_SPEED_GET;
@@ -1626,37 +1580,20 @@ int liquidio_get_speed(struct lio *lio)
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_UBOOT_CTL, 0, 0, 0);
- sc->callback = liquidio_nic_seapi_ctl_callback;
- sc->callback_arg = sc;
- sc->wait_time = 5000;
-
retval = octeon_send_soft_command(oct, sc);
if (retval == IQ_SEND_FAILED) {
dev_info(&oct->pci_dev->dev, "Failed to send soft command\n");
- oct->no_speed_setting = 1;
- oct->speed_setting = 25;
-
- retval = -EBUSY;
+ octeon_free_soft_command(oct, sc);
+ retval = -EIO;
} else {
- if (wait_for_completion_timeout(&ctx->complete,
- msecs_to_jiffies(10000)) == 0) {
- dev_err(&oct->pci_dev->dev, "%s: sc timeout\n",
- __func__);
-
- oct->speed_setting = 25;
- oct->no_speed_setting = 1;
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
+ return retval;
- octeon_free_soft_command(oct, sc);
-
- return -EINTR;
- }
retval = resp->status;
if (retval) {
dev_err(&oct->pci_dev->dev,
"%s failed retval=%d\n", __func__, retval);
- oct->no_speed_setting = 1;
- oct->speed_setting = 25;
- octeon_free_soft_command(oct, sc);
retval = -EIO;
} else {
u32 var;
@@ -1664,16 +1601,23 @@ int liquidio_get_speed(struct lio *lio)
var = be32_to_cpu((__force __be32)resp->speed);
oct->speed_setting = var;
if (var == 0xffff) {
- oct->no_speed_setting = 1;
/* unable to access boot variables
* get the default value based on the NIC type
*/
- oct->speed_setting = 25;
+ if (oct->subsystem_id ==
+ OCTEON_CN2350_25GB_SUBSYS_ID ||
+ oct->subsystem_id ==
+ OCTEON_CN2360_25GB_SUBSYS_ID) {
+ oct->no_speed_setting = 1;
+ oct->speed_setting = 25;
+ } else {
+ oct->speed_setting = 10;
+ }
}
+
}
+ WRITE_ONCE(sc->caller_is_done, true);
}
- octeon_free_soft_command(oct, sc);
-
return retval;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 6663749..8ddc191 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2969,30 +2969,15 @@ static int liquidio_get_vf_config(struct net_device *netdev, int vfidx,
return 0;
}
-static void trusted_vf_callback(struct octeon_device *oct_dev,
- u32 status, void *ptr)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
- struct lio_trusted_vf_ctx *ctx;
-
- ctx = (struct lio_trusted_vf_ctx *)sc->ctxptr;
- ctx->status = status;
-
- complete(&ctx->complete);
-}
-
static int liquidio_send_vf_trust_cmd(struct lio *lio, int vfidx, bool trusted)
{
struct octeon_device *oct = lio->oct_dev;
- struct lio_trusted_vf_ctx *ctx;
struct octeon_soft_command *sc;
- int ctx_size, retval;
-
- ctx_size = sizeof(struct lio_trusted_vf_ctx);
- sc = octeon_alloc_soft_command(oct, 0, 0, ctx_size);
+ int retval;
- ctx = (struct lio_trusted_vf_ctx *)sc->ctxptr;
- init_completion(&ctx->complete);
+ sc = octeon_alloc_soft_command(oct, 0, 16, 0);
+ if (!sc)
+ return -ENOMEM;
sc->iq_no = lio->linfo.txpciq[0].s.q_no;
@@ -3001,23 +2986,21 @@ static int liquidio_send_vf_trust_cmd(struct lio *lio, int vfidx, bool trusted)
OPCODE_NIC_SET_TRUSTED_VF, 0, vfidx + 1,
trusted);
- sc->callback = trusted_vf_callback;
- sc->callback_arg = sc;
- sc->wait_time = 1000;
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
retval = octeon_send_soft_command(oct, sc);
if (retval == IQ_SEND_FAILED) {
+ octeon_free_soft_command(oct, sc);
retval = -1;
} else {
/* Wait for response or timeout */
- if (wait_for_completion_timeout(&ctx->complete,
- msecs_to_jiffies(2000)))
- retval = ctx->status;
- else
- retval = -1;
- }
+ retval = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (retval)
+ return (retval);
- octeon_free_soft_command(oct, sc);
+ WRITE_ONCE(sc->caller_is_done, true);
+ }
return retval;
}
@@ -3733,7 +3716,6 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
octeon_dev->speed_setting = 10;
}
octeon_dev->speed_boot = octeon_dev->speed_setting;
-
}
devlink = devlink_alloc(&liquidio_devlink_ops,
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
index ddd7431..dfd4d10 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c
@@ -49,44 +49,25 @@ static const struct net_device_ops lio_vf_rep_ndev_ops = {
.ndo_change_mtu = lio_vf_rep_change_mtu,
};
-static void
-lio_vf_rep_send_sc_complete(struct octeon_device *oct,
- u32 status, void *ptr)
-{
- struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr;
- struct lio_vf_rep_sc_ctx *ctx =
- (struct lio_vf_rep_sc_ctx *)sc->ctxptr;
- struct lio_vf_rep_resp *resp =
- (struct lio_vf_rep_resp *)sc->virtrptr;
-
- if (status != OCTEON_REQUEST_TIMEOUT && READ_ONCE(resp->status))
- WRITE_ONCE(resp->status, 0);
-
- complete(&ctx->complete);
-}
-
static int
lio_vf_rep_send_soft_command(struct octeon_device *oct,
void *req, int req_size,
void *resp, int resp_size)
{
int tot_resp_size = sizeof(struct lio_vf_rep_resp) + resp_size;
- int ctx_size = sizeof(struct lio_vf_rep_sc_ctx);
struct octeon_soft_command *sc = NULL;
struct lio_vf_rep_resp *rep_resp;
- struct lio_vf_rep_sc_ctx *ctx;
void *sc_req;
int err;
sc = (struct octeon_soft_command *)
octeon_alloc_soft_command(oct, req_size,
- tot_resp_size, ctx_size);
+ tot_resp_size, 0);
if (!sc)
return -ENOMEM;
- ctx = (struct lio_vf_rep_sc_ctx *)sc->ctxptr;
- memset(ctx, 0, ctx_size);
- init_completion(&ctx->complete);
+ init_completion(&sc->complete);
+ sc->sc_status = OCTEON_REQUEST_PENDING;
sc_req = (struct lio_vf_rep_req *)sc->virtdptr;
memcpy(sc_req, req, req_size);
@@ -98,23 +79,24 @@ lio_vf_rep_send_soft_command(struct octeon_device *oct,
sc->iq_no = 0;
octeon_prepare_soft_command(oct, sc, OPCODE_NIC,
OPCODE_NIC_VF_REP_CMD, 0, 0, 0);
- sc->callback = lio_vf_rep_send_sc_complete;
- sc->callback_arg = sc;
- sc->wait_time = LIO_VF_REP_REQ_TMO_MS;
err = octeon_send_soft_command(oct, sc);
if (err == IQ_SEND_FAILED)
goto free_buff;
- wait_for_completion_timeout(&ctx->complete,
- msecs_to_jiffies
- (2 * LIO_VF_REP_REQ_TMO_MS));
+ err = wait_for_sc_completion_timeout(oct, sc, 0);
+ if (err)
+ return err;
+
err = READ_ONCE(rep_resp->status) ? -EBUSY : 0;
if (err)
dev_err(&oct->pci_dev->dev, "VF rep send config failed\n");
-
- if (resp)
+ else if (resp)
memcpy(resp, (rep_resp + 1), resp_size);
+
+ WRITE_ONCE(sc->caller_is_done, true);
+ return err;
+
free_buff:
octeon_free_soft_command(oct, sc);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_main.h b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
index c846eec..de2a229 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_main.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_main.h
@@ -188,6 +188,72 @@ sleep_timeout_cond(wait_queue_head_t *wait_queue,
remove_wait_queue(wait_queue, &we);
}
+/* input parameter:
+ * sc: pointer to a soft request
+ * timeout: milli sec which an application wants to wait for the
+ response of the request.
+ * 0: the request will wait until its response gets back
+ * from the firmware within LIO_SC_MAX_TMO_MS milli sec.
+ * It the response does not return within
+ * LIO_SC_MAX_TMO_MS milli sec, lio_process_ordered_list()
+ * will move the request to zombie response list.
+ *
+ * return value:
+ * 0: got the response from firmware for the sc request.
+ * errno -EINTR: user abort the command.
+ * errno -ETIME: user spefified timeout value has been expired.
+ * errno -EBUSY: the response of the request does not return in
+ * resonable time (LIO_SC_MAX_TMO_MS).
+ * the sc wll be move to zombie response list by
+ * lio_process_ordered_list()
+ *
+ * A request with non-zero return value, the sc->caller_is_done
+ * will be marked 1.
+ * When getting a request with zero return value, the requestor
+ * should mark sc->caller_is_done with 1 after examing the
+ * response of sc.
+ * lio_process_ordered_list() will free the soft command on behalf
+ * of the soft command requestor.
+ * This is to fix the possible race condition of both timeout process
+ * and lio_process_ordered_list()/callback function to free a
+ * sc strucutre.
+ */
+static inline int
+wait_for_sc_completion_timeout(struct octeon_device *oct_dev,
+ struct octeon_soft_command *sc,
+ unsigned long timeout)
+{
+ int errno = 0;
+ long timeout_jiff;
+
+ if (timeout)
+ timeout_jiff = msecs_to_jiffies(timeout);
+ else
+ timeout_jiff = MAX_SCHEDULE_TIMEOUT;
+
+ timeout_jiff =
+ wait_for_completion_interruptible_timeout(&sc->complete,
+ timeout_jiff);
+ if (timeout_jiff == 0) {
+ dev_err(&oct_dev->pci_dev->dev, "%s: sc is timeout\n",
+ __func__);
+ WRITE_ONCE(sc->caller_is_done, true);
+ errno = -ETIME;
+ } else if (timeout_jiff == -ERESTARTSYS) {
+ dev_err(&oct_dev->pci_dev->dev, "%s: sc is interrupted\n",
+ __func__);
+ WRITE_ONCE(sc->caller_is_done, true);
+ errno = -EINTR;
+ } else if (sc->sc_status == OCTEON_REQUEST_TIMEOUT) {
+ dev_err(&oct_dev->pci_dev->dev, "%s: sc has fatal timeout\n",
+ __func__);
+ WRITE_ONCE(sc->caller_is_done, true);
+ errno = -EBUSY;
+ }
+
+ return errno;
+}
+
#ifndef ROUNDUP4
#define ROUNDUP4(val) (((val) + 3) & 0xfffffffc)
#endif
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
index d7a3916..a62826a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h
@@ -87,12 +87,6 @@ struct oct_nic_seapi_resp {
u64 status;
};
-struct liquidio_nic_seapi_ctl_context {
- int octeon_id;
- u32 status;
- struct completion complete;
-};
-
/** LiquidIO per-interface network private data */
struct lio {
/** State of the interface. Rx/Tx happens only in the RUNNING state. */
--
2.9.0
^ permalink raw reply related
* [PATCH net-next 1/4] liquidio: improve soft command handling
From: Felix Manlunas @ 2018-08-29 1:51 UTC (permalink / raw)
To: davem
Cc: netdev, raghu.vatsavayi, derek.chickles, satananda.burla,
felix.manlunas, weilin.chang
In-Reply-To: <20180829015058.GA7898@felix-thinkpad.cavium.com>
1. Set LIO_SC_MAX_TMO_MS as the maximum timeout value for a soft command
(sc). All sc's use this value as a hard timeout value. Add expiry_time
in struct octeon_soft_command to keep the hard timeout value. The field
wait_time and timeout in struct octeon_soft_command will be obsoleted in
the last patch of this patch series.
2. Add processing a synchronous sc in sc response thread
lio_process_ordered_list. The memory allocated for a synchronous sc will
be freed by lio_process_ordered_list() to the sc pool.
3. Add two response lists for lio_process_ordered_list to process the
storage allocated for sc's:
OCTEON_DONE_SC_LIST response list keeps all sc's which will be freed to
the pool after their requestors have finished processing the responses.
OCTEON_ZOMBIE_SC_LIST response list keeps all sc's which have got
LIO_SC_MAX_TMO_MS timeout.
When an sc gets a hard timeout, lio_process_order_list() will recheck
its status 1 ms later. If the status has not updated by the firmware at
that time, the sc will be removed from OCTEON_DONE_SC_LIST response list
to OCTEON_ZOMBIE_SC_LIST response list. The sc's in the
OCTEON_ZOMBIE_SC_LIST response list will be freed when the driver is
unloaded.
Signed-off-by: Weilin Chang <weilin.chang@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
---
drivers/net/ethernet/cavium/liquidio/lio_main.c | 31 +++++-
drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 34 +++++-
.../net/ethernet/cavium/liquidio/octeon_config.h | 2 +-
drivers/net/ethernet/cavium/liquidio/octeon_iq.h | 11 ++
drivers/net/ethernet/cavium/liquidio/octeon_nic.c | 3 +-
.../net/ethernet/cavium/liquidio/request_manager.c | 114 +++++++++++++++------
.../ethernet/cavium/liquidio/response_manager.c | 82 +++++++++++++--
.../ethernet/cavium/liquidio/response_manager.h | 4 +-
8 files changed, 232 insertions(+), 49 deletions(-)
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 6fb13fa..6663749 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -1037,12 +1037,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
/* fallthrough */
case OCT_DEV_IO_QUEUES_DONE:
- if (wait_for_pending_requests(oct))
- dev_err(&oct->pci_dev->dev, "There were pending requests\n");
-
if (lio_wait_for_instr_fetch(oct))
dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
+ if (wait_for_pending_requests(oct))
+ dev_err(&oct->pci_dev->dev, "There were pending requests\n");
+
/* Disable the input and output queues now. No more packets will
* arrive from Octeon, but we should wait for all packet
* processing to finish.
@@ -1052,6 +1052,31 @@ static void octeon_destroy_resources(struct octeon_device *oct)
if (lio_wait_for_oq_pkts(oct))
dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
+ /* Force all requests waiting to be fetched by OCTEON to
+ * complete.
+ */
+ for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+ struct octeon_instr_queue *iq;
+
+ if (!(oct->io_qmask.iq & BIT_ULL(i)))
+ continue;
+ iq = oct->instr_queue[i];
+
+ if (atomic_read(&iq->instr_pending)) {
+ spin_lock_bh(&iq->lock);
+ iq->fill_cnt = 0;
+ iq->octeon_read_index = iq->host_write_index;
+ iq->stats.instr_processed +=
+ atomic_read(&iq->instr_pending);
+ lio_process_iq_request_list(oct, iq, 0);
+ spin_unlock_bh(&iq->lock);
+ }
+ }
+
+ lio_process_ordered_list(oct, 1);
+ octeon_free_sc_done_list(oct);
+ octeon_free_sc_zombie_list(oct);
+
/* fallthrough */
case OCT_DEV_INTR_SET_DONE:
/* Disable interrupts */
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index b778357..59c2dd9 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -471,12 +471,12 @@ static void octeon_destroy_resources(struct octeon_device *oct)
case OCT_DEV_HOST_OK:
/* fallthrough */
case OCT_DEV_IO_QUEUES_DONE:
- if (wait_for_pending_requests(oct))
- dev_err(&oct->pci_dev->dev, "There were pending requests\n");
-
if (lio_wait_for_instr_fetch(oct))
dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n");
+ if (wait_for_pending_requests(oct))
+ dev_err(&oct->pci_dev->dev, "There were pending requests\n");
+
/* Disable the input and output queues now. No more packets will
* arrive from Octeon, but we should wait for all packet
* processing to finish.
@@ -485,7 +485,33 @@ static void octeon_destroy_resources(struct octeon_device *oct)
if (lio_wait_for_oq_pkts(oct))
dev_err(&oct->pci_dev->dev, "OQ had pending packets\n");
- /* fall through */
+
+ /* Force all requests waiting to be fetched by OCTEON to
+ * complete.
+ */
+ for (i = 0; i < MAX_OCTEON_INSTR_QUEUES(oct); i++) {
+ struct octeon_instr_queue *iq;
+
+ if (!(oct->io_qmask.iq & BIT_ULL(i)))
+ continue;
+ iq = oct->instr_queue[i];
+
+ if (atomic_read(&iq->instr_pending)) {
+ spin_lock_bh(&iq->lock);
+ iq->fill_cnt = 0;
+ iq->octeon_read_index = iq->host_write_index;
+ iq->stats.instr_processed +=
+ atomic_read(&iq->instr_pending);
+ lio_process_iq_request_list(oct, iq, 0);
+ spin_unlock_bh(&iq->lock);
+ }
+ }
+
+ lio_process_ordered_list(oct, 1);
+ octeon_free_sc_done_list(oct);
+ octeon_free_sc_zombie_list(oct);
+
+ /* fall through */
case OCT_DEV_INTR_SET_DONE:
/* Disable interrupts */
oct->fn_list.disable_interrupt(oct, OCTEON_ALL_INTR);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_config.h b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
index ceac743..056dceb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_config.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_config.h
@@ -440,7 +440,7 @@ struct octeon_config {
/* Response lists - 1 ordered, 1 unordered-blocking, 1 unordered-nonblocking
* NoResponse Lists are now maintained with each IQ. (Dec' 2007).
*/
-#define MAX_RESPONSE_LISTS 4
+#define MAX_RESPONSE_LISTS 6
/* Opcode hash bits. The opcode is hashed on the lower 6-bits to lookup the
* dispatch table.
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index aecd0d3..3437d7f 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -294,11 +294,20 @@ struct octeon_soft_command {
/** Time out and callback */
size_t wait_time;
size_t timeout;
+ size_t expiry_time;
+
u32 iq_no;
void (*callback)(struct octeon_device *, u32, void *);
void *callback_arg;
+
+ int caller_is_done;
+ u32 sc_status;
+ struct completion complete;
};
+/* max timeout (in milli sec) for soft request */
+#define LIO_SC_MAX_TMO_MS 60000
+
/** Maximum number of buffers to allocate into soft command buffer pool
*/
#define MAX_SOFT_COMMAND_BUFFERS 256
@@ -319,6 +328,8 @@ struct octeon_sc_buffer_pool {
(((octeon_dev_ptr)->instr_queue[iq_no]->stats.field) += count)
int octeon_setup_sc_buffer_pool(struct octeon_device *oct);
+int octeon_free_sc_done_list(struct octeon_device *oct);
+int octeon_free_sc_zombie_list(struct octeon_device *oct);
int octeon_free_sc_buffer_pool(struct octeon_device *oct);
struct octeon_soft_command *
octeon_alloc_soft_command(struct octeon_device *oct,
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
index 150609b..b7364bb 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_nic.c
@@ -75,8 +75,7 @@ octeon_alloc_soft_command_resp(struct octeon_device *oct,
else
sc->cmd.cmd2.rptr = sc->dmarptr;
- sc->wait_time = 1000;
- sc->timeout = jiffies + sc->wait_time;
+ sc->expiry_time = jiffies + msecs_to_jiffies(LIO_SC_MAX_TMO_MS);
return sc;
}
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 5de5ce9..bd0153e 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -409,33 +409,22 @@ lio_process_iq_request_list(struct octeon_device *oct,
else
irh = (struct octeon_instr_irh *)
&sc->cmd.cmd2.irh;
- if (irh->rflag) {
- /* We're expecting a response from Octeon.
- * It's up to lio_process_ordered_list() to
- * process sc. Add sc to the ordered soft
- * command response list because we expect
- * a response from Octeon.
- */
- spin_lock_irqsave
- (&oct->response_list
- [OCTEON_ORDERED_SC_LIST].lock,
- flags);
- atomic_inc(&oct->response_list
- [OCTEON_ORDERED_SC_LIST].
- pending_req_count);
- list_add_tail(&sc->node, &oct->response_list
- [OCTEON_ORDERED_SC_LIST].head);
- spin_unlock_irqrestore
- (&oct->response_list
- [OCTEON_ORDERED_SC_LIST].lock,
- flags);
- } else {
- if (sc->callback) {
- /* This callback must not sleep */
- sc->callback(oct, OCTEON_REQUEST_DONE,
- sc->callback_arg);
- }
- }
+
+ /* We're expecting a response from Octeon.
+ * It's up to lio_process_ordered_list() to
+ * process sc. Add sc to the ordered soft
+ * command response list because we expect
+ * a response from Octeon.
+ */
+ spin_lock_irqsave(&oct->response_list
+ [OCTEON_ORDERED_SC_LIST].lock, flags);
+ atomic_inc(&oct->response_list
+ [OCTEON_ORDERED_SC_LIST].pending_req_count);
+ list_add_tail(&sc->node, &oct->response_list
+ [OCTEON_ORDERED_SC_LIST].head);
+ spin_unlock_irqrestore(&oct->response_list
+ [OCTEON_ORDERED_SC_LIST].lock,
+ flags);
break;
default:
dev_err(&oct->pci_dev->dev,
@@ -755,8 +744,7 @@ int octeon_send_soft_command(struct octeon_device *oct,
len = (u32)ih2->dlengsz;
}
- if (sc->wait_time)
- sc->timeout = jiffies + sc->wait_time;
+ sc->expiry_time = jiffies + msecs_to_jiffies(LIO_SC_MAX_TMO_MS);
return (octeon_send_command(oct, sc->iq_no, 1, &sc->cmd, sc,
len, REQTYPE_SOFT_COMMAND));
@@ -791,11 +779,76 @@ int octeon_setup_sc_buffer_pool(struct octeon_device *oct)
return 0;
}
+int octeon_free_sc_done_list(struct octeon_device *oct)
+{
+ struct octeon_response_list *done_sc_list, *zombie_sc_list;
+ struct octeon_soft_command *sc;
+ struct list_head *tmp, *tmp2;
+ spinlock_t *sc_lists_lock; /* lock for response_list */
+
+ done_sc_list = &oct->response_list[OCTEON_DONE_SC_LIST];
+ zombie_sc_list = &oct->response_list[OCTEON_ZOMBIE_SC_LIST];
+
+ if (!atomic_read(&done_sc_list->pending_req_count))
+ return 0;
+
+ sc_lists_lock = &oct->response_list[OCTEON_ORDERED_SC_LIST].lock;
+
+ spin_lock_bh(sc_lists_lock);
+
+ list_for_each_safe(tmp, tmp2, &done_sc_list->head) {
+ sc = list_entry(tmp, struct octeon_soft_command, node);
+
+ if (READ_ONCE(sc->caller_is_done)) {
+ list_del(&sc->node);
+ atomic_dec(&done_sc_list->pending_req_count);
+
+ if (*sc->status_word == COMPLETION_WORD_INIT) {
+ /* timeout; move sc to zombie list */
+ list_add_tail(&sc->node, &zombie_sc_list->head);
+ atomic_inc(&zombie_sc_list->pending_req_count);
+ } else {
+ octeon_free_soft_command(oct, sc);
+ }
+ }
+ }
+
+ spin_unlock_bh(sc_lists_lock);
+
+ return 0;
+}
+
+int octeon_free_sc_zombie_list(struct octeon_device *oct)
+{
+ struct octeon_response_list *zombie_sc_list;
+ struct octeon_soft_command *sc;
+ struct list_head *tmp, *tmp2;
+ spinlock_t *sc_lists_lock; /* lock for response_list */
+
+ zombie_sc_list = &oct->response_list[OCTEON_ZOMBIE_SC_LIST];
+ sc_lists_lock = &oct->response_list[OCTEON_ORDERED_SC_LIST].lock;
+
+ spin_lock_bh(sc_lists_lock);
+
+ list_for_each_safe(tmp, tmp2, &zombie_sc_list->head) {
+ list_del(tmp);
+ atomic_dec(&zombie_sc_list->pending_req_count);
+ sc = list_entry(tmp, struct octeon_soft_command, node);
+ octeon_free_soft_command(oct, sc);
+ }
+
+ spin_unlock_bh(sc_lists_lock);
+
+ return 0;
+}
+
int octeon_free_sc_buffer_pool(struct octeon_device *oct)
{
struct list_head *tmp, *tmp2;
struct octeon_soft_command *sc;
+ octeon_free_sc_zombie_list(oct);
+
spin_lock_bh(&oct->sc_buf_pool.lock);
list_for_each_safe(tmp, tmp2, &oct->sc_buf_pool.head) {
@@ -824,6 +877,9 @@ struct octeon_soft_command *octeon_alloc_soft_command(struct octeon_device *oct,
struct octeon_soft_command *sc = NULL;
struct list_head *tmp;
+ if (!rdatasize)
+ rdatasize = 16;
+
WARN_ON((offset + datasize + rdatasize + ctxsize) >
SOFT_COMMAND_BUFFER_SIZE);
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.c b/drivers/net/ethernet/cavium/liquidio/response_manager.c
index fe5b537..ac7747c 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.c
@@ -69,6 +69,8 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
u32 status;
u64 status64;
+ octeon_free_sc_done_list(octeon_dev);
+
ordered_sc_list = &octeon_dev->response_list[OCTEON_ORDERED_SC_LIST];
do {
@@ -111,26 +113,88 @@ int lio_process_ordered_list(struct octeon_device *octeon_dev,
}
}
}
- } else if (force_quit || (sc->timeout &&
- time_after(jiffies, (unsigned long)sc->timeout))) {
- dev_err(&octeon_dev->pci_dev->dev, "%s: cmd failed, timeout (%ld, %ld)\n",
- __func__, (long)jiffies, (long)sc->timeout);
+ } else if (unlikely(force_quit) || (sc->expiry_time &&
+ time_after(jiffies, (unsigned long)sc->expiry_time))) {
+ struct octeon_instr_irh *irh =
+ (struct octeon_instr_irh *)&sc->cmd.cmd3.irh;
+
+ dev_err(&octeon_dev->pci_dev->dev, "%s: ", __func__);
+ dev_err(&octeon_dev->pci_dev->dev,
+ "cmd %x/%x/%llx/%llx failed, ",
+ irh->opcode, irh->subcode,
+ sc->cmd.cmd3.ossp[0], sc->cmd.cmd3.ossp[1]);
+ dev_err(&octeon_dev->pci_dev->dev,
+ "timeout (%ld, %ld)\n",
+ (long)jiffies, (long)sc->expiry_time);
status = OCTEON_REQUEST_TIMEOUT;
}
if (status != OCTEON_REQUEST_PENDING) {
+ sc->sc_status = status;
+
/* we have received a response or we have timed out */
/* remove node from linked list */
list_del(&sc->node);
atomic_dec(&octeon_dev->response_list
- [OCTEON_ORDERED_SC_LIST].
- pending_req_count);
- spin_unlock_bh
- (&ordered_sc_list->lock);
+ [OCTEON_ORDERED_SC_LIST].
+ pending_req_count);
+
+ if (!sc->callback) {
+ atomic_inc(&octeon_dev->response_list
+ [OCTEON_DONE_SC_LIST].
+ pending_req_count);
+ list_add_tail(&sc->node,
+ &octeon_dev->response_list
+ [OCTEON_DONE_SC_LIST].head);
+
+ if (unlikely(READ_ONCE(sc->caller_is_done))) {
+ /* caller does not wait for response
+ * from firmware
+ */
+ if (status != OCTEON_REQUEST_DONE) {
+ struct octeon_instr_irh *irh;
+
+ irh =
+ (struct octeon_instr_irh *)
+ &sc->cmd.cmd3.irh;
+ dev_dbg
+ (&octeon_dev->pci_dev->dev,
+ "%s: sc failed: opcode=%x, ",
+ __func__, irh->opcode);
+ dev_dbg
+ (&octeon_dev->pci_dev->dev,
+ "subcode=%x, ossp[0]=%llx, ",
+ irh->subcode,
+ sc->cmd.cmd3.ossp[0]);
+ dev_dbg
+ (&octeon_dev->pci_dev->dev,
+ "ossp[1]=%llx, status=%d\n",
+ sc->cmd.cmd3.ossp[1],
+ status);
+ }
+ } else {
+ complete(&sc->complete);
+ }
+
+ spin_unlock_bh(&ordered_sc_list->lock);
+ } else {
+ /* sc with callback function */
+ if (status == OCTEON_REQUEST_TIMEOUT) {
+ atomic_inc(&octeon_dev->response_list
+ [OCTEON_ZOMBIE_SC_LIST].
+ pending_req_count);
+ list_add_tail(&sc->node,
+ &octeon_dev->response_list
+ [OCTEON_ZOMBIE_SC_LIST].
+ head);
+ }
+
+ spin_unlock_bh(&ordered_sc_list->lock);
- if (sc->callback)
sc->callback(octeon_dev, status,
sc->callback_arg);
+ /* sc is freed by caller */
+ }
request_complete++;
diff --git a/drivers/net/ethernet/cavium/liquidio/response_manager.h b/drivers/net/ethernet/cavium/liquidio/response_manager.h
index 9169c28..ed4020d 100644
--- a/drivers/net/ethernet/cavium/liquidio/response_manager.h
+++ b/drivers/net/ethernet/cavium/liquidio/response_manager.h
@@ -53,7 +53,9 @@ enum {
OCTEON_ORDERED_LIST = 0,
OCTEON_UNORDERED_NONBLOCKING_LIST = 1,
OCTEON_UNORDERED_BLOCKING_LIST = 2,
- OCTEON_ORDERED_SC_LIST = 3
+ OCTEON_ORDERED_SC_LIST = 3,
+ OCTEON_DONE_SC_LIST = 4,
+ OCTEON_ZOMBIE_SC_LIST = 5
};
/** Response Order values for a Octeon Request. */
--
2.9.0
^ permalink raw reply related
* [PATCH] neighbour: confirm neigh entries when ARP packet is received
From: Vasily Khoruzhick @ 2018-08-29 2:48 UTC (permalink / raw)
To: Ihar Hrachyshka, David S. Miller, Roopa Prabhu, Alexey Dobriyan,
Jim Westfall, Stephen Hemminger, Vasily Khoruzhick, Kees Cook,
Wolfgang Bumiller, Eric Dumazet, netdev
Cc: Vasily Khoruzhick
Update 'confirmed' timestamp when ARP packet is received. It shouldn't
affect locktime logic and anyway entry can be confirmed by any higher-layer
protocol. Thus it makes no sense not to confirm it when ARP packet is
received.
Fixes: 77d7123342 ("neighbour: update neigh timestamps iff update is
effective")
Signed-off-by: Vasily Khoruzhick <vasilykh@arista.com>
---
net/core/neighbour.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index aa19d86937af..901418ef70ea 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1180,6 +1180,9 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
lladdr = neigh->ha;
}
+ if (new & NUD_CONNECTED)
+ neigh->confirmed = jiffies;
+
/* If entry was valid and address is not changed,
do not change entry state, if new one is STALE.
*/
@@ -1205,11 +1208,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
* neighbour entry. Otherwise we risk to move the locktime window with
* noop updates and ignore relevant ARP updates.
*/
- if (new != old || lladdr != neigh->ha) {
- if (new & NUD_CONNECTED)
- neigh->confirmed = jiffies;
+ if (new != old || lladdr != neigh->ha)
neigh->updated = jiffies;
- }
if (new != old) {
neigh_del_timer(neigh);
--
2.18.0
^ permalink raw reply related
* RE: [PATCH 4/6] net/wan/fsl_ucc_hdlc: default hmask value
From: Qiang Zhao @ 2018-08-29 2:54 UTC (permalink / raw)
To: David Gounaris, netdev@vger.kernel.org,
linuxppc-dev@lists.ozlabs.org
Cc: David Gounaris
In-Reply-To: <20180828110921.2542-5-david.gounaris@infinera.com>
From: David Gounaris <david.gounaris@infinera.com>
Date: 2018/8/28 19:09
> Subject: [PATCH 4/6] net/wan/fsl_ucc_hdlc: default hmask value
>
> Set default HMASK to 0x0000 to use
> promiscuous mode in the hdlc controller.
>
> Signed-off-by: David Gounaris <david.gounaris@infinera.com>
> ---
> drivers/net/wan/fsl_ucc_hdlc.h | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/drivers/net/wan/fsl_ucc_hdlc.h b/drivers/net/wan/fsl_ucc_hdlc.h
> index c21134c1f180..5bc3d1a6ca6e 100644
> --- a/drivers/net/wan/fsl_ucc_hdlc.h
> +++ b/drivers/net/wan/fsl_ucc_hdlc.h
> @@ -134,7 +134,7 @@ struct ucc_hdlc_private {
>
> #define HDLC_HEAD_MASK 0x0000
> #define DEFAULT_HDLC_HEAD 0xff44
> -#define DEFAULT_ADDR_MASK 0x00ff
> +#define DEFAULT_ADDR_MASK 0x0000
> #define DEFAULT_HDLC_ADDR 0x00ff
>
> #define BMR_GBL 0x20000000
> --
It is not proper to set default HMASK to 0x0000, how about to add a new property standing for hmask into device tree,
If get this property from dtb, then set it with the value from dtb, otherwise, set it with default HMASK ox00ff?
Best Regards
Qiang Zhao
^ permalink raw reply
* Re: [PATCH RFT] net: dsa: Allow configuring CPU port VLANs
From: Maxim Uvarov @ 2018-08-29 7:14 UTC (permalink / raw)
To: Florian Fainelli
Cc: Ilias Apalodimas, petrm, netdev, jiri, Andrew Lunn,
Vivien Didelot, David Miller, kernel list
In-Reply-To: <25821da3-b923-485f-0991-e1dc943aefec@gmail.com>
вт, 28 авг. 2018 г. в 22:17, Florian Fainelli <f.fainelli@gmail.com>:
>
> On 08/28/2018 12:08 PM, Maxim Uvarov wrote:
> > вт, 28 авг. 2018 г. в 20:00, Florian Fainelli <f.fainelli@gmail.com>:
> >>
> >> On 08/28/2018 01:32 AM, Ilias Apalodimas wrote:
> >>> On Fri, Aug 10, 2018 at 04:58:10PM -0700, Florian Fainelli wrote:
> >>>> On 06/25/2018 02:17 AM, Ilias Apalodimas wrote:
> >>>>> On Mon, Jun 25, 2018 at 12:13:10PM +0300, Petr Machata wrote:
> >>>>>> Florian Fainelli <f.fainelli@gmail.com> writes:
> >>>>>>
> >>>>>>> if (netif_is_bridge_master(vlan->obj.orig_dev))
> >>>>>>> - return -EOPNOTSUPP;
> >>>>>>> + info.port = dp->cpu_dp->index;
> >>>>>>
> >>>>>> The condition above will trigger also when a VLAN is added on a member
> >>>>>> port, and there's no other port with that VLAN. In that case the VLAN
> >>>>>> comes without the BRIDGE_VLAN_INFO_BRENTRY flag. In mlxsw we have this
> >>>>>> to get the bridge VLANs:
> >>>>>>
> >>>>>> if (netif_is_bridge_master(orig_dev)) {
> >>>>>> [...]
> >>>>>> if ((vlan->flags & BRIDGE_VLAN_INFO_BRENTRY) &&
> >>>>>> [...]
> >>>>>>
> >>>>>> This doesn't appear to be done in DSA unless I'm missing something.
> >>>>> Petr's right. This will trigger for VLANs added on 'not cpu ports' if the VLAN
> >>>>> is not already a member.
> >>>>>
> >>>>> This command has BRIDGE_VLAN_INFO_BRENTRY set:
> >>>>> bridge vlan add dev br0 vid 100 pvid untagged self
> >>>>> I had the same issue on my CPSW RFC and solved it
> >>>>> exactly the same was as Petr suggested.
> >>>>
> >>>> Humm, there must be something obvious I am missing, but the following
> >>>> don't exactly result in what I would expect after adding a check for
> >>>> vlan->flags & BRIDGE_VLAN_INFO_BRENTRY:
> >>>>
> >>>> brctl addbr br0
> >>>> echo 1 > /sys/class/net/br0/bridge/vlan_filtering
> >>>> brctl addif br0 lan1
> >>>>
> >>>> #1 results in lan1 being programmed with VID 1, PVID, untagged, but not
> >>>> the CPU port. I would have sort of expected that the bridge layer would
> >>>> also push the configuration to br0/CPU port since this is the default VLAN:
> >>>>
> >>>> bridge vlan show dev br0
> >>>> port vlan ids
> >>>> br0 1 PVID Egress Untagged
> >>>>
> >>>> But it does not.
> >>>>
> >>>> bridge vlan add vid 2 dev lan1
> >>>>
> >>>> #2 same thing, results in only lan1 being programmed with VID 2, tagged
> >>>> but that is expected because we are creating the VLAN only for the
> >>>> user-facing port.
> >>>>
> >>>> bridge vlan add vid 3 dev br0 self
> >>>>
> >>>> #3 results in the CPU port being programmed with VID 3, tagged, again,
> >>>> this is expected because we are only programming the bridge master/CPU
> >>>> port here.
> >>>>
> >>>> Does #1 also happen for cpsw and mlxsw or do you actually get events
> >>>> about the bridge's default VLAN configuration? Or does the switch driver
> >>>> actually need to obtain that at the time the port is enslaved somehow?
> >>> As long as ports are attached you get the events (one event per attached port
> >>> iirc)
> >>> if the event is checked against BRIDGE_VLAN_INFO_BRENTRY, the only way to add a
> >>> VLAN to the cpu port is via 'bridge vlan add vid 3 dev br0 self'
> >>
> >> Do we have a guarantee that upon port enslavement, whatever default_pvid
> >> is configured on the bridge master device also happens to be the port's
> >> default_pvid settings as well?
> >
> > I think default pvid is per port thing. I.e. each port can have it's
> > own pvid (i.e. it will tag with vlan id not tagged incoming packet to
> > that port),
>
> We are talking about the bridge master device's default_pvid which can
> be set prior to any port being enslaved into the bridge. As of today, if
> you enslave a port of a switch into a bridge, you need to properly
> configure the CPU/management port as well otherwise things just wont' be
> working. At the time we enslave the first port into the bridge, there is
> no notification AFAICT that is generated to tell us about what the
> bridge master device's default_pvid is.
>
> > I did not exactly understand use case. With adding vlan filtering to
> > cpu port you filter out packets from other vlan groups to cpu port.
> > This might be useful
> > only for multicast packes or missing fbd entry on some dsa port. Is
> > filtering multicast a main problem to solve here?
> > Linux is missing vlan ingress policy. I.e. filtering (echo 1 >
> > /sys/br0/vlan_filter) has to be case of 3 policies: secure (default
> > now), check and fallback. With current secure mode it
> > might work, but with check mode it will be needed to add all vlans to
> > cpu port. Btw, on some hardware vlan ingress policies are also per
> > port, not per bridge.
>
> The general use case is that the CPU port on switches that have such a
> thing is just a normal port on which you should be able to configure
> exactly the VLAN membership and attributes.
>
that has to be good feature to add.
> With DSA switches today, we cannot do that, because there is no network
> interface exposed for the CPU port (and there should not be one), so
> when you target the bridge master device, e.g: br0, we can generate
> events towards the switch driver that map to the CPU port.
>
> There are many reasons for trying to do that, if we don't support such a
> thing, then we need to have the CPU port be part of all VLAN IDs that
> get added to ports, as a tagged member (because if untagged, you can't
> differentiate traffic anymore).
>
> Regarding your suggestion, we could certainly change vlan_filtering to
> take several values:
>
> 0: disabled
> 1: secure
> 2: check
>
> Or something like that.
I think that will work.
Maxim.
> --
> Florian
--
Best regards,
Maxim Uvarov
^ permalink raw reply
* Re: Oops running iptables -F OUTPUT
From: Nicholas Piggin @ 2018-08-29 3:28 UTC (permalink / raw)
To: Andreas Schwab
Cc: netdev, linuxppc-dev, Ard Biesheuvel, Jessica Yu,
Michael Ellerman, Will Deacon, Ingo Molnar, Andrew Morton,
linux-arch, Linus Torvalds, x86, linux-arm-kernel
In-Reply-To: <20180828140632.593291cf@roar.ozlabs.ibm.com>
On Tue, 28 Aug 2018 14:06:32 +1000
Nicholas Piggin <nicholas.piggin@gmail.com> wrote:
> On Mon, 27 Aug 2018 19:11:01 +0200
> Andreas Schwab <schwab@linux-m68k.org> wrote:
>
> > I'm getting this Oops when running iptables -F OUTPUT:
> >
> > [ 91.139409] Unable to handle kernel paging request for data at address 0xd0000001fff12f34
> > [ 91.139414] Faulting instruction address: 0xd0000000016a5718
> > [ 91.139419] Oops: Kernel access of bad area, sig: 11 [#1]
> > [ 91.139426] BE SMP NR_CPUS=2 PowerMac
> > [ 91.139434] Modules linked in: iptable_filter ip_tables x_tables bpfilter nfsd auth_rpcgss lockd grace nfs_acl sunrpc tun af_packet snd_aoa_codec_tas snd_aoa_fabric_layout snd_aoa snd_aoa_i2sbus snd_aoa_soundbus snd_pcm_oss snd_pcm snd_seq snd_timer snd_seq_device snd_mixer_oss snd sungem sr_mod firewire_ohci cdrom sungem_phy soundcore firewire_core pata_macio crc_itu_t sg hid_generic usbhid linear md_mod ohci_pci ohci_hcd ehci_pci ehci_hcd usbcore usb_common dm_snapshot dm_bufio dm_mirror dm_region_hash dm_log dm_mod sata_svw
> > [ 91.139522] CPU: 1 PID: 3620 Comm: iptables Not tainted 4.19.0-rc1 #1
> > [ 91.139526] NIP: d0000000016a5718 LR: d0000000016a569c CTR: c0000000006f560c
> > [ 91.139531] REGS: c0000001fa577670 TRAP: 0300 Not tainted (4.19.0-rc1)
> > [ 91.139534] MSR: 900000000200b032 <SF,HV,VEC,EE,FP,ME,IR,DR,RI> CR: 84002484 XER: 20000000
> > [ 91.139553] DAR: d0000001fff12f34 DSISR: 40000000 IRQMASK: 0
> > GPR00: d0000000016a569c c0000001fa5778f0 d0000000016b0400 0000000000000000
> > GPR04: 0000000000000002 0000000000000000 80000001fa46418e c0000001fa0d05c8
> > GPR08: d0000000016b0400 d00037fffff13000 00000001ff3e7000 d0000000016a6fb8
> > GPR12: c0000000006f560c c00000000ffff780 0000000000000000 0000000000000000
> > GPR16: 0000000011635010 00003fffa1b7aa68 0000000000000000 0000000000000000
> > GPR20: 0000000000000003 0000000010013918 00000000116350c0 c000000000b88990
> > GPR24: c000000000b88ba4 0000000000000000 d0000001fff12f34 0000000000000000
> > GPR28: d0000000016b8000 c0000001fa20f400 c0000001fa20f440 0000000000000000
> > [ 91.139627] NIP [d0000000016a5718] .alloc_counters.isra.10+0xbc/0x140 [ip_tables]
> > [ 91.139634] LR [d0000000016a569c] .alloc_counters.isra.10+0x40/0x140 [ip_tables]
> > [ 91.139638] Call Trace:
> > [ 91.139645] [c0000001fa5778f0] [d0000000016a569c] .alloc_counters.isra.10+0x40/0x140 [ip_tables] (unreliable)
> > [ 91.139655] [c0000001fa5779b0] [d0000000016a5b54] .do_ipt_get_ctl+0x110/0x2ec [ip_tables]
> > [ 91.139666] [c0000001fa577aa0] [c0000000006233e0] .nf_getsockopt+0x68/0x88
> > [ 91.139674] [c0000001fa577b40] [c000000000631608] .ip_getsockopt+0xbc/0x128
> > [ 91.139682] [c0000001fa577bf0] [c00000000065adf4] .raw_getsockopt+0x18/0x5c
> > [ 91.139690] [c0000001fa577c60] [c0000000005b5f60] .sock_common_getsockopt+0x2c/0x40
> > [ 91.139697] [c0000001fa577cd0] [c0000000005b3394] .__sys_getsockopt+0xa4/0xd0
> > [ 91.139704] [c0000001fa577d80] [c0000000005b5ab0] .__se_sys_socketcall+0x238/0x2b4
> > [ 91.139712] [c0000001fa577e30] [c00000000000a31c] system_call+0x5c/0x70
> > [ 91.139716] Instruction dump:
> > [ 91.139721] 39290040 7d3d4a14 7fbe4840 409cff98 81380000 2b890001 419d000c 393e0060
> > [ 91.139736] 48000010 7d57c82a e93e0060 7d295214 <815a0000> 794807e1 41e20010 7c210b78
> > [ 91.139752] ---[ end trace f5d1d5431651845d ]---
>
> This is due to 7290d58095 ("module: use relative references for
> __ksymtab entries"). This part of kernel/module.c -
>
> /* Divert to percpu allocation if a percpu var. */
> if (sym[i].st_shndx == info->index.pcpu)
> secbase = (unsigned long)mod_percpu(mod);
> else
> secbase = info->sechdrs[sym[i].st_shndx].sh_addr;
> sym[i].st_value += secbase;
>
> Causes the distance to the target to exceed 32-bits on powerpc, so
> it doesn't fit in a rel32 reloc. Not sure how other archs cope.
Any progress on this one? I had a bit of a look but can't see a really
trivial fix and don't have a lot of time to work on it. Maybe use 64
bit relative offsets for per-cpu exports, or better might be apply the
per-cpu fixup when linking against the symbol rather than when writing
the module symbol table.
Until then I'd like to just remove HAVE_ARCH_PREL32_RELOCATIONS from
powerpc/Kconfig, but if other archs are going to have issues too, we
could just revert
271ca788774aa ("arch: enable relative relocations for arm64, power and x86")
arm64, x86 -- can the distance between your module percpu data link
location -> module percpu runtime allocation location exceed 31 bits?
Thanks,
Nick
^ permalink raw reply
* [PATCH][net-next] vxlan: reduce dirty cache line in vxlan_find_mac
From: Li RongQing @ 2018-08-29 3:52 UTC (permalink / raw)
To: netdev
vxlan_find_mac() unconditionally set f->used for every packet,
this causes a cache miss for every packet, since remote, hlist
and used of vxlan_fdb share the same cache line, which are
accessed when send every packets.
so f->used is set only if not equal to jiffies, to reduce dirty
cache line times, this gives 3% speed-up with small packets.
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
---
drivers/net/vxlan.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index ababba37d735..e5d236595206 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -464,7 +464,7 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
struct vxlan_fdb *f;
f = __vxlan_find_mac(vxlan, mac, vni);
- if (f)
+ if (f && f->used != jiffies)
f->used = jiffies;
return f;
--
2.16.2
^ permalink raw reply related
* Re: Oops running iptables -F OUTPUT
From: Nicholas Piggin @ 2018-08-29 3:53 UTC (permalink / raw)
To: Andreas Schwab
Cc: netdev, linuxppc-dev, Ard Biesheuvel, Jessica Yu,
Michael Ellerman, Will Deacon, Ingo Molnar, Andrew Morton,
linux-arch, Linus Torvalds, x86, linux-arm-kernel
In-Reply-To: <20180829132827.6dbc4352@roar.ozlabs.ibm.com>
On Wed, 29 Aug 2018 13:28:27 +1000
Nicholas Piggin <npiggin@gmail.com> wrote:
> On Tue, 28 Aug 2018 14:06:32 +1000
> Nicholas Piggin <nicholas.piggin@gmail.com> wrote:
>
> > On Mon, 27 Aug 2018 19:11:01 +0200
> > Andreas Schwab <schwab@linux-m68k.org> wrote:
> >
> > > I'm getting this Oops when running iptables -F OUTPUT:
> > >
> > > [ 91.139409] Unable to handle kernel paging request for data at address 0xd0000001fff12f34
> > > [ 91.139414] Faulting instruction address: 0xd0000000016a5718
> > > [ 91.139419] Oops: Kernel access of bad area, sig: 11 [#1]
> > > [ 91.139426] BE SMP NR_CPUS=2 PowerMac
> > > [ 91.139434] Modules linked in: iptable_filter ip_tables x_tables bpfilter nfsd auth_rpcgss lockd grace nfs_acl sunrpc tun af_packet snd_aoa_codec_tas snd_aoa_fabric_layout snd_aoa snd_aoa_i2sbus snd_aoa_soundbus snd_pcm_oss snd_pcm snd_seq snd_timer snd_seq_device snd_mixer_oss snd sungem sr_mod firewire_ohci cdrom sungem_phy soundcore firewire_core pata_macio crc_itu_t sg hid_generic usbhid linear md_mod ohci_pci ohci_hcd ehci_pci ehci_hcd usbcore usb_common dm_snapshot dm_bufio dm_mirror dm_region_hash dm_log dm_mod sata_svw
> > > [ 91.139522] CPU: 1 PID: 3620 Comm: iptables Not tainted 4.19.0-rc1 #1
> > > [ 91.139526] NIP: d0000000016a5718 LR: d0000000016a569c CTR: c0000000006f560c
> > > [ 91.139531] REGS: c0000001fa577670 TRAP: 0300 Not tainted (4.19.0-rc1)
> > > [ 91.139534] MSR: 900000000200b032 <SF,HV,VEC,EE,FP,ME,IR,DR,RI> CR: 84002484 XER: 20000000
> > > [ 91.139553] DAR: d0000001fff12f34 DSISR: 40000000 IRQMASK: 0
> > > GPR00: d0000000016a569c c0000001fa5778f0 d0000000016b0400 0000000000000000
> > > GPR04: 0000000000000002 0000000000000000 80000001fa46418e c0000001fa0d05c8
> > > GPR08: d0000000016b0400 d00037fffff13000 00000001ff3e7000 d0000000016a6fb8
> > > GPR12: c0000000006f560c c00000000ffff780 0000000000000000 0000000000000000
> > > GPR16: 0000000011635010 00003fffa1b7aa68 0000000000000000 0000000000000000
> > > GPR20: 0000000000000003 0000000010013918 00000000116350c0 c000000000b88990
> > > GPR24: c000000000b88ba4 0000000000000000 d0000001fff12f34 0000000000000000
> > > GPR28: d0000000016b8000 c0000001fa20f400 c0000001fa20f440 0000000000000000
> > > [ 91.139627] NIP [d0000000016a5718] .alloc_counters.isra.10+0xbc/0x140 [ip_tables]
> > > [ 91.139634] LR [d0000000016a569c] .alloc_counters.isra.10+0x40/0x140 [ip_tables]
> > > [ 91.139638] Call Trace:
> > > [ 91.139645] [c0000001fa5778f0] [d0000000016a569c] .alloc_counters.isra.10+0x40/0x140 [ip_tables] (unreliable)
> > > [ 91.139655] [c0000001fa5779b0] [d0000000016a5b54] .do_ipt_get_ctl+0x110/0x2ec [ip_tables]
> > > [ 91.139666] [c0000001fa577aa0] [c0000000006233e0] .nf_getsockopt+0x68/0x88
> > > [ 91.139674] [c0000001fa577b40] [c000000000631608] .ip_getsockopt+0xbc/0x128
> > > [ 91.139682] [c0000001fa577bf0] [c00000000065adf4] .raw_getsockopt+0x18/0x5c
> > > [ 91.139690] [c0000001fa577c60] [c0000000005b5f60] .sock_common_getsockopt+0x2c/0x40
> > > [ 91.139697] [c0000001fa577cd0] [c0000000005b3394] .__sys_getsockopt+0xa4/0xd0
> > > [ 91.139704] [c0000001fa577d80] [c0000000005b5ab0] .__se_sys_socketcall+0x238/0x2b4
> > > [ 91.139712] [c0000001fa577e30] [c00000000000a31c] system_call+0x5c/0x70
> > > [ 91.139716] Instruction dump:
> > > [ 91.139721] 39290040 7d3d4a14 7fbe4840 409cff98 81380000 2b890001 419d000c 393e0060
> > > [ 91.139736] 48000010 7d57c82a e93e0060 7d295214 <815a0000> 794807e1 41e20010 7c210b78
> > > [ 91.139752] ---[ end trace f5d1d5431651845d ]---
> >
> > This is due to 7290d58095 ("module: use relative references for
> > __ksymtab entries"). This part of kernel/module.c -
> >
> > /* Divert to percpu allocation if a percpu var. */
> > if (sym[i].st_shndx == info->index.pcpu)
> > secbase = (unsigned long)mod_percpu(mod);
> > else
> > secbase = info->sechdrs[sym[i].st_shndx].sh_addr;
> > sym[i].st_value += secbase;
> >
> > Causes the distance to the target to exceed 32-bits on powerpc, so
> > it doesn't fit in a rel32 reloc. Not sure how other archs cope.
>
> Any progress on this one? I had a bit of a look but can't see a really
> trivial fix and don't have a lot of time to work on it. Maybe use 64
> bit relative offsets for per-cpu exports, or better might be apply the
> per-cpu fixup when linking against the symbol rather than when writing
> the module symbol table.
>
> Until then I'd like to just remove HAVE_ARCH_PREL32_RELOCATIONS from
> powerpc/Kconfig, but if other archs are going to have issues too, we
> could just revert
>
> 271ca788774aa ("arch: enable relative relocations for arm64, power and x86")
>
> arm64, x86 -- can the distance between your module percpu data link
> location -> module percpu runtime allocation location exceed 31 bits?
[Sorry ignore this, I missed some mail, will reply in the thread]
Thanks,
Nick
^ permalink raw reply
* [PATCH 0/5] net: mvneta: some bug fix and trivial improvement
From: Jisheng Zhang @ 2018-08-29 8:25 UTC (permalink / raw)
To: thomas.petazzoni, David S. Miller
Cc: netdev, linux-kernel, Andrew Lunn, Gregory CLEMENT,
linux-arm-kernel
patch1 fixes rx_offset_correction set and usage. Because the
rx_offset_correction is RX packet offset correction for platforms,
it's not related with SW BM, instead, it's only related with the
platform's NET_SKB_PAD.
patch2 fixes the wrong function to unmap rx buf
patch3 removes the NETIF_F_GRO check ourself, because the net subsystem
will handle it for us.
patch4 enables NETIF_F_RXCSUM by default, since the driver and HW
supports the feature.
patch5 is a trivial optimization, to reduce smp_processor_id() calling
in mvneta_tx_done_gbe.
Jisheng Zhang (5):
net: mvneta: fix rx_offset_correction set and usage
net: mvneta: fix the wrong function to unmap rx buf
net: mvneta: Don't check NETIF_F_GRO ourself
net: mvneta: enable NETIF_F_RXCSUM by default
net: mvneta: reduce smp_processor_id() calling in mvneta_tx_done_gbe
drivers/net/ethernet/marvell/mvneta.c | 49 ++++++++++++---------------
1 file changed, 22 insertions(+), 27 deletions(-)
--
2.18.0
^ permalink raw reply
* [PATCH 1/5] net: mvneta: fix rx_offset_correction set and usage
From: Jisheng Zhang @ 2018-08-29 8:27 UTC (permalink / raw)
To: thomas.petazzoni, David S. Miller
Cc: netdev, linux-kernel, Andrew Lunn, Gregory CLEMENT,
linux-arm-kernel
In-Reply-To: <20180829162456.2bd69796@xhacker.debian>
The rx_offset_correction is RX packet offset correction for platforms,
it's not related with SW BM, instead, it's only related with the
platform's NET_SKB_PAD.
Fix the issue by reverting to the original behavior.
Fixes: 562e2f467e71 ("net: mvneta: Improve the buffer allocation method for SWBM")
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
---
drivers/net/ethernet/marvell/mvneta.c | 24 ++++++++++--------------
1 file changed, 10 insertions(+), 14 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index bc80a678abc3..0ce94f6587a5 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2899,21 +2899,18 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp,
mvreg_write(pp, MVNETA_RXQ_BASE_ADDR_REG(rxq->id), rxq->descs_phys);
mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size);
+ /* Set Offset */
+ mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD - pp->rx_offset_correction);
+
/* Set coalescing pkts and time */
mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal);
if (!pp->bm_priv) {
- /* Set Offset */
- mvneta_rxq_offset_set(pp, rxq, 0);
mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size);
mvneta_rxq_bm_disable(pp, rxq);
mvneta_rxq_fill(pp, rxq, rxq->size);
} else {
- /* Set Offset */
- mvneta_rxq_offset_set(pp, rxq,
- NET_SKB_PAD - pp->rx_offset_correction);
-
mvneta_rxq_bm_enable(pp, rxq);
/* Fill RXQ with buffers from RX pool */
mvneta_rxq_long_pool_set(pp, rxq);
@@ -4547,7 +4544,13 @@ static int mvneta_probe(struct platform_device *pdev)
SET_NETDEV_DEV(dev, &pdev->dev);
pp->id = global_port_id++;
- pp->rx_offset_correction = 0; /* not relevant for SW BM */
+
+ /* Set RX packet offset correction for platforms, whose
+ * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
+ * platforms and 0B for 32-bit ones.
+ */
+ pp->rx_offset_correction =
+ max(0, NET_SKB_PAD - MVNETA_RX_PKT_OFFSET_CORRECTION);
/* Obtain access to BM resources if enabled and already initialized */
bm_node = of_parse_phandle(dn, "buffer-manager", 0);
@@ -4562,13 +4565,6 @@ static int mvneta_probe(struct platform_device *pdev)
pp->bm_priv = NULL;
}
}
- /* Set RX packet offset correction for platforms, whose
- * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
- * platforms and 0B for 32-bit ones.
- */
- pp->rx_offset_correction = max(0,
- NET_SKB_PAD -
- MVNETA_RX_PKT_OFFSET_CORRECTION);
}
of_node_put(bm_node);
--
2.18.0
^ permalink raw reply related
* [PATCH 3/5] net: mvneta: Don't check NETIF_F_GRO ourself
From: Jisheng Zhang @ 2018-08-29 8:28 UTC (permalink / raw)
To: thomas.petazzoni, David S. Miller
Cc: netdev, linux-kernel, Andrew Lunn, Gregory CLEMENT,
linux-arm-kernel
In-Reply-To: <20180829162456.2bd69796@xhacker.debian>
napi_gro_receive() checks NETIF_F_GRO bit as well, if the bit is not
set, we will go through GRO_NORMAL in napi_skb_finish(), so fall back
to netif_receive_skb_internal(), so we don't need to check NETIF_F_GRO
ourself.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
---
drivers/net/ethernet/marvell/mvneta.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index d9206094fce3..06634d4f9b94 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2065,10 +2065,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
/* Linux processing */
rxq->skb->protocol = eth_type_trans(rxq->skb, dev);
- if (dev->features & NETIF_F_GRO)
- napi_gro_receive(napi, rxq->skb);
- else
- netif_receive_skb(rxq->skb);
+ napi_gro_receive(napi, rxq->skb);
/* clean uncomplete skb pointer in queue */
rxq->skb = NULL;
--
2.18.0
^ permalink raw reply related
* [PATCH 4/5] net: mvneta: enable NETIF_F_RXCSUM by default
From: Jisheng Zhang @ 2018-08-29 8:29 UTC (permalink / raw)
To: thomas.petazzoni, David S. Miller
Cc: netdev, linux-kernel, Andrew Lunn, Gregory CLEMENT,
linux-arm-kernel
In-Reply-To: <20180829162456.2bd69796@xhacker.debian>
The code and HW supports NETIF_F_RXCSUM, so let's enable it by default.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
---
drivers/net/ethernet/marvell/mvneta.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 06634d4f9b94..7d98f7828a30 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4591,7 +4591,8 @@ static int mvneta_probe(struct platform_device *pdev)
}
}
- dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_TSO;
+ dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
+ NETIF_F_TSO | NETIF_F_RXCSUM;
dev->hw_features |= dev->features;
dev->vlan_features |= dev->features;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
--
2.18.0
^ permalink raw reply related
* [PATCH 5/5] net: mvneta: reduce smp_processor_id() calling in mvneta_tx_done_gbe
From: Jisheng Zhang @ 2018-08-29 8:30 UTC (permalink / raw)
To: thomas.petazzoni, David S. Miller
Cc: netdev, linux-kernel, Andrew Lunn, Gregory CLEMENT,
linux-arm-kernel
In-Reply-To: <20180829162456.2bd69796@xhacker.debian>
In the loop of mvneta_tx_done_gbe(), we call the smp_processor_id()
each time, move the call out of the loop to optimize the code a bit.
Before the patch, the loop looks like(under arm64):
ldr x1, [x29,#120]
...
ldr w24, [x1,#36]
...
bl 0 <_raw_spin_lock>
str w24, [x27,#132]
...
After the patch, the loop looks like(under arm64):
...
bl 0 <_raw_spin_lock>
str w23, [x28,#132]
...
where w23 is loaded so be ready before the loop.
From another side, mvneta_tx_done_gbe() is called from mvneta_poll()
which is in non-preemptible context, so it's safe to call the
smp_processor_id() function once.
Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
---
drivers/net/ethernet/marvell/mvneta.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 7d98f7828a30..62e81e267e13 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2507,12 +2507,13 @@ static void mvneta_tx_done_gbe(struct mvneta_port *pp, u32 cause_tx_done)
{
struct mvneta_tx_queue *txq;
struct netdev_queue *nq;
+ int cpu = smp_processor_id();
while (cause_tx_done) {
txq = mvneta_tx_done_policy(pp, cause_tx_done);
nq = netdev_get_tx_queue(pp->dev, txq->id);
- __netif_tx_lock(nq, smp_processor_id());
+ __netif_tx_lock(nq, cpu);
if (txq->count)
mvneta_txq_done(pp, txq);
--
2.18.0
^ permalink raw reply related
* Re: [PATCH net-next 0/5] rtnetlink: add IFA_IF_NETNSID for RTM_GETADDR
From: Kirill Tkhai @ 2018-08-29 8:30 UTC (permalink / raw)
To: Christian Brauner, netdev, linux-kernel
Cc: davem, kuznet, yoshfuji, pombredanne, kstewart, gregkh, dsahern,
fw, lucien.xin, jakub.kicinski, jbenc, nicolas.dichtel,
Christian Brauner
In-Reply-To: <20180828231859.29758-1-christian@brauner.io>
Hi, Christian,
On 29.08.2018 02:18, Christian Brauner wrote:
> From: Christian Brauner <christian.brauner@ubuntu.com>
>
> Hey,
>
> A while back we introduced and enabled IFLA_IF_NETNSID in
> RTM_{DEL,GET,NEW}LINK requests (cf. [1], [2], [3], [4], [5]). This has led
> to signficant performance increases since it allows userspace to avoid
> taking the hit of a setns(netns_fd, CLONE_NEWNET), then getting the
> interfaces from the netns associated with the netns_fd. Especially when a
> lot of network namespaces are in use, using setns() becomes increasingly
> problematic when performance matters.
could you please give a real example, when setns()+socket(AF_NETLINK) cause
problems with the performance? You should do this only once on application
startup, and then you have created netlink sockets in any net namespaces you
need. What is the problem here?
> Usually, RTML_GETLINK requests are followed by RTM_GETADDR requests (cf.
> getifaddrs() style functions and friends). But currently, RTM_GETADDR
> requests do not support a similar property like IFLA_IF_NETNSID for
> RTM_*LINK requests.
> This is problematic since userspace can retrieve interfaces from another
> network namespace by sending a IFLA_IF_NETNSID property along but
> RTM_GETLINK request but is still forced to use the legacy setns() style of
> retrieving interfaces in RTM_GETADDR requests.
>
> The goal of this series is to make it possible to perform RTM_GETADDR
> requests on different network namespaces. To this end a new IFA_IF_NETNSID
> property for RTM_*ADDR requests is introduced. It can be used to send a
> network namespace identifier along in RTM_*ADDR requests. The network
> namespace identifier will be used to retrieve the target network namespace
> in which the request is supposed to be fulfilled. This aligns the behavior
> of RTM_*ADDR requests with the behavior of RTM_*LINK requests.
>
> Security:
> - The caller must have assigned a valid network namespace identifier for
> the target network namespace.
> - The caller must have CAP_NET_ADMIN in the owning user namespace of the
> target network namespace.
>
> Thanks!
> Christian
>
> [1]: commit 7973bfd8758d ("rtnetlink: remove check for IFLA_IF_NETNSID")
> [2]: commit 5bb8ed075428 ("rtnetlink: enable IFLA_IF_NETNSID for RTM_NEWLINK")
> [3]: commit b61ad68a9fe8 ("rtnetlink: enable IFLA_IF_NETNSID for RTM_DELLINK")
> [4]: commit c310bfcb6e1b ("rtnetlink: enable IFLA_IF_NETNSID for RTM_SETLINK")
> [5]: commit 7c4f63ba8243 ("rtnetlink: enable IFLA_IF_NETNSID in do_setlink()")
>
> Christian Brauner (5):
> rtnetlink: add rtnl_get_net_ns_capable()
> if_addr: add IFA_IF_NETNSID
> ipv4: enable IFA_IF_NETNSID for RTM_GETADDR
> ipv6: enable IFA_IF_NETNSID for RTM_GETADDR
> rtnetlink: move type calculation out of loop
>
> include/net/rtnetlink.h | 1 +
> include/uapi/linux/if_addr.h | 1 +
> net/core/rtnetlink.c | 15 +++++---
> net/ipv4/devinet.c | 38 +++++++++++++++-----
> net/ipv6/addrconf.c | 70 ++++++++++++++++++++++++++++--------
> 5 files changed, 97 insertions(+), 28 deletions(-)
>
^ permalink raw reply
* Re: Oops running iptables -F OUTPUT
From: Nicholas Piggin @ 2018-08-29 4:36 UTC (permalink / raw)
To: Ard Biesheuvel
Cc: Andreas Schwab, <netdev@vger.kernel.org>, linuxppc-dev,
Jessica Yu, Michael Ellerman, Will Deacon, Ingo Molnar,
Andrew Morton, linux-arch, Linus Torvalds
In-Reply-To: <CAKv+Gu_hPaxrVtsBOoviRraYk4FWnT9zQVCVF=i27xd_nGHryw@mail.gmail.com>
On Tue, 28 Aug 2018 18:09:09 +0200
Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> On 28 August 2018 at 15:56, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> > Hello Andreas, Nick,
> >
> > On 28 August 2018 at 06:06, Nicholas Piggin <nicholas.piggin@gmail.com> wrote:
> >> On Mon, 27 Aug 2018 19:11:01 +0200
> >> Andreas Schwab <schwab@linux-m68k.org> wrote:
> >>
> >>> I'm getting this Oops when running iptables -F OUTPUT:
> >>>
> >>> [ 91.139409] Unable to handle kernel paging request for data at address 0xd0000001fff12f34
> >>> [ 91.139414] Faulting instruction address: 0xd0000000016a5718
> >>> [ 91.139419] Oops: Kernel access of bad area, sig: 11 [#1]
> >>> [ 91.139426] BE SMP NR_CPUS=2 PowerMac
> >>> [ 91.139434] Modules linked in: iptable_filter ip_tables x_tables bpfilter nfsd auth_rpcgss lockd grace nfs_acl sunrpc tun af_packet snd_aoa_codec_tas snd_aoa_fabric_layout snd_aoa snd_aoa_i2sbus snd_aoa_soundbus snd_pcm_oss snd_pcm snd_seq snd_timer snd_seq_device snd_mixer_oss snd sungem sr_mod firewire_ohci cdrom sungem_phy soundcore firewire_core pata_macio crc_itu_t sg hid_generic usbhid linear md_mod ohci_pci ohci_hcd ehci_pci ehci_hcd usbcore usb_common dm_snapshot dm_bufio dm_mirror dm_region_hash dm_log dm_mod sata_svw
> >>> [ 91.139522] CPU: 1 PID: 3620 Comm: iptables Not tainted 4.19.0-rc1 #1
> >>> [ 91.139526] NIP: d0000000016a5718 LR: d0000000016a569c CTR: c0000000006f560c
> >>> [ 91.139531] REGS: c0000001fa577670 TRAP: 0300 Not tainted (4.19.0-rc1)
> >>> [ 91.139534] MSR: 900000000200b032 <SF,HV,VEC,EE,FP,ME,IR,DR,RI> CR: 84002484 XER: 20000000
> >>> [ 91.139553] DAR: d0000001fff12f34 DSISR: 40000000 IRQMASK: 0
> >>> GPR00: d0000000016a569c c0000001fa5778f0 d0000000016b0400 0000000000000000
> >>> GPR04: 0000000000000002 0000000000000000 80000001fa46418e c0000001fa0d05c8
> >>> GPR08: d0000000016b0400 d00037fffff13000 00000001ff3e7000 d0000000016a6fb8
> >>> GPR12: c0000000006f560c c00000000ffff780 0000000000000000 0000000000000000
> >>> GPR16: 0000000011635010 00003fffa1b7aa68 0000000000000000 0000000000000000
> >>> GPR20: 0000000000000003 0000000010013918 00000000116350c0 c000000000b88990
> >>> GPR24: c000000000b88ba4 0000000000000000 d0000001fff12f34 0000000000000000
> >>> GPR28: d0000000016b8000 c0000001fa20f400 c0000001fa20f440 0000000000000000
> >>> [ 91.139627] NIP [d0000000016a5718] .alloc_counters.isra.10+0xbc/0x140 [ip_tables]
> >>> [ 91.139634] LR [d0000000016a569c] .alloc_counters.isra.10+0x40/0x140 [ip_tables]
> >>> [ 91.139638] Call Trace:
> >>> [ 91.139645] [c0000001fa5778f0] [d0000000016a569c] .alloc_counters.isra.10+0x40/0x140 [ip_tables] (unreliable)
> >>> [ 91.139655] [c0000001fa5779b0] [d0000000016a5b54] .do_ipt_get_ctl+0x110/0x2ec [ip_tables]
> >>> [ 91.139666] [c0000001fa577aa0] [c0000000006233e0] .nf_getsockopt+0x68/0x88
> >>> [ 91.139674] [c0000001fa577b40] [c000000000631608] .ip_getsockopt+0xbc/0x128
> >>> [ 91.139682] [c0000001fa577bf0] [c00000000065adf4] .raw_getsockopt+0x18/0x5c
> >>> [ 91.139690] [c0000001fa577c60] [c0000000005b5f60] .sock_common_getsockopt+0x2c/0x40
> >>> [ 91.139697] [c0000001fa577cd0] [c0000000005b3394] .__sys_getsockopt+0xa4/0xd0
> >>> [ 91.139704] [c0000001fa577d80] [c0000000005b5ab0] .__se_sys_socketcall+0x238/0x2b4
> >>> [ 91.139712] [c0000001fa577e30] [c00000000000a31c] system_call+0x5c/0x70
> >>> [ 91.139716] Instruction dump:
> >>> [ 91.139721] 39290040 7d3d4a14 7fbe4840 409cff98 81380000 2b890001 419d000c 393e0060
> >>> [ 91.139736] 48000010 7d57c82a e93e0060 7d295214 <815a0000> 794807e1 41e20010 7c210b78
> >>> [ 91.139752] ---[ end trace f5d1d5431651845d ]---
> >>
> >> This is due to 7290d58095 ("module: use relative references for
> >> __ksymtab entries"). This part of kernel/module.c -
> >>
> >> /* Divert to percpu allocation if a percpu var. */
> >> if (sym[i].st_shndx == info->index.pcpu)
> >> secbase = (unsigned long)mod_percpu(mod);
> >> else
> >> secbase = info->sechdrs[sym[i].st_shndx].sh_addr;
> >> sym[i].st_value += secbase;
> >>
> >> Causes the distance to the target to exceed 32-bits on powerpc, so
> >> it doesn't fit in a rel32 reloc. Not sure how other archs cope.
> >>
> >
> > Apologies for the breakage. It does indeed appear to affect all
> > architectures, and I'm a bit puzzled why you are the first one to spot
> > it.
> >
> > I will try to find a clean way to special case the per-CPU variable
> > __ksymtab references in the generic module code, and if that is too
> > cumbersome, we can switch to 64-bit relative references (or rather,
> > native word size relative references) instead. Or revert the whole
> > thing ...
>
> OK, after a bit of digging, and confirming that the arm64
> implementation works as expected (its module loader actually detects
> overflows of the 32-bit place relative relocations, so the problem
> definitely does not occur there), I think I found the explanation why
> this occurs on powerpc and not on x86 or arm64.
>
> Could you please check whether this change makes the issue go away?
> (whitespace damage courtesy of Gmail)
>
> diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
> index 6a501b25dd85..57d09d5ceb1a 100644
> --- a/arch/powerpc/kernel/setup_64.c
> +++ b/arch/powerpc/kernel/setup_64.c
> @@ -779,7 +779,6 @@ EXPORT_SYMBOL(__per_cpu_offset);
>
> void __init setup_per_cpu_areas(void)
> {
> - const size_t dyn_size = PERCPU_MODULE_RESERVE + PERCPU_DYNAMIC_RESERVE;
> size_t atom_size;
> unsigned long delta;
> unsigned int cpu;
> @@ -795,7 +794,9 @@ void __init setup_per_cpu_areas(void)
> else
> atom_size = 1 << 20;
>
> - rc = pcpu_embed_first_chunk(0, dyn_size, atom_size, pcpu_cpu_distance,
> + rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
> + PERCPU_DYNAMIC_RESERVE,
> + atom_size, pcpu_cpu_distance,
> pcpu_fc_alloc, pcpu_fc_free);
> if (rc < 0)
> panic("cannot initialize percpu area (err=%d)", rc);
>
> The git log does not explain why power deviates from x86 and arm64 in
> the way it initializes the percpu areas.
The reason for 64-bit powerpc is actually that modules are allocated in
vmalloc space which is a long way out from the linear map where the per
cpu embedded chunk is.
It does look like x86 and arm64 are probably okay because they set up a
module vmalloc area close to their kernel text in the linear map, which
should be close to per-cpu I guess.
I'm not entirely sure why pcpu setup is different on powerpc, but I
think the module vmalloc addresses bite first anyway.
Okay I'd say let's just remove powerpc for now.
Thanks,
Nick
^ permalink raw reply
* [PATCH net-next v2] net/tls: Add support for async decryption of tls records
From: Vakul Garg @ 2018-08-29 9:56 UTC (permalink / raw)
To: netdev; +Cc: borisp, aviadye, davejwatson, davem, Vakul Garg
When tls records are decrypted using asynchronous acclerators such as
NXP CAAM engine, the crypto apis return -EINPROGRESS. Presently, on
getting -EINPROGRESS, the tls record processing stops till the time the
crypto accelerator finishes off and returns the result. This incurs a
context switch and is not an efficient way of accessing the crypto
accelerators. Crypto accelerators work efficient when they are queued
with multiple crypto jobs without having to wait for the previous ones
to complete.
The patch submits multiple crypto requests without having to wait for
for previous ones to complete. This has been implemented for records
which are decrypted in zero-copy mode. At the end of recvmsg(), we wait
for all the asynchronous decryption requests to complete.
The references to records which have been sent for async decryption are
dropped. For cases where record decryption is not possible in zero-copy
mode, asynchronous decryption is not used and we wait for decryption
crypto api to complete.
For crypto requests executing in async fashion, the memory for
aead_request, sglists and skb etc is freed from the decryption
completion handler. The decryption completion handler wakesup the
sleeping user context when recvmsg() flags that it has done sending
all the decryption requests and there are no more decryption requests
pending to be completed.
Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Reviewed-by: Dave Watson <davejwatson@fb.com>
---
Changes since v1:
- Simplified recvmsg() so to drop reference to skb in case it
was submimtted for async decryption.
- Modified tls_sw_advance_skb() to handle case when input skb is
NULL.
include/net/tls.h | 6 +++
net/tls/tls_sw.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++++------
2 files changed, 127 insertions(+), 13 deletions(-)
diff --git a/include/net/tls.h b/include/net/tls.h
index d5c683e8bb22..cd0a65bd92f9 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -124,6 +124,12 @@ struct tls_sw_context_rx {
struct sk_buff *recv_pkt;
u8 control;
bool decrypted;
+ atomic_t decrypt_pending;
+ bool async_notify;
+};
+
+struct decrypt_req_ctx {
+ struct sock *sk;
};
struct tls_record_info {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 52fbe727d7c1..9503e5a4c27e 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -43,12 +43,50 @@
#define MAX_IV_SIZE TLS_CIPHER_AES_GCM_128_IV_SIZE
+static void tls_decrypt_done(struct crypto_async_request *req, int err)
+{
+ struct aead_request *aead_req = (struct aead_request *)req;
+ struct decrypt_req_ctx *req_ctx =
+ (struct decrypt_req_ctx *)(aead_req + 1);
+
+ struct scatterlist *sgout = aead_req->dst;
+
+ struct tls_context *tls_ctx = tls_get_ctx(req_ctx->sk);
+ struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+ int pending = atomic_dec_return(&ctx->decrypt_pending);
+ struct scatterlist *sg;
+ unsigned int pages;
+
+ /* Propagate if there was an err */
+ if (err) {
+ ctx->async_wait.err = err;
+ tls_err_abort(req_ctx->sk, err);
+ }
+
+ /* Release the skb, pages and memory allocated for crypto req */
+ kfree_skb(req->data);
+
+ /* Skip the first S/G entry as it points to AAD */
+ for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) {
+ if (!sg)
+ break;
+ put_page(sg_page(sg));
+ }
+
+ kfree(aead_req);
+
+ if (!pending && READ_ONCE(ctx->async_notify))
+ complete(&ctx->async_wait.completion);
+}
+
static int tls_do_decryption(struct sock *sk,
+ struct sk_buff *skb,
struct scatterlist *sgin,
struct scatterlist *sgout,
char *iv_recv,
size_t data_len,
- struct aead_request *aead_req)
+ struct aead_request *aead_req,
+ bool async)
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
@@ -59,10 +97,34 @@ static int tls_do_decryption(struct sock *sk,
aead_request_set_crypt(aead_req, sgin, sgout,
data_len + tls_ctx->rx.tag_size,
(u8 *)iv_recv);
- aead_request_set_callback(aead_req, CRYPTO_TFM_REQ_MAY_BACKLOG,
- crypto_req_done, &ctx->async_wait);
- ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait);
+ if (async) {
+ struct decrypt_req_ctx *req_ctx;
+
+ req_ctx = (struct decrypt_req_ctx *)(aead_req + 1);
+ req_ctx->sk = sk;
+
+ aead_request_set_callback(aead_req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG,
+ tls_decrypt_done, skb);
+ atomic_inc(&ctx->decrypt_pending);
+ } else {
+ aead_request_set_callback(aead_req,
+ CRYPTO_TFM_REQ_MAY_BACKLOG,
+ crypto_req_done, &ctx->async_wait);
+ }
+
+ ret = crypto_aead_decrypt(aead_req);
+ if (ret == -EINPROGRESS) {
+ if (async)
+ return ret;
+
+ ret = crypto_wait_req(ret, &ctx->async_wait);
+ }
+
+ if (async)
+ atomic_dec(&ctx->decrypt_pending);
+
return ret;
}
@@ -763,7 +825,10 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
}
/* Prepare and submit AEAD request */
- err = tls_do_decryption(sk, sgin, sgout, iv, data_len, aead_req);
+ err = tls_do_decryption(sk, skb, sgin, sgout, iv,
+ data_len, aead_req, *zc);
+ if (err == -EINPROGRESS)
+ return err;
/* Release the pages in case iov was mapped to pages */
for (; pages > 0; pages--)
@@ -788,8 +853,12 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
#endif
if (!ctx->decrypted) {
err = decrypt_internal(sk, skb, dest, NULL, chunk, zc);
- if (err < 0)
+ if (err < 0) {
+ if (err == -EINPROGRESS)
+ tls_advance_record_sn(sk, &tls_ctx->rx);
+
return err;
+ }
} else {
*zc = false;
}
@@ -817,18 +886,20 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb,
{
struct tls_context *tls_ctx = tls_get_ctx(sk);
struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
- struct strp_msg *rxm = strp_msg(skb);
- if (len < rxm->full_len) {
- rxm->offset += len;
- rxm->full_len -= len;
+ if (skb) {
+ struct strp_msg *rxm = strp_msg(skb);
- return false;
+ if (len < rxm->full_len) {
+ rxm->offset += len;
+ rxm->full_len -= len;
+ return false;
+ }
+ kfree_skb(skb);
}
/* Finished with message */
ctx->recv_pkt = NULL;
- kfree_skb(skb);
__strp_unpause(&ctx->strp);
return true;
@@ -851,6 +922,7 @@ int tls_sw_recvmsg(struct sock *sk,
int target, err = 0;
long timeo;
bool is_kvec = msg->msg_iter.type & ITER_KVEC;
+ int num_async = 0;
flags |= nonblock;
@@ -863,6 +935,7 @@ int tls_sw_recvmsg(struct sock *sk,
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
bool zc = false;
+ bool async = false;
int chunk = 0;
skb = tls_wait_data(sk, flags, timeo, &err);
@@ -870,6 +943,7 @@ int tls_sw_recvmsg(struct sock *sk,
goto recv_end;
rxm = strp_msg(skb);
+
if (!cmsg) {
int cerr;
@@ -896,26 +970,39 @@ int tls_sw_recvmsg(struct sock *sk,
err = decrypt_skb_update(sk, skb, &msg->msg_iter,
&chunk, &zc);
- if (err < 0) {
+ if (err < 0 && err != -EINPROGRESS) {
tls_err_abort(sk, EBADMSG);
goto recv_end;
}
+
+ if (err == -EINPROGRESS) {
+ async = true;
+ num_async++;
+ goto pick_next_record;
+ }
+
ctx->decrypted = true;
}
if (!zc) {
chunk = min_t(unsigned int, rxm->full_len, len);
+
err = skb_copy_datagram_msg(skb, rxm->offset, msg,
chunk);
if (err < 0)
goto recv_end;
}
+pick_next_record:
copied += chunk;
len -= chunk;
if (likely(!(flags & MSG_PEEK))) {
u8 control = ctx->control;
+ /* For async, drop current skb reference */
+ if (async)
+ skb = NULL;
+
if (tls_sw_advance_skb(sk, skb, chunk)) {
/* Return full control message to
* userspace before trying to parse
@@ -924,14 +1011,33 @@ int tls_sw_recvmsg(struct sock *sk,
msg->msg_flags |= MSG_EOR;
if (control != TLS_RECORD_TYPE_DATA)
goto recv_end;
+ } else {
+ break;
}
}
+
/* If we have a new message from strparser, continue now. */
if (copied >= target && !ctx->recv_pkt)
break;
} while (len);
recv_end:
+ if (num_async) {
+ /* Wait for all previously submitted records to be decrypted */
+ smp_store_mb(ctx->async_notify, true);
+ if (atomic_read(&ctx->decrypt_pending)) {
+ err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait);
+ if (err) {
+ /* one of async decrypt failed */
+ tls_err_abort(sk, err);
+ copied = 0;
+ }
+ } else {
+ reinit_completion(&ctx->async_wait.completion);
+ }
+ WRITE_ONCE(ctx->async_notify, false);
+ }
+
release_sock(sk);
return copied ? : err;
}
@@ -1271,6 +1377,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
goto free_aead;
if (sw_ctx_rx) {
+ (*aead)->reqsize = sizeof(struct decrypt_req_ctx);
+
/* Set up strparser */
memset(&cb, 0, sizeof(cb));
cb.rcv_msg = tls_queue;
--
2.13.6
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox