* [PATCH 09/58] net/irda: Convert timers to use timer_setup()
From: Kees Cook @ 2017-10-17 0:28 UTC (permalink / raw)
To: David S. Miller
Cc: Kees Cook, Samuel Ortiz, Stephen Hemminger, Johannes Berg,
Ingo Molnar, netdev, Thomas Gleixner, linux-kernel
In-Reply-To: <1508200182-104605-1-git-send-email-keescook@chromium.org>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Samuel Ortiz <samuel@sortiz.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
.../staging/irda/include/net/irda/irlmp_event.h | 6 +--
drivers/staging/irda/include/net/irda/timer.h | 11 ++---
drivers/staging/irda/net/af_irda.c | 7 ++-
drivers/staging/irda/net/ircomm/ircomm_tty.c | 2 +-
.../staging/irda/net/ircomm/ircomm_tty_attach.c | 8 ++--
drivers/staging/irda/net/irda_device.c | 10 ++--
drivers/staging/irda/net/iriap.c | 10 ++--
drivers/staging/irda/net/irlan/irlan_client.c | 6 +--
drivers/staging/irda/net/irlan/irlan_common.c | 4 +-
drivers/staging/irda/net/irlap.c | 16 +++----
drivers/staging/irda/net/irlap_event.c | 6 +--
drivers/staging/irda/net/irlmp.c | 8 ++--
drivers/staging/irda/net/irlmp_event.c | 10 ++--
drivers/staging/irda/net/irttp.c | 11 ++---
drivers/staging/irda/net/timer.c | 54 +++++++++++-----------
15 files changed, 79 insertions(+), 90 deletions(-)
diff --git a/drivers/staging/irda/include/net/irda/irlmp_event.h b/drivers/staging/irda/include/net/irda/irlmp_event.h
index 9e4ec17a7449..a1a082fe384e 100644
--- a/drivers/staging/irda/include/net/irda/irlmp_event.h
+++ b/drivers/staging/irda/include/net/irda/irlmp_event.h
@@ -82,9 +82,9 @@ typedef enum {
extern const char *const irlmp_state[];
extern const char *const irlsap_state[];
-void irlmp_watchdog_timer_expired(void *data);
-void irlmp_discovery_timer_expired(void *data);
-void irlmp_idle_timer_expired(void *data);
+void irlmp_watchdog_timer_expired(struct timer_list *t);
+void irlmp_discovery_timer_expired(struct timer_list *t);
+void irlmp_idle_timer_expired(struct timer_list *t);
void irlmp_do_lap_event(struct lap_cb *self, IRLMP_EVENT event,
struct sk_buff *skb);
diff --git a/drivers/staging/irda/include/net/irda/timer.h b/drivers/staging/irda/include/net/irda/timer.h
index d784f242cf7b..a6635f0afae9 100644
--- a/drivers/staging/irda/include/net/irda/timer.h
+++ b/drivers/staging/irda/include/net/irda/timer.h
@@ -72,14 +72,11 @@ struct lap_cb;
#define WATCHDOG_TIMEOUT (20*HZ) /* 20 sec */
-typedef void (*TIMER_CALLBACK)(void *);
-
-static inline void irda_start_timer(struct timer_list *ptimer, int timeout,
- void* data, TIMER_CALLBACK callback)
+static inline void irda_start_timer(struct timer_list *ptimer, int timeout,
+ void (*callback)(struct timer_list *))
{
- ptimer->function = (void (*)(unsigned long)) callback;
- ptimer->data = (unsigned long) data;
-
+ ptimer->function = (TIMER_FUNC_TYPE) callback;
+
/* Set new value for timer (update or add timer).
* We use mod_timer() because it's more efficient and also
* safer with respect to race conditions - Jean II */
diff --git a/drivers/staging/irda/net/af_irda.c b/drivers/staging/irda/net/af_irda.c
index 23fa7c8b09a5..b82a47b9ef0b 100644
--- a/drivers/staging/irda/net/af_irda.c
+++ b/drivers/staging/irda/net/af_irda.c
@@ -429,11 +429,11 @@ static void irda_selective_discovery_indication(discinfo_t *discovery,
* We were waiting for a node to be discovered, but nothing has come up
* so far. Wake up the user and tell him that we failed...
*/
-static void irda_discovery_timeout(u_long priv)
+static void irda_discovery_timeout(struct timer_list *t)
{
struct irda_sock *self;
- self = (struct irda_sock *) priv;
+ self = from_timer(self, t, watchdog);
BUG_ON(self == NULL);
/* Nothing for the caller */
@@ -2505,8 +2505,7 @@ static int irda_getsockopt(struct socket *sock, int level, int optname,
/* Set watchdog timer to expire in <val> ms. */
self->errno = 0;
- setup_timer(&self->watchdog, irda_discovery_timeout,
- (unsigned long)self);
+ timer_setup(&self->watchdog, irda_discovery_timeout, 0);
mod_timer(&self->watchdog,
jiffies + msecs_to_jiffies(val));
diff --git a/drivers/staging/irda/net/ircomm/ircomm_tty.c b/drivers/staging/irda/net/ircomm/ircomm_tty.c
index ec157c3419b5..473abfaffe7b 100644
--- a/drivers/staging/irda/net/ircomm/ircomm_tty.c
+++ b/drivers/staging/irda/net/ircomm/ircomm_tty.c
@@ -395,7 +395,7 @@ static int ircomm_tty_install(struct tty_driver *driver, struct tty_struct *tty)
self->max_data_size = IRCOMM_TTY_DATA_UNINITIALISED;
/* Init some important stuff */
- init_timer(&self->watchdog_timer);
+ timer_setup(&self->watchdog_timer, NULL, 0);
spin_lock_init(&self->spinlock);
/*
diff --git a/drivers/staging/irda/net/ircomm/ircomm_tty_attach.c b/drivers/staging/irda/net/ircomm/ircomm_tty_attach.c
index 0a411019c098..e2d5ce8ba0db 100644
--- a/drivers/staging/irda/net/ircomm/ircomm_tty_attach.c
+++ b/drivers/staging/irda/net/ircomm/ircomm_tty_attach.c
@@ -52,7 +52,7 @@ static void ircomm_tty_getvalue_confirm(int result, __u16 obj_id,
struct ias_value *value, void *priv);
static void ircomm_tty_start_watchdog_timer(struct ircomm_tty_cb *self,
int timeout);
-static void ircomm_tty_watchdog_timer_expired(void *data);
+static void ircomm_tty_watchdog_timer_expired(struct timer_list *timer);
static int ircomm_tty_state_idle(struct ircomm_tty_cb *self,
IRCOMM_TTY_EVENT event,
@@ -587,7 +587,7 @@ static void ircomm_tty_start_watchdog_timer(struct ircomm_tty_cb *self,
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
- irda_start_timer(&self->watchdog_timer, timeout, (void *) self,
+ irda_start_timer(&self->watchdog_timer, timeout,
ircomm_tty_watchdog_timer_expired);
}
@@ -597,9 +597,9 @@ static void ircomm_tty_start_watchdog_timer(struct ircomm_tty_cb *self,
* Called when the connect procedure have taken to much time.
*
*/
-static void ircomm_tty_watchdog_timer_expired(void *data)
+static void ircomm_tty_watchdog_timer_expired(struct timer_list *t)
{
- struct ircomm_tty_cb *self = (struct ircomm_tty_cb *) data;
+ struct ircomm_tty_cb *self = from_timer(self, t, watchdog_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == IRCOMM_TTY_MAGIC, return;);
diff --git a/drivers/staging/irda/net/irda_device.c b/drivers/staging/irda/net/irda_device.c
index d33de8a8762a..682b4eea15e0 100644
--- a/drivers/staging/irda/net/irda_device.c
+++ b/drivers/staging/irda/net/irda_device.c
@@ -57,7 +57,7 @@ static void __irda_task_delete(struct irda_task *task);
static hashbin_t *dongles;
static hashbin_t *tasks;
-static void irda_task_timer_expired(void *data);
+static void irda_task_timer_expired(struct timer_list *timer);
int __init irda_device_init(void)
{
@@ -233,7 +233,7 @@ static int irda_task_kick(struct irda_task *task)
}
irda_task_delete(task);
} else if (timeout > 0) {
- irda_start_timer(&task->timer, timeout, (void *)task,
+ irda_start_timer(&task->timer, timeout,
irda_task_timer_expired);
finished = FALSE;
} else {
@@ -251,11 +251,9 @@ static int irda_task_kick(struct irda_task *task)
* Task time has expired. We now try to execute task (again), and restart
* the timer if the task has not finished yet
*/
-static void irda_task_timer_expired(void *data)
+static void irda_task_timer_expired(struct timer_list *t)
{
- struct irda_task *task;
-
- task = data;
+ struct irda_task *task = from_timer(task, t, timer);
irda_task_kick(task);
}
diff --git a/drivers/staging/irda/net/iriap.c b/drivers/staging/irda/net/iriap.c
index 1138eaf5c682..d64192e9db8b 100644
--- a/drivers/staging/irda/net/iriap.c
+++ b/drivers/staging/irda/net/iriap.c
@@ -76,12 +76,12 @@ static void iriap_connect_confirm(void *instance, void *sap,
static int iriap_data_indication(void *instance, void *sap,
struct sk_buff *skb);
-static void iriap_watchdog_timer_expired(void *data);
+static void iriap_watchdog_timer_expired(struct timer_list *t);
static inline void iriap_start_watchdog_timer(struct iriap_cb *self,
int timeout)
{
- irda_start_timer(&self->watchdog_timer, timeout, self,
+ irda_start_timer(&self->watchdog_timer, timeout,
iriap_watchdog_timer_expired);
}
@@ -199,7 +199,7 @@ struct iriap_cb *iriap_open(__u8 slsap_sel, int mode, void *priv,
* we connect, so this must have a sane value... Jean II */
self->max_header_size = LMP_MAX_HEADER;
- init_timer(&self->watchdog_timer);
+ timer_setup(&self->watchdog_timer, NULL, 0);
hashbin_insert(iriap, (irda_queue_t *) self, (long) self, NULL);
@@ -946,9 +946,9 @@ void iriap_call_indication(struct iriap_cb *self, struct sk_buff *skb)
* Query has taken too long time, so abort
*
*/
-static void iriap_watchdog_timer_expired(void *data)
+static void iriap_watchdog_timer_expired(struct timer_list *t)
{
- struct iriap_cb *self = (struct iriap_cb *) data;
+ struct iriap_cb *self = from_timer(self, t, watchdog_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == IAS_MAGIC, return;);
diff --git a/drivers/staging/irda/net/irlan/irlan_client.c b/drivers/staging/irda/net/irlan/irlan_client.c
index c5837a40c78e..0b65e80849ae 100644
--- a/drivers/staging/irda/net/irlan/irlan_client.c
+++ b/drivers/staging/irda/net/irlan/irlan_client.c
@@ -68,9 +68,9 @@ static void irlan_check_response_param(struct irlan_cb *self, char *param,
char *value, int val_len);
static void irlan_client_open_ctrl_tsap(struct irlan_cb *self);
-static void irlan_client_kick_timer_expired(void *data)
+static void irlan_client_kick_timer_expired(struct timer_list *t)
{
- struct irlan_cb *self = (struct irlan_cb *) data;
+ struct irlan_cb *self = from_timer(self, t, client.kick_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;);
@@ -89,7 +89,7 @@ static void irlan_client_kick_timer_expired(void *data)
static void irlan_client_start_kick_timer(struct irlan_cb *self, int timeout)
{
- irda_start_timer(&self->client.kick_timer, timeout, (void *) self,
+ irda_start_timer(&self->client.kick_timer, timeout,
irlan_client_kick_timer_expired);
}
diff --git a/drivers/staging/irda/net/irlan/irlan_common.c b/drivers/staging/irda/net/irlan/irlan_common.c
index 481bbc2a4349..fdcd7147007d 100644
--- a/drivers/staging/irda/net/irlan/irlan_common.c
+++ b/drivers/staging/irda/net/irlan/irlan_common.c
@@ -228,8 +228,8 @@ static struct irlan_cb __init *irlan_open(__u32 saddr, __u32 daddr)
self->media = MEDIA_802_3;
self->disconnect_reason = LM_USER_REQUEST;
- init_timer(&self->watchdog_timer);
- init_timer(&self->client.kick_timer);
+ timer_setup(&self->watchdog_timer, NULL, 0);
+ timer_setup(&self->client.kick_timer, NULL, 0);
init_waitqueue_head(&self->open_wait);
skb_queue_head_init(&self->client.txq);
diff --git a/drivers/staging/irda/net/irlap.c b/drivers/staging/irda/net/irlap.c
index 1cde711bcab5..d7d894423b4f 100644
--- a/drivers/staging/irda/net/irlap.c
+++ b/drivers/staging/irda/net/irlap.c
@@ -148,14 +148,14 @@ struct irlap_cb *irlap_open(struct net_device *dev, struct qos_info *qos,
/* Copy to the driver */
memcpy(dev->dev_addr, &self->saddr, 4);
- init_timer(&self->slot_timer);
- init_timer(&self->query_timer);
- init_timer(&self->discovery_timer);
- init_timer(&self->final_timer);
- init_timer(&self->poll_timer);
- init_timer(&self->wd_timer);
- init_timer(&self->backoff_timer);
- init_timer(&self->media_busy_timer);
+ timer_setup(&self->slot_timer, NULL, 0);
+ timer_setup(&self->query_timer, NULL, 0);
+ timer_setup(&self->discovery_timer, NULL, 0);
+ timer_setup(&self->final_timer, NULL, 0);
+ timer_setup(&self->poll_timer, NULL, 0);
+ timer_setup(&self->wd_timer, NULL, 0);
+ timer_setup(&self->backoff_timer, NULL, 0);
+ timer_setup(&self->media_busy_timer, NULL, 0);
irlap_apply_default_connection_parameters(self);
diff --git a/drivers/staging/irda/net/irlap_event.c b/drivers/staging/irda/net/irlap_event.c
index 0e1b4d79f745..634188b07e0a 100644
--- a/drivers/staging/irda/net/irlap_event.c
+++ b/drivers/staging/irda/net/irlap_event.c
@@ -163,9 +163,9 @@ static int (*state[])(struct irlap_cb *self, IRLAP_EVENT event,
* Poll timer has expired. Normally we must now send a RR frame to the
* remote device
*/
-static void irlap_poll_timer_expired(void *data)
+static void irlap_poll_timer_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, poll_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -222,7 +222,7 @@ static void irlap_start_poll_timer(struct irlap_cb *self, int timeout)
if (timeout == 0)
irlap_do_event(self, POLL_TIMER_EXPIRED, NULL, NULL);
else
- irda_start_timer(&self->poll_timer, timeout, self,
+ irda_start_timer(&self->poll_timer, timeout,
irlap_poll_timer_expired);
}
diff --git a/drivers/staging/irda/net/irlmp.c b/drivers/staging/irda/net/irlmp.c
index 43964594aa12..34355061ab0b 100644
--- a/drivers/staging/irda/net/irlmp.c
+++ b/drivers/staging/irda/net/irlmp.c
@@ -109,7 +109,7 @@ int __init irlmp_init(void)
irlmp->last_lsap_sel = 0x0f; /* Reserved 0x00-0x0f */
strcpy(sysctl_devname, "Linux");
- init_timer(&irlmp->discovery_timer);
+ timer_setup(&irlmp->discovery_timer, NULL, 0);
/* Do discovery every 3 seconds, conditionally */
if (sysctl_discovery)
@@ -185,7 +185,7 @@ struct lsap_cb *irlmp_open_lsap(__u8 slsap_sel, notify_t *notify, __u8 pid)
self->dlsap_sel = LSAP_ANY;
/* self->connected = FALSE; -> already NULL via memset() */
- init_timer(&self->watchdog_timer);
+ timer_setup(&self->watchdog_timer, NULL, 0);
self->notify = *notify;
@@ -311,7 +311,7 @@ void irlmp_register_link(struct irlap_cb *irlap, __u32 saddr, notify_t *notify)
lap->lap_state = LAP_STANDBY;
- init_timer(&lap->idle_timer);
+ timer_setup(&lap->idle_timer, NULL, 0);
/*
* Insert into queue of LMP links
@@ -655,7 +655,7 @@ struct lsap_cb *irlmp_dup(struct lsap_cb *orig, void *instance)
/* Not everything is the same */
new->notify.instance = instance;
- init_timer(&new->watchdog_timer);
+ timer_setup(&new->watchdog_timer, NULL, 0);
hashbin_insert(irlmp->unconnected_lsaps, (irda_queue_t *) new,
(long) new, NULL);
diff --git a/drivers/staging/irda/net/irlmp_event.c b/drivers/staging/irda/net/irlmp_event.c
index e306cf2c1e04..ddad0994b6dc 100644
--- a/drivers/staging/irda/net/irlmp_event.c
+++ b/drivers/staging/irda/net/irlmp_event.c
@@ -165,7 +165,7 @@ void irlmp_do_lap_event(struct lap_cb *self, IRLMP_EVENT event,
(*lap_state[self->lap_state]) (self, event, skb);
}
-void irlmp_discovery_timer_expired(void *data)
+void irlmp_discovery_timer_expired(struct timer_list *t)
{
/* We always cleanup the log (active & passive discovery) */
irlmp_do_expiry();
@@ -176,9 +176,9 @@ void irlmp_discovery_timer_expired(void *data)
irlmp_start_discovery_timer(irlmp, sysctl_discovery_timeout * HZ);
}
-void irlmp_watchdog_timer_expired(void *data)
+void irlmp_watchdog_timer_expired(struct timer_list *t)
{
- struct lsap_cb *self = (struct lsap_cb *) data;
+ struct lsap_cb *self = from_timer(self, t, watchdog_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LMP_LSAP_MAGIC, return;);
@@ -186,9 +186,9 @@ void irlmp_watchdog_timer_expired(void *data)
irlmp_do_lsap_event(self, LM_WATCHDOG_TIMEOUT, NULL);
}
-void irlmp_idle_timer_expired(void *data)
+void irlmp_idle_timer_expired(struct timer_list *t)
{
- struct lap_cb *self = (struct lap_cb *) data;
+ struct lap_cb *self = from_timer(self, t, idle_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LMP_LAP_MAGIC, return;);
diff --git a/drivers/staging/irda/net/irttp.c b/drivers/staging/irda/net/irttp.c
index b6ab41d5b3a3..741a94f39b4e 100644
--- a/drivers/staging/irda/net/irttp.c
+++ b/drivers/staging/irda/net/irttp.c
@@ -62,7 +62,6 @@ static void irttp_run_rx_queue(struct tsap_cb *self);
static void irttp_flush_queues(struct tsap_cb *self);
static void irttp_fragment_skb(struct tsap_cb *self, struct sk_buff *skb);
static struct sk_buff *irttp_reassemble_skb(struct tsap_cb *self);
-static void irttp_todo_expired(unsigned long data);
static int irttp_param_max_sdu_size(void *instance, irda_param_t *param,
int get);
@@ -160,9 +159,9 @@ static inline void irttp_start_todo_timer(struct tsap_cb *self, int timeout)
* killed (need user context), and we can't guarantee that here...
* Jean II
*/
-static void irttp_todo_expired(unsigned long data)
+static void irttp_todo_expired(struct timer_list *t)
{
- struct tsap_cb *self = (struct tsap_cb *) data;
+ struct tsap_cb *self = from_timer(self, t, todo_timer);
/* Check that we still exist */
if (!self || self->magic != TTP_TSAP_MAGIC)
@@ -374,7 +373,7 @@ static int irttp_param_max_sdu_size(void *instance, irda_param_t *param,
static void irttp_init_tsap(struct tsap_cb *tsap)
{
spin_lock_init(&tsap->lock);
- init_timer(&tsap->todo_timer);
+ timer_setup(&tsap->todo_timer, irttp_todo_expired, 0);
skb_queue_head_init(&tsap->rx_queue);
skb_queue_head_init(&tsap->tx_queue);
@@ -410,10 +409,6 @@ struct tsap_cb *irttp_open_tsap(__u8 stsap_sel, int credit, notify_t *notify)
/* Initialize internal objects */
irttp_init_tsap(self);
- /* Initialise todo timer */
- self->todo_timer.data = (unsigned long) self;
- self->todo_timer.function = &irttp_todo_expired;
-
/* Initialize callbacks for IrLMP to use */
irda_notify_init(&ttp_notify);
ttp_notify.connect_confirm = irttp_connect_confirm;
diff --git a/drivers/staging/irda/net/timer.c b/drivers/staging/irda/net/timer.c
index f2280f73b057..cf00c0d848aa 100644
--- a/drivers/staging/irda/net/timer.c
+++ b/drivers/staging/irda/net/timer.c
@@ -34,16 +34,16 @@
extern int sysctl_slot_timeout;
-static void irlap_slot_timer_expired(void* data);
-static void irlap_query_timer_expired(void* data);
-static void irlap_final_timer_expired(void* data);
-static void irlap_wd_timer_expired(void* data);
-static void irlap_backoff_timer_expired(void* data);
-static void irlap_media_busy_expired(void* data);
+static void irlap_slot_timer_expired(struct timer_list *t);
+static void irlap_query_timer_expired(struct timer_list *t);
+static void irlap_final_timer_expired(struct timer_list *t);
+static void irlap_wd_timer_expired(struct timer_list *t);
+static void irlap_backoff_timer_expired(struct timer_list *t);
+static void irlap_media_busy_expired(struct timer_list *t);
void irlap_start_slot_timer(struct irlap_cb *self, int timeout)
{
- irda_start_timer(&self->slot_timer, timeout, (void *) self,
+ irda_start_timer(&self->slot_timer, timeout,
irlap_slot_timer_expired);
}
@@ -66,32 +66,32 @@ void irlap_start_query_timer(struct irlap_cb *self, int S, int s)
/* Set or re-set the timer. We reset the timer for each received
* discovery query, which allow us to automatically adjust to
* the speed of the peer discovery (faster or slower). Jean II */
- irda_start_timer( &self->query_timer, timeout, (void *) self,
+ irda_start_timer(&self->query_timer, timeout,
irlap_query_timer_expired);
}
void irlap_start_final_timer(struct irlap_cb *self, int timeout)
{
- irda_start_timer(&self->final_timer, timeout, (void *) self,
+ irda_start_timer(&self->final_timer, timeout,
irlap_final_timer_expired);
}
void irlap_start_wd_timer(struct irlap_cb *self, int timeout)
{
- irda_start_timer(&self->wd_timer, timeout, (void *) self,
+ irda_start_timer(&self->wd_timer, timeout,
irlap_wd_timer_expired);
}
void irlap_start_backoff_timer(struct irlap_cb *self, int timeout)
{
- irda_start_timer(&self->backoff_timer, timeout, (void *) self,
+ irda_start_timer(&self->backoff_timer, timeout,
irlap_backoff_timer_expired);
}
void irlap_start_mbusy_timer(struct irlap_cb *self, int timeout)
{
irda_start_timer(&self->media_busy_timer, timeout,
- (void *) self, irlap_media_busy_expired);
+ irlap_media_busy_expired);
}
void irlap_stop_mbusy_timer(struct irlap_cb *self)
@@ -110,19 +110,19 @@ void irlap_stop_mbusy_timer(struct irlap_cb *self)
void irlmp_start_watchdog_timer(struct lsap_cb *self, int timeout)
{
- irda_start_timer(&self->watchdog_timer, timeout, (void *) self,
+ irda_start_timer(&self->watchdog_timer, timeout,
irlmp_watchdog_timer_expired);
}
void irlmp_start_discovery_timer(struct irlmp_cb *self, int timeout)
{
- irda_start_timer(&self->discovery_timer, timeout, (void *) self,
+ irda_start_timer(&self->discovery_timer, timeout,
irlmp_discovery_timer_expired);
}
void irlmp_start_idle_timer(struct lap_cb *self, int timeout)
{
- irda_start_timer(&self->idle_timer, timeout, (void *) self,
+ irda_start_timer(&self->idle_timer, timeout,
irlmp_idle_timer_expired);
}
@@ -138,9 +138,9 @@ void irlmp_stop_idle_timer(struct lap_cb *self)
* IrLAP slot timer has expired
*
*/
-static void irlap_slot_timer_expired(void *data)
+static void irlap_slot_timer_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, slot_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -154,9 +154,9 @@ static void irlap_slot_timer_expired(void *data)
* IrLAP query timer has expired
*
*/
-static void irlap_query_timer_expired(void *data)
+static void irlap_query_timer_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, query_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -170,9 +170,9 @@ static void irlap_query_timer_expired(void *data)
*
*
*/
-static void irlap_final_timer_expired(void *data)
+static void irlap_final_timer_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, final_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -186,9 +186,9 @@ static void irlap_final_timer_expired(void *data)
*
*
*/
-static void irlap_wd_timer_expired(void *data)
+static void irlap_wd_timer_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, wd_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -202,9 +202,9 @@ static void irlap_wd_timer_expired(void *data)
*
*
*/
-static void irlap_backoff_timer_expired(void *data)
+static void irlap_backoff_timer_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, backoff_timer);
IRDA_ASSERT(self != NULL, return;);
IRDA_ASSERT(self->magic == LAP_MAGIC, return;);
@@ -218,9 +218,9 @@ static void irlap_backoff_timer_expired(void *data)
*
*
*/
-static void irlap_media_busy_expired(void *data)
+static void irlap_media_busy_expired(struct timer_list *t)
{
- struct irlap_cb *self = (struct irlap_cb *) data;
+ struct irlap_cb *self = from_timer(self, t, media_busy_timer);
IRDA_ASSERT(self != NULL, return;);
--
2.7.4
^ permalink raw reply related
* Re: RFC(v2): Audit Kernel Container IDs
From: Richard Guy Briggs @ 2017-10-17 0:33 UTC (permalink / raw)
To: Casey Schaufler
Cc: cgroups, Linux Containers, Linux API, Linux Audit, Linux FS Devel,
Linux Kernel, Linux Network Development, mszeredi,
Andy Lutomirski, jlayton, Carlos O'Donell, Al Viro,
David Howells, Simo Sorce, trondmy, Eric Paris, Serge E. Hallyn,
Eric W. Biederman
In-Reply-To: <75b7d6a6-42ba-2dff-1836-1091c7c024e7@schaufler-ca.com>
On 2017-10-12 16:33, Casey Schaufler wrote:
> On 10/12/2017 7:14 AM, Richard Guy Briggs wrote:
> > Containers are a userspace concept. The kernel knows nothing of them.
> >
> > The Linux audit system needs a way to be able to track the container
> > provenance of events and actions. Audit needs the kernel's help to do
> > this.
> >
> > Since the concept of a container is entirely a userspace concept, a
> > registration from the userspace container orchestration system initiates
> > this. This will define a point in time and a set of resources
> > associated with a particular container with an audit container ID.
> >
> > The registration is a pseudo filesystem (proc, since PID tree already
> > exists) write of a u8[16] UUID representing the container ID to a file
> > representing a process that will become the first process in a new
> > container. This write might place restrictions on mount namespaces
> > required to define a container, or at least careful checking of
> > namespaces in the kernel to verify permissions of the orchestrator so it
> > can't change its own container ID. A bind mount of nsfs may be
> > necessary in the container orchestrator's mntNS.
> > Note: Use a 128-bit scalar rather than a string to make compares faster
> > and simpler.
> >
> > Require a new CAP_CONTAINER_ADMIN to be able to carry out the
> > registration.
>
> Hang on. If containers are a user space concept, how can
> you want CAP_CONTAINER_ANYTHING? If there's not such thing as
> a container, how can you be asking for a capability to manage
> them?
There is such a thing, but the kernel doesn't know about it yet. This
same situation exists for loginuid and sessionid which are userspace
concepts that the kernel tracks for the convenience of userspace. As
for its name, I'm not particularly picky, so if you don't like
CAP_CONTAINER_* then I'm fine with CAP_AUDIT_CONTAINERID. It really
needs to be distinct from CAP_AUDIT_WRITE and CAP_AUDIT_CONTROL since we
don't want to give the ability to set a containerID to any process that
is able to do audit logging (such as vsftpd) and similarly we don't want
to give the orchestrator the ability to control the setup of the audit
daemon.
>
> > At that time, record the target container's user-supplied
> > container identifier along with the target container's first process
> > (which may become the target container's "init" process) process ID
> > (referenced from the initial PID namespace), all namespace IDs (in the
> > form of a nsfs device number and inode number tuple) in a new auxilliary
> > record AUDIT_CONTAINER with a qualifying op=$action field.
> >
> > Issue a new auxilliary record AUDIT_CONTAINER_INFO for each valid
> > container ID present on an auditable action or event.
> >
> > Forked and cloned processes inherit their parent's container ID,
> > referenced in the process' task_struct.
> >
> > Mimic setns(2) and return an error if the process has already initiated
> > threading or forked since this registration should happen before the
> > process execution is started by the orchestrator and hence should not
> > yet have any threads or children. If this is deemed overly restrictive,
> > switch all threads and children to the new containerID.
> >
> > Trust the orchestrator to judiciously use and restrict CAP_CONTAINER_ADMIN.
> >
> > Log the creation of every namespace, inheriting/adding its spawning
> > process' containerID(s), if applicable. Include the spawning and
> > spawned namespace IDs (device and inode number tuples).
> > [AUDIT_NS_CREATE, AUDIT_NS_DESTROY] [clone(2), unshare(2), setns(2)]
> > Note: At this point it appears only network namespaces may need to track
> > container IDs apart from processes since incoming packets may cause an
> > auditable event before being associated with a process.
> >
> > Log the destruction of every namespace when it is no longer used by any
> > process, include the namespace IDs (device and inode number tuples).
> > [AUDIT_NS_DESTROY] [process exit, unshare(2), setns(2)]
> >
> > Issue a new auxilliary record AUDIT_NS_CHANGE listing (opt: op=$action)
> > the parent and child namespace IDs for any changes to a process'
> > namespaces. [setns(2)]
> > Note: It may be possible to combine AUDIT_NS_* record formats and
> > distinguish them with an op=$action field depending on the fields
> > required for each message type.
> >
> > When a container ceases to exist because the last process in that
> > container has exited and hence the last namespace has been destroyed and
> > its refcount dropping to zero, log the fact.
> > (This latter is likely needed for certification accountability.) A
> > container object may need a list of processes and/or namespaces.
> >
> > A namespace cannot directly migrate from one container to another but
> > could be assigned to a newly spawned container. A namespace can be
> > moved from one container to another indirectly by having that namespace
> > used in a second process in another container and then ending all the
> > processes in the first container.
> >
> > (v2)
> > - switch from u64 to u128 UUID
> > - switch from "signal" and "trigger" to "register"
> > - restrict registration to single process or force all threads and children into same container
> >
> > - RGB
- RGB
--
Richard Guy Briggs <rgb@redhat.com>
Sr. S/W Engineer, Kernel Security, Base Operating Systems
Remote, Ottawa, Red Hat Canada
IRC: rgb, SunRaycer
Voice: +1.647.777.2635, Internal: (81) 32635
^ permalink raw reply
* [PATCH 16/58] net: ethernet: stmmac: Convert timers to use timer_setup()
From: Kees Cook @ 2017-10-17 0:29 UTC (permalink / raw)
To: David S. Miller
Cc: Kees Cook, Giuseppe Cavallaro, Alexandre Torgue, netdev,
Thomas Gleixner, linux-kernel
In-Reply-To: <1508200182-104605-1-git-send-email-keescook@chromium.org>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Giuseppe Cavallaro <peppe.cavallaro@st.com>
---
drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c | 22 ++++++++++------------
1 file changed, 10 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
index 6a9c954492f2..8b50afcdb52d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
+++ b/drivers/net/ethernet/stmicro/stmmac/altr_tse_pcs.c
@@ -118,10 +118,9 @@ int tse_pcs_init(void __iomem *base, struct tse_pcs *pcs)
return ret;
}
-static void pcs_link_timer_callback(unsigned long data)
+static void pcs_link_timer_callback(struct tse_pcs *pcs)
{
u16 val = 0;
- struct tse_pcs *pcs = (struct tse_pcs *)data;
void __iomem *tse_pcs_base = pcs->tse_pcs_base;
void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base;
@@ -138,12 +137,11 @@ static void pcs_link_timer_callback(unsigned long data)
}
}
-static void auto_nego_timer_callback(unsigned long data)
+static void auto_nego_timer_callback(struct tse_pcs *pcs)
{
u16 val = 0;
u16 speed = 0;
u16 duplex = 0;
- struct tse_pcs *pcs = (struct tse_pcs *)data;
void __iomem *tse_pcs_base = pcs->tse_pcs_base;
void __iomem *sgmii_adapter_base = pcs->sgmii_adapter_base;
@@ -201,14 +199,14 @@ static void auto_nego_timer_callback(unsigned long data)
}
}
-static void aneg_link_timer_callback(unsigned long data)
+static void aneg_link_timer_callback(struct timer_list *t)
{
- struct tse_pcs *pcs = (struct tse_pcs *)data;
+ struct tse_pcs *pcs = from_timer(pcs, t, aneg_link_timer);
if (pcs->autoneg == AUTONEG_ENABLE)
- auto_nego_timer_callback(data);
+ auto_nego_timer_callback(pcs);
else if (pcs->autoneg == AUTONEG_DISABLE)
- pcs_link_timer_callback(data);
+ pcs_link_timer_callback(pcs);
}
void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev,
@@ -237,8 +235,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev,
tse_pcs_reset(tse_pcs_base, pcs);
- setup_timer(&pcs->aneg_link_timer,
- aneg_link_timer_callback, (unsigned long)pcs);
+ timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback,
+ 0);
mod_timer(&pcs->aneg_link_timer, jiffies +
msecs_to_jiffies(AUTONEGO_LINK_TIMER));
} else if (phy_dev->autoneg == AUTONEG_DISABLE) {
@@ -270,8 +268,8 @@ void tse_pcs_fix_mac_speed(struct tse_pcs *pcs, struct phy_device *phy_dev,
tse_pcs_reset(tse_pcs_base, pcs);
- setup_timer(&pcs->aneg_link_timer,
- aneg_link_timer_callback, (unsigned long)pcs);
+ timer_setup(&pcs->aneg_link_timer, aneg_link_timer_callback,
+ 0);
mod_timer(&pcs->aneg_link_timer, jiffies +
msecs_to_jiffies(AUTONEGO_LINK_TIMER));
}
--
2.7.4
^ permalink raw reply related
* Re: Linux 4.12+ memory leak on router with i40e NICs
From: Paweł Staszewski @ 2017-10-17 0:44 UTC (permalink / raw)
To: Alexander Duyck
Cc: Pavlos Parissis, Anders K. Pedersen | Cohaesio,
netdev@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
alexander.h.duyck@intel.com
In-Reply-To: <CAKgT0Uf=0yasidUfyadNSxzkhKvtxH2t83fjb-SU7OaAnrMReA@mail.gmail.com>
W dniu 2017-10-17 o 01:56, Alexander Duyck pisze:
> On Mon, Oct 16, 2017 at 4:34 PM, Paweł Staszewski <pstaszewski@itcare.pl> wrote:
>>
>> W dniu 2017-10-16 o 18:26, Paweł Staszewski pisze:
>>
>>>
>>> W dniu 2017-10-16 o 13:20, Pavlos Parissis pisze:
>>>> On 15/10/2017 02:58 πμ, Alexander Duyck wrote:
>>>>> Hi Pawel,
>>>>>
>>>>> To clarify is that Dave Miller's tree or Linus's that you are talking
>>>>> about? If it is Dave's tree how long ago was it you pulled it since I
>>>>> think the fix was just pushed by Jeff Kirsher a few days ago.
>>>>>
>>>>> The issue should be fixed in the following commit:
>>>>>
>>>>> https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/commit/drivers/net/ethernet/intel/i40e/i40e_txrx.c?id=2b9478ffc550f17c6cd8c69057234e91150f5972
>>>>>
>>>> Do you know when it is going to be available on net-next and linux-stable
>>>> repos?
>>>>
>>>> Cheers,
>>>> Pavlos
>>>>
>>>>
>>> I will make some tests today night with "net" git tree where this patch is
>>> included.
>>> Starting from 0:00 CET
>>> :)
>>>
>>>
>> Upgraded and looks like problem is not solved with that patch
>> Currently running system with
>> https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git/
>> kernel
>>
>> Still about 0.5GB of memory is leaking somewhere
>>
>> Also can confirm that the latest kernel where memory is not leaking (with
>> use i40e driver intel 710 cards) is 4.11.12
>> With kernel 4.11.12 - after hour no change in memory usage.
>>
>> also checked that with ixgbe instead of i40e with same net.git kernel there
>> is no memleak - after hour same memory usage - so for 100% this is i40e
>> driver problem.
> So how long was the run to get the .5GB of memory leaking?
1 hour
>
> Also is there any chance of you being able to bisect to determine
> where the memory leak was introduced since as you pointed out it
> didn't exist in 4.11.12 so odds are it was introduced somewhere
> between 4.11 and the latest kernel release.
Can be hard cause currently need to back to 4.11.12 - this is production
host/router
Will try to find some free/test router for tests/bicects with i40e
driver (intel 710 cards)
>
> Thanks.
>
> - Alex
>
^ permalink raw reply
* [PATCH 58/58] sunrpc: Convert timers to use timer_setup()
From: Kees Cook @ 2017-10-17 0:29 UTC (permalink / raw)
To: David S. Miller
Cc: Kees Cook, Trond Myklebust, Anna Schumaker, J. Bruce Fields,
Jeff Layton, linux-nfs, netdev, Thomas Gleixner, linux-kernel
In-Reply-To: <1508200182-104605-1-git-send-email-keescook@chromium.org>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Cc: Anna Schumaker <anna.schumaker@netapp.com>
Cc: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Jeff Layton <jlayton@poochiereds.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-nfs@vger.kernel.org
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
net/sunrpc/sched.c | 8 ++++----
net/sunrpc/svc.c | 2 +-
net/sunrpc/svc_xprt.c | 9 ++++-----
net/sunrpc/xprt.c | 9 ++++-----
4 files changed, 13 insertions(+), 15 deletions(-)
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index 0cc83839c13c..5dea47eb31bb 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -44,7 +44,7 @@ static mempool_t *rpc_buffer_mempool __read_mostly;
static void rpc_async_schedule(struct work_struct *);
static void rpc_release_task(struct rpc_task *task);
-static void __rpc_queue_timer_fn(unsigned long ptr);
+static void __rpc_queue_timer_fn(struct timer_list *t);
/*
* RPC tasks sit here while waiting for conditions to improve.
@@ -228,7 +228,7 @@ static void __rpc_init_priority_wait_queue(struct rpc_wait_queue *queue, const c
queue->maxpriority = nr_queues - 1;
rpc_reset_waitqueue_priority(queue);
queue->qlen = 0;
- setup_timer(&queue->timer_list.timer, __rpc_queue_timer_fn, (unsigned long)queue);
+ timer_setup(&queue->timer_list.timer, __rpc_queue_timer_fn, 0);
INIT_LIST_HEAD(&queue->timer_list.list);
rpc_assign_waitqueue_name(queue, qname);
}
@@ -635,9 +635,9 @@ void rpc_wake_up_status(struct rpc_wait_queue *queue, int status)
}
EXPORT_SYMBOL_GPL(rpc_wake_up_status);
-static void __rpc_queue_timer_fn(unsigned long ptr)
+static void __rpc_queue_timer_fn(struct timer_list *t)
{
- struct rpc_wait_queue *queue = (struct rpc_wait_queue *)ptr;
+ struct rpc_wait_queue *queue = from_timer(queue, t, timer_list.timer);
struct rpc_task *task, *n;
unsigned long expires, now, timeo;
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index aa04666f929d..33f4ae68426d 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -455,7 +455,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
serv->sv_xdrsize = xdrsize;
INIT_LIST_HEAD(&serv->sv_tempsocks);
INIT_LIST_HEAD(&serv->sv_permsocks);
- init_timer(&serv->sv_temptimer);
+ timer_setup(&serv->sv_temptimer, NULL, 0);
spin_lock_init(&serv->sv_lock);
__svc_init_bc(serv);
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index d16a8b423c20..71de77bd4423 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -28,7 +28,7 @@ module_param(svc_rpc_per_connection_limit, uint, 0644);
static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
static int svc_deferred_recv(struct svc_rqst *rqstp);
static struct cache_deferred_req *svc_defer(struct cache_req *req);
-static void svc_age_temp_xprts(unsigned long closure);
+static void svc_age_temp_xprts(struct timer_list *t);
static void svc_delete_xprt(struct svc_xprt *xprt);
/* apparently the "standard" is that clients close
@@ -785,8 +785,7 @@ static void svc_add_new_temp_xprt(struct svc_serv *serv, struct svc_xprt *newxpt
serv->sv_tmpcnt++;
if (serv->sv_temptimer.function == NULL) {
/* setup timer to age temp transports */
- setup_timer(&serv->sv_temptimer, svc_age_temp_xprts,
- (unsigned long)serv);
+ serv->sv_temptimer.function = (TIMER_FUNC_TYPE)svc_age_temp_xprts;
mod_timer(&serv->sv_temptimer,
jiffies + svc_conn_age_period * HZ);
}
@@ -960,9 +959,9 @@ int svc_send(struct svc_rqst *rqstp)
* Timer function to close old temporary transports, using
* a mark-and-sweep algorithm.
*/
-static void svc_age_temp_xprts(unsigned long closure)
+static void svc_age_temp_xprts(struct timer_list *t)
{
- struct svc_serv *serv = (struct svc_serv *)closure;
+ struct svc_serv *serv = from_timer(serv, t, sv_temptimer);
struct svc_xprt *xprt;
struct list_head *le, *next;
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index e741ec2b4d8e..4b00302e1867 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -696,9 +696,9 @@ xprt_schedule_autodisconnect(struct rpc_xprt *xprt)
}
static void
-xprt_init_autodisconnect(unsigned long data)
+xprt_init_autodisconnect(struct timer_list *t)
{
- struct rpc_xprt *xprt = (struct rpc_xprt *)data;
+ struct rpc_xprt *xprt = from_timer(xprt, t, timer);
spin_lock(&xprt->transport_lock);
if (!list_empty(&xprt->recv))
@@ -1422,10 +1422,9 @@ struct rpc_xprt *xprt_create_transport(struct xprt_create *args)
xprt->idle_timeout = 0;
INIT_WORK(&xprt->task_cleanup, xprt_autoclose);
if (xprt_has_timer(xprt))
- setup_timer(&xprt->timer, xprt_init_autodisconnect,
- (unsigned long)xprt);
+ timer_setup(&xprt->timer, xprt_init_autodisconnect, 0);
else
- init_timer(&xprt->timer);
+ timer_setup(&xprt->timer, NULL, 0);
if (strlen(args->servername) > RPC_MAXNETNAMELEN) {
xprt_destroy(xprt);
--
2.7.4
^ permalink raw reply related
* [PATCH 24/58] chelsio: Convert timers to use timer_setup()
From: Kees Cook @ 2017-10-17 0:29 UTC (permalink / raw)
To: David S. Miller
Cc: Kees Cook, Johannes Berg, Eric Dumazet, netdev, Thomas Gleixner,
linux-kernel
In-Reply-To: <1508200182-104605-1-git-send-email-keescook@chromium.org>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly.
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
drivers/net/ethernet/chelsio/cxgb/sge.c | 29 +++++++++++++----------------
1 file changed, 13 insertions(+), 16 deletions(-)
diff --git a/drivers/net/ethernet/chelsio/cxgb/sge.c b/drivers/net/ethernet/chelsio/cxgb/sge.c
index 75e439918700..30de26ef3da4 100644
--- a/drivers/net/ethernet/chelsio/cxgb/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb/sge.c
@@ -1882,10 +1882,10 @@ netdev_tx_t t1_start_xmit(struct sk_buff *skb, struct net_device *dev)
/*
* Callback for the Tx buffer reclaim timer. Runs with softirqs disabled.
*/
-static void sge_tx_reclaim_cb(unsigned long data)
+static void sge_tx_reclaim_cb(struct timer_list *t)
{
int i;
- struct sge *sge = (struct sge *)data;
+ struct sge *sge = from_timer(sge, t, tx_reclaim_timer);
for (i = 0; i < SGE_CMDQ_N; ++i) {
struct cmdQ *q = &sge->cmdQ[i];
@@ -1978,10 +1978,10 @@ void t1_sge_start(struct sge *sge)
/*
* Callback for the T2 ESPI 'stuck packet feature' workaorund
*/
-static void espibug_workaround_t204(unsigned long data)
+static void espibug_workaround_t204(struct timer_list *t)
{
- struct adapter *adapter = (struct adapter *)data;
- struct sge *sge = adapter->sge;
+ struct sge *sge = from_timer(sge, t, espibug_timer);
+ struct adapter *adapter = sge->adapter;
unsigned int nports = adapter->params.nports;
u32 seop[MAX_NPORTS];
@@ -2021,10 +2021,10 @@ static void espibug_workaround_t204(unsigned long data)
mod_timer(&sge->espibug_timer, jiffies + sge->espibug_timeout);
}
-static void espibug_workaround(unsigned long data)
+static void espibug_workaround(struct timer_list *t)
{
- struct adapter *adapter = (struct adapter *)data;
- struct sge *sge = adapter->sge;
+ struct sge *sge = from_timer(sge, t, espibug_timer);
+ struct adapter *adapter = sge->adapter;
if (netif_running(adapter->port[0].dev)) {
struct sk_buff *skb = sge->espibug_skb[0];
@@ -2075,18 +2075,15 @@ struct sge *t1_sge_create(struct adapter *adapter, struct sge_params *p)
goto nomem_port;
}
- setup_timer(&sge->tx_reclaim_timer, sge_tx_reclaim_cb,
- (unsigned long)sge);
+ timer_setup(&sge->tx_reclaim_timer, sge_tx_reclaim_cb, 0);
if (is_T2(sge->adapter)) {
- init_timer(&sge->espibug_timer);
+ timer_setup(&sge->espibug_timer,
+ adapter->params.nports > 1 ? espibug_workaround_t204 : espibug_workaround,
+ 0);
- if (adapter->params.nports > 1) {
+ if (adapter->params.nports > 1)
tx_sched_init(sge);
- sge->espibug_timer.function = espibug_workaround_t204;
- } else
- sge->espibug_timer.function = espibug_workaround;
- sge->espibug_timer.data = (unsigned long)sge->adapter;
sge->espibug_timeout = 1;
/* for T204, every 10ms */
--
2.7.4
^ permalink raw reply related
* [PATCH 19/58] drivers/atm/suni: Convert timers to use timer_setup()
From: Kees Cook @ 2017-10-17 0:29 UTC (permalink / raw)
To: David S. Miller
Cc: Kees Cook, Chas Williams, linux-atm-general, netdev,
Thomas Gleixner, linux-kernel
In-Reply-To: <1508200182-104605-1-git-send-email-keescook@chromium.org>
In preparation for unconditionally passing the struct timer_list pointer to
all timer callbacks, switch to using the new timer_setup() and from_timer()
to pass the timer pointer explicitly. Passes NULL timer when doing non-
timer call.
Cc: Chas Williams <3chas3@gmail.com>
Cc: linux-atm-general@lists.sourceforge.net
Cc: netdev@vger.kernel.org
Signed-off-by: Kees Cook <keescook@chromium.org>
---
drivers/atm/suni.c | 10 ++++------
1 file changed, 4 insertions(+), 6 deletions(-)
diff --git a/drivers/atm/suni.c b/drivers/atm/suni.c
index b0363149b2fd..b8825f2d79e0 100644
--- a/drivers/atm/suni.c
+++ b/drivers/atm/suni.c
@@ -53,7 +53,7 @@ static DEFINE_SPINLOCK(sunis_lock);
if (atomic_read(&stats->s) < 0) atomic_set(&stats->s,INT_MAX);
-static void suni_hz(unsigned long from_timer)
+static void suni_hz(struct timer_list *timer)
{
struct suni_priv *walk;
struct atm_dev *dev;
@@ -85,7 +85,7 @@ static void suni_hz(unsigned long from_timer)
((GET(TACP_TCC) & 0xff) << 8) |
((GET(TACP_TCCM) & 7) << 16));
}
- if (from_timer) mod_timer(&poll_timer,jiffies+HZ);
+ if (timer) mod_timer(&poll_timer,jiffies+HZ);
}
@@ -322,13 +322,11 @@ static int suni_start(struct atm_dev *dev)
printk(KERN_WARNING "%s(itf %d): no signal\n",dev->type,
dev->number);
PRIV(dev)->loop_mode = ATM_LM_NONE;
- suni_hz(0); /* clear SUNI counters */
+ suni_hz(NULL); /* clear SUNI counters */
(void) fetch_stats(dev,NULL,1); /* clear kernel counters */
if (first) {
- init_timer(&poll_timer);
+ timer_setup(&poll_timer, suni_hz, 0);
poll_timer.expires = jiffies+HZ;
- poll_timer.function = suni_hz;
- poll_timer.data = 1;
#if 0
printk(KERN_DEBUG "[u] p=0x%lx,n=0x%lx\n",(unsigned long) poll_timer.list.prev,
(unsigned long) poll_timer.list.next);
--
2.7.4
^ permalink raw reply related
* Re: WARNING in tcp_update_reordering
From: Yuchung Cheng @ 2017-10-17 0:50 UTC (permalink / raw)
To: David Ahern; +Cc: Eric Dumazet, netdev@vger.kernel.org
In-Reply-To: <5cd139e4-5a50-ba99-d54a-cfe06ccee3e9@gmail.com>
On Mon, Oct 16, 2017 at 3:38 PM, David Ahern <dsahern@gmail.com> wrote:
>
> I need to throw this one over the fence. I triggered the trace below
> testing changes to the tcp tracepoint. It is not readily reproducible
> and does not appear to be correlated to the perf session.
We're seeing this internally at Google a lot as well. The culprit is
because TCP tries to measure/track reordering in precise packet
distance (tp->reordering). That's difficult but also fairly useless to
get right because that highly depends on the instantaneous
traffic load and L2/pathing behavior. In other words the previous
reordering degree has little bearing for my next reordering based on
our analysis. The
warning itself has minor to no impact on TCP performance or
reliability.
I am testing a patch to replace that approach (and remove the
warning). Should be ready soon.
>
> Triggered by the following:
> ssh into VM and run 'top -d1'
> in host, drop tcp packets:
> $ sudo iptables -I INPUT -i br1 -p tcp -j DROP
> and then 5 - 7 seconds later remove the rule:
> $ sudo iptables -D INPUT -i br1 -p tcp -j DROP
>
> [ 73.695849] ------------[ cut here ]------------
> [ 73.697258] WARNING: CPU: 1 PID: 0 at
> /home/dsa/kernel-2.git/net/ipv4/tcp_input.c:889
> tcp_update_reordering+0x4/0x72
> [ 73.700306] Modules linked in: vrf
> [ 73.701316] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.14.0-rc4+ #43
> [ 73.703170] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996),
> BIOS 1.7.5-20140531_083030-gandalf 04/01/2014
> [ 73.706040] task: ffff88003e132180 task.stack: ffffc90000078000
> [ 73.707769] RIP: 0010:tcp_update_reordering+0x4/0x72
> [ 73.709209] RSP: 0018:ffff88003fd039c0 EFLAGS: 00010282
> [ 73.710702] RAX: 0000000000000004 RBX: ffff88003c7be800 RCX:
> 0000000000000004
> [ 73.711797] RDX: 0000000000000000 RSI: 00000000fffffffb RDI:
> ffff88003c7be800
> [ 73.712809] RBP: ffff88003fd03a38 R08: 0000000000000000 R09:
> 0000000000000000
> [ 73.713831] R10: ffff88003fd03a90 R11: 0000000000000000 R12:
> ffff88003fd03a90
> [ 73.714846] R13: 0000000000000000 R14: ffff88003c7bef40 R15:
> ffff88003c7bef48
> [ 73.715871] FS: 0000000000000000(0000) GS:ffff88003fd00000(0000)
> knlGS:0000000000000000
> [ 73.717016] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
> [ 73.717823] CR2: 000056441f284000 CR3: 000000003d7ba002 CR4:
> 00000000000606e0
> [ 73.718834] Call Trace:
> [ 73.719193] <IRQ>
> [ 73.719497] ? tcp_sacktag_write_queue+0x533/0x5ab
> [ 73.720180] ? tcp_mtu_to_mss+0xd/0x1c
> [ 73.720718] tcp_ack+0x320/0xd21
> [ 73.721189] tcp_rcv_established+0x251/0x2c2
> [ 73.721799] tcp_v4_do_rcv+0x9a/0x169
> [ 73.722328] tcp_v4_rcv+0x55c/0x7bb
> [ 73.722841] ip_local_deliver_finish+0xc0/0x141
> [ 73.723486] ip_local_deliver+0xa5/0xae
> [ 73.724038] ? xfrm4_policy_check.constprop.10+0x52/0x52
> [ 73.724787] ip_rcv_finish+0x2de/0x35c
> [ 73.725326] ip_rcv+0x271/0x2ea
> [ 73.725787] ? deliver_ptype_list_skb+0x48/0x69
> [ 73.726430] __netif_receive_skb_core+0x326/0x54a
> [ 73.727112] ? kvm_clock_read+0x1e/0x20
> [ 73.727664] ? kvm_clock_get_cycles+0x9/0xb
> [ 73.728257] __netif_receive_skb+0x16/0x6d
> [ 73.728837] ? __netif_receive_skb+0x16/0x6d
> [ 73.729446] netif_receive_skb_internal+0x4d/0xa3
> [ 73.730116] napi_gro_receive+0x75/0xcc
> [ 73.730667] receive_buf+0xa05/0xa16
> [ 73.731192] ? vring_unmap_one+0x1a/0x68
> [ 73.731754] virtnet_poll+0x103/0x1b1
> [ 73.732284] net_rx_action+0xdb/0x249
> [ 73.732814] __do_softirq+0xfc/0x26b
> [ 73.733332] irq_exit+0x51/0x92
> [ 73.733788] do_IRQ+0x98/0xb0
> [ 73.734225] common_interrupt+0x93/0x93
> [ 73.734779] </IRQ>
> [ 73.735095] RIP: 0010:native_safe_halt+0x6/0x8
> [ 73.735726] RSP: 0018:ffffc9000007bea8 EFLAGS: 00000246 ORIG_RAX:
> ffffffffffffff6e
> [ 73.736784] RAX: 0000000000000000 RBX: 0000000000000000 RCX:
> ffff88003fd10ca0
> [ 73.737776] RDX: 00000000000101ba RSI: 0000000000000001 RDI:
> 0000000000000001
> [ 73.738780] RBP: ffffc9000007bea8 R08: ffff88003d48a900 R09:
> 0000000000000200
> [ 73.739777] R10: 0000000000000003 R11: 0000000000000001 R12:
> 0000000000000000
> [ 73.740779] R13: ffff88003e132180 R14: ffff88003e132180 R15:
> ffff88003e132180
> [ 73.741781] default_idle+0x1a/0x2d
> [ 73.742285] arch_cpu_idle+0xa/0xc
> [ 73.742784] default_idle_call+0x19/0x1b
> [ 73.743352] do_idle+0xd7/0x1a9
> [ 73.743807] cpu_startup_entry+0x1a/0x1c
> [ 73.744371] start_secondary+0x11e/0x120
> [ 73.744930] secondary_startup_64+0xa5/0xa5
> [ 73.745526] Code: 02 74 0b 48 c7 87 e0 06 00 00 00 00 00 00 8a 97 2c
> 06 00 00 83 e0 0d c1 e0 04 5d 83 e2 0f 09 d0 88 87 2c 06 00 00 c3 85 f6
> 79 03 <0f> ff c3 3b b7 10 06 00 00 55 48 89 e5 41 54 41 89 d4 53 48 89
> [ 73.748142] ---[ end trace 730e0fcd13f383bc ]---
^ permalink raw reply
* Re: WARNING in tcp_update_reordering
From: David Ahern @ 2017-10-17 1:00 UTC (permalink / raw)
To: Yuchung Cheng; +Cc: Eric Dumazet, netdev@vger.kernel.org, Andrei Vagin
In-Reply-To: <CAK6E8=ejn5GoscPBh5PdhQTzcU1wZ66=8ZS806Tox_S9CvnZaA@mail.gmail.com>
[ cc Andrei who reported a similar trace ]
On 10/16/17 6:50 PM, Yuchung Cheng wrote:
> On Mon, Oct 16, 2017 at 3:38 PM, David Ahern <dsahern@gmail.com> wrote:
>> I need to throw this one over the fence. I triggered the trace below
>> testing changes to the tcp tracepoint. It is not readily reproducible
>> and does not appear to be correlated to the perf session.
> We're seeing this internally at Google a lot as well. The culprit is
> because TCP tries to measure/track reordering in precise packet
> distance (tp->reordering). That's difficult but also fairly useless to
> get right because that highly depends on the instantaneous
> traffic load and L2/pathing behavior. In other words the previous
> reordering degree has little bearing for my next reordering based on
> our analysis. The
> warning itself has minor to no impact on TCP performance or
> reliability.
>
> I am testing a patch to replace that approach (and remove the
> warning). Should be ready soon.
>
Thanks for the update.
^ permalink raw reply
* [next-queue PATCH v9 0/6] TSN: Add qdisc based config interface for CBS
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Vinicius Costa Gomes, jhs, xiyou.wangcong, jiri, andre.guedes,
ivan.briano, jesus.sanchez-palencia, boon.leong.ong,
richardcochran, henrik, levipearson, rodney.cummings
Hi,
Changes from v8:
- Add an explicit padding field to the tc_cbs_qopt struct, as pointed
out by David Laight;
Changes from v7:
- Fixed comments from Eric Dumazet and Ivan Khoronzhuk;
Changes since v6:
- Fixed compilation for 32bit arches;
- Aligned the behaviour of .select_queue() of the mq qdisc to be the
same as mqprio;
Changes since v5:
- Fixed comments from Jiri Pirko;
Changes since v4:
- Added a software implementation of the CBS algorithm;
Changes since v3:
- None, only a clean patchset without old patches;
Changes since v2:
- squashed the patch introducing the userspace API into the patch
implementing CBS;
Changes since v1:
- Solved the mqprio dependency;
- Fixed a mqprio bug, that caused the inner qdisc to have a wrong
dev_queue associated with it;
Changes from the RFC:
- Fixed comments from Henrik Austad;
- Simplified the Qdisc, using the generic implementation of callbacks
where possible;
- Small refactor on the driver (igb) code;
This patchset is a proposal of how the Traffic Control subsystem can
be used to offload the configuration of the Credit Based Shaper
(defined in the IEEE 802.1Q-2014 Section 8.6.8.2) into supported
network devices.
As part of this work, we've assessed previous public discussions
related to TSN enabling: patches from Henrik Austad (Cisco), the
presentation from Eric Mann at Linux Plumbers 2012, patches from
Gangfeng Huang (National Instruments) and the current state of the
OpenAVNU project (https://github.com/AVnu/OpenAvnu/).
Overview
========
Time-sensitive Networking (TSN) is a set of standards that aim to
address resources availability for providing bandwidth reservation and
bounded latency on Ethernet based LANs. The proposal described here
aims to cover mainly what is needed to enable the following standards:
802.1Qat and 802.1Qav.
The initial target of this work is the Intel i210 NIC, but other
controllers' datasheet were also taken into account, like the Renesas
RZ/A1H RZ/A1M group and the Synopsis DesignWare Ethernet QoS
controller.
Proposal
========
Feature-wise, what is covered here is the configuration interfaces for
HW implementations of the Credit-Based shaper (CBS, 802.1Qav). CBS is
a per-queue shaper. Given that this feature is related to traffic
shaping, and that the traffic control subsystem already provides a
queueing discipline that offloads config into the device driver (i.e.
mqprio), designing a new qdisc for the specific purpose of offloading
the config for the CBS shaper seemed like a good fit.
For steering traffic into the correct queues, we use the socket option
SO_PRIORITY and then a mechanism to map priority to traffic classes /
Tx queues. The qdisc mqprio is currently used in our tests.
As for the CBS config interface, this patchset is proposing a new
qdisc called 'cbs'. Its 'tc' cmd line is:
$ tc qdisc add dev IFACE parent ID cbs locredit N hicredit M sendslope S \
idleslope I
Note that the parameters for this qdisc are the ones defined by the
802.1Q-2014 spec, so no hardware specific functionality is exposed here.
Per-stream shaping, as defined by IEEE 802.1Q-2014 Section 34.6.1, is
not yet covered by this proposal.
Testing this RFC
================
Attached to this cover letter are:
- calculate_cbs_params.py: A Python script to calculate the
parameters to the CBS queueing discipline;
- tsn-talker.c: A sample C implementation of the talker side of a stream;
- tsn-listener.c: A sample C implementation of the listener side of a
stream;
For testing the patches of this series, you may want to use the
attached samples to this cover letter and use the 'mqprio' qdisc to
setup the priorities to Tx queues mapping, together with the 'cbs'
qdisc to configure the HW shaper of the i210 controller:
1) Setup priorities to traffic classes to hardware queues mapping
$ tc qdisc replace dev ens4 handle 100: parent root mqprio num_tc 3 \
map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0
For a more detailed explanation, see mqprio(8), in short, this command
will map traffic with priority 3 to the hardware queue 0, traffic with
priority 2 to hardware queue 1, and the rest will be mapped to
hardware queues 2 and 3.
2) Check scheme. You want to get the inner qdiscs ID from the bottom up
$ tc -g class show dev ens4
Ex.:
+---(100:3) mqprio
| +---(100:6) mqprio
| +---(100:7) mqprio
|
+---(100:2) mqprio
| +---(100:5) mqprio
|
+---(100:1) mqprio
+---(100:4) mqprio
* Here '100:4' is Tx Queue #0 and '100:5' is Tx Queue #1.
3) Calculate CBS parameters for classes A and B. i.e. BW for A is 20Mbps and
for B is 10Mbps:
$ calc_cbs_params.py -A 20000 -a 1500 -B 10000 -b 1500
4) Configure CBS for traffic class A (priority 3) as provided by the script:
$ tc qdisc replace dev ens4 parent 100:4 cbs locredit -1470 \
hicredit 30 sendslope -980000 idleslope 20000
5) Configure CBS for traffic class B (priority 2):
$ tc qdisc replace dev ens4 parent 100:5 cbs \
locredit -1485 hicredit 31 sendslope -990000 idleslope 10000
6) Run Listener:
$ ./tsn-listener -d 01:AA:AA:AA:AA:AA -i ens4 -s 1500
7) Run Talker for class A (prio 3 here), compiled from samples/tsn/talker.c
$ ./tsn-talker -d 01:AA:AA:AA:AA:AA -i ens4 -p 3 -s 1500
* The bandwidth displayed on the listener output at this stage should be very
close to the one configured for class A.
8) You can also run a Talker for class B (prio 2 here and using a
different address):
$ ./tsn-talker -d 01:BB:BB:BB:BB:BB -i ens4 -p 2 -s 1500
Authors
=======
- Andre Guedes <andre.guedes@intel.com>
- Ivan Briano <ivan.briano@intel.com>
- Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
- Vinicius Gomes <vinicius.gomes@intel.com>
Andre Guedes (1):
igb: Add support for CBS offload
Jesus Sanchez-Palencia (3):
net/sched: Check for null dev_queue on create flow
net/sched: Change behavior of mq select_queue()
net/sched: Add select_queue() class_ops for mqprio
Vinicius Costa Gomes (2):
net/sched: Introduce Credit Based Shaper (CBS) qdisc
net/sched: Add support for HW offloading for CBS
drivers/net/ethernet/intel/igb/e1000_defines.h | 23 ++
drivers/net/ethernet/intel/igb/e1000_regs.h | 8 +
drivers/net/ethernet/intel/igb/igb.h | 6 +
drivers/net/ethernet/intel/igb/igb_main.c | 347 +++++++++++++++++++++++
include/linux/netdevice.h | 1 +
include/net/pkt_sched.h | 9 +
include/uapi/linux/pkt_sched.h | 19 ++
net/sched/Kconfig | 11 +
net/sched/Makefile | 1 +
net/sched/sch_cbs.c | 373 +++++++++++++++++++++++++
net/sched/sch_generic.c | 8 +-
net/sched/sch_mq.c | 10 +-
net/sched/sch_mqprio.c | 7 +
13 files changed, 813 insertions(+), 10 deletions(-)
create mode 100644 net/sched/sch_cbs.c
Annex: Sample files
===================
calc_cbs_params.py
--8<---------------cut here---------------start------------->8---
#!/usr/bin/env python
#
# Copyright (c) 2017, Intel Corporation
#
# Redistribution and use in source and binary forms, with or without
# modification, are permitted provided that the following conditions are met:
#
# * Redistributions of source code must retain the above copyright notice,
# this list of conditions and the following disclaimer.
# * Redistributions in binary form must reproduce the above copyright
# notice, this list of conditions and the following disclaimer in the
# documentation and/or other materials provided with the distribution.
# * Neither the name of Intel Corporation nor the names of its contributors
# may be used to endorse or promote products derived from this software
# without specific prior written permission.
#
# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
# AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
# DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
# SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
# CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
# OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
import argparse
import math
def print_cbs_params_for_class_a(args):
idleslope = args.idleslope_a
sendslope = idleslope - args.link_speed
# According to 802.1Q-2014 spec, Annex L, hiCredit and
# loCredit for SR class A are calculated following the
# equations L-10 and L-12, respectively.
hicredit = math.ceil(idleslope * args.frame_non_sr / args.link_speed)
locredit = math.ceil(sendslope * args.frame_a / args.link_speed)
print("tc qdisc add dev <IFNAME> parent <QDISC-ID> cbs idleslope %d sendslope %d hicredit %d locredit %d" % \
(idleslope, sendslope, hicredit, locredit))
def print_cbs_params_for_class_b(args):
idleslope = args.idleslope_b
sendslope = idleslope - args.link_speed
# Annex L doesn't present a straightforward equation to
# calculate hiCredit for Class B so we have to derive it
# based on generic equations presented in that Annex.
#
# L-3 is the primary equation to calculate hiCredit. Section
# L.2 states that the 'maxInterferenceSize' for SR class B
# is the maximum burst size for SR class A plus the
# maxInterferenceSize from SR class A (which is equal to the
# maximum frame from non-SR traffic).
#
# The maximum burst size for SR class A equation is shown in
# L-16. Merging L-16 into L-3 we get the resulting equation
# which calculates hiCredit B (refer to section L.3 in case
# you're not familiar with the legend):
#
# hiCredit B = Rb * ( Mo Ma )
# ---------- + ------
# Ro - Ra Ro
#
hicredit = math.ceil(idleslope * \
((args.frame_non_sr / (args.link_speed - args.idleslope_a)) + \
(args.frame_a / args.link_speed)))
# loCredit B is calculated following equation L-2.
locredit = math.ceil(sendslope * args.frame_b / args.link_speed)
print("tc qdisc add dev <IFNAME> parent <QDISC-ID> cbs idleslope %d sendslope %d hicredit %d locredit %d" % \
(idleslope, sendslope, hicredit, locredit))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-S', dest='link_speed', default=1000000.0, type=float,
help='Link speed in kbps')
parser.add_argument('-s', dest='frame_non_sr', default=1500.0, type=float,
help='Maximum frame size from non-SR traffic (MTU size'
'usually')
parser.add_argument('-A', dest='idleslope_a', default=0, type=float,
help='Idleslope for SR class A in kbps')
parser.add_argument('-a', dest='frame_a', default=0, type=float,
help='Maximum frame size for SR class A traffic')
parser.add_argument('-B', dest='idleslope_b', default=0, type=float,
help='Idleslope for SR class B in kbps')
parser.add_argument('-b', dest='frame_b', default=0, type=float,
help='Maximum frame size for SR class B traffic')
args = parser.parse_args()
if args.idleslope_a > 0:
print_cbs_params_for_class_a(args)
if args.idleslope_b > 0:
print_cbs_params_for_class_b(args)
if __name__ == "__main__":
main()
--8<---------------cut here---------------end--------------->8---
tsn-talker.c
--8<---------------cut here---------------start------------->8---
/*
* Copyright (c) 2017, Intel Corporation
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Intel Corporation nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
* OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <alloca.h>
#include <argp.h>
#include <arpa/inet.h>
#include <inttypes.h>
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <unistd.h>
#define MAGIC 0xCC
static uint8_t ifname[IFNAMSIZ];
static uint8_t macaddr[ETH_ALEN];
static int priority = -1;
static size_t size = 1500;
static uint64_t seq;
static int delay = -1;
static struct argp_option options[] = {
{"dst-addr", 'd', "MACADDR", 0, "Stream Destination MAC address" },
{"delay", 'D', "NUM", 0, "Delay (in us) between packet transmission" },
{"ifname", 'i', "IFNAME", 0, "Network Interface" },
{"prio", 'p', "NUM", 0, "SO_PRIORITY to be set in socket" },
{"packet-size", 's', "NUM", 0, "Size of packets to be transmitted" },
{ 0 }
};
static error_t parser(int key, char *arg, struct argp_state *state)
{
int res;
switch (key) {
case 'd':
res = sscanf(arg, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
&macaddr[0], &macaddr[1], &macaddr[2],
&macaddr[3], &macaddr[4], &macaddr[5]);
if (res != 6) {
printf("Invalid address\n");
exit(EXIT_FAILURE);
}
break;
case 'D':
delay = atoi(arg);
break;
case 'i':
strncpy(ifname, arg, sizeof(ifname) - 1);
break;
case 'p':
priority = atoi(arg);
break;
case 's':
size = atoi(arg);
break;
}
return 0;
}
static struct argp argp = { options, parser };
int main(int argc, char *argv[])
{
int fd, res;
struct ifreq req;
uint8_t *data;
struct sockaddr_ll sk_addr = {
.sll_family = AF_PACKET,
.sll_protocol = htons(ETH_P_TSN),
.sll_halen = ETH_ALEN,
};
argp_parse(&argp, argc, argv, 0, NULL, NULL);
fd = socket(AF_PACKET, SOCK_DGRAM, htons(ETH_P_TSN));
if (fd < 0) {
perror("Couldn't open socket");
return 1;
}
strncpy(req.ifr_name, ifname, sizeof(req.ifr_name));
res = ioctl(fd, SIOCGIFINDEX, &req);
if (res < 0) {
perror("Couldn't get interface index");
goto err;
}
sk_addr.sll_ifindex = req.ifr_ifindex;
memcpy(&sk_addr.sll_addr, macaddr, ETH_ALEN);
if (priority != -1) {
res = setsockopt(fd, SOL_SOCKET, SO_PRIORITY, &priority,
sizeof(priority));
if (res < 0) {
perror("Couldn't set priority");
goto err;
}
}
data = alloca(size);
memset(data, MAGIC, size);
printf("Sending packets...\n");
while (1) {
uint64_t *seq_ptr = (uint64_t *) &data[0];
ssize_t n;
*seq_ptr = seq++;
n = sendto(fd, data, size, 0, (struct sockaddr *) &sk_addr,
sizeof(sk_addr));
if (n < 0)
perror("Failed to send data");
if (delay > 0)
usleep(delay);
}
close(fd);
return 0;
err:
close(fd);
return 1;
}
--8<---------------cut here---------------end--------------->8---
tsn-listener.c
--8<---------------cut here---------------start------------->8---
/*
* Copyright (c) 2017, Intel Corporation
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* * Redistributions of source code must retain the above copyright notice,
* this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of Intel Corporation nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
* SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
* STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED
* OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <alloca.h>
#include <argp.h>
#include <arpa/inet.h>
#include <inttypes.h>
#include <linux/if.h>
#include <linux/if_ether.h>
#include <linux/if_packet.h>
#include <poll.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/ioctl.h>
#include <sys/timerfd.h>
#include <unistd.h>
static uint8_t ifname[IFNAMSIZ];
static uint8_t macaddr[ETH_ALEN];
static uint64_t data_count;
static int size = 1500;
static time_t interval = 1;
static bool check_seq = false;
static uint64_t expected_seq;
static struct argp_option options[] = {
{"check-seq", 'c', NULL, 0, "Check sequence number within packet" },
{"dst-addr", 'd', "MACADDR", 0, "Stream Destination MAC address" },
{"ifname", 'i', "IFNAME", 0, "Network Interface" },
{"interval", 'I', "SEC", 0, "Interval between bandwidth reports" },
{"packet-size", 's', "NUM", 0, "Expected packet size" },
{ 0 }
};
static error_t parser(int key, char *arg, struct argp_state *state)
{
int res;
switch (key) {
case 'c':
check_seq = true;
break;
case 'd':
res = sscanf(arg, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx",
&macaddr[0], &macaddr[1], &macaddr[2],
&macaddr[3], &macaddr[4], &macaddr[5]);
if (res != 6) {
printf("Invalid address\n");
exit(EXIT_FAILURE);
}
break;
case 'i':
strncpy(ifname, arg, sizeof(ifname) - 1);
break;
case 'I':
interval = atoi(arg);
break;
case 's':
size = atoi(arg);
break;
}
return 0;
}
static struct argp argp = { options, parser };
static int setup_timer(void)
{
int fd, res;
struct itimerspec tspec = { 0 };
fd = timerfd_create(CLOCK_MONOTONIC, 0);
if (fd < 0) {
perror("Couldn't create timer");
return -1;
}
tspec.it_value.tv_sec = interval;
tspec.it_interval.tv_sec = interval;
res = timerfd_settime(fd, 0, &tspec, NULL);
if (res < 0) {
perror("Couldn't set timer");
close(fd);
return -1;
}
return fd;
}
static int setup_socket(void)
{
int fd, res;
struct sockaddr_ll sk_addr = {
.sll_family = AF_PACKET,
.sll_protocol = htons(ETH_P_TSN),
};
fd = socket(AF_PACKET, SOCK_DGRAM, htons(ETH_P_TSN));
if (fd < 0) {
perror("Couldn't open socket");
return -1;
}
/* If user provided a network interface, bind() to it. */
if (ifname[0] != '\0') {
struct ifreq req;
strncpy(req.ifr_name, ifname, sizeof(req.ifr_name));
res = ioctl(fd, SIOCGIFINDEX, &req);
if (res < 0) {
perror("Couldn't get interface index");
goto err;
}
sk_addr.sll_ifindex = req.ifr_ifindex;
res = bind(fd, (struct sockaddr *) &sk_addr, sizeof(sk_addr));
if (res < 0) {
perror("Couldn't bind() to interface");
goto err;
}
}
/* If user provided the stream destination address, set it as multicast
* address.
*/
if (macaddr[0] != '\0') {
struct packet_mreq mreq;
mreq.mr_ifindex = sk_addr.sll_ifindex;
mreq.mr_type = PACKET_MR_MULTICAST;
mreq.mr_alen = ETH_ALEN;
memcpy(&mreq.mr_address, macaddr, ETH_ALEN);
res = setsockopt(fd, SOL_PACKET, PACKET_ADD_MEMBERSHIP,
&mreq, sizeof(struct packet_mreq));
if (res < 0) {
perror("Couldn't set PACKET_ADD_MEMBERSHIP");
goto err;
}
}
return fd;
err:
close(fd);
return -1;
}
static void recv_packet(int fd)
{
uint8_t *data = alloca(size);
ssize_t n = recv(fd, data, size, 0);
if (n < 0) {
perror("Failed to receive data");
return;
}
if (n != size)
printf("Size mismatch: expected %d, got %d\n", size, n);
if (check_seq) {
uint64_t *seq = (uint64_t *) &data[0];
/* If 'expected_seq' is equal to zero, it means this is the
* first packet we received so we don't know what sequence
* number to expect.
*/
if (expected_seq == 0)
expected_seq = *seq;
if (*seq != expected_seq) {
printf("Sequence mismatch: expected %llu, got %llu\n",
expected_seq, *seq);
expected_seq = *seq;
}
expected_seq++;
}
data_count += n;
}
static void report_bw(int fd)
{
uint64_t expirations;
ssize_t n = read(fd, &expirations, sizeof(uint64_t));
if (n < 0) {
perror("Couldn't read timerfd");
return;
}
if (expirations != 1)
printf("Some went wrong with timerfd\n");
printf("Receiving data rate: %llu kbps\n", (data_count * 8) / (1000 * interval));
data_count = 0;
}
int main(int argc, char *argv[])
{
int sk_fd, timer_fd, res;
struct pollfd fds[2];
argp_parse(&argp, argc, argv, 0, NULL, NULL);
sk_fd = setup_socket();
if (sk_fd < 0)
return 1;
timer_fd = setup_timer();
if (timer_fd < 0) {
close(sk_fd);
return 1;
}
fds[0].fd = sk_fd;
fds[0].events = POLLIN;
fds[1].fd = timer_fd;
fds[1].events = POLLIN;
printf("Waiting for packets...\n");
while (1) {
res = poll(fds, 2, -1);
if (res < 0) {
perror("Error on poll()");
goto err;
}
if (fds[0].revents & POLLIN)
recv_packet(fds[0].fd);
if (fds[1].revents & POLLIN) {
report_bw(fds[1].fd);
}
}
close(timer_fd);
close(sk_fd);
return 0;
err:
close(timer_fd);
close(sk_fd);
return 1;
}
--8<---------------cut here---------------end--------------->8---
^ permalink raw reply
* [next-queue PATCH v9 1/6] net/sched: Check for null dev_queue on create flow
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Jesus Sanchez-Palencia, jhs, xiyou.wangcong, jiri, andre.guedes,
ivan.briano, boon.leong.ong, richardcochran, henrik, levipearson,
rodney.cummings
In-Reply-To: <20171017010128.22141-1-vinicius.gomes@intel.com>
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
In qdisc_alloc() the dev_queue pointer was used without any checks
being performed. If qdisc_create() gets a null dev_queue pointer, it
just passes it along to qdisc_alloc(), leading to a crash. That
happens if a root qdisc implements select_queue() and returns a null
dev_queue pointer for an "invalid handle", for example, or if the
dev_queue associated with the parent qdisc is null.
This patch is in preparation for the next in this series, where
select_queue() is being added to mqprio and as it may return a null
dev_queue.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
net/sched/sch_generic.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index a0a198768aad..de2408f1ccd3 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -603,8 +603,14 @@ struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,
struct Qdisc *sch;
unsigned int size = QDISC_ALIGN(sizeof(*sch)) + ops->priv_size;
int err = -ENOBUFS;
- struct net_device *dev = dev_queue->dev;
+ struct net_device *dev;
+
+ if (!dev_queue) {
+ err = -EINVAL;
+ goto errout;
+ }
+ dev = dev_queue->dev;
p = kzalloc_node(size, GFP_KERNEL,
netdev_queue_numa_node_read(dev_queue));
--
2.14.2
^ permalink raw reply related
* [next-queue PATCH v9 2/6] net/sched: Change behavior of mq select_queue()
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Jesus Sanchez-Palencia, jhs, xiyou.wangcong, jiri, andre.guedes,
ivan.briano, boon.leong.ong, richardcochran, henrik, levipearson,
rodney.cummings
In-Reply-To: <20171017010128.22141-1-vinicius.gomes@intel.com>
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Currently, the class_ops select_queue() implementation on sch_mq
returns a pointer to netdev_queue #0 when it receives and invalid
qdisc id. That can be misleading since all of mq's inner qdiscs are
attached to a valid netdev_queue.
Here we fix that by returning NULL when a qdisc id is invalid. This is
aligned with how select_queue() is implemented for sch_mqprio in the
next patch on this series, keeping a consistent behavior between these
two qdiscs.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
net/sched/sch_mq.c | 10 +---------
1 file changed, 1 insertion(+), 9 deletions(-)
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index f3a3e507422b..213b586a06a0 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -130,15 +130,7 @@ static struct netdev_queue *mq_queue_get(struct Qdisc *sch, unsigned long cl)
static struct netdev_queue *mq_select_queue(struct Qdisc *sch,
struct tcmsg *tcm)
{
- unsigned int ntx = TC_H_MIN(tcm->tcm_parent);
- struct netdev_queue *dev_queue = mq_queue_get(sch, ntx);
-
- if (!dev_queue) {
- struct net_device *dev = qdisc_dev(sch);
-
- return netdev_get_tx_queue(dev, 0);
- }
- return dev_queue;
+ return mq_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
}
static int mq_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new,
--
2.14.2
^ permalink raw reply related
* [next-queue PATCH v9 3/6] net/sched: Add select_queue() class_ops for mqprio
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Jesus Sanchez-Palencia, jhs, xiyou.wangcong, jiri, andre.guedes,
ivan.briano, boon.leong.ong, richardcochran, henrik, levipearson,
rodney.cummings
In-Reply-To: <20171017010128.22141-1-vinicius.gomes@intel.com>
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
When replacing a child qdisc from mqprio, tc_modify_qdisc() must fetch
the netdev_queue pointer that the current child qdisc is associated
with before creating the new qdisc.
Currently, when using mqprio as root qdisc, the kernel will end up
getting the queue #0 pointer from the mqprio (root qdisc), which leaves
any new child qdisc with a possibly wrong netdev_queue pointer.
Implementing the Qdisc_class_ops select_queue() on mqprio fixes this
issue and avoid an inconsistent state when child qdiscs are replaced.
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
net/sched/sch_mqprio.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 6bcdfe6e7b63..8c042ae323e3 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -396,6 +396,12 @@ static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
}
}
+static struct netdev_queue *mqprio_select_queue(struct Qdisc *sch,
+ struct tcmsg *tcm)
+{
+ return mqprio_queue_get(sch, TC_H_MIN(tcm->tcm_parent));
+}
+
static const struct Qdisc_class_ops mqprio_class_ops = {
.graft = mqprio_graft,
.leaf = mqprio_leaf,
@@ -403,6 +409,7 @@ static const struct Qdisc_class_ops mqprio_class_ops = {
.walk = mqprio_walk,
.dump = mqprio_dump_class,
.dump_stats = mqprio_dump_class_stats,
+ .select_queue = mqprio_select_queue,
};
static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = {
--
2.14.2
^ permalink raw reply related
* [next-queue PATCH v9 4/6] net/sched: Introduce Credit Based Shaper (CBS) qdisc
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Vinicius Costa Gomes, jhs, xiyou.wangcong, jiri, andre.guedes,
ivan.briano, jesus.sanchez-palencia, boon.leong.ong,
richardcochran, henrik, levipearson, rodney.cummings
In-Reply-To: <20171017010128.22141-1-vinicius.gomes@intel.com>
This queueing discipline implements the shaper algorithm defined by
the 802.1Q-2014 Section 8.6.8.2 and detailed in Annex L.
It's primary usage is to apply some bandwidth reservation to user
defined traffic classes, which are mapped to different queues via the
mqprio qdisc.
Only a simple software implementation is added for now.
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
---
include/uapi/linux/pkt_sched.h | 19 +++
net/sched/Kconfig | 11 ++
net/sched/Makefile | 1 +
net/sched/sch_cbs.c | 293 +++++++++++++++++++++++++++++++++++++++++
4 files changed, 324 insertions(+)
create mode 100644 net/sched/sch_cbs.c
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 099bf5528fed..25b6ab82a586 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -871,4 +871,23 @@ struct tc_pie_xstats {
__u32 maxq; /* maximum queue size */
__u32 ecn_mark; /* packets marked with ecn*/
};
+
+/* CBS */
+struct tc_cbs_qopt {
+ __u8 offload;
+ __u8 _pad[3];
+ __s32 hicredit;
+ __s32 locredit;
+ __s32 idleslope;
+ __s32 sendslope;
+};
+
+enum {
+ TCA_CBS_UNSPEC,
+ TCA_CBS_PARMS,
+ __TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
#endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index e70ed26485a2..c03d86a7775e 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -172,6 +172,17 @@ config NET_SCH_TBF
To compile this code as a module, choose M here: the
module will be called sch_tbf.
+config NET_SCH_CBS
+ tristate "Credit Based Shaper (CBS)"
+ ---help---
+ Say Y here if you want to use the Credit Based Shaper (CBS) packet
+ scheduling algorithm.
+
+ See the top of <file:net/sched/sch_cbs.c> for more details.
+
+ To compile this code as a module, choose M here: the
+ module will be called sch_cbs.
+
config NET_SCH_GRED
tristate "Generic Random Early Detection (GRED)"
---help---
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 7b915d226de7..80c8f92d162d 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_NET_SCH_FQ_CODEL) += sch_fq_codel.o
obj-$(CONFIG_NET_SCH_FQ) += sch_fq.o
obj-$(CONFIG_NET_SCH_HHF) += sch_hhf.o
obj-$(CONFIG_NET_SCH_PIE) += sch_pie.o
+obj-$(CONFIG_NET_SCH_CBS) += sch_cbs.o
obj-$(CONFIG_NET_CLS_U32) += cls_u32.o
obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
new file mode 100644
index 000000000000..c0102b589494
--- /dev/null
+++ b/net/sched/sch_cbs.c
@@ -0,0 +1,293 @@
+/*
+ * net/sched/sch_cbs.c Credit Based Shaper
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Authors: Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ *
+ */
+
+/* Credit Based Shaper (CBS)
+ * =========================
+ *
+ * This is a simple rate-limiting shaper aimed at TSN applications on
+ * systems with known traffic workloads.
+ *
+ * Its algorithm is defined by the IEEE 802.1Q-2014 Specification,
+ * Section 8.6.8.2, and explained in more detail in the Annex L of the
+ * same specification.
+ *
+ * There are four tunables to be considered:
+ *
+ * 'idleslope': Idleslope is the rate of credits that is
+ * accumulated (in kilobits per second) when there is at least
+ * one packet waiting for transmission. Packets are transmitted
+ * when the current value of credits is equal or greater than
+ * zero. When there is no packet to be transmitted the amount of
+ * credits is set to zero. This is the main tunable of the CBS
+ * algorithm.
+ *
+ * 'sendslope':
+ * Sendslope is the rate of credits that is depleted (it should be a
+ * negative number of kilobits per second) when a transmission is
+ * ocurring. It can be calculated as follows, (IEEE 802.1Q-2014 Section
+ * 8.6.8.2 item g):
+ *
+ * sendslope = idleslope - port_transmit_rate
+ *
+ * 'hicredit': Hicredit defines the maximum amount of credits (in
+ * bytes) that can be accumulated. Hicredit depends on the
+ * characteristics of interfering traffic,
+ * 'max_interference_size' is the maximum size of any burst of
+ * traffic that can delay the transmission of a frame that is
+ * available for transmission for this traffic class, (IEEE
+ * 802.1Q-2014 Annex L, Equation L-3):
+ *
+ * hicredit = max_interference_size * (idleslope / port_transmit_rate)
+ *
+ * 'locredit': Locredit is the minimum amount of credits that can
+ * be reached. It is a function of the traffic flowing through
+ * this qdisc (IEEE 802.1Q-2014 Annex L, Equation L-2):
+ *
+ * locredit = max_frame_size * (sendslope / port_transmit_rate)
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+
+#define BYTES_PER_KBIT (1000LL / 8)
+
+struct cbs_sched_data {
+ s64 port_rate; /* in bytes/s */
+ s64 last; /* timestamp in ns */
+ s64 credits; /* in bytes */
+ s32 locredit; /* in bytes */
+ s32 hicredit; /* in bytes */
+ s64 sendslope; /* in bytes/s */
+ s64 idleslope; /* in bytes/s */
+ struct qdisc_watchdog watchdog;
+ int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch);
+ struct sk_buff *(*dequeue)(struct Qdisc *sch);
+};
+
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ if (sch->q.qlen == 0 && q->credits > 0) {
+ /* We need to stop accumulating credits when there's
+ * no enqueued packets and q->credits is positive.
+ */
+ q->credits = 0;
+ q->last = ktime_get_ns();
+ }
+
+ return qdisc_enqueue_tail(skb, sch);
+}
+
+static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ struct sk_buff **to_free)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ return q->enqueue(skb, sch);
+}
+
+/* timediff is in ns, slope is in bytes/s */
+static s64 timediff_to_credits(s64 timediff, s64 slope)
+{
+ return div64_s64(timediff * slope, NSEC_PER_SEC);
+}
+
+static s64 delay_from_credits(s64 credits, s64 slope)
+{
+ if (unlikely(slope == 0))
+ return S64_MAX;
+
+ return div64_s64(-credits * NSEC_PER_SEC, slope);
+}
+
+static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate)
+{
+ if (unlikely(port_rate == 0))
+ return S64_MAX;
+
+ return div64_s64(len * slope, port_rate);
+}
+
+static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ s64 now = ktime_get_ns();
+ struct sk_buff *skb;
+ s64 credits;
+ int len;
+
+ if (q->credits < 0) {
+ credits = timediff_to_credits(now - q->last, q->idleslope);
+
+ credits = q->credits + credits;
+ q->credits = min_t(s64, credits, q->hicredit);
+
+ if (q->credits < 0) {
+ s64 delay;
+
+ delay = delay_from_credits(q->credits, q->idleslope);
+ qdisc_watchdog_schedule_ns(&q->watchdog, now + delay);
+
+ q->last = now;
+
+ return NULL;
+ }
+ }
+
+ skb = qdisc_dequeue_head(sch);
+ if (!skb)
+ return NULL;
+
+ len = qdisc_pkt_len(skb);
+
+ /* As sendslope is a negative number, this will decrease the
+ * amount of q->credits.
+ */
+ credits = credits_from_len(len, q->sendslope, q->port_rate);
+ credits += q->credits;
+
+ q->credits = max_t(s64, credits, q->locredit);
+ q->last = now;
+
+ return skb;
+}
+
+static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ return q->dequeue(sch);
+}
+
+static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = {
+ [TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) },
+};
+
+static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
+ struct nlattr *tb[TCA_CBS_MAX + 1];
+ struct ethtool_link_ksettings ecmd;
+ struct tc_cbs_qopt *qopt;
+ s64 link_speed;
+ int err;
+
+ err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL);
+ if (err < 0)
+ return err;
+
+ if (!tb[TCA_CBS_PARMS])
+ return -EINVAL;
+
+ qopt = nla_data(tb[TCA_CBS_PARMS]);
+
+ if (qopt->offload)
+ return -EOPNOTSUPP;
+
+ if (!__ethtool_get_link_ksettings(dev, &ecmd))
+ link_speed = ecmd.base.speed;
+ else
+ link_speed = SPEED_1000;
+
+ q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
+
+ q->enqueue = cbs_enqueue_soft;
+ q->dequeue = cbs_dequeue_soft;
+
+ q->hicredit = qopt->hicredit;
+ q->locredit = qopt->locredit;
+ q->idleslope = qopt->idleslope * BYTES_PER_KBIT;
+ q->sendslope = qopt->sendslope * BYTES_PER_KBIT;
+
+ return 0;
+}
+
+static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ if (!opt)
+ return -EINVAL;
+
+ qdisc_watchdog_init(&q->watchdog, sch);
+
+ return cbs_change(sch, opt);
+}
+
+static void cbs_destroy(struct Qdisc *sch)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+
+ qdisc_watchdog_cancel(&q->watchdog);
+}
+
+static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+ struct cbs_sched_data *q = qdisc_priv(sch);
+ struct tc_cbs_qopt opt = { };
+ struct nlattr *nest;
+
+ nest = nla_nest_start(skb, TCA_OPTIONS);
+ if (!nest)
+ goto nla_put_failure;
+
+ opt.hicredit = q->hicredit;
+ opt.locredit = q->locredit;
+ opt.sendslope = q->sendslope / BYTES_PER_KBIT;
+ opt.idleslope = q->idleslope / BYTES_PER_KBIT;
+ opt.offload = 0;
+
+ if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt))
+ goto nla_put_failure;
+
+ return nla_nest_end(skb, nest);
+
+nla_put_failure:
+ nla_nest_cancel(skb, nest);
+ return -1;
+}
+
+static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
+ .id = "cbs",
+ .priv_size = sizeof(struct cbs_sched_data),
+ .enqueue = cbs_enqueue,
+ .dequeue = cbs_dequeue,
+ .peek = qdisc_peek_dequeued,
+ .init = cbs_init,
+ .reset = qdisc_reset_queue,
+ .destroy = cbs_destroy,
+ .change = cbs_change,
+ .dump = cbs_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __init cbs_module_init(void)
+{
+ return register_qdisc(&cbs_qdisc_ops);
+}
+
+static void __exit cbs_module_exit(void)
+{
+ unregister_qdisc(&cbs_qdisc_ops);
+}
+module_init(cbs_module_init)
+module_exit(cbs_module_exit)
+MODULE_LICENSE("GPL");
--
2.14.2
^ permalink raw reply related
* [next-queue PATCH v9 6/6] igb: Add support for CBS offload
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Andre Guedes, jhs, xiyou.wangcong, jiri, ivan.briano,
jesus.sanchez-palencia, boon.leong.ong, richardcochran, henrik,
levipearson, rodney.cummings
In-Reply-To: <20171017010128.22141-1-vinicius.gomes@intel.com>
From: Andre Guedes <andre.guedes@intel.com>
This patch adds support for Credit-Based Shaper (CBS) qdisc offload
from Traffic Control system. This support enable us to leverage the
Forwarding and Queuing for Time-Sensitive Streams (FQTSS) features
from Intel i210 Ethernet Controller. FQTSS is the former 802.1Qav
standard which was merged into 802.1Q in 2014. It enables traffic
prioritization and bandwidth reservation via the Credit-Based Shaper
which is implemented in hardware by i210 controller.
The patch introduces the igb_setup_tc() function which implements the
support for CBS qdisc hardware offload in the IGB driver. CBS offload
is the only traffic control offload supported by the driver at the
moment.
FQTSS transmission mode from i210 controller is automatically enabled
by the IGB driver when the CBS is enabled for the first hardware
queue. Likewise, FQTSS mode is automatically disabled when CBS is
disabled for the last hardware queue. Changing FQTSS mode requires NIC
reset.
FQTSS feature is supported by i210 controller only.
Signed-off-by: Andre Guedes <andre.guedes@intel.com>
---
drivers/net/ethernet/intel/igb/e1000_defines.h | 23 ++
drivers/net/ethernet/intel/igb/e1000_regs.h | 8 +
drivers/net/ethernet/intel/igb/igb.h | 6 +
drivers/net/ethernet/intel/igb/igb_main.c | 347 +++++++++++++++++++++++++
4 files changed, 384 insertions(+)
diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 1de82f247312..83cabff1e0ab 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -353,7 +353,18 @@
#define E1000_RXPBS_CFG_TS_EN 0x80000000
#define I210_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */
+#define I210_RXPBSIZE_MASK 0x0000003F
+#define I210_RXPBSIZE_PB_32KB 0x00000020
#define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */
+#define I210_TXPBSIZE_MASK 0xC0FFFFFF
+#define I210_TXPBSIZE_PB0_8KB (8 << 0)
+#define I210_TXPBSIZE_PB1_8KB (8 << 6)
+#define I210_TXPBSIZE_PB2_4KB (4 << 12)
+#define I210_TXPBSIZE_PB3_4KB (4 << 18)
+
+#define I210_DTXMXPKTSZ_DEFAULT 0x00000098
+
+#define I210_SR_QUEUES_NUM 2
/* SerDes Control */
#define E1000_SCTL_DISABLE_SERDES_LOOPBACK 0x0400
@@ -1051,4 +1062,16 @@
#define E1000_VLAPQF_P_VALID(_n) (0x1 << (3 + (_n) * 4))
#define E1000_VLAPQF_QUEUE_MASK 0x03
+/* TX Qav Control fields */
+#define E1000_TQAVCTRL_XMIT_MODE BIT(0)
+#define E1000_TQAVCTRL_DATAFETCHARB BIT(4)
+#define E1000_TQAVCTRL_DATATRANARB BIT(8)
+
+/* TX Qav Credit Control fields */
+#define E1000_TQAVCC_IDLESLOPE_MASK 0xFFFF
+#define E1000_TQAVCC_QUEUEMODE BIT(31)
+
+/* Transmit Descriptor Control fields */
+#define E1000_TXDCTL_PRIORITY BIT(27)
+
#endif
diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h
index 58adbf234e07..8eee081d395f 100644
--- a/drivers/net/ethernet/intel/igb/e1000_regs.h
+++ b/drivers/net/ethernet/intel/igb/e1000_regs.h
@@ -421,6 +421,14 @@ do { \
#define E1000_I210_FLA 0x1201C
+#define E1000_I210_DTXMXPKTSZ 0x355C
+
+#define E1000_I210_TXDCTL(_n) (0x0E028 + ((_n) * 0x40))
+
+#define E1000_I210_TQAVCTRL 0x3570
+#define E1000_I210_TQAVCC(_n) (0x3004 + ((_n) * 0x40))
+#define E1000_I210_TQAVHC(_n) (0x300C + ((_n) * 0x40))
+
#define E1000_INVM_DATA_REG(_n) (0x12120 + 4*(_n))
#define E1000_INVM_SIZE 64 /* Number of INVM Data Registers */
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 06ffb2bc713e..92845692087a 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -281,6 +281,11 @@ struct igb_ring {
u16 count; /* number of desc. in the ring */
u8 queue_index; /* logical index of the ring*/
u8 reg_idx; /* physical index of the ring */
+ bool cbs_enable; /* indicates if CBS is enabled */
+ s32 idleslope; /* idleSlope in kbps */
+ s32 sendslope; /* sendSlope in kbps */
+ s32 hicredit; /* hiCredit in bytes */
+ s32 locredit; /* loCredit in bytes */
/* everything past this point are written often */
u16 next_to_clean;
@@ -621,6 +626,7 @@ struct igb_adapter {
#define IGB_FLAG_EEE BIT(14)
#define IGB_FLAG_VLAN_PROMISC BIT(15)
#define IGB_FLAG_RX_LEGACY BIT(16)
+#define IGB_FLAG_FQTSS BIT(17)
/* Media Auto Sense */
#define IGB_MAS_ENABLE_0 0X0001
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 837d9b46a390..be2cf263efa9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -34,6 +34,7 @@
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/ip6_checksum.h>
+#include <net/pkt_sched.h>
#include <linux/net_tstamp.h>
#include <linux/mii.h>
#include <linux/ethtool.h>
@@ -62,6 +63,17 @@
#define BUILD 0
#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \
__stringify(BUILD) "-k"
+
+enum queue_mode {
+ QUEUE_MODE_STRICT_PRIORITY,
+ QUEUE_MODE_STREAM_RESERVATION,
+};
+
+enum tx_queue_prio {
+ TX_QUEUE_PRIO_HIGH,
+ TX_QUEUE_PRIO_LOW,
+};
+
char igb_driver_name[] = "igb";
char igb_driver_version[] = DRV_VERSION;
static const char igb_driver_string[] =
@@ -1271,6 +1283,12 @@ static int igb_alloc_q_vector(struct igb_adapter *adapter,
ring->count = adapter->tx_ring_count;
ring->queue_index = txr_idx;
+ ring->cbs_enable = false;
+ ring->idleslope = 0;
+ ring->sendslope = 0;
+ ring->hicredit = 0;
+ ring->locredit = 0;
+
u64_stats_init(&ring->tx_syncp);
u64_stats_init(&ring->tx_syncp2);
@@ -1598,6 +1616,284 @@ static void igb_get_hw_control(struct igb_adapter *adapter)
ctrl_ext | E1000_CTRL_EXT_DRV_LOAD);
}
+static void enable_fqtss(struct igb_adapter *adapter, bool enable)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct e1000_hw *hw = &adapter->hw;
+
+ WARN_ON(hw->mac.type != e1000_i210);
+
+ if (enable)
+ adapter->flags |= IGB_FLAG_FQTSS;
+ else
+ adapter->flags &= ~IGB_FLAG_FQTSS;
+
+ if (netif_running(netdev))
+ schedule_work(&adapter->reset_task);
+}
+
+static bool is_fqtss_enabled(struct igb_adapter *adapter)
+{
+ return (adapter->flags & IGB_FLAG_FQTSS) ? true : false;
+}
+
+static void set_tx_desc_fetch_prio(struct e1000_hw *hw, int queue,
+ enum tx_queue_prio prio)
+{
+ u32 val;
+
+ WARN_ON(hw->mac.type != e1000_i210);
+ WARN_ON(queue < 0 || queue > 4);
+
+ val = rd32(E1000_I210_TXDCTL(queue));
+
+ if (prio == TX_QUEUE_PRIO_HIGH)
+ val |= E1000_TXDCTL_PRIORITY;
+ else
+ val &= ~E1000_TXDCTL_PRIORITY;
+
+ wr32(E1000_I210_TXDCTL(queue), val);
+}
+
+static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
+{
+ u32 val;
+
+ WARN_ON(hw->mac.type != e1000_i210);
+ WARN_ON(queue < 0 || queue > 1);
+
+ val = rd32(E1000_I210_TQAVCC(queue));
+
+ if (mode == QUEUE_MODE_STREAM_RESERVATION)
+ val |= E1000_TQAVCC_QUEUEMODE;
+ else
+ val &= ~E1000_TQAVCC_QUEUEMODE;
+
+ wr32(E1000_I210_TQAVCC(queue), val);
+}
+
+/**
+ * igb_configure_cbs - Configure Credit-Based Shaper (CBS)
+ * @adapter: pointer to adapter struct
+ * @queue: queue number
+ * @enable: true = enable CBS, false = disable CBS
+ * @idleslope: idleSlope in kbps
+ * @sendslope: sendSlope in kbps
+ * @hicredit: hiCredit in bytes
+ * @locredit: loCredit in bytes
+ *
+ * Configure CBS for a given hardware queue. When disabling, idleslope,
+ * sendslope, hicredit, locredit arguments are ignored. Returns 0 if
+ * success. Negative otherwise.
+ **/
+static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
+ bool enable, int idleslope, int sendslope,
+ int hicredit, int locredit)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct e1000_hw *hw = &adapter->hw;
+ u32 tqavcc;
+ u16 value;
+
+ WARN_ON(hw->mac.type != e1000_i210);
+ WARN_ON(queue < 0 || queue > 1);
+
+ if (enable) {
+ set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+ set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+
+ /* According to i210 datasheet section 7.2.7.7, we should set
+ * the 'idleSlope' field from TQAVCC register following the
+ * equation:
+ *
+ * For 100 Mbps link speed:
+ *
+ * value = BW * 0x7735 * 0.2 (E1)
+ *
+ * For 1000Mbps link speed:
+ *
+ * value = BW * 0x7735 * 2 (E2)
+ *
+ * E1 and E2 can be merged into one equation as shown below.
+ * Note that 'link-speed' is in Mbps.
+ *
+ * value = BW * 0x7735 * 2 * link-speed
+ * -------------- (E3)
+ * 1000
+ *
+ * 'BW' is the percentage bandwidth out of full link speed
+ * which can be found with the following equation. Note that
+ * idleSlope here is the parameter from this function which
+ * is in kbps.
+ *
+ * BW = idleSlope
+ * ----------------- (E4)
+ * link-speed * 1000
+ *
+ * That said, we can come up with a generic equation to
+ * calculate the value we should set it TQAVCC register by
+ * replacing 'BW' in E3 by E4. The resulting equation is:
+ *
+ * value = idleSlope * 0x7735 * 2 * link-speed
+ * ----------------- -------------- (E5)
+ * link-speed * 1000 1000
+ *
+ * 'link-speed' is present in both sides of the fraction so
+ * it is canceled out. The final equation is the following:
+ *
+ * value = idleSlope * 61034
+ * ----------------- (E6)
+ * 1000000
+ */
+ value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
+
+ tqavcc = rd32(E1000_I210_TQAVCC(queue));
+ tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
+ tqavcc |= value;
+ wr32(E1000_I210_TQAVCC(queue), tqavcc);
+
+ wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735);
+ } else {
+ set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+ set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+
+ /* Set idleSlope to zero. */
+ tqavcc = rd32(E1000_I210_TQAVCC(queue));
+ tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
+ wr32(E1000_I210_TQAVCC(queue), tqavcc);
+
+ /* Set hiCredit to zero. */
+ wr32(E1000_I210_TQAVHC(queue), 0);
+ }
+
+ /* XXX: In i210 controller the sendSlope and loCredit parameters from
+ * CBS are not configurable by software so we don't do any 'controller
+ * configuration' in respect to these parameters.
+ */
+
+ netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
+ (enable) ? "enabled" : "disabled", queue,
+ idleslope, sendslope, hicredit, locredit);
+}
+
+static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
+ bool enable, int idleslope, int sendslope,
+ int hicredit, int locredit)
+{
+ struct igb_ring *ring;
+
+ if (queue < 0 || queue > adapter->num_tx_queues)
+ return -EINVAL;
+
+ ring = adapter->tx_ring[queue];
+
+ ring->cbs_enable = enable;
+ ring->idleslope = idleslope;
+ ring->sendslope = sendslope;
+ ring->hicredit = hicredit;
+ ring->locredit = locredit;
+
+ return 0;
+}
+
+static bool is_any_cbs_enabled(struct igb_adapter *adapter)
+{
+ struct igb_ring *ring;
+ int i;
+
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ ring = adapter->tx_ring[i];
+
+ if (ring->cbs_enable)
+ return true;
+ }
+
+ return false;
+}
+
+static void igb_setup_tx_mode(struct igb_adapter *adapter)
+{
+ struct net_device *netdev = adapter->netdev;
+ struct e1000_hw *hw = &adapter->hw;
+ u32 val;
+
+ /* Only i210 controller supports changing the transmission mode. */
+ if (hw->mac.type != e1000_i210)
+ return;
+
+ if (is_fqtss_enabled(adapter)) {
+ int i, max_queue;
+
+ /* Configure TQAVCTRL register: set transmit mode to 'Qav',
+ * set data fetch arbitration to 'round robin' and set data
+ * transfer arbitration to 'credit shaper algorithm.
+ */
+ val = rd32(E1000_I210_TQAVCTRL);
+ val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB;
+ val &= ~E1000_TQAVCTRL_DATAFETCHARB;
+ wr32(E1000_I210_TQAVCTRL, val);
+
+ /* Configure Tx and Rx packet buffers sizes as described in
+ * i210 datasheet section 7.2.7.7.
+ */
+ val = rd32(E1000_TXPBS);
+ val &= ~I210_TXPBSIZE_MASK;
+ val |= I210_TXPBSIZE_PB0_8KB | I210_TXPBSIZE_PB1_8KB |
+ I210_TXPBSIZE_PB2_4KB | I210_TXPBSIZE_PB3_4KB;
+ wr32(E1000_TXPBS, val);
+
+ val = rd32(E1000_RXPBS);
+ val &= ~I210_RXPBSIZE_MASK;
+ val |= I210_RXPBSIZE_PB_32KB;
+ wr32(E1000_RXPBS, val);
+
+ /* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ
+ * register should not exceed the buffer size programmed in
+ * TXPBS. The smallest buffer size programmed in TXPBS is 4kB
+ * so according to the datasheet we should set MAX_TPKT_SIZE to
+ * 4kB / 64.
+ *
+ * However, when we do so, no frame from queue 2 and 3 are
+ * transmitted. It seems the MAX_TPKT_SIZE should not be great
+ * or _equal_ to the buffer size programmed in TXPBS. For this
+ * reason, we set set MAX_ TPKT_SIZE to (4kB - 1) / 64.
+ */
+ val = (4096 - 1) / 64;
+ wr32(E1000_I210_DTXMXPKTSZ, val);
+
+ /* Since FQTSS mode is enabled, apply any CBS configuration
+ * previously set. If no previous CBS configuration has been
+ * done, then the initial configuration is applied, which means
+ * CBS is disabled.
+ */
+ max_queue = (adapter->num_tx_queues < I210_SR_QUEUES_NUM) ?
+ adapter->num_tx_queues : I210_SR_QUEUES_NUM;
+
+ for (i = 0; i < max_queue; i++) {
+ struct igb_ring *ring = adapter->tx_ring[i];
+
+ igb_configure_cbs(adapter, i, ring->cbs_enable,
+ ring->idleslope, ring->sendslope,
+ ring->hicredit, ring->locredit);
+ }
+ } else {
+ wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
+ wr32(E1000_TXPBS, I210_TXPBSIZE_DEFAULT);
+ wr32(E1000_I210_DTXMXPKTSZ, I210_DTXMXPKTSZ_DEFAULT);
+
+ val = rd32(E1000_I210_TQAVCTRL);
+ /* According to Section 8.12.21, the other flags we've set when
+ * enabling FQTSS are not relevant when disabling FQTSS so we
+ * don't set they here.
+ */
+ val &= ~E1000_TQAVCTRL_XMIT_MODE;
+ wr32(E1000_I210_TQAVCTRL, val);
+ }
+
+ netdev_dbg(netdev, "FQTSS %s\n", (is_fqtss_enabled(adapter)) ?
+ "enabled" : "disabled");
+}
+
/**
* igb_configure - configure the hardware for RX and TX
* @adapter: private board structure
@@ -1609,6 +1905,7 @@ static void igb_configure(struct igb_adapter *adapter)
igb_get_hw_control(adapter);
igb_set_rx_mode(netdev);
+ igb_setup_tx_mode(adapter);
igb_restore_vlan(adapter);
@@ -2150,6 +2447,55 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev,
return features;
}
+static int igb_offload_cbs(struct igb_adapter *adapter,
+ struct tc_cbs_qopt_offload *qopt)
+{
+ struct e1000_hw *hw = &adapter->hw;
+ int err;
+
+ /* CBS offloading is only supported by i210 controller. */
+ if (hw->mac.type != e1000_i210)
+ return -EOPNOTSUPP;
+
+ /* CBS offloading is only supported by queue 0 and queue 1. */
+ if (qopt->queue < 0 || qopt->queue > 1)
+ return -EINVAL;
+
+ err = igb_save_cbs_params(adapter, qopt->queue, qopt->enable,
+ qopt->idleslope, qopt->sendslope,
+ qopt->hicredit, qopt->locredit);
+ if (err)
+ return err;
+
+ if (is_fqtss_enabled(adapter)) {
+ igb_configure_cbs(adapter, qopt->queue, qopt->enable,
+ qopt->idleslope, qopt->sendslope,
+ qopt->hicredit, qopt->locredit);
+
+ if (!is_any_cbs_enabled(adapter))
+ enable_fqtss(adapter, false);
+
+ } else {
+ enable_fqtss(adapter, true);
+ }
+
+ return 0;
+}
+
+static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
+ void *type_data)
+{
+ struct igb_adapter *adapter = netdev_priv(dev);
+
+ switch (type) {
+ case TC_SETUP_CBS:
+ return igb_offload_cbs(adapter, type_data);
+
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+
static const struct net_device_ops igb_netdev_ops = {
.ndo_open = igb_open,
.ndo_stop = igb_close,
@@ -2175,6 +2521,7 @@ static const struct net_device_ops igb_netdev_ops = {
.ndo_set_features = igb_set_features,
.ndo_fdb_add = igb_ndo_fdb_add,
.ndo_features_check = igb_features_check,
+ .ndo_setup_tc = igb_setup_tc,
};
/**
--
2.14.2
^ permalink raw reply related
* [next-queue PATCH v9 5/6] net/sched: Add support for HW offloading for CBS
From: Vinicius Costa Gomes @ 2017-10-17 1:01 UTC (permalink / raw)
To: netdev, intel-wired-lan
Cc: Vinicius Costa Gomes, jhs, xiyou.wangcong, jiri, andre.guedes,
ivan.briano, jesus.sanchez-palencia, boon.leong.ong,
richardcochran, henrik, levipearson, rodney.cummings
In-Reply-To: <20171017010128.22141-1-vinicius.gomes@intel.com>
This adds support for offloading the CBS algorithm to the controller,
if supported. Drivers wanting to support CBS offload must implement
the .ndo_setup_tc callback and handle the TC_SETUP_CBS (introduced
here) type.
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
---
include/linux/netdevice.h | 1 +
include/net/pkt_sched.h | 9 ++++
net/sched/sch_cbs.c | 104 ++++++++++++++++++++++++++++++++++++++++------
3 files changed, 102 insertions(+), 12 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 31bb3010c69b..1f6c44ef5b21 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -775,6 +775,7 @@ enum tc_setup_type {
TC_SETUP_CLSFLOWER,
TC_SETUP_CLSMATCHALL,
TC_SETUP_CLSBPF,
+ TC_SETUP_CBS,
};
/* These structures hold the attributes of xdp state that are being passed
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 259bc191ba59..7c597b050b36 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -146,4 +146,13 @@ static inline bool is_classid_clsact_egress(u32 classid)
TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_EGRESS);
}
+struct tc_cbs_qopt_offload {
+ u8 enable;
+ s32 queue;
+ s32 hicredit;
+ s32 locredit;
+ s32 idleslope;
+ s32 sendslope;
+};
+
#endif
diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index c0102b589494..cae021c642e5 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -68,6 +68,8 @@
#define BYTES_PER_KBIT (1000LL / 8)
struct cbs_sched_data {
+ bool offload;
+ int queue;
s64 port_rate; /* in bytes/s */
s64 last; /* timestamp in ns */
s64 credits; /* in bytes */
@@ -80,6 +82,11 @@ struct cbs_sched_data {
struct sk_buff *(*dequeue)(struct Qdisc *sch);
};
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch)
+{
+ return qdisc_enqueue_tail(skb, sch);
+}
+
static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
{
struct cbs_sched_data *q = qdisc_priv(sch);
@@ -169,6 +176,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
return skb;
}
+static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch)
+{
+ return qdisc_dequeue_head(sch);
+}
+
static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
{
struct cbs_sched_data *q = qdisc_priv(sch);
@@ -180,14 +192,66 @@ static const struct nla_policy cbs_policy[TCA_CBS_MAX + 1] = {
[TCA_CBS_PARMS] = { .len = sizeof(struct tc_cbs_qopt) },
};
+static void cbs_disable_offload(struct net_device *dev,
+ struct cbs_sched_data *q)
+{
+ struct tc_cbs_qopt_offload cbs = { };
+ const struct net_device_ops *ops;
+ int err;
+
+ if (!q->offload)
+ return;
+
+ q->enqueue = cbs_enqueue_soft;
+ q->dequeue = cbs_dequeue_soft;
+
+ ops = dev->netdev_ops;
+ if (!ops->ndo_setup_tc)
+ return;
+
+ cbs.queue = q->queue;
+ cbs.enable = 0;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+ if (err < 0)
+ pr_warn("Couldn't disable CBS offload for queue %d\n",
+ cbs.queue);
+}
+
+static int cbs_enable_offload(struct net_device *dev, struct cbs_sched_data *q,
+ const struct tc_cbs_qopt *opt)
+{
+ const struct net_device_ops *ops = dev->netdev_ops;
+ struct tc_cbs_qopt_offload cbs = { };
+ int err;
+
+ if (!ops->ndo_setup_tc)
+ return -EOPNOTSUPP;
+
+ cbs.queue = q->queue;
+
+ cbs.enable = 1;
+ cbs.hicredit = opt->hicredit;
+ cbs.locredit = opt->locredit;
+ cbs.idleslope = opt->idleslope;
+ cbs.sendslope = opt->sendslope;
+
+ err = ops->ndo_setup_tc(dev, TC_SETUP_CBS, &cbs);
+ if (err < 0)
+ return err;
+
+ q->enqueue = cbs_enqueue_offload;
+ q->dequeue = cbs_dequeue_offload;
+
+ return 0;
+}
+
static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
{
struct cbs_sched_data *q = qdisc_priv(sch);
struct net_device *dev = qdisc_dev(sch);
struct nlattr *tb[TCA_CBS_MAX + 1];
- struct ethtool_link_ksettings ecmd;
struct tc_cbs_qopt *qopt;
- s64 link_speed;
int err;
err = nla_parse_nested(tb, TCA_CBS_MAX, opt, cbs_policy, NULL);
@@ -199,23 +263,30 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
qopt = nla_data(tb[TCA_CBS_PARMS]);
- if (qopt->offload)
- return -EOPNOTSUPP;
+ if (!qopt->offload) {
+ struct ethtool_link_ksettings ecmd;
+ s64 link_speed;
- if (!__ethtool_get_link_ksettings(dev, &ecmd))
- link_speed = ecmd.base.speed;
- else
- link_speed = SPEED_1000;
+ if (!__ethtool_get_link_ksettings(dev, &ecmd))
+ link_speed = ecmd.base.speed;
+ else
+ link_speed = SPEED_1000;
- q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
+ q->port_rate = link_speed * 1000 * BYTES_PER_KBIT;
- q->enqueue = cbs_enqueue_soft;
- q->dequeue = cbs_dequeue_soft;
+ cbs_disable_offload(dev, q);
+ } else {
+ err = cbs_enable_offload(dev, q, qopt);
+ if (err < 0)
+ return err;
+ }
+ /* Everything went OK, save the parameters used. */
q->hicredit = qopt->hicredit;
q->locredit = qopt->locredit;
q->idleslope = qopt->idleslope * BYTES_PER_KBIT;
q->sendslope = qopt->sendslope * BYTES_PER_KBIT;
+ q->offload = qopt->offload;
return 0;
}
@@ -223,10 +294,16 @@ static int cbs_change(struct Qdisc *sch, struct nlattr *opt)
static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
{
struct cbs_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
if (!opt)
return -EINVAL;
+ q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+ q->enqueue = cbs_enqueue_soft;
+ q->dequeue = cbs_dequeue_soft;
+
qdisc_watchdog_init(&q->watchdog, sch);
return cbs_change(sch, opt);
@@ -235,8 +312,11 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt)
static void cbs_destroy(struct Qdisc *sch)
{
struct cbs_sched_data *q = qdisc_priv(sch);
+ struct net_device *dev = qdisc_dev(sch);
qdisc_watchdog_cancel(&q->watchdog);
+
+ cbs_disable_offload(dev, q);
}
static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -253,7 +333,7 @@ static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
opt.locredit = q->locredit;
opt.sendslope = q->sendslope / BYTES_PER_KBIT;
opt.idleslope = q->idleslope / BYTES_PER_KBIT;
- opt.offload = 0;
+ opt.offload = q->offload;
if (nla_put(skb, TCA_CBS_PARMS, sizeof(opt), &opt))
goto nla_put_failure;
--
2.14.2
^ permalink raw reply related
* RE: [patch net v2 4/4] selftests: Introduce a new test case to tc testsuite
From: Chris Mi @ 2017-10-17 1:03 UTC (permalink / raw)
To: Lucas Bates
Cc: netdev@vger.kernel.org, Jamal Hadi Salim, Cong Wang, Jiri Pirko,
davem@davemloft.net
In-Reply-To: <CAMDBHYJ6PyuFFXVj3y2o+qd3CFomjdH_cd05kU+CdHQv4bCRrg@mail.gmail.com>
> -----Original Message-----
> From: Lucas Bates [mailto:lucasb@mojatatu.com]
> Sent: Tuesday, October 17, 2017 12:25 AM
> To: Chris Mi <chrism@mellanox.com>
> Cc: netdev@vger.kernel.org; Jamal Hadi Salim <jhs@mojatatu.com>; Cong
> Wang <xiyou.wangcong@gmail.com>; Jiri Pirko <jiri@resnulli.us>;
> davem@davemloft.net
> Subject: Re: [patch net v2 4/4] selftests: Introduce a new test case to tc
> testsuite
>
> On Mon, Oct 16, 2017 at 7:18 AM, Chris Mi <chrism@mellanox.com> wrote:
> > In this patchset, we fixed a tc bug. This patch adds the test case
> > that reproduces the bug. To run this test case, user should specify an
> > existing NIC device:
> > # sudo ./tdc.py -d enp4s0f0
> >
> > This test case belongs to category "flower". If user doesn't specify a
> > NIC device, the test cases belong to "flower" will not be run.
> >
> > In this test case, we create 1M filters and all filters share the same
> > action. When destroying all filters, kernel should not panic. It takes
> > about 18s to run it.
> >
> > Signed-off-by: Chris Mi <chrism@mellanox.com>
> > Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
>
> I'm a little wary about adding changes like these into tdc.py directly; I don't
> think it's going to be sustainable in the long run.
> Even the namespace creation I put in to the original version is too specific and
> limiting.
>
> There are some upcoming changes to tdc to help address these particular
> issues. I'll ack this for now, thanks.
OK. Thanks for your review, Lucas.
>
> Acked-by: Lucas Bates <lucasb@mojatatu.com>
>
>
> > ---
> > .../tc-testing/tc-tests/filters/tests.json | 23
> +++++++++++++++++++++-
> > tools/testing/selftests/tc-testing/tdc.py | 20 +++++++++++++++----
> > tools/testing/selftests/tc-testing/tdc_config.py | 2 ++
> > 3 files changed, 40 insertions(+), 5 deletions(-)
> >
> > diff --git
> > a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
> > b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
> > index c727b96..5fa02d8 100644
> > --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
> > +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
> > @@ -17,5 +17,26 @@
> > "teardown": [
> > "$TC qdisc del dev $DEV1 ingress"
> > ]
> > + },
> > + {
> > + "id": "d052",
> > + "name": "Add 1M filters with the same action",
> > + "category": [
> > + "filter",
> > + "flower"
> > + ],
> > + "setup": [
> > + "$TC qdisc add dev $DEV2 ingress",
> > + "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
> > + ],
> > + "cmdUnderTest": "$TC -b $BATCH_FILE",
> > + "expExitCode": "0",
> > + "verifyCmd": "$TC actions list action gact",
> > + "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000
> bind 1000000",
> > + "matchCount": "1",
> > + "teardown": [
> > + "$TC qdisc del dev $DEV2 ingress",
> > + "/bin/rm $BATCH_FILE"
> > + ]
> > }
> > -]
> > \ No newline at end of file
> > +]
> > diff --git a/tools/testing/selftests/tc-testing/tdc.py
> > b/tools/testing/selftests/tc-testing/tdc.py
> > index cd61b78..5f11f5d 100755
> > --- a/tools/testing/selftests/tc-testing/tdc.py
> > +++ b/tools/testing/selftests/tc-testing/tdc.py
> > @@ -88,7 +88,7 @@ def prepare_env(cmdlist):
> > exit(1)
> >
> >
> > -def test_runner(filtered_tests):
> > +def test_runner(filtered_tests, args):
> > """
> > Driver function for the unit tests.
> >
> > @@ -105,6 +105,8 @@ def test_runner(filtered_tests):
> > for tidx in testlist:
> > result = True
> > tresult = ""
> > + if "flower" in tidx["category"] and args.device == None:
> > + continue
> > print("Test " + tidx["id"] + ": " + tidx["name"])
> > prepare_env(tidx["setup"])
> > (p, procout) = exec_cmd(tidx["cmdUnderTest"]) @@ -152,6
> > +154,10 @@ def ns_create():
> > exec_cmd(cmd, False)
> > cmd = 'ip -s $NS link set $DEV1 up'
> > exec_cmd(cmd, False)
> > + cmd = 'ip link set $DEV2 netns $NS'
> > + exec_cmd(cmd, False)
> > + cmd = 'ip -s $NS link set $DEV2 up'
> > + exec_cmd(cmd, False)
> >
> >
> > def ns_destroy():
> > @@ -211,7 +217,8 @@ def set_args(parser):
> > help='Execute the single test case with specified ID')
> > parser.add_argument('-i', '--id', action='store_true', dest='gen_id',
> > help='Generate ID numbers for new test cases')
> > - return parser
> > + parser.add_argument('-d', '--device',
> > + help='Execute the test case in flower
> > + category')
> > return parser
> >
> >
> > @@ -225,6 +232,8 @@ def check_default_settings(args):
> >
> > if args.path != None:
> > NAMES['TC'] = args.path
> > + if args.device != None:
> > + NAMES['DEV2'] = args.device
> > if not os.path.isfile(NAMES['TC']):
> > print("The specified tc path " + NAMES['TC'] + " does not exist.")
> > exit(1)
> > @@ -381,14 +390,17 @@ def set_operation_mode(args):
> > if (len(alltests) == 0):
> > print("Cannot find a test case with ID matching " + target_id)
> > exit(1)
> > - catresults = test_runner(alltests)
> > + catresults = test_runner(alltests, args)
> > print("All test results: " + "\n\n" + catresults)
> > elif (len(target_category) > 0):
> > + if (target_category == "flower") and args.device == None:
> > + print("Please specify a NIC device (-d) to run category flower")
> > + exit(1)
> > if (target_category not in ucat):
> > print("Specified category is not present in this file.")
> > exit(1)
> > else:
> > - catresults = test_runner(testcases[target_category])
> > + catresults = test_runner(testcases[target_category],
> > + args)
> > print("Category " + target_category + "\n\n" +
> > catresults)
> >
> > ns_destroy()
> > diff --git a/tools/testing/selftests/tc-testing/tdc_config.py
> > b/tools/testing/selftests/tc-testing/tdc_config.py
> > index 0108737..b635251 100644
> > --- a/tools/testing/selftests/tc-testing/tdc_config.py
> > +++ b/tools/testing/selftests/tc-testing/tdc_config.py
> > @@ -12,6 +12,8 @@ NAMES = {
> > # Name of veth devices to be created for the namespace
> > 'DEV0': 'v0p0',
> > 'DEV1': 'v0p1',
> > + 'DEV2': '',
> > + 'BATCH_FILE': './batch.txt',
> > # Name of the namespace to use
> > 'NS': 'tcut'
> > }
> > --
> > 1.8.3.1
> >
^ permalink raw reply
* homepage of iptuils-tracepth ?
From: shirish शिरीष @ 2017-10-17 1:09 UTC (permalink / raw)
To: netdev
Dear all,
Please CC me as I'm not subscribed to the list. I recently came across
iptuils-tracepath . I tried to find the upstream homepage for it and
saw http://www.skbuff.net/iputils/ but it shows an older version while
Debian seems to have the later/latest
[$] apt-cache policy iputils-tracepath
iputils-tracepath:
Installed: 3:20161105-1
Candidate: 3:20161105-1
Version table:
*** 3:20161105-1 600
600 http://httpredir.debian.org/debian buster/main amd64 Packages
1 http://httpredir.debian.org/debian unstable/main amd64 Packages
100 /var/lib/dpkg/status
while the one shown on the skbuff.net shows one from 2015 only. It
would be nice to see a better home. Also there doesn't seem to be a
mirror on github.com
Look forward to know more.
--
Regards,
Shirish Agarwal शिरीष अग्रवाल
My quotes in this email licensed under CC 3.0
http://creativecommons.org/licenses/by-nc/3.0/
http://flossexperiences.wordpress.com
EB80 462B 08E1 A0DE A73A 2C2F 9F3D C7A4 E1C4 D2D8
^ permalink raw reply
* Re: RFC(v2): Audit Kernel Container IDs
From: Casey Schaufler @ 2017-10-17 1:10 UTC (permalink / raw)
To: Richard Guy Briggs
Cc: cgroups, Linux Containers, Linux API, Linux Audit, Linux FS Devel,
Linux Kernel, Linux Network Development, mszeredi,
Andy Lutomirski, jlayton, Carlos O'Donell, Al Viro,
David Howells, Simo Sorce, trondmy, Eric Paris, Serge E. Hallyn,
Eric W. Biederman
In-Reply-To: <20171017003340.whjdkqmkw4lydwy7@madcap2.tricolour.ca>
On 10/16/2017 5:33 PM, Richard Guy Briggs wrote:
> On 2017-10-12 16:33, Casey Schaufler wrote:
>> On 10/12/2017 7:14 AM, Richard Guy Briggs wrote:
>>> Containers are a userspace concept. The kernel knows nothing of them.
>>>
>>> The Linux audit system needs a way to be able to track the container
>>> provenance of events and actions. Audit needs the kernel's help to do
>>> this.
>>>
>>> Since the concept of a container is entirely a userspace concept, a
>>> registration from the userspace container orchestration system initiates
>>> this. This will define a point in time and a set of resources
>>> associated with a particular container with an audit container ID.
>>>
>>> The registration is a pseudo filesystem (proc, since PID tree already
>>> exists) write of a u8[16] UUID representing the container ID to a file
>>> representing a process that will become the first process in a new
>>> container. This write might place restrictions on mount namespaces
>>> required to define a container, or at least careful checking of
>>> namespaces in the kernel to verify permissions of the orchestrator so it
>>> can't change its own container ID. A bind mount of nsfs may be
>>> necessary in the container orchestrator's mntNS.
>>> Note: Use a 128-bit scalar rather than a string to make compares faster
>>> and simpler.
>>>
>>> Require a new CAP_CONTAINER_ADMIN to be able to carry out the
>>> registration.
>> Hang on. If containers are a user space concept, how can
>> you want CAP_CONTAINER_ANYTHING? If there's not such thing as
>> a container, how can you be asking for a capability to manage
>> them?
> There is such a thing, but the kernel doesn't know about it yet.
Then how can it be the kernel's place to control access to a
container resource, that is, the containerID.
> This
> same situation exists for loginuid and sessionid which are userspace
> concepts that the kernel tracks for the convenience of userspace.
Ah, no. Loginuid identifies a user, which is a kernel concept in
that a user is defined by the uid. The session ID has well defined
kernel semantics. You're trying to say that the containerID is an
opaque value that is meaningless to the kernel, but you still want
the kernel to protect it. How can the kernel know if it is protecting
it correctly?
> As
> for its name, I'm not particularly picky, so if you don't like
> CAP_CONTAINER_* then I'm fine with CAP_AUDIT_CONTAINERID. It really
> needs to be distinct from CAP_AUDIT_WRITE and CAP_AUDIT_CONTROL since we
> don't want to give the ability to set a containerID to any process that
> is able to do audit logging (such as vsftpd) and similarly we don't want
> to give the orchestrator the ability to control the setup of the audit
> daemon.
Sorry, but what aspect of the kernel security policy is this
capability supposed to protect? That's what capabilities are
for, not the undefined support of undefined user-space behavior.
If it's audit behavior, you want CAP_AUDIT_CONTROL. If it's
more than audit behavior you have to define what system security
policy you're dealing with in order to pick the right capability.
We get this request pretty regularly. "I need my own capability
because I have a niche thing that isn't part of the system security
policy but that is important!" Fit the containerID into the
system security policy, and if that results in using CAP_SYS_ADMIN,
oh well.
>>> At that time, record the target container's user-supplied
>>> container identifier along with the target container's first process
>>> (which may become the target container's "init" process) process ID
>>> (referenced from the initial PID namespace), all namespace IDs (in the
>>> form of a nsfs device number and inode number tuple) in a new auxilliary
>>> record AUDIT_CONTAINER with a qualifying op=$action field.
>>>
>>> Issue a new auxilliary record AUDIT_CONTAINER_INFO for each valid
>>> container ID present on an auditable action or event.
>>>
>>> Forked and cloned processes inherit their parent's container ID,
>>> referenced in the process' task_struct.
>>>
>>> Mimic setns(2) and return an error if the process has already initiated
>>> threading or forked since this registration should happen before the
>>> process execution is started by the orchestrator and hence should not
>>> yet have any threads or children. If this is deemed overly restrictive,
>>> switch all threads and children to the new containerID.
>>>
>>> Trust the orchestrator to judiciously use and restrict CAP_CONTAINER_ADMIN.
>>>
>>> Log the creation of every namespace, inheriting/adding its spawning
>>> process' containerID(s), if applicable. Include the spawning and
>>> spawned namespace IDs (device and inode number tuples).
>>> [AUDIT_NS_CREATE, AUDIT_NS_DESTROY] [clone(2), unshare(2), setns(2)]
>>> Note: At this point it appears only network namespaces may need to track
>>> container IDs apart from processes since incoming packets may cause an
>>> auditable event before being associated with a process.
>>>
>>> Log the destruction of every namespace when it is no longer used by any
>>> process, include the namespace IDs (device and inode number tuples).
>>> [AUDIT_NS_DESTROY] [process exit, unshare(2), setns(2)]
>>>
>>> Issue a new auxilliary record AUDIT_NS_CHANGE listing (opt: op=$action)
>>> the parent and child namespace IDs for any changes to a process'
>>> namespaces. [setns(2)]
>>> Note: It may be possible to combine AUDIT_NS_* record formats and
>>> distinguish them with an op=$action field depending on the fields
>>> required for each message type.
>>>
>>> When a container ceases to exist because the last process in that
>>> container has exited and hence the last namespace has been destroyed and
>>> its refcount dropping to zero, log the fact.
>>> (This latter is likely needed for certification accountability.) A
>>> container object may need a list of processes and/or namespaces.
>>>
>>> A namespace cannot directly migrate from one container to another but
>>> could be assigned to a newly spawned container. A namespace can be
>>> moved from one container to another indirectly by having that namespace
>>> used in a second process in another container and then ending all the
>>> processes in the first container.
>>>
>>> (v2)
>>> - switch from u64 to u128 UUID
>>> - switch from "signal" and "trigger" to "register"
>>> - restrict registration to single process or force all threads and children into same container
>>>
>>> - RGB
> - RGB
>
> --
> Richard Guy Briggs <rgb@redhat.com>
> Sr. S/W Engineer, Kernel Security, Base Operating Systems
> Remote, Ottawa, Red Hat Canada
> IRC: rgb, SunRaycer
> Voice: +1.647.777.2635, Internal: (81) 32635
>
^ permalink raw reply
* RE: [patch net v2 1/4] net/sched: Change tc_action refcnt and bindcnt to atomic
From: Chris Mi @ 2017-10-17 1:14 UTC (permalink / raw)
To: Cong Wang
Cc: Linux Kernel Network Developers, Jamal Hadi Salim, Lucas Bates,
Jiri Pirko, David Miller
In-Reply-To: <CAM_iQpXA5y8nqCRAxy-9VJTSf3Z7g-6pL1PL1omcwkZn1apFUw@mail.gmail.com>
> -----Original Message-----
> From: Cong Wang [mailto:xiyou.wangcong@gmail.com]
> Sent: Tuesday, October 17, 2017 1:06 AM
> To: Chris Mi <chrism@mellanox.com>
> Cc: Linux Kernel Network Developers <netdev@vger.kernel.org>; Jamal Hadi
> Salim <jhs@mojatatu.com>; Lucas Bates <lucasb@mojatatu.com>; Jiri Pirko
> <jiri@resnulli.us>; David Miller <davem@davemloft.net>
> Subject: Re: [patch net v2 1/4] net/sched: Change tc_action refcnt and
> bindcnt to atomic
>
> On Mon, Oct 16, 2017 at 4:18 AM, Chris Mi <chrism@mellanox.com> wrote:
> > If many filters share the same action. That action's refcnt and
> > bindcnt could be manipulated by many RCU callbacks at the same time.
> > This patch makes these operations atomic.
>
> Actually I have been thinking about removing these RCU callbacks, they are
> not necessary AFAIK, callers hold RTNL lock so they are allowed to block. The
> only drawback is that adding a synchronize_rcu(), but these are slow paths
> anyway...
>
> I am not sure, it is arguable anyway, essentially it is:
>
> synchronize_rcu() in slow path vs. multiple RCU callback races
>
>
> >
> > Fixes commit in pre-git era.
> >
> > Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
>
> This is not true, the action RCU callbacks were introduced
> by:
>
> commit c7de2cf053420d63bac85133469c965d4b1083e1
> Author: Eric Dumazet <eric.dumazet@gmail.com>
> Date: Wed Jun 9 02:09:23 2010 +0000
>
> pkt_sched: gen_kill_estimator() rcu fixes
>
>
> and the filter RCU callbacks were introduced by the patchset like this one:
>
>
> commit 1ce87720d456e471de0fbd814dc5d1fe10fc1c44
> Author: John Fastabend <john.fastabend@gmail.com>
> Date: Fri Sep 12 20:09:16 2014 -0700
>
> net: sched: make cls_u32 lockless
I don't think this bug were introduced by above two commits only.
Actually, this bug were introduced by several commits, at least the following:
1. refcnt and bindcnt are not atomic
2. passing actions using list instead of arrays (I think initially we are using arrays)
3. using RCU callbacks
So instead of blaming the latest commit, it is better to say it is a pre-git error.
^ permalink raw reply
* [patch net v3 0/4] net/sched: Fix a system panic when deleting filters
From: Chris Mi @ 2017-10-17 1:20 UTC (permalink / raw)
To: netdev; +Cc: jhs, lucasb, xiyou.wangcong, jiri, davem
If some filters share the same action, when deleting these filters,
it is possible to create a system panic. This is because deletions
could be manipulated by many RCU callbacks at the same time.
This patch set fixes these issues. To reproduce the issue run selftests
in patch 3 and 4. To test if the issue was fixed, apply patches 1 and 2
and then repeat the tests.
v2 changelog
============
Revise the comment and add Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
v3 changelog
============
Add Acked-by: Lucas Bates <lucasb@mojatatu.com> for patch 3 and 4
Chris Mi (4):
net/sched: Change tc_action refcnt and bindcnt to atomic
net/sched: Use action array instead of action list as parameter
selftests: Introduce a new script to generate tc batch file
selftests: Introduce a new test case to tc testsuite
include/net/act_api.h | 11 +-
net/sched/act_api.c | 124 +++++++++++++--------
net/sched/act_bpf.c | 4 +-
net/sched/act_connmark.c | 4 +-
net/sched/act_csum.c | 4 +-
net/sched/act_gact.c | 4 +-
net/sched/act_ife.c | 4 +-
net/sched/act_ipt.c | 4 +-
net/sched/act_mirred.c | 4 +-
net/sched/act_nat.c | 4 +-
net/sched/act_pedit.c | 4 +-
net/sched/act_police.c | 4 +-
net/sched/act_sample.c | 4 +-
net/sched/act_simple.c | 4 +-
net/sched/act_skbedit.c | 4 +-
net/sched/act_skbmod.c | 4 +-
net/sched/act_tunnel_key.c | 4 +-
net/sched/act_vlan.c | 4 +-
net/sched/cls_api.c | 18 +--
.../tc-testing/tc-tests/filters/tests.json | 23 +++-
tools/testing/selftests/tc-testing/tdc.py | 20 +++-
tools/testing/selftests/tc-testing/tdc_batch.py | 62 +++++++++++
tools/testing/selftests/tc-testing/tdc_config.py | 2 +
23 files changed, 222 insertions(+), 102 deletions(-)
create mode 100755 tools/testing/selftests/tc-testing/tdc_batch.py
--
1.8.3.1
^ permalink raw reply
* [patch net v3 1/4] net/sched: Change tc_action refcnt and bindcnt to atomic
From: Chris Mi @ 2017-10-17 1:20 UTC (permalink / raw)
To: netdev; +Cc: jhs, lucasb, xiyou.wangcong, jiri, davem
In-Reply-To: <1508203218-17998-1-git-send-email-chrism@mellanox.com>
If many filters share the same action. That action's refcnt and bindcnt
could be manipulated by many RCU callbacks at the same time. This patch
makes these operations atomic.
Fixes commit in pre-git era.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Chris Mi <chrism@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
include/net/act_api.h | 4 ++--
net/sched/act_api.c | 21 +++++++++++----------
net/sched/act_bpf.c | 4 ++--
net/sched/act_connmark.c | 4 ++--
net/sched/act_csum.c | 4 ++--
net/sched/act_gact.c | 4 ++--
net/sched/act_ife.c | 4 ++--
net/sched/act_ipt.c | 4 ++--
net/sched/act_mirred.c | 4 ++--
net/sched/act_nat.c | 4 ++--
net/sched/act_pedit.c | 4 ++--
net/sched/act_police.c | 4 ++--
net/sched/act_sample.c | 4 ++--
net/sched/act_simple.c | 4 ++--
net/sched/act_skbedit.c | 4 ++--
net/sched/act_skbmod.c | 4 ++--
net/sched/act_tunnel_key.c | 4 ++--
net/sched/act_vlan.c | 4 ++--
18 files changed, 45 insertions(+), 44 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index b944e0eb..a469ab6 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -25,8 +25,8 @@ struct tc_action {
struct tcf_idrinfo *idrinfo;
u32 tcfa_index;
- int tcfa_refcnt;
- int tcfa_bindcnt;
+ atomic_t tcfa_refcnt;
+ atomic_t tcfa_bindcnt;
u32 tcfa_capab;
int tcfa_action;
struct tcf_t tcfa_tm;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index da6fa82..9c0224d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -88,12 +88,13 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
if (p) {
if (bind)
- p->tcfa_bindcnt--;
- else if (strict && p->tcfa_bindcnt > 0)
+ atomic_dec(&p->tcfa_bindcnt);
+ else if (strict && atomic_read(&p->tcfa_bindcnt) > 0)
return -EPERM;
- p->tcfa_refcnt--;
- if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) {
+ atomic_dec(&p->tcfa_refcnt);
+ if (atomic_read(&p->tcfa_bindcnt) == 0 &&
+ atomic_read(&p->tcfa_refcnt) == 0) {
if (p->ops->cleanup)
p->ops->cleanup(p, bind);
tcf_idr_remove(p->idrinfo, p);
@@ -245,8 +246,8 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
if (index && p) {
if (bind)
- p->tcfa_bindcnt++;
- p->tcfa_refcnt++;
+ atomic_inc(&p->tcfa_bindcnt);
+ atomic_inc(&p->tcfa_refcnt);
*a = p;
return true;
}
@@ -274,9 +275,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
if (unlikely(!p))
return -ENOMEM;
- p->tcfa_refcnt = 1;
+ atomic_set(&p->tcfa_refcnt, 1);
if (bind)
- p->tcfa_bindcnt = 1;
+ atomic_set(&p->tcfa_bindcnt, 1);
if (cpustats) {
p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
@@ -727,7 +728,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
return;
list_for_each_entry(a, actions, list)
- a->tcfa_refcnt--;
+ atomic_dec(&a->tcfa_refcnt);
}
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
@@ -751,7 +752,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
}
act->order = i;
if (ovr)
- act->tcfa_refcnt++;
+ atomic_inc(&act->tcfa_refcnt);
list_add_tail(&act->list, actions);
}
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index c0c707e..4ddf281 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -141,8 +141,8 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
struct tcf_bpf *prog = to_bpf(act);
struct tc_act_bpf opt = {
.index = prog->tcf_index,
- .refcnt = prog->tcf_refcnt - ref,
- .bindcnt = prog->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&prog->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
.action = prog->tcf_action,
};
struct tcf_t tm;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 10b7a88..d2cf658 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -153,8 +153,8 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
struct tc_connmark opt = {
.index = ci->tcf_index,
- .refcnt = ci->tcf_refcnt - ref,
- .bindcnt = ci->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&ci->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
.action = ci->tcf_action,
.zone = ci->zone,
};
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 1c40caa..b9ca424 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -575,8 +575,8 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
.update_flags = p->update_flags,
.index = p->tcf_index,
.action = p->tcf_action,
- .refcnt = p->tcf_refcnt - ref,
- .bindcnt = p->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&p->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index e29a48e..b1326b7 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -169,8 +169,8 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_gact *gact = to_gact(a);
struct tc_gact opt = {
.index = gact->tcf_index,
- .refcnt = gact->tcf_refcnt - ref,
- .bindcnt = gact->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&gact->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&gact->tcf_bindcnt) - bind,
.action = gact->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 8ccd358..5cdcc87 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -551,8 +551,8 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
struct tcf_ife_info *ife = to_ife(a);
struct tc_ife opt = {
.index = ife->tcf_index,
- .refcnt = ife->tcf_refcnt - ref,
- .bindcnt = ife->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&ife->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&ife->tcf_bindcnt) - bind,
.action = ife->tcf_action,
.flags = ife->flags,
};
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index d9e399a..02c14dc 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -277,8 +277,8 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
if (unlikely(!t))
goto nla_put_failure;
- c.bindcnt = ipt->tcf_bindcnt - bind;
- c.refcnt = ipt->tcf_refcnt - ref;
+ c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
+ c.refcnt = atomic_read(&ipt->tcf_refcnt) - ref;
strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 416627c..aeeeb38 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -249,8 +249,8 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
struct tc_mirred opt = {
.index = m->tcf_index,
.action = m->tcf_action,
- .refcnt = m->tcf_refcnt - ref,
- .bindcnt = m->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&m->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&m->tcf_bindcnt) - bind,
.eaction = m->tcfm_eaction,
.ifindex = m->tcfm_ifindex,
};
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index c365d01..58fa1ae 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -256,8 +256,8 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
.index = p->tcf_index,
.action = p->tcf_action,
- .refcnt = p->tcf_refcnt - ref,
- .bindcnt = p->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&p->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 491fe5de..27b9fea 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -391,8 +391,8 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
opt->nkeys = p->tcfp_nkeys;
opt->flags = p->tcfp_flags;
opt->action = p->tcf_action;
- opt->refcnt = p->tcf_refcnt - ref;
- opt->bindcnt = p->tcf_bindcnt - bind;
+ opt->refcnt = atomic_read(&p->tcf_refcnt) - ref;
+ opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
if (p->tcfp_keys_ex) {
tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 3bb2ebf..d8a1ac6 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -272,8 +272,8 @@ static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
.action = police->tcf_action,
.mtu = police->tcfp_mtu,
.burst = PSCHED_NS2TICKS(police->tcfp_burst),
- .refcnt = police->tcf_refcnt - ref,
- .bindcnt = police->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&police->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&police->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index ec986ae..64889a4 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -179,8 +179,8 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
struct tc_sample opt = {
.index = s->tcf_index,
.action = s->tcf_action,
- .refcnt = s->tcf_refcnt - ref,
- .bindcnt = s->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&s->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&s->tcf_bindcnt) - bind,
};
struct tcf_t t;
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index e7b57e5..ec7e397 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -148,8 +148,8 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_defact *d = to_defact(a);
struct tc_defact opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 59949d6..2b05e56 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -172,8 +172,8 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_skbedit *d = to_skbedit(a);
struct tc_skbedit opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index b642ad3..ca1ddf9 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -201,8 +201,8 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_skbmod_params *p = rtnl_dereference(d->skbmod_p);
struct tc_skbmod opt = {
.index = d->tcf_index,
- .refcnt = d->tcf_refcnt - ref,
- .bindcnt = d->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&d->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
.action = d->tcf_action,
};
struct tcf_t t;
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 30c9627..158d472 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -250,8 +250,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_tunnel_key_params *params;
struct tc_tunnel_key opt = {
.index = t->tcf_index,
- .refcnt = t->tcf_refcnt - ref,
- .bindcnt = t->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&t->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&t->tcf_bindcnt) - bind,
};
struct tcf_t tm;
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 16eb067..e2d7aab 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -208,8 +208,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
struct tcf_vlan *v = to_vlan(a);
struct tc_vlan opt = {
.index = v->tcf_index,
- .refcnt = v->tcf_refcnt - ref,
- .bindcnt = v->tcf_bindcnt - bind,
+ .refcnt = atomic_read(&v->tcf_refcnt) - ref,
+ .bindcnt = atomic_read(&v->tcf_bindcnt) - bind,
.action = v->tcf_action,
.v_action = v->tcfv_action,
};
--
1.8.3.1
^ permalink raw reply related
* [patch net v3 3/4] selftests: Introduce a new script to generate tc batch file
From: Chris Mi @ 2017-10-17 1:20 UTC (permalink / raw)
To: netdev; +Cc: jhs, lucasb, xiyou.wangcong, jiri, davem
In-Reply-To: <1508203218-17998-1-git-send-email-chrism@mellanox.com>
# ./tdc_batch.py -h
usage: tdc_batch.py [-h] [-n NUMBER] [-o] [-s] [-p] device file
TC batch file generator
positional arguments:
device device name
file batch file name
optional arguments:
-h, --help show this help message and exit
-n NUMBER, --number NUMBER
how many lines in batch file
-o, --skip_sw skip_sw (offload), by default skip_hw
-s, --share_action all filters share the same action
-p, --prio all filters have different prio
Signed-off-by: Chris Mi <chrism@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
---
tools/testing/selftests/tc-testing/tdc_batch.py | 62 +++++++++++++++++++++++++
1 file changed, 62 insertions(+)
create mode 100755 tools/testing/selftests/tc-testing/tdc_batch.py
diff --git a/tools/testing/selftests/tc-testing/tdc_batch.py b/tools/testing/selftests/tc-testing/tdc_batch.py
new file mode 100755
index 0000000..707c6bf
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tdc_batch.py
@@ -0,0 +1,62 @@
+#!/usr/bin/python3
+
+"""
+tdc_batch.py - a script to generate TC batch file
+
+Copyright (C) 2017 Chris Mi <chrism@mellanox.com>
+"""
+
+import argparse
+
+parser = argparse.ArgumentParser(description='TC batch file generator')
+parser.add_argument("device", help="device name")
+parser.add_argument("file", help="batch file name")
+parser.add_argument("-n", "--number", type=int,
+ help="how many lines in batch file")
+parser.add_argument("-o", "--skip_sw",
+ help="skip_sw (offload), by default skip_hw",
+ action="store_true")
+parser.add_argument("-s", "--share_action",
+ help="all filters share the same action",
+ action="store_true")
+parser.add_argument("-p", "--prio",
+ help="all filters have different prio",
+ action="store_true")
+args = parser.parse_args()
+
+device = args.device
+file = open(args.file, 'w')
+
+number = 1
+if args.number:
+ number = args.number
+
+skip = "skip_hw"
+if args.skip_sw:
+ skip = "skip_sw"
+
+share_action = ""
+if args.share_action:
+ share_action = "index 1"
+
+prio = "prio 1"
+if args.prio:
+ prio = ""
+ if number > 0x4000:
+ number = 0x4000
+
+index = 0
+for i in range(0x100):
+ for j in range(0x100):
+ for k in range(0x100):
+ mac = ("%02x:%02x:%02x" % (i, j, k))
+ src_mac = "e4:11:00:" + mac
+ dst_mac = "e4:12:00:" + mac
+ cmd = ("filter add dev %s %s protocol ip parent ffff: flower %s "
+ "src_mac %s dst_mac %s action drop %s" %
+ (device, prio, skip, src_mac, dst_mac, share_action))
+ file.write("%s\n" % cmd)
+ index += 1
+ if index >= number:
+ file.close()
+ exit(0)
--
1.8.3.1
^ permalink raw reply related
* [patch net v3 2/4] net/sched: Use action array instead of action list as parameter
From: Chris Mi @ 2017-10-17 1:20 UTC (permalink / raw)
To: netdev; +Cc: jhs, lucasb, xiyou.wangcong, jiri, davem
In-Reply-To: <1508203218-17998-1-git-send-email-chrism@mellanox.com>
When destroying filters, actions should be destroyed first.
The pointers of each action are saved in an array. TC doesn't
use the array directly, but put all actions in a doubly linked
list and use that list as parameter.
There is no problem if each filter has its own actions. But if
some filters share the same action, when these filters are
destroyed, RCU callback fl_destroy_filter() may be called at the
same time. That means the same action's 'struct list_head list'
could be manipulated at the same time. It may point to an invalid
address so that system will panic.
This patch uses the action array directly to fix this issue.
Fixes commit in pre-git era.
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Chris Mi <chrism@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
include/net/act_api.h | 7 ++--
net/sched/act_api.c | 103 +++++++++++++++++++++++++++++++-------------------
net/sched/cls_api.c | 18 +++------
3 files changed, 75 insertions(+), 53 deletions(-)
diff --git a/include/net/act_api.h b/include/net/act_api.h
index a469ab6..081a313 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -148,16 +148,17 @@ static inline int tcf_idr_release(struct tc_action *a, bool bind)
int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
int tcf_unregister_action(struct tc_action_ops *a,
struct pernet_operations *ops);
-int tcf_action_destroy(struct list_head *actions, int bind);
+int tcf_action_destroy(struct tc_action **actions, int nr, int bind);
int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
int nr_actions, struct tcf_result *res);
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct list_head *actions);
+ struct tc_action **actions, int *nr);
struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
struct nlattr *nla, struct nlattr *est,
char *name, int ovr, int bind);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
+int tcf_action_dump(struct sk_buff *skb, struct tc_action **actions, int nr,
+ int bind, int ref);
int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9c0224d..391d560 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -513,13 +513,15 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
}
EXPORT_SYMBOL(tcf_action_exec);
-int tcf_action_destroy(struct list_head *actions, int bind)
+int tcf_action_destroy(struct tc_action **actions, int nr, int bind)
{
const struct tc_action_ops *ops;
- struct tc_action *a, *tmp;
+ struct tc_action *a;
int ret = 0;
+ int i;
- list_for_each_entry_safe(a, tmp, actions, list) {
+ for (i = 0; i < nr; i++) {
+ a = actions[i];
ops = a->ops;
ret = __tcf_idr_release(a, bind, true);
if (ret == ACT_P_DELETED)
@@ -568,14 +570,16 @@ int tcf_action_destroy(struct list_head *actions, int bind)
}
EXPORT_SYMBOL(tcf_action_dump_1);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *actions,
+int tcf_action_dump(struct sk_buff *skb, struct tc_action **actions, int nr,
int bind, int ref)
{
struct tc_action *a;
- int err = -EINVAL;
struct nlattr *nest;
+ int err = -EINVAL;
+ int i;
- list_for_each_entry(a, actions, list) {
+ for (i = 0; i < nr; i++) {
+ a = actions[i];
nest = nla_nest_start(skb, a->order);
if (nest == NULL)
goto nla_put_failure;
@@ -700,10 +704,7 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
err = tcf_action_goto_chain_init(a, tp);
if (err) {
- LIST_HEAD(actions);
-
- list_add_tail(&a->list, &actions);
- tcf_action_destroy(&actions, bind);
+ tcf_action_destroy(&a, 1, bind);
return ERR_PTR(err);
}
}
@@ -720,23 +721,27 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
return ERR_PTR(err);
}
-static void cleanup_a(struct list_head *actions, int ovr)
+static void cleanup_a(struct tc_action **actions, int nr, int ovr)
{
struct tc_action *a;
+ int i;
if (!ovr)
return;
- list_for_each_entry(a, actions, list)
+ for (i = 0; i < nr; i++) {
+ a = actions[i];
atomic_dec(&a->tcfa_refcnt);
+ }
}
int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
struct nlattr *est, char *name, int ovr, int bind,
- struct list_head *actions)
+ struct tc_action **actions, int *nr)
{
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
struct tc_action *act;
+ int n = 0;
int err;
int i;
@@ -753,17 +758,19 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
act->order = i;
if (ovr)
atomic_inc(&act->tcfa_refcnt);
- list_add_tail(&act->list, actions);
+ actions[n++] = act;
}
+ *nr = n;
/* Remove the temp refcnt which was necessary to protect against
* destroying an existing action which was being replaced
*/
- cleanup_a(actions, ovr);
+ cleanup_a(actions, n, ovr);
return 0;
err:
- tcf_action_destroy(actions, bind);
+ tcf_action_destroy(actions, n, bind);
+ *nr = 0;
return err;
}
@@ -811,9 +818,9 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *p,
return -1;
}
-static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
- u32 portid, u32 seq, u16 flags, int event, int bind,
- int ref)
+static int tca_get_fill(struct sk_buff *skb, struct tc_action **actions,
+ int nr, u32 portid, u32 seq, u16 flags, int event,
+ int bind, int ref)
{
struct tcamsg *t;
struct nlmsghdr *nlh;
@@ -832,7 +839,7 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
if (nest == NULL)
goto out_nlmsg_trim;
- if (tcf_action_dump(skb, actions, bind, ref) < 0)
+ if (tcf_action_dump(skb, actions, nr, bind, ref) < 0)
goto out_nlmsg_trim;
nla_nest_end(skb, nest);
@@ -847,14 +854,14 @@ static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
static int
tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
- struct list_head *actions, int event)
+ struct tc_action **actions, int nr, int event)
{
struct sk_buff *skb;
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb)
return -ENOBUFS;
- if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
+ if (tca_get_fill(skb, actions, nr, portid, n->nlmsg_seq, 0, event,
0, 0) <= 0) {
kfree_skb(skb);
return -EINVAL;
@@ -968,7 +975,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
}
static int
-tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+tcf_del_notify(struct net *net, struct nlmsghdr *n,
+ struct tc_action **actions, int nr,
u32 portid)
{
int ret;
@@ -978,14 +986,14 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
if (!skb)
return -ENOBUFS;
- if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
- 0, 1) <= 0) {
+ if (tca_get_fill(skb, actions, nr, portid, n->nlmsg_seq, 0,
+ RTM_DELACTION, 0, 1) <= 0) {
kfree_skb(skb);
return -EINVAL;
}
/* now do the delete */
- ret = tcf_action_destroy(actions, 0);
+ ret = tcf_action_destroy(actions, nr, 0);
if (ret < 0) {
kfree_skb(skb);
return ret;
@@ -1002,10 +1010,11 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
u32 portid, int event)
{
- int i, ret;
struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
+ struct tc_action **actions;
struct tc_action *act;
- LIST_HEAD(actions);
+ int i, ret;
+ int nr = 0;
ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, NULL);
if (ret < 0)
@@ -1018,6 +1027,11 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
return -EINVAL;
}
+ actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *),
+ GFP_KERNEL);
+ if (!actions)
+ return -ENOMEM;
+
for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
act = tcf_action_get_1(net, tb[i], n, portid);
if (IS_ERR(act)) {
@@ -1025,25 +1039,28 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
goto err;
}
act->order = i;
- list_add_tail(&act->list, &actions);
+ actions[nr++] = act;
}
if (event == RTM_GETACTION)
- ret = tcf_get_notify(net, portid, n, &actions, event);
+ ret = tcf_get_notify(net, portid, n, actions, nr, event);
else { /* delete */
- ret = tcf_del_notify(net, n, &actions, portid);
+ ret = tcf_del_notify(net, n, actions, nr, portid);
if (ret)
goto err;
+ kfree(actions);
return ret;
}
err:
if (event != RTM_GETACTION)
- tcf_action_destroy(&actions, 0);
+ tcf_action_destroy(actions, nr, 0);
+ kfree(actions);
return ret;
}
static int
-tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+tcf_add_notify(struct net *net, struct nlmsghdr *n,
+ struct tc_action **actions, int nr,
u32 portid)
{
struct sk_buff *skb;
@@ -1053,7 +1070,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
if (!skb)
return -ENOBUFS;
- if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, n->nlmsg_flags,
+ if (tca_get_fill(skb, actions, nr, portid, n->nlmsg_seq, n->nlmsg_flags,
RTM_NEWACTION, 0, 0) <= 0) {
kfree_skb(skb);
return -EINVAL;
@@ -1069,14 +1086,24 @@ static int tca_action_flush(struct net *net, struct nlattr *nla,
static int tcf_action_add(struct net *net, struct nlattr *nla,
struct nlmsghdr *n, u32 portid, int ovr)
{
+ struct tc_action **actions;
int ret = 0;
- LIST_HEAD(actions);
+ int nr;
- ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions);
+ actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *),
+ GFP_KERNEL);
+ if (!actions)
+ return -ENOMEM;
+
+ ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0,
+ actions, &nr);
if (ret)
- return ret;
+ goto out;
- return tcf_add_notify(net, n, &actions, portid);
+ ret = tcf_add_notify(net, n, actions, nr, portid);
+out:
+ kfree(actions);
+ return ret;
}
static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 0b2219a..acaa0c6 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -879,8 +879,7 @@ void tcf_exts_destroy(struct tcf_exts *exts)
#ifdef CONFIG_NET_CLS_ACT
LIST_HEAD(actions);
- tcf_exts_to_list(exts, &actions);
- tcf_action_destroy(&actions, TCA_ACT_UNBIND);
+ tcf_action_destroy(exts->actions, exts->nr_actions, TCA_ACT_UNBIND);
kfree(exts->actions);
exts->nr_actions = 0;
#endif
@@ -905,17 +904,14 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
exts->actions[0] = act;
exts->nr_actions = 1;
} else if (exts->action && tb[exts->action]) {
- LIST_HEAD(actions);
- int err, i = 0;
+ int err;
err = tcf_action_init(net, tp, tb[exts->action],
rate_tlv, NULL, ovr, TCA_ACT_BIND,
- &actions);
+ exts->actions,
+ &exts->nr_actions);
if (err)
return err;
- list_for_each_entry(act, &actions, list)
- exts->actions[i++] = act;
- exts->nr_actions = i;
}
}
#else
@@ -961,14 +957,12 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
* tc data even if iproute2 was newer - jhs
*/
if (exts->type != TCA_OLD_COMPAT) {
- LIST_HEAD(actions);
-
nest = nla_nest_start(skb, exts->action);
if (nest == NULL)
goto nla_put_failure;
- tcf_exts_to_list(exts, &actions);
- if (tcf_action_dump(skb, &actions, 0, 0) < 0)
+ if (tcf_action_dump(skb, exts->actions,
+ exts->nr_actions, 0, 0) < 0)
goto nla_put_failure;
nla_nest_end(skb, nest);
} else if (exts->police) {
--
1.8.3.1
^ permalink raw reply related
* [patch net v3 4/4] selftests: Introduce a new test case to tc testsuite
From: Chris Mi @ 2017-10-17 1:20 UTC (permalink / raw)
To: netdev; +Cc: jhs, lucasb, xiyou.wangcong, jiri, davem
In-Reply-To: <1508203218-17998-1-git-send-email-chrism@mellanox.com>
In this patchset, we fixed a tc bug. This patch adds the test case
that reproduces the bug. To run this test case, user should specify
an existing NIC device:
# sudo ./tdc.py -d enp4s0f0
This test case belongs to category "flower". If user doesn't specify
a NIC device, the test cases belong to "flower" will not be run.
In this test case, we create 1M filters and all filters share the same
action. When destroying all filters, kernel should not panic. It takes
about 18s to run it.
Signed-off-by: Chris Mi <chrism@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
---
.../tc-testing/tc-tests/filters/tests.json | 23 +++++++++++++++++++++-
tools/testing/selftests/tc-testing/tdc.py | 20 +++++++++++++++----
tools/testing/selftests/tc-testing/tdc_config.py | 2 ++
3 files changed, 40 insertions(+), 5 deletions(-)
diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index c727b96..5fa02d8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -17,5 +17,26 @@
"teardown": [
"$TC qdisc del dev $DEV1 ingress"
]
+ },
+ {
+ "id": "d052",
+ "name": "Add 1M filters with the same action",
+ "category": [
+ "filter",
+ "flower"
+ ],
+ "setup": [
+ "$TC qdisc add dev $DEV2 ingress",
+ "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000"
+ ],
+ "cmdUnderTest": "$TC -b $BATCH_FILE",
+ "expExitCode": "0",
+ "verifyCmd": "$TC actions list action gact",
+ "matchPattern": "action order 0: gact action drop.*index 1 ref 1000000 bind 1000000",
+ "matchCount": "1",
+ "teardown": [
+ "$TC qdisc del dev $DEV2 ingress",
+ "/bin/rm $BATCH_FILE"
+ ]
}
-]
\ No newline at end of file
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index cd61b78..5f11f5d 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -88,7 +88,7 @@ def prepare_env(cmdlist):
exit(1)
-def test_runner(filtered_tests):
+def test_runner(filtered_tests, args):
"""
Driver function for the unit tests.
@@ -105,6 +105,8 @@ def test_runner(filtered_tests):
for tidx in testlist:
result = True
tresult = ""
+ if "flower" in tidx["category"] and args.device == None:
+ continue
print("Test " + tidx["id"] + ": " + tidx["name"])
prepare_env(tidx["setup"])
(p, procout) = exec_cmd(tidx["cmdUnderTest"])
@@ -152,6 +154,10 @@ def ns_create():
exec_cmd(cmd, False)
cmd = 'ip -s $NS link set $DEV1 up'
exec_cmd(cmd, False)
+ cmd = 'ip link set $DEV2 netns $NS'
+ exec_cmd(cmd, False)
+ cmd = 'ip -s $NS link set $DEV2 up'
+ exec_cmd(cmd, False)
def ns_destroy():
@@ -211,7 +217,8 @@ def set_args(parser):
help='Execute the single test case with specified ID')
parser.add_argument('-i', '--id', action='store_true', dest='gen_id',
help='Generate ID numbers for new test cases')
- return parser
+ parser.add_argument('-d', '--device',
+ help='Execute the test case in flower category')
return parser
@@ -225,6 +232,8 @@ def check_default_settings(args):
if args.path != None:
NAMES['TC'] = args.path
+ if args.device != None:
+ NAMES['DEV2'] = args.device
if not os.path.isfile(NAMES['TC']):
print("The specified tc path " + NAMES['TC'] + " does not exist.")
exit(1)
@@ -381,14 +390,17 @@ def set_operation_mode(args):
if (len(alltests) == 0):
print("Cannot find a test case with ID matching " + target_id)
exit(1)
- catresults = test_runner(alltests)
+ catresults = test_runner(alltests, args)
print("All test results: " + "\n\n" + catresults)
elif (len(target_category) > 0):
+ if (target_category == "flower") and args.device == None:
+ print("Please specify a NIC device (-d) to run category flower")
+ exit(1)
if (target_category not in ucat):
print("Specified category is not present in this file.")
exit(1)
else:
- catresults = test_runner(testcases[target_category])
+ catresults = test_runner(testcases[target_category], args)
print("Category " + target_category + "\n\n" + catresults)
ns_destroy()
diff --git a/tools/testing/selftests/tc-testing/tdc_config.py b/tools/testing/selftests/tc-testing/tdc_config.py
index 0108737..b635251 100644
--- a/tools/testing/selftests/tc-testing/tdc_config.py
+++ b/tools/testing/selftests/tc-testing/tdc_config.py
@@ -12,6 +12,8 @@ NAMES = {
# Name of veth devices to be created for the namespace
'DEV0': 'v0p0',
'DEV1': 'v0p1',
+ 'DEV2': '',
+ 'BATCH_FILE': './batch.txt',
# Name of the namespace to use
'NS': 'tcut'
}
--
1.8.3.1
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox