* [net-next 1/9] net/mlx5: Change flow counters addlist type to single linked list
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 2/9] net/mlx5: Add new list to store deleted flow counters Saeed Mahameed
` (8 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Vlad Buslov, Saeed Mahameed
From: Vlad Buslov <vladbu@mellanox.com>
In order to prevent flow counters stats work function from traversing whole
flow counters tree while searching for deleted flow counters, new list to
store deleted flow counters will be added to struct mlx5_fc_stats. However,
the flow counter structure itself has no space left to store any more data
in first cache line. To free space that is needed to store additional list
node, convert current addlist double linked list (two pointers per node) to
atomic single linked list (one pointer per node).
Lockless NULL-terminated single linked list data type doesn't require any
additional external synchronization for operations used by flow counters
module (add single new element, remove all elements from list and traverse
them). Remove addlist_lock that is no longer needed.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Amir Vadai <amir@vadai.me>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 3 +-
.../ethernet/mellanox/mlx5/core/fs_counters.c | 45 +++++++++----------
include/linux/mlx5/driver.h | 4 +-
3 files changed, 23 insertions(+), 29 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 32070e5d993d..f68590291e0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -36,6 +36,7 @@
#include <linux/refcount.h>
#include <linux/mlx5/fs.h>
#include <linux/rhashtable.h>
+#include <linux/llist.h>
enum fs_node_type {
FS_TYPE_NAMESPACE,
@@ -139,7 +140,7 @@ struct mlx5_fc_cache {
struct mlx5_fc {
struct rb_node node;
- struct list_head list;
+ struct llist_node addlist;
/* last{packets,bytes} members are used when calculating the delta since
* last reading
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 58af6be13dfa..d996d6cf9e19 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -52,7 +52,9 @@
* access to counter list:
* - create (user context)
* - mlx5_fc_create() only adds to an addlist to be used by
- * mlx5_fc_stats_query_work(). addlist is protected by a spinlock.
+ * mlx5_fc_stats_query_work(). addlist is a lockless single linked list
+ * that doesn't require any additional synchronization when adding single
+ * node.
* - spawn thread to do the actual destroy
*
* - destroy (user context)
@@ -156,28 +158,29 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
return node;
}
+static void mlx5_free_fc(struct mlx5_core_dev *dev,
+ struct mlx5_fc *counter)
+{
+ mlx5_cmd_fc_free(dev, counter->id);
+ kfree(counter);
+}
+
static void mlx5_fc_stats_work(struct work_struct *work)
{
struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev,
priv.fc_stats.work.work);
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+ struct llist_node *tmplist = llist_del_all(&fc_stats->addlist);
unsigned long now = jiffies;
struct mlx5_fc *counter = NULL;
struct mlx5_fc *last = NULL;
struct rb_node *node;
- LIST_HEAD(tmplist);
-
- spin_lock(&fc_stats->addlist_lock);
- list_splice_tail_init(&fc_stats->addlist, &tmplist);
-
- if (!list_empty(&tmplist) || !RB_EMPTY_ROOT(&fc_stats->counters))
+ if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters))
queue_delayed_work(fc_stats->wq, &fc_stats->work,
fc_stats->sampling_interval);
- spin_unlock(&fc_stats->addlist_lock);
-
- list_for_each_entry(counter, &tmplist, list)
+ llist_for_each_entry(counter, tmplist, addlist)
mlx5_fc_stats_insert(&fc_stats->counters, counter);
node = rb_first(&fc_stats->counters);
@@ -229,9 +232,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
counter->cache.lastuse = jiffies;
counter->aging = true;
- spin_lock(&fc_stats->addlist_lock);
- list_add(&counter->list, &fc_stats->addlist);
- spin_unlock(&fc_stats->addlist_lock);
+ llist_add(&counter->addlist, &fc_stats->addlist);
mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
}
@@ -268,8 +269,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
fc_stats->counters = RB_ROOT;
- INIT_LIST_HEAD(&fc_stats->addlist);
- spin_lock_init(&fc_stats->addlist_lock);
+ init_llist_head(&fc_stats->addlist);
fc_stats->wq = create_singlethread_workqueue("mlx5_fc");
if (!fc_stats->wq)
@@ -284,6 +284,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+ struct llist_node *tmplist;
struct mlx5_fc *counter;
struct mlx5_fc *tmp;
struct rb_node *node;
@@ -292,13 +293,9 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
destroy_workqueue(dev->priv.fc_stats.wq);
dev->priv.fc_stats.wq = NULL;
- list_for_each_entry_safe(counter, tmp, &fc_stats->addlist, list) {
- list_del(&counter->list);
-
- mlx5_cmd_fc_free(dev, counter->id);
-
- kfree(counter);
- }
+ tmplist = llist_del_all(&fc_stats->addlist);
+ llist_for_each_entry_safe(counter, tmp, tmplist, addlist)
+ mlx5_free_fc(dev, counter);
node = rb_first(&fc_stats->counters);
while (node) {
@@ -308,9 +305,7 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
rb_erase(&counter->node, &fc_stats->counters);
- mlx5_cmd_fc_free(dev, counter->id);
-
- kfree(counter);
+ mlx5_free_fc(dev, counter);
}
}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 7a452716de4b..c00549293982 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -584,9 +584,7 @@ struct mlx5_irq_info {
struct mlx5_fc_stats {
struct rb_root counters;
- struct list_head addlist;
- /* protect addlist add/splice operations */
- spinlock_t addlist_lock;
+ struct llist_head addlist;
struct workqueue_struct *wq;
struct delayed_work work;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 2/9] net/mlx5: Add new list to store deleted flow counters
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
2018-09-06 4:33 ` [net-next 1/9] net/mlx5: Change flow counters addlist type to single linked list Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 3/9] net/mlx5: Store flow counters in a list Saeed Mahameed
` (7 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Vlad Buslov, Saeed Mahameed
From: Vlad Buslov <vladbu@mellanox.com>
In order to prevent flow counters stats work function from traversing whole
flow counters tree while searching for deleted flow counters, new list to
store deleted flow counters is added to struct mlx5_fc_stats. Lockless
NULL-terminated single linked list data type is used due to following
reasons:
- This use case only needs to add single element to list and
remove/iterate whole list. Lockless list doesn't require any additional
synchronization for these operations.
- First cache line of flow counter data structure only has space to store
single additional pointer, which precludes usage of double linked list.
Remove flow counter 'deleted' flag that is no longer needed.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Amir Vadai <amir@vadai.me>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +-
.../ethernet/mellanox/mlx5/core/fs_counters.c | 34 +++++++------------
include/linux/mlx5/driver.h | 1 +
3 files changed, 14 insertions(+), 23 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index f68590291e0c..617d6239c5f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -141,6 +141,7 @@ struct mlx5_fc_cache {
struct mlx5_fc {
struct rb_node node;
struct llist_node addlist;
+ struct llist_node dellist;
/* last{packets,bytes} members are used when calculating the delta since
* last reading
@@ -149,7 +150,6 @@ struct mlx5_fc {
u64 lastbytes;
u32 id;
- bool deleted;
bool aging;
struct mlx5_fc_cache cache ____cacheline_aligned_in_smp;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index d996d6cf9e19..f1266f215a31 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -58,7 +58,7 @@
* - spawn thread to do the actual destroy
*
* - destroy (user context)
- * - mark a counter as deleted
+ * - add a counter to lockless dellist
* - spawn thread to do the actual del
*
* - dump (user context)
@@ -171,9 +171,8 @@ static void mlx5_fc_stats_work(struct work_struct *work)
priv.fc_stats.work.work);
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
struct llist_node *tmplist = llist_del_all(&fc_stats->addlist);
+ struct mlx5_fc *counter = NULL, *last = NULL, *tmp;
unsigned long now = jiffies;
- struct mlx5_fc *counter = NULL;
- struct mlx5_fc *last = NULL;
struct rb_node *node;
if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters))
@@ -183,26 +182,17 @@ static void mlx5_fc_stats_work(struct work_struct *work)
llist_for_each_entry(counter, tmplist, addlist)
mlx5_fc_stats_insert(&fc_stats->counters, counter);
- node = rb_first(&fc_stats->counters);
- while (node) {
- counter = rb_entry(node, struct mlx5_fc, node);
-
- node = rb_next(node);
-
- if (counter->deleted) {
- rb_erase(&counter->node, &fc_stats->counters);
-
- mlx5_cmd_fc_free(dev, counter->id);
-
- kfree(counter);
- continue;
- }
+ tmplist = llist_del_all(&fc_stats->dellist);
+ llist_for_each_entry_safe(counter, tmp, tmplist, dellist) {
+ rb_erase(&counter->node, &fc_stats->counters);
- last = counter;
+ mlx5_free_fc(dev, counter);
}
- if (time_before(now, fc_stats->next_query) || !last)
+ node = rb_last(&fc_stats->counters);
+ if (time_before(now, fc_stats->next_query) || !node)
return;
+ last = rb_entry(node, struct mlx5_fc, node);
node = rb_first(&fc_stats->counters);
while (node) {
@@ -254,13 +244,12 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
return;
if (counter->aging) {
- counter->deleted = true;
+ llist_add(&counter->dellist, &fc_stats->dellist);
mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
return;
}
- mlx5_cmd_fc_free(dev, counter->id);
- kfree(counter);
+ mlx5_free_fc(dev, counter);
}
EXPORT_SYMBOL(mlx5_fc_destroy);
@@ -270,6 +259,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
fc_stats->counters = RB_ROOT;
init_llist_head(&fc_stats->addlist);
+ init_llist_head(&fc_stats->dellist);
fc_stats->wq = create_singlethread_workqueue("mlx5_fc");
if (!fc_stats->wq)
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index c00549293982..4b53ac64004b 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -585,6 +585,7 @@ struct mlx5_irq_info {
struct mlx5_fc_stats {
struct rb_root counters;
struct llist_head addlist;
+ struct llist_head dellist;
struct workqueue_struct *wq;
struct delayed_work work;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 3/9] net/mlx5: Store flow counters in a list
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
2018-09-06 4:33 ` [net-next 1/9] net/mlx5: Change flow counters addlist type to single linked list Saeed Mahameed
2018-09-06 4:33 ` [net-next 2/9] net/mlx5: Add new list to store deleted flow counters Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 4/9] net/mlx5: Add flow counters idr Saeed Mahameed
` (6 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Vlad Buslov, Saeed Mahameed
From: Vlad Buslov <vladbu@mellanox.com>
In order to improve performance of flow counter stats query loop that
traverses all configured flow counters, replace rb_tree with double-linked
list. This change improves performance of traversing flow counters by
removing the tree traversal. (profiling data showed that call to rb_next
was most top CPU consumer)
However, lookup of flow flow counter in list becomes linear, instead of
logarithmic. This problem is fixed by next patch in series, which adds idr
for fast lookup. Idr is to be used because it is not an intrusive data
structure and doesn't require adding any new members to struct mlx5_fc,
which allows its control data part to stay <= 1 cache line in size.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Amir Vadai <amir@vadai.me>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/fs_core.h | 2 +-
.../ethernet/mellanox/mlx5/core/fs_counters.c | 88 +++++++++----------
include/linux/mlx5/driver.h | 2 +-
3 files changed, 42 insertions(+), 50 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 617d6239c5f3..a06f83c0c2b6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -139,7 +139,7 @@ struct mlx5_fc_cache {
};
struct mlx5_fc {
- struct rb_node node;
+ struct list_head list;
struct llist_node addlist;
struct llist_node dellist;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index f1266f215a31..90ebfee37508 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -73,36 +73,38 @@
* elapsed, the thread will actually query the hardware.
*/
-static void mlx5_fc_stats_insert(struct rb_root *root, struct mlx5_fc *counter)
+static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev,
+ u32 id)
{
- struct rb_node **new = &root->rb_node;
- struct rb_node *parent = NULL;
-
- while (*new) {
- struct mlx5_fc *this = rb_entry(*new, struct mlx5_fc, node);
- int result = counter->id - this->id;
-
- parent = *new;
- if (result < 0)
- new = &((*new)->rb_left);
- else
- new = &((*new)->rb_right);
- }
+ struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+ struct mlx5_fc *counter;
+
+ list_for_each_entry(counter, &fc_stats->counters, list)
+ if (counter->id > id)
+ return &counter->list;
+
+ return &fc_stats->counters;
+}
+
+static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev,
+ struct mlx5_fc *counter)
+{
+ struct list_head *next = mlx5_fc_counters_lookup_next(dev, counter->id);
- /* Add new node and rebalance tree. */
- rb_link_node(&counter->node, parent, new);
- rb_insert_color(&counter->node, root);
+ list_add_tail(&counter->list, next);
}
-/* The function returns the last node that was queried so the caller
+/* The function returns the last counter that was queried so the caller
* function can continue calling it till all counters are queried.
*/
-static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
+static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
struct mlx5_fc *first,
u32 last_id)
{
+ struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+ struct mlx5_fc *counter = NULL;
struct mlx5_cmd_fc_bulk *b;
- struct rb_node *node = NULL;
+ bool more = false;
u32 afirst_id;
int num;
int err;
@@ -132,14 +134,16 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
goto out;
}
- for (node = &first->node; node; node = rb_next(node)) {
- struct mlx5_fc *counter = rb_entry(node, struct mlx5_fc, node);
+ counter = first;
+ list_for_each_entry_from(counter, &fc_stats->counters, list) {
struct mlx5_fc_cache *c = &counter->cache;
u64 packets;
u64 bytes;
- if (counter->id > last_id)
+ if (counter->id > last_id) {
+ more = true;
break;
+ }
mlx5_cmd_fc_bulk_get(dev, b,
counter->id, &packets, &bytes);
@@ -155,7 +159,7 @@ static struct rb_node *mlx5_fc_stats_query(struct mlx5_core_dev *dev,
out:
mlx5_cmd_fc_bulk_free(b);
- return node;
+ return more ? counter : NULL;
}
static void mlx5_free_fc(struct mlx5_core_dev *dev,
@@ -173,33 +177,30 @@ static void mlx5_fc_stats_work(struct work_struct *work)
struct llist_node *tmplist = llist_del_all(&fc_stats->addlist);
struct mlx5_fc *counter = NULL, *last = NULL, *tmp;
unsigned long now = jiffies;
- struct rb_node *node;
- if (tmplist || !RB_EMPTY_ROOT(&fc_stats->counters))
+ if (tmplist || !list_empty(&fc_stats->counters))
queue_delayed_work(fc_stats->wq, &fc_stats->work,
fc_stats->sampling_interval);
llist_for_each_entry(counter, tmplist, addlist)
- mlx5_fc_stats_insert(&fc_stats->counters, counter);
+ mlx5_fc_stats_insert(dev, counter);
tmplist = llist_del_all(&fc_stats->dellist);
llist_for_each_entry_safe(counter, tmp, tmplist, dellist) {
- rb_erase(&counter->node, &fc_stats->counters);
+ list_del(&counter->list);
mlx5_free_fc(dev, counter);
}
- node = rb_last(&fc_stats->counters);
- if (time_before(now, fc_stats->next_query) || !node)
+ if (time_before(now, fc_stats->next_query) ||
+ list_empty(&fc_stats->counters))
return;
- last = rb_entry(node, struct mlx5_fc, node);
-
- node = rb_first(&fc_stats->counters);
- while (node) {
- counter = rb_entry(node, struct mlx5_fc, node);
+ last = list_last_entry(&fc_stats->counters, struct mlx5_fc, list);
- node = mlx5_fc_stats_query(dev, counter, last->id);
- }
+ counter = list_first_entry(&fc_stats->counters, struct mlx5_fc,
+ list);
+ while (counter)
+ counter = mlx5_fc_stats_query(dev, counter, last->id);
fc_stats->next_query = now + fc_stats->sampling_interval;
}
@@ -257,7 +258,7 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
- fc_stats->counters = RB_ROOT;
+ INIT_LIST_HEAD(&fc_stats->counters);
init_llist_head(&fc_stats->addlist);
init_llist_head(&fc_stats->dellist);
@@ -277,7 +278,6 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
struct llist_node *tmplist;
struct mlx5_fc *counter;
struct mlx5_fc *tmp;
- struct rb_node *node;
cancel_delayed_work_sync(&dev->priv.fc_stats.work);
destroy_workqueue(dev->priv.fc_stats.wq);
@@ -287,16 +287,8 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
llist_for_each_entry_safe(counter, tmp, tmplist, addlist)
mlx5_free_fc(dev, counter);
- node = rb_first(&fc_stats->counters);
- while (node) {
- counter = rb_entry(node, struct mlx5_fc, node);
-
- node = rb_next(node);
-
- rb_erase(&counter->node, &fc_stats->counters);
-
+ list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list)
mlx5_free_fc(dev, counter);
- }
}
int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter,
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 4b53ac64004b..61bed33e6675 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -583,7 +583,7 @@ struct mlx5_irq_info {
};
struct mlx5_fc_stats {
- struct rb_root counters;
+ struct list_head counters;
struct llist_head addlist;
struct llist_head dellist;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 4/9] net/mlx5: Add flow counters idr
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (2 preceding siblings ...)
2018-09-06 4:33 ` [net-next 3/9] net/mlx5: Store flow counters in a list Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 5/9] net/mlx5e: Move mlx5e_priv_flags into en_ethtool.c Saeed Mahameed
` (5 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Vlad Buslov, Saeed Mahameed
From: Vlad Buslov <vladbu@mellanox.com>
Previous patch in series changed flow counter storage structure from
rb_tree to linked list in order to improve flow counter traversal
performance. The drawback of such solution is that flow counter lookup by
id becomes linear in complexity.
Store pointers to flow counters in idr in order to improve lookup
performance to logarithmic again. Idr is non-intrusive data structure and
doesn't require extending flow counter struct with new elements. This means
that idr can be used for lookup, while linked list from previous patch is
used for traversal, and struct mlx5_fc size is <= 2 cache lines.
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Amir Vadai <amir@vadai.me>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../ethernet/mellanox/mlx5/core/fs_counters.c | 37 +++++++++++++++++--
include/linux/mlx5/driver.h | 2 +
2 files changed, 35 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
index 90ebfee37508..09206c4acd9a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c
@@ -77,13 +77,18 @@ static struct list_head *mlx5_fc_counters_lookup_next(struct mlx5_core_dev *dev,
u32 id)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+ unsigned long next_id = (unsigned long)id + 1;
struct mlx5_fc *counter;
- list_for_each_entry(counter, &fc_stats->counters, list)
- if (counter->id > id)
- return &counter->list;
+ rcu_read_lock();
+ /* skip counters that are in idr, but not yet in counters list */
+ while ((counter = idr_get_next_ul(&fc_stats->counters_idr,
+ &next_id)) != NULL &&
+ list_empty(&counter->list))
+ next_id++;
+ rcu_read_unlock();
- return &fc_stats->counters;
+ return counter ? &counter->list : &fc_stats->counters;
}
static void mlx5_fc_stats_insert(struct mlx5_core_dev *dev,
@@ -214,15 +219,29 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
counter = kzalloc(sizeof(*counter), GFP_KERNEL);
if (!counter)
return ERR_PTR(-ENOMEM);
+ INIT_LIST_HEAD(&counter->list);
err = mlx5_cmd_fc_alloc(dev, &counter->id);
if (err)
goto err_out;
if (aging) {
+ u32 id = counter->id;
+
counter->cache.lastuse = jiffies;
counter->aging = true;
+ idr_preload(GFP_KERNEL);
+ spin_lock(&fc_stats->counters_idr_lock);
+
+ err = idr_alloc_u32(&fc_stats->counters_idr, counter, &id, id,
+ GFP_NOWAIT);
+
+ spin_unlock(&fc_stats->counters_idr_lock);
+ idr_preload_end();
+ if (err)
+ goto err_out_alloc;
+
llist_add(&counter->addlist, &fc_stats->addlist);
mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
@@ -230,6 +249,8 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging)
return counter;
+err_out_alloc:
+ mlx5_cmd_fc_free(dev, counter->id);
err_out:
kfree(counter);
@@ -245,6 +266,10 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter)
return;
if (counter->aging) {
+ spin_lock(&fc_stats->counters_idr_lock);
+ WARN_ON(!idr_remove(&fc_stats->counters_idr, counter->id));
+ spin_unlock(&fc_stats->counters_idr_lock);
+
llist_add(&counter->dellist, &fc_stats->dellist);
mod_delayed_work(fc_stats->wq, &fc_stats->work, 0);
return;
@@ -258,6 +283,8 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev)
{
struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats;
+ spin_lock_init(&fc_stats->counters_idr_lock);
+ idr_init(&fc_stats->counters_idr);
INIT_LIST_HEAD(&fc_stats->counters);
init_llist_head(&fc_stats->addlist);
init_llist_head(&fc_stats->dellist);
@@ -283,6 +310,8 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev)
destroy_workqueue(dev->priv.fc_stats.wq);
dev->priv.fc_stats.wq = NULL;
+ idr_destroy(&fc_stats->counters_idr);
+
tmplist = llist_del_all(&fc_stats->addlist);
llist_for_each_entry_safe(counter, tmp, tmplist, addlist)
mlx5_free_fc(dev, counter);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 61bed33e6675..2a0c845f6bdb 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -583,6 +583,8 @@ struct mlx5_irq_info {
};
struct mlx5_fc_stats {
+ spinlock_t counters_idr_lock; /* protects counters_idr */
+ struct idr counters_idr;
struct list_head counters;
struct llist_head addlist;
struct llist_head dellist;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 5/9] net/mlx5e: Move mlx5e_priv_flags into en_ethtool.c
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (3 preceding siblings ...)
2018-09-06 4:33 ` [net-next 4/9] net/mlx5: Add flow counters idr Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 6/9] net/mlx5e: Move Q counters allocation and drop RQ to init_rx Saeed Mahameed
` (4 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Kamal Heib, Saeed Mahameed
From: Kamal Heib <kamalheib1@gmail.com>
Move the definition of mlx5e_priv_flags into en_ethtool.c because it's
only used there.
Fixes: 4e59e2888139 ("net/mlx5e: Introduce net device priv flags infrastructure")
Signed-off-by: Kamal Heib <kamalheib1@gmail.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 7 -------
drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 7 +++++++
2 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index db2cfcd21d43..de0f7702c86a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -204,13 +204,6 @@ struct mlx5e_umr_wqe {
extern const char mlx5e_self_tests[][ETH_GSTRING_LEN];
-static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = {
- "rx_cqe_moder",
- "tx_cqe_moder",
- "rx_cqe_compress",
- "rx_striding_rq",
-};
-
enum mlx5e_priv_flag {
MLX5E_PFLAG_RX_CQE_BASED_MODER = (1 << 0),
MLX5E_PFLAG_TX_CQE_BASED_MODER = (1 << 1),
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 98dd3e0ada72..8cd338ceb237 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -135,6 +135,13 @@ void mlx5e_build_ptys2ethtool_map(void)
ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT);
}
+static const char mlx5e_priv_flags[][ETH_GSTRING_LEN] = {
+ "rx_cqe_moder",
+ "tx_cqe_moder",
+ "rx_cqe_compress",
+ "rx_striding_rq",
+};
+
int mlx5e_ethtool_get_sset_count(struct mlx5e_priv *priv, int sset)
{
int i, num_stats = 0;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 6/9] net/mlx5e: Move Q counters allocation and drop RQ to init_rx
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (4 preceding siblings ...)
2018-09-06 4:33 ` [net-next 5/9] net/mlx5e: Move mlx5e_priv_flags into en_ethtool.c Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 7/9] net/mlx5e: Replace PTP clock lock from RW lock to seq lock Saeed Mahameed
` (3 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Roi Dayan, Saeed Mahameed
From: Roi Dayan <roid@mellanox.com>
Not all profiles query the HW Q counters in update_stats() callback.
HW Q couners are limited per device and in case of representors all
their Q counters are allocated on the parent PF device.
Avoid reundant allocation of HW Q counters by moving the allocation
to init_rx profile callback.
Signed-off-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 6 +++
.../net/ethernet/mellanox/mlx5/core/en_main.c | 45 +++++++++----------
.../net/ethernet/mellanox/mlx5/core/en_rep.c | 12 ++++-
.../ethernet/mellanox/mlx5/core/ipoib/ipoib.c | 17 ++++++-
4 files changed, 55 insertions(+), 25 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index de0f7702c86a..01a967e717e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -898,6 +898,12 @@ void mlx5e_destroy_mdev_resources(struct mlx5_core_dev *mdev);
int mlx5e_refresh_tirs(struct mlx5e_priv *priv, bool enable_uc_lb);
/* common netdev helpers */
+void mlx5e_create_q_counters(struct mlx5e_priv *priv);
+void mlx5e_destroy_q_counters(struct mlx5e_priv *priv);
+int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
+ struct mlx5e_rq *drop_rq);
+void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq);
+
int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv);
int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5a7939e70190..d14c4051edd8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3049,8 +3049,8 @@ static int mlx5e_alloc_drop_cq(struct mlx5_core_dev *mdev,
return mlx5e_alloc_cq_common(mdev, param, cq);
}
-static int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
- struct mlx5e_rq *drop_rq)
+int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
+ struct mlx5e_rq *drop_rq)
{
struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5e_cq_param cq_param = {};
@@ -3094,7 +3094,7 @@ static int mlx5e_open_drop_rq(struct mlx5e_priv *priv,
return err;
}
-static void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
+void mlx5e_close_drop_rq(struct mlx5e_rq *drop_rq)
{
mlx5e_destroy_rq(drop_rq);
mlx5e_free_rq(drop_rq);
@@ -4726,7 +4726,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
mlx5e_tls_build_netdev(priv);
}
-static void mlx5e_create_q_counters(struct mlx5e_priv *priv)
+void mlx5e_create_q_counters(struct mlx5e_priv *priv)
{
struct mlx5_core_dev *mdev = priv->mdev;
int err;
@@ -4744,7 +4744,7 @@ static void mlx5e_create_q_counters(struct mlx5e_priv *priv)
}
}
-static void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
+void mlx5e_destroy_q_counters(struct mlx5e_priv *priv)
{
if (priv->q_counter)
mlx5_core_dealloc_q_counter(priv->mdev, priv->q_counter);
@@ -4783,9 +4783,17 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
struct mlx5_core_dev *mdev = priv->mdev;
int err;
+ mlx5e_create_q_counters(priv);
+
+ err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
+ if (err) {
+ mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+ goto err_destroy_q_counters;
+ }
+
err = mlx5e_create_indirect_rqt(priv);
if (err)
- return err;
+ goto err_close_drop_rq;
err = mlx5e_create_direct_rqts(priv);
if (err)
@@ -4821,6 +4829,10 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
mlx5e_destroy_direct_rqts(priv);
err_destroy_indirect_rqts:
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+err_close_drop_rq:
+ mlx5e_close_drop_rq(&priv->drop_rq);
+err_destroy_q_counters:
+ mlx5e_destroy_q_counters(priv);
return err;
}
@@ -4832,6 +4844,8 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv)
mlx5e_destroy_indirect_tirs(priv);
mlx5e_destroy_direct_rqts(priv);
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+ mlx5e_close_drop_rq(&priv->drop_rq);
+ mlx5e_destroy_q_counters(priv);
}
static int mlx5e_init_nic_tx(struct mlx5e_priv *priv)
@@ -4975,7 +4989,6 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
int mlx5e_attach_netdev(struct mlx5e_priv *priv)
{
- struct mlx5_core_dev *mdev = priv->mdev;
const struct mlx5e_profile *profile;
int err;
@@ -4986,28 +4999,16 @@ int mlx5e_attach_netdev(struct mlx5e_priv *priv)
if (err)
goto out;
- mlx5e_create_q_counters(priv);
-
- err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
- if (err) {
- mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
- goto err_destroy_q_counters;
- }
-
err = profile->init_rx(priv);
if (err)
- goto err_close_drop_rq;
+ goto err_cleanup_tx;
if (profile->enable)
profile->enable(priv);
return 0;
-err_close_drop_rq:
- mlx5e_close_drop_rq(&priv->drop_rq);
-
-err_destroy_q_counters:
- mlx5e_destroy_q_counters(priv);
+err_cleanup_tx:
profile->cleanup_tx(priv);
out:
@@ -5025,8 +5026,6 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
flush_workqueue(priv->wq);
profile->cleanup_rx(priv);
- mlx5e_close_drop_rq(&priv->drop_rq);
- mlx5e_destroy_q_counters(priv);
profile->cleanup_tx(priv);
cancel_delayed_work_sync(&priv->update_stats_work);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index c9cc9747d21d..f6eead24931f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -999,14 +999,21 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
struct mlx5e_rep_priv *rpriv = priv->ppriv;
struct mlx5_eswitch_rep *rep = rpriv->rep;
+ struct mlx5_core_dev *mdev = priv->mdev;
struct mlx5_flow_handle *flow_rule;
int err;
mlx5e_init_l2_addr(priv);
+ err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
+ if (err) {
+ mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+ return err;
+ }
+
err = mlx5e_create_direct_rqts(priv);
if (err)
- return err;
+ goto err_close_drop_rq;
err = mlx5e_create_direct_tirs(priv);
if (err)
@@ -1027,6 +1034,8 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
mlx5e_destroy_direct_tirs(priv);
err_destroy_direct_rqts:
mlx5e_destroy_direct_rqts(priv);
+err_close_drop_rq:
+ mlx5e_close_drop_rq(&priv->drop_rq);
return err;
}
@@ -1037,6 +1046,7 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
mlx5_del_flow_rules(rpriv->vport_rx_rule);
mlx5e_destroy_direct_tirs(priv);
mlx5e_destroy_direct_rqts(priv);
+ mlx5e_close_drop_rq(&priv->drop_rq);
}
static int mlx5e_init_rep_tx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index 3dd9f885ed8b..a825ed093efd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@ -349,11 +349,20 @@ static void mlx5i_destroy_flow_steering(struct mlx5e_priv *priv)
static int mlx5i_init_rx(struct mlx5e_priv *priv)
{
+ struct mlx5_core_dev *mdev = priv->mdev;
int err;
+ mlx5e_create_q_counters(priv);
+
+ err = mlx5e_open_drop_rq(priv, &priv->drop_rq);
+ if (err) {
+ mlx5_core_err(mdev, "open drop rq failed, %d\n", err);
+ goto err_destroy_q_counters;
+ }
+
err = mlx5e_create_indirect_rqt(priv);
if (err)
- return err;
+ goto err_close_drop_rq;
err = mlx5e_create_direct_rqts(priv);
if (err)
@@ -381,6 +390,10 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
mlx5e_destroy_direct_rqts(priv);
err_destroy_indirect_rqts:
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+err_close_drop_rq:
+ mlx5e_close_drop_rq(&priv->drop_rq);
+err_destroy_q_counters:
+ mlx5e_destroy_q_counters(priv);
return err;
}
@@ -391,6 +404,8 @@ static void mlx5i_cleanup_rx(struct mlx5e_priv *priv)
mlx5e_destroy_indirect_tirs(priv);
mlx5e_destroy_direct_rqts(priv);
mlx5e_destroy_rqt(priv, &priv->indir_rqt);
+ mlx5e_close_drop_rq(&priv->drop_rq);
+ mlx5e_destroy_q_counters(priv);
}
static const struct mlx5e_profile mlx5i_nic_profile = {
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 7/9] net/mlx5e: Replace PTP clock lock from RW lock to seq lock
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (5 preceding siblings ...)
2018-09-06 4:33 ` [net-next 6/9] net/mlx5e: Move Q counters allocation and drop RQ to init_rx Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 8/9] net/mlx5e: Set ECN for received packets using CQE indication Saeed Mahameed
` (2 subsequent siblings)
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Shay Agroskin, Saeed Mahameed
From: Shay Agroskin <shayag@mellanox.com>
Changed "priv.clock.lock" lock from 'rw_lock' to 'seq_lock'
in order to improve packet rate performance.
Tested on Intel(R) Xeon(R) CPU E5-2660 v2 @ 2.20GHz.
Sent 64b packets between two peers connected by ConnectX-5,
and measured packet rate for the receiver in three modes:
no time-stamping (base rate)
time-stamping using rw_lock (old lock) for critical region
time-stamping using seq_lock (new lock) for critical region
Only the receiver time stamped its packets.
The measured packet rate improvements are:
Single flow (multiple TX rings to single RX ring):
without timestamping: 4.26 (M packets)/sec
with rw-lock (old lock): 4.1 (M packets)/sec
with seq-lock (new lock): 4.16 (M packets)/sec
1.46% improvement
Multiple flows (multiple TX rings to six RX rings):
without timestamping: 22 (M packets)/sec
with rw-lock (old lock): 11.7 (M packets)/sec
with seq-lock (new lock): 21.3 (M packets)/sec
82.05% improvement
The packet rate improvement is due to the lack of atomic operations
for the 'readers' by the seq-lock.
Since there are much more 'readers' than 'writers' contention
on this lock, almost all atomic operations are saved.
this results in a dramatic decrease in overall
cache misses.
Signed-off-by: Shay Agroskin <shayag@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../ethernet/mellanox/mlx5/core/lib/clock.c | 34 +++++++++----------
.../ethernet/mellanox/mlx5/core/lib/clock.h | 8 +++--
include/linux/mlx5/driver.h | 2 +-
3 files changed, 23 insertions(+), 21 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 3f767cde4c1d..0d90b1b4a3d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -111,10 +111,10 @@ static void mlx5_pps_out(struct work_struct *work)
for (i = 0; i < clock->ptp_info.n_pins; i++) {
u64 tstart;
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
tstart = clock->pps_info.start[i];
clock->pps_info.start[i] = 0;
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
if (!tstart)
continue;
@@ -132,10 +132,10 @@ static void mlx5_timestamp_overflow(struct work_struct *work)
overflow_work);
unsigned long flags;
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
timecounter_read(&clock->tc);
mlx5_update_clock_info_page(clock->mdev);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
schedule_delayed_work(&clock->overflow_work, clock->overflow_period);
}
@@ -147,10 +147,10 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp,
u64 ns = timespec64_to_ns(ts);
unsigned long flags;
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
timecounter_init(&clock->tc, &clock->cycles, ns);
mlx5_update_clock_info_page(clock->mdev);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
return 0;
}
@@ -162,9 +162,9 @@ static int mlx5_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts)
u64 ns;
unsigned long flags;
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
ns = timecounter_read(&clock->tc);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
*ts = ns_to_timespec64(ns);
@@ -177,10 +177,10 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
ptp_info);
unsigned long flags;
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
timecounter_adjtime(&clock->tc, delta);
mlx5_update_clock_info_page(clock->mdev);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
return 0;
}
@@ -203,12 +203,12 @@ static int mlx5_ptp_adjfreq(struct ptp_clock_info *ptp, s32 delta)
adj *= delta;
diff = div_u64(adj, 1000000000ULL);
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
timecounter_read(&clock->tc);
clock->cycles.mult = neg_adj ? clock->nominal_c_mult - diff :
clock->nominal_c_mult + diff;
mlx5_update_clock_info_page(clock->mdev);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
return 0;
}
@@ -307,12 +307,12 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
ts.tv_nsec = rq->perout.start.nsec;
ns = timespec64_to_ns(&ts);
cycles_now = mlx5_read_internal_timer(mdev);
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
nsec_now = timecounter_cyc2time(&clock->tc, cycles_now);
nsec_delta = ns - nsec_now;
cycles_delta = div64_u64(nsec_delta << clock->cycles.shift,
clock->cycles.mult);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
time_stamp = cycles_now + cycles_delta;
field_select = MLX5_MTPPS_FS_PIN_MODE |
MLX5_MTPPS_FS_PATTERN |
@@ -471,14 +471,14 @@ void mlx5_pps_event(struct mlx5_core_dev *mdev,
ts.tv_sec += 1;
ts.tv_nsec = 0;
ns = timespec64_to_ns(&ts);
- write_lock_irqsave(&clock->lock, flags);
+ write_seqlock_irqsave(&clock->lock, flags);
nsec_now = timecounter_cyc2time(&clock->tc, cycles_now);
nsec_delta = ns - nsec_now;
cycles_delta = div64_u64(nsec_delta << clock->cycles.shift,
clock->cycles.mult);
clock->pps_info.start[pin] = cycles_now + cycles_delta;
schedule_work(&clock->pps_info.out_work);
- write_unlock_irqrestore(&clock->lock, flags);
+ write_sequnlock_irqrestore(&clock->lock, flags);
break;
default:
mlx5_core_err(mdev, " Unhandled event\n");
@@ -498,7 +498,7 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
return;
}
- rwlock_init(&clock->lock);
+ seqlock_init(&clock->lock);
clock->cycles.read = read_internal_timer;
clock->cycles.shift = MLX5_CYCLES_SHIFT;
clock->cycles.mult = clocksource_khz2mult(dev_freq,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index 02e2e4575e4f..263cb6e2aeee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -46,11 +46,13 @@ static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
u64 timestamp)
{
+ unsigned int seq;
u64 nsec;
- read_lock(&clock->lock);
- nsec = timecounter_cyc2time(&clock->tc, timestamp);
- read_unlock(&clock->lock);
+ do {
+ seq = read_seqbegin(&clock->lock);
+ nsec = timecounter_cyc2time(&clock->tc, timestamp);
+ } while (read_seqretry(&clock->lock, seq));
return ns_to_ktime(nsec);
}
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 2a0c845f6bdb..b7fce2c9443d 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -805,7 +805,7 @@ struct mlx5_pps {
};
struct mlx5_clock {
- rwlock_t lock;
+ seqlock_t lock;
struct cyclecounter cycles;
struct timecounter tc;
struct hwtstamp_config hwtstamp_config;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 8/9] net/mlx5e: Set ECN for received packets using CQE indication
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (6 preceding siblings ...)
2018-09-06 4:33 ` [net-next 7/9] net/mlx5e: Replace PTP clock lock from RW lock to seq lock Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 4:33 ` [net-next 9/9] net/mlx5e: don't set CHECKSUM_COMPLETE on SCTP packets Saeed Mahameed
2018-09-06 22:50 ` [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 David Miller
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Natali Shechtman, Saeed Mahameed
From: Natali Shechtman <natali@mellanox.com>
In multi-host (MH) NIC scheme, a single HW port serves multiple hosts
or sockets on the same host.
The HW uses a mechanism in the PCIe buffer which monitors
the amount of consumed PCIe buffers per host.
On a certain configuration, under congestion,
the HW emulates a switch doing ECN marking on packets using ECN
indication on the completion descriptor (CQE).
The driver needs to set the ECN bits on the packet SKB,
such that the network stack can react on that, this commit does that.
Signed-off-by: Natali Shechtman <natali@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
.../net/ethernet/mellanox/mlx5/core/en_rx.c | 35 ++++++++++++++++---
.../ethernet/mellanox/mlx5/core/en_stats.c | 3 ++
.../ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
3 files changed, 35 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 6a959e8b1f9d..2175d6972dc3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -37,6 +37,7 @@
#include <net/busy_poll.h>
#include <net/ip6_checksum.h>
#include <net/page_pool.h>
+#include <net/inet_ecn.h>
#include "en.h"
#include "en_tc.h"
#include "eswitch.h"
@@ -690,12 +691,29 @@ static inline void mlx5e_skb_set_hash(struct mlx5_cqe64 *cqe,
skb_set_hash(skb, be32_to_cpu(cqe->rss_hash_result), ht);
}
-static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth)
+static inline bool is_last_ethertype_ip(struct sk_buff *skb, int *network_depth,
+ __be16 *proto)
{
- __be16 ethertype = ((struct ethhdr *)skb->data)->h_proto;
+ *proto = ((struct ethhdr *)skb->data)->h_proto;
+ *proto = __vlan_get_protocol(skb, *proto, network_depth);
+ return (*proto == htons(ETH_P_IP) || *proto == htons(ETH_P_IPV6));
+}
+
+static inline void mlx5e_enable_ecn(struct mlx5e_rq *rq, struct sk_buff *skb)
+{
+ int network_depth = 0;
+ __be16 proto;
+ void *ip;
+ int rc;
- ethertype = __vlan_get_protocol(skb, ethertype, network_depth);
- return (ethertype == htons(ETH_P_IP) || ethertype == htons(ETH_P_IPV6));
+ if (unlikely(!is_last_ethertype_ip(skb, &network_depth, &proto)))
+ return;
+
+ ip = skb->data + network_depth;
+ rc = ((proto == htons(ETH_P_IP)) ? IP_ECN_set_ce((struct iphdr *)ip) :
+ IP6_ECN_set_ce(skb, (struct ipv6hdr *)ip));
+
+ rq->stats->ecn_mark += !!rc;
}
static __be32 mlx5e_get_fcs(struct sk_buff *skb)
@@ -745,6 +763,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
{
struct mlx5e_rq_stats *stats = rq->stats;
int network_depth = 0;
+ __be16 proto;
if (unlikely(!(netdev->features & NETIF_F_RXCSUM)))
goto csum_none;
@@ -755,7 +774,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
return;
}
- if (likely(is_last_ethertype_ip(skb, &network_depth))) {
+ if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
if (network_depth > ETH_HLEN)
@@ -790,6 +809,8 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
stats->csum_none++;
}
+#define MLX5E_CE_BIT_MASK 0x80
+
static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
u32 cqe_bcnt,
struct mlx5e_rq *rq,
@@ -834,6 +855,10 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
skb->mark = be32_to_cpu(cqe->sop_drop_qpn) & MLX5E_TC_FLOW_ID_MASK;
mlx5e_handle_csum(netdev, cqe, rq, skb, !!lro_num_seg);
+ /* checking CE bit in cqe - MSB in ml_path field */
+ if (unlikely(cqe->ml_path & MLX5E_CE_BIT_MASK))
+ mlx5e_enable_ecn(rq, skb);
+
skb->protocol = eth_type_trans(skb, netdev);
}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 6839481f7697..90c7607b1f44 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -53,6 +53,7 @@ static const struct counter_desc sw_stats_desc[] = {
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) },
+ { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_ecn_mark) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary) },
{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_none) },
@@ -144,6 +145,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
s->rx_bytes += rq_stats->bytes;
s->rx_lro_packets += rq_stats->lro_packets;
s->rx_lro_bytes += rq_stats->lro_bytes;
+ s->rx_ecn_mark += rq_stats->ecn_mark;
s->rx_removed_vlan_packets += rq_stats->removed_vlan_packets;
s->rx_csum_none += rq_stats->csum_none;
s->rx_csum_complete += rq_stats->csum_complete;
@@ -1144,6 +1146,7 @@ static const struct counter_desc rq_stats_desc[] = {
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
+ { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, ecn_mark) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index a4c035aedd46..a5fb3dc27f50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -66,6 +66,7 @@ struct mlx5e_sw_stats {
u64 tx_nop;
u64 rx_lro_packets;
u64 rx_lro_bytes;
+ u64 rx_ecn_mark;
u64 rx_removed_vlan_packets;
u64 rx_csum_unnecessary;
u64 rx_csum_none;
@@ -184,6 +185,7 @@ struct mlx5e_rq_stats {
u64 csum_none;
u64 lro_packets;
u64 lro_bytes;
+ u64 ecn_mark;
u64 removed_vlan_packets;
u64 xdp_drop;
u64 xdp_redirect;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* [net-next 9/9] net/mlx5e: don't set CHECKSUM_COMPLETE on SCTP packets
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (7 preceding siblings ...)
2018-09-06 4:33 ` [net-next 8/9] net/mlx5e: Set ECN for received packets using CQE indication Saeed Mahameed
@ 2018-09-06 4:33 ` Saeed Mahameed
2018-09-06 22:50 ` [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 David Miller
9 siblings, 0 replies; 11+ messages in thread
From: Saeed Mahameed @ 2018-09-06 4:33 UTC (permalink / raw)
To: David S. Miller; +Cc: netdev, Alaa Hleihel, Saeed Mahameed
From: Alaa Hleihel <alaa@mellanox.com>
CHECKSUM_COMPLETE is not applicable to SCTP protocol.
Setting it for SCTP packets leads to CRC32c validation failure.
Fixes: bbceefce9adf ("net/mlx5e: Support RX CHECKSUM_COMPLETE")
Signed-off-by: Alaa Hleihel <alaa@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 2175d6972dc3..424bc89184c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -755,6 +755,14 @@ static __be32 mlx5e_get_fcs(struct sk_buff *skb)
return fcs_bytes;
}
+static u8 get_ip_proto(struct sk_buff *skb, __be16 proto)
+{
+ void *ip_p = skb->data + sizeof(struct ethhdr);
+
+ return (proto == htons(ETH_P_IP)) ? ((struct iphdr *)ip_p)->protocol :
+ ((struct ipv6hdr *)ip_p)->nexthdr;
+}
+
static inline void mlx5e_handle_csum(struct net_device *netdev,
struct mlx5_cqe64 *cqe,
struct mlx5e_rq *rq,
@@ -775,6 +783,9 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
}
if (likely(is_last_ethertype_ip(skb, &network_depth, &proto))) {
+ if (unlikely(get_ip_proto(skb, proto) == IPPROTO_SCTP))
+ goto csum_unnecessary;
+
skb->ip_summed = CHECKSUM_COMPLETE;
skb->csum = csum_unfold((__force __sum16)cqe->check_sum);
if (network_depth > ETH_HLEN)
@@ -792,6 +803,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev,
return;
}
+csum_unnecessary:
if (likely((cqe->hds_ip_ext & CQE_L3_OK) &&
(cqe->hds_ip_ext & CQE_L4_OK))) {
skb->ip_summed = CHECKSUM_UNNECESSARY;
--
2.17.1
^ permalink raw reply related [flat|nested] 11+ messages in thread* Re: [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05
2018-09-06 4:33 [pull request][net-next 0/9] Mellanox, mlx5 ethernet updates 2018-09-05 Saeed Mahameed
` (8 preceding siblings ...)
2018-09-06 4:33 ` [net-next 9/9] net/mlx5e: don't set CHECKSUM_COMPLETE on SCTP packets Saeed Mahameed
@ 2018-09-06 22:50 ` David Miller
9 siblings, 0 replies; 11+ messages in thread
From: David Miller @ 2018-09-06 22:50 UTC (permalink / raw)
To: saeedm; +Cc: netdev
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 5 Sep 2018 21:33:22 -0700
> This pull request provides some updates to mlx5 ethernet driver.
>
> For more information please see tag log below.
>
> Please pull and let me know if there's any problem.
Pulled, thank you.
^ permalink raw reply [flat|nested] 11+ messages in thread