* [PATCH 09/15 net-next,v2] net: sched: remove tcf_block_cb_{register,unregister}()
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
Now replaced by the tcf_block_setup() core registration, remove this.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: no changes.
include/net/pkt_cls.h | 41 +----------------------------------
net/sched/cls_api.c | 59 ---------------------------------------------------
2 files changed, 1 insertion(+), 99 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index cc64dd45dfc2..52c11e390d9e 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -88,17 +88,7 @@ struct tcf_block_cb *tcf_block_cb_lookup(struct net *net, tc_setup_cb_t *cb,
void *cb_ident);
void tcf_block_cb_incref(struct tcf_block_cb *block_cb);
unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb);
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv,
- struct netlink_ext_ack *extack);
-int tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv, struct netlink_ext_ack *extack);
-void __tcf_block_cb_unregister(struct tcf_block *block,
- struct tcf_block_cb *block_cb);
-void tcf_block_cb_unregister(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident);
+
int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
tc_indr_block_bind_cb_t *cb, void *cb_ident);
int tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
@@ -218,35 +208,6 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
}
static inline
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv,
- struct netlink_ext_ack *extack)
-{
- return NULL;
-}
-
-static inline
-int tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv, struct netlink_ext_ack *extack)
-{
- return 0;
-}
-
-static inline
-void __tcf_block_cb_unregister(struct tcf_block *block,
- struct tcf_block_cb *block_cb)
-{
-}
-
-static inline
-void tcf_block_cb_unregister(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident)
-{
-}
-
-static inline
int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
tc_indr_block_bind_cb_t *cb, void *cb_ident)
{
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e546d56c1a39..aa7ab707c399 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -797,65 +797,6 @@ void tcf_block_cb_remove(struct tcf_block_cb *block_cb,
}
EXPORT_SYMBOL(tcf_block_cb_remove);
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv,
- struct netlink_ext_ack *extack)
-{
- struct tcf_block_cb *block_cb;
- int err;
-
- /* Replay any already present rules */
- err = tcf_block_playback_offloads(block, cb, cb_priv, true,
- tcf_block_offload_in_use(block),
- extack);
- if (err)
- return ERR_PTR(err);
-
- block_cb = tcf_block_cb_alloc(block->net, cb, cb_ident, cb_priv, NULL);
- if (IS_ERR(block_cb))
- return block_cb;
-
- list_add(&block_cb->list, &block->cb_list);
- return block_cb;
-}
-EXPORT_SYMBOL(__tcf_block_cb_register);
-
-int tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv, struct netlink_ext_ack *extack)
-{
- struct tcf_block_cb *block_cb;
-
- block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
- extack);
- return PTR_ERR_OR_ZERO(block_cb);
-}
-EXPORT_SYMBOL(tcf_block_cb_register);
-
-void __tcf_block_cb_unregister(struct tcf_block *block,
- struct tcf_block_cb *block_cb)
-{
- tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
- false, tcf_block_offload_in_use(block),
- NULL);
- list_del(&block_cb->list);
- kfree(block_cb);
-}
-EXPORT_SYMBOL(__tcf_block_cb_unregister);
-
-void tcf_block_cb_unregister(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident)
-{
- struct tcf_block_cb *block_cb;
-
- block_cb = tcf_block_cb_lookup(block->net, cb, cb_ident);
- if (!block_cb)
- return;
- __tcf_block_cb_unregister(block, block_cb);
-}
-EXPORT_SYMBOL(tcf_block_cb_unregister);
-
static int tcf_block_bind(struct tcf_block *block, struct tc_block_offload *bo)
{
struct tcf_block_cb *block_cb, *next;
--
2.11.0
^ permalink raw reply related
* [PATCH 08/15 net-next,v2] net: cls_api: do not expose tcf_block to drivers
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
Expose the block_shared flag which is what drivers.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: fix incorrect correction of block_shared in net/sched/cls_api.c
drivers/net/ethernet/mscc/ocelot_tc.c | 2 +-
drivers/net/ethernet/netronome/nfp/flower/offload.c | 2 +-
include/net/pkt_cls.h | 2 +-
net/sched/cls_api.c | 6 +++---
4 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/drivers/net/ethernet/mscc/ocelot_tc.c b/drivers/net/ethernet/mscc/ocelot_tc.c
index 5c3bf639f87c..a52c233da571 100644
--- a/drivers/net/ethernet/mscc/ocelot_tc.c
+++ b/drivers/net/ethernet/mscc/ocelot_tc.c
@@ -140,7 +140,7 @@ static int ocelot_setup_tc_block(struct ocelot_port *port,
if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) {
cb = ocelot_setup_tc_block_cb_ig;
- port->tc.block_shared = tcf_block_shared(f->block);
+ port->tc.block_shared = f->block_shared;
} else if (f->binder_type == TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS) {
cb = ocelot_setup_tc_block_cb_eg;
} else {
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index fa44dce810ed..a19f4aafc3af 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -1313,7 +1313,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
return -EOPNOTSUPP;
repr_priv = repr->app_priv;
- repr_priv->block_shared = tcf_block_shared(f->block);
+ repr_priv->block_shared = f->block_shared;
switch (f->command) {
case TC_BLOCK_BIND:
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index cb899c4552f4..cc64dd45dfc2 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -663,7 +663,7 @@ struct tc_block_offload {
enum tcf_block_binder_type binder_type;
struct list_head cb_list;
struct net *net;
- struct tcf_block *block;
+ bool block_shared;
struct netlink_ext_ack *extack;
};
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 3f036d50af65..e546d56c1a39 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1073,7 +1073,7 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
.command = command,
.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
.net = dev_net(indr_dev->dev),
- .block = indr_dev->block,
+ .block_shared = tcf_block_shared(indr_dev->block),
};
INIT_LIST_HEAD(&bo.cb_list);
@@ -1164,7 +1164,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
.command = command,
.binder_type = ei->binder_type,
.net = dev_net(dev),
- .block = block,
+ .block_shared = tcf_block_shared(block),
.extack = extack,
};
INIT_LIST_HEAD(&bo.cb_list);
@@ -1194,7 +1194,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
bo.net = dev_net(dev);
bo.command = command;
bo.binder_type = ei->binder_type;
- bo.block = block;
+ bo.block_shared = tcf_block_shared(block);
bo.extack = extack;
INIT_LIST_HEAD(&bo.cb_list);
--
2.11.0
^ permalink raw reply related
* [PATCH 06/15 net-next,v2] net: sched: add tcf_setup_block_offload()
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
Most drivers do the same thing to set up the block, add a helper
function to do this.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: no changes.
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++-------------
drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 28 ++++--------------
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 26 ++++-------------
drivers/net/ethernet/intel/i40e/i40e_main.c | 26 ++++-------------
drivers/net/ethernet/intel/iavf/iavf_main.c | 35 ++++-------------------
drivers/net/ethernet/intel/igb/igb_main.c | 23 ++-------------
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 27 ++++-------------
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 27 ++++-------------
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 26 ++++-------------
drivers/net/ethernet/netronome/nfp/abm/cls.c | 17 ++---------
drivers/net/ethernet/netronome/nfp/bpf/main.c | 29 ++++---------------
drivers/net/ethernet/qlogic/qede/qede_main.c | 23 ++-------------
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 22 ++------------
drivers/net/netdevsim/netdev.c | 26 ++++-------------
include/net/pkt_cls.h | 10 +++++++
net/sched/cls_api.c | 20 +++++++++++++
16 files changed, 91 insertions(+), 300 deletions(-)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b7b62273c955..bda732ab6538 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -9847,32 +9847,16 @@ static int bnxt_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
}
-static int bnxt_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct bnxt *bp = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
- bp, bp, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int bnxt_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct bnxt *bp = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return bnxt_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ bnxt_setup_tc_block_cb, bp, bp,
+ true);
case TC_SETUP_QDISC_MQPRIO: {
struct tc_mqprio_qopt *mqprio = type_data;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index f760921389a3..c8bb104f28d4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -161,34 +161,16 @@ static int bnxt_vf_rep_setup_tc_block_cb(enum tc_setup_type type,
}
}
-static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block,
- bnxt_vf_rep_setup_tc_block_cb,
- vf_rep, vf_rep, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block,
- bnxt_vf_rep_setup_tc_block_cb, vf_rep);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int bnxt_vf_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct bnxt_vf_rep *vf_rep = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return bnxt_vf_rep_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ bnxt_vf_rep_setup_tc_block_cb,
+ vf_rep, vf_rep, true);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index b08efc48d42f..a09b9c909be1 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3190,32 +3190,16 @@ static int cxgb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
}
-static int cxgb_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct port_info *pi = netdev2pinfo(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
- pi, dev, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int cxgb_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct port_info *pi = netdev2pinfo(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return cxgb_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ cxgb_setup_tc_block_cb, pi, dev,
+ true);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 5361c08328f7..1e703daa50fd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -8177,34 +8177,18 @@ static int i40e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
}
-static int i40e_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct i40e_netdev_priv *np = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
- np, np, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int __i40e_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data)
{
+ struct i40e_netdev_priv *np = netdev_priv(netdev);
+
switch (type) {
case TC_SETUP_QDISC_MQPRIO:
return i40e_setup_tc(netdev, type_data);
case TC_SETUP_BLOCK:
- return i40e_setup_tc_block(netdev, type_data);
+ return tcf_setup_block_offload(type_data,
+ i40e_setup_tc_block_cb, np, np,
+ true);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 881561b36083..29640e4b15f2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3114,35 +3114,6 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
/**
- * iavf_setup_tc_block - register callbacks for tc
- * @netdev: network interface device structure
- * @f: tc offload data
- *
- * This function registers block callbacks for tc
- * offloads
- **/
-static int iavf_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct iavf_adapter *adapter = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
-/**
* iavf_setup_tc - configure multiple traffic classes
* @netdev: network interface device structure
* @type: type of offload
@@ -3156,11 +3127,15 @@ static int iavf_setup_tc_block(struct net_device *dev,
static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type,
void *type_data)
{
+ struct iavf_adapter *adapter = netdev_priv(netdev);
+
switch (type) {
case TC_SETUP_QDISC_MQPRIO:
return __iavf_setup_tc(netdev, type_data);
case TC_SETUP_BLOCK:
- return iavf_setup_tc_block(netdev, type_data);
+ return tcf_setup_block_offload(type_data,
+ iavf_setup_tc_block_cb, adapter,
+ adapter, true);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f66dae72fe37..75a29adce0ce 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2783,25 +2783,6 @@ static int igb_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
}
-static int igb_setup_tc_block(struct igb_adapter *adapter,
- struct tc_block_offload *f)
-{
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int igb_offload_txtime(struct igb_adapter *adapter,
struct tc_etf_qopt_offload *qopt)
{
@@ -2834,7 +2815,9 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
case TC_SETUP_QDISC_CBS:
return igb_offload_cbs(adapter, type_data);
case TC_SETUP_BLOCK:
- return igb_setup_tc_block(adapter, type_data);
+ return tcf_setup_block_offload(type_data, igb_setup_tc_block_cb,
+ adapter, adapter, true);
+
case TC_SETUP_QDISC_ETF:
return igb_offload_txtime(adapter, type_data);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index b613e72c8ee4..7d3fe89ce807 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9607,27 +9607,6 @@ static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
}
-static int ixgbe_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct ixgbe_adapter *adapter = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
- adapter, adapter, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
- adapter);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int ixgbe_setup_tc_mqprio(struct net_device *dev,
struct tc_mqprio_qopt *mqprio)
{
@@ -9638,9 +9617,13 @@ static int ixgbe_setup_tc_mqprio(struct net_device *dev,
static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct ixgbe_adapter *adapter = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return ixgbe_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ ixgbe_setup_tc_block_cb,
+ adapter, adapter, true);
case TC_SETUP_QDISC_MQPRIO:
return ixgbe_setup_tc_mqprio(dev, type_data);
default:
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 1085040675ae..ffb501cfbc8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3345,36 +3345,19 @@ static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
return -EOPNOTSUPP;
}
}
-
-static int mlx5e_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct mlx5e_priv *priv = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
- priv, priv, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
- priv);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
#endif
static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
switch (type) {
#ifdef CONFIG_MLX5_ESWITCH
case TC_SETUP_BLOCK:
- return mlx5e_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ mlx5e_setup_tc_block_cb,
+ priv, priv, true);
#endif
case TC_SETUP_QDISC_MQPRIO:
return mlx5e_setup_tc_mqprio(dev, type_data);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 330034fcdfc5..120de25c63c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -1178,32 +1178,16 @@ static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data,
}
}
-static int mlx5e_rep_setup_tc_block(struct net_device *dev,
- struct tc_block_offload *f)
-{
- struct mlx5e_priv *priv = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
- priv, priv, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type,
void *type_data)
{
+ struct mlx5e_priv *priv = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return mlx5e_rep_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ mlx5e_rep_setup_tc_cb,
+ priv, priv, true);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/netronome/nfp/abm/cls.c b/drivers/net/ethernet/netronome/nfp/abm/cls.c
index ff3913085665..d99981ec04a3 100644
--- a/drivers/net/ethernet/netronome/nfp/abm/cls.c
+++ b/drivers/net/ethernet/netronome/nfp/abm/cls.c
@@ -265,19 +265,6 @@ static int nfp_abm_setup_tc_block_cb(enum tc_setup_type type,
int nfp_abm_setup_cls_block(struct net_device *netdev, struct nfp_repr *repr,
struct tc_block_offload *f)
{
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block,
- nfp_abm_setup_tc_block_cb,
- repr, repr, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, nfp_abm_setup_tc_block_cb,
- repr);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
+ return tcf_setup_block_offload(f, nfp_abm_setup_tc_block_cb, repr, repr,
+ true);
}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 9c136da25221..fac38899dc23 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -160,35 +160,16 @@ static int nfp_bpf_setup_tc_block_cb(enum tc_setup_type type,
return 0;
}
-static int nfp_bpf_setup_tc_block(struct net_device *netdev,
- struct tc_block_offload *f)
-{
- struct nfp_net *nn = netdev_priv(netdev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block,
- nfp_bpf_setup_tc_block_cb,
- nn, nn, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block,
- nfp_bpf_setup_tc_block_cb,
- nn);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int nfp_bpf_setup_tc(struct nfp_app *app, struct net_device *netdev,
enum tc_setup_type type, void *type_data)
{
+ struct nfp_net *nn = netdev_priv(netdev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return nfp_bpf_setup_tc_block(netdev, type_data);
+ return tcf_setup_block_offload(type_data,
+ nfp_bpf_setup_tc_block_cb,
+ nn, nn, true);
default:
return -EOPNOTSUPP;
}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index d4a29660751d..013046a30732 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -579,25 +579,6 @@ static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
}
}
-static int qede_setup_tc_block(struct qede_dev *edev,
- struct tc_block_offload *f)
-{
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block,
- qede_setup_tc_block_cb,
- edev, edev, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, qede_setup_tc_block_cb, edev);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int
qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
void *type_data)
@@ -607,7 +588,9 @@ qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
switch (type) {
case TC_SETUP_BLOCK:
- return qede_setup_tc_block(edev, type_data);
+ return tcf_setup_block_offload(type_data,
+ qede_setup_tc_block_cb,
+ edev, edev, true);
case TC_SETUP_QDISC_MQPRIO:
mqprio = type_data;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 3425d4dda03d..ffed6b51040a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3853,24 +3853,6 @@ static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
return ret;
}
-static int stmmac_setup_tc_block(struct stmmac_priv *priv,
- struct tc_block_offload *f)
-{
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
- priv, priv, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
void *type_data)
{
@@ -3878,7 +3860,9 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
switch (type) {
case TC_SETUP_BLOCK:
- return stmmac_setup_tc_block(priv, type_data);
+ return tcf_setup_block_offload(type_data,
+ stmmac_setup_tc_block_cb,
+ priv, priv, true);
case TC_SETUP_QDISC_CBS:
return stmmac_tc_setup_cbs(priv, priv, type_data);
default:
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index e5c8aa08e1cd..240727623e9b 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -78,26 +78,6 @@ nsim_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv)
return nsim_bpf_setup_tc_block_cb(type, type_data, cb_priv);
}
-static int
-nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
-{
- struct netdevsim *ns = netdev_priv(dev);
-
- if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
- return -EOPNOTSUPP;
-
- switch (f->command) {
- case TC_BLOCK_BIND:
- return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
- ns, ns, f->extack);
- case TC_BLOCK_UNBIND:
- tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
- return 0;
- default:
- return -EOPNOTSUPP;
- }
-}
-
static int nsim_set_vf_mac(struct net_device *dev, int vf, u8 *mac)
{
struct netdevsim *ns = netdev_priv(dev);
@@ -226,9 +206,13 @@ static int nsim_set_vf_link_state(struct net_device *dev, int vf, int state)
static int
nsim_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data)
{
+ struct netdevsim *ns = netdev_priv(dev);
+
switch (type) {
case TC_SETUP_BLOCK:
- return nsim_setup_tc_block(dev, type_data);
+ return tcf_setup_block_offload(type_data,
+ nsim_setup_tc_block_cb, ns, ns,
+ true);
default:
return -EOPNOTSUPP;
}
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index fd0bfb63ab70..d35711758ddb 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -111,6 +111,8 @@ void tc_indr_block_cb_unregister(struct net_device *dev,
int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp,
struct tcf_result *res, bool compat_mode);
+int tcf_setup_block_offload(struct tc_block_offload *f, tc_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv, bool ingress_only);
#else
static inline bool tcf_block_shared(struct tcf_block *block)
{
@@ -161,6 +163,14 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
{
}
+static inline int tcf_setup_block_offload(struct tc_block_offload *f,
+ tc_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv,
+ bool ingress_only)
+{
+ return -EOPNOTSUPP;
+}
+
static inline struct tcf_block_cb *
tcf_block_cb_alloc(tc_setup_cb_t *cb, void *cb_ident, void *cb_priv,
void (*release)(void *cb_priv))
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 534a545ea51e..003f24a1323f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -922,6 +922,26 @@ static int tcf_block_setup(struct tcf_block *block, struct tc_block_offload *bo)
return err;
}
+int tcf_setup_block_offload(struct tc_block_offload *f, tc_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv, bool ingress_only)
+{
+ if (ingress_only &&
+ f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+ return -EOPNOTSUPP;
+
+ switch (f->command) {
+ case TC_BLOCK_BIND:
+ return tcf_block_cb_register(f->block, cb, cb_ident, cb_priv,
+ f->extack);
+ case TC_BLOCK_UNBIND:
+ tcf_block_cb_unregister(f->block, cb, cb_ident);
+ return 0;
+ default:
+ return -EOPNOTSUPP;
+ }
+}
+EXPORT_SYMBOL(tcf_setup_block_offload);
+
static struct rhashtable indr_setup_block_ht;
struct tc_indr_block_dev {
--
2.11.0
^ permalink raw reply related
* [PATCH 05/15 net-next,v2] net: sched: add release callback to struct tcf_block_cb
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
Call it on tcf_block_cb object to release the driver private block area.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: no changes.
include/net/pkt_cls.h | 6 ++++--
net/sched/cls_api.c | 10 ++++++++--
2 files changed, 12 insertions(+), 4 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index d660cb4fad75..fd0bfb63ab70 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -73,7 +73,8 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
}
struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
- void *cb_ident, void *cb_priv);
+ void *cb_ident, void *cb_priv,
+ void (*release)(void *cb_priv));
void tcf_block_cb_free(struct tcf_block_cb *block_cb);
struct tc_block_offload;
@@ -161,7 +162,8 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
}
static inline struct tcf_block_cb *
-tcf_block_cb_alloc(tc_setup_cb_t *cb, void *cb_ident, void *cb_priv)
+tcf_block_cb_alloc(tc_setup_cb_t *cb, void *cb_ident, void *cb_priv,
+ void (*release)(void *cb_priv))
{
return ERR_PTR(-EOPNOTSUPP);
}
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index a2c1258cc8dc..534a545ea51e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -713,6 +713,7 @@ struct tcf_block_cb {
struct list_head global_list;
struct list_head list;
tc_setup_cb_t *cb;
+ void (*release)(void *cb_priv);
void *cb_ident;
void *cb_priv;
unsigned int refcnt;
@@ -750,7 +751,8 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
EXPORT_SYMBOL(tcf_block_cb_decref);
struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
- void *cb_ident, void *cb_priv)
+ void *cb_ident, void *cb_priv,
+ void (*release)(void *cb_priv))
{
struct tcf_block_cb *block_cb;
@@ -760,6 +762,7 @@ struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
block_cb->cb = cb;
block_cb->cb_ident = cb_ident;
+ block_cb->release = release;
block_cb->cb_priv = cb_priv;
return block_cb;
@@ -768,6 +771,9 @@ EXPORT_SYMBOL(tcf_block_cb_alloc);
void tcf_block_cb_free(struct tcf_block_cb *block_cb)
{
+ if (block_cb->release)
+ block_cb->release(block_cb->cb_priv);
+
kfree(block_cb);
}
EXPORT_SYMBOL(tcf_block_cb_free);
@@ -801,7 +807,7 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
if (err)
return ERR_PTR(err);
- block_cb = tcf_block_cb_alloc(cb, cb_ident, cb_priv);
+ block_cb = tcf_block_cb_alloc(cb, cb_ident, cb_priv, NULL);
if (IS_ERR(block_cb))
return block_cb;
--
2.11.0
^ permalink raw reply related
* [PATCH 04/15 net-next,v2] net: sched: add tcf_block_setup()
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
This new function allows us to handle tcf_block_cb registrations /
unregistrations from the core, in order to remove a dependency with the
tcf_block object and the .reoffload cls_api callback.
The tcf_block_cb_add() call places the tcf_block_cb object, which has
been set up by the driver, in the tc_block_offload->cb_list. This is a
temporary list that is used to convey the tcf_block_cb objects back to
the core for registration.
Note that this patch introduces a global tcf_block_cb_list, however,
this is a temporary artifact to make it easy for me to update the code
to use this new infrastructure. This global list goes away in a follow
up patch to add per-driver flow block lists.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: no changes.
include/net/pkt_cls.h | 19 ++++++++++
net/sched/cls_api.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 120 insertions(+), 1 deletion(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index b50df3b9456c..d660cb4fad75 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -75,6 +75,13 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
void *cb_ident, void *cb_priv);
void tcf_block_cb_free(struct tcf_block_cb *block_cb);
+
+struct tc_block_offload;
+void tcf_block_cb_add(struct tcf_block_cb *block_cb,
+ struct tc_block_offload *offload);
+void tcf_block_cb_remove(struct tcf_block_cb *block_cb,
+ struct tc_block_offload *offload);
+
void *tcf_block_cb_priv(struct tcf_block_cb *block_cb);
struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident);
@@ -163,6 +170,17 @@ static inline void tcf_block_cb_free(struct tcf_block_cb *block_cb)
{
}
+struct tc_block_offload;
+static inline void tcf_block_cb_add(struct tcf_block_cb *block_cb,
+ struct tc_block_offload *offload)
+{
+}
+
+static inline void tcf_block_cb_remove(struct tcf_block_cb *block_cb,
+ struct tc_block_offload *offload)
+{
+}
+
static inline
void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
{
@@ -631,6 +649,7 @@ enum tc_block_command {
struct tc_block_offload {
enum tc_block_command command;
enum tcf_block_binder_type binder_type;
+ struct list_head cb_list;
struct tcf_block *block;
struct netlink_ext_ack *extack;
};
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 93b74a15e7ac..a2c1258cc8dc 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -710,6 +710,7 @@ static bool tcf_block_offload_in_use(struct tcf_block *block)
}
struct tcf_block_cb {
+ struct list_head global_list;
struct list_head list;
tc_setup_cb_t *cb;
void *cb_ident;
@@ -723,6 +724,8 @@ void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
}
EXPORT_SYMBOL(tcf_block_cb_priv);
+static LIST_HEAD(tcf_block_cb_list);
+
struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident)
{ struct tcf_block_cb *block_cb;
@@ -769,6 +772,20 @@ void tcf_block_cb_free(struct tcf_block_cb *block_cb)
}
EXPORT_SYMBOL(tcf_block_cb_free);
+void tcf_block_cb_add(struct tcf_block_cb *block_cb,
+ struct tc_block_offload *offload)
+{
+ list_add_tail(&block_cb->global_list, &offload->cb_list);
+}
+EXPORT_SYMBOL(tcf_block_cb_add);
+
+void tcf_block_cb_remove(struct tcf_block_cb *block_cb,
+ struct tc_block_offload *offload)
+{
+ list_move(&block_cb->global_list, &offload->cb_list);
+}
+EXPORT_SYMBOL(tcf_block_cb_remove);
+
struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
void *cb_priv,
@@ -828,6 +845,77 @@ void tcf_block_cb_unregister(struct tcf_block *block,
}
EXPORT_SYMBOL(tcf_block_cb_unregister);
+static int tcf_block_bind(struct tcf_block *block, struct tc_block_offload *bo)
+{
+ struct tcf_block_cb *block_cb, *next;
+ int err, i = 0;
+
+ list_for_each_entry(block_cb, &bo->cb_list, global_list) {
+ err = tcf_block_playback_offloads(block, block_cb->cb,
+ block_cb->cb_priv, true,
+ tcf_block_offload_in_use(block),
+ bo->extack);
+ if (err)
+ goto err_unroll;
+
+ list_add(&block_cb->list, &block->cb_list);
+ i++;
+ }
+ list_splice(&bo->cb_list, &tcf_block_cb_list);
+
+ return 0;
+
+err_unroll:
+ list_for_each_entry_safe(block_cb, next, &bo->cb_list, global_list) {
+ if (i-- > 0) {
+ list_del(&block_cb->list);
+ tcf_block_playback_offloads(block, block_cb->cb,
+ block_cb->cb_priv, false,
+ tcf_block_offload_in_use(block),
+ NULL);
+ }
+ kfree(block_cb);
+ }
+
+ return err;
+}
+
+static void tcf_block_unbind(struct tcf_block *block,
+ struct tc_block_offload *bo)
+{
+ struct tcf_block_cb *block_cb, *next;
+
+ list_for_each_entry_safe(block_cb, next, &bo->cb_list, global_list) {
+ list_del(&block_cb->global_list);
+ tcf_block_playback_offloads(block, block_cb->cb,
+ block_cb->cb_priv, false,
+ tcf_block_offload_in_use(block),
+ NULL);
+ list_del(&block_cb->list);
+ tcf_block_cb_free(block_cb);
+ }
+}
+
+static int tcf_block_setup(struct tcf_block *block, struct tc_block_offload *bo)
+{
+ int err;
+
+ switch (bo->command) {
+ case TC_BLOCK_BIND:
+ err = tcf_block_bind(block, bo);
+ break;
+ case TC_BLOCK_UNBIND:
+ err = 0;
+ tcf_block_unbind(block, bo);
+ break;
+ default:
+ WARN_ON_ONCE(1);
+ err = -EOPNOTSUPP;
+ }
+
+ return err;
+}
+
static struct rhashtable indr_setup_block_ht;
struct tc_indr_block_dev {
@@ -944,12 +1032,14 @@ static void tc_indr_block_ing_cmd(struct tc_indr_block_dev *indr_dev,
.binder_type = TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS,
.block = indr_dev->block,
};
+ INIT_LIST_HEAD(&bo.cb_list);
if (!indr_dev->block)
return;
indr_block_cb->cb(indr_dev->dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
&bo);
+ tcf_block_setup(indr_dev->block, &bo);
}
int __tc_indr_block_cb_register(struct net_device *dev, void *cb_priv,
@@ -1033,6 +1123,7 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
.block = block,
.extack = extack,
};
+ INIT_LIST_HEAD(&bo.cb_list);
indr_dev = tc_indr_block_dev_lookup(dev);
if (!indr_dev)
@@ -1043,6 +1134,8 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
list_for_each_entry(indr_block_cb, &indr_dev->cb_list, list)
indr_block_cb->cb(dev, indr_block_cb->cb_priv, TC_SETUP_BLOCK,
&bo);
+
+ tcf_block_setup(block, &bo);
}
static int tcf_block_offload_cmd(struct tcf_block *block,
@@ -1052,12 +1145,19 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
struct netlink_ext_ack *extack)
{
struct tc_block_offload bo = {};
+ int err;
bo.command = command;
bo.binder_type = ei->binder_type;
bo.block = block;
bo.extack = extack;
- return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+ INIT_LIST_HEAD(&bo.cb_list);
+
+ err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+ if (err < 0)
+ return err;
+
+ return tcf_block_setup(block, &bo);
}
static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
--
2.11.0
^ permalink raw reply related
* [PATCH 01/15 net-next,v2] net: sched: move tcf_block_cb before indr_block
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
The indr_block infrastructure will depend on the tcf_block_cb object,
move this code on top to avoid forward declarations.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: no changes.
net/sched/cls_api.c | 484 ++++++++++++++++++++++++++--------------------------
1 file changed, 242 insertions(+), 242 deletions(-)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ad36bbcc583e..b2417fda26ec 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -565,6 +565,248 @@ static struct tcf_block *tc_dev_ingress_block(struct net_device *dev)
return cops->tcf_block(qdisc, TC_H_MIN_INGRESS, NULL);
}
+static struct tcf_chain *
+__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
+{
+ mutex_lock(&block->lock);
+ if (chain)
+ chain = list_is_last(&chain->list, &block->chain_list) ?
+ NULL : list_next_entry(chain, list);
+ else
+ chain = list_first_entry_or_null(&block->chain_list,
+ struct tcf_chain, list);
+
+ /* skip all action-only chains */
+ while (chain && tcf_chain_held_by_acts_only(chain))
+ chain = list_is_last(&chain->list, &block->chain_list) ?
+ NULL : list_next_entry(chain, list);
+
+ if (chain)
+ tcf_chain_hold(chain);
+ mutex_unlock(&block->lock);
+
+ return chain;
+}
+
+/* Function to be used by all clients that want to iterate over all chains on
+ * block. It properly obtains block->lock and takes reference to chain before
+ * returning it. Users of this function must be tolerant to concurrent chain
+ * insertion/deletion or ensure that no concurrent chain modification is
+ * possible. Note that all netlink dump callbacks cannot guarantee to provide
+ * consistent dump because rtnl lock is released each time skb is filled with
+ * data and sent to user-space.
+ */
+
+struct tcf_chain *
+tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
+{
+ struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain);
+
+ if (chain)
+ tcf_chain_put(chain);
+
+ return chain_next;
+}
+EXPORT_SYMBOL(tcf_get_next_chain);
+
+static struct tcf_proto *
+__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
+{
+ u32 prio = 0;
+
+ ASSERT_RTNL();
+ mutex_lock(&chain->filter_chain_lock);
+
+ if (!tp) {
+ tp = tcf_chain_dereference(chain->filter_chain, chain);
+ } else if (tcf_proto_is_deleting(tp)) {
+ /* 'deleting' flag is set and chain->filter_chain_lock was
+ * unlocked, which means next pointer could be invalid. Restart
+ * search.
+ */
+ prio = tp->prio + 1;
+ tp = tcf_chain_dereference(chain->filter_chain, chain);
+
+ for (; tp; tp = tcf_chain_dereference(tp->next, chain))
+ if (!tp->deleting && tp->prio >= prio)
+ break;
+ } else {
+ tp = tcf_chain_dereference(tp->next, chain);
+ }
+
+ if (tp)
+ tcf_proto_get(tp);
+
+ mutex_unlock(&chain->filter_chain_lock);
+
+ return tp;
+}
+
+/* Function to be used by all clients that want to iterate over all tp's on
+ * chain. Users of this function must be tolerant to concurrent tp
+ * insertion/deletion or ensure that no concurrent chain modification is
+ * possible. Note that all netlink dump callbacks cannot guarantee to provide
+ * consistent dump because rtnl lock is released each time skb is filled with
+ * data and sent to user-space.
+ */
+
+struct tcf_proto *
+tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp,
+ bool rtnl_held)
+{
+ struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp);
+
+ if (tp)
+ tcf_proto_put(tp, rtnl_held, NULL);
+
+ return tp_next;
+}
+EXPORT_SYMBOL(tcf_get_next_proto);
+
+static int
+tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
+ void *cb_priv, bool add, bool offload_in_use,
+ struct netlink_ext_ack *extack)
+{
+ struct tcf_chain *chain, *chain_prev;
+ struct tcf_proto *tp, *tp_prev;
+ int err;
+
+ for (chain = __tcf_get_next_chain(block, NULL);
+ chain;
+ chain_prev = chain,
+ chain = __tcf_get_next_chain(block, chain),
+ tcf_chain_put(chain_prev)) {
+ for (tp = __tcf_get_next_proto(chain, NULL); tp;
+ tp_prev = tp,
+ tp = __tcf_get_next_proto(chain, tp),
+ tcf_proto_put(tp_prev, true, NULL)) {
+ if (tp->ops->reoffload) {
+ err = tp->ops->reoffload(tp, add, cb, cb_priv,
+ extack);
+ if (err && add)
+ goto err_playback_remove;
+ } else if (add && offload_in_use) {
+ err = -EOPNOTSUPP;
+ NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support");
+ goto err_playback_remove;
+ }
+ }
+ }
+
+ return 0;
+
+err_playback_remove:
+ tcf_proto_put(tp, true, NULL);
+ tcf_chain_put(chain);
+ tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
+ extack);
+ return err;
+}
+
+static bool tcf_block_offload_in_use(struct tcf_block *block)
+{
+ return block->offloadcnt;
+}
+
+struct tcf_block_cb {
+ struct list_head list;
+ tc_setup_cb_t *cb;
+ void *cb_ident;
+ void *cb_priv;
+ unsigned int refcnt;
+};
+
+void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
+{
+ return block_cb->cb_priv;
+}
+EXPORT_SYMBOL(tcf_block_cb_priv);
+
+struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident)
+{ struct tcf_block_cb *block_cb;
+
+ list_for_each_entry(block_cb, &block->cb_list, list)
+ if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
+ return block_cb;
+ return NULL;
+}
+EXPORT_SYMBOL(tcf_block_cb_lookup);
+
+void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
+{
+ block_cb->refcnt++;
+}
+EXPORT_SYMBOL(tcf_block_cb_incref);
+
+unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
+{
+ return --block_cb->refcnt;
+}
+EXPORT_SYMBOL(tcf_block_cb_decref);
+
+struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv,
+ struct netlink_ext_ack *extack)
+{
+ struct tcf_block_cb *block_cb;
+ int err;
+
+ /* Replay any already present rules */
+ err = tcf_block_playback_offloads(block, cb, cb_priv, true,
+ tcf_block_offload_in_use(block),
+ extack);
+ if (err)
+ return ERR_PTR(err);
+
+ block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
+ if (!block_cb)
+ return ERR_PTR(-ENOMEM);
+ block_cb->cb = cb;
+ block_cb->cb_ident = cb_ident;
+ block_cb->cb_priv = cb_priv;
+ list_add(&block_cb->list, &block->cb_list);
+ return block_cb;
+}
+EXPORT_SYMBOL(__tcf_block_cb_register);
+
+int tcf_block_cb_register(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident,
+ void *cb_priv, struct netlink_ext_ack *extack)
+{
+ struct tcf_block_cb *block_cb;
+
+ block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
+ extack);
+ return PTR_ERR_OR_ZERO(block_cb);
+}
+EXPORT_SYMBOL(tcf_block_cb_register);
+
+void __tcf_block_cb_unregister(struct tcf_block *block,
+ struct tcf_block_cb *block_cb)
+{
+ tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
+ false, tcf_block_offload_in_use(block),
+ NULL);
+ list_del(&block_cb->list);
+ kfree(block_cb);
+}
+EXPORT_SYMBOL(__tcf_block_cb_unregister);
+
+void tcf_block_cb_unregister(struct tcf_block *block,
+ tc_setup_cb_t *cb, void *cb_ident)
+{
+ struct tcf_block_cb *block_cb;
+
+ block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
+ if (!block_cb)
+ return;
+ __tcf_block_cb_unregister(block, block_cb);
+}
+EXPORT_SYMBOL(tcf_block_cb_unregister);
+
static struct rhashtable indr_setup_block_ht;
struct tc_indr_block_dev {
@@ -782,11 +1024,6 @@ static void tc_indr_block_call(struct tcf_block *block, struct net_device *dev,
&bo);
}
-static bool tcf_block_offload_in_use(struct tcf_block *block)
-{
- return block->offloadcnt;
-}
-
static int tcf_block_offload_cmd(struct tcf_block *block,
struct net_device *dev,
struct tcf_block_ext_info *ei,
@@ -1003,104 +1240,6 @@ static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index)
return block;
}
-static struct tcf_chain *
-__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
-{
- mutex_lock(&block->lock);
- if (chain)
- chain = list_is_last(&chain->list, &block->chain_list) ?
- NULL : list_next_entry(chain, list);
- else
- chain = list_first_entry_or_null(&block->chain_list,
- struct tcf_chain, list);
-
- /* skip all action-only chains */
- while (chain && tcf_chain_held_by_acts_only(chain))
- chain = list_is_last(&chain->list, &block->chain_list) ?
- NULL : list_next_entry(chain, list);
-
- if (chain)
- tcf_chain_hold(chain);
- mutex_unlock(&block->lock);
-
- return chain;
-}
-
-/* Function to be used by all clients that want to iterate over all chains on
- * block. It properly obtains block->lock and takes reference to chain before
- * returning it. Users of this function must be tolerant to concurrent chain
- * insertion/deletion or ensure that no concurrent chain modification is
- * possible. Note that all netlink dump callbacks cannot guarantee to provide
- * consistent dump because rtnl lock is released each time skb is filled with
- * data and sent to user-space.
- */
-
-struct tcf_chain *
-tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain)
-{
- struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain);
-
- if (chain)
- tcf_chain_put(chain);
-
- return chain_next;
-}
-EXPORT_SYMBOL(tcf_get_next_chain);
-
-static struct tcf_proto *
-__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp)
-{
- u32 prio = 0;
-
- ASSERT_RTNL();
- mutex_lock(&chain->filter_chain_lock);
-
- if (!tp) {
- tp = tcf_chain_dereference(chain->filter_chain, chain);
- } else if (tcf_proto_is_deleting(tp)) {
- /* 'deleting' flag is set and chain->filter_chain_lock was
- * unlocked, which means next pointer could be invalid. Restart
- * search.
- */
- prio = tp->prio + 1;
- tp = tcf_chain_dereference(chain->filter_chain, chain);
-
- for (; tp; tp = tcf_chain_dereference(tp->next, chain))
- if (!tp->deleting && tp->prio >= prio)
- break;
- } else {
- tp = tcf_chain_dereference(tp->next, chain);
- }
-
- if (tp)
- tcf_proto_get(tp);
-
- mutex_unlock(&chain->filter_chain_lock);
-
- return tp;
-}
-
-/* Function to be used by all clients that want to iterate over all tp's on
- * chain. Users of this function must be tolerant to concurrent tp
- * insertion/deletion or ensure that no concurrent chain modification is
- * possible. Note that all netlink dump callbacks cannot guarantee to provide
- * consistent dump because rtnl lock is released each time skb is filled with
- * data and sent to user-space.
- */
-
-struct tcf_proto *
-tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp,
- bool rtnl_held)
-{
- struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp);
-
- if (tp)
- tcf_proto_put(tp, rtnl_held, NULL);
-
- return tp_next;
-}
-EXPORT_SYMBOL(tcf_get_next_proto);
-
static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held)
{
struct tcf_chain *chain;
@@ -1494,145 +1633,6 @@ void tcf_block_put(struct tcf_block *block)
EXPORT_SYMBOL(tcf_block_put);
-struct tcf_block_cb {
- struct list_head list;
- tc_setup_cb_t *cb;
- void *cb_ident;
- void *cb_priv;
- unsigned int refcnt;
-};
-
-void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
-{
- return block_cb->cb_priv;
-}
-EXPORT_SYMBOL(tcf_block_cb_priv);
-
-struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident)
-{ struct tcf_block_cb *block_cb;
-
- list_for_each_entry(block_cb, &block->cb_list, list)
- if (block_cb->cb == cb && block_cb->cb_ident == cb_ident)
- return block_cb;
- return NULL;
-}
-EXPORT_SYMBOL(tcf_block_cb_lookup);
-
-void tcf_block_cb_incref(struct tcf_block_cb *block_cb)
-{
- block_cb->refcnt++;
-}
-EXPORT_SYMBOL(tcf_block_cb_incref);
-
-unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
-{
- return --block_cb->refcnt;
-}
-EXPORT_SYMBOL(tcf_block_cb_decref);
-
-static int
-tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
- void *cb_priv, bool add, bool offload_in_use,
- struct netlink_ext_ack *extack)
-{
- struct tcf_chain *chain, *chain_prev;
- struct tcf_proto *tp, *tp_prev;
- int err;
-
- for (chain = __tcf_get_next_chain(block, NULL);
- chain;
- chain_prev = chain,
- chain = __tcf_get_next_chain(block, chain),
- tcf_chain_put(chain_prev)) {
- for (tp = __tcf_get_next_proto(chain, NULL); tp;
- tp_prev = tp,
- tp = __tcf_get_next_proto(chain, tp),
- tcf_proto_put(tp_prev, true, NULL)) {
- if (tp->ops->reoffload) {
- err = tp->ops->reoffload(tp, add, cb, cb_priv,
- extack);
- if (err && add)
- goto err_playback_remove;
- } else if (add && offload_in_use) {
- err = -EOPNOTSUPP;
- NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support");
- goto err_playback_remove;
- }
- }
- }
-
- return 0;
-
-err_playback_remove:
- tcf_proto_put(tp, true, NULL);
- tcf_chain_put(chain);
- tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
- extack);
- return err;
-}
-
-struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv,
- struct netlink_ext_ack *extack)
-{
- struct tcf_block_cb *block_cb;
- int err;
-
- /* Replay any already present rules */
- err = tcf_block_playback_offloads(block, cb, cb_priv, true,
- tcf_block_offload_in_use(block),
- extack);
- if (err)
- return ERR_PTR(err);
-
- block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
- if (!block_cb)
- return ERR_PTR(-ENOMEM);
- block_cb->cb = cb;
- block_cb->cb_ident = cb_ident;
- block_cb->cb_priv = cb_priv;
- list_add(&block_cb->list, &block->cb_list);
- return block_cb;
-}
-EXPORT_SYMBOL(__tcf_block_cb_register);
-
-int tcf_block_cb_register(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident,
- void *cb_priv, struct netlink_ext_ack *extack)
-{
- struct tcf_block_cb *block_cb;
-
- block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
- extack);
- return PTR_ERR_OR_ZERO(block_cb);
-}
-EXPORT_SYMBOL(tcf_block_cb_register);
-
-void __tcf_block_cb_unregister(struct tcf_block *block,
- struct tcf_block_cb *block_cb)
-{
- tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
- false, tcf_block_offload_in_use(block),
- NULL);
- list_del(&block_cb->list);
- kfree(block_cb);
-}
-EXPORT_SYMBOL(__tcf_block_cb_unregister);
-
-void tcf_block_cb_unregister(struct tcf_block *block,
- tc_setup_cb_t *cb, void *cb_ident)
-{
- struct tcf_block_cb *block_cb;
-
- block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
- if (!block_cb)
- return;
- __tcf_block_cb_unregister(block, block_cb);
-}
-EXPORT_SYMBOL(tcf_block_cb_unregister);
-
/* Main classifier routine: scans classifier chain attached
* to this qdisc, (optionally) tests for protocol and asks
* specific classifiers.
--
2.11.0
^ permalink raw reply related
* [PATCH 03/15 net-next,v2] net: sched: add tcf_block_cb_free()
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
Just a stub to release tcf_block_cb objects, follow up patch extends it
to have a release callback in it for the private data.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: no changes.
include/net/pkt_cls.h | 5 +++++
net/sched/cls_api.c | 6 ++++++
2 files changed, 11 insertions(+)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a756d895c7a4..b50df3b9456c 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -74,6 +74,7 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
void *cb_ident, void *cb_priv);
+void tcf_block_cb_free(struct tcf_block_cb *block_cb);
void *tcf_block_cb_priv(struct tcf_block_cb *block_cb);
struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident);
@@ -158,6 +159,10 @@ tcf_block_cb_alloc(tc_setup_cb_t *cb, void *cb_ident, void *cb_priv)
return ERR_PTR(-EOPNOTSUPP);
}
+static inline void tcf_block_cb_free(struct tcf_block_cb *block_cb)
+{
+}
+
static inline
void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
{
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 6cd76e3df2be..93b74a15e7ac 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -763,6 +763,12 @@ struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
}
EXPORT_SYMBOL(tcf_block_cb_alloc);
+void tcf_block_cb_free(struct tcf_block_cb *block_cb)
+{
+ kfree(block_cb);
+}
+EXPORT_SYMBOL(tcf_block_cb_free);
+
struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
void *cb_priv,
--
2.11.0
^ permalink raw reply related
* [PATCH 02/15 net-next,v2] net: sched: add tcf_block_cb_alloc()
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
In-Reply-To: <20190704234843.6601-1-pablo@netfilter.org>
Add a new helper function to allocate tcf_block_cb objects.
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
v2: return -EOPNOTSUPP if sched/cls_api is disabled, per Marcelo Ricardo Leitner .
include/net/pkt_cls.h | 8 ++++++++
net/sched/cls_api.c | 27 +++++++++++++++++++++------
2 files changed, 29 insertions(+), 6 deletions(-)
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 1a7596ba0dbe..a756d895c7a4 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -72,6 +72,8 @@ static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
return block->q;
}
+struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv);
void *tcf_block_cb_priv(struct tcf_block_cb *block_cb);
struct tcf_block_cb *tcf_block_cb_lookup(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident);
@@ -150,6 +152,12 @@ void tc_setup_cb_block_unregister(struct tcf_block *block, tc_setup_cb_t *cb,
{
}
+static inline struct tcf_block_cb *
+tcf_block_cb_alloc(tc_setup_cb_t *cb, void *cb_ident, void *cb_priv)
+{
+ return ERR_PTR(-EOPNOTSUPP);
+}
+
static inline
void *tcf_block_cb_priv(struct tcf_block_cb *block_cb)
{
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b2417fda26ec..6cd76e3df2be 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -746,6 +746,23 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
}
EXPORT_SYMBOL(tcf_block_cb_decref);
+struct tcf_block_cb *tcf_block_cb_alloc(tc_setup_cb_t *cb,
+ void *cb_ident, void *cb_priv)
+{
+ struct tcf_block_cb *block_cb;
+
+ block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
+ if (!block_cb)
+ return ERR_PTR(-ENOMEM);
+
+ block_cb->cb = cb;
+ block_cb->cb_ident = cb_ident;
+ block_cb->cb_priv = cb_priv;
+
+ return block_cb;
+}
+EXPORT_SYMBOL(tcf_block_cb_alloc);
+
struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
tc_setup_cb_t *cb, void *cb_ident,
void *cb_priv,
@@ -761,12 +778,10 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
if (err)
return ERR_PTR(err);
- block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
- if (!block_cb)
- return ERR_PTR(-ENOMEM);
- block_cb->cb = cb;
- block_cb->cb_ident = cb_ident;
- block_cb->cb_priv = cb_priv;
+ block_cb = tcf_block_cb_alloc(cb, cb_ident, cb_priv);
+ if (IS_ERR(block_cb))
+ return block_cb;
+
list_add(&block_cb->list, &block->cb_list);
return block_cb;
}
--
2.11.0
^ permalink raw reply related
* [PATCH 00/15 net-next,v2] netfilter: add hardware offload infrastructure
From: Pablo Neira Ayuso @ 2019-07-04 23:48 UTC (permalink / raw)
To: netdev
Cc: netfilter-devel, davem, thomas.lendacky, f.fainelli, ariel.elior,
michael.chan, madalin.bucur, yisen.zhuang, salil.mehta,
jeffrey.t.kirsher, tariqt, saeedm, jiri, idosch, jakub.kicinski,
peppe.cavallaro, grygorii.strashko, andrew, vivien.didelot,
alexandre.torgue, joabreu, linux-net-drivers, ogerlitz,
Manish.Chopra, marcelo.leitner, mkubecek, venkatkumar.duvvuru,
maxime.chevallier, cphealy
Hi,
This patchset adds support for Netfilter hardware offloads.
This patchset reuses the existing block infrastructure, the
netdev_ops->ndo_setup_tc() interface, TC_SETUP_CLSFLOWER classifier and
the flow rule API.
Patch #1 moves tcf_block_cb code before the indirect block
infrastructure to avoid forward declarations in the next
patches. This is just a preparation patch.
Patch #2 adds tcf_block_cb_alloc() to allocate flow block callbacks.
Patch #3 adds tcf_block_cb_free() to release flow block callbacks.
Patch #4 adds the tcf_block_setup() infrastructure, which allows drivers
to set up flow block callbacks. This infrastructure transports
these objects via list (through the tc_block_offload object)
back to the core for registration.
CLS_API DRIVER
TC_SETUP_BLOCK ----------> setup flow_block_cb object &
it adds object to flow_block_offload->cb_list
|
CLS_API <-----------------------'
registers list with flow blocks
flow_block_cb & travels back to
calls ->reoffload the core for registration
This patch introduces a global flow block list for all drivers
which is a temporary artifact to make incremental changes, it
is removed in patch #12!
Patch #5 extends tcf_block_cb_alloc() to allow drivers to set a release
callback that is invoked from tcf_block_cb_free() to release
private driver block information.
Patch #6 adds tcf_setup_block_offload(), this helper function is used by
most drivers to setup the block, including common bind and
unbind operations.
Patch #7 adapts drivers to use the infrastructure introduced in Patch #4.
Patch #8 stops exposing the tc block structure to drivers, by caching
the only information that drivers need, ie. block is shared
flag.
Patch #9 removes the tcf_block_cb_register() / _unregister()
infrastructure, since it is now unused after Patch #7.
Patch #10 moves the flow_block API to the net/core/flow_offload.c file.
This renames from tcf_block_cb to flow_block_cb as well as the
functions to allocate, release, lookup and setup flow block
callbacks.
Patch #11 makes sure that only one flow block callback per device is
possible by now. This means only one of the ethtool / tc /
netfilter subsystems can use hardware offloads, until drivers
are updated to remove this limitation.
Patch #12 introduces a flow block list per-driver, this is a step
towards offloading multiple subsystems. This needs more work
on the driver side to support for this.
Patch #13 renames TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND.
Patch #14 renames TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*.
Patch #15 introduces basic netfilter hardware offload infrastructure
for the ingress chain. This includes 5-tuple exact matching
and accept / drop rule actions. Only basechains are supported
at this stage, no .reoffload callback is implemented either.
Default policy to "accept" is only supported for now.
An example ruleset looks like this:
table netdev filter {
flags offload;
chain ingress {
type filter hook ingress device eth0 priority 0;
ip daddr 192.168.0.10 tcp dport 22 drop
}
}
The 'offload' flag specifies that this table (and anything that is enclosed
into this table) belongs to hardware.
Please, apply, thanks.
Pablo Neira Ayuso (15):
net: sched: move tcf_block_cb before indr_block
net: sched: add tcf_block_cb_alloc()
net: sched: add tcf_block_cb_free()
net: sched: add tcf_block_setup()
net: sched: add release callback to struct tcf_block_cb
net: sched: add tcf_setup_block_offload()
net: use tcf_block_setup() infrastructure
net: cls_api: do not expose tcf_block to drivers
net: sched: remove tcf_block_cb_{register,unregister}()
net: flow_offload: add flow_block_cb API
net: flow_offload: don't allow subsystem to reuse blocks
net: flow_offload: make flow block callback list per-driver
net: flow_offload: rename TC_BLOCK_{UN}BIND to FLOW_BLOCK_{UN}BIND
net: flow_offload: rename TCF_BLOCK_BINDER_TYPE_* to FLOW_BLOCK_BINDER_TYPE_*
netfilter: nf_tables: add hardware offload support
drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 +-
drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c | 29 +-
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 26 +-
drivers/net/ethernet/intel/i40e/i40e_main.c | 26 +-
drivers/net/ethernet/intel/iavf/iavf_main.c | 35 +-
drivers/net/ethernet/intel/igb/igb_main.c | 26 +-
drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 29 +-
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 29 +-
drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 70 ++-
drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 97 ++--
drivers/net/ethernet/mscc/ocelot_ace.h | 4 +-
drivers/net/ethernet/mscc/ocelot_flower.c | 47 +-
drivers/net/ethernet/mscc/ocelot_tc.c | 42 +-
drivers/net/ethernet/netronome/nfp/abm/cls.c | 22 +-
drivers/net/ethernet/netronome/nfp/abm/main.h | 2 +-
drivers/net/ethernet/netronome/nfp/bpf/main.c | 30 +-
.../net/ethernet/netronome/nfp/flower/offload.c | 76 +--
drivers/net/ethernet/qlogic/qede/qede_main.c | 23 +-
drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 23 +-
drivers/net/netdevsim/netdev.c | 29 +-
include/net/flow_offload.h | 56 +++
include/net/netfilter/nf_tables.h | 13 +
include/net/netfilter/nf_tables_offload.h | 76 +++
include/net/pkt_cls.h | 90 +---
include/uapi/linux/netfilter/nf_tables.h | 2 +
net/core/flow_offload.c | 123 +++++
net/dsa/slave.c | 28 +-
net/netfilter/Makefile | 2 +-
net/netfilter/nf_tables_api.c | 22 +-
net/netfilter/nf_tables_offload.c | 261 ++++++++++
net/netfilter/nft_cmp.c | 53 +++
net/netfilter/nft_immediate.c | 31 ++
net/netfilter/nft_meta.c | 27 ++
net/netfilter/nft_payload.c | 187 ++++++++
net/sched/cls_api.c | 526 ++++++++++-----------
net/sched/sch_ingress.c | 6 +-
36 files changed, 1411 insertions(+), 783 deletions(-)
create mode 100644 include/net/netfilter/nf_tables_offload.h
create mode 100644 net/netfilter/nf_tables_offload.c
--
2.11.0
^ permalink raw reply
* Re: [PATCH net-next 4/6] arm64: dts: fsl: ls1028a: Add Felix switch port DT node
From: Vladimir Oltean @ 2019-07-04 23:32 UTC (permalink / raw)
To: Alexandre Belloni
Cc: Andrew Lunn, Allan W. Nielsen, Claudiu Manoil, David S . Miller,
devicetree@vger.kernel.org, netdev@vger.kernel.org,
Alexandru Marginean, linux-kernel@vger.kernel.org,
UNGLinuxDriver@microchip.com, Allan Nielsen, Rob Herring,
linux-arm-kernel@lists.infradead.org
In-Reply-To: <20190624182614.GC5690@piout.net>
On Tue, 25 Jun 2019 at 00:23, Alexandre Belloni
<alexandre.belloni@bootlin.com> wrote:
>
> On 24/06/2019 18:24:31+0200, Andrew Lunn wrote:
> > On Mon, Jun 24, 2019 at 05:23:45PM +0200, Allan W. Nielsen wrote:
> > > Hi Andrew,
> > >
> > > The 06/24/2019 16:26, Andrew Lunn wrote:
> > > > > > Yeah, there are 2 ethernet controller ports (managed by the enetc driver)
> > > > > > connected inside the SoC via SGMII links to 2 of the switch ports, one of
> > > > > > these switch ports can be configured as CPU port (with follow-up patches).
> > > > > >
> > > > > > This configuration may look prettier on DSA, but the main restriction here
> > > > > > is that the entire functionality is provided by the ocelot driver which is a
> > > > > > switchdev driver. I don't think it would be a good idea to copy-paste code
> > > > > > from ocelot to a separate dsa driver.
> > > > > >
> > > > >
> > > > > We should probably make the ocelot driver a DSA driver then...
> > > > An important part of DSA is being able to direct frames out specific
> > > > ports when they ingress via the CPU port. Does the silicon support
> > > > this? At the moment, i think it is using polled IO.
> > >
> > > That is supported, it requires a bit of initial configuration of the Chip, but
> > > nothing big (I believe this configuration is part of Claudiu's change-set).
> > >
> > > But how do you envision this done?
> > >
> > > - Let the existing SwitchDev driver and the DSA driver use a set of common
> > > functions.
> > > - Convert the existing Ocelot driver from SwitchDev to DSA
> > > - Fork (copy) the existing driver of Ocelot, and modify it as needed for the
> > > Felix driver
> > >
> > > My guess is the first one, but I would like to understand what you have in mind.
> >
> > I don't know the various architectures the switch is used in. But it
> > does seem like a core library, and then a switchdev wrapper for Ocelot
> > and a DSA wrapper for Felix would make sense.
>
> Ocelot could also be used in a DSA setting where one port can be
> connected to an external MAC and be used to inject/extract frames
> to/from any other ports. In that case, the IFH would serve as the DSA
> tag.
>
>
> --
> Alexandre Belloni, Bootlin
> Embedded Linux and Kernel engineering
> https://bootlin.com
Hi everyone,
Thank you for the nice discussion.
I've been talking off-list to Claudiu and Alexandru about switchdev vs
DSA for the Felix/Ocelot switches.
My initial reaction was the same as Andrew's - there's a CPU-facing
Ethernet MAC with some vendor-defined injection and extraction
headers? Sounds like DSA.
But then we discussed about what DSA for Felix/Ocelot would look like.
Here are some points to consider:
- DSA is typically used for discrete switches, switchdev is typically
used for embedded ones. As far as I understand from Allan's message,
Ocelot is really an entire switching SoC that's running Linux inside
(on the MIPS CPU) with a switchdev driver. There is no (mainline?)
driver that would control the Ocelot SoC from a higher-level Linux
system. The latter would (maybe) fit DSA more.
- The D in DSA is for cascaded switches. Apart from the absence of
such a "Ocelot SoC" driver (which maybe can be written, I don't know),
I think the switching core itself has some fundamental limitations
that make a DSA implementation questionable:
1. The switch has a single port which can apply these vendor tags.
Also the injection header is different than the extraction header. See
more at #4.
2. The switch will tag all frames that go upstream on this port
towards the CPU, no matter what source port they came from. It can't
be told "hey, don't add a tag for frames coming from this
downstream-facing port, because it's a DSA port and not front-panel,
so there's another switch underneath you who already added a tag to
the frame". So frames that arrive at the CPU through an array of N
cascaded Felix/Ocelot switches will need to be peeled off, one by one,
by N vendor tags.
3. The extraction header does not contain a field for the "switch
id", only for the "source port". This means that if you want to figure
out the switch id, you really *need* to make a topology out of those
stacked vendor tags and figure out which switch it was by counting the
tags. It also means that you can only have Felix/Ocelot in a linear
topology.
4. The switch cannot parse its own vendor tags. This is a big one,
because it means that for an autonomously forwarded frame which
transits two cascaded switches but doesn't reach the CPU, there is no
one in the path who's going to consume the vendor tag. So the frame
will exit the other front-panel port with extra bytes in it.
Ok, let's say that all of the above limitations have one thing in
common - the vendor tags aren't really thought out with DSA-like
setups in mind. In theory it's possible to not use the native tags and
instead implement a dsa_8021q tagger for it. But then, RX timestamps
for PTP are also transmitted to the CPU through this vendor header,
and losing PTP is a big no-no.
So my conclusion is that DSA for Felix/Ocelot doesn't make a lot of
sense if the whole purpose is to hide the CPU-facing netdev.
In a cascaded setup, these switches could only sit at the top of tree,
and ironically, they'd be better modeled as a switchdev DSA master
port than part of the DSA tree itself. Put these switches anywhere
else in the tree and they're just troublemakers.
As for the LS1028A, I think that connecting this embedded switch via
two Ethernet MACs is just poorly thought out design, but that doesn't
mean DSA is going to help it in any way other than perhaps cosmetic.
Regards,
-Vladimir
^ permalink raw reply
* [PATCH v7 net-next 2/5] net: ethernet: ti: davinci_cpdma: add dma mapped submit
From: Ivan Khoronzhuk @ 2019-07-04 23:14 UTC (permalink / raw)
To: grygorii.strashko, hawk, davem
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190704231406.27083-1-ivan.khoronzhuk@linaro.org>
In case if dma mapped packet needs to be sent, like with XDP
page pool, the "mapped" submit can be used. This patch adds dma
mapped submit based on regular one.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/davinci_cpdma.c | 89 ++++++++++++++++++++++---
drivers/net/ethernet/ti/davinci_cpdma.h | 4 ++
2 files changed, 83 insertions(+), 10 deletions(-)
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 5cf1758d425b..8da46394c0e7 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -139,6 +139,7 @@ struct submit_info {
int directed;
void *token;
void *data;
+ int flags;
int len;
};
@@ -184,6 +185,8 @@ static struct cpdma_control_info controls[] = {
(directed << CPDMA_TO_PORT_SHIFT)); \
} while (0)
+#define CPDMA_DMA_EXT_MAP BIT(16)
+
static void cpdma_desc_pool_destroy(struct cpdma_ctlr *ctlr)
{
struct cpdma_desc_pool *pool = ctlr->pool;
@@ -1015,6 +1018,7 @@ static int cpdma_chan_submit_si(struct submit_info *si)
struct cpdma_chan *chan = si->chan;
struct cpdma_ctlr *ctlr = chan->ctlr;
int len = si->len;
+ int swlen = len;
struct cpdma_desc __iomem *desc;
dma_addr_t buffer;
u32 mode;
@@ -1036,16 +1040,22 @@ static int cpdma_chan_submit_si(struct submit_info *si)
chan->stats.runt_transmit_buff++;
}
- buffer = dma_map_single(ctlr->dev, si->data, len, chan->dir);
- ret = dma_mapping_error(ctlr->dev, buffer);
- if (ret) {
- cpdma_desc_free(ctlr->pool, desc, 1);
- return -EINVAL;
- }
-
mode = CPDMA_DESC_OWNER | CPDMA_DESC_SOP | CPDMA_DESC_EOP;
cpdma_desc_to_port(chan, mode, si->directed);
+ if (si->flags & CPDMA_DMA_EXT_MAP) {
+ buffer = (u32)si->data;
+ dma_sync_single_for_device(ctlr->dev, buffer, len, chan->dir);
+ swlen |= CPDMA_DMA_EXT_MAP;
+ } else {
+ buffer = dma_map_single(ctlr->dev, si->data, len, chan->dir);
+ ret = dma_mapping_error(ctlr->dev, buffer);
+ if (ret) {
+ cpdma_desc_free(ctlr->pool, desc, 1);
+ return -EINVAL;
+ }
+ }
+
/* Relaxed IO accessors can be used here as there is read barrier
* at the end of write sequence.
*/
@@ -1055,7 +1065,7 @@ static int cpdma_chan_submit_si(struct submit_info *si)
writel_relaxed(mode | len, &desc->hw_mode);
writel_relaxed((uintptr_t)si->token, &desc->sw_token);
writel_relaxed(buffer, &desc->sw_buffer);
- writel_relaxed(len, &desc->sw_len);
+ writel_relaxed(swlen, &desc->sw_len);
desc_read(desc, sw_len);
__cpdma_chan_submit(chan, desc);
@@ -1079,6 +1089,32 @@ int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
si.data = data;
si.len = len;
si.directed = directed;
+ si.flags = 0;
+
+ spin_lock_irqsave(&chan->lock, flags);
+ if (chan->state == CPDMA_STATE_TEARDOWN) {
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return -EINVAL;
+ }
+
+ ret = cpdma_chan_submit_si(&si);
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return ret;
+}
+
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed)
+{
+ struct submit_info si;
+ unsigned long flags;
+ int ret;
+
+ si.chan = chan;
+ si.token = token;
+ si.data = (void *)(u32)data;
+ si.len = len;
+ si.directed = directed;
+ si.flags = CPDMA_DMA_EXT_MAP;
spin_lock_irqsave(&chan->lock, flags);
if (chan->state == CPDMA_STATE_TEARDOWN) {
@@ -1103,6 +1139,32 @@ int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
si.data = data;
si.len = len;
si.directed = directed;
+ si.flags = 0;
+
+ spin_lock_irqsave(&chan->lock, flags);
+ if (chan->state != CPDMA_STATE_ACTIVE) {
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return -EINVAL;
+ }
+
+ ret = cpdma_chan_submit_si(&si);
+ spin_unlock_irqrestore(&chan->lock, flags);
+ return ret;
+}
+
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed)
+{
+ struct submit_info si;
+ unsigned long flags;
+ int ret;
+
+ si.chan = chan;
+ si.token = token;
+ si.data = (void *)(u32)data;
+ si.len = len;
+ si.directed = directed;
+ si.flags = CPDMA_DMA_EXT_MAP;
spin_lock_irqsave(&chan->lock, flags);
if (chan->state != CPDMA_STATE_ACTIVE) {
@@ -1140,10 +1202,17 @@ static void __cpdma_chan_free(struct cpdma_chan *chan,
uintptr_t token;
token = desc_read(desc, sw_token);
- buff_dma = desc_read(desc, sw_buffer);
origlen = desc_read(desc, sw_len);
- dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+ buff_dma = desc_read(desc, sw_buffer);
+ if (origlen & CPDMA_DMA_EXT_MAP) {
+ origlen &= ~CPDMA_DMA_EXT_MAP;
+ dma_sync_single_for_cpu(ctlr->dev, buff_dma, origlen,
+ chan->dir);
+ } else {
+ dma_unmap_single(ctlr->dev, buff_dma, origlen, chan->dir);
+ }
+
cpdma_desc_free(pool, desc, 1);
(*chan->handler)((void *)token, outlen, status);
}
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 9343c8c73c1b..0271a20c2e09 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -77,8 +77,12 @@ int cpdma_chan_stop(struct cpdma_chan *chan);
int cpdma_chan_get_stats(struct cpdma_chan *chan,
struct cpdma_chan_stats *stats);
+int cpdma_chan_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed);
int cpdma_chan_submit(struct cpdma_chan *chan, void *token, void *data,
int len, int directed);
+int cpdma_chan_idle_submit_mapped(struct cpdma_chan *chan, void *token,
+ dma_addr_t data, int len, int directed);
int cpdma_chan_idle_submit(struct cpdma_chan *chan, void *token, void *data,
int len, int directed);
int cpdma_chan_process(struct cpdma_chan *chan, int quota);
--
2.17.1
^ permalink raw reply related
* [PATCH v7 net-next 5/5] net: ethernet: ti: cpsw: add XDP support
From: Ivan Khoronzhuk @ 2019-07-04 23:14 UTC (permalink / raw)
To: grygorii.strashko, hawk, davem
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190704231406.27083-1-ivan.khoronzhuk@linaro.org>
Add XDP support based on rx page_pool allocator, one frame per page.
Page pool allocator is used with assumption that only one rx_handler
is running simultaneously. DMA map/unmap is reused from page pool
despite there is no need to map whole page.
Due to specific of cpsw, the same TX/RX handler can be used by 2
network devices, so special fields in buffer are added to identify
an interface the frame is destined to. Thus XDP works for both
interfaces, that allows to test xdp redirect between two interfaces
easily. Aslo, each rx queue have own page pools, but common for both
netdevs.
XDP prog is common for all channels till appropriate changes are added
in XDP infrastructure. Also, once page_pool recycling becomes part of
skb netstack some simplifications can be added, like removing
page_pool_release_page() before skb receive.
In order to keep rx_dev while redirect, that can be somehow used in
future, do flush in rx_handler, that allows to keep rx dev the same
while reidrect. It allows to conform with tracing rx_dev pointed
by Jesper.
Also, there is probability, that XDP generic code can be extended to
support multi ndev drivers like this one, using same rx queue for
several ndevs, based on switchdev for instance or else. In this case,
driver can be modified like exposed here:
https://lkml.org/lkml/2019/7/3/243
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 502 ++++++++++++++++++++++---
drivers/net/ethernet/ti/cpsw_ethtool.c | 37 +-
drivers/net/ethernet/ti/cpsw_priv.h | 7 +
4 files changed, 488 insertions(+), 59 deletions(-)
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index a800d3417411..834afca3a019 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -50,6 +50,7 @@ config TI_CPSW
depends on ARCH_DAVINCI || ARCH_OMAP2PLUS || COMPILE_TEST
select TI_DAVINCI_MDIO
select MFD_SYSCON
+ select PAGE_POOL
select REGMAP
---help---
This driver supports TI's CPSW Ethernet Switch.
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 32b7b3b74a6b..c17bb9381116 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -31,6 +31,10 @@
#include <linux/if_vlan.h>
#include <linux/kmemleak.h>
#include <linux/sys_soc.h>
+#include <net/page_pool.h>
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
+#include <linux/filter.h>
#include <linux/pinctrl/consumer.h>
#include <net/pkt_cls.h>
@@ -60,6 +64,10 @@ static int descs_pool_size = CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT;
module_param(descs_pool_size, int, 0444);
MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
+/* The buf includes headroom compatible with both skb and xdpf */
+#define CPSW_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define CPSW_HEADROOM ALIGN(CPSW_HEADROOM_NA, sizeof(long))
+
#define for_each_slave(priv, func, arg...) \
do { \
struct cpsw_slave *slave; \
@@ -74,6 +82,11 @@ MODULE_PARM_DESC(descs_pool_size, "Number of CPDMA CPPI descriptors in pool");
(func)(slave++, ##arg); \
} while (0)
+#define CPSW_XMETA_OFFSET ALIGN(sizeof(struct xdp_frame), sizeof(long))
+
+#define CPSW_XDP_CONSUMED 1
+#define CPSW_XDP_PASS 0
+
static int cpsw_ndo_vlan_rx_add_vid(struct net_device *ndev,
__be16 proto, u16 vid);
@@ -337,24 +350,58 @@ void cpsw_intr_disable(struct cpsw_common *cpsw)
return;
}
+static int cpsw_is_xdpf_handle(void *handle)
+{
+ return (unsigned long)handle & BIT(0);
+}
+
+static void *cpsw_xdpf_to_handle(struct xdp_frame *xdpf)
+{
+ return (void *)((unsigned long)xdpf | BIT(0));
+}
+
+static struct xdp_frame *cpsw_handle_to_xdpf(void *handle)
+{
+ return (struct xdp_frame *)((unsigned long)handle & ~BIT(0));
+}
+
+struct __aligned(sizeof(long)) cpsw_meta_xdp {
+ struct net_device *ndev;
+ int ch;
+};
+
void cpsw_tx_handler(void *token, int len, int status)
{
+ struct cpsw_meta_xdp *xmeta;
+ struct xdp_frame *xdpf;
+ struct net_device *ndev;
struct netdev_queue *txq;
- struct sk_buff *skb = token;
- struct net_device *ndev = skb->dev;
- struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+ struct sk_buff *skb;
+ int ch;
+
+ if (cpsw_is_xdpf_handle(token)) {
+ xdpf = cpsw_handle_to_xdpf(token);
+ xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+ ndev = xmeta->ndev;
+ ch = xmeta->ch;
+ xdp_return_frame(xdpf);
+ } else {
+ skb = token;
+ ndev = skb->dev;
+ ch = skb_get_queue_mapping(skb);
+ cpts_tx_timestamp(ndev_to_cpsw(ndev)->cpts, skb);
+ dev_kfree_skb_any(skb);
+ }
/* Check whether the queue is stopped due to stalled tx dma, if the
* queue is stopped then start the queue as we have free desc for tx
*/
- txq = netdev_get_tx_queue(ndev, skb_get_queue_mapping(skb));
+ txq = netdev_get_tx_queue(ndev, ch);
if (unlikely(netif_tx_queue_stopped(txq)))
netif_tx_wake_queue(txq);
- cpts_tx_timestamp(cpsw->cpts, skb);
ndev->stats.tx_packets++;
ndev->stats.tx_bytes += len;
- dev_kfree_skb_any(skb);
}
static void cpsw_rx_vlan_encap(struct sk_buff *skb)
@@ -400,24 +447,252 @@ static void cpsw_rx_vlan_encap(struct sk_buff *skb)
}
}
+static int cpsw_xdp_tx_frame(struct cpsw_priv *priv, struct xdp_frame *xdpf,
+ struct page *page)
+{
+ struct cpsw_common *cpsw = priv->cpsw;
+ struct cpsw_meta_xdp *xmeta;
+ struct cpdma_chan *txch;
+ dma_addr_t dma;
+ int ret, port;
+
+ xmeta = (void *)xdpf + CPSW_XMETA_OFFSET;
+ xmeta->ndev = priv->ndev;
+ xmeta->ch = 0;
+ txch = cpsw->txv[0].ch;
+
+ port = priv->emac_port + cpsw->data.dual_emac;
+ if (page) {
+ dma = page_pool_get_dma_addr(page);
+ dma += xdpf->data - (void *)xdpf;
+ ret = cpdma_chan_submit_mapped(txch, cpsw_xdpf_to_handle(xdpf),
+ dma, xdpf->len, port);
+ } else {
+ if (sizeof(*xmeta) > xdpf->headroom) {
+ xdp_return_frame_rx_napi(xdpf);
+ return -EINVAL;
+ }
+
+ ret = cpdma_chan_submit(txch, cpsw_xdpf_to_handle(xdpf),
+ xdpf->data, xdpf->len, port);
+ }
+
+ if (ret) {
+ priv->ndev->stats.tx_dropped++;
+ xdp_return_frame_rx_napi(xdpf);
+ }
+
+ return ret;
+}
+
+static int cpsw_run_xdp(struct cpsw_priv *priv, int ch, struct xdp_buff *xdp,
+ struct page *page)
+{
+ struct cpsw_common *cpsw = priv->cpsw;
+ struct net_device *ndev = priv->ndev;
+ int ret = CPSW_XDP_CONSUMED;
+ struct xdp_frame *xdpf;
+ struct bpf_prog *prog;
+ u32 act;
+
+ rcu_read_lock();
+
+ prog = READ_ONCE(priv->xdp_prog);
+ if (!prog) {
+ ret = CPSW_XDP_PASS;
+ goto out;
+ }
+
+ act = bpf_prog_run_xdp(prog, xdp);
+ switch (act) {
+ case XDP_PASS:
+ ret = CPSW_XDP_PASS;
+ break;
+ case XDP_TX:
+ xdpf = convert_to_xdp_frame(xdp);
+ if (unlikely(!xdpf))
+ goto drop;
+
+ cpsw_xdp_tx_frame(priv, xdpf, page);
+ break;
+ case XDP_REDIRECT:
+ if (xdp_do_redirect(ndev, xdp, prog))
+ goto drop;
+
+ /* Have to flush here, per packet, instead of doing it in bulk
+ * at the end of the napi handler. The RX devices on this
+ * particular hardware is sharing a common queue, so the
+ * incoming device might change per packet.
+ */
+ xdp_do_flush_map();
+ break;
+ default:
+ bpf_warn_invalid_xdp_action(act);
+ /* fall through */
+ case XDP_ABORTED:
+ trace_xdp_exception(ndev, prog, act);
+ /* fall through -- handle aborts by dropping packet */
+ case XDP_DROP:
+ goto drop;
+ }
+out:
+ rcu_read_unlock();
+ return ret;
+drop:
+ rcu_read_unlock();
+ page_pool_recycle_direct(cpsw->page_pool[ch], page);
+ return ret;
+}
+
+static unsigned int cpsw_rxbuf_total_len(unsigned int len)
+{
+ len += CPSW_HEADROOM;
+ len += SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+
+ return SKB_DATA_ALIGN(len);
+}
+
+static struct page_pool *cpsw_create_page_pool(struct cpsw_common *cpsw,
+ int size)
+{
+ struct page_pool_params pp_params;
+ struct page_pool *pool;
+
+ pp_params.order = 0;
+ pp_params.flags = PP_FLAG_DMA_MAP;
+ pp_params.pool_size = size;
+ pp_params.nid = NUMA_NO_NODE;
+ pp_params.dma_dir = DMA_BIDIRECTIONAL;
+ pp_params.dev = cpsw->dev;
+
+ pool = page_pool_create(&pp_params);
+ if (IS_ERR(pool))
+ dev_err(cpsw->dev, "cannot create rx page pool\n");
+
+ return pool;
+}
+
+static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+ struct cpsw_common *cpsw = priv->cpsw;
+ struct xdp_rxq_info *rxq;
+ struct page_pool *pool;
+ int ret;
+
+ pool = cpsw->page_pool[ch];
+ rxq = &priv->xdp_rxq[ch];
+
+ ret = xdp_rxq_info_reg(rxq, priv->ndev, ch);
+ if (ret)
+ return ret;
+
+ ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+ if (ret)
+ xdp_rxq_info_unreg(rxq);
+
+ return ret;
+}
+
+static void cpsw_ndev_destroy_xdp_rxq(struct cpsw_priv *priv, int ch)
+{
+ struct xdp_rxq_info *rxq = &priv->xdp_rxq[ch];
+
+ if (!xdp_rxq_info_is_reg(rxq))
+ return;
+
+ xdp_rxq_info_unreg(rxq);
+}
+
+static int cpsw_create_rx_pool(struct cpsw_common *cpsw, int ch)
+{
+ struct page_pool *pool;
+ int ret = 0, pool_size;
+
+ pool_size = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
+ pool = cpsw_create_page_pool(cpsw, pool_size);
+ if (IS_ERR(pool))
+ ret = PTR_ERR(pool);
+ else
+ cpsw->page_pool[ch] = pool;
+
+ return ret;
+}
+
+void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw)
+{
+ struct net_device *ndev;
+ int i, ch;
+
+ for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+ for (i = 0; i < cpsw->data.slaves; i++) {
+ ndev = cpsw->slaves[i].ndev;
+ if (!ndev)
+ continue;
+
+ cpsw_ndev_destroy_xdp_rxq(netdev_priv(ndev), ch);
+ }
+
+ page_pool_destroy(cpsw->page_pool[ch]);
+ cpsw->page_pool[ch] = NULL;
+ }
+}
+
+int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw)
+{
+ struct net_device *ndev;
+ int i, ch, ret;
+
+ for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+ ret = cpsw_create_rx_pool(cpsw, ch);
+ if (ret)
+ goto err_cleanup;
+
+ /* using same page pool is allowed as no running rx handlers
+ * simultaneously for both ndevs
+ */
+ for (i = 0; i < cpsw->data.slaves; i++) {
+ ndev = cpsw->slaves[i].ndev;
+ if (!ndev)
+ continue;
+
+ ret = cpsw_ndev_create_xdp_rxq(netdev_priv(ndev), ch);
+ if (ret)
+ goto err_cleanup;
+ }
+ }
+
+ return 0;
+
+err_cleanup:
+ cpsw_destroy_xdp_rxqs(cpsw);
+
+ return ret;
+}
+
static void cpsw_rx_handler(void *token, int len, int status)
{
- struct cpdma_chan *ch;
- struct sk_buff *skb = token;
- struct sk_buff *new_skb;
- struct net_device *ndev = skb->dev;
- int ret = 0, port;
- struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
+ struct page *new_page, *page = token;
+ void *pa = page_address(page);
+ struct cpsw_meta_xdp *xmeta = pa + CPSW_XMETA_OFFSET;
+ struct cpsw_common *cpsw = ndev_to_cpsw(xmeta->ndev);
+ int pkt_size = cpsw->rx_packet_max;
+ int ret = 0, port, ch = xmeta->ch;
+ int headroom = CPSW_HEADROOM;
+ struct net_device *ndev = xmeta->ndev;
struct cpsw_priv *priv;
+ struct page_pool *pool;
+ struct sk_buff *skb;
+ struct xdp_buff xdp;
+ dma_addr_t dma;
- if (cpsw->data.dual_emac) {
+ if (cpsw->data.dual_emac && status >= 0) {
port = CPDMA_RX_SOURCE_PORT(status);
- if (port) {
+ if (port)
ndev = cpsw->slaves[--port].ndev;
- skb->dev = ndev;
- }
}
+ priv = netdev_priv(ndev);
+ pool = cpsw->page_pool[ch];
if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
/* In dual emac mode check for all interfaces */
if (cpsw->data.dual_emac && cpsw->usage_count &&
@@ -426,43 +701,87 @@ static void cpsw_rx_handler(void *token, int len, int status)
* is already down and the other interface is up
* and running, instead of freeing which results
* in reducing of the number of rx descriptor in
- * DMA engine, requeue skb back to cpdma.
+ * DMA engine, requeue page back to cpdma.
*/
- new_skb = skb;
+ new_page = page;
goto requeue;
}
- /* the interface is going down, skbs are purged */
- dev_kfree_skb_any(skb);
+ /* the interface is going down, pages are purged */
+ page_pool_recycle_direct(pool, page);
return;
}
- new_skb = netdev_alloc_skb_ip_align(ndev, cpsw->rx_packet_max);
- if (new_skb) {
- skb_copy_queue_mapping(new_skb, skb);
- skb_put(skb, len);
- if (status & CPDMA_RX_VLAN_ENCAP)
- cpsw_rx_vlan_encap(skb);
- priv = netdev_priv(ndev);
- if (priv->rx_ts_enabled)
- cpts_rx_timestamp(cpsw->cpts, skb);
- skb->protocol = eth_type_trans(skb, ndev);
- netif_receive_skb(skb);
- ndev->stats.rx_bytes += len;
- ndev->stats.rx_packets++;
- kmemleak_not_leak(new_skb);
- } else {
+ new_page = page_pool_dev_alloc_pages(pool);
+ if (unlikely(!new_page)) {
+ new_page = page;
ndev->stats.rx_dropped++;
- new_skb = skb;
+ goto requeue;
+ }
+
+ if (priv->xdp_prog) {
+ if (status & CPDMA_RX_VLAN_ENCAP) {
+ xdp.data = pa + CPSW_HEADROOM +
+ CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+ xdp.data_end = xdp.data + len -
+ CPSW_RX_VLAN_ENCAP_HDR_SIZE;
+ } else {
+ xdp.data = pa + CPSW_HEADROOM;
+ xdp.data_end = xdp.data + len;
+ }
+
+ xdp_set_data_meta_invalid(&xdp);
+
+ xdp.data_hard_start = pa;
+ xdp.rxq = &priv->xdp_rxq[ch];
+
+ ret = cpsw_run_xdp(priv, ch, &xdp, page);
+ if (ret != CPSW_XDP_PASS)
+ goto requeue;
+
+ /* XDP prog might have changed packet data and boundaries */
+ len = xdp.data_end - xdp.data;
+ headroom = xdp.data - xdp.data_hard_start;
+
+ /* XDP prog can modify vlan tag, so can't use encap header */
+ status &= ~CPDMA_RX_VLAN_ENCAP;
}
+ /* pass skb to netstack if no XDP prog or returned XDP_PASS */
+ skb = build_skb(pa, cpsw_rxbuf_total_len(pkt_size));
+ if (!skb) {
+ ndev->stats.rx_dropped++;
+ page_pool_recycle_direct(pool, page);
+ goto requeue;
+ }
+
+ skb_reserve(skb, headroom);
+ skb_put(skb, len);
+ skb->dev = ndev;
+ if (status & CPDMA_RX_VLAN_ENCAP)
+ cpsw_rx_vlan_encap(skb);
+ if (priv->rx_ts_enabled)
+ cpts_rx_timestamp(cpsw->cpts, skb);
+ skb->protocol = eth_type_trans(skb, ndev);
+
+ /* unmap page as no netstack skb page recycling */
+ page_pool_release_page(pool, page);
+ netif_receive_skb(skb);
+
+ ndev->stats.rx_bytes += len;
+ ndev->stats.rx_packets++;
+
requeue:
- ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch;
- ret = cpdma_chan_submit(ch, new_skb, new_skb->data,
- skb_tailroom(new_skb), 0);
+ xmeta = page_address(new_page) + CPSW_XMETA_OFFSET;
+ xmeta->ndev = ndev;
+ xmeta->ch = ch;
+
+ dma = page_pool_get_dma_addr(new_page) + CPSW_HEADROOM;
+ ret = cpdma_chan_submit_mapped(cpsw->rxv[ch].ch, new_page, dma,
+ pkt_size, 0);
if (ret < 0) {
WARN_ON(ret == -ENOMEM);
- dev_kfree_skb_any(new_skb);
+ page_pool_recycle_direct(pool, new_page);
}
}
@@ -1032,33 +1351,39 @@ static void cpsw_init_host_port(struct cpsw_priv *priv)
int cpsw_fill_rx_channels(struct cpsw_priv *priv)
{
struct cpsw_common *cpsw = priv->cpsw;
- struct sk_buff *skb;
+ struct cpsw_meta_xdp *xmeta;
+ struct page_pool *pool;
+ struct page *page;
int ch_buf_num;
int ch, i, ret;
+ dma_addr_t dma;
for (ch = 0; ch < cpsw->rx_ch_num; ch++) {
+ pool = cpsw->page_pool[ch];
ch_buf_num = cpdma_chan_get_rx_buf_num(cpsw->rxv[ch].ch);
for (i = 0; i < ch_buf_num; i++) {
- skb = __netdev_alloc_skb_ip_align(priv->ndev,
- cpsw->rx_packet_max,
- GFP_KERNEL);
- if (!skb) {
- cpsw_err(priv, ifup, "cannot allocate skb\n");
+ page = page_pool_dev_alloc_pages(pool);
+ if (!page) {
+ cpsw_err(priv, ifup, "allocate rx page err\n");
return -ENOMEM;
}
- skb_set_queue_mapping(skb, ch);
- ret = cpdma_chan_idle_submit(cpsw->rxv[ch].ch, skb,
- skb->data,
- skb_tailroom(skb), 0);
+ xmeta = page_address(page) + CPSW_XMETA_OFFSET;
+ xmeta->ndev = priv->ndev;
+ xmeta->ch = ch;
+
+ dma = page_pool_get_dma_addr(page) + CPSW_HEADROOM;
+ ret = cpdma_chan_idle_submit_mapped(cpsw->rxv[ch].ch,
+ page, dma,
+ cpsw->rx_packet_max,
+ 0);
if (ret < 0) {
cpsw_err(priv, ifup,
- "cannot submit skb to channel %d rx, error %d\n",
+ "cannot submit page to channel %d rx, error %d\n",
ch, ret);
- kfree_skb(skb);
+ page_pool_recycle_direct(pool, page);
return ret;
}
- kmemleak_not_leak(skb);
}
cpsw_info(priv, ifup, "ch %d rx, submitted %d descriptors\n",
@@ -1394,6 +1719,13 @@ static int cpsw_ndo_open(struct net_device *ndev)
enable_irq(cpsw->irqs_table[0]);
}
+ /* create rxqs for both infs in dual mac as they use same pool
+ * and must be destroyed together when no users.
+ */
+ ret = cpsw_create_xdp_rxqs(cpsw);
+ if (ret < 0)
+ goto err_cleanup;
+
ret = cpsw_fill_rx_channels(priv);
if (ret < 0)
goto err_cleanup;
@@ -1422,9 +1754,10 @@ static int cpsw_ndo_open(struct net_device *ndev)
err_cleanup:
if (!cpsw->usage_count) {
cpdma_ctlr_stop(cpsw->dma);
- for_each_slave(priv, cpsw_slave_stop, cpsw);
+ cpsw_destroy_xdp_rxqs(cpsw);
}
+ for_each_slave(priv, cpsw_slave_stop, cpsw);
pm_runtime_put_sync(cpsw->dev);
netif_carrier_off(priv->ndev);
return ret;
@@ -1447,6 +1780,7 @@ static int cpsw_ndo_stop(struct net_device *ndev)
cpsw_intr_disable(cpsw);
cpdma_ctlr_stop(cpsw->dma);
cpsw_ale_stop(cpsw->ale);
+ cpsw_destroy_xdp_rxqs(cpsw);
}
for_each_slave(priv, cpsw_slave_stop, cpsw);
@@ -2004,6 +2338,64 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
}
}
+static int cpsw_xdp_prog_setup(struct cpsw_priv *priv, struct netdev_bpf *bpf)
+{
+ struct bpf_prog *prog = bpf->prog;
+
+ if (!priv->xdpi.prog && !prog)
+ return 0;
+
+ if (!xdp_attachment_flags_ok(&priv->xdpi, bpf))
+ return -EBUSY;
+
+ WRITE_ONCE(priv->xdp_prog, prog);
+
+ xdp_attachment_setup(&priv->xdpi, bpf);
+
+ return 0;
+}
+
+static int cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+
+ switch (bpf->command) {
+ case XDP_SETUP_PROG:
+ return cpsw_xdp_prog_setup(priv, bpf);
+
+ case XDP_QUERY_PROG:
+ return xdp_attachment_query(&priv->xdpi, bpf);
+
+ default:
+ return -EINVAL;
+ }
+}
+
+static int cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+ struct xdp_frame **frames, u32 flags)
+{
+ struct cpsw_priv *priv = netdev_priv(ndev);
+ struct xdp_frame *xdpf;
+ int i, drops = 0;
+
+ if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+ return -EINVAL;
+
+ for (i = 0; i < n; i++) {
+ xdpf = frames[i];
+ if (xdpf->len < CPSW_MIN_PACKET_SIZE) {
+ xdp_return_frame_rx_napi(xdpf);
+ drops++;
+ continue;
+ }
+
+ if (cpsw_xdp_tx_frame(priv, xdpf, NULL))
+ drops++;
+ }
+
+ return n - drops;
+}
+
#ifdef CONFIG_NET_POLL_CONTROLLER
static void cpsw_ndo_poll_controller(struct net_device *ndev)
{
@@ -2032,6 +2424,8 @@ static const struct net_device_ops cpsw_netdev_ops = {
.ndo_vlan_rx_add_vid = cpsw_ndo_vlan_rx_add_vid,
.ndo_vlan_rx_kill_vid = cpsw_ndo_vlan_rx_kill_vid,
.ndo_setup_tc = cpsw_ndo_setup_tc,
+ .ndo_bpf = cpsw_ndo_bpf,
+ .ndo_xdp_xmit = cpsw_ndo_xdp_xmit,
};
static void cpsw_get_drvinfo(struct net_device *ndev,
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index e4d7185fde49..31248a6cc642 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -578,6 +578,18 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx,
return 0;
}
+static void cpsw_fail(struct cpsw_common *cpsw)
+{
+ struct net_device *ndev;
+ int i;
+
+ for (i = 0; i < cpsw->data.slaves; i++) {
+ ndev = cpsw->slaves[i].ndev;
+ if (ndev)
+ dev_close(ndev);
+ }
+}
+
int cpsw_set_channels_common(struct net_device *ndev,
struct ethtool_channels *chs,
cpdma_handler_fn rx_handler)
@@ -585,7 +597,7 @@ int cpsw_set_channels_common(struct net_device *ndev,
struct cpsw_priv *priv = netdev_priv(ndev);
struct cpsw_common *cpsw = priv->cpsw;
struct net_device *sl_ndev;
- int i, ret;
+ int i, new_pools, ret;
ret = cpsw_check_ch_settings(cpsw, chs);
if (ret < 0)
@@ -593,6 +605,8 @@ int cpsw_set_channels_common(struct net_device *ndev,
cpsw_suspend_data_pass(ndev);
+ new_pools = (chs->rx_count != cpsw->rx_ch_num) && cpsw->usage_count;
+
ret = cpsw_update_channels_res(priv, chs->rx_count, 1, rx_handler);
if (ret)
goto err;
@@ -622,12 +636,19 @@ int cpsw_set_channels_common(struct net_device *ndev,
cpsw_split_res(cpsw);
+ if (new_pools) {
+ cpsw_destroy_xdp_rxqs(cpsw);
+ ret = cpsw_create_xdp_rxqs(cpsw);
+ if (ret)
+ goto err;
+ }
+
ret = cpsw_resume_data_pass(ndev);
if (!ret)
return 0;
err:
dev_err(priv->dev, "cannot update channels number, closing device\n");
- dev_close(ndev);
+ cpsw_fail(cpsw);
return ret;
}
@@ -647,8 +668,7 @@ void cpsw_get_ringparam(struct net_device *ndev,
int cpsw_set_ringparam(struct net_device *ndev,
struct ethtool_ringparam *ering)
{
- struct cpsw_priv *priv = netdev_priv(ndev);
- struct cpsw_common *cpsw = priv->cpsw;
+ struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
int descs_num, ret;
/* ignore ering->tx_pending - only rx_pending adjustment is supported */
@@ -672,13 +692,20 @@ int cpsw_set_ringparam(struct net_device *ndev,
return ret;
}
+ if (cpsw->usage_count) {
+ cpsw_destroy_xdp_rxqs(cpsw);
+ ret = cpsw_create_xdp_rxqs(cpsw);
+ if (ret)
+ goto err;
+ }
+
ret = cpsw_resume_data_pass(ndev);
if (!ret)
return 0;
err:
cpdma_set_num_rx_descs(cpsw->dma, descs_num);
dev_err(cpsw->dev, "cannot set ring params, closing device\n");
- dev_close(ndev);
+ cpsw_fail(cpsw);
return ret;
}
diff --git a/drivers/net/ethernet/ti/cpsw_priv.h b/drivers/net/ethernet/ti/cpsw_priv.h
index 04795b97ee71..086bf38a4736 100644
--- a/drivers/net/ethernet/ti/cpsw_priv.h
+++ b/drivers/net/ethernet/ti/cpsw_priv.h
@@ -346,6 +346,7 @@ struct cpsw_common {
int rx_ch_num, tx_ch_num;
int speed;
int usage_count;
+ struct page_pool *page_pool[CPSW_MAX_QUEUES];
};
struct cpsw_priv {
@@ -360,6 +361,10 @@ struct cpsw_priv {
int shp_cfg_speed;
int tx_ts_enabled;
int rx_ts_enabled;
+ struct bpf_prog *xdp_prog;
+ struct xdp_rxq_info xdp_rxq[CPSW_MAX_QUEUES];
+ struct xdp_attachment_info xdpi;
+
u32 emac_port;
struct cpsw_common *cpsw;
};
@@ -391,6 +396,8 @@ int cpsw_fill_rx_channels(struct cpsw_priv *priv);
void cpsw_intr_enable(struct cpsw_common *cpsw);
void cpsw_intr_disable(struct cpsw_common *cpsw);
void cpsw_tx_handler(void *token, int len, int status);
+int cpsw_create_xdp_rxqs(struct cpsw_common *cpsw);
+void cpsw_destroy_xdp_rxqs(struct cpsw_common *cpsw);
/* ethtool */
u32 cpsw_get_msglevel(struct net_device *ndev);
--
2.17.1
^ permalink raw reply related
* [PATCH v7 net-next 3/5] net: ethernet: ti: davinci_cpdma: allow desc split while down
From: Ivan Khoronzhuk @ 2019-07-04 23:14 UTC (permalink / raw)
To: grygorii.strashko, hawk, davem
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190704231406.27083-1-ivan.khoronzhuk@linaro.org>
That's possible to set ring params while interfaces are down. When
interface gets up it uses number of descs to fill rx queue and on
later on changes to create rx pools. Usually, this resplit can happen
after phy is up, but it can be needed before this, so allow it to
happen while setting number of rx descs, when interfaces are down.
Also, if no dependency on intf state, move it to cpdma layer, where
it should be.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/cpsw_ethtool.c | 17 +++++++++++------
drivers/net/ethernet/ti/davinci_cpdma.c | 17 ++++++++++++++++-
drivers/net/ethernet/ti/davinci_cpdma.h | 3 +--
3 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index f60dc1dfc443..c477e6b620d6 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -650,7 +650,7 @@ int cpsw_set_ringparam(struct net_device *ndev,
{
struct cpsw_priv *priv = netdev_priv(ndev);
struct cpsw_common *cpsw = priv->cpsw;
- int ret;
+ int descs_num, ret;
/* ignore ering->tx_pending - only rx_pending adjustment is supported */
@@ -659,20 +659,25 @@ int cpsw_set_ringparam(struct net_device *ndev,
ering->rx_pending > (cpsw->descs_pool_size - CPSW_MAX_QUEUES))
return -EINVAL;
- if (ering->rx_pending == cpdma_get_num_rx_descs(cpsw->dma))
+ descs_num = cpdma_get_num_rx_descs(cpsw->dma);
+ if (ering->rx_pending == descs_num)
return 0;
cpsw_suspend_data_pass(ndev);
- cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+ ret = cpdma_set_num_rx_descs(cpsw->dma, ering->rx_pending);
+ if (ret) {
+ if (cpsw_resume_data_pass(ndev))
+ goto err;
- if (cpsw->usage_count)
- cpdma_chan_split_pool(cpsw->dma);
+ return ret;
+ }
ret = cpsw_resume_data_pass(ndev);
if (!ret)
return 0;
-
+err:
+ cpdma_set_num_rx_descs(cpsw->dma, descs_num);
dev_err(cpsw->dev, "cannot set ring params, closing device\n");
dev_close(ndev);
return ret;
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 8da46394c0e7..a3b6aeb4e935 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -1423,8 +1423,23 @@ int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr)
return ctlr->num_tx_desc;
}
-void cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc)
+int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc)
{
+ unsigned long flags;
+ int temp, ret;
+
+ spin_lock_irqsave(&ctlr->lock, flags);
+
+ temp = ctlr->num_rx_desc;
ctlr->num_rx_desc = num_rx_desc;
ctlr->num_tx_desc = ctlr->pool->num_desc - ctlr->num_rx_desc;
+ ret = cpdma_chan_split_pool(ctlr);
+ if (ret) {
+ ctlr->num_rx_desc = temp;
+ ctlr->num_tx_desc = ctlr->pool->num_desc - ctlr->num_rx_desc;
+ }
+
+ spin_unlock_irqrestore(&ctlr->lock, flags);
+
+ return ret;
}
diff --git a/drivers/net/ethernet/ti/davinci_cpdma.h b/drivers/net/ethernet/ti/davinci_cpdma.h
index 0271a20c2e09..d3cfe234d16a 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.h
+++ b/drivers/net/ethernet/ti/davinci_cpdma.h
@@ -116,8 +116,7 @@ enum cpdma_control {
int cpdma_control_get(struct cpdma_ctlr *ctlr, int control);
int cpdma_control_set(struct cpdma_ctlr *ctlr, int control, int value);
int cpdma_get_num_rx_descs(struct cpdma_ctlr *ctlr);
-void cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc);
+int cpdma_set_num_rx_descs(struct cpdma_ctlr *ctlr, int num_rx_desc);
int cpdma_get_num_tx_descs(struct cpdma_ctlr *ctlr);
-int cpdma_chan_split_pool(struct cpdma_ctlr *ctlr);
#endif
--
2.17.1
^ permalink raw reply related
* [PATCH v7 net-next 4/5] net: ethernet: ti: cpsw_ethtool: allow res split while down
From: Ivan Khoronzhuk @ 2019-07-04 23:14 UTC (permalink / raw)
To: grygorii.strashko, hawk, davem
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
In-Reply-To: <20190704231406.27083-1-ivan.khoronzhuk@linaro.org>
That's possible to set channel num while interfaces are down. When
interface gets up it should resplit budget. This resplit can happen
after phy is up but only if speed is changed, so should be set before
this, for this allow it to happen while changing number of channels,
when interfaces are down.
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
drivers/net/ethernet/ti/cpsw_ethtool.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/ti/cpsw_ethtool.c b/drivers/net/ethernet/ti/cpsw_ethtool.c
index c477e6b620d6..e4d7185fde49 100644
--- a/drivers/net/ethernet/ti/cpsw_ethtool.c
+++ b/drivers/net/ethernet/ti/cpsw_ethtool.c
@@ -620,8 +620,7 @@ int cpsw_set_channels_common(struct net_device *ndev,
}
}
- if (cpsw->usage_count)
- cpsw_split_res(cpsw);
+ cpsw_split_res(cpsw);
ret = cpsw_resume_data_pass(ndev);
if (!ret)
--
2.17.1
^ permalink raw reply related
* [PATCH v7 net-next 1/5] net: core: page_pool: add user refcnt and reintroduce page_pool_destroy
From: Ivan Khoronzhuk @ 2019-07-04 23:14 UTC (permalink / raw)
To: grygorii.strashko, hawk, davem
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk,
Jesper Dangaard Brouer
In-Reply-To: <20190704231406.27083-1-ivan.khoronzhuk@linaro.org>
Jesper recently removed page_pool_destroy() (from driver invocation)
and moved shutdown and free of page_pool into xdp_rxq_info_unreg(),
in-order to handle in-flight packets/pages. This created an asymmetry
in drivers create/destroy pairs.
This patch reintroduce page_pool_destroy and add page_pool user
refcnt. This serves the purpose to simplify drivers error handling as
driver now drivers always calls page_pool_destroy() and don't need to
track if xdp_rxq_info_reg_mem_model() was unsuccessful.
This could be used for a special cases where a single RX-queue (with a
single page_pool) provides packets for two net_device'es, and thus
needs to register the same page_pool twice with two xdp_rxq_info
structures.
This patch is primarily to ease API usage for drivers. The recently
merged netsec driver, actually have a bug in this area, which is
solved by this API change.
This patch is a modified version of Ivan Khoronzhu's original patch.
Link: https://lore.kernel.org/netdev/20190625175948.24771-2-ivan.khoronzhuk@linaro.org/
Fixes: 5c67bf0ec4d0 ("net: netsec: Use page_pool API")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
---
.../net/ethernet/mellanox/mlx5/core/en_main.c | 4 +--
drivers/net/ethernet/socionext/netsec.c | 8 ++----
include/net/page_pool.h | 25 +++++++++++++++++++
net/core/page_pool.c | 8 ++++++
net/core/xdp.c | 3 +++
5 files changed, 40 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2f9093ba82aa..ac882b2341d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -575,8 +575,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
}
err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
MEM_TYPE_PAGE_POOL, rq->page_pool);
- if (err)
- page_pool_free(rq->page_pool);
}
if (err)
goto err_free;
@@ -644,6 +642,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
if (rq->xdp_prog)
bpf_prog_put(rq->xdp_prog);
xdp_rxq_info_unreg(&rq->xdp_rxq);
+ page_pool_destroy(rq->page_pool);
mlx5_wq_destroy(&rq->wq_ctrl);
return err;
@@ -678,6 +677,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
}
xdp_rxq_info_unreg(&rq->xdp_rxq);
+ page_pool_destroy(rq->page_pool);
mlx5_wq_destroy(&rq->wq_ctrl);
}
diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 5544a722543f..43ab0ce90704 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -1210,15 +1210,11 @@ static void netsec_uninit_pkt_dring(struct netsec_priv *priv, int id)
}
}
- /* Rx is currently using page_pool
- * since the pool is created during netsec_setup_rx_dring(), we need to
- * free the pool manually if the registration failed
- */
+ /* Rx is currently using page_pool */
if (id == NETSEC_RING_RX) {
if (xdp_rxq_info_is_reg(&dring->xdp_rxq))
xdp_rxq_info_unreg(&dring->xdp_rxq);
- else
- page_pool_free(dring->page_pool);
+ page_pool_destroy(dring->page_pool);
}
memset(dring->desc, 0, sizeof(struct netsec_desc) * DESC_NUM);
diff --git a/include/net/page_pool.h b/include/net/page_pool.h
index ee9c871d2043..2cbcdbdec254 100644
--- a/include/net/page_pool.h
+++ b/include/net/page_pool.h
@@ -101,6 +101,12 @@ struct page_pool {
struct ptr_ring ring;
atomic_t pages_state_release_cnt;
+
+ /* A page_pool is strictly tied to a single RX-queue being
+ * protected by NAPI, due to above pp_alloc_cache. This
+ * refcnt serves purpose is to simplify drivers error handling.
+ */
+ refcount_t user_cnt;
};
struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
@@ -134,6 +140,15 @@ static inline void page_pool_free(struct page_pool *pool)
#endif
}
+/* Drivers use this instead of page_pool_free */
+static inline void page_pool_destroy(struct page_pool *pool)
+{
+ if (!pool)
+ return;
+
+ page_pool_free(pool);
+}
+
/* Never call this directly, use helpers below */
void __page_pool_put_page(struct page_pool *pool,
struct page *page, bool allow_direct);
@@ -201,4 +216,14 @@ static inline bool is_page_pool_compiled_in(void)
#endif
}
+static inline void page_pool_get(struct page_pool *pool)
+{
+ refcount_inc(&pool->user_cnt);
+}
+
+static inline bool page_pool_put(struct page_pool *pool)
+{
+ return refcount_dec_and_test(&pool->user_cnt);
+}
+
#endif /* _NET_PAGE_POOL_H */
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index b366f59885c1..3272dc7a8c81 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -49,6 +49,9 @@ static int page_pool_init(struct page_pool *pool,
atomic_set(&pool->pages_state_release_cnt, 0);
+ /* Driver calling page_pool_create() also call page_pool_destroy() */
+ refcount_set(&pool->user_cnt, 1);
+
if (pool->p.flags & PP_FLAG_DMA_MAP)
get_device(pool->p.dev);
@@ -70,6 +73,7 @@ struct page_pool *page_pool_create(const struct page_pool_params *params)
kfree(pool);
return ERR_PTR(err);
}
+
return pool;
}
EXPORT_SYMBOL(page_pool_create);
@@ -356,6 +360,10 @@ static void __warn_in_flight(struct page_pool *pool)
void __page_pool_free(struct page_pool *pool)
{
+ /* Only last user actually free/release resources */
+ if (!page_pool_put(pool))
+ return;
+
WARN(pool->alloc.count, "API usage violation");
WARN(!ptr_ring_empty(&pool->ring), "ptr_ring is not empty");
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 829377cc83db..d7bf62ffbb5e 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -370,6 +370,9 @@ int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
goto err;
}
+ if (type == MEM_TYPE_PAGE_POOL)
+ page_pool_get(xdp_alloc->page_pool);
+
mutex_unlock(&mem_id_lock);
trace_mem_connect(xdp_alloc, xdp_rxq);
--
2.17.1
^ permalink raw reply related
* [PATCH v7 net-next 0/5] net: ethernet: ti: cpsw: Add XDP support
From: Ivan Khoronzhuk @ 2019-07-04 23:14 UTC (permalink / raw)
To: grygorii.strashko, hawk, davem
Cc: ast, linux-kernel, linux-omap, xdp-newbies, ilias.apalodimas,
netdev, daniel, jakub.kicinski, john.fastabend, Ivan Khoronzhuk
This patchset adds XDP support for TI cpsw driver and base it on
page_pool allocator. It was verified on af_xdp socket drop,
af_xdp l2f, ebpf XDP_DROP, XDP_REDIRECT, XDP_PASS, XDP_TX.
It was verified with following configs enabled:
CONFIG_JIT=y
CONFIG_BPFILTER=y
CONFIG_BPF_SYSCALL=y
CONFIG_XDP_SOCKETS=y
CONFIG_BPF_EVENTS=y
CONFIG_HAVE_EBPF_JIT=y
CONFIG_BPF_JIT=y
CONFIG_CGROUP_BPF=y
Link on previous v6:
https://lkml.org/lkml/2019/7/3/243
Also regular tests with iperf2 were done in order to verify impact on
regular netstack performance, compared with base commit:
https://pastebin.com/JSMT0iZ4
v6..v7:
- rolled back to v4 solution but with small modification
- picked up patch:
https://www.spinics.net/lists/netdev/msg583145.html
- added changes related to netsec fix and cpsw
v5..v6:
- do changes that is rx_dev while redirect/flush cycle is kept the same
- dropped net: ethernet: ti: davinci_cpdma: return handler status
- other changes desc in patches
v4..v5:
- added two plreliminary patches:
net: ethernet: ti: davinci_cpdma: allow desc split while down
net: ethernet: ti: cpsw_ethtool: allow res split while down
- added xdp alocator refcnt on xdp level, avoiding page pool refcnt
- moved flush status as separate argument for cpdma_chan_process
- reworked cpsw code according to last changes to allocator
- added missed statistic counter
v3..v4:
- added page pool user counter
- use same pool for ndevs in dual mac
- restructured page pool create/destroy according to the last changes in API
v2..v3:
- each rxq and ndev has its own page pool
v1..v2:
- combined xdp_xmit functions
- used page allocation w/o refcnt juggle
- unmapped page for skb netstack
- moved rxq/page pool allocation to open/close pair
- added several preliminary patches:
net: page_pool: add helper function to retrieve dma addresses
net: page_pool: add helper function to unmap dma addresses
net: ethernet: ti: cpsw: use cpsw as drv data
net: ethernet: ti: cpsw_ethtool: simplify slave loops
Ivan Khoronzhuk (5):
net: core: page_pool: add user refcnt and reintroduce
page_pool_destroy
net: ethernet: ti: davinci_cpdma: add dma mapped submit
net: ethernet: ti: davinci_cpdma: allow desc split while down
net: ethernet: ti: cpsw_ethtool: allow res split while down
net: ethernet: ti: cpsw: add XDP support
.../net/ethernet/mellanox/mlx5/core/en_main.c | 4 +-
drivers/net/ethernet/socionext/netsec.c | 8 +-
drivers/net/ethernet/ti/Kconfig | 1 +
drivers/net/ethernet/ti/cpsw.c | 502 ++++++++++++++++--
drivers/net/ethernet/ti/cpsw_ethtool.c | 57 +-
drivers/net/ethernet/ti/cpsw_priv.h | 7 +
drivers/net/ethernet/ti/davinci_cpdma.c | 106 +++-
drivers/net/ethernet/ti/davinci_cpdma.h | 7 +-
include/net/page_pool.h | 25 +
net/core/page_pool.c | 8 +
net/core/xdp.c | 3 +
11 files changed, 640 insertions(+), 88 deletions(-)
--
2.17.1
^ permalink raw reply
* Re: bug: tpacket_snd can cause data corruption
From: Willem de Bruijn @ 2019-07-04 22:59 UTC (permalink / raw)
To: Frank de Brabander
Cc: David S . Miller, Willem de Bruijn, Network Development
In-Reply-To: <d32bc4b8-b547-1d78-e245-2ec51df19c77@gmail.com>
> > Can you reproduce the issue when running the modified test in a
> > network namespace (./in_netns.sh ./txring_overwrite)?
> But even when running the test with ./in_netns.sh it shows
> "wrong pattern", this time without length mismatches:
>
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
> wrong pattern: 0x62 != 0x61
>
> As already mentioned, it seems to trigger mainly (only ?) when
> an USB device is connected. The PC I'm testing this on has an
> USB hub with many ports and connected devices. When connecting
> this USB hub, the amount of "wrong pattern" errors that are
> shown seems to correlate to the amount of new devices
> that the kernel should detect. Connecting in a single USB device
> also triggers the error, but not on every attempt.
>
> Unfortunately have not found any other way to force the
> error to trigger. E.g. running stress-ng to generate CPU load or
> timer interrupts does not seem to have any impact.
Interesting, thanks for testing. No exact idea so far. The USB devices
are not necessarily network devices, I suppose? I don't immediately
have a setup to test the usb hotplug, so cannot yet reproduce the bug.
^ permalink raw reply
* [PATCH v3 0/4] net: dsa: Add Vitesse VSC73xx parallel mode
From: Pawel Dembicki @ 2019-07-04 22:29 UTC (permalink / raw)
Cc: Pawel Dembicki, linus.walleij, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, Rob Herring, Mark Rutland,
netdev, devicetree, linux-kernel
Main goal of this patch series is to add support for CPU attached parallel
bus in Vitesse VSC73xx switches. Existing driver supports only SPI mode.
Second change is needed for devices in unmanaged state.
V3:
- fix commit messages and descriptions about memory-mapped I/O mode
V2:
- drop changes in compatible strings
- make changes less invasive
- drop mutex in platform part and move mutex from core to spi part
- fix indentation
- fix devm_ioremap_resource result check
- add cover letter
Pawel Dembicki (4):
net: dsa: Change DT bindings for Vitesse VSC73xx switches
net: dsa: vsc73xx: Split vsc73xx driver
net: dsa: vsc73xx: add support for parallel mode
net: dsa: vsc73xx: Assert reset if iCPU is enabled
.../bindings/net/dsa/vitesse,vsc73xx.txt | 58 ++++-
drivers/net/dsa/Kconfig | 20 +-
drivers/net/dsa/Makefile | 4 +-
...tesse-vsc73xx.c => vitesse-vsc73xx-core.c} | 206 +++---------------
drivers/net/dsa/vitesse-vsc73xx-platform.c | 164 ++++++++++++++
drivers/net/dsa/vitesse-vsc73xx-spi.c | 203 +++++++++++++++++
drivers/net/dsa/vitesse-vsc73xx.h | 29 +++
7 files changed, 499 insertions(+), 185 deletions(-)
rename drivers/net/dsa/{vitesse-vsc73xx.c => vitesse-vsc73xx-core.c} (90%)
create mode 100644 drivers/net/dsa/vitesse-vsc73xx-platform.c
create mode 100644 drivers/net/dsa/vitesse-vsc73xx-spi.c
create mode 100644 drivers/net/dsa/vitesse-vsc73xx.h
--
2.20.1
^ permalink raw reply
* [PATCH v3 1/4] net: dsa: Change DT bindings for Vitesse VSC73xx switches
From: Pawel Dembicki @ 2019-07-04 22:29 UTC (permalink / raw)
Cc: Pawel Dembicki, linus.walleij, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, Rob Herring, Mark Rutland,
netdev, devicetree, linux-kernel
In-Reply-To: <20190704222907.2888-1-paweldembicki@gmail.com>
This commit introduce how to use vsc73xx platform driver.
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
.../bindings/net/dsa/vitesse,vsc73xx.txt | 58 +++++++++++++++++--
1 file changed, 54 insertions(+), 4 deletions(-)
diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
index ed4710c40641..bbf4a13f6d75 100644
--- a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
+++ b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
@@ -2,8 +2,8 @@ Vitesse VSC73xx Switches
========================
This defines device tree bindings for the Vitesse VSC73xx switch chips.
-The Vitesse company has been acquired by Microsemi and Microsemi in turn
-acquired by Microchip but retains this vendor branding.
+The Vitesse company has been acquired by Microsemi and Microsemi has
+been acquired Microchip but retains this vendor branding.
The currently supported switch chips are:
Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
@@ -11,8 +11,14 @@ Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
-The device tree node is an SPI device so it must reside inside a SPI bus
-device tree node, see spi/spi-bus.txt
+This switch could have two different management interface.
+
+If SPI interface is used, the device tree node is an SPI device so it must
+reside inside a SPI bus device tree node, see spi/spi-bus.txt
+
+When the chip is connected to a parallel memory bus and work in memory-mapped
+I/O mode, a platform device is used to represent the vsc73xx. In this case it
+must reside inside a platform bus device tree node.
Required properties:
@@ -38,6 +44,7 @@ and subnodes of DSA switches.
Examples:
+SPI:
switch@0 {
compatible = "vitesse,vsc7395";
reg = <0>;
@@ -79,3 +86,46 @@ switch@0 {
};
};
};
+
+Platform:
+switch@2,0 {
+ #address-cells = <1>;
+ #size-cells = <1>;
+ compatible = "vitesse,vsc7385";
+ reg = <0x2 0x0 0x20000>;
+ reset-gpios = <&gpio0 12 GPIO_ACTIVE_LOW>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ reg = <0>;
+ label = "lan1";
+ };
+ port@1 {
+ reg = <1>;
+ label = "lan2";
+ };
+ port@2 {
+ reg = <2>;
+ label = "lan3";
+ };
+ port@3 {
+ reg = <3>;
+ label = "lan4";
+ };
+ vsc: port@6 {
+ reg = <6>;
+ label = "cpu";
+ ethernet = <&enet0>;
+ phy-mode = "rgmii";
+ fixed-link {
+ speed = <1000>;
+ full-duplex;
+ pause;
+ };
+ };
+ };
+
+};
--
2.20.1
^ permalink raw reply related
* [PATCH v3 4/4] net: dsa: vsc73xx: Assert reset if iCPU is enabled
From: Pawel Dembicki @ 2019-07-04 22:29 UTC (permalink / raw)
Cc: Pawel Dembicki, linus.walleij, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, Rob Herring, Mark Rutland,
netdev, devicetree, linux-kernel
In-Reply-To: <20190704222907.2888-1-paweldembicki@gmail.com>
Driver allow to use devices with disabled iCPU only.
Some devices have pre-initialised iCPU by bootloader.
That state make switch unmanaged. This patch force reset
if device is in unmanaged state. In the result chip lost
internal firmware from RAM and it can be managed.
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/vitesse-vsc73xx-core.c | 36 ++++++++++++--------------
1 file changed, 17 insertions(+), 19 deletions(-)
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index 10063f31d9a3..614377ef7956 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -417,22 +417,8 @@ static int vsc73xx_detect(struct vsc73xx *vsc)
}
if (val == 0xffffffff) {
- dev_info(vsc->dev, "chip seems dead, assert reset\n");
- gpiod_set_value_cansleep(vsc->reset, 1);
- /* Reset pulse should be 20ns minimum, according to datasheet
- * table 245, so 10us should be fine
- */
- usleep_range(10, 100);
- gpiod_set_value_cansleep(vsc->reset, 0);
- /* Wait 20ms according to datasheet table 245 */
- msleep(20);
-
- ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
- VSC73XX_ICPU_MBOX_VAL, &val);
- if (val == 0xffffffff) {
- dev_err(vsc->dev, "seems not to help, giving up\n");
- return -ENODEV;
- }
+ dev_info(vsc->dev, "chip seems dead.\n");
+ return -EAGAIN;
}
ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
@@ -483,9 +469,8 @@ static int vsc73xx_detect(struct vsc73xx *vsc)
}
if (icpu_si_boot_en && !icpu_pi_en) {
dev_err(vsc->dev,
- "iCPU enabled boots from SI, no external memory\n");
- dev_err(vsc->dev, "no idea how to deal with this\n");
- return -ENODEV;
+ "iCPU enabled boots from PI/SI, no external memory\n");
+ return -EAGAIN;
}
if (!icpu_si_boot_en && icpu_pi_en) {
dev_err(vsc->dev,
@@ -1158,6 +1143,19 @@ int vsc73xx_probe(struct vsc73xx *vsc)
msleep(20);
ret = vsc73xx_detect(vsc);
+ if (ret == -EAGAIN) {
+ dev_err(vsc->dev,
+ "Chip seems to be out of control. Assert reset and try again.\n");
+ gpiod_set_value_cansleep(vsc->reset, 1);
+ /* Reset pulse should be 20ns minimum, according to datasheet
+ * table 245, so 10us should be fine
+ */
+ usleep_range(10, 100);
+ gpiod_set_value_cansleep(vsc->reset, 0);
+ /* Wait 20ms according to datasheet table 245 */
+ msleep(20);
+ ret = vsc73xx_detect(vsc);
+ }
if (ret) {
dev_err(dev, "no chip found (%d)\n", ret);
return -ENODEV;
--
2.20.1
^ permalink raw reply related
* [PATCH v3 3/4] net: dsa: vsc73xx: add support for parallel mode
From: Pawel Dembicki @ 2019-07-04 22:29 UTC (permalink / raw)
Cc: Pawel Dembicki, linus.walleij, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, Rob Herring, Mark Rutland,
netdev, devicetree, linux-kernel
In-Reply-To: <20190704222907.2888-1-paweldembicki@gmail.com>
This patch add platform part of vsc73xx driver.
It allows to use chip connected to a parallel memory bus and work in
memory-mapped I/O mode. (aka PI bus in chip manual)
By default device is working in big endian mode.
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
---
drivers/net/dsa/Kconfig | 9 ++
drivers/net/dsa/Makefile | 1 +
drivers/net/dsa/vitesse-vsc73xx-platform.c | 164 +++++++++++++++++++++
3 files changed, 174 insertions(+)
create mode 100644 drivers/net/dsa/vitesse-vsc73xx-platform.c
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 4ab2aa09e2e4..cf9dbd15dd2d 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -116,4 +116,13 @@ config NET_DSA_VITESSE_VSC73XX_SPI
---help---
This enables support for the Vitesse VSC7385, VSC7388, VSC7395
and VSC7398 SparX integrated ethernet switches in SPI managed mode.
+
+config NET_DSA_VITESSE_VSC73XX_PLATFORM
+ tristate "Vitesse VSC7385/7388/7395/7398 Platform mode support"
+ depends on HAS_IOMEM
+ select NET_DSA_VITESSE_VSC73XX
+ ---help---
+ This enables support for the Vitesse VSC7385, VSC7388, VSC7395
+ and VSC7398 SparX integrated ethernet switches, connected over
+ a CPU-attached address bus and work in memory-mapped I/O mode.
endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 117bf78be211..d5e4c668ac03 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -15,6 +15,7 @@ obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx-core.o
+obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_PLATFORM) += vitesse-vsc73xx-platform.o
obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o
obj-y += b53/
obj-y += microchip/
diff --git a/drivers/net/dsa/vitesse-vsc73xx-platform.c b/drivers/net/dsa/vitesse-vsc73xx-platform.c
new file mode 100644
index 000000000000..0541785f9fee
--- /dev/null
+++ b/drivers/net/dsa/vitesse-vsc73xx-platform.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DSA driver for:
+ * Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+ *
+ * This driver takes control of the switch chip connected over CPU-attached
+ * address bus and configures it to route packages around when connected to
+ * a CPU port.
+ *
+ * Copyright (C) 2019 Pawel Dembicki <paweldembicki@gmail.com>
+ * Based on vitesse-vsc-spi.c by:
+ * Copyright (C) 2018 Linus Wallej <linus.walleij@linaro.org>
+ * Includes portions of code from the firmware uploader by:
+ * Copyright (C) 2009 Gabor Juhos <juhosg@openwrt.org>
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+#include "vitesse-vsc73xx.h"
+
+#define VSC73XX_CMD_PLATFORM_BLOCK_SHIFT 14
+#define VSC73XX_CMD_PLATFORM_BLOCK_MASK 0x7
+#define VSC73XX_CMD_PLATFORM_SUBBLOCK_SHIFT 10
+#define VSC73XX_CMD_PLATFORM_SUBBLOCK_MASK 0xf
+#define VSC73XX_CMD_PLATFORM_REGISTER_SHIFT 2
+
+/**
+ * struct vsc73xx_platform - VSC73xx Platform state container
+ */
+struct vsc73xx_platform {
+ struct platform_device *pdev;
+ void __iomem *base_addr;
+ struct vsc73xx vsc;
+};
+
+static const struct vsc73xx_ops vsc73xx_platform_ops;
+
+static u32 vsc73xx_make_addr(u8 block, u8 subblock, u8 reg)
+{
+ u32 ret;
+
+ ret = (block & VSC73XX_CMD_PLATFORM_BLOCK_MASK)
+ << VSC73XX_CMD_PLATFORM_BLOCK_SHIFT;
+ ret |= (subblock & VSC73XX_CMD_PLATFORM_SUBBLOCK_MASK)
+ << VSC73XX_CMD_PLATFORM_SUBBLOCK_SHIFT;
+ ret |= reg << VSC73XX_CMD_PLATFORM_REGISTER_SHIFT;
+
+ return ret;
+}
+
+static int vsc73xx_platform_read(struct vsc73xx *vsc, u8 block, u8 subblock,
+ u8 reg, u32 *val)
+{
+ struct vsc73xx_platform *vsc_platform = vsc->priv;
+ u32 offset;
+
+ if (!vsc73xx_is_addr_valid(block, subblock))
+ return -EINVAL;
+
+ offset = vsc73xx_make_addr(block, subblock, reg);
+ /* By default vsc73xx running in big-endian mode.
+ * (See "Register Addressing" section 5.5.3 in the VSC7385 manual.)
+ */
+ *val = ioread32be(vsc_platform->base_addr + offset);
+
+ return 0;
+}
+
+static int vsc73xx_platform_write(struct vsc73xx *vsc, u8 block, u8 subblock,
+ u8 reg, u32 val)
+{
+ struct vsc73xx_platform *vsc_platform = vsc->priv;
+ u32 offset;
+
+ if (!vsc73xx_is_addr_valid(block, subblock))
+ return -EINVAL;
+
+ offset = vsc73xx_make_addr(block, subblock, reg);
+ iowrite32be(val, vsc_platform->base_addr + offset);
+
+ return 0;
+}
+
+static int vsc73xx_platform_probe(struct platform_device *pdev)
+{
+ struct device *dev = &pdev->dev;
+ struct vsc73xx_platform *vsc_platform;
+ struct resource *res = NULL;
+ int ret;
+
+ vsc_platform = devm_kzalloc(dev, sizeof(*vsc_platform), GFP_KERNEL);
+ if (!vsc_platform)
+ return -ENOMEM;
+
+ platform_set_drvdata(pdev, vsc_platform);
+ vsc_platform->pdev = pdev;
+ vsc_platform->vsc.dev = dev;
+ vsc_platform->vsc.priv = vsc_platform;
+ vsc_platform->vsc.ops = &vsc73xx_platform_ops;
+
+ /* obtain I/O memory space */
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ if (!res) {
+ dev_err(&pdev->dev, "cannot obtain I/O memory space\n");
+ ret = -ENXIO;
+ return ret;
+ }
+
+ vsc_platform->base_addr = devm_ioremap_resource(&pdev->dev, res);
+ if (IS_ERR(vsc_platform->base_addr)) {
+ dev_err(&pdev->dev, "cannot request I/O memory space\n");
+ ret = -ENXIO;
+ return ret;
+ }
+
+ return vsc73xx_probe(&vsc_platform->vsc);
+}
+
+static int vsc73xx_platform_remove(struct platform_device *pdev)
+{
+ struct vsc73xx_platform *vsc_platform = platform_get_drvdata(pdev);
+
+ return vsc73xx_remove(&vsc_platform->vsc);
+}
+
+static const struct vsc73xx_ops vsc73xx_platform_ops = {
+ .read = vsc73xx_platform_read,
+ .write = vsc73xx_platform_write,
+};
+
+static const struct of_device_id vsc73xx_of_match[] = {
+ {
+ .compatible = "vitesse,vsc7385",
+ },
+ {
+ .compatible = "vitesse,vsc7388",
+ },
+ {
+ .compatible = "vitesse,vsc7395",
+ },
+ {
+ .compatible = "vitesse,vsc7398",
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
+
+static struct platform_driver vsc73xx_platform_driver = {
+ .probe = vsc73xx_platform_probe,
+ .remove = vsc73xx_platform_remove,
+ .driver = {
+ .name = "vsc73xx-platform",
+ .of_match_table = vsc73xx_of_match,
+ },
+};
+module_platform_driver(vsc73xx_platform_driver);
+
+MODULE_AUTHOR("Pawel Dembicki <paweldembicki@gmail.com>");
+MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 Platform driver");
+MODULE_LICENSE("GPL v2");
--
2.20.1
^ permalink raw reply related
* [PATCH v3 2/4] net: dsa: vsc73xx: Split vsc73xx driver
From: Pawel Dembicki @ 2019-07-04 22:29 UTC (permalink / raw)
Cc: Pawel Dembicki, linus.walleij, Andrew Lunn, Vivien Didelot,
Florian Fainelli, David S. Miller, Rob Herring, Mark Rutland,
netdev, devicetree, linux-kernel
In-Reply-To: <20190704222907.2888-1-paweldembicki@gmail.com>
This driver (currently) only takes control of the switch chip over
SPI and configures it to route packages around when connected to a
CPU port. But Vitesse chip support also parallel interface.
This patch split driver into two parts: core and spi. It is required
for add support to another managing interface.
Tested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Pawel Dembicki <paweldembicki@gmail.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
---
drivers/net/dsa/Kconfig | 11 +-
drivers/net/dsa/Makefile | 3 +-
...tesse-vsc73xx.c => vitesse-vsc73xx-core.c} | 170 +--------------
drivers/net/dsa/vitesse-vsc73xx-spi.c | 203 ++++++++++++++++++
drivers/net/dsa/vitesse-vsc73xx.h | 29 +++
5 files changed, 254 insertions(+), 162 deletions(-)
rename drivers/net/dsa/{vitesse-vsc73xx.c => vitesse-vsc73xx-core.c} (91%)
create mode 100644 drivers/net/dsa/vitesse-vsc73xx-spi.c
create mode 100644 drivers/net/dsa/vitesse-vsc73xx.h
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index b91e78e3598f..4ab2aa09e2e4 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -99,8 +99,8 @@ config NET_DSA_SMSC_LAN9303_MDIO
for MDIO managed mode.
config NET_DSA_VITESSE_VSC73XX
- tristate "Vitesse VSC7385/7388/7395/7398 support"
- depends on OF && SPI
+ tristate
+ depends on OF
depends on NET_DSA
select FIXED_PHY
select VITESSE_PHY
@@ -109,4 +109,11 @@ config NET_DSA_VITESSE_VSC73XX
This enables support for the Vitesse VSC7385, VSC7388,
VSC7395 and VSC7398 SparX integrated ethernet switches.
+config NET_DSA_VITESSE_VSC73XX_SPI
+ tristate "Vitesse VSC7385/7388/7395/7398 SPI mode support"
+ depends on SPI
+ select NET_DSA_VITESSE_VSC73XX
+ ---help---
+ This enables support for the Vitesse VSC7385, VSC7388, VSC7395
+ and VSC7398 SparX integrated ethernet switches in SPI managed mode.
endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index fefb6aaa82ba..117bf78be211 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -14,7 +14,8 @@ realtek-objs := realtek-smi.o rtl8366.o rtl8366rb.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
-obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx.o
+obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx-core.o
+obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX_SPI) += vitesse-vsc73xx-spi.o
obj-y += b53/
obj-y += microchip/
obj-y += mv88e6xxx/
diff --git a/drivers/net/dsa/vitesse-vsc73xx.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
similarity index 91%
rename from drivers/net/dsa/vitesse-vsc73xx.c
rename to drivers/net/dsa/vitesse-vsc73xx-core.c
index d4780610ea8a..10063f31d9a3 100644
--- a/drivers/net/dsa/vitesse-vsc73xx.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -10,10 +10,6 @@
* handling the switch in a memory-mapped manner by connecting to that external
* CPU's memory bus.
*
- * This driver (currently) only takes control of the switch chip over SPI and
- * configures it to route packages around when connected to a CPU port. The
- * chip has embedded PHYs and VLAN support so we model it using DSA.
- *
* Copyright (C) 2018 Linus Wallej <linus.walleij@linaro.org>
* Includes portions of code from the firmware uploader by:
* Copyright (C) 2009 Gabor Juhos <juhosg@openwrt.org>
@@ -24,8 +20,6 @@
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_mdio.h>
-#include <linux/platform_device.h>
-#include <linux/spi/spi.h>
#include <linux/bitops.h>
#include <linux/if_bridge.h>
#include <linux/etherdevice.h>
@@ -34,6 +28,8 @@
#include <linux/random.h>
#include <net/dsa.h>
+#include "vitesse-vsc73xx.h"
+
#define VSC73XX_BLOCK_MAC 0x1 /* Subblocks 0-4, 6 (CPU port) */
#define VSC73XX_BLOCK_ANALYZER 0x2 /* Only subblock 0 */
#define VSC73XX_BLOCK_MII 0x3 /* Subblocks 0 and 1 */
@@ -255,13 +251,6 @@
#define VSC73XX_GLORESET_PHY_RESET BIT(1)
#define VSC73XX_GLORESET_MASTER_RESET BIT(0)
-#define VSC73XX_CMD_MODE_READ 0
-#define VSC73XX_CMD_MODE_WRITE 1
-#define VSC73XX_CMD_MODE_SHIFT 4
-#define VSC73XX_CMD_BLOCK_SHIFT 5
-#define VSC73XX_CMD_BLOCK_MASK 0x7
-#define VSC73XX_CMD_SUBBLOCK_MASK 0xf
-
#define VSC7385_CLOCK_DELAY ((3 << 4) | 3)
#define VSC7385_CLOCK_DELAY_MASK ((3 << 4) | 3)
@@ -274,20 +263,6 @@
VSC73XX_ICPU_CTRL_CLK_EN | \
VSC73XX_ICPU_CTRL_SRST)
-/**
- * struct vsc73xx - VSC73xx state container
- */
-struct vsc73xx {
- struct device *dev;
- struct gpio_desc *reset;
- struct spi_device *spi;
- struct dsa_switch *ds;
- struct gpio_chip gc;
- u16 chipid;
- u8 addr[ETH_ALEN];
- struct mutex lock; /* Protects SPI traffic */
-};
-
#define IS_7385(a) ((a)->chipid == VSC73XX_CHIPID_ID_7385)
#define IS_7388(a) ((a)->chipid == VSC73XX_CHIPID_ID_7388)
#define IS_7395(a) ((a)->chipid == VSC73XX_CHIPID_ID_7395)
@@ -365,7 +340,7 @@ static const struct vsc73xx_counter vsc73xx_tx_counters[] = {
{ 29, "TxQoSClass3" }, /* non-standard counter */
};
-static int vsc73xx_is_addr_valid(u8 block, u8 subblock)
+int vsc73xx_is_addr_valid(u8 block, u8 subblock)
{
switch (block) {
case VSC73XX_BLOCK_MAC:
@@ -396,96 +371,18 @@ static int vsc73xx_is_addr_valid(u8 block, u8 subblock)
return 0;
}
-
-static u8 vsc73xx_make_addr(u8 mode, u8 block, u8 subblock)
-{
- u8 ret;
-
- ret = (block & VSC73XX_CMD_BLOCK_MASK) << VSC73XX_CMD_BLOCK_SHIFT;
- ret |= (mode & 1) << VSC73XX_CMD_MODE_SHIFT;
- ret |= subblock & VSC73XX_CMD_SUBBLOCK_MASK;
-
- return ret;
-}
+EXPORT_SYMBOL(vsc73xx_is_addr_valid);
static int vsc73xx_read(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
u32 *val)
{
- struct spi_transfer t[2];
- struct spi_message m;
- u8 cmd[4];
- u8 buf[4];
- int ret;
-
- if (!vsc73xx_is_addr_valid(block, subblock))
- return -EINVAL;
-
- spi_message_init(&m);
-
- memset(&t, 0, sizeof(t));
-
- t[0].tx_buf = cmd;
- t[0].len = sizeof(cmd);
- spi_message_add_tail(&t[0], &m);
-
- t[1].rx_buf = buf;
- t[1].len = sizeof(buf);
- spi_message_add_tail(&t[1], &m);
-
- cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_READ, block, subblock);
- cmd[1] = reg;
- cmd[2] = 0;
- cmd[3] = 0;
-
- mutex_lock(&vsc->lock);
- ret = spi_sync(vsc->spi, &m);
- mutex_unlock(&vsc->lock);
-
- if (ret)
- return ret;
-
- *val = (buf[0] << 24) | (buf[1] << 16) | (buf[2] << 8) | buf[3];
-
- return 0;
+ return vsc->ops->read(vsc, block, subblock, reg, val);
}
static int vsc73xx_write(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
u32 val)
{
- struct spi_transfer t[2];
- struct spi_message m;
- u8 cmd[2];
- u8 buf[4];
- int ret;
-
- if (!vsc73xx_is_addr_valid(block, subblock))
- return -EINVAL;
-
- spi_message_init(&m);
-
- memset(&t, 0, sizeof(t));
-
- t[0].tx_buf = cmd;
- t[0].len = sizeof(cmd);
- spi_message_add_tail(&t[0], &m);
-
- t[1].tx_buf = buf;
- t[1].len = sizeof(buf);
- spi_message_add_tail(&t[1], &m);
-
- cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_WRITE, block, subblock);
- cmd[1] = reg;
-
- buf[0] = (val >> 24) & 0xff;
- buf[1] = (val >> 16) & 0xff;
- buf[2] = (val >> 8) & 0xff;
- buf[3] = val & 0xff;
-
- mutex_lock(&vsc->lock);
- ret = spi_sync(vsc->spi, &m);
- mutex_unlock(&vsc->lock);
-
- return ret;
+ return vsc->ops->write(vsc, block, subblock, reg, val);
}
static int vsc73xx_update_bits(struct vsc73xx *vsc, u8 block, u8 subblock,
@@ -1245,21 +1142,11 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
return 0;
}
-static int vsc73xx_probe(struct spi_device *spi)
+int vsc73xx_probe(struct vsc73xx *vsc)
{
- struct device *dev = &spi->dev;
- struct vsc73xx *vsc;
+ struct device *dev = vsc->dev;
int ret;
- vsc = devm_kzalloc(dev, sizeof(*vsc), GFP_KERNEL);
- if (!vsc)
- return -ENOMEM;
-
- spi_set_drvdata(spi, vsc);
- vsc->spi = spi_dev_get(spi);
- vsc->dev = dev;
- mutex_init(&vsc->lock);
-
/* Release reset, if any */
vsc->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
if (IS_ERR(vsc->reset)) {
@@ -1270,14 +1157,6 @@ static int vsc73xx_probe(struct spi_device *spi)
/* Wait 20ms according to datasheet table 245 */
msleep(20);
- spi->mode = SPI_MODE_0;
- spi->bits_per_word = 8;
- ret = spi_setup(spi);
- if (ret < 0) {
- dev_err(dev, "spi setup failed.\n");
- return ret;
- }
-
ret = vsc73xx_detect(vsc);
if (ret) {
dev_err(dev, "no chip found (%d)\n", ret);
@@ -1321,43 +1200,16 @@ static int vsc73xx_probe(struct spi_device *spi)
return 0;
}
+EXPORT_SYMBOL(vsc73xx_probe);
-static int vsc73xx_remove(struct spi_device *spi)
+int vsc73xx_remove(struct vsc73xx *vsc)
{
- struct vsc73xx *vsc = spi_get_drvdata(spi);
-
dsa_unregister_switch(vsc->ds);
gpiod_set_value(vsc->reset, 1);
return 0;
}
-
-static const struct of_device_id vsc73xx_of_match[] = {
- {
- .compatible = "vitesse,vsc7385",
- },
- {
- .compatible = "vitesse,vsc7388",
- },
- {
- .compatible = "vitesse,vsc7395",
- },
- {
- .compatible = "vitesse,vsc7398",
- },
- { },
-};
-MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
-
-static struct spi_driver vsc73xx_driver = {
- .probe = vsc73xx_probe,
- .remove = vsc73xx_remove,
- .driver = {
- .name = "vsc73xx",
- .of_match_table = vsc73xx_of_match,
- },
-};
-module_spi_driver(vsc73xx_driver);
+EXPORT_SYMBOL(vsc73xx_remove);
MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 driver");
diff --git a/drivers/net/dsa/vitesse-vsc73xx-spi.c b/drivers/net/dsa/vitesse-vsc73xx-spi.c
new file mode 100644
index 000000000000..e73c8fcddc9f
--- /dev/null
+++ b/drivers/net/dsa/vitesse-vsc73xx-spi.c
@@ -0,0 +1,203 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DSA driver for:
+ * Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+ *
+ * This driver takes control of the switch chip over SPI and
+ * configures it to route packages around when connected to a CPU port.
+ *
+ * Copyright (C) 2018 Linus Wallej <linus.walleij@linaro.org>
+ * Includes portions of code from the firmware uploader by:
+ * Copyright (C) 2009 Gabor Juhos <juhosg@openwrt.org>
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/spi/spi.h>
+
+#include "vitesse-vsc73xx.h"
+
+#define VSC73XX_CMD_SPI_MODE_READ 0
+#define VSC73XX_CMD_SPI_MODE_WRITE 1
+#define VSC73XX_CMD_SPI_MODE_SHIFT 4
+#define VSC73XX_CMD_SPI_BLOCK_SHIFT 5
+#define VSC73XX_CMD_SPI_BLOCK_MASK 0x7
+#define VSC73XX_CMD_SPI_SUBBLOCK_MASK 0xf
+
+/**
+ * struct vsc73xx_spi - VSC73xx SPI state container
+ */
+struct vsc73xx_spi {
+ struct spi_device *spi;
+ struct mutex lock; /* Protects SPI traffic */
+ struct vsc73xx vsc;
+};
+
+static const struct vsc73xx_ops vsc73xx_spi_ops;
+
+static u8 vsc73xx_make_addr(u8 mode, u8 block, u8 subblock)
+{
+ u8 ret;
+
+ ret =
+ (block & VSC73XX_CMD_SPI_BLOCK_MASK) << VSC73XX_CMD_SPI_BLOCK_SHIFT;
+ ret |= (mode & 1) << VSC73XX_CMD_SPI_MODE_SHIFT;
+ ret |= subblock & VSC73XX_CMD_SPI_SUBBLOCK_MASK;
+
+ return ret;
+}
+
+static int vsc73xx_spi_read(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+ u32 *val)
+{
+ struct vsc73xx_spi *vsc_spi = vsc->priv;
+ struct spi_transfer t[2];
+ struct spi_message m;
+ u8 cmd[4];
+ u8 buf[4];
+ int ret;
+
+ if (!vsc73xx_is_addr_valid(block, subblock))
+ return -EINVAL;
+
+ spi_message_init(&m);
+
+ memset(&t, 0, sizeof(t));
+
+ t[0].tx_buf = cmd;
+ t[0].len = sizeof(cmd);
+ spi_message_add_tail(&t[0], &m);
+
+ t[1].rx_buf = buf;
+ t[1].len = sizeof(buf);
+ spi_message_add_tail(&t[1], &m);
+
+ cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_SPI_MODE_READ, block, subblock);
+ cmd[1] = reg;
+ cmd[2] = 0;
+ cmd[3] = 0;
+
+ mutex_lock(&vsc_spi->lock);
+ ret = spi_sync(vsc_spi->spi, &m);
+ mutex_unlock(&vsc_spi->lock);
+
+ if (ret)
+ return ret;
+
+ *val = (buf[0] << 24) | (buf[1] << 16) | (buf[2] << 8) | buf[3];
+
+ return 0;
+}
+
+static int vsc73xx_spi_write(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+ u32 val)
+{
+ struct vsc73xx_spi *vsc_spi = vsc->priv;
+ struct spi_transfer t[2];
+ struct spi_message m;
+ u8 cmd[2];
+ u8 buf[4];
+ int ret;
+
+ if (!vsc73xx_is_addr_valid(block, subblock))
+ return -EINVAL;
+
+ spi_message_init(&m);
+
+ memset(&t, 0, sizeof(t));
+
+ t[0].tx_buf = cmd;
+ t[0].len = sizeof(cmd);
+ spi_message_add_tail(&t[0], &m);
+
+ t[1].tx_buf = buf;
+ t[1].len = sizeof(buf);
+ spi_message_add_tail(&t[1], &m);
+
+ cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_SPI_MODE_WRITE, block, subblock);
+ cmd[1] = reg;
+
+ buf[0] = (val >> 24) & 0xff;
+ buf[1] = (val >> 16) & 0xff;
+ buf[2] = (val >> 8) & 0xff;
+ buf[3] = val & 0xff;
+
+ mutex_lock(&vsc_spi->lock);
+ ret = spi_sync(vsc_spi->spi, &m);
+ mutex_unlock(&vsc_spi->lock);
+
+ return ret;
+}
+
+static int vsc73xx_spi_probe(struct spi_device *spi)
+{
+ struct device *dev = &spi->dev;
+ struct vsc73xx_spi *vsc_spi;
+ int ret;
+
+ vsc_spi = devm_kzalloc(dev, sizeof(*vsc_spi), GFP_KERNEL);
+ if (!vsc_spi)
+ return -ENOMEM;
+
+ spi_set_drvdata(spi, vsc_spi);
+ vsc_spi->spi = spi_dev_get(spi);
+ vsc_spi->vsc.dev = dev;
+ vsc_spi->vsc.priv = vsc_spi;
+ vsc_spi->vsc.ops = &vsc73xx_spi_ops;
+ mutex_init(&vsc_spi->lock);
+
+ spi->mode = SPI_MODE_0;
+ spi->bits_per_word = 8;
+ ret = spi_setup(spi);
+ if (ret < 0) {
+ dev_err(dev, "spi setup failed.\n");
+ return ret;
+ }
+
+ return vsc73xx_probe(&vsc_spi->vsc);
+}
+
+static int vsc73xx_spi_remove(struct spi_device *spi)
+{
+ struct vsc73xx_spi *vsc_spi = spi_get_drvdata(spi);
+
+ return vsc73xx_remove(&vsc_spi->vsc);
+}
+
+static const struct vsc73xx_ops vsc73xx_spi_ops = {
+ .read = vsc73xx_spi_read,
+ .write = vsc73xx_spi_write,
+};
+
+static const struct of_device_id vsc73xx_of_match[] = {
+ {
+ .compatible = "vitesse,vsc7385",
+ },
+ {
+ .compatible = "vitesse,vsc7388",
+ },
+ {
+ .compatible = "vitesse,vsc7395",
+ },
+ {
+ .compatible = "vitesse,vsc7398",
+ },
+ { },
+};
+MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
+
+static struct spi_driver vsc73xx_spi_driver = {
+ .probe = vsc73xx_spi_probe,
+ .remove = vsc73xx_spi_remove,
+ .driver = {
+ .name = "vsc73xx-spi",
+ .of_match_table = vsc73xx_of_match,
+ },
+};
+module_spi_driver(vsc73xx_spi_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 SPI driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/dsa/vitesse-vsc73xx.h b/drivers/net/dsa/vitesse-vsc73xx.h
new file mode 100644
index 000000000000..7478f8d4e0a9
--- /dev/null
+++ b/drivers/net/dsa/vitesse-vsc73xx.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/device.h>
+#include <linux/etherdevice.h>
+#include <linux/gpio/driver.h>
+
+/**
+ * struct vsc73xx - VSC73xx state container
+ */
+struct vsc73xx {
+ struct device *dev;
+ struct gpio_desc *reset;
+ struct dsa_switch *ds;
+ struct gpio_chip gc;
+ u16 chipid;
+ u8 addr[ETH_ALEN];
+ const struct vsc73xx_ops *ops;
+ void *priv;
+};
+
+struct vsc73xx_ops {
+ int (*read)(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+ u32 *val);
+ int (*write)(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+ u32 val);
+};
+
+int vsc73xx_is_addr_valid(u8 block, u8 subblock);
+int vsc73xx_probe(struct vsc73xx *vsc);
+int vsc73xx_remove(struct vsc73xx *vsc);
--
2.20.1
^ permalink raw reply related
* Re: [PATCH net-next 0/9] net: hns3: some cleanups & bugfixes
From: Jakub Kicinski @ 2019-07-04 22:13 UTC (permalink / raw)
To: Huazhong Tan
Cc: davem, netdev, linux-kernel, salil.mehta, yisen.zhuang, linuxarm
In-Reply-To: <1562249068-40176-1-git-send-email-tanhuazhong@huawei.com>
On Thu, 4 Jul 2019 22:04:19 +0800, Huazhong Tan wrote:
> This patch-set includes cleanups and bugfixes for
> the HNS3 ethernet controller driver.
>
> [patch 1/9] fixes VF's broadcast promisc mode not enabled after
> initializing.
>
> [patch 2/9] adds hints for fibre port not support flow control.
>
> [patch 3/9] fixes a port capbility updating issue.
>
> [patch 4/9 - 9/9] adds some cleanups for HNS3 driver.
For the unsigned "fixes" it seems it may have been easier to fix the
macroes than the users, but perhaps that's hard. Series looks
unobjectionable :)
^ permalink raw reply
* Re: [PATCH net-next v2 4/4] qed*: Add devlink support for configuration attributes.
From: Jakub Kicinski @ 2019-07-04 22:07 UTC (permalink / raw)
To: Sudarsana Reddy Kalluru; +Cc: davem, netdev, mkalderon, aelior, Jiri Pirko
In-Reply-To: <20190704132011.13600-5-skalluru@marvell.com>
On Thu, 4 Jul 2019 06:20:11 -0700, Sudarsana Reddy Kalluru wrote:
> This patch adds implementation for devlink callbacks for reading and
> configuring the device attributes.
>
> Signed-off-by: Sudarsana Reddy Kalluru <skalluru@marvell.com>
> Signed-off-by: Ariel Elior <aelior@marvell.com>
> ---
> Documentation/networking/devlink-params-qede.txt | 72 ++++++++
> drivers/net/ethernet/qlogic/qed/qed_main.c | 38 +++++
> drivers/net/ethernet/qlogic/qede/qede.h | 3 +
> drivers/net/ethernet/qlogic/qede/qede_devlink.c | 202 ++++++++++++++++++++++-
> drivers/net/ethernet/qlogic/qede/qede_devlink.h | 23 +++
> include/linux/qed/qed_if.h | 16 ++
> 6 files changed, 353 insertions(+), 1 deletion(-)
> create mode 100644 Documentation/networking/devlink-params-qede.txt
>
> diff --git a/Documentation/networking/devlink-params-qede.txt b/Documentation/networking/devlink-params-qede.txt
> new file mode 100644
> index 0000000..f78a993
> --- /dev/null
> +++ b/Documentation/networking/devlink-params-qede.txt
> @@ -0,0 +1,72 @@
> +enable_sriov [DEVICE, GENERIC]
> + Configuration mode: Permanent
> +
> +iwarp_cmt [DEVICE, DRIVER-SPECIFIC]
> + Enable iWARP support over 100G device (CMT mode).
> + Type: Boolean
> + Configuration mode: runtime
> +
> +entity_id [DEVICE, DRIVER-SPECIFIC]
> + Set the entity ID value to be used for this device
> + while reading/configuring the devlink attributes.
> + Type: u8
> + Configuration mode: runtime
Can you explain what this is?
> +device_capabilities [DEVICE, DRIVER-SPECIFIC]
> + Set the entity ID value to be used for this device
> + while reading/configuring the devlink attributes.
> + Type: u8
> + Configuration mode: runtime
Looks like you copied the previous text here.
> +mf_mode [DEVICE, DRIVER-SPECIFIC]
> + Configure Multi Function mode for the device.
> + Supported MF modes and the assoicated values are,
> + MF allowed(0), Default(1), SPIO4(2), NPAR1.0(3),
> + NPAR1.5(4), NPAR2.0(5), BD(6) and UFP(7)
NPAR should have a proper API in devlink port, what are the other modes?
> + Type: u8
> + Configuration mode: Permanent
> +
> +dcbx_mode [PORT, DRIVER-SPECIFIC]
> + Configure DCBX mode for the device.
> + Supported dcbx modes are,
> + Disabled(0), IEEE(1), CEE(2) and Dynamic(3)
> + Type: u8
> + Configuration mode: Permanent
Why is this a permanent parameter?
> +preboot_oprom [PORT, DRIVER-SPECIFIC]
> + Enable Preboot Option ROM.
> + Type: Boolean
> + Configuration mode: Permanent
This should definitely not be a driver specific toggle.
> +preboot_boot_protocol [PORT, DRIVER-SPECIFIC]
> + Configure preboot Boot protocol.
> + Possible values are,
> + PXE(0), iSCSI Boot(3), FCoE Boot(4) and NONE(7)
> + Type: u8
> + Configuration mode: Permanent
Ditto.
> +preboot_vlan [PORT, DRIVER-SPECIFIC]
> + Preboot VLAN.
> + Type: u16
> + Configuration mode: Permanent
> +
> +preboot_vlan_value [PORT, DRIVER-SPECIFIC]
> + Configure Preboot VLAN value.
> + Type: u16
> + Configuration mode: Permanent
And these.
> +mba_delay_time [PORT, DRIVER-SPECIFIC]
> + Configure MBA Delay Time. Supported range is [0-15].
> + Type: u8
> + Configuration mode: Permanent
> +
> +mba_setup_hot_key [PORT, DRIVER-SPECIFIC]
> + Configure MBA setup Hot Key. Possible values are,
> + Ctrl S(0) and Ctrl B(1).
> + Type: u8
> + Configuration mode: Permanent
> +
> +mba_hide_setup_prompt [PORT, DRIVER-SPECIFIC]
> + Configure MBA hide setup prompt.
> + Type: Boolean
> + Configuration mode: Permanent
^ permalink raw reply
* NEIGH: BUG, double timer add, state is 8
From: Marek Majkowski @ 2019-07-04 21:59 UTC (permalink / raw)
To: David Miller, dsahern; +Cc: netdev, kernel-team
Morning,
I found a way to hit an obscure BUG in the
net/core/neighbour.c:neigh_add_timer(), by piping two carefully
crafted messages into AF_NETLINK socket.
https://github.com/torvalds/linux/blob/v5.2-rc7/net/core/neighbour.c#L259
if (unlikely(mod_timer(&n->timer, when))) {
printk("NEIGH: BUG, double timer add, state is %x\n", n->nud_state);
dump_stack();
}
The repro is here:
https://gist.github.com/majek/d70297b9d72bc2e2b82145e122722a0c
wget https://gist.githubusercontent.com/majek/d70297b9d72bc2e2b82145e122722a0c/raw/9e140bcedecc28d722022f1da142a379a9b7a7b0/double_timer_add_bug.c
You need root for AF_NETLINK socket. I would lie if I said I
understand what these netlink messages actually do.
Tested under virtme, with 5.2-rc7 kernel.
Full stack trace:
4,147643,57161310899,-;NEIGH: BUG, double timer add, state is 8
4,147644,57161311114,-;CPU: 0 PID: 266 Comm: xxx Not tainted 5.2.0-rc7kvm+ #6
4,147645,57161311260,-;Hardware name: QEMU Standard PC (i440FX + PIIX,
1996), BIOS 1.10.2-1ubuntu1 04/01/2014
4,147646,57161311401,-;Call Trace:
4,147647,57161311616,-; dump_stack (linux/lib/dump_stack.c:115)
4,147648,57161311771,-; neigh_add_timer
(linux/net/core/neighbour.c:265 linux/net/core/neighbour.c:259)
4,147649,57161311878,-; __neigh_event_send (linux/net/core/neighbour.c:1143)
4,147650,57161312043,-; ? lockdep_hardirqs_on
(linux/kernel/locking/lockdep.c:3218
linux/kernel/locking/lockdep.c:3263)
4,147651,57161312205,-; ? __local_bh_enable_ip
(linux/arch/x86/include/asm/paravirt.h:777 linux/kernel/softirq.c:194)
4,147652,57161312311,-; ? neigh_lookup
(linux/include/linux/rcupdate.h:213 linux/include/linux/rcupdate.h:680
linux/net/core/neighbour.c:539)
4,147653,57161312454,-; ? trace_hardirqs_on
(linux/kernel/trace/trace_preemptirq.c:32)
4,147654,57161312579,-; ? neigh_lookup (linux/net/core/neighbour.c:1106)
4,147655,57161312700,-; ? __local_bh_enable_ip
(linux/arch/x86/include/asm/paravirt.h:777 linux/kernel/softirq.c:194)
4,147656,57161312804,-; ? neigh_lookup (linux/net/core/neighbour.c:541)
4,147657,57161312949,-; ? udp_gro_receive.cold.8 (linux/net/ipv4/arp.c:216)
4,147658,57161313087,-; neigh_add (linux/include/net/neighbour.h:445
linux/net/core/neighbour.c:1963)
4,147659,57161313216,-; ? neigh_xmit (linux/net/core/neighbour.c:1850)
4,147660,57161313346,-; ? __sanitizer_cov_trace_const_cmp8
(linux/kernel/kcov.c:198)
4,147661,57161313522,-; ? neigh_xmit (linux/net/core/neighbour.c:1850)
4,147662,57161313644,-; rtnetlink_rcv_msg (linux/net/core/rtnetlink.c:5214)
4,147663,57161313751,-; ? rtnetlink_put_metrics
(linux/net/core/rtnetlink.c:5117)
4,147664,57161313875,-; ? find_held_lock (linux/kernel/locking/lockdep.c:3898)
4,147665,57161314023,-; netlink_rcv_skb (linux/net/netlink/af_netlink.c:2483)
4,147666,57161314152,-; ? rtnetlink_put_metrics
(linux/net/core/rtnetlink.c:5117)
4,147667,57161314311,-; ? netlink_ack (linux/net/netlink/af_netlink.c:2459)
4,147668,57161314416,-; ? netlink_deliver_tap
(linux/net/netlink/af_netlink.c:333)
4,147669,57161314538,-; rtnetlink_rcv (linux/net/core/rtnetlink.c:5233)
4,147670,57161314701,-; netlink_unicast
(linux/net/netlink/af_netlink.c:1308
linux/net/netlink/af_netlink.c:1333)
4,147671,57161314811,-; ? netlink_attachskb
(linux/net/netlink/af_netlink.c:1318)
4,147672,57161315093,-; ? _copy_from_iter_full (linux/lib/iov_iter.c:780)
4,147673,57161315239,-; netlink_sendmsg (linux/net/netlink/af_netlink.c:1922)
4,147674,57161315349,-; ? netlink_unicast (linux/net/netlink/af_netlink.c:1848)
4,147675,57161315543,-; ? apparmor_socket_sendmsg
(linux/security/apparmor/lsm.c:937)
4,147676,57161315690,-; ? netlink_unicast (linux/net/netlink/af_netlink.c:1848)
4,147677,57161315838,-; sock_sendmsg (linux/net/socket.c:646
linux/net/socket.c:665)
4,147678,57161315983,-; ___sys_sendmsg (linux/net/socket.c:2286)
4,147679,57161316105,-; ? trace_hardirqs_on
(linux/kernel/trace/trace_preemptirq.c:32)
4,147680,57161316247,-; ? copy_msghdr_from_user (linux/net/socket.c:2214)
4,147681,57161316361,-; ? __wake_up_common_lock (linux/kernel/sched/wait.c:125)
4,147682,57161316470,-; ? __wake_up_common (linux/kernel/sched/wait.c:112)
4,147683,57161316584,-; ? _raw_write_unlock_irq
(linux/arch/x86/include/asm/paravirt.h:777
linux/include/linux/rwlock_api_smp.h:267
linux/kernel/locking/spinlock.c:343)
4,147684,57161316757,-; ? trace_hardirqs_on
(linux/kernel/trace/trace_preemptirq.c:32)
4,147685,57161316867,-; ? __wake_up (linux/kernel/sched/wait.c:147)
4,147686,57161316985,-; ? netlink_bind (linux/net/netlink/af_netlink.c:981)
4,147687,57161317096,-; ? netlink_setsockopt
(linux/net/netlink/af_netlink.c:981)
4,147688,57161317223,-; ? kasan_check_read (linux/mm/kasan/common.c:95)
4,147689,57161317346,-; ? __fget_light
(linux/include/linux/compiler.h:194
linux/arch/x86/include/asm/atomic.h:31
linux/include/asm-generic/atomic-instrumented.h:27
linux/fs/file.c:770)
4,147690,57161317454,-; ? __sanitizer_cov_trace_const_cmp8
(linux/kernel/kcov.c:198)
4,147691,57161317561,-; ? sockfd_lookup_light (linux/net/socket.c:505)
4,147692,57161317685,-; __sys_sendmsg (linux/net/socket.c:2326)
4,147693,57161317821,-; ? __ia32_sys_shutdown (linux/net/socket.c:2312)
4,147694,57161317927,-; ? __fd_install
(linux/arch/x86/include/asm/preempt.h:84
linux/include/linux/rcupdate.h:724 linux/fs/file.c:608)
4,147695,57161318050,-; ? fd_install (linux/fs/file.c:614)
4,147696,57161318162,-; ? entry_SYSCALL_64_after_hwframe
(linux/arch/x86/entry/entry_64.S:177)
4,147697,57161318270,-; ? lockdep_hardirqs_on
(linux/kernel/locking/lockdep.c:3218
linux/kernel/locking/lockdep.c:3263)
4,147698,57161318413,-; __x64_sys_sendmsg (linux/net/socket.c:2331)
4,147699,57161318532,-; do_syscall_64 (linux/arch/x86/entry/common.c:301)
4,147700,57161318640,-; entry_SYSCALL_64_after_hwframe
(linux/arch/x86/entry/entry_64.S:177)
4,147701,57161318768,-;RIP: 0033:0x7f7c28863d04
4,147702,57161318901,-;Code: 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb
b5 0f 1f 80 00 00 00 00 48 8d 05 01 dc 2c 00 8b 00 85 c0 75 13 b8 2e
00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 f3 c3 66 90 41 54 55 41 89 d4
53 48 89 f5
All code
========
0: 00 f7 add %dh,%bh
2: d8 64 89 02 fsubs 0x2(%rcx,%rcx,4)
6: 48 c7 c0 ff ff ff ff mov $0xffffffffffffffff,%rax
d: eb b5 jmp 0xffffffffffffffc4
f: 0f 1f 80 00 00 00 00 nopl 0x0(%rax)
16: 48 8d 05 01 dc 2c 00 lea 0x2cdc01(%rip),%rax # 0x2cdc1e
1d: 8b 00 mov (%rax),%eax
1f: 85 c0 test %eax,%eax
21: 75 13 jne 0x36
23: b8 2e 00 00 00 mov $0x2e,%eax
28: 0f 05 syscall
2a:* 48 3d 00 f0 ff ff cmp $0xfffffffffffff000,%rax <-- trapping instruction
30: 77 54 ja 0x86
32: f3 c3 repz retq
34: 66 90 xchg %ax,%ax
36: 41 54 push %r12
38: 55 push %rbp
39: 41 89 d4 mov %edx,%r12d
3c: 53 push %rbx
3d: 48 89 f5 mov %rsi,%rbp
Code starting with the faulting instruction
===========================================
0: 48 3d 00 f0 ff ff cmp $0xfffffffffffff000,%rax
6: 77 54 ja 0x5c
8: f3 c3 repz retq
a: 66 90 xchg %ax,%ax
c: 41 54 push %r12
e: 55 push %rbp
f: 41 89 d4 mov %edx,%r12d
12: 53 push %rbx
13: 48 89 f5 mov %rsi,%rbp
4,147703,57161319051,-;RSP: 002b:00007ffd5901b648 EFLAGS: 00000246
ORIG_RAX: 000000000000002e
4,147704,57161319210,-;RAX: ffffffffffffffda RBX: 000000000000003b
RCX: 00007f7c28863d04
4,147705,57161319369,-;RDX: 0000000000000000 RSI: 00007ffd5901b710
RDI: 0000000000000006
4,147706,57161319495,-;RBP: 0000000000000006 R08: 0000000000000010
R09: 0000000000000000
4,147707,57161319664,-;R10: 00007ffd5901b758 R11: 0000000000000246
R12: 00007f7c28cc3f70
4,147708,57161319771,-;R13: 00007ffd5901d790 R14: 0000000000000000
R15: 00007ffd5901b750
Cheers,
Marek
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox