[PATCH net-next 0/5] net: dsa: bcm_sf2: Store rules in lists

[PATCH net-next 0/5] net: dsa: bcm_sf2: Store rules in lists

[Florian Fainelli]

Hi all,

This patch series changes the bcm-sf2 driver to keep a copy of the
inserted rules as opposed to using the HW as a storage area for a number
of reasons:

- this helps us with doing duplicate rule detection in a faster way, it
  would have required a full rule read before

- this helps with Pablo's on-going work to convert ethtool_rx_flow_spec
  to a more generic flow rule structure by having fewer code paths to
  convert to the new structure/helpers

- we need to cache copies to restore them during drive resumption,
  because depending on the low power mode the system has entered, the
  switch may have lost all of its context

Florian Fainelli (5):
  net: dsa: bcm_sf2: Keep copy of inserted rules
  net: dsa: bcm_sf2: Split rule handling from HW operation
  net: dsa: bcm_sf2: Restore CFP rules during system resume
  net: dsa: bcm_sf2: Get rid of unmarshalling functions
  net: systemport: Restore Broadcom tag match filters upon resume

 drivers/net/dsa/bcm_sf2.c                  |   6 +
 drivers/net/dsa/bcm_sf2.h                  |   3 +
 drivers/net/dsa/bcm_sf2_cfp.c              | 497 ++++++++-------------
 drivers/net/ethernet/broadcom/bcmsysport.c |  12 +
 drivers/net/ethernet/broadcom/bcmsysport.h |   1 +
 5 files changed, 204 insertions(+), 315 deletions(-)

-- 
2.17.1

[PATCH net-next 1/5] net: dsa: bcm_sf2: Keep copy of inserted rules

[Florian Fainelli]

We tried hard to use the hardware as a storage area, which made things
needlessly complex in that we had to both marshall and unmarshall the
ethtool_rx_flow_spec into what the CFP hardware understands but it did
not require any driver level allocations, so that was nice.

Keep a copy of the ethtool_rx_flow_spec rule we want to insert, and also
make sure we don't have a duplicate rule already. This greatly speeds up
the deletion time since we only need to clear the slice's valid bit and
not perform a full read.

This is a preparatory step for being able to restore rules upon system
resumption where the hardware loses its context partially or entirely.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 drivers/net/dsa/bcm_sf2.c     |   2 +
 drivers/net/dsa/bcm_sf2.h     |   2 +
 drivers/net/dsa/bcm_sf2_cfp.c | 144 +++++++++++++++++++++++++++++++---
 3 files changed, 137 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 2eb68769562c..89722dbfafb8 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -1061,6 +1061,7 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev)
 	spin_lock_init(&priv->indir_lock);
 	mutex_init(&priv->stats_mutex);
 	mutex_init(&priv->cfp.lock);
+	INIT_LIST_HEAD(&priv->cfp.rules_list);
 
 	/* CFP rule #0 cannot be used for specific classifications, flag it as
 	 * permanently used
@@ -1166,6 +1167,7 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev)
 
 	priv->wol_ports_mask = 0;
 	dsa_unregister_switch(priv->dev->ds);
+	bcm_sf2_cfp_exit(priv->dev->ds);
 	/* Disable all ports and interrupts */
 	bcm_sf2_sw_suspend(priv->dev->ds);
 	bcm_sf2_mdio_unregister(priv);
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index cc31e986e6e3..03444982c25e 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -56,6 +56,7 @@ struct bcm_sf2_cfp_priv {
 	DECLARE_BITMAP(used, CFP_NUM_RULES);
 	DECLARE_BITMAP(unique, CFP_NUM_RULES);
 	unsigned int rules_cnt;
+	struct list_head rules_list;
 };
 
 struct bcm_sf2_priv {
@@ -213,5 +214,6 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc);
 int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv);
+void bcm_sf2_cfp_exit(struct dsa_switch *ds);
 
 #endif /* __BCM_SF2_H */
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 47c5f272a084..29b6b4204662 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -20,6 +20,12 @@
 #include "bcm_sf2.h"
 #include "bcm_sf2_regs.h"
 
+struct cfp_rule {
+	int port;
+	struct ethtool_rx_flow_spec fs;
+	struct list_head next;
+};
+
 struct cfp_udf_slice_layout {
 	u8 slices[UDFS_PER_SLICE];
 	u32 mask_value;
@@ -515,6 +521,61 @@ static void bcm_sf2_cfp_slice_ipv6(struct bcm_sf2_priv *priv,
 	core_writel(priv, reg, offset);
 }
 
+static struct cfp_rule *bcm_sf2_cfp_rule_find(struct bcm_sf2_priv *priv,
+					      int port, u32 location)
+{
+	struct cfp_rule *rule = NULL;
+
+	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
+		if (rule->port == port && rule->fs.location == location)
+			break;
+	};
+
+	return rule;
+}
+
+static int bcm_sf2_cfp_rule_cmp(struct bcm_sf2_priv *priv, int port,
+				struct ethtool_rx_flow_spec *fs)
+{
+	struct cfp_rule *rule = NULL;
+	size_t fs_size = 0;
+	int ret = 1;
+
+	if (list_empty(&priv->cfp.rules_list))
+		return ret;
+
+	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
+		ret = 1;
+		if (rule->port != port)
+			continue;
+
+		if (rule->fs.flow_type != fs->flow_type ||
+		    rule->fs.ring_cookie != fs->ring_cookie ||
+		    rule->fs.m_ext.data[0] != fs->m_ext.data[0])
+			continue;
+
+		switch (fs->flow_type & ~FLOW_EXT) {
+		case TCP_V6_FLOW:
+		case UDP_V6_FLOW:
+			fs_size = sizeof(struct ethtool_tcpip6_spec);
+			break;
+		case TCP_V4_FLOW:
+		case UDP_V4_FLOW:
+			fs_size = sizeof(struct ethtool_tcpip4_spec);
+			break;
+		default:
+			continue;
+		}
+
+		ret = memcmp(&rule->fs.h_u, &fs->h_u, fs_size);
+		ret |= memcmp(&rule->fs.m_u, &fs->m_u, fs_size);
+		if (ret == 0)
+			break;
+	}
+
+	return ret;
+}
+
 static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 				     unsigned int port_num,
 				     unsigned int queue_num,
@@ -735,6 +796,7 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	__u64 ring_cookie = fs->ring_cookie;
 	unsigned int queue_num, port_num;
+	struct cfp_rule *rule = NULL;
 	int ret = -EINVAL;
 
 	/* Check for unsupported extensions */
@@ -750,6 +812,10 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	    fs->location > bcm_sf2_cfp_rule_size(priv))
 		return -EINVAL;
 
+	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
+	if (ret == 0)
+		return -EEXIST;
+
 	/* This rule is a Wake-on-LAN filter and we must specifically
 	 * target the CPU port in order for it to be working.
 	 */
@@ -775,6 +841,10 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	if (port_num >= 7)
 		port_num -= 1;
 
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
 	switch (fs->flow_type & ~FLOW_EXT) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
@@ -787,9 +857,19 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 						queue_num, fs);
 		break;
 	default:
+		ret = -EINVAL;
 		break;
 	}
 
+	if (ret) {
+		kfree(rule);
+		return ret;
+	}
+
+	rule->port = port;
+	memcpy(&rule->fs, fs, sizeof(*fs));
+	list_add_tail(&rule->next, &priv->cfp.rules_list);
+
 	return ret;
 }
 
@@ -833,6 +913,7 @@ static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
 static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 				u32 loc)
 {
+	struct cfp_rule *rule;
 	u32 next_loc = 0;
 	int ret;
 
@@ -843,6 +924,10 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (!test_bit(loc, priv->cfp.unique) || loc == 0)
 		return -EINVAL;
 
+	rule = bcm_sf2_cfp_rule_find(priv, port, loc);
+	if (!rule)
+		return -EINVAL;
+
 	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
 	if (ret)
 		return ret;
@@ -851,6 +936,9 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (next_loc)
 		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
 
+	list_del(&rule->next);
+	kfree(rule);
+
 	return ret;
 }
 
@@ -867,9 +955,9 @@ static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 	flow->m_ext.data[1] ^= cpu_to_be32(~0);
 }
 
-static int bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
-				    struct ethtool_tcpip4_spec *v4_spec,
-				    bool mask)
+static int __maybe_unused bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
+						   struct ethtool_tcpip4_spec *v4_spec,
+						   bool mask)
 {
 	u32 reg, offset, ipv4;
 	u16 src_dst_port;
@@ -969,9 +1057,10 @@ static int bcm_sf2_cfp_ipv4_rule_get(struct bcm_sf2_priv *priv, int port,
 	return bcm_sf2_cfp_unslice_ipv4(priv, v4_m_spec, true);
 }
 
-static int bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
-				     __be32 *ip6_addr, __be16 *port,
-				     bool mask)
+static int __maybe_unused bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
+						   __be32 *ip6_addr,
+						   __be16 *port,
+						   bool mask)
 {
 	u32 reg, tmp, offset;
 
@@ -1050,9 +1139,10 @@ static int bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
 	return 0;
 }
 
-static int bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv, int port,
-				     struct ethtool_rx_flow_spec *fs,
-				     u32 next_loc)
+static int __maybe_unused bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv,
+						    int port,
+						    struct ethtool_rx_flow_spec *fs,
+						    u32 next_loc)
 {
 	struct ethtool_tcpip6_spec *v6_spec = NULL, *v6_m_spec = NULL;
 	u32 reg;
@@ -1111,8 +1201,9 @@ static int bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv, int port,
 					&v6_m_spec->psrc, true);
 }
 
-static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
-				struct ethtool_rxnfc *nfc)
+static int __maybe_unused bcm_sf2_cfp_rule_get_hw(struct bcm_sf2_priv *priv,
+						  int port,
+						  struct ethtool_rxnfc *nfc)
 {
 	u32 reg, ipv4_or_chain_id;
 	unsigned int queue_num;
@@ -1174,6 +1265,25 @@ static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
 	return 0;
 }
 
+static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
+				struct ethtool_rxnfc *nfc)
+{
+	struct cfp_rule *rule;
+
+	rule = bcm_sf2_cfp_rule_find(priv, port, nfc->fs.location);
+	if (!rule)
+		return -EINVAL;
+
+	memcpy(&nfc->fs, &rule->fs, sizeof(rule->fs));
+
+	bcm_sf2_invert_masks(&nfc->fs);
+
+	/* Put the TCAM size here */
+	nfc->data = bcm_sf2_cfp_rule_size(priv);
+
+	return 0;
+}
+
 /* We implement the search doing a TCAM search operation */
 static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 				    int port, struct ethtool_rxnfc *nfc,
@@ -1302,3 +1412,15 @@ int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv)
 
 	return 0;
 }
+
+void bcm_sf2_cfp_exit(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	struct cfp_rule *rule, *n;
+
+	if (list_empty(&priv->cfp.rules_list))
+		return;
+
+	list_for_each_entry_safe_reverse(rule, n, &priv->cfp.rules_list, next)
+		bcm_sf2_cfp_rule_del(priv, rule->port, rule->fs.location);
+}
-- 
2.17.1

[PATCH net-next 2/5] net: dsa: bcm_sf2: Split rule handling from HW operation

[Florian Fainelli]

In preparation for restoring CFP rules during system wide system
suspend/resume where the hardware loses its context, split the rule
validation from its actual insertion as well as the rule removal from
its actual hardware deletion operation.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 89 +++++++++++++++++++++--------------
 1 file changed, 54 insertions(+), 35 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 29b6b4204662..396bfa43c2e1 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -789,32 +789,14 @@ static int bcm_sf2_cfp_ipv6_rule_set(struct bcm_sf2_priv *priv, int port,
 	return ret;
 }
 
-static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
-				struct ethtool_rx_flow_spec *fs)
+static int bcm_sf2_cfp_rule_insert(struct dsa_switch *ds, int port,
+				   struct ethtool_rx_flow_spec *fs)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	s8 cpu_port = ds->ports[port].cpu_dp->index;
 	__u64 ring_cookie = fs->ring_cookie;
 	unsigned int queue_num, port_num;
-	struct cfp_rule *rule = NULL;
-	int ret = -EINVAL;
-
-	/* Check for unsupported extensions */
-	if ((fs->flow_type & FLOW_EXT) && (fs->m_ext.vlan_etype ||
-	     fs->m_ext.data[1]))
-		return -EINVAL;
-
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    test_bit(fs->location, priv->cfp.used))
-		return -EBUSY;
-
-	if (fs->location != RX_CLS_LOC_ANY &&
-	    fs->location > bcm_sf2_cfp_rule_size(priv))
-		return -EINVAL;
-
-	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
-	if (ret == 0)
-		return -EEXIST;
+	int ret;
 
 	/* This rule is a Wake-on-LAN filter and we must specifically
 	 * target the CPU port in order for it to be working.
@@ -841,10 +823,6 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	if (port_num >= 7)
 		port_num -= 1;
 
-	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
-	if (!rule)
-		return -ENOMEM;
-
 	switch (fs->flow_type & ~FLOW_EXT) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
@@ -861,6 +839,38 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 		break;
 	}
 
+	return ret;
+}
+
+static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
+				struct ethtool_rx_flow_spec *fs)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	struct cfp_rule *rule = NULL;
+	int ret = -EINVAL;
+
+	/* Check for unsupported extensions */
+	if ((fs->flow_type & FLOW_EXT) && (fs->m_ext.vlan_etype ||
+	     fs->m_ext.data[1]))
+		return -EINVAL;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    test_bit(fs->location, priv->cfp.used))
+		return -EBUSY;
+
+	if (fs->location != RX_CLS_LOC_ANY &&
+	    fs->location > bcm_sf2_cfp_rule_size(priv))
+		return -EINVAL;
+
+	ret = bcm_sf2_cfp_rule_cmp(priv, port, fs);
+	if (ret == 0)
+		return -EEXIST;
+
+	rule = kzalloc(sizeof(*rule), GFP_KERNEL);
+	if (!rule)
+		return -ENOMEM;
+
+	ret = bcm_sf2_cfp_rule_insert(ds, port, fs);
 	if (ret) {
 		kfree(rule);
 		return ret;
@@ -910,13 +920,28 @@ static int bcm_sf2_cfp_rule_del_one(struct bcm_sf2_priv *priv, int port,
 	return 0;
 }
 
-static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
-				u32 loc)
+static int bcm_sf2_cfp_rule_remove(struct bcm_sf2_priv *priv, int port,
+				   u32 loc)
 {
-	struct cfp_rule *rule;
 	u32 next_loc = 0;
 	int ret;
 
+	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
+	if (ret)
+		return ret;
+
+	/* If this was an IPv6 rule, delete is companion rule too */
+	if (next_loc)
+		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
+
+	return ret;
+}
+
+static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port, u32 loc)
+{
+	struct cfp_rule *rule;
+	int ret;
+
 	/* Refuse deleting unused rules, and those that are not unique since
 	 * that could leave IPv6 rules with one of the chained rule in the
 	 * table.
@@ -928,13 +953,7 @@ static int bcm_sf2_cfp_rule_del(struct bcm_sf2_priv *priv, int port,
 	if (!rule)
 		return -EINVAL;
 
-	ret = bcm_sf2_cfp_rule_del_one(priv, port, loc, &next_loc);
-	if (ret)
-		return ret;
-
-	/* If this was an IPv6 rule, delete is companion rule too */
-	if (next_loc)
-		ret = bcm_sf2_cfp_rule_del_one(priv, port, next_loc, NULL);
+	ret = bcm_sf2_cfp_rule_remove(priv, port, loc);
 
 	list_del(&rule->next);
 	kfree(rule);
-- 
2.17.1

[PATCH net-next 3/5] net: dsa: bcm_sf2: Restore CFP rules during system resume

[Florian Fainelli]

The hardware can lose its context during system suspend, and depending
on the switch generation (7445 vs. 7278), while the rules are still
there, they will have their valid bit cleared (because that's the
fastest way for the HW to reset things). Just make sure we re-apply them
coming back from resume. The 7445 switch is an older version of the core
that has some quirky RAM technology requiring a delete then re-inser to
guarantee the RAM entries are properly latched.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 drivers/net/dsa/bcm_sf2.c     |  4 ++++
 drivers/net/dsa/bcm_sf2.h     |  1 +
 drivers/net/dsa/bcm_sf2_cfp.c | 36 +++++++++++++++++++++++++++++++++++
 3 files changed, 41 insertions(+)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 89722dbfafb8..d8b93043b789 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -710,6 +710,10 @@ static int bcm_sf2_sw_resume(struct dsa_switch *ds)
 		return ret;
 	}
 
+	ret = bcm_sf2_cfp_resume(ds);
+	if (ret)
+		return ret;
+
 	if (priv->hw_params.num_gphy == 1)
 		bcm_sf2_gphy_enable_set(ds, true);
 
diff --git a/drivers/net/dsa/bcm_sf2.h b/drivers/net/dsa/bcm_sf2.h
index 03444982c25e..faaef320ec48 100644
--- a/drivers/net/dsa/bcm_sf2.h
+++ b/drivers/net/dsa/bcm_sf2.h
@@ -215,5 +215,6 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc);
 int bcm_sf2_cfp_rst(struct bcm_sf2_priv *priv);
 void bcm_sf2_cfp_exit(struct dsa_switch *ds);
+int bcm_sf2_cfp_resume(struct dsa_switch *ds);
 
 #endif /* __BCM_SF2_H */
diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 396bfa43c2e1..5034e4f56fd5 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -1443,3 +1443,39 @@ void bcm_sf2_cfp_exit(struct dsa_switch *ds)
 	list_for_each_entry_safe_reverse(rule, n, &priv->cfp.rules_list, next)
 		bcm_sf2_cfp_rule_del(priv, rule->port, rule->fs.location);
 }
+
+int bcm_sf2_cfp_resume(struct dsa_switch *ds)
+{
+	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	struct cfp_rule *rule;
+	int ret = 0;
+	u32 reg;
+
+	if (list_empty(&priv->cfp.rules_list))
+		return ret;
+
+	reg = core_readl(priv, CORE_CFP_CTL_REG);
+	reg &= ~CFP_EN_MAP_MASK;
+	core_writel(priv, reg, CORE_CFP_CTL_REG);
+
+	ret = bcm_sf2_cfp_rst(priv);
+	if (ret)
+		return ret;
+
+	list_for_each_entry(rule, &priv->cfp.rules_list, next) {
+		ret = bcm_sf2_cfp_rule_remove(priv, rule->port,
+					      rule->fs.location);
+		if (ret) {
+			dev_err(ds->dev, "failed to remove rule\n");
+			return ret;
+		}
+
+		ret = bcm_sf2_cfp_rule_insert(ds, rule->port, &rule->fs);
+		if (ret) {
+			dev_err(ds->dev, "failed to restore rule\n");
+			return ret;
+		}
+	};
+
+	return ret;
+}
-- 
2.17.1

[PATCH net-next 4/5] net: dsa: bcm_sf2: Get rid of unmarshalling functions

[Florian Fainelli]

Now that we have migrated the CFP rule handling to a list with a
software copy, the delete/get operation just returns what is on the
list, no need to read from the hardware which is both slow and more
error prone.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 310 ----------------------------------
 1 file changed, 310 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 5034e4f56fd5..8f734abde7b3 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -974,316 +974,6 @@ static void bcm_sf2_invert_masks(struct ethtool_rx_flow_spec *flow)
 	flow->m_ext.data[1] ^= cpu_to_be32(~0);
 }
 
-static int __maybe_unused bcm_sf2_cfp_unslice_ipv4(struct bcm_sf2_priv *priv,
-						   struct ethtool_tcpip4_spec *v4_spec,
-						   bool mask)
-{
-	u32 reg, offset, ipv4;
-	u16 src_dst_port;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(3);
-	else
-		offset = CORE_CFP_DATA_PORT(3);
-
-	reg = core_readl(priv, offset);
-	/* src port [15:8] */
-	src_dst_port = reg << 8;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(2);
-	else
-		offset = CORE_CFP_DATA_PORT(2);
-
-	reg = core_readl(priv, offset);
-	/* src port [7:0] */
-	src_dst_port |= (reg >> 24);
-
-	v4_spec->pdst = cpu_to_be16(src_dst_port);
-	v4_spec->psrc = cpu_to_be16((u16)(reg >> 8));
-
-	/* IPv4 dst [15:8] */
-	ipv4 = (reg & 0xff) << 8;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(1);
-	else
-		offset = CORE_CFP_DATA_PORT(1);
-
-	reg = core_readl(priv, offset);
-	/* IPv4 dst [31:16] */
-	ipv4 |= ((reg >> 8) & 0xffff) << 16;
-	/* IPv4 dst [7:0] */
-	ipv4 |= (reg >> 24) & 0xff;
-	v4_spec->ip4dst = cpu_to_be32(ipv4);
-
-	/* IPv4 src [15:8] */
-	ipv4 = (reg & 0xff) << 8;
-
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(0);
-	else
-		offset = CORE_CFP_DATA_PORT(0);
-	reg = core_readl(priv, offset);
-
-	/* Once the TCAM is programmed, the mask reflects the slice number
-	 * being matched, don't bother checking it when reading back the
-	 * mask spec
-	 */
-	if (!mask && !(reg & SLICE_VALID))
-		return -EINVAL;
-
-	/* IPv4 src [7:0] */
-	ipv4 |= (reg >> 24) & 0xff;
-	/* IPv4 src [31:16] */
-	ipv4 |= ((reg >> 8) & 0xffff) << 16;
-	v4_spec->ip4src = cpu_to_be32(ipv4);
-
-	return 0;
-}
-
-static int bcm_sf2_cfp_ipv4_rule_get(struct bcm_sf2_priv *priv, int port,
-				     struct ethtool_rx_flow_spec *fs)
-{
-	struct ethtool_tcpip4_spec *v4_spec = NULL, *v4_m_spec = NULL;
-	u32 reg;
-	int ret;
-
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-
-	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
-	case IPPROTO_TCP:
-		fs->flow_type = TCP_V4_FLOW;
-		v4_spec = &fs->h_u.tcp_ip4_spec;
-		v4_m_spec = &fs->m_u.tcp_ip4_spec;
-		break;
-	case IPPROTO_UDP:
-		fs->flow_type = UDP_V4_FLOW;
-		v4_spec = &fs->h_u.udp_ip4_spec;
-		v4_m_spec = &fs->m_u.udp_ip4_spec;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	fs->m_ext.data[0] = cpu_to_be32((reg >> IP_FRAG_SHIFT) & 1);
-	v4_spec->tos = (reg >> IPTOS_SHIFT) & IPTOS_MASK;
-
-	ret = bcm_sf2_cfp_unslice_ipv4(priv, v4_spec, false);
-	if (ret)
-		return ret;
-
-	return bcm_sf2_cfp_unslice_ipv4(priv, v4_m_spec, true);
-}
-
-static int __maybe_unused bcm_sf2_cfp_unslice_ipv6(struct bcm_sf2_priv *priv,
-						   __be32 *ip6_addr,
-						   __be16 *port,
-						   bool mask)
-{
-	u32 reg, tmp, offset;
-
-	/* C-Tag		[31:24]
-	 * UDF_n_B8		[23:8] (port)
-	 * UDF_n_B7 (upper)	[7:0] (addr[15:8])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(4);
-	else
-		offset = CORE_CFP_DATA_PORT(4);
-	reg = core_readl(priv, offset);
-	*port = cpu_to_be32(reg) >> 8;
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B7 (lower)	[31:24] (addr[7:0])
-	 * UDF_n_B6		[23:8] (addr[31:16])
-	 * UDF_n_B5 (upper)	[7:0] (addr[47:40])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(3);
-	else
-		offset = CORE_CFP_DATA_PORT(3);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[3] = cpu_to_be32(tmp);
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B5 (lower)	[31:24] (addr[39:32])
-	 * UDF_n_B4		[23:8] (addr[63:48])
-	 * UDF_n_B3 (upper)	[7:0] (addr[79:72])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(2);
-	else
-		offset = CORE_CFP_DATA_PORT(2);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[2] = cpu_to_be32(tmp);
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B3 (lower)	[31:24] (addr[71:64])
-	 * UDF_n_B2		[23:8] (addr[95:80])
-	 * UDF_n_B1 (upper)	[7:0] (addr[111:104])
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(1);
-	else
-		offset = CORE_CFP_DATA_PORT(1);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[1] = cpu_to_be32(tmp);
-	tmp = (u32)(reg & 0xff) << 8;
-
-	/* UDF_n_B1 (lower)	[31:24] (addr[103:96])
-	 * UDF_n_B0		[23:8] (addr[127:112])
-	 * Reserved		[7:4]
-	 * Slice ID		[3:2]
-	 * Slice valid		[1:0]
-	 */
-	if (mask)
-		offset = CORE_CFP_MASK_PORT(0);
-	else
-		offset = CORE_CFP_DATA_PORT(0);
-	reg = core_readl(priv, offset);
-	tmp |= (reg >> 24) & 0xff;
-	tmp |= (u32)((reg >> 8) << 16);
-	ip6_addr[0] = cpu_to_be32(tmp);
-
-	if (!mask && !(reg & SLICE_VALID))
-		return -EINVAL;
-
-	return 0;
-}
-
-static int __maybe_unused bcm_sf2_cfp_ipv6_rule_get(struct bcm_sf2_priv *priv,
-						    int port,
-						    struct ethtool_rx_flow_spec *fs,
-						    u32 next_loc)
-{
-	struct ethtool_tcpip6_spec *v6_spec = NULL, *v6_m_spec = NULL;
-	u32 reg;
-	int ret;
-
-	/* UDPv6 and TCPv6 both use ethtool_tcpip6_spec so we are fine
-	 * assuming tcp_ip6_spec here being an union.
-	 */
-	v6_spec = &fs->h_u.tcp_ip6_spec;
-	v6_m_spec = &fs->m_u.tcp_ip6_spec;
-
-	/* Read the second half first */
-	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6dst, &v6_spec->pdst,
-				       false);
-	if (ret)
-		return ret;
-
-	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6dst,
-				       &v6_m_spec->pdst, true);
-	if (ret)
-		return ret;
-
-	/* Read last to avoid next entry clobbering the results during search
-	 * operations. We would not have the port enabled for this rule, so
-	 * don't bother checking it.
-	 */
-	(void)core_readl(priv, CORE_CFP_DATA_PORT(7));
-
-	/* The slice number is valid, so read the rule we are chained from now
-	 * which is our first half.
-	 */
-	bcm_sf2_cfp_rule_addr_set(priv, next_loc);
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
-	if (ret)
-		return ret;
-
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-
-	switch ((reg & IPPROTO_MASK) >> IPPROTO_SHIFT) {
-	case IPPROTO_TCP:
-		fs->flow_type = TCP_V6_FLOW;
-		break;
-	case IPPROTO_UDP:
-		fs->flow_type = UDP_V6_FLOW;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	ret = bcm_sf2_cfp_unslice_ipv6(priv, v6_spec->ip6src, &v6_spec->psrc,
-				       false);
-	if (ret)
-		return ret;
-
-	return bcm_sf2_cfp_unslice_ipv6(priv, v6_m_spec->ip6src,
-					&v6_m_spec->psrc, true);
-}
-
-static int __maybe_unused bcm_sf2_cfp_rule_get_hw(struct bcm_sf2_priv *priv,
-						  int port,
-						  struct ethtool_rxnfc *nfc)
-{
-	u32 reg, ipv4_or_chain_id;
-	unsigned int queue_num;
-	int ret;
-
-	bcm_sf2_cfp_rule_addr_set(priv, nfc->fs.location);
-
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | ACT_POL_RAM);
-	if (ret)
-		return ret;
-
-	reg = core_readl(priv, CORE_ACT_POL_DATA0);
-
-	ret = bcm_sf2_cfp_op(priv, OP_SEL_READ | TCAM_SEL);
-	if (ret)
-		return ret;
-
-	/* Extract the destination port */
-	nfc->fs.ring_cookie = fls((reg >> DST_MAP_IB_SHIFT) &
-				  DST_MAP_IB_MASK) - 1;
-
-	/* There is no Port 6, so we compensate for that here */
-	if (nfc->fs.ring_cookie >= 6)
-		nfc->fs.ring_cookie++;
-	nfc->fs.ring_cookie *= SF2_NUM_EGRESS_QUEUES;
-
-	/* Extract the destination queue */
-	queue_num = (reg >> NEW_TC_SHIFT) & NEW_TC_MASK;
-	nfc->fs.ring_cookie += queue_num;
-
-	/* Extract the L3_FRAMING or CHAIN_ID */
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(6));
-
-	/* With IPv6 rules this would contain a non-zero chain ID since
-	 * we reserve entry 0 and it cannot be used. So if we read 0 here
-	 * this means an IPv4 rule.
-	 */
-	ipv4_or_chain_id = (reg >> L3_FRAMING_SHIFT) & 0xff;
-	if (ipv4_or_chain_id == 0)
-		ret = bcm_sf2_cfp_ipv4_rule_get(priv, port, &nfc->fs);
-	else
-		ret = bcm_sf2_cfp_ipv6_rule_get(priv, port, &nfc->fs,
-						ipv4_or_chain_id);
-	if (ret)
-		return ret;
-
-	/* Read last to avoid next entry clobbering the results during search
-	 * operations
-	 */
-	reg = core_readl(priv, CORE_CFP_DATA_PORT(7));
-	if (!(reg & 1 << port))
-		return -EINVAL;
-
-	bcm_sf2_invert_masks(&nfc->fs);
-
-	/* Put the TCAM size here */
-	nfc->data = bcm_sf2_cfp_rule_size(priv);
-
-	return 0;
-}
-
 static int bcm_sf2_cfp_rule_get(struct bcm_sf2_priv *priv, int port,
 				struct ethtool_rxnfc *nfc)
 {
-- 
2.17.1

[PATCH net-next 5/5] net: systemport: Restore Broadcom tag match filters upon resume

[Florian Fainelli]

Some of the system suspend states that we support wipe out entirely the
HW contents. If we had a Wake-on-LAN filter programmed prior to going
into suspend, but we did not actually wake-up from Wake-on-LAN and
instead used a deeper suspend state, make sure we restore the CID number
that we need to match against.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 12 ++++++++++++
 drivers/net/ethernet/broadcom/bcmsysport.h |  1 +
 2 files changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 0e2d99c737e3..2e60dda32adc 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1068,6 +1068,7 @@ static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
 
 static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 {
+	unsigned int index;
 	u32 reg;
 
 	/* Disable RXCHK, active filters and Broadcom tag matching */
@@ -1076,6 +1077,15 @@ static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 		 RXCHK_BRCM_TAG_MATCH_SHIFT | RXCHK_EN | RXCHK_BRCM_TAG_EN);
 	rxchk_writel(priv, reg, RXCHK_CONTROL);
 
+	/* Make sure we restore correct CID index in case HW lost
+	 * its context during deep idle state
+	 */
+	for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+		rxchk_writel(priv, priv->filters_loc[index] <<
+			     RXCHK_BRCM_TAG_CID_SHIFT, RXCHK_BRCM_TAG(index));
+		rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
+	}
+
 	/* Clear the MagicPacket detection logic */
 	mpd_enable_set(priv, false);
 
@@ -2189,6 +2199,7 @@ static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
 	rxchk_writel(priv, reg, RXCHK_BRCM_TAG(index));
 	rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
 
+	priv->filters_loc[index] = nfc->fs.location;
 	set_bit(index, priv->filters);
 
 	return 0;
@@ -2208,6 +2219,7 @@ static int bcm_sysport_rule_del(struct bcm_sysport_priv *priv,
 	 * be taken care of during suspend time by bcm_sysport_suspend_to_wol
 	 */
 	clear_bit(index, priv->filters);
+	priv->filters_loc[index] = 0;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index a7a230884a87..7a0b7bfedd19 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -786,6 +786,7 @@ struct bcm_sysport_priv {
 	/* Ethtool */
 	u32			msg_enable;
 	DECLARE_BITMAP(filters, RXCHK_BRCM_TAG_MAX);
+	u32			filters_loc[RXCHK_BRCM_TAG_MAX];
 
 	struct bcm_sysport_stats64	stats64;
 
-- 
2.17.1

Re: [PATCH net-next 0/5] net: dsa: bcm_sf2: Store rules in lists

[David Miller]

From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue,  6 Nov 2018 12:58:36 -0800

> Hi all,
> 
> This patch series changes the bcm-sf2 driver to keep a copy of the
> inserted rules as opposed to using the HW as a storage area for a number
> of reasons:
> 
> - this helps us with doing duplicate rule detection in a faster way, it
>   would have required a full rule read before
> 
> - this helps with Pablo's on-going work to convert ethtool_rx_flow_spec
>   to a more generic flow rule structure by having fewer code paths to
>   convert to the new structure/helpers
> 
> - we need to cache copies to restore them during drive resumption,
>   because depending on the low power mode the system has entered, the
>   switch may have lost all of its context

Looks good to me, series applied and build testing right now.

I will say that the ethtool flow spec comparison should probably
eventually be broken out into a helper function places somewhere
common.  It's very likely this approach, and thus the helper, can
be used by other drivers in a similar situation.

Thanks.

Re: [PATCH net-next 0/5] net: dsa: bcm_sf2: Store rules in lists

[Florian Fainelli]

On 11/6/18 3:06 PM, David Miller wrote:
> From: Florian Fainelli <f.fainelli@gmail.com>
> Date: Tue,  6 Nov 2018 12:58:36 -0800
> 
>> Hi all,
>>
>> This patch series changes the bcm-sf2 driver to keep a copy of the
>> inserted rules as opposed to using the HW as a storage area for a number
>> of reasons:
>>
>> - this helps us with doing duplicate rule detection in a faster way, it
>>   would have required a full rule read before
>>
>> - this helps with Pablo's on-going work to convert ethtool_rx_flow_spec
>>   to a more generic flow rule structure by having fewer code paths to
>>   convert to the new structure/helpers
>>
>> - we need to cache copies to restore them during drive resumption,
>>   because depending on the low power mode the system has entered, the
>>   switch may have lost all of its context
> 
> Looks good to me, series applied and build testing right now.
> 
> I will say that the ethtool flow spec comparison should probably
> eventually be broken out into a helper function places somewhere
> common.  It's very likely this approach, and thus the helper, can
> be used by other drivers in a similar situation.

Sure, that could be done, I will check with Pablo how he wants to
approach that as well since he is reworking how flow rules are
represented. Thanks!
-- 
Florian