From 52849bcf0029ccc553be304e4f804938a39112e2 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 Oct 2021 14:40:36 +0300 Subject: net: mscc: ocelot: avoid overflowing the PTP timestamp FIFO PTP packets with 2-step TX timestamp requests are matched to packets based on the egress port number and a 6-bit timestamp identifier. All PTP timestamps are held in a common FIFO that is 128 entry deep. This patch ensures that back-to-back timestamping requests cannot exceed the hardware FIFO capacity. If that happens, simply send the packets without requesting a TX timestamp to be taken (in the case of felix, since the DSA API has a void return code in ds->ops->port_txtstamp) or drop them (in the case of ocelot). I've moved the ts_id_lock from a per-port basis to a per-switch basis, because we need separate accounting for both numbers of PTP frames in flight. And since we need locking to inc/dec the per-switch counter, that also offers protection for the per-port counter and hence there is no reason to have a per-port counter anymore. Fixes: 4e3b0468e6d7 ("net: mscc: PTP Hardware Clock (PHC) support") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'drivers/net/dsa/ocelot/felix.c') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index a3a9636430d6..50ef20724958 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1291,8 +1291,12 @@ static void felix_txtstamp(struct dsa_switch *ds, int port, if (!ocelot->ptp) return; - if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) + if (ocelot_port_txtstamp_request(ocelot, port, skb, &clone)) { + dev_err_ratelimited(ds->dev, + "port %d delivering skb without TX timestamp\n", + port); return; + } if (clone) OCELOT_SKB_CB(skb)->clone = clone; -- cgit v1.2.3 From 49f885b2d97093451410e7279aa29d81e094e108 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 Oct 2021 14:40:41 +0300 Subject: net: dsa: tag_ocelot_8021q: break circular dependency with ocelot switch lib Michael reported that when using the "ocelot-8021q" tagging protocol, the switch driver module must be manually loaded before the tagging protocol can be loaded/is available. This appears to be the same problem described here: https://lore.kernel.org/netdev/20210908220834.d7gmtnwrorhharna@skbuf/ where due to the fact that DSA tagging protocols make use of symbols exported by the switch drivers, circular dependencies appear and this breaks module autoloading. The ocelot_8021q driver needs the ocelot_can_inject() and ocelot_port_inject_frame() functions from the switch library. Previously the wrong approach was taken to solve that dependency: shims were provided for the case where the ocelot switch library was compiled out, but that turns out to be insufficient, because the dependency when the switch lib _is_ compiled is problematic too. We cannot declare ocelot_can_inject() and ocelot_port_inject_frame() as static inline functions, because these access I/O functions like __ocelot_write_ix() which is called by ocelot_write_rix(). Making those static inline basically means exposing the whole guts of the ocelot switch library, not ideal... We already have one tagging protocol driver which calls into the switch driver during xmit but not using any exported symbol: sja1105_defer_xmit. We can do the same thing here: create a kthread worker and one work item per skb, and let the switch driver itself do the register accesses to send the skb, and then consume it. Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Reported-by: Michael Walle Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 96 ++++++++++++++++++++++++++++++++++++++++-- drivers/net/dsa/ocelot/felix.h | 1 + include/linux/dsa/ocelot.h | 12 ++++++ include/soc/mscc/ocelot.h | 27 ------------ net/dsa/Kconfig | 2 - net/dsa/tag_ocelot_8021q.c | 38 +++++++++++------ 6 files changed, 130 insertions(+), 46 deletions(-) (limited to 'drivers/net/dsa/ocelot/felix.c') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 50ef20724958..f8603e068e7c 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1074,6 +1074,73 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return 0; } +#define work_to_xmit_work(w) \ + container_of((w), struct felix_deferred_xmit_work, work) + +static void felix_port_deferred_xmit(struct kthread_work *work) +{ + struct felix_deferred_xmit_work *xmit_work = work_to_xmit_work(work); + struct dsa_switch *ds = xmit_work->dp->ds; + struct sk_buff *skb = xmit_work->skb; + u32 rew_op = ocelot_ptp_rew_op(skb); + struct ocelot *ocelot = ds->priv; + int port = xmit_work->dp->index; + int retries = 10; + + do { + if (ocelot_can_inject(ocelot, 0)) + break; + + cpu_relax(); + } while (--retries); + + if (!retries) { + dev_err(ocelot->dev, "port %d failed to inject skb\n", + port); + kfree_skb(skb); + return; + } + + ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); + + consume_skb(skb); + kfree(xmit_work); +} + +static int felix_port_setup_tagger_data(struct dsa_switch *ds, int port) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct ocelot *ocelot = ds->priv; + struct felix *felix = ocelot_to_felix(ocelot); + struct felix_port *felix_port; + + if (!dsa_port_is_user(dp)) + return 0; + + felix_port = kzalloc(sizeof(*felix_port), GFP_KERNEL); + if (!felix_port) + return -ENOMEM; + + felix_port->xmit_worker = felix->xmit_worker; + felix_port->xmit_work_fn = felix_port_deferred_xmit; + + dp->priv = felix_port; + + return 0; +} + +static void felix_port_teardown_tagger_data(struct dsa_switch *ds, int port) +{ + struct dsa_port *dp = dsa_to_port(ds, port); + struct felix_port *felix_port = dp->priv; + + if (!felix_port) + return; + + dp->priv = NULL; + kfree(felix_port); +} + /* Hardware initialization done here so that we can allocate structures with * devm without fear of dsa_register_switch returning -EPROBE_DEFER and causing * us to allocate structures twice (leak memory) and map PCI memory twice @@ -1102,6 +1169,12 @@ static int felix_setup(struct dsa_switch *ds) } } + felix->xmit_worker = kthread_create_worker(0, "felix_xmit"); + if (IS_ERR(felix->xmit_worker)) { + err = PTR_ERR(felix->xmit_worker); + goto out_deinit_timestamp; + } + for (port = 0; port < ds->num_ports; port++) { if (dsa_is_unused_port(ds, port)) continue; @@ -1112,6 +1185,14 @@ static int felix_setup(struct dsa_switch *ds) * bits of vlan tag. */ felix_port_qos_map_init(ocelot, port); + + err = felix_port_setup_tagger_data(ds, port); + if (err) { + dev_err(ds->dev, + "port %d failed to set up tagger data: %pe\n", + port, ERR_PTR(err)); + goto out_deinit_ports; + } } err = ocelot_devlink_sb_register(ocelot); @@ -1138,9 +1219,13 @@ out_deinit_ports: if (dsa_is_unused_port(ds, port)) continue; + felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } + kthread_destroy_worker(felix->xmit_worker); + +out_deinit_timestamp: ocelot_deinit_timestamp(ocelot); ocelot_deinit(ocelot); @@ -1164,17 +1249,20 @@ static void felix_teardown(struct dsa_switch *ds) felix_del_tag_protocol(ds, port, felix->tag_proto); } - ocelot_devlink_sb_unregister(ocelot); - ocelot_deinit_timestamp(ocelot); - ocelot_deinit(ocelot); - for (port = 0; port < ocelot->num_phys_ports; port++) { if (dsa_is_unused_port(ds, port)) continue; + felix_port_teardown_tagger_data(ds, port); ocelot_deinit_port(ocelot, port); } + kthread_destroy_worker(felix->xmit_worker); + + ocelot_devlink_sb_unregister(ocelot); + ocelot_deinit_timestamp(ocelot); + ocelot_deinit(ocelot); + if (felix->info->mdio_bus_free) felix->info->mdio_bus_free(ocelot); } diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 54024b6f9498..be3e42e135c0 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -62,6 +62,7 @@ struct felix { resource_size_t switch_base; resource_size_t imdio_base; enum dsa_tag_protocol tag_proto; + struct kthread_worker *xmit_worker; }; struct net_device *felix_port_to_netdev(struct ocelot *ocelot, int port); diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 50641a7529ad..8ae999f587c4 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -5,6 +5,7 @@ #ifndef _NET_DSA_TAG_OCELOT_H #define _NET_DSA_TAG_OCELOT_H +#include #include #include @@ -160,6 +161,17 @@ struct ocelot_skb_cb { * +------+------+------+------+------+------+------+------+ */ +struct felix_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + +struct felix_port { + void (*xmit_work_fn)(struct kthread_work *work); + struct kthread_worker *xmit_worker; +}; + static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) { packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index 66b2e65c1179..d7055b41982d 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -737,8 +737,6 @@ u32 __ocelot_target_read_ix(struct ocelot *ocelot, enum ocelot_target target, void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, u32 val, u32 reg, u32 offset); -#if IS_ENABLED(CONFIG_MSCC_OCELOT_SWITCH_LIB) - /* Packet I/O */ bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, @@ -746,31 +744,6 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); -#else - -static inline bool ocelot_can_inject(struct ocelot *ocelot, int grp) -{ - return false; -} - -static inline void ocelot_port_inject_frame(struct ocelot *ocelot, int port, - int grp, u32 rew_op, - struct sk_buff *skb) -{ -} - -static inline int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, - struct sk_buff **skb) -{ - return -EIO; -} - -static inline void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp) -{ -} - -#endif - /* Hardware initialization */ int ocelot_regfields_init(struct ocelot *ocelot, const struct reg_field *const regfields); diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index d166377d7085..d8ee15f1c7a9 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -112,8 +112,6 @@ config NET_DSA_TAG_OCELOT config NET_DSA_TAG_OCELOT_8021Q tristate "Tag driver for Ocelot family of switches, using VLAN" - depends on MSCC_OCELOT_SWITCH_LIB || \ - (MSCC_OCELOT_SWITCH_LIB=n && COMPILE_TEST) help Say Y or M if you want to enable support for tagging frames with a custom VLAN-based header. Frames that require timestamping, such as diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 1e4e66ea6796..d05c352f96e5 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -10,10 +10,31 @@ */ #include #include -#include -#include #include "dsa_priv.h" +static struct sk_buff *ocelot_defer_xmit(struct dsa_port *dp, + struct sk_buff *skb) +{ + struct felix_deferred_xmit_work *xmit_work; + struct felix_port *felix_port = dp->priv; + + xmit_work = kzalloc(sizeof(*xmit_work), GFP_ATOMIC); + if (!xmit_work) + return NULL; + + /* Calls felix_port_deferred_xmit in felix.c */ + kthread_init_work(&xmit_work->work, felix_port->xmit_work_fn); + /* Increase refcount so the kfree_skb in dsa_slave_xmit + * won't really free the packet. + */ + xmit_work->dp = dp; + xmit_work->skb = skb_get(skb); + + kthread_queue_work(felix_port->xmit_worker, &xmit_work->work); + + return NULL; +} + static struct sk_buff *ocelot_xmit(struct sk_buff *skb, struct net_device *netdev) { @@ -21,18 +42,9 @@ static struct sk_buff *ocelot_xmit(struct sk_buff *skb, u16 tx_vid = dsa_8021q_tx_vid(dp->ds, dp->index); u16 queue_mapping = skb_get_queue_mapping(skb); u8 pcp = netdev_txq_to_tc(netdev, queue_mapping); - struct ocelot *ocelot = dp->ds->priv; - int port = dp->index; - u32 rew_op = 0; - rew_op = ocelot_ptp_rew_op(skb); - if (rew_op) { - if (!ocelot_can_inject(ocelot, 0)) - return NULL; - - ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb); - return NULL; - } + if (ocelot_ptp_rew_op(skb)) + return ocelot_defer_xmit(dp, skb); return dsa_8021q_xmit(skb, netdev, ETH_P_8021Q, ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); -- cgit v1.2.3 From 1328a883258b4507909090ed0a9ad63771f9f780 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 Oct 2021 14:40:42 +0300 Subject: net: dsa: felix: purge skb from TX timestamping queue if it cannot be sent At present, when a PTP packet which requires TX timestamping gets dropped under congestion by the switch, things go downhill very fast. The driver keeps a clone of that skb in a queue of packets awaiting TX timestamp interrupts, but interrupts will never be raised for the dropped packets. Moreover, matching timestamped packets to timestamps is done by a 2-bit timestamp ID, and this can wrap around and we can match on the wrong skb. Since with the default NPI-based tagging protocol, we get no notification about packet drops, the best we can do is eventually recover from the drop of a PTP frame: its skb will be dead memory until another skb which was assigned the same timestamp ID happens to find it. However, with the ocelot-8021q tagger which injects packets using the manual register interface, it appears that we can check for more information, such as: - whether the input queue has reached the high watermark or not - whether the injection group's FIFO can accept additional data or not so we know that a PTP frame is likely to get dropped before actually sending it, and drop it ourselves (because DSA uses NETIF_F_LLTX, so it can't return NETDEV_TX_BUSY to ask the qdisc to requeue the packet). But when we do that, we can also remove the skb from the timestamping queue, because there surely won't be any timestamp that matches it. Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping") Signed-off-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) (limited to 'drivers/net/dsa/ocelot/felix.c') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index f8603e068e7c..9af8f900aa56 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1074,6 +1074,33 @@ static int felix_init_structs(struct felix *felix, int num_phys_ports) return 0; } +static void ocelot_port_purge_txtstamp_skb(struct ocelot *ocelot, int port, + struct sk_buff *skb) +{ + struct ocelot_port *ocelot_port = ocelot->ports[port]; + struct sk_buff *clone = OCELOT_SKB_CB(skb)->clone; + struct sk_buff *skb_match = NULL, *skb_tmp; + unsigned long flags; + + if (!clone) + return; + + spin_lock_irqsave(&ocelot_port->tx_skbs.lock, flags); + + skb_queue_walk_safe(&ocelot_port->tx_skbs, skb, skb_tmp) { + if (skb != clone) + continue; + __skb_unlink(skb, &ocelot_port->tx_skbs); + skb_match = skb; + break; + } + + spin_unlock_irqrestore(&ocelot_port->tx_skbs.lock, flags); + + WARN_ONCE(!skb_match, + "Could not find skb clone in TX timestamping list\n"); +} + #define work_to_xmit_work(w) \ container_of((w), struct felix_deferred_xmit_work, work) @@ -1097,6 +1124,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work) if (!retries) { dev_err(ocelot->dev, "port %d failed to inject skb\n", port); + ocelot_port_purge_txtstamp_skb(ocelot, port, skb); kfree_skb(skb); return; } -- cgit v1.2.3 From 8d5f7954b7c8de54902a8beda141064a7e2e6ee0 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Tue, 12 Oct 2021 14:40:44 +0300 Subject: net: dsa: felix: break at first CPU port during init and teardown The NXP LS1028A switch has two Ethernet ports towards the CPU, but only one of them is capable of acting as an NPI port at a time (inject and extract packets using DSA tags). However, using the alternative ocelot-8021q tagging protocol, it should be possible to use both CPU ports symmetrically, but for that we need to mark both ports in the device tree as DSA masters. In the process of doing that, it can be seen that traffic to/from the network stack gets broken, and this is because the Felix driver iterates through all DSA CPU ports and configures them as NPI ports. But since there can only be a single NPI port, we effectively end up in a situation where DSA thinks the default CPU port is the first one, but the hardware port configured to be an NPI is the last one. I would like to treat this as a bug, because if the updated device trees are going to start circulating, it would be really good for existing kernels to support them, too. Fixes: adb3dccf090b ("net: dsa: felix: convert to the new .change_tag_protocol DSA API") Signed-off-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: Jakub Kicinski --- drivers/net/dsa/ocelot/felix.c | 19 ++++++++++++------- 1 file changed, 12 insertions(+), 7 deletions(-) (limited to 'drivers/net/dsa/ocelot/felix.c') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 9af8f900aa56..341236dcbdb4 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -266,12 +266,12 @@ static void felix_8021q_cpu_port_deinit(struct ocelot *ocelot, int port) */ static int felix_setup_mmio_filtering(struct felix *felix) { - unsigned long user_ports = 0, cpu_ports = 0; + unsigned long user_ports = dsa_user_ports(felix->ds); struct ocelot_vcap_filter *redirect_rule; struct ocelot_vcap_filter *tagging_rule; struct ocelot *ocelot = &felix->ocelot; struct dsa_switch *ds = felix->ds; - int port, ret; + int cpu = -1, port, ret; tagging_rule = kzalloc(sizeof(struct ocelot_vcap_filter), GFP_KERNEL); if (!tagging_rule) @@ -284,12 +284,15 @@ static int felix_setup_mmio_filtering(struct felix *felix) } for (port = 0; port < ocelot->num_phys_ports; port++) { - if (dsa_is_user_port(ds, port)) - user_ports |= BIT(port); - if (dsa_is_cpu_port(ds, port)) - cpu_ports |= BIT(port); + if (dsa_is_cpu_port(ds, port)) { + cpu = port; + break; + } } + if (cpu < 0) + return -EINVAL; + tagging_rule->key_type = OCELOT_VCAP_KEY_ETYPE; *(__be16 *)tagging_rule->key.etype.etype.value = htons(ETH_P_1588); *(__be16 *)tagging_rule->key.etype.etype.mask = htons(0xffff); @@ -325,7 +328,7 @@ static int felix_setup_mmio_filtering(struct felix *felix) * the CPU port module */ redirect_rule->action.mask_mode = OCELOT_MASK_MODE_REDIRECT; - redirect_rule->action.port_mask = cpu_ports; + redirect_rule->action.port_mask = BIT(cpu); } else { /* Trap PTP packets only to the CPU port module (which is * redirected to the NPI port) @@ -1235,6 +1238,7 @@ static int felix_setup(struct dsa_switch *ds) * there's no real point in checking for errors. */ felix_set_tag_protocol(ds, port, felix->tag_proto); + break; } ds->mtu_enforcement_ingress = true; @@ -1275,6 +1279,7 @@ static void felix_teardown(struct dsa_switch *ds) continue; felix_del_tag_protocol(ds, port, felix->tag_proto); + break; } for (port = 0; port < ocelot->num_phys_ports; port++) { -- cgit v1.2.3