diff options
100 files changed, 3793 insertions, 1080 deletions
diff --git a/Documentation/firmware-guide/acpi/dsd/phy.rst b/Documentation/firmware-guide/acpi/dsd/phy.rst new file mode 100644 index 000000000000..7d01ae8b3cc6 --- /dev/null +++ b/Documentation/firmware-guide/acpi/dsd/phy.rst @@ -0,0 +1,133 @@ +.. SPDX-License-Identifier: GPL-2.0 + +========================= +MDIO bus and PHYs in ACPI +========================= + +The PHYs on an MDIO bus [1] are probed and registered using +fwnode_mdiobus_register_phy(). + +Later, for connecting these PHYs to their respective MACs, the PHYs registered +on the MDIO bus have to be referenced. + +This document introduces two _DSD properties that are to be used +for connecting PHYs on the MDIO bus [3] to the MAC layer. + +These properties are defined in accordance with the "Device +Properties UUID For _DSD" [2] document and the +daffd814-6eba-4d8c-8a91-bc9bbf4aa301 UUID must be used in the Device +Data Descriptors containing them. + +phy-handle +---------- +For each MAC node, a device property "phy-handle" is used to reference +the PHY that is registered on an MDIO bus. This is mandatory for +network interfaces that have PHYs connected to MAC via MDIO bus. + +During the MDIO bus driver initialization, PHYs on this bus are probed +using the _ADR object as shown below and are registered on the MDIO bus. + +:: + Scope(\_SB.MDI0) + { + Device(PHY1) { + Name (_ADR, 0x1) + } // end of PHY1 + + Device(PHY2) { + Name (_ADR, 0x2) + } // end of PHY2 + } + +Later, during the MAC driver initialization, the registered PHY devices +have to be retrieved from the MDIO bus. For this, the MAC driver needs +references to the previously registered PHYs which are provided +as device object references (e.g. \_SB.MDI0.PHY1). + +phy-mode +-------- +The "phy-mode" _DSD property is used to describe the connection to +the PHY. The valid values for "phy-mode" are defined in [4]. + +The following ASL example illustrates the usage of these properties. + +DSDT entry for MDIO node +------------------------ + +The MDIO bus has an SoC component (MDIO controller) and a platform +component (PHYs on the MDIO bus). + +a) Silicon Component +This node describes the MDIO controller, MDI0 +--------------------------------------------- +:: + Scope(_SB) + { + Device(MDI0) { + Name(_HID, "NXP0006") + Name(_CCA, 1) + Name(_UID, 0) + Name(_CRS, ResourceTemplate() { + Memory32Fixed(ReadWrite, MDI0_BASE, MDI_LEN) + Interrupt(ResourceConsumer, Level, ActiveHigh, Shared) + { + MDI0_IT + } + }) // end of _CRS for MDI0 + } // end of MDI0 + } + +b) Platform Component +The PHY1 and PHY2 nodes represent the PHYs connected to MDIO bus MDI0 +--------------------------------------------------------------------- +:: + Scope(\_SB.MDI0) + { + Device(PHY1) { + Name (_ADR, 0x1) + } // end of PHY1 + + Device(PHY2) { + Name (_ADR, 0x2) + } // end of PHY2 + } + +DSDT entries representing MAC nodes +----------------------------------- + +Below are the MAC nodes where PHY nodes are referenced. +phy-mode and phy-handle are used as explained earlier. +------------------------------------------------------ +:: + Scope(\_SB.MCE0.PR17) + { + Name (_DSD, Package () { + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package (2) {"phy-mode", "rgmii-id"}, + Package (2) {"phy-handle", \_SB.MDI0.PHY1} + } + }) + } + + Scope(\_SB.MCE0.PR18) + { + Name (_DSD, Package () { + ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"), + Package () { + Package (2) {"phy-mode", "rgmii-id"}, + Package (2) {"phy-handle", \_SB.MDI0.PHY2}} + } + }) + } + +References +========== + +[1] Documentation/networking/phy.rst + +[2] https://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf + +[3] Documentation/firmware-guide/acpi/DSD-properties-rules.rst + +[4] Documentation/devicetree/bindings/net/ethernet-controller.yaml diff --git a/Documentation/networking/dsa/dsa.rst b/Documentation/networking/dsa/dsa.rst index 8688009514cc..20baacf2bc5c 100644 --- a/Documentation/networking/dsa/dsa.rst +++ b/Documentation/networking/dsa/dsa.rst @@ -93,14 +93,15 @@ A tagging protocol may tag all packets with switch tags of the same length, or the tag length might vary (for example packets with PTP timestamps might require an extended switch tag, or there might be one tag length on TX and a different one on RX). Either way, the tagging protocol driver must populate the -``struct dsa_device_ops::overhead`` with the length in octets of the longest -switch frame header. The DSA framework will automatically adjust the MTU of the -master interface to accomodate for this extra size in order for DSA user ports -to support the standard MTU (L2 payload length) of 1500 octets. The ``overhead`` -is also used to request from the network stack, on a best-effort basis, the -allocation of packets with a ``needed_headroom`` or ``needed_tailroom`` -sufficient such that the act of pushing the switch tag on transmission of a -packet does not cause it to reallocate due to lack of memory. +``struct dsa_device_ops::needed_headroom`` and/or ``struct dsa_device_ops::needed_tailroom`` +with the length in octets of the longest switch frame header/trailer. The DSA +framework will automatically adjust the MTU of the master interface to +accommodate for this extra size in order for DSA user ports to support the +standard MTU (L2 payload length) of 1500 octets. The ``needed_headroom`` and +``needed_tailroom`` properties are also used to request from the network stack, +on a best-effort basis, the allocation of packets with enough extra space such +that the act of pushing the switch tag on transmission of a packet does not +cause it to reallocate due to lack of memory. Even though applications are not expected to parse DSA-specific frame headers, the format on the wire of the tagging protocol represents an Application Binary @@ -169,8 +170,8 @@ The job of this method is to prepare the skb in a way that the switch will understand what egress port the packet is for (and not deliver it towards other ports). Typically this is fulfilled by pushing a frame header. Checking for insufficient size in the skb headroom or tailroom is unnecessary provided that -the ``overhead`` and ``tail_tag`` properties were filled out properly, because -DSA ensures there is enough space before calling this method. +the ``needed_headroom`` and ``needed_tailroom`` properties were filled out +properly, because DSA ensures there is enough space before calling this method. The reception of a packet goes through the tagger's ``rcv`` function. The passed ``struct sk_buff *skb`` has ``skb->data`` pointing at diff --git a/MAINTAINERS b/MAINTAINERS index e69c1991ec3b..2172f594be8f 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6811,6 +6811,8 @@ F: Documentation/devicetree/bindings/net/mdio* F: Documentation/devicetree/bindings/net/qca,ar803x.yaml F: Documentation/networking/phy.rst F: drivers/net/mdio/ +F: drivers/net/mdio/acpi_mdio.c +F: drivers/net/mdio/fwnode_mdio.c F: drivers/net/mdio/of_mdio.c F: drivers/net/pcs/ F: drivers/net/phy/ diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h index 8fc52679543d..cb4f73c7228d 100644 --- a/arch/s390/include/asm/qdio.h +++ b/arch/s390/include/asm/qdio.h @@ -137,7 +137,6 @@ struct slibe { * @user0: user defineable value * @res4: reserved paramater * @user1: user defineable value - * @user2: user defineable value */ struct qaob { u64 res0[6]; @@ -152,8 +151,7 @@ struct qaob { u16 dcount[QDIO_MAX_ELEMENTS_PER_BUFFER]; u64 user0; u64 res4[2]; - u64 user1; - u64 user2; + u8 user1[16]; } __attribute__ ((packed, aligned(256))); /** diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c index 3b54b8fd7396..e7ddd281afff 100644 --- a/drivers/acpi/utils.c +++ b/drivers/acpi/utils.c @@ -277,6 +277,20 @@ acpi_evaluate_integer(acpi_handle handle, EXPORT_SYMBOL(acpi_evaluate_integer); +int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + unsigned long long adr; + acpi_status status; + + status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL, &adr); + if (ACPI_FAILURE(status)) + return -ENODATA; + + *addr = (u32)adr; + return 0; +} +EXPORT_SYMBOL(acpi_get_local_address); + acpi_status acpi_evaluate_reference(acpi_handle handle, acpi_string pathname, diff --git a/drivers/net/dsa/sja1105/sja1105.h b/drivers/net/dsa/sja1105/sja1105.h index f762f5488a76..5f3449351668 100644 --- a/drivers/net/dsa/sja1105/sja1105.h +++ b/drivers/net/dsa/sja1105/sja1105.h @@ -109,6 +109,8 @@ struct sja1105_info { int num_cbs_shapers; int max_frame_mem; int num_ports; + bool multiple_cascade_ports; + enum dsa_tag_protocol tag_proto; const struct sja1105_dynamic_table_ops *dyn_ops; const struct sja1105_table_ops *static_ops; const struct sja1105_regs *regs; @@ -128,6 +130,8 @@ struct sja1105_info { const unsigned char *addr, u16 vid); void (*ptp_cmd_packing)(u8 *buf, struct sja1105_ptp_cmd *cmd, enum packing_op op); + bool (*rxtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); + void (*txtstamp)(struct dsa_switch *ds, int port, struct sk_buff *skb); int (*clocking_setup)(struct sja1105_private *priv); const char *name; bool supports_mii[SJA1105_MAX_NUM_PORTS]; diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 3b031864ad74..6e2cfbf605ef 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -654,14 +654,6 @@ static int sja1105_init_general_params(struct sja1105_private *priv) .host_port = priv->ds->num_ports, /* Default to an invalid value */ .mirr_port = priv->ds->num_ports, - /* Link-local traffic received on casc_port will be forwarded - * to host_port without embedding the source port and device ID - * info in the destination MAC address (presumably because it - * is a cascaded port and a downstream SJA switch already did - * that). Default to an invalid port (to disable the feature) - * and overwrite this if we find any DSA (cascaded) ports. - */ - .casc_port = priv->ds->num_ports, /* No TTEthernet */ .vllupformat = SJA1105_VL_FORMAT_PSFP, .vlmarker = 0, @@ -673,7 +665,12 @@ static int sja1105_init_general_params(struct sja1105_private *priv) */ .tpid = ETH_P_SJA1105, .tpid2 = ETH_P_SJA1105, + /* Enable the TTEthernet engine on SJA1110 */ + .tte_en = true, + /* Set up the EtherType for control packets on SJA1110 */ + .header_type = ETH_P_SJA1110, }; + struct sja1105_general_params_entry *general_params; struct dsa_switch *ds = priv->ds; struct sja1105_table *table; int port; @@ -699,12 +696,26 @@ static int sja1105_init_general_params(struct sja1105_private *priv) table->entry_count = table->ops->max_entry_count; + general_params = table->entries; + /* This table only has a single entry */ - ((struct sja1105_general_params_entry *)table->entries)[0] = - default_general_params; + general_params[0] = default_general_params; sja1110_select_tdmaconfigidx(priv); + /* Link-local traffic received on casc_port will be forwarded + * to host_port without embedding the source port and device ID + * info in the destination MAC address, and no RX timestamps will be + * taken either (presumably because it is a cascaded port and a + * downstream SJA switch already did that). + * To disable the feature, we need to do different things depending on + * switch generation. On SJA1105 we need to set an invalid port, while + * on SJA1110 which support multiple cascaded ports, this field is a + * bitmask so it must be left zero. + */ + if (!priv->info->multiple_cascade_ports) + general_params->casc_port = ds->num_ports; + return 0; } @@ -2165,7 +2176,9 @@ static enum dsa_tag_protocol sja1105_get_tag_protocol(struct dsa_switch *ds, int port, enum dsa_tag_protocol mp) { - return DSA_TAG_PROTO_SJA1105; + struct sja1105_private *priv = ds->priv; + + return priv->info->tag_proto; } static int sja1105_find_free_subvlan(u16 *subvlan_map, bool pvid) diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c index 0bc566b9e958..691f6dd7e669 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.c +++ b/drivers/net/dsa/sja1105/sja1105_ptp.c @@ -79,6 +79,7 @@ static int sja1105_change_rxtstamping(struct sja1105_private *priv, priv->tagger_data.stampable_skb = NULL; } ptp_cancel_worker_sync(ptp_data->clock); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); return sja1105_static_config_reload(priv, SJA1105_RX_HWTSTAMPING); @@ -397,7 +398,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) *shwt = (struct skb_shared_hwtstamps) {0}; - ts = SJA1105_SKB_CB(skb)->meta_tstamp; + ts = SJA1105_SKB_CB(skb)->tstamp; ts = sja1105_tstamp_reconstruct(ds, ticks, ts); shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts)); @@ -413,9 +414,7 @@ static long sja1105_rxtstamp_work(struct ptp_clock_info *ptp) return -1; } -/* Called from dsa_skb_defer_rx_timestamp */ -bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, - struct sk_buff *skb, unsigned int type) +bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) { struct sja1105_private *priv = ds->priv; struct sja1105_ptp_data *ptp_data = &priv->ptp_data; @@ -431,6 +430,89 @@ bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, return true; } +bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) +{ + struct skb_shared_hwtstamps *shwt = skb_hwtstamps(skb); + u64 ts = SJA1105_SKB_CB(skb)->tstamp; + + *shwt = (struct skb_shared_hwtstamps) {0}; + + shwt->hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(ts)); + + /* Don't defer */ + return false; +} + +/* Called from dsa_skb_defer_rx_timestamp */ +bool sja1105_port_rxtstamp(struct dsa_switch *ds, int port, + struct sk_buff *skb, unsigned int type) +{ + struct sja1105_private *priv = ds->priv; + + return priv->info->rxtstamp(ds, port, skb); +} + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp) +{ + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sk_buff *skb, *skb_tmp, *skb_match = NULL; + struct skb_shared_hwtstamps shwt = {0}; + + /* We don't care about RX timestamps on the CPU port */ + if (dir == SJA1110_META_TSTAMP_RX) + return; + + spin_lock(&ptp_data->skb_txtstamp_queue.lock); + + skb_queue_walk_safe(&ptp_data->skb_txtstamp_queue, skb, skb_tmp) { + if (SJA1105_SKB_CB(skb)->ts_id != ts_id) + continue; + + __skb_unlink(skb, &ptp_data->skb_txtstamp_queue); + skb_match = skb; + + break; + } + + spin_unlock(&ptp_data->skb_txtstamp_queue.lock); + + if (WARN_ON(!skb_match)) + return; + + shwt.hwtstamp = ns_to_ktime(sja1105_ticks_to_ns(tstamp)); + skb_complete_tx_timestamp(skb_match, &shwt); +} +EXPORT_SYMBOL_GPL(sja1110_process_meta_tstamp); + +/* In addition to cloning the skb which is done by the common + * sja1105_port_txtstamp, we need to generate a timestamp ID and save the + * packet to the TX timestamping queue. + */ +void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct sja1105_private *priv = ds->priv; + struct sja1105_ptp_data *ptp_data = &priv->ptp_data; + struct sja1105_port *sp = &priv->ports[port]; + u8 ts_id; + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + spin_lock(&sp->data->meta_lock); + + ts_id = sp->data->ts_id; + /* Deal automatically with 8-bit wraparound */ + sp->data->ts_id++; + + SJA1105_SKB_CB(clone)->ts_id = ts_id; + + spin_unlock(&sp->data->meta_lock); + + skb_queue_tail(&ptp_data->skb_txtstamp_queue, clone); +} + /* Called from dsa_skb_tx_timestamp. This callback is just to clone * the skb and have it available in SJA1105_SKB_CB in the .port_deferred_xmit * callback, where we will timestamp it synchronously. @@ -449,6 +531,9 @@ void sja1105_port_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb) return; SJA1105_SKB_CB(skb)->clone = clone; + + if (priv->info->txtstamp) + priv->info->txtstamp(ds, port, skb); } static int sja1105_ptp_reset(struct dsa_switch *ds) @@ -865,7 +950,10 @@ int sja1105_ptp_clock_register(struct dsa_switch *ds) .n_per_out = 1, }; + /* Only used on SJA1105 */ skb_queue_head_init(&ptp_data->skb_rxtstamp_queue); + /* Only used on SJA1110 */ + skb_queue_head_init(&ptp_data->skb_txtstamp_queue); spin_lock_init(&tagger_data->meta_lock); ptp_data->clock = ptp_clock_register(&ptp_data->caps, ds->dev); @@ -890,6 +978,7 @@ void sja1105_ptp_clock_unregister(struct dsa_switch *ds) del_timer_sync(&ptp_data->extts_timer); ptp_cancel_worker_sync(ptp_data->clock); + skb_queue_purge(&ptp_data->skb_txtstamp_queue); skb_queue_purge(&ptp_data->skb_rxtstamp_queue); ptp_clock_unregister(ptp_data->clock); ptp_data->clock = NULL; diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.h b/drivers/net/dsa/sja1105/sja1105_ptp.h index 34f97f58a355..3c874bb4c17b 100644 --- a/drivers/net/dsa/sja1105/sja1105_ptp.h +++ b/drivers/net/dsa/sja1105/sja1105_ptp.h @@ -75,7 +75,12 @@ struct sja1105_ptp_cmd { struct sja1105_ptp_data { struct timer_list extts_timer; + /* Used only on SJA1105 to reconstruct partial timestamps */ struct sk_buff_head skb_rxtstamp_queue; + /* Used on SJA1110 where meta frames are generated only for + * 2-step TX timestamps + */ + struct sk_buff_head skb_txtstamp_queue; struct ptp_clock_info caps; struct ptp_clock *clock; struct sja1105_ptp_cmd cmd; @@ -122,6 +127,10 @@ int __sja1105_ptp_adjtime(struct dsa_switch *ds, s64 delta); int sja1105_ptp_commit(struct dsa_switch *ds, struct sja1105_ptp_cmd *cmd, sja1105_spi_rw_mode_t rw); +bool sja1105_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +bool sja1110_rxtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); +void sja1110_txtstamp(struct dsa_switch *ds, int port, struct sk_buff *skb); + #else struct sja1105_ptp_cmd; @@ -184,6 +193,10 @@ static inline int sja1105_ptp_commit(struct dsa_switch *ds, #define sja1105_hwtstamp_set NULL +#define sja1105_rxtstamp NULL +#define sja1110_rxtstamp NULL +#define sja1110_txtstamp NULL + #endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ #endif /* _SJA1105_PTP_H */ diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index 54ecb5565761..32d00212423c 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -569,6 +569,7 @@ const struct sja1105_info sja1105e_info = { .static_ops = sja1105e_table_ops, .dyn_ops = sja1105et_dyn_ops, .qinq_tpid = ETH_P_8021Q, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, .ptpegr_ts_bytes = 4, @@ -579,6 +580,7 @@ const struct sja1105_info sja1105e_info = { .fdb_add_cmd = sja1105et_fdb_add, .fdb_del_cmd = sja1105et_fdb_del, .ptp_cmd_packing = sja1105et_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, .regs = &sja1105et_regs, .port_speed = { @@ -600,6 +602,7 @@ const struct sja1105_info sja1105t_info = { .static_ops = sja1105t_table_ops, .dyn_ops = sja1105et_dyn_ops, .qinq_tpid = ETH_P_8021Q, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = false, .ptp_ts_bits = 24, .ptpegr_ts_bytes = 4, @@ -610,6 +613,7 @@ const struct sja1105_info sja1105t_info = { .fdb_add_cmd = sja1105et_fdb_add, .fdb_del_cmd = sja1105et_fdb_del, .ptp_cmd_packing = sja1105et_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, .regs = &sja1105et_regs, .port_speed = { @@ -631,6 +635,7 @@ const struct sja1105_info sja1105p_info = { .static_ops = sja1105p_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -642,6 +647,7 @@ const struct sja1105_info sja1105p_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, .regs = &sja1105pqrs_regs, .port_speed = { @@ -663,6 +669,7 @@ const struct sja1105_info sja1105q_info = { .static_ops = sja1105q_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -674,6 +681,7 @@ const struct sja1105_info sja1105q_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, .regs = &sja1105pqrs_regs, .port_speed = { @@ -695,6 +703,7 @@ const struct sja1105_info sja1105r_info = { .static_ops = sja1105r_table_ops, .dyn_ops = sja1105pqrs_dyn_ops, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -706,6 +715,7 @@ const struct sja1105_info sja1105r_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, .regs = &sja1105pqrs_regs, .port_speed = { @@ -729,6 +739,7 @@ const struct sja1105_info sja1105s_info = { .dyn_ops = sja1105pqrs_dyn_ops, .regs = &sja1105pqrs_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1105, .can_limit_mcast_flood = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, @@ -740,6 +751,7 @@ const struct sja1105_info sja1105s_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1105_rxtstamp, .clocking_setup = sja1105_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -762,7 +774,9 @@ const struct sja1105_info sja1110a_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -773,6 +787,8 @@ const struct sja1105_info sja1110a_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -807,7 +823,9 @@ const struct sja1105_info sja1110b_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -818,6 +836,8 @@ const struct sja1105_info sja1110b_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -852,7 +872,9 @@ const struct sja1105_info sja1110c_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -863,6 +885,8 @@ const struct sja1105_info sja1110c_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, @@ -897,7 +921,9 @@ const struct sja1105_info sja1110d_info = { .dyn_ops = sja1110_dyn_ops, .regs = &sja1110_regs, .qinq_tpid = ETH_P_8021AD, + .tag_proto = DSA_TAG_PROTO_SJA1110, .can_limit_mcast_flood = true, + .multiple_cascade_ports = true, .ptp_ts_bits = 32, .ptpegr_ts_bytes = 8, .max_frame_mem = SJA1110_MAX_FRAME_MEMORY, @@ -908,6 +934,8 @@ const struct sja1105_info sja1110d_info = { .fdb_add_cmd = sja1105pqrs_fdb_add, .fdb_del_cmd = sja1105pqrs_fdb_del, .ptp_cmd_packing = sja1105pqrs_ptp_cmd_packing, + .rxtstamp = sja1110_rxtstamp, + .txtstamp = sja1110_txtstamp, .clocking_setup = sja1110_clocking_setup, .port_speed = { [SJA1105_SPEED_AUTO] = 0, diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index eda571819d45..1491b72008f3 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -212,6 +212,7 @@ size_t sja1110_general_params_entry_packing(void *buf, void *entry_ptr, sja1105_packing(buf, &entry->egrmirrdei, 110, 110, size, op); sja1105_packing(buf, &entry->replay_port, 109, 106, size, op); sja1105_packing(buf, &entry->tdmaconfigidx, 70, 67, size, op); + sja1105_packing(buf, &entry->header_type, 64, 49, size, op); sja1105_packing(buf, &entry->tte_en, 16, 16, size, op); return size; } diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index 9bef51791bff..bce0f5c03d0b 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -217,6 +217,7 @@ struct sja1105_general_params_entry { /* SJA1110 only */ u64 tte_en; u64 tdmaconfigidx; + u64 header_type; }; struct sja1105_schedule_entry_points_entry { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c index 4dfadf2b70d6..ae6d382d8735 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.c @@ -1,6 +1,9 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) /* Copyright 2019 NXP */ +#include <linux/acpi.h> +#include <linux/property.h> + #include "dpaa2-eth.h" #include "dpaa2-mac.h" @@ -34,39 +37,51 @@ static int phy_mode(enum dpmac_eth_if eth_if, phy_interface_t *if_mode) return 0; } -/* Caller must call of_node_put on the returned value */ -static struct device_node *dpaa2_mac_get_node(u16 dpmac_id) +static struct fwnode_handle *dpaa2_mac_get_node(struct device *dev, + u16 dpmac_id) { - struct device_node *dpmacs, *dpmac = NULL; - u32 id; + struct fwnode_handle *fwnode, *parent, *child = NULL; + struct device_node *dpmacs = NULL; int err; + u32 id; - dpmacs = of_find_node_by_name(NULL, "dpmacs"); - if (!dpmacs) - return NULL; + fwnode = dev_fwnode(dev->parent); + if (is_of_node(fwnode)) { + dpmacs = of_find_node_by_name(NULL, "dpmacs"); + if (!dpmacs) + return NULL; + parent = of_fwnode_handle(dpmacs); + } else if (is_acpi_node(fwnode)) { + parent = fwnode; + } - while ((dpmac = of_get_next_child(dpmacs, dpmac)) != NULL) { - err = of_property_read_u32(dpmac, "reg", &id); + fwnode_for_each_child_node(parent, child) { + err = -EINVAL; + if (is_acpi_device_node(child)) + err = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &id); + else if (is_of_node(child)) + err = of_property_read_u32(to_of_node(child), "reg", &id); if (err) continue; - if (id == dpmac_id) - break; - } + if (id == dpmac_id) { + of_node_put(dpmacs); + return child; + } + } of_node_put(dpmacs); - - return dpmac; + return NULL; } -static int dpaa2_mac_get_if_mode(struct device_node *node, +static int dpaa2_mac_get_if_mode(struct fwnode_handle *dpmac_node, struct dpmac_attr attr) { phy_interface_t if_mode; int err; - err = of_get_phy_mode(node, &if_mode); - if (!err) - return if_mode; + err = fwnode_get_phy_mode(dpmac_node); + if (err > 0) + return err; err = phy_mode(attr.eth_if, &if_mode); if (!err) @@ -235,26 +250,27 @@ static const struct phylink_mac_ops dpaa2_mac_phylink_ops = { }; static int dpaa2_pcs_create(struct dpaa2_mac *mac, - struct device_node *dpmac_node, int id) + struct fwnode_handle *dpmac_node, + int id) { struct mdio_device *mdiodev; - struct device_node *node; + struct fwnode_handle *node; - node = of_parse_phandle(dpmac_node, "pcs-handle", 0); - if (!node) { + node = fwnode_find_reference(dpmac_node, "pcs-handle", 0); + if (IS_ERR(node)) { /* do not error out on old DTS files */ netdev_warn(mac->net_dev, "pcs-handle node not found\n"); return 0; } - if (!of_device_is_available(node)) { + if (!fwnode_device_is_available(node)) { netdev_err(mac->net_dev, "pcs-handle node not available\n"); - of_node_put(node); + fwnode_handle_put(node); return -ENODEV; } - mdiodev = of_mdio_find_device(node); - of_node_put(node); + mdiodev = fwnode_mdio_find_device(node); + fwnode_handle_put(node); if (!mdiodev) return -EPROBE_DEFER; @@ -283,13 +299,13 @@ static void dpaa2_pcs_destroy(struct dpaa2_mac *mac) int dpaa2_mac_connect(struct dpaa2_mac *mac) { struct net_device *net_dev = mac->net_dev; - struct device_node *dpmac_node; + struct fwnode_handle *dpmac_node; struct phylink *phylink; int err; mac->if_link_type = mac->attr.link_type; - dpmac_node = mac->of_node; + dpmac_node = mac->fw_node; if (!dpmac_node) { netdev_err(net_dev, "No dpmac@%d node found.\n", mac->attr.id); return -ENODEV; @@ -304,7 +320,7 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) * error out if the interface mode requests them and there is no PHY * to act upon them */ - if (of_phy_is_fixed_link(dpmac_node) && + if (of_phy_is_fixed_link(to_of_node(dpmac_node)) && (mac->if_mode == PHY_INTERFACE_MODE_RGMII_ID || mac->if_mode == PHY_INTERFACE_MODE_RGMII_RXID || mac->if_mode == PHY_INTERFACE_MODE_RGMII_TXID)) { @@ -324,7 +340,7 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) mac->phylink_config.type = PHYLINK_NETDEV; phylink = phylink_create(&mac->phylink_config, - of_fwnode_handle(dpmac_node), mac->if_mode, + dpmac_node, mac->if_mode, &dpaa2_mac_phylink_ops); if (IS_ERR(phylink)) { err = PTR_ERR(phylink); @@ -335,9 +351,9 @@ int dpaa2_mac_connect(struct dpaa2_mac *mac) if (mac->pcs) phylink_set_pcs(mac->phylink, &mac->pcs->pcs); - err = phylink_of_phy_connect(mac->phylink, dpmac_node, 0); + err = phylink_fwnode_phy_connect(mac->phylink, dpmac_node, 0); if (err) { - netdev_err(net_dev, "phylink_of_phy_connect() = %d\n", err); + netdev_err(net_dev, "phylink_fwnode_phy_connect() = %d\n", err); goto err_phylink_destroy; } @@ -384,8 +400,8 @@ int dpaa2_mac_open(struct dpaa2_mac *mac) /* Find the device node representing the MAC device and link the device * behind the associated netdev to it. */ - mac->of_node = dpaa2_mac_get_node(mac->attr.id); - net_dev->dev.of_node = mac->of_node; + mac->fw_node = dpaa2_mac_get_node(&mac->mc_dev->dev, mac->attr.id); + net_dev->dev.of_node = to_of_node(mac->fw_node); return 0; @@ -399,8 +415,8 @@ void dpaa2_mac_close(struct dpaa2_mac *mac) struct fsl_mc_device *dpmac_dev = mac->mc_dev; dpmac_close(mac->mc_io, 0, dpmac_dev->mc_handle); - if (mac->of_node) - of_node_put(mac->of_node); + if (mac->fw_node) + fwnode_handle_put(mac->fw_node); } static char dpaa2_mac_ethtool_stats[][ETH_GSTRING_LEN] = { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h index 8ebcb3420d02..7842cbb2207a 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-mac.h @@ -24,7 +24,7 @@ struct dpaa2_mac { phy_interface_t if_mode; enum dpmac_link_type if_link_type; struct lynx_pcs *pcs; - struct device_node *of_node; + struct fwnode_handle *fw_node; }; bool dpaa2_mac_is_type_fixed(struct fsl_mc_device *dpmac_dev, diff --git a/drivers/net/ethernet/freescale/xgmac_mdio.c b/drivers/net/ethernet/freescale/xgmac_mdio.c index bfa2826c5545..0b68852379da 100644 --- a/drivers/net/ethernet/freescale/xgmac_mdio.c +++ b/drivers/net/ethernet/freescale/xgmac_mdio.c @@ -2,6 +2,7 @@ * QorIQ 10G MDIO Controller * * Copyright 2012 Freescale Semiconductor, Inc. + * Copyright 2021 NXP * * Authors: Andy Fleming <afleming@freescale.com> * Timur Tabi <timur@freescale.com> @@ -11,15 +12,17 @@ * kind, whether express or implied. */ -#include <linux/kernel.h> -#include <linux/slab.h> +#include <linux/acpi.h> +#include <linux/acpi_mdio.h> #include <linux/interrupt.h> -#include <linux/module.h> -#include <linux/phy.h> +#include <linux/kernel.h> #include <linux/mdio.h> +#include <linux/module.h> #include <linux/of_address.h> -#include <linux/of_platform.h> #include <linux/of_mdio.h> +#include <linux/of_platform.h> +#include <linux/phy.h> +#include <linux/slab.h> /* Number of microseconds to wait for a register to respond */ #define TIMEOUT 1000 @@ -243,10 +246,10 @@ static int xgmac_mdio_read(struct mii_bus *bus, int phy_id, int regnum) static int xgmac_mdio_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node; - struct mii_bus *bus; - struct resource *res; + struct fwnode_handle *fwnode; struct mdio_fsl_priv *priv; + struct resource *res; + struct mii_bus *bus; int ret; /* In DPAA-1, MDIO is one of the many FMan sub-devices. The FMan @@ -279,13 +282,22 @@ static int xgmac_mdio_probe(struct platform_device *pdev) goto err_ioremap; } + /* For both ACPI and DT cases, endianness of MDIO controller + * needs to be specified using "little-endian" property. + */ priv->is_little_endian = device_property_read_bool(&pdev->dev, "little-endian"); priv->has_a011043 = device_property_read_bool(&pdev->dev, "fsl,erratum-a011043"); - ret = of_mdiobus_register(bus, np); + fwnode = pdev->dev.fwnode; + if (is_of_node(fwnode)) + ret = of_mdiobus_register(bus, to_of_node(fwnode)); + else if (is_acpi_node(fwnode)) + ret = acpi_mdiobus_register(bus, fwnode); + else + ret = -EINVAL; if (ret) { dev_err(&pdev->dev, "cannot register MDIO bus\n"); goto err_registration; diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig index fa6025dc4cdb..bb062b02fb85 100644 --- a/drivers/net/ethernet/hisilicon/Kconfig +++ b/drivers/net/ethernet/hisilicon/Kconfig @@ -102,6 +102,7 @@ config HNS3_HCLGE tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support" default m depends on PCI_MSI + imply PTP_1588_CLOCK help This selects the HNS3_HCLGE network acceleration engine & its hardware compatibility layer. The engine would be used in Hisilicon hip08 family of diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index e564aa32a414..ba883b0a19f0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -276,6 +276,7 @@ enum hnae3_dbg_cmd { HNAE3_DBG_CMD_MAC_MC, HNAE3_DBG_CMD_MNG_TBL, HNAE3_DBG_CMD_LOOPBACK, + HNAE3_DBG_CMD_PTP_INFO, HNAE3_DBG_CMD_INTERRUPT_INFO, HNAE3_DBG_CMD_RESET_INFO, HNAE3_DBG_CMD_IMP_INFO, @@ -525,6 +526,12 @@ struct hnae3_ae_dev { * Check if any cls flower rule exist * dbg_read_cmd * Execute debugfs read command. + * set_tx_hwts_info + * Save information for 1588 tx packet + * get_rx_hwts + * Get 1588 rx hwstamp + * get_ts_info + * Get phc info */ struct hnae3_ae_ops { int (*init_ae_dev)(struct hnae3_ae_dev *ae_dev); @@ -710,6 +717,12 @@ struct hnae3_ae_ops { struct ethtool_link_ksettings *cmd); int (*set_phy_link_ksettings)(struct hnae3_handle *handle, const struct ethtool_link_ksettings *cmd); + bool (*set_tx_hwts_info)(struct hnae3_handle *handle, + struct sk_buff *skb); + void (*get_rx_hwts)(struct hnae3_handle *handle, struct sk_buff *skb, + u32 nsec, u32 sec); + int (*get_ts_info)(struct hnae3_handle *handle, + struct ethtool_ts_info *info); }; struct hnae3_dcb_ops { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index a0edca848392..c512a63c423b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -316,6 +316,13 @@ static struct hns3_dbg_cmd_info hns3_dbg_cmd[] = { .buf_len = HNS3_DBG_READ_LEN, .init = hns3_dbg_common_file_init, }, + { + .name = "ptp_info", + .cmd = HNAE3_DBG_CMD_PTP_INFO, + .dentry = HNS3_DBG_DENTRY_COMMON, + .buf_len = HNS3_DBG_READ_LEN, + .init = hns3_dbg_common_file_init, + }, }; static struct hns3_dbg_cap_info hns3_dbg_cap[] = { @@ -1059,8 +1066,10 @@ int hns3_dbg_init(struct hnae3_handle *handle) handle->hnae3_dbgfs); for (i = 0; i < ARRAY_SIZE(hns3_dbg_cmd); i++) { - if (hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && - ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) + if ((hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_TM_NODES && + ae_dev->dev_version <= HNAE3_DEVICE_VERSION_V2) || + (hns3_dbg_cmd[i].cmd == HNAE3_DBG_CMD_PTP_INFO && + !test_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps))) continue; if (!hns3_dbg_cmd[i].init) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 393979bec170..9a45f3cde6a2 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1799,6 +1799,18 @@ static void hns3_tx_doorbell(struct hns3_enet_ring *ring, int num, WRITE_ONCE(ring->last_to_use, ring->next_to_use); } +static void hns3_tsyn(struct net_device *netdev, struct sk_buff *skb, + struct hns3_desc *desc) +{ + struct hnae3_handle *h = hns3_get_handle(netdev); + + if (!(h->ae_algo->ops->set_tx_hwts_info && + h->ae_algo->ops->set_tx_hwts_info(h, skb))) + return; + + desc->tx.bdtp_fe_sc_vld_ra_ri |= cpu_to_le16(BIT(HNS3_TXD_TSYN_B)); +} + netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) { struct hns3_nic_priv *priv = netdev_priv(netdev); @@ -1851,10 +1863,16 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) pre_ntu = ring->next_to_use ? (ring->next_to_use - 1) : (ring->desc_num - 1); + + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) + hns3_tsyn(netdev, skb, &ring->desc[pre_ntu]); + ring->desc[pre_ntu].tx.bdtp_fe_sc_vld_ra_ri |= cpu_to_le16(BIT(HNS3_TXD_FE_B)); trace_hns3_tx_desc(ring, pre_ntu); + skb_tx_timestamp(skb); + /* Complete translate all packets */ dev_queue = netdev_get_tx_queue(netdev, ring->queue_index); doorbell = __netdev_tx_sent_queue(dev_queue, desc_cb->send_bytes, @@ -3585,6 +3603,15 @@ static int hns3_handle_bdinfo(struct hns3_enet_ring *ring, struct sk_buff *skb) ol_info = le32_to_cpu(desc->rx.ol_info); csum = le16_to_cpu(desc->csum); + if (unlikely(bd_base_info & BIT(HNS3_RXD_TS_VLD_B))) { + struct hnae3_handle *h = hns3_get_handle(netdev); + u32 nsec = le32_to_cpu(desc->ts_nsec); + u32 sec = le32_to_cpu(desc->ts_sec); + + if (h->ae_algo->ops->get_rx_hwts) + h->ae_algo->ops->get_rx_hwts(h, skb, nsec, sec); + } + /* Based on hw strategy, the tag offloaded will be stored at * ot_vlan_tag in two layer tag case, and stored at vlan_tag * in one layer tag case. diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 5698a14a804e..79821c7bdc16 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -122,8 +122,9 @@ enum hns3_nic_state { #define HNS3_RXD_LUM_B 9 #define HNS3_RXD_CRCP_B 10 #define HNS3_RXD_L3L4P_B 11 -#define HNS3_RXD_TSIND_S 12 -#define HNS3_RXD_TSIND_M (0x7 << HNS3_RXD_TSIND_S) +#define HNS3_RXD_TSIDX_S 12 +#define HNS3_RXD_TSIDX_M (0x3 << HNS3_RXD_TSIDX_S) +#define HNS3_RXD_TS_VLD_B 14 #define HNS3_RXD_LKBK_B 15 #define HNS3_RXD_GRO_SIZE_S 16 #define HNS3_RXD_GRO_SIZE_M (0x3fff << HNS3_RXD_GRO_SIZE_S) @@ -240,6 +241,10 @@ struct __packed hns3_desc { union { __le64 addr; __le16 csum; + struct { + __le32 ts_nsec; + __le32 ts_sec; + }; }; union { struct { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index bb7c2ec7ed6f..acef5435d7b7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -1598,6 +1598,17 @@ static int hns3_set_priv_flags(struct net_device *netdev, u32 pflags) ETHTOOL_COALESCE_TX_USECS_HIGH | \ ETHTOOL_COALESCE_MAX_FRAMES) +static int hns3_get_ts_info(struct net_device *netdev, + struct ethtool_ts_info *info) +{ + struct hnae3_handle *handle = hns3_get_handle(netdev); + + if (handle->ae_algo->ops->get_ts_info) + return handle->ae_algo->ops->get_ts_info(handle, info); + + return ethtool_op_get_ts_info(netdev, info); +} + static const struct ethtool_ops hns3vf_ethtool_ops = { .supported_coalesce_params = HNS3_ETHTOOL_COALESCE, .get_drvinfo = hns3_get_drvinfo, @@ -1662,6 +1673,7 @@ static const struct ethtool_ops hns3_ethtool_ops = { .get_module_eeprom = hns3_get_module_eeprom, .get_priv_flags = hns3_get_priv_flags, .set_priv_flags = hns3_set_priv_flags, + .get_ts_info = hns3_get_ts_info, }; void hns3_ethtool_set_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile index 6c28c8f6292c..a685392dbfe9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/Makefile @@ -7,6 +7,6 @@ ccflags-y := -I $(srctree)/drivers/net/ethernet/hisilicon/hns3 ccflags-y += -I $(srctree)/$(src) obj-$(CONFIG_HNS3_HCLGE) += hclge.o -hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o +hclge-objs = hclge_main.o hclge_cmd.o hclge_mdio.o hclge_tm.o hclge_mbx.o hclge_err.o hclge_debugfs.o hclge_ptp.o hclge-$(CONFIG_HNS3_DCB) += hclge_dcb.o diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 221811af9473..51be76f1795e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -130,6 +130,10 @@ enum hclge_opcode_type { HCLGE_OPC_COMMON_LOOPBACK = 0x0315, HCLGE_OPC_CONFIG_FEC_MODE = 0x031A, + /* PTP commands */ + HCLGE_OPC_PTP_INT_EN = 0x0501, + HCLGE_OPC_PTP_MODE_CFG = 0x0507, + /* PFC/Pause commands */ HCLGE_OPC_CFG_MAC_PAUSE_EN = 0x0701, HCLGE_OPC_CFG_PFC_PAUSE_EN = 0x0702, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index 0d433a5ff807..6fc50d09b9db 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -2173,6 +2173,57 @@ static int hclge_dbg_dump_vlan_config(struct hclge_dev *hdev, char *buf, return hclge_dbg_dump_vlan_offload_config(hdev, buf, len, &pos); } +static int hclge_dbg_dump_ptp_info(struct hclge_dev *hdev, char *buf, int len) +{ + struct hclge_ptp *ptp = hdev->ptp; + u32 sw_cfg = ptp->ptp_cfg; + unsigned int tx_start; + unsigned int last_rx; + int pos = 0; + u32 hw_cfg; + int ret; + + pos += scnprintf(buf + pos, len - pos, "phc %s's debug info:\n", + ptp->info.name); + pos += scnprintf(buf + pos, len - pos, "ptp enable: %s\n", + test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags) ? + "yes" : "no"); + pos += scnprintf(buf + pos, len - pos, "ptp tx enable: %s\n", + test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ? + "yes" : "no"); + pos += scnprintf(buf + pos, len - pos, "ptp rx enable: %s\n", + test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags) ? + "yes" : "no"); + + last_rx = jiffies_to_msecs(ptp->last_rx); + pos += scnprintf(buf + pos, len - pos, "last rx time: %lu.%lu\n", + last_rx / MSEC_PER_SEC, last_rx % MSEC_PER_SEC); + pos += scnprintf(buf + pos, len - pos, "rx count: %lu\n", ptp->rx_cnt); + + tx_start = jiffies_to_msecs(ptp->tx_start); + pos += scnprintf(buf + pos, len - pos, "last tx start time: %lu.%lu\n", + tx_start / MSEC_PER_SEC, tx_start % MSEC_PER_SEC); + pos += scnprintf(buf + pos, len - pos, "tx count: %lu\n", ptp->tx_cnt); + pos += scnprintf(buf + pos, len - pos, "tx skipped count: %lu\n", + ptp->tx_skipped); + pos += scnprintf(buf + pos, len - pos, "tx timeout count: %lu\n", + ptp->tx_timeout); + pos += scnprintf(buf + pos, len - pos, "last tx seqid: %u\n", + ptp->last_tx_seqid); + + ret = hclge_ptp_cfg_qry(hdev, &hw_cfg); + if (ret) + return ret; + + pos += scnprintf(buf + pos, len - pos, "sw_cfg: %#x, hw_cfg: %#x\n", + sw_cfg, hw_cfg); + + pos += scnprintf(buf + pos, len - pos, "tx type: %d, rx filter: %d\n", + ptp->ts_cfg.tx_type, ptp->ts_cfg.rx_filter); + + return 0; +} + static int hclge_dbg_dump_mac_uc(struct hclge_dev *hdev, char *buf, int len) { hclge_dbg_dump_mac_list(hdev, buf, len, true); @@ -2245,6 +2296,10 @@ static const struct hclge_dbg_func hclge_dbg_cmd_func[] = { .dbg_dump = hclge_dbg_dump_loopback, }, { + .cmd = HNAE3_DBG_CMD_PTP_INFO, + .dbg_dump = hclge_dbg_dump_ptp_info, + }, + { .cmd = HNAE3_DBG_CMD_INTERRUPT_INFO, .dbg_dump = hclge_dbg_dump_interrupt, }, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index c90d7c1550c5..f6fdf93c8cad 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -3346,6 +3346,12 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) hw_err_src_reg & HCLGE_RAS_REG_ERR_MASK) return HCLGE_VECTOR0_EVENT_ERR; + /* check for vector0 ptp event source */ + if (BIT(HCLGE_VECTOR0_REG_PTP_INT_B) & msix_src_reg) { + *clearval = msix_src_reg; + return HCLGE_VECTOR0_EVENT_PTP; + } + /* check for vector0 mailbox(=CMDQ RX) event source */ if (BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) { cmdq_src_reg &= ~BIT(HCLGE_VECTOR0_RX_CMDQ_INT_B); @@ -3365,6 +3371,7 @@ static void hclge_clear_event_cause(struct hclge_dev *hdev, u32 event_type, u32 regclr) { switch (event_type) { + case HCLGE_VECTOR0_EVENT_PTP: case HCLGE_VECTOR0_EVENT_RST: hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, regclr); break; @@ -3393,6 +3400,7 @@ static void hclge_enable_vector(struct hclge_misc_vector *vector, bool enable) static irqreturn_t hclge_misc_irq_handle(int irq, void *data) { struct hclge_dev *hdev = data; + unsigned long flags; u32 clearval = 0; u32 event_cause; @@ -3407,6 +3415,11 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) case HCLGE_VECTOR0_EVENT_RST: hclge_reset_task_schedule(hdev); break; + case HCLGE_VECTOR0_EVENT_PTP: + spin_lock_irqsave(&hdev->ptp->lock, flags); + hclge_ptp_clean_tx_hwts(hdev); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + break; case HCLGE_VECTOR0_EVENT_MBX: /* If we are here then, * 1. Either we are not handling any mbx task and we are not @@ -3428,7 +3441,8 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) hclge_clear_event_cause(hdev, event_cause, clearval); /* Enable interrupt if it is not caused by reset event or error event */ - if (event_cause == HCLGE_VECTOR0_EVENT_MBX || + if (event_cause == HCLGE_VECTOR0_EVENT_PTP || + event_cause == HCLGE_VECTOR0_EVENT_MBX || event_cause == HCLGE_VECTOR0_EVENT_OTHER) hclge_enable_vector(&hdev->misc_vector, true); @@ -4375,6 +4389,27 @@ out: hclge_task_schedule(hdev, delta); } +static void hclge_ptp_service_task(struct hclge_dev *hdev) +{ + unsigned long flags; + + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state) || + !test_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state) || + !time_is_before_jiffies(hdev->ptp->tx_start + HZ)) + return; + + /* to prevent concurrence with the irq handler */ + spin_lock_irqsave(&hdev->ptp->lock, flags); + + /* check HCLGE_STATE_PTP_TX_HANDLING here again, since the irq + * handler may handle it just before spin_lock_irqsave(). + */ + if (test_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) + hclge_ptp_clean_tx_hwts(hdev); + + spin_unlock_irqrestore(&hdev->ptp->lock, flags); +} + static void hclge_service_task(struct work_struct *work) { struct hclge_dev *hdev = @@ -4382,6 +4417,7 @@ static void hclge_service_task(struct work_struct *work) hclge_errhand_service_task(hdev); hclge_reset_service_task(hdev); + hclge_ptp_service_task(hdev); hclge_mailbox_service_task(hdev); hclge_periodic_service_task(hdev); @@ -9413,8 +9449,15 @@ static int hclge_do_ioctl(struct hnae3_handle *handle, struct ifreq *ifr, struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - if (!hdev->hw.mac.phydev) - return hclge_mii_ioctl(hdev, ifr, cmd); + switch (cmd) { + case SIOCGHWTSTAMP: + return hclge_ptp_get_cfg(hdev, ifr); + case SIOCSHWTSTAMP: + return hclge_ptp_set_cfg(hdev, ifr); + default: + if (!hdev->hw.mac.phydev) + return hclge_mii_ioctl(hdev, ifr, cmd); + } return phy_mii_ioctl(hdev->hw.mac.phydev, ifr, cmd); } @@ -11530,6 +11573,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) goto err_mdiobus_unreg; } + ret = hclge_ptp_init(hdev); + if (ret) + goto err_mdiobus_unreg; + INIT_KFIFO(hdev->mac_tnl_log); hclge_dcb_ops_set(hdev); @@ -11901,6 +11948,10 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) return ret; } + ret = hclge_ptp_init(hdev); + if (ret) + return ret; + /* Log and clear the hw errors those already occurred */ if (hnae3_dev_ras_imp_supported(hdev)) hclge_handle_occurred_error(hdev); @@ -11954,6 +12005,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_clear_vf_vlan(hdev); hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); + hclge_ptp_uninit(hdev); hclge_uninit_rxd_adv_layout(hdev); hclge_uninit_mac_table(hdev); hclge_del_all_fd_entries(hdev); @@ -12850,6 +12902,9 @@ static const struct hnae3_ae_ops hclge_ops = { .cls_flower_active = hclge_is_cls_flower_active, .get_phy_link_ksettings = hclge_get_phy_link_ksettings, .set_phy_link_ksettings = hclge_set_phy_link_ksettings, + .set_tx_hwts_info = hclge_ptp_set_tx_info, + .get_rx_hwts = hclge_ptp_get_rx_hwts, + .get_ts_info = hclge_ptp_get_ts_info, }; static struct hnae3_ae_algo ae_algo = { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 582972a6f60e..02852738ce21 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -10,6 +10,7 @@ #include <linux/kfifo.h> #include "hclge_cmd.h" +#include "hclge_ptp.h" #include "hnae3.h" #define HCLGE_MOD_VERSION "1.0" @@ -178,6 +179,7 @@ enum HLCGE_PORT_TYPE { #define HCLGE_FUN_RST_ING_B 0 /* Vector0 register bits define */ +#define HCLGE_VECTOR0_REG_PTP_INT_B 0 #define HCLGE_VECTOR0_GLOBALRESET_INT_B 5 #define HCLGE_VECTOR0_CORERESET_INT_B 6 #define HCLGE_VECTOR0_IMPRESET_INT_B 7 @@ -230,6 +232,8 @@ enum HCLGE_DEV_STATE { HCLGE_STATE_FD_TBL_CHANGED, HCLGE_STATE_FD_CLEAR_ALL, HCLGE_STATE_FD_USER_DEF_CHANGED, + HCLGE_STATE_PTP_EN, + HCLGE_STATE_PTP_TX_HANDLING, HCLGE_STATE_MAX }; @@ -237,6 +241,7 @@ enum hclge_evt_cause { HCLGE_VECTOR0_EVENT_RST, HCLGE_VECTOR0_EVENT_MBX, HCLGE_VECTOR0_EVENT_ERR, + HCLGE_VECTOR0_EVENT_PTP, HCLGE_VECTOR0_EVENT_OTHER, }; @@ -935,6 +940,7 @@ struct hclge_dev { /* affinity mask and notify for misc interrupt */ cpumask_t affinity_mask; struct irq_affinity_notify affinity_notify; + struct hclge_ptp *ptp; }; /* VPort level vlan tag configuration for TX direction */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c new file mode 100644 index 000000000000..b3eb8f109dbb --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c @@ -0,0 +1,544 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (c) 2021 Hisilicon Limited. + +#include <linux/skbuff.h> +#include "hclge_main.h" +#include "hnae3.h" + +static int hclge_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + u64 adj_val, adj_base, diff; + unsigned long flags; + bool is_neg = false; + u32 quo, numerator; + + if (ppb < 0) { + ppb = -ppb; + is_neg = true; + } + + adj_base = HCLGE_PTP_CYCLE_ADJ_BASE * HCLGE_PTP_CYCLE_ADJ_UNIT; + adj_val = adj_base * ppb; + diff = div_u64(adj_val, 1000000000ULL); + + if (is_neg) + adj_val = adj_base - diff; + else + adj_val = adj_base + diff; + + /* This clock cycle is defined by three part: quotient, numerator + * and denominator. For example, 2.5ns, the quotient is 2, + * denominator is fixed to HCLGE_PTP_CYCLE_ADJ_UNIT, and numerator + * is 0.5 * HCLGE_PTP_CYCLE_ADJ_UNIT. + */ + quo = div_u64_rem(adj_val, HCLGE_PTP_CYCLE_ADJ_UNIT, &numerator); + + spin_lock_irqsave(&hdev->ptp->lock, flags); + writel(quo, hdev->ptp->io_base + HCLGE_PTP_CYCLE_QUO_REG); + writel(numerator, hdev->ptp->io_base + HCLGE_PTP_CYCLE_NUM_REG); + writel(HCLGE_PTP_CYCLE_ADJ_UNIT, + hdev->ptp->io_base + HCLGE_PTP_CYCLE_DEN_REG); + writel(HCLGE_PTP_CYCLE_ADJ_EN, + hdev->ptp->io_base + HCLGE_PTP_CYCLE_CFG_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + return 0; +} + +bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + struct hclge_ptp *ptp = hdev->ptp; + + if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) || + test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) { + ptp->tx_skipped++; + return false; + } + + ptp->tx_start = jiffies; + ptp->tx_skb = skb_get(skb); + ptp->tx_cnt++; + + return true; +} + +void hclge_ptp_clean_tx_hwts(struct hclge_dev *hdev) +{ + struct sk_buff *skb = hdev->ptp->tx_skb; + struct skb_shared_hwtstamps hwts; + u32 hi, lo; + u64 ns; + + ns = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_NSEC_REG) & + HCLGE_PTP_TX_TS_NSEC_MASK; + lo = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_SEC_L_REG); + hi = readl(hdev->ptp->io_base + HCLGE_PTP_TX_TS_SEC_H_REG) & + HCLGE_PTP_TX_TS_SEC_H_MASK; + hdev->ptp->last_tx_seqid = readl(hdev->ptp->io_base + + HCLGE_PTP_TX_TS_SEQID_REG); + + if (skb) { + hdev->ptp->tx_skb = NULL; + hdev->ptp->tx_cleaned++; + + ns += (((u64)hi) << 32 | lo) * NSEC_PER_SEC; + hwts.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(skb, &hwts); + dev_kfree_skb_any(skb); + } + + clear_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state); +} + +void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, + u32 nsec, u32 sec) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + unsigned long flags; + u64 ns = nsec; + u32 sec_h; + + if (!test_bit(HCLGE_PTP_FLAG_RX_EN, &hdev->ptp->flags)) + return; + + /* Since the BD does not have enough space for the higher 16 bits of + * second, and this part will not change frequently, so read it + * from register. + */ + spin_lock_irqsave(&hdev->ptp->lock, flags); + sec_h = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_H_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + ns += (((u64)sec_h) << HCLGE_PTP_SEC_H_OFFSET | sec) * NSEC_PER_SEC; + skb_hwtstamps(skb)->hwtstamp = ns_to_ktime(ns); + hdev->ptp->last_rx = jiffies; + hdev->ptp->rx_cnt++; +} + +static int hclge_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + unsigned long flags; + u32 hi, lo; + u64 ns; + + spin_lock_irqsave(&hdev->ptp->lock, flags); + ns = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_NSEC_REG); + hi = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_H_REG); + lo = readl(hdev->ptp->io_base + HCLGE_PTP_CUR_TIME_SEC_L_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + ns += (((u64)hi) << HCLGE_PTP_SEC_H_OFFSET | lo) * NSEC_PER_SEC; + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int hclge_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + unsigned long flags; + + spin_lock_irqsave(&hdev->ptp->lock, flags); + writel(ts->tv_nsec, hdev->ptp->io_base + HCLGE_PTP_TIME_NSEC_REG); + writel(ts->tv_sec >> HCLGE_PTP_SEC_H_OFFSET, + hdev->ptp->io_base + HCLGE_PTP_TIME_SEC_H_REG); + writel(ts->tv_sec & HCLGE_PTP_SEC_L_MASK, + hdev->ptp->io_base + HCLGE_PTP_TIME_SEC_L_REG); + /* synchronize the time of phc */ + writel(HCLGE_PTP_TIME_SYNC_EN, + hdev->ptp->io_base + HCLGE_PTP_TIME_SYNC_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + return 0; +} + +static int hclge_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct hclge_dev *hdev = hclge_ptp_get_hdev(ptp); + unsigned long flags; + bool is_neg = false; + u32 adj_val = 0; + + if (delta < 0) { + adj_val |= HCLGE_PTP_TIME_NSEC_NEG; + delta = -delta; + is_neg = true; + } + + if (delta > HCLGE_PTP_TIME_NSEC_MASK) { + struct timespec64 ts; + s64 ns; + + hclge_ptp_gettimex(ptp, &ts, NULL); + ns = timespec64_to_ns(&ts); + ns = is_neg ? ns - delta : ns + delta; + ts = ns_to_timespec64(ns); + return hclge_ptp_settime(ptp, &ts); + } + + adj_val |= delta & HCLGE_PTP_TIME_NSEC_MASK; + + spin_lock_irqsave(&hdev->ptp->lock, flags); + writel(adj_val, hdev->ptp->io_base + HCLGE_PTP_TIME_NSEC_REG); + writel(HCLGE_PTP_TIME_ADJ_EN, + hdev->ptp->io_base + HCLGE_PTP_TIME_ADJ_REG); + spin_unlock_irqrestore(&hdev->ptp->lock, flags); + + return 0; +} + +int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr) +{ + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, &hdev->ptp->ts_cfg, + sizeof(struct hwtstamp_config)) ? -EFAULT : 0; +} + +static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en) +{ + struct hclge_ptp_int_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_ptp_int_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_INT_EN, false); + req->int_en = en ? 1 : 0; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to %s ptp interrupt, ret = %d\n", + en ? "enable" : "disable", ret); + + return ret; +} + +int hclge_ptp_cfg_qry(struct hclge_dev *hdev, u32 *cfg) +{ + struct hclge_ptp_cfg_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_ptp_cfg_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_MODE_CFG, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to query ptp config, ret = %d\n", ret); + return ret; + } + + *cfg = le32_to_cpu(req->cfg); + + return 0; +} + +static int hclge_ptp_cfg(struct hclge_dev *hdev, u32 cfg) +{ + struct hclge_ptp_cfg_cmd *req; + struct hclge_desc desc; + int ret; + + req = (struct hclge_ptp_cfg_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PTP_MODE_CFG, false); + req->cfg = cpu_to_le32(cfg); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "failed to config ptp, ret = %d\n", ret); + + return ret; +} + +static int hclge_ptp_set_tx_mode(struct hwtstamp_config *cfg, + unsigned long *flags, u32 *ptp_cfg) +{ + switch (cfg->tx_type) { + case HWTSTAMP_TX_OFF: + clear_bit(HCLGE_PTP_FLAG_TX_EN, flags); + break; + case HWTSTAMP_TX_ON: + set_bit(HCLGE_PTP_FLAG_TX_EN, flags); + *ptp_cfg |= HCLGE_PTP_TX_EN_B; + break; + default: + return -ERANGE; + } + + return 0; +} + +static int hclge_ptp_set_rx_mode(struct hwtstamp_config *cfg, + unsigned long *flags, u32 *ptp_cfg) +{ + int rx_filter = cfg->rx_filter; + + switch (cfg->rx_filter) { + case HWTSTAMP_FILTER_NONE: + clear_bit(HCLGE_PTP_FLAG_RX_EN, flags); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + set_bit(HCLGE_PTP_FLAG_RX_EN, flags); + *ptp_cfg |= HCLGE_PTP_RX_EN_B; + *ptp_cfg |= HCLGE_PTP_UDP_FULL_TYPE << HCLGE_PTP_UDP_EN_SHIFT; + rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + set_bit(HCLGE_PTP_FLAG_RX_EN, flags); + *ptp_cfg |= HCLGE_PTP_RX_EN_B; + *ptp_cfg |= HCLGE_PTP_UDP_FULL_TYPE << HCLGE_PTP_UDP_EN_SHIFT; + *ptp_cfg |= HCLGE_PTP_MSG1_V2_DEFAULT << HCLGE_PTP_MSG1_SHIFT; + *ptp_cfg |= HCLGE_PTP_MSG0_V2_EVENT << HCLGE_PTP_MSG0_SHIFT; + *ptp_cfg |= HCLGE_PTP_MSG_TYPE_V2 << HCLGE_PTP_MSG_TYPE_SHIFT; + rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_ALL: + default: + return -ERANGE; + } + + cfg->rx_filter = rx_filter; + + return 0; +} + +static int hclge_ptp_set_ts_mode(struct hclge_dev *hdev, + struct hwtstamp_config *cfg) +{ + unsigned long flags = hdev->ptp->flags; + u32 ptp_cfg = 0; + int ret; + + if (test_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags)) + ptp_cfg |= HCLGE_PTP_EN_B; + + ret = hclge_ptp_set_tx_mode(cfg, &flags, &ptp_cfg); + if (ret) + return ret; + + ret = hclge_ptp_set_rx_mode(cfg, &flags, &ptp_cfg); + if (ret) + return ret; + + ret = hclge_ptp_cfg(hdev, ptp_cfg); + if (ret) + return ret; + + hdev->ptp->flags = flags; + hdev->ptp->ptp_cfg = ptp_cfg; + + return 0; +} + +int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr) +{ + struct hwtstamp_config cfg; + int ret; + + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) { + dev_err(&hdev->pdev->dev, "phc is unsupported\n"); + return -EOPNOTSUPP; + } + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + ret = hclge_ptp_set_ts_mode(hdev, &cfg); + if (ret) + return ret; + + hdev->ptp->ts_cfg = cfg; + + return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +int hclge_ptp_get_ts_info(struct hnae3_handle *handle, + struct ethtool_ts_info *info) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + if (!test_bit(HCLGE_STATE_PTP_EN, &hdev->state)) { + dev_err(&hdev->pdev->dev, "phc is unsupported\n"); + return -EOPNOTSUPP; + } + + info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (hdev->ptp->clock) + info->phc_index = ptp_clock_index(hdev->ptp->clock); + else + info->phc_index = -1; + + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); + + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ); + + info->rx_filters |= BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); + + return 0; +} + +static int hclge_ptp_create_clock(struct hclge_dev *hdev) +{ +#define HCLGE_PTP_NAME_LEN 32 + + struct hclge_ptp *ptp; + + ptp = devm_kzalloc(&hdev->pdev->dev, sizeof(*ptp), GFP_KERNEL); + if (!ptp) + return -ENOMEM; + + ptp->hdev = hdev; + snprintf(ptp->info.name, HCLGE_PTP_NAME_LEN, "%s", + HCLGE_DRIVER_NAME); + ptp->info.owner = THIS_MODULE; + ptp->info.max_adj = HCLGE_PTP_CYCLE_ADJ_MAX; + ptp->info.n_ext_ts = 0; + ptp->info.pps = 0; + ptp->info.adjfreq = hclge_ptp_adjfreq; + ptp->info.adjtime = hclge_ptp_adjtime; + ptp->info.gettimex64 = hclge_ptp_gettimex; + ptp->info.settime64 = hclge_ptp_settime; + + ptp->info.n_alarm = 0; + ptp->clock = ptp_clock_register(&ptp->info, &hdev->pdev->dev); + if (IS_ERR(ptp->clock)) { + dev_err(&hdev->pdev->dev, + "%d failed to register ptp clock, ret = %ld\n", + ptp->info.n_alarm, PTR_ERR(ptp->clock)); + return -ENODEV; + } else if (!ptp->clock) { + dev_err(&hdev->pdev->dev, "failed to register ptp clock\n"); + return -ENODEV; + } + + spin_lock_init(&ptp->lock); + ptp->io_base = hdev->hw.io_base + HCLGE_PTP_REG_OFFSET; + ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE; + ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF; + hdev->ptp = ptp; + + return 0; +} + +static void hclge_ptp_destroy_clock(struct hclge_dev *hdev) +{ + ptp_clock_unregister(hdev->ptp->clock); + hdev->ptp->clock = NULL; + devm_kfree(&hdev->pdev->dev, hdev->ptp); + hdev->ptp = NULL; +} + +int hclge_ptp_init(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); + struct timespec64 ts; + int ret; + + if (!test_bit(HNAE3_DEV_SUPPORT_PTP_B, ae_dev->caps)) + return 0; + + if (!hdev->ptp) { + ret = hclge_ptp_create_clock(hdev); + if (ret) + return ret; + } + + ret = hclge_ptp_int_en(hdev, true); + if (ret) + goto out; + + set_bit(HCLGE_PTP_FLAG_EN, &hdev->ptp->flags); + ret = hclge_ptp_adjfreq(&hdev->ptp->info, 0); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to init freq, ret = %d\n", ret); + goto out; + } + + ret = hclge_ptp_set_ts_mode(hdev, &hdev->ptp->ts_cfg); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to init ts mode, ret = %d\n", ret); + goto out; + } + + ktime_get_real_ts64(&ts); + ret = hclge_ptp_settime(&hdev->ptp->info, &ts); + if (ret) { + dev_err(&hdev->pdev->dev, + "failed to init ts time, ret = %d\n", ret); + goto out; + } + + set_bit(HCLGE_STATE_PTP_EN, &hdev->state); + dev_info(&hdev->pdev->dev, "phc initializes ok!\n"); + + return 0; + +out: + hclge_ptp_destroy_clock(hdev); + + return ret; +} + +void hclge_ptp_uninit(struct hclge_dev *hdev) +{ + struct hclge_ptp *ptp = hdev->ptp; + + if (!ptp) + return; + + hclge_ptp_int_en(hdev, false); + clear_bit(HCLGE_STATE_PTP_EN, &hdev->state); + clear_bit(HCLGE_PTP_FLAG_EN, &ptp->flags); + ptp->ts_cfg.rx_filter = HWTSTAMP_FILTER_NONE; + ptp->ts_cfg.tx_type = HWTSTAMP_TX_OFF; + + if (hclge_ptp_set_ts_mode(hdev, &ptp->ts_cfg)) + dev_err(&hdev->pdev->dev, "failed to disable phc\n"); + + if (ptp->tx_skb) { + struct sk_buff *skb = ptp->tx_skb; + + ptp->tx_skb = NULL; + dev_kfree_skb_any(skb); + } + + hclge_ptp_destroy_clock(hdev); +} diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h new file mode 100644 index 000000000000..b3ca7afdaaa6 --- /dev/null +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +// Copyright (c) 2021 Hisilicon Limited. + +#ifndef __HCLGE_PTP_H +#define __HCLGE_PTP_H + +#include <linux/ptp_clock_kernel.h> +#include <linux/net_tstamp.h> +#include <linux/types.h> + +#define HCLGE_PTP_REG_OFFSET 0x29000 + +#define HCLGE_PTP_TX_TS_SEQID_REG 0x0 +#define HCLGE_PTP_TX_TS_NSEC_REG 0x4 +#define HCLGE_PTP_TX_TS_NSEC_MASK GENMASK(29, 0) +#define HCLGE_PTP_TX_TS_SEC_L_REG 0x8 +#define HCLGE_PTP_TX_TS_SEC_H_REG 0xC +#define HCLGE_PTP_TX_TS_SEC_H_MASK GENMASK(15, 0) +#define HCLGE_PTP_TX_TS_CNT_REG 0x30 + +#define HCLGE_PTP_TIME_SEC_H_REG 0x50 +#define HCLGE_PTP_TIME_SEC_H_MASK GENMASK(15, 0) +#define HCLGE_PTP_TIME_SEC_L_REG 0x54 +#define HCLGE_PTP_TIME_NSEC_REG 0x58 +#define HCLGE_PTP_TIME_NSEC_MASK GENMASK(29, 0) +#define HCLGE_PTP_TIME_NSEC_NEG BIT(31) +#define HCLGE_PTP_TIME_SYNC_REG 0x5C +#define HCLGE_PTP_TIME_SYNC_EN BIT(0) +#define HCLGE_PTP_TIME_ADJ_REG 0x60 +#define HCLGE_PTP_TIME_ADJ_EN BIT(0) +#define HCLGE_PTP_CYCLE_QUO_REG 0x64 +#define HCLGE_PTP_CYCLE_DEN_REG 0x68 +#define HCLGE_PTP_CYCLE_NUM_REG 0x6C +#define HCLGE_PTP_CYCLE_CFG_REG 0x70 +#define HCLGE_PTP_CYCLE_ADJ_EN BIT(0) +#define HCLGE_PTP_CUR_TIME_SEC_H_REG 0x74 +#define HCLGE_PTP_CUR_TIME_SEC_L_REG 0x78 +#define HCLGE_PTP_CUR_TIME_NSEC_REG 0x7C + +#define HCLGE_PTP_CYCLE_ADJ_BASE 2 +#define HCLGE_PTP_CYCLE_ADJ_MAX 500000000 +#define HCLGE_PTP_CYCLE_ADJ_UNIT 100000000 +#define HCLGE_PTP_SEC_H_OFFSET 32u +#define HCLGE_PTP_SEC_L_MASK GENMASK(31, 0) + +#define HCLGE_PTP_FLAG_EN BIT(0) +#define HCLGE_PTP_FLAG_TX_EN BIT(1) +#define HCLGE_PTP_FLAG_RX_EN BIT(2) + +struct hclge_ptp { + struct hclge_dev *hdev; + struct ptp_clock *clock; + struct sk_buff *tx_skb; + unsigned long flags; + void __iomem *io_base; + struct ptp_clock_info info; + struct hwtstamp_config ts_cfg; + spinlock_t lock; /* protects ptp registers */ + u32 ptp_cfg; + u32 last_tx_seqid; + unsigned long tx_start; + unsigned long tx_cnt; + unsigned long tx_skipped; + unsigned long tx_cleaned; + unsigned long last_rx; + unsigned long rx_cnt; + unsigned long tx_timeout; +}; + +struct hclge_ptp_int_cmd { +#define HCLGE_PTP_INT_EN_B BIT(0) + + u8 int_en; + u8 rsvd[23]; +}; + +enum hclge_ptp_udp_type { + HCLGE_PTP_UDP_NOT_TYPE, + HCLGE_PTP_UDP_P13F_TYPE, + HCLGE_PTP_UDP_P140_TYPE, + HCLGE_PTP_UDP_FULL_TYPE, +}; + +enum hclge_ptp_msg_type { + HCLGE_PTP_MSG_TYPE_V2_L2, + HCLGE_PTP_MSG_TYPE_V2, + HCLGE_PTP_MSG_TYPE_V2_EVENT, +}; + +enum hclge_ptp_msg0_type { + HCLGE_PTP_MSG0_V2_DELAY_REQ = 1, + HCLGE_PTP_MSG0_V2_PDELAY_REQ, + HCLGE_PTP_MSG0_V2_DELAY_RESP, + HCLGE_PTP_MSG0_V2_EVENT = 0xF, +}; + +#define HCLGE_PTP_MSG1_V2_DEFAULT 1 + +struct hclge_ptp_cfg_cmd { +#define HCLGE_PTP_EN_B BIT(0) +#define HCLGE_PTP_TX_EN_B BIT(1) +#define HCLGE_PTP_RX_EN_B BIT(2) +#define HCLGE_PTP_UDP_EN_SHIFT 3 +#define HCLGE_PTP_UDP_EN_MASK GENMASK(4, 3) +#define HCLGE_PTP_MSG_TYPE_SHIFT 8 +#define HCLGE_PTP_MSG_TYPE_MASK GENMASK(9, 8) +#define HCLGE_PTP_MSG1_SHIFT 16 +#define HCLGE_PTP_MSG1_MASK GENMASK(19, 16) +#define HCLGE_PTP_MSG0_SHIFT 24 +#define HCLGE_PTP_MSG0_MASK GENMASK(27, 24) + + __le32 cfg; + u8 rsvd[20]; +}; + +static inline struct hclge_dev *hclge_ptp_get_hdev(struct ptp_clock_info *info) +{ + struct hclge_ptp *ptp = container_of(info, struct hclge_ptp, info); + + return ptp->hdev; +} + +bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb); +void hclge_ptp_clean_tx_hwts(struct hclge_dev *dev); +void hclge_ptp_get_rx_hwts(struct hnae3_handle *handle, struct sk_buff *skb, + u32 nsec, u32 sec); +int hclge_ptp_get_cfg(struct hclge_dev *hdev, struct ifreq *ifr); +int hclge_ptp_set_cfg(struct hclge_dev *hdev, struct ifreq *ifr); +int hclge_ptp_init(struct hclge_dev *hdev); +void hclge_ptp_uninit(struct hclge_dev *hdev); +int hclge_ptp_get_ts_info(struct hnae3_handle *handle, + struct ethtool_ts_info *info); +int hclge_ptp_cfg_qry(struct hclge_dev *hdev, u32 *cfg); +#endif diff --git a/drivers/net/ethernet/marvell/octeontx2/af/common.h b/drivers/net/ethernet/marvell/octeontx2/af/common.h index e66109367487..47f5ed006a93 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/common.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/common.h @@ -197,6 +197,11 @@ enum nix_scheduler { #define SDP_CHANNELS 256 +/* The mask is to extract lower 10-bits of channel number + * which CPT will pass to X2P. + */ +#define NIX_CHAN_CPT_X2P_MASK (0x3ffull) + /* NIX LSO format indices. * As of now TSO is the only one using, so statically assigning indices. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h index cedb2616c509..aee6a6f31b0d 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/mbox.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/mbox.h @@ -134,6 +134,7 @@ M(MSIX_OFFSET, 0x005, msix_offset, msg_req, msix_offset_rsp) \ M(VF_FLR, 0x006, vf_flr, msg_req, msg_rsp) \ M(PTP_OP, 0x007, ptp_op, ptp_req, ptp_rsp) \ M(GET_HW_CAP, 0x008, get_hw_cap, msg_req, get_hw_cap_rsp) \ +M(SET_VF_PERM, 0x00b, set_vf_perm, set_vf_perm, msg_rsp) \ /* CGX mbox IDs (range 0x200 - 0x3FF) */ \ M(CGX_START_RXTX, 0x200, cgx_start_rxtx, msg_req, msg_rsp) \ M(CGX_STOP_RXTX, 0x201, cgx_stop_rxtx, msg_req, msg_rsp) \ @@ -611,7 +612,9 @@ enum nix_af_status { NIX_AF_INVAL_SSO_PF_FUNC = -420, NIX_AF_ERR_TX_VTAG_NOSPC = -421, NIX_AF_ERR_RX_VTAG_INUSE = -422, - NIX_AF_ERR_NPC_KEY_NOT_SUPP = -423, + NIX_AF_ERR_PTP_CONFIG_FAIL = -423, + NIX_AF_ERR_NPC_KEY_NOT_SUPP = -424, + NIX_AF_ERR_INVALID_NIXBLK = -425, }; /* For NIX RX vtag action */ @@ -913,6 +916,7 @@ struct nix_rx_mode { #define NIX_RX_MODE_UCAST BIT(0) #define NIX_RX_MODE_PROMISC BIT(1) #define NIX_RX_MODE_ALLMULTI BIT(2) +#define NIX_RX_MODE_USE_MCE BIT(3) u16 mode; }; @@ -1228,6 +1232,14 @@ struct ptp_rsp { u64 clk; }; +struct set_vf_perm { + struct mbox_msghdr hdr; + u16 vf; +#define RESET_VF_PERM BIT_ULL(0) +#define VF_TRUSTED BIT_ULL(1) + u64 flags; +}; + /* CPT mailbox error codes * Range 901 - 1000. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/af/npc.h b/drivers/net/ethernet/marvell/octeontx2/af/npc.h index fe19704173a1..19bad9a59c8f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/npc.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/npc.h @@ -438,7 +438,8 @@ struct nix_tx_action { /* NPC MCAM reserved entry index per nixlf */ #define NIXLF_UCAST_ENTRY 0 #define NIXLF_BCAST_ENTRY 1 -#define NIXLF_PROMISC_ENTRY 2 +#define NIXLF_ALLMULTI_ENTRY 2 +#define NIXLF_PROMISC_ENTRY 3 struct npc_coalesced_kpu_prfl { #define NPC_SIGN 0x00666f727063706e diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c index bc71a9c462de..f11a02d6b6ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c @@ -1758,6 +1758,48 @@ int rvu_mbox_handler_get_hw_cap(struct rvu *rvu, struct msg_req *req, return 0; } +int rvu_mbox_handler_set_vf_perm(struct rvu *rvu, struct set_vf_perm *req, + struct msg_rsp *rsp) +{ + struct rvu_hwinfo *hw = rvu->hw; + u16 pcifunc = req->hdr.pcifunc; + struct rvu_pfvf *pfvf; + int blkaddr, nixlf; + u16 target; + + /* Only PF can add VF permissions */ + if ((pcifunc & RVU_PFVF_FUNC_MASK) || is_afvf(pcifunc)) + return -EOPNOTSUPP; + + target = (pcifunc & ~RVU_PFVF_FUNC_MASK) | (req->vf + 1); + pfvf = rvu_get_pfvf(rvu, target); + + if (req->flags & RESET_VF_PERM) { + pfvf->flags &= RVU_CLEAR_VF_PERM; + } else if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) ^ + (req->flags & VF_TRUSTED)) { + change_bit(PF_SET_VF_TRUSTED, &pfvf->flags); + /* disable multicast and promisc entries */ + if (!test_bit(PF_SET_VF_TRUSTED, &pfvf->flags)) { + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, target); + if (blkaddr < 0) + return 0; + nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], + target, 0); + if (nixlf < 0) + return 0; + npc_enadis_default_mce_entry(rvu, target, nixlf, + NIXLF_ALLMULTI_ENTRY, + false); + npc_enadis_default_mce_entry(rvu, target, nixlf, + NIXLF_PROMISC_ENTRY, + false); + } + } + + return 0; +} + static int rvu_process_mbox_msg(struct otx2_mbox *mbox, int devid, struct mbox_msghdr *req) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h index 74ed929f101b..c88dab7747ef 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h @@ -223,13 +223,17 @@ struct rvu_pfvf { u16 maxlen; u16 minlen; - u8 pf_set_vf_cfg; u8 mac_addr[ETH_ALEN]; /* MAC address of this PF/VF */ u8 default_mac[ETH_ALEN]; /* MAC address from FWdata */ - /* Broadcast pkt replication info */ + /* Broadcast/Multicast/Promisc pkt replication info */ u16 bcast_mce_idx; + u16 mcast_mce_idx; + u16 promisc_mce_idx; struct nix_mce_list bcast_mce_list; + struct nix_mce_list mcast_mce_list; + struct nix_mce_list promisc_mce_list; + bool use_mce_list; struct rvu_npc_mcam_rule *def_ucast_rule; @@ -239,8 +243,18 @@ struct rvu_pfvf { u8 nix_blkaddr; /* BLKADDR_NIX0/1 assigned to this PF */ u8 nix_rx_intf; /* NIX0_RX/NIX1_RX interface to NPC */ u8 nix_tx_intf; /* NIX0_TX/NIX1_TX interface to NPC */ + unsigned long flags; }; +enum rvu_pfvf_flags { + NIXLF_INITIALIZED = 0, + PF_SET_VF_MAC, + PF_SET_VF_CFG, + PF_SET_VF_TRUSTED, +}; + +#define RVU_CLEAR_VF_PERM ~GENMASK(PF_SET_VF_TRUSTED, PF_SET_VF_MAC) + struct nix_txsch { struct rsrc_bmap schq; u8 lvl; @@ -548,11 +562,16 @@ static inline u16 rvu_nix_chan_cpt(struct rvu *rvu, u8 chan) /* Function Prototypes * RVU */ -static inline int is_afvf(u16 pcifunc) +static inline bool is_afvf(u16 pcifunc) { return !(pcifunc & ~RVU_PFVF_FUNC_MASK); } +static inline bool is_vf(u16 pcifunc) +{ + return !!(pcifunc & RVU_PFVF_FUNC_MASK); +} + /* check if PF_FUNC is AF */ static inline bool is_pffunc_af(u16 pcifunc) { @@ -608,6 +627,12 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id) *lmac_id = (map & 0xF); } +static inline bool is_cgx_vf(struct rvu *rvu, u16 pcifunc) +{ + return ((pcifunc & RVU_PFVF_FUNC_MASK) && + is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))); +} + #define M(_name, _id, fn_name, req, rsp) \ int rvu_mbox_handler_ ## fn_name(struct rvu *, struct req *, struct rsp *); MBOX_MESSAGES @@ -637,10 +662,16 @@ void rvu_nix_freemem(struct rvu *rvu); int rvu_get_nixlf_count(struct rvu *rvu); void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int npalf); int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr); -int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add); +int nix_update_mce_list(struct rvu *rvu, u16 pcifunc, + struct nix_mce_list *mce_list, + int mce_idx, int mcam_index, bool add); +void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type, + struct nix_mce_list **mce_list, int *mce_idx); struct nix_hw *get_nix_hw(struct rvu_hwinfo *hw, int blkaddr); int rvu_get_next_nix_blkaddr(struct rvu *rvu, int blkaddr); void rvu_nix_reset_mac(struct rvu_pfvf *pfvf, int pcifunc); +int nix_get_struct_ptrs(struct rvu *rvu, u16 pcifunc, + struct nix_hw **nix_hw, int *blkaddr); /* NPC APIs */ int rvu_npc_init(struct rvu *rvu); @@ -651,13 +682,19 @@ int npc_config_ts_kpuaction(struct rvu *rvu, int pf, u16 pcifunc, bool en); void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan, u8 *mac_addr); void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, - int nixlf, u64 chan, u8 chan_cnt, - bool allmulti); -void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); -void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf); + int nixlf, u64 chan, u8 chan_cnt); +void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable); void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan); -void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable); +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable); +void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + u64 chan); +void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable); +void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, + int nixlf, int type, bool enable); void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_free_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf); void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf); diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c index 9bf8eaabf9ab..7103f8216ad1 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c @@ -2132,6 +2132,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused) struct rvu *rvu = s->private; struct npc_mcam *mcam; int pf, vf = -1; + bool enabled; int blkaddr; u16 target; u64 hits; @@ -2173,7 +2174,9 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused) } rvu_dbg_npc_mcam_show_action(s, iter); - seq_printf(s, "\tenabled: %s\n", iter->enable ? "yes" : "no"); + + enabled = is_mcam_entry_enabled(rvu, mcam, blkaddr, iter->entry); + seq_printf(s, "\tenabled: %s\n", enabled ? "yes" : "no"); if (!iter->has_cntr) continue; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c index 174ef09f9069..d8cb665b7d8a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c @@ -21,6 +21,8 @@ static void nix_free_tx_vtag_entries(struct rvu *rvu, u16 pcifunc); static int rvu_nix_get_bpid(struct rvu *rvu, struct nix_bp_cfg_req *req, int type, int chan_id); +static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc, + int type, bool add); enum mc_tbl_sz { MC_TBL_SZ_256, @@ -132,6 +134,22 @@ int nix_get_nixlf(struct rvu *rvu, u16 pcifunc, int *nixlf, int *nix_blkaddr) return 0; } +int nix_get_struct_ptrs(struct rvu *rvu, u16 pcifunc, + struct nix_hw **nix_hw, int *blkaddr) +{ + struct rvu_pfvf *pfvf; + + pfvf = rvu_get_pfvf(rvu, pcifunc); + *blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (!pfvf->nixlf || *blkaddr < 0) + return NIX_AF_ERR_AF_LF_INVALID; + + *nix_hw = get_nix_hw(rvu->hw, *blkaddr); + if (!*nix_hw) + return NIX_AF_ERR_INVALID_NIXBLK; + return 0; +} + static void nix_mce_list_init(struct nix_mce_list *list, int max) { INIT_HLIST_HEAD(&list->head); @@ -274,7 +292,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) pfvf->tx_chan_cnt = 1; rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, - pfvf->rx_chan_cnt, false); + pfvf->rx_chan_cnt); break; } @@ -285,16 +303,17 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf) pfvf->rx_chan_base, pfvf->mac_addr); /* Add this PF_FUNC to bcast pkt replication list */ - err = nix_update_bcast_mce_list(rvu, pcifunc, true); + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_BCAST_ENTRY, true); if (err) { dev_err(rvu->dev, "Bcast list, failed to enable PF_FUNC 0x%x\n", pcifunc); return err; } - + /* Install MCAM rule matching Ethernet broadcast mac address */ rvu_npc_install_bcast_match_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base); + pfvf->maxlen = NIC_HW_MIN_FRS; pfvf->minlen = NIC_HW_MIN_FRS; @@ -310,7 +329,7 @@ static void nix_interface_deinit(struct rvu *rvu, u16 pcifunc, u8 nixlf) pfvf->minlen = 0; /* Remove this PF_FUNC from bcast pkt replication list */ - err = nix_update_bcast_mce_list(rvu, pcifunc, false); + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_BCAST_ENTRY, false); if (err) { dev_err(rvu->dev, "Bcast list, failed to disable PF_FUNC 0x%x\n", @@ -2203,8 +2222,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw, aq_req.op = op; aq_req.qidx = mce; - /* Forward bcast pkts to RQ0, RSS not needed */ - aq_req.mce.op = 0; + /* Use RSS with RSS index 0 */ + aq_req.mce.op = 1; aq_req.mce.index = 0; aq_req.mce.eol = eol; aq_req.mce.pf_func = pcifunc; @@ -2222,8 +2241,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw, return 0; } -static int nix_update_mce_list(struct nix_mce_list *mce_list, - u16 pcifunc, bool add) +static int nix_update_mce_list_entry(struct nix_mce_list *mce_list, + u16 pcifunc, bool add) { struct mce *mce, *tail = NULL; bool delete = false; @@ -2234,6 +2253,9 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, if (mce->pcifunc == pcifunc && !add) { delete = true; break; + } else if (mce->pcifunc == pcifunc && add) { + /* entry already exists */ + return 0; } tail = mce; } @@ -2261,36 +2283,23 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list, return 0; } -int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) +int nix_update_mce_list(struct rvu *rvu, u16 pcifunc, + struct nix_mce_list *mce_list, + int mce_idx, int mcam_index, bool add) { - int err = 0, idx, next_idx, last_idx; - struct nix_mce_list *mce_list; + int err = 0, idx, next_idx, last_idx, blkaddr, npc_blkaddr; + struct npc_mcam *mcam = &rvu->hw->mcam; struct nix_mcast *mcast; struct nix_hw *nix_hw; - struct rvu_pfvf *pfvf; struct mce *mce; - int blkaddr; - - /* Broadcast pkt replication is not needed for AF's VFs, hence skip */ - if (is_afvf(pcifunc)) - return 0; - - blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); - if (blkaddr < 0) - return 0; - nix_hw = get_nix_hw(rvu->hw, blkaddr); - if (!nix_hw) - return 0; - - mcast = &nix_hw->mcast; + if (!mce_list) + return -EINVAL; /* Get this PF/VF func's MCE index */ - pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); - idx = pfvf->bcast_mce_idx + (pcifunc & RVU_PFVF_FUNC_MASK); + idx = mce_idx + (pcifunc & RVU_PFVF_FUNC_MASK); - mce_list = &pfvf->bcast_mce_list; - if (idx > (pfvf->bcast_mce_idx + mce_list->max)) { + if (idx > (mce_idx + mce_list->max)) { dev_err(rvu->dev, "%s: Idx %d > max MCE idx %d, for PF%d bcast list\n", __func__, idx, mce_list->max, @@ -2298,20 +2307,26 @@ int nix_update_bcast_mce_list(struct rvu *rvu, u16 pcifunc, bool add) return -EINVAL; } + err = nix_get_struct_ptrs(rvu, pcifunc, &nix_hw, &blkaddr); + if (err) + return err; + + mcast = &nix_hw->mcast; mutex_lock(&mcast->mce_lock); - err = nix_update_mce_list(mce_list, pcifunc, add); + err = nix_update_mce_list_entry(mce_list, pcifunc, add); if (err) goto end; /* Disable MCAM entry in NPC */ if (!mce_list->count) { - rvu_npc_enable_bcast_entry(rvu, pcifunc, false); + npc_blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + npc_enable_mcam_entry(rvu, mcam, npc_blkaddr, mcam_index, false); goto end; } /* Dump the updated list to HW */ - idx = pfvf->bcast_mce_idx; + idx = mce_idx; last_idx = idx + mce_list->count - 1; hlist_for_each_entry(mce, &mce_list->head, node) { if (idx > last_idx) @@ -2332,7 +2347,71 @@ end: return err; } -static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) +void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type, + struct nix_mce_list **mce_list, int *mce_idx) +{ + struct rvu_hwinfo *hw = rvu->hw; + struct rvu_pfvf *pfvf; + + if (!hw->cap.nix_rx_multicast || + !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc & ~RVU_PFVF_FUNC_MASK))) { + *mce_list = NULL; + *mce_idx = 0; + return; + } + + /* Get this PF/VF func's MCE index */ + pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + + if (type == NIXLF_BCAST_ENTRY) { + *mce_list = &pfvf->bcast_mce_list; + *mce_idx = pfvf->bcast_mce_idx; + } else if (type == NIXLF_ALLMULTI_ENTRY) { + *mce_list = &pfvf->mcast_mce_list; + *mce_idx = pfvf->mcast_mce_idx; + } else if (type == NIXLF_PROMISC_ENTRY) { + *mce_list = &pfvf->promisc_mce_list; + *mce_idx = pfvf->promisc_mce_idx; + } else { + *mce_list = NULL; + *mce_idx = 0; + } +} + +static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc, + int type, bool add) +{ + int err = 0, nixlf, blkaddr, mcam_index, mce_idx; + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + struct nix_mce_list *mce_list; + + /* skip multicast pkt replication for AF's VFs */ + if (is_afvf(pcifunc)) + return 0; + + if (!hw->cap.nix_rx_multicast) + return 0; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc); + if (blkaddr < 0) + return -EINVAL; + + nixlf = rvu_get_lf(rvu, &hw->block[blkaddr], pcifunc, 0); + if (nixlf < 0) + return -EINVAL; + + nix_get_mce_list(rvu, pcifunc, type, &mce_list, &mce_idx); + + mcam_index = npc_get_nixlf_mcam_index(mcam, + pcifunc & ~RVU_PFVF_FUNC_MASK, + nixlf, type); + err = nix_update_mce_list(rvu, pcifunc, mce_list, + mce_idx, mcam_index, add); + return err; +} + +static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw) { struct nix_mcast *mcast = &nix_hw->mcast; int err, pf, numvfs, idx; @@ -2355,11 +2434,18 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) if (pfvf->nix_blkaddr != nix_hw->blkaddr) continue; - /* Save the start MCE */ + /* save start idx of broadcast mce list */ pfvf->bcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); - nix_mce_list_init(&pfvf->bcast_mce_list, numvfs + 1); + /* save start idx of multicast mce list */ + pfvf->mcast_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); + nix_mce_list_init(&pfvf->mcast_mce_list, numvfs + 1); + + /* save the start idx of promisc mce list */ + pfvf->promisc_mce_idx = nix_alloc_mce_list(mcast, numvfs + 1); + nix_mce_list_init(&pfvf->promisc_mce_list, numvfs + 1); + for (idx = 0; idx < (numvfs + 1); idx++) { /* idx-0 is for PF, followed by VFs */ pcifunc = (pf << RVU_PFVF_PF_SHIFT); @@ -2375,6 +2461,22 @@ static int nix_setup_bcast_tables(struct rvu *rvu, struct nix_hw *nix_hw) pcifunc, 0, true); if (err) return err; + + /* add dummy entries to multicast mce list */ + err = nix_blk_setup_mce(rvu, nix_hw, + pfvf->mcast_mce_idx + idx, + NIX_AQ_INSTOP_INIT, + pcifunc, 0, true); + if (err) + return err; + + /* add dummy entries to promisc mce list */ + err = nix_blk_setup_mce(rvu, nix_hw, + pfvf->promisc_mce_idx + idx, + NIX_AQ_INSTOP_INIT, + pcifunc, 0, true); + if (err) + return err; } } return 0; @@ -2421,7 +2523,7 @@ static int nix_setup_mcast(struct rvu *rvu, struct nix_hw *nix_hw, int blkaddr) mutex_init(&mcast->mce_lock); - return nix_setup_bcast_tables(rvu, nix_hw); + return nix_setup_mce_tables(rvu, nix_hw); } static int nix_setup_txvlan(struct rvu *rvu, struct nix_hw *nix_hw) @@ -3035,15 +3137,22 @@ int rvu_mbox_handler_nix_set_mac_addr(struct rvu *rvu, pfvf = rvu_get_pfvf(rvu, pcifunc); - /* VF can't overwrite admin(PF) changes */ - if (from_vf && pfvf->pf_set_vf_cfg) + /* untrusted VF can't overwrite admin(PF) changes */ + if (!test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && + (from_vf && test_bit(PF_SET_VF_MAC, &pfvf->flags))) { + dev_warn(rvu->dev, + "MAC address set by admin(PF) cannot be overwritten by untrusted VF"); return -EPERM; + } ether_addr_copy(pfvf->mac_addr, req->mac_addr); rvu_npc_install_ucast_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, req->mac_addr); + if (test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && from_vf) + ether_addr_copy(pfvf->default_mac, req->mac_addr); + return 0; } @@ -3067,30 +3176,75 @@ int rvu_mbox_handler_nix_get_mac_addr(struct rvu *rvu, int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req, struct msg_rsp *rsp) { - bool allmulti = false, disable_promisc = false; + bool allmulti, promisc, nix_rx_multicast; u16 pcifunc = req->hdr.pcifunc; - int blkaddr, nixlf, err; struct rvu_pfvf *pfvf; + int nixlf, err; - err = nix_get_nixlf(rvu, pcifunc, &nixlf, &blkaddr); + pfvf = rvu_get_pfvf(rvu, pcifunc); + promisc = req->mode & NIX_RX_MODE_PROMISC ? true : false; + allmulti = req->mode & NIX_RX_MODE_ALLMULTI ? true : false; + pfvf->use_mce_list = req->mode & NIX_RX_MODE_USE_MCE ? true : false; + + nix_rx_multicast = rvu->hw->cap.nix_rx_multicast & pfvf->use_mce_list; + + if (is_vf(pcifunc) && !nix_rx_multicast && + (promisc || allmulti)) { + dev_warn_ratelimited(rvu->dev, + "VF promisc/multicast not supported\n"); + return 0; + } + + /* untrusted VF can't configure promisc/allmulti */ + if (is_vf(pcifunc) && !test_bit(PF_SET_VF_TRUSTED, &pfvf->flags) && + (promisc || allmulti)) + return 0; + + err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); if (err) return err; - pfvf = rvu_get_pfvf(rvu, pcifunc); + if (nix_rx_multicast) { + /* add/del this PF_FUNC to/from mcast pkt replication list */ + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_ALLMULTI_ENTRY, + allmulti); + if (err) { + dev_err(rvu->dev, + "Failed to update pcifunc 0x%x to multicast list\n", + pcifunc); + return err; + } - if (req->mode & NIX_RX_MODE_PROMISC) - allmulti = false; - else if (req->mode & NIX_RX_MODE_ALLMULTI) - allmulti = true; - else - disable_promisc = true; + /* add/del this PF_FUNC to/from promisc pkt replication list */ + err = nix_update_mce_rule(rvu, pcifunc, NIXLF_PROMISC_ENTRY, + promisc); + if (err) { + dev_err(rvu->dev, + "Failed to update pcifunc 0x%x to promisc list\n", + pcifunc); + return err; + } + } - if (disable_promisc) - rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf); - else + /* install/uninstall allmulti entry */ + if (allmulti) { + rvu_npc_install_allmulti_entry(rvu, pcifunc, nixlf, + pfvf->rx_chan_base); + } else { + if (!nix_rx_multicast) + rvu_npc_enable_allmulti_entry(rvu, pcifunc, nixlf, false); + } + + /* install/uninstall promisc entry */ + if (promisc) { rvu_npc_install_promisc_entry(rvu, pcifunc, nixlf, pfvf->rx_chan_base, - pfvf->rx_chan_cnt, allmulti); + pfvf->rx_chan_cnt); + } else { + if (!nix_rx_multicast) + rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf, false); + } + return 0; } @@ -3648,6 +3802,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { u16 pcifunc = req->hdr.pcifunc; + struct rvu_pfvf *pfvf; int nixlf, err; err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); @@ -3658,6 +3813,9 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req, npc_mcam_enable_flows(rvu, pcifunc); + pfvf = rvu_get_pfvf(rvu, pcifunc); + set_bit(NIXLF_INITIALIZED, &pfvf->flags); + return rvu_cgx_start_stop_io(rvu, pcifunc, true); } @@ -3665,6 +3823,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, struct msg_rsp *rsp) { u16 pcifunc = req->hdr.pcifunc; + struct rvu_pfvf *pfvf; int nixlf, err; err = nix_get_nixlf(rvu, pcifunc, &nixlf, NULL); @@ -3673,6 +3832,9 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req, rvu_npc_disable_mcam_entries(rvu, pcifunc, nixlf); + pfvf = rvu_get_pfvf(rvu, pcifunc); + clear_bit(NIXLF_INITIALIZED, &pfvf->flags); + return rvu_cgx_start_stop_io(rvu, pcifunc, false); } @@ -3691,6 +3853,8 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf) nix_rx_sync(rvu, blkaddr); nix_txschq_free(rvu, pcifunc); + clear_bit(NIXLF_INITIALIZED, &pfvf->flags); + rvu_cgx_start_stop_io(rvu, pcifunc, false); if (pfvf->sq_ctx) { diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index 053cc872d0cc..5c2bd4337170 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -19,7 +19,7 @@ #include "cgx.h" #include "npc_profile.h" -#define RSVD_MCAM_ENTRIES_PER_PF 2 /* Bcast & Promisc */ +#define RSVD_MCAM_ENTRIES_PER_PF 3 /* Broadcast, Promisc and AllMulticast */ #define RSVD_MCAM_ENTRIES_PER_NIXLF 1 /* Ucast for LFs */ #define NPC_PARSE_RESULT_DMAC_OFFSET 8 @@ -214,8 +214,10 @@ int npc_get_nixlf_mcam_index(struct npc_mcam *mcam, */ if (type == NIXLF_BCAST_ENTRY) return index; - else if (type == NIXLF_PROMISC_ENTRY) + else if (type == NIXLF_ALLMULTI_ENTRY) return index + 1; + else if (type == NIXLF_PROMISC_ENTRY) + return index + 2; } return npc_get_ucast_mcam_index(mcam, pcifunc, nixlf); @@ -413,37 +415,49 @@ static void npc_fill_entryword(struct mcam_entry *entry, int idx, } } -static void npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, - int blkaddr, int index, - struct mcam_entry *entry) +static u64 npc_get_default_entry_action(struct rvu *rvu, struct npc_mcam *mcam, + int blkaddr, u16 pf_func) +{ + int bank, nixlf, index; + + /* get ucast entry rule entry index */ + nix_get_nixlf(rvu, pf_func, &nixlf, NULL); + index = npc_get_nixlf_mcam_index(mcam, pf_func, nixlf, + NIXLF_UCAST_ENTRY); + bank = npc_get_bank(mcam, index); + index &= (mcam->banksize - 1); + + return rvu_read64(rvu, blkaddr, + NPC_AF_MCAMEX_BANKX_ACTION(index, bank)); +} + +static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, + int blkaddr, int index, struct mcam_entry *entry, + bool *enable) { u16 owner, target_func; struct rvu_pfvf *pfvf; - int bank, nixlf; u64 rx_action; owner = mcam->entry2pfvf_map[index]; target_func = (entry->action >> 4) & 0xffff; - /* return incase target is PF or LBK or rule owner is not PF */ + /* do nothing when target is LBK/PF or owner is not PF */ if (is_afvf(target_func) || (owner & RVU_PFVF_FUNC_MASK) || !(target_func & RVU_PFVF_FUNC_MASK)) return; + /* save entry2target_pffunc */ pfvf = rvu_get_pfvf(rvu, target_func); mcam->entry2target_pffunc[index] = target_func; - /* return if nixlf is not attached or initialized */ - if (!is_nixlf_attached(rvu, target_func) || !pfvf->def_ucast_rule) - return; - /* get VF ucast entry rule */ - nix_get_nixlf(rvu, target_func, &nixlf, NULL); - index = npc_get_nixlf_mcam_index(mcam, target_func, - nixlf, NIXLF_UCAST_ENTRY); - bank = npc_get_bank(mcam, index); - index &= (mcam->banksize - 1); + /* don't enable rule when nixlf not attached or initialized */ + if (!(is_nixlf_attached(rvu, target_func) && + test_bit(NIXLF_INITIALIZED, &pfvf->flags))) + *enable = false; - rx_action = rvu_read64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index, bank)); + /* copy VF default entry action to the VF mcam entry */ + rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, + target_func); if (rx_action) entry->action = rx_action; } @@ -495,10 +509,9 @@ static void npc_config_mcam_entry(struct rvu *rvu, struct npc_mcam *mcam, NPC_AF_MCAMEX_BANKX_CAMX_W1(index, bank, 0), cam0); } - /* copy VF default entry action to the VF mcam entry */ + /* PF installing VF rule */ if (intf == NIX_INTF_RX && actindex < mcam->bmap_entries) - npc_get_default_entry_action(rvu, mcam, blkaddr, actindex, - entry); + npc_fixup_vf_rule(rvu, mcam, blkaddr, index, entry, &enable); /* Set 'action' */ rvu_write64(rvu, blkaddr, @@ -649,30 +662,32 @@ void rvu_npc_install_ucast_entry(struct rvu *rvu, u16 pcifunc, } void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, - int nixlf, u64 chan, u8 chan_cnt, - bool allmulti) + int nixlf, u64 chan, u8 chan_cnt) { struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc); struct npc_install_flow_req req = { 0 }; struct npc_install_flow_rsp rsp = { 0 }; struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; int blkaddr, ucast_idx, index; - u8 mac_addr[ETH_ALEN] = { 0 }; struct nix_rx_action action; u64 relaxed_mask; - /* Only PF or AF VF can add a promiscuous entry */ - if ((pcifunc & RVU_PFVF_FUNC_MASK) && !is_afvf(pcifunc)) + if (!hw->cap.nix_rx_multicast && is_cgx_vf(rvu, pcifunc)) return; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) return; - *(u64 *)&action = 0x00; index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_PROMISC_ENTRY); + if (is_cgx_vf(rvu, pcifunc)) + index = npc_get_nixlf_mcam_index(mcam, + pcifunc & ~RVU_PFVF_FUNC_MASK, + nixlf, NIXLF_PROMISC_ENTRY); + /* If the corresponding PF's ucast action is RSS, * use the same action for promisc also */ @@ -680,19 +695,20 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, nixlf, NIXLF_UCAST_ENTRY); if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx)) *(u64 *)&action = npc_get_mcam_action(rvu, mcam, - blkaddr, ucast_idx); + blkaddr, ucast_idx); if (action.op != NIX_RX_ACTIONOP_RSS) { *(u64 *)&action = 0x00; action.op = NIX_RX_ACTIONOP_UCAST; - action.pf_func = pcifunc; } - if (allmulti) { - mac_addr[0] = 0x01; /* LSB bit of 1st byte in DMAC */ - ether_addr_copy(req.packet.dmac, mac_addr); - ether_addr_copy(req.mask.dmac, mac_addr); - req.features = BIT_ULL(NPC_DMAC); + /* RX_ACTION set to MCAST for CGX PF's */ + if (hw->cap.nix_rx_multicast && pfvf->use_mce_list && + is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) { + *(u64 *)&action = 0x00; + action.op = NIX_RX_ACTIONOP_MCAST; + pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + action.index = pfvf->promisc_mce_idx; } req.chan_mask = 0xFFFU; @@ -720,8 +736,8 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc, rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } -static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc, - int nixlf, bool enable) +void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, + int nixlf, bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, index; @@ -730,25 +746,14 @@ static void npc_enadis_promisc_entry(struct rvu *rvu, u16 pcifunc, if (blkaddr < 0) return; - /* Only PF's have a promiscuous entry */ - if (pcifunc & RVU_PFVF_FUNC_MASK) - return; + /* Get 'pcifunc' of PF device */ + pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, NIXLF_PROMISC_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } -void rvu_npc_disable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf) -{ - npc_enadis_promisc_entry(rvu, pcifunc, nixlf, false); -} - -void rvu_npc_enable_promisc_entry(struct rvu *rvu, u16 pcifunc, int nixlf) -{ - npc_enadis_promisc_entry(rvu, pcifunc, nixlf, true); -} - void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, int nixlf, u64 chan) { @@ -758,8 +763,6 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, struct npc_mcam *mcam = &rvu->hw->mcam; struct rvu_hwinfo *hw = rvu->hw; int blkaddr, index; - u32 req_index = 0; - u8 op; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) @@ -772,7 +775,7 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, /* If pkt replication is not supported, * then only PF is allowed to add a bcast match entry. */ - if (!hw->cap.nix_rx_multicast && pcifunc & RVU_PFVF_FUNC_MASK) + if (!hw->cap.nix_rx_multicast && is_vf(pcifunc)) return; /* Get 'pcifunc' of PF device */ @@ -786,10 +789,10 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, * so install entry with UCAST action, so that PF * receives all broadcast packets. */ - op = NIX_RX_ACTIONOP_UCAST; + req.op = NIX_RX_ACTIONOP_UCAST; } else { - op = NIX_RX_ACTIONOP_MCAST; - req_index = pfvf->bcast_mce_idx; + req.op = NIX_RX_ACTIONOP_MCAST; + req.index = pfvf->bcast_mce_idx; } eth_broadcast_addr((u8 *)&req.packet.dmac); @@ -798,15 +801,110 @@ void rvu_npc_install_bcast_match_entry(struct rvu *rvu, u16 pcifunc, req.channel = chan; req.intf = pfvf->nix_rx_intf; req.entry = index; - req.op = op; req.hdr.pcifunc = 0; /* AF is requester */ req.vf = pcifunc; - req.index = req_index; rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); } -void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) +void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + int blkaddr, index; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + + /* Get 'pcifunc' of PF device */ + pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; + + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, + NIXLF_BCAST_ENTRY); + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); +} + +void rvu_npc_install_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + u64 chan) +{ + struct npc_install_flow_req req = { 0 }; + struct npc_install_flow_rsp rsp = { 0 }; + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + int blkaddr, ucast_idx, index; + u8 mac_addr[ETH_ALEN] = { 0 }; + struct nix_rx_action action; + struct rvu_pfvf *pfvf; + u16 vf_func; + + /* Only CGX PF/VF can add allmulticast entry */ + if (is_afvf(pcifunc)) + return; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + + /* Get 'pcifunc' of PF device */ + vf_func = pcifunc & RVU_PFVF_FUNC_MASK; + pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; + pfvf = rvu_get_pfvf(rvu, pcifunc); + index = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_ALLMULTI_ENTRY); + + /* If the corresponding PF's ucast action is RSS, + * use the same action for multicast entry also + */ + ucast_idx = npc_get_nixlf_mcam_index(mcam, pcifunc, + nixlf, NIXLF_UCAST_ENTRY); + if (is_mcam_entry_enabled(rvu, mcam, blkaddr, ucast_idx)) + *(u64 *)&action = npc_get_mcam_action(rvu, mcam, + blkaddr, ucast_idx); + + if (action.op != NIX_RX_ACTIONOP_RSS) { + *(u64 *)&action = 0x00; + action.op = NIX_RX_ACTIONOP_UCAST; + action.pf_func = pcifunc; + } + + /* RX_ACTION set to MCAST for CGX PF's */ + if (hw->cap.nix_rx_multicast && pfvf->use_mce_list) { + *(u64 *)&action = 0x00; + action.op = NIX_RX_ACTIONOP_MCAST; + action.index = pfvf->mcast_mce_idx; + } + + mac_addr[0] = 0x01; /* LSB bit of 1st byte in DMAC */ + ether_addr_copy(req.packet.dmac, mac_addr); + ether_addr_copy(req.mask.dmac, mac_addr); + req.features = BIT_ULL(NPC_DMAC); + + /* For cn10k the upper two bits of the channel number are + * cpt channel number. with masking out these bits in the + * mcam entry, same entry used for NIX will allow packets + * received from cpt for parsing. + */ + if (!is_rvu_otx2(rvu)) + req.chan_mask = NIX_CHAN_CPT_X2P_MASK; + else + req.chan_mask = 0xFFFU; + + req.channel = chan; + req.intf = pfvf->nix_rx_intf; + req.entry = index; + req.op = action.op; + req.hdr.pcifunc = 0; /* AF is requester */ + req.vf = pcifunc | vf_func; + req.index = action.index; + req.match_id = action.match_id; + req.flow_key_alg = action.flow_key_alg; + + rvu_mbox_handler_npc_install_flow(rvu, &req, &rsp); +} + +void rvu_npc_enable_allmulti_entry(struct rvu *rvu, u16 pcifunc, int nixlf, + bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; int blkaddr, index; @@ -818,7 +916,8 @@ void rvu_npc_enable_bcast_entry(struct rvu *rvu, u16 pcifunc, bool enable) /* Get 'pcifunc' of PF device */ pcifunc = pcifunc & ~RVU_PFVF_FUNC_MASK; - index = npc_get_nixlf_mcam_index(mcam, pcifunc, 0, NIXLF_BCAST_ENTRY); + index = npc_get_nixlf_mcam_index(mcam, pcifunc, nixlf, + NIXLF_ALLMULTI_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); } @@ -860,6 +959,7 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, int group, int alg_idx, int mcam_index) { struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; struct nix_rx_action action; int blkaddr, index, bank; struct rvu_pfvf *pfvf; @@ -915,7 +1015,8 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, /* If PF's promiscuous entry is enabled, * Set RSS action for that entry as well */ - if (is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { + if ((!hw->cap.nix_rx_multicast || !pfvf->use_mce_list) && + is_mcam_entry_enabled(rvu, mcam, blkaddr, index)) { bank = npc_get_bank(mcam, index); index &= (mcam->banksize - 1); @@ -925,12 +1026,47 @@ void rvu_npc_update_flowkey_alg_idx(struct rvu *rvu, u16 pcifunc, int nixlf, } } +void npc_enadis_default_mce_entry(struct rvu *rvu, u16 pcifunc, + int nixlf, int type, bool enable) +{ + struct npc_mcam *mcam = &rvu->hw->mcam; + struct rvu_hwinfo *hw = rvu->hw; + struct nix_mce_list *mce_list; + int index, blkaddr, mce_idx; + struct rvu_pfvf *pfvf; + + blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); + if (blkaddr < 0) + return; + + index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, + nixlf, type); + + /* disable MCAM entry when packet replication is not supported by hw */ + if (!hw->cap.nix_rx_multicast && !is_vf(pcifunc)) { + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); + return; + } + + /* return incase mce list is not enabled */ + pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK); + if (hw->cap.nix_rx_multicast && is_vf(pcifunc) && + type != NIXLF_BCAST_ENTRY && !pfvf->use_mce_list) + return; + + nix_get_mce_list(rvu, pcifunc, type, &mce_list, &mce_idx); + + nix_update_mce_list(rvu, pcifunc, mce_list, + mce_idx, index, enable); + if (enable) + npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); +} + static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf, bool enable) { struct npc_mcam *mcam = &rvu->hw->mcam; - struct nix_rx_action action; - int index, bank, blkaddr; + int index, blkaddr; blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NPC, 0); if (blkaddr < 0) @@ -941,48 +1077,33 @@ static void npc_enadis_default_entries(struct rvu *rvu, u16 pcifunc, nixlf, NIXLF_UCAST_ENTRY); npc_enable_mcam_entry(rvu, mcam, blkaddr, index, enable); - /* For PF, ena/dis promisc and bcast MCAM match entries. - * For VFs add/delete from bcast list when RX multicast - * feature is present. + /* Nothing to do for VFs, on platforms where pkt replication + * is not supported */ - if (pcifunc & RVU_PFVF_FUNC_MASK && !rvu->hw->cap.nix_rx_multicast) + if ((pcifunc & RVU_PFVF_FUNC_MASK) && !rvu->hw->cap.nix_rx_multicast) return; - /* For bcast, enable/disable only if it's action is not - * packet replication, incase if action is replication - * then this PF/VF's nixlf is removed from bcast replication - * list. - */ - index = npc_get_nixlf_mcam_index(mcam, pcifunc & ~RVU_PFVF_FUNC_MASK, - nixlf, NIXLF_BCAST_ENTRY); - bank = npc_get_bank(mcam, index); - *(u64 *)&action = rvu_read64(rvu, blkaddr, - NPC_AF_MCAMEX_BANKX_ACTION(index & (mcam->banksize - 1), bank)); - - /* VFs will not have BCAST entry */ - if (action.op != NIX_RX_ACTIONOP_MCAST && - !(pcifunc & RVU_PFVF_FUNC_MASK)) { - npc_enable_mcam_entry(rvu, mcam, - blkaddr, index, enable); - } else { - nix_update_bcast_mce_list(rvu, pcifunc, enable); - /* Enable PF's BCAST entry for packet replication */ - rvu_npc_enable_bcast_entry(rvu, pcifunc, enable); - } - - if (enable) - rvu_npc_enable_promisc_entry(rvu, pcifunc, nixlf); - else - rvu_npc_disable_promisc_entry(rvu, pcifunc, nixlf); + /* add/delete pf_func to broadcast MCE list */ + npc_enadis_default_mce_entry(rvu, pcifunc, nixlf, + NIXLF_BCAST_ENTRY, enable); } void rvu_npc_disable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf) { npc_enadis_default_entries(rvu, pcifunc, nixlf, false); + + /* Delete multicast and promisc MCAM entries */ + npc_enadis_default_mce_entry(rvu, pcifunc, nixlf, + NIXLF_ALLMULTI_ENTRY, false); + npc_enadis_default_mce_entry(rvu, pcifunc, nixlf, + NIXLF_PROMISC_ENTRY, false); } void rvu_npc_enable_default_entries(struct rvu *rvu, u16 pcifunc, int nixlf) { + /* Enables only broadcast match entry. Promisc/Allmulti are enabled + * in set_rx_mode mbox handler. + */ npc_enadis_default_entries(rvu, pcifunc, nixlf, true); } @@ -1002,7 +1123,8 @@ void rvu_npc_disable_mcam_entries(struct rvu *rvu, u16 pcifunc, int nixlf) /* Disable MCAM entries directing traffic to this 'pcifunc' */ list_for_each_entry_safe(rule, tmp, &mcam->mcam_rules, list) { if (is_npc_intf_rx(rule->intf) && - rule->rx_action.pf_func == pcifunc) { + rule->rx_action.pf_func == pcifunc && + rule->rx_action.op != NIX_RX_ACTIONOP_MCAST) { npc_enable_mcam_entry(rvu, mcam, blkaddr, rule->entry, false); rule->enable = false; diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c index 7f35b62eea13..6ba6a835e2fa 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_fs.c @@ -1103,9 +1103,11 @@ find_rule: if (pf_set_vfs_mac) { ether_addr_copy(pfvf->default_mac, req->packet.dmac); ether_addr_copy(pfvf->mac_addr, req->packet.dmac); + set_bit(PF_SET_VF_MAC, &pfvf->flags); } - if (pfvf->pf_set_vf_cfg && req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7) + if (test_bit(PF_SET_VF_CFG, &pfvf->flags) && + req->vtag0_type == NIX_AF_LFX_RX_VTAG_TYPE7) rule->vfvlan_cfg = true; return 0; @@ -1167,7 +1169,7 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, /* PF installing for its VF */ if (req->hdr.pcifunc && !from_vf && req->vf) - pfvf->pf_set_vf_cfg = 1; + set_bit(PF_SET_VF_CFG, &pfvf->flags); /* update req destination mac addr */ if ((req->features & BIT_ULL(NPC_DMAC)) && is_npc_intf_rx(req->intf) && @@ -1177,9 +1179,12 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, } err = nix_get_nixlf(rvu, target, &nixlf, NULL); + if (err && is_npc_intf_rx(req->intf) && !pf_set_vfs_mac) + return -EINVAL; - /* If interface is uninitialized then do not enable entry */ - if (err || (!req->default_rule && !pfvf->def_ucast_rule)) + /* don't enable rule when nixlf not attached or initialized */ + if (!(is_nixlf_attached(rvu, target) && + test_bit(NIXLF_INITIALIZED, &pfvf->flags))) enable = false; /* Packets reaching NPC in Tx path implies that a @@ -1193,6 +1198,14 @@ int rvu_mbox_handler_npc_install_flow(struct rvu *rvu, if (from_vf && !enable) return -EINVAL; + /* PF sets VF mac & VF NIXLF is not attached, update the mac addr */ + if (pf_set_vfs_mac && !enable) { + ether_addr_copy(pfvf->default_mac, req->packet.dmac); + ether_addr_copy(pfvf->mac_addr, req->packet.dmac); + set_bit(PF_SET_VF_MAC, &pfvf->flags); + return 0; + } + /* If message is from VF then its flow should not overlap with * reserved unicast flow. */ diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h index 45730d0d92f2..543aee726fbe 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h @@ -223,6 +223,11 @@ struct otx2_hw { u64 *nix_lmt_base; }; +enum vfperm { + OTX2_RESET_VF_PERM, + OTX2_TRUSTED_VF, +}; + struct otx2_vf_config { struct otx2_nic *pf; struct delayed_work link_event_work; @@ -230,6 +235,7 @@ struct otx2_vf_config { u8 mac[ETH_ALEN]; u16 vlan; int tx_vtag_idx; + bool trusted; }; struct flr_work { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index 03004fdac0c6..82b53e72268f 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -39,6 +39,8 @@ MODULE_DESCRIPTION(DRV_STRING); MODULE_LICENSE("GPL v2"); MODULE_DEVICE_TABLE(pci, otx2_pf_id_table); +static void otx2_vf_link_event_task(struct work_struct *work); + enum { TYPE_PFAF, TYPE_PFVF, @@ -1820,9 +1822,11 @@ static void otx2_do_set_rx_mode(struct work_struct *work) if (promisc) req->mode |= NIX_RX_MODE_PROMISC; - else if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) + if (netdev->flags & (IFF_ALLMULTI | IFF_MULTICAST)) req->mode |= NIX_RX_MODE_ALLMULTI; + req->mode |= NIX_RX_MODE_USE_MCE; + otx2_sync_mbox_msg(&pf->mbox); mutex_unlock(&pf->mbox.lock); } @@ -2044,7 +2048,7 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) if (!netif_running(netdev)) return -EAGAIN; - if (vf >= pci_num_vf(pdev)) + if (vf >= pf->total_vfs) return -EINVAL; if (!is_valid_ether_addr(mac)) @@ -2055,7 +2059,8 @@ static int otx2_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) ret = otx2_do_set_vf_mac(pf, vf, mac); if (ret == 0) - dev_info(&pdev->dev, "Reload VF driver to apply the changes\n"); + dev_info(&pdev->dev, + "Load/Reload VF driver\n"); return ret; } @@ -2241,10 +2246,63 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf, ivi->vf = vf; ether_addr_copy(ivi->mac, config->mac); ivi->vlan = config->vlan; + ivi->trusted = config->trusted; return 0; } +static int otx2_set_vf_permissions(struct otx2_nic *pf, int vf, + int req_perm) +{ + struct set_vf_perm *req; + int rc; + + mutex_lock(&pf->mbox.lock); + req = otx2_mbox_alloc_msg_set_vf_perm(&pf->mbox); + if (!req) { + rc = -ENOMEM; + goto out; + } + + /* Let AF reset VF permissions as sriov is disabled */ + if (req_perm == OTX2_RESET_VF_PERM) { + req->flags |= RESET_VF_PERM; + } else if (req_perm == OTX2_TRUSTED_VF) { + if (pf->vf_configs[vf].trusted) + req->flags |= VF_TRUSTED; + } + + req->vf = vf; + rc = otx2_sync_mbox_msg(&pf->mbox); +out: + mutex_unlock(&pf->mbox.lock); + return rc; +} + +static int otx2_ndo_set_vf_trust(struct net_device *netdev, int vf, + bool enable) +{ + struct otx2_nic *pf = netdev_priv(netdev); + struct pci_dev *pdev = pf->pdev; + int rc; + + if (vf >= pci_num_vf(pdev)) + return -EINVAL; + + if (pf->vf_configs[vf].trusted == enable) + return 0; + + pf->vf_configs[vf].trusted = enable; + rc = otx2_set_vf_permissions(pf, vf, OTX2_TRUSTED_VF); + + if (rc) + pf->vf_configs[vf].trusted = !enable; + else + netdev_info(pf->netdev, "VF %d is %strusted\n", + vf, enable ? "" : "not "); + return rc; +} + static const struct net_device_ops otx2_netdev_ops = { .ndo_open = otx2_open, .ndo_stop = otx2_stop, @@ -2261,6 +2319,7 @@ static const struct net_device_ops otx2_netdev_ops = { .ndo_set_vf_vlan = otx2_set_vf_vlan, .ndo_get_vf_config = otx2_get_vf_config, .ndo_setup_tc = otx2_setup_tc, + .ndo_set_vf_trust = otx2_ndo_set_vf_trust, }; static int otx2_wq_init(struct otx2_nic *pf) @@ -2315,6 +2374,40 @@ static int otx2_realloc_msix_vectors(struct otx2_nic *pf) return otx2_register_mbox_intr(pf, false); } +static int otx2_sriov_vfcfg_init(struct otx2_nic *pf) +{ + int i; + + pf->vf_configs = devm_kcalloc(pf->dev, pf->total_vfs, + sizeof(struct otx2_vf_config), + GFP_KERNEL); + if (!pf->vf_configs) + return -ENOMEM; + + for (i = 0; i < pf->total_vfs; i++) { + pf->vf_configs[i].pf = pf; + pf->vf_configs[i].intf_down = true; + pf->vf_configs[i].trusted = false; + INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work, + otx2_vf_link_event_task); + } + + return 0; +} + +static void otx2_sriov_vfcfg_cleanup(struct otx2_nic *pf) +{ + int i; + + if (!pf->vf_configs) + return; + + for (i = 0; i < pf->total_vfs; i++) { + cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work); + otx2_set_vf_permissions(pf, i, OTX2_RESET_VF_PERM); + } +} + static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) { struct device *dev = &pdev->dev; @@ -2509,6 +2602,11 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) if (err) goto err_mcam_flow_del; + /* Initialize SR-IOV resources */ + err = otx2_sriov_vfcfg_init(pf); + if (err) + goto err_pf_sriov_init; + /* Enable link notifications */ otx2_cgx_config_linkevents(pf, true); @@ -2518,6 +2616,8 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; +err_pf_sriov_init: + otx2_shutdown_tc(pf); err_mcam_flow_del: otx2_mcam_flow_del(pf); err_unreg_netdev: @@ -2576,7 +2676,7 @@ static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) { struct net_device *netdev = pci_get_drvdata(pdev); struct otx2_nic *pf = netdev_priv(netdev); - int ret, i; + int ret; /* Init PF <=> VF mailbox stuff */ ret = otx2_pfvf_mbox_init(pf, numvfs); @@ -2587,23 +2687,9 @@ static int otx2_sriov_enable(struct pci_dev *pdev, int numvfs) if (ret) goto free_mbox; - pf->vf_configs = kcalloc(numvfs, sizeof(struct otx2_vf_config), - GFP_KERNEL); - if (!pf->vf_configs) { - ret = -ENOMEM; - goto free_intr; - } - - for (i = 0; i < numvfs; i++) { - pf->vf_configs[i].pf = pf; - pf->vf_configs[i].intf_down = true; - INIT_DELAYED_WORK(&pf->vf_configs[i].link_event_work, - otx2_vf_link_event_task); - } - ret = otx2_pf_flr_init(pf, numvfs); if (ret) - goto free_configs; + goto free_intr; ret = otx2_register_flr_me_intr(pf, numvfs); if (ret) @@ -2618,8 +2704,6 @@ free_flr_intr: otx2_disable_flr_me_intr(pf); free_flr: otx2_flr_wq_destroy(pf); -free_configs: - kfree(pf->vf_configs); free_intr: otx2_disable_pfvf_mbox_intr(pf, numvfs); free_mbox: @@ -2632,17 +2716,12 @@ static int otx2_sriov_disable(struct pci_dev *pdev) struct net_device *netdev = pci_get_drvdata(pdev); struct otx2_nic *pf = netdev_priv(netdev); int numvfs = pci_num_vf(pdev); - int i; if (!numvfs) return 0; pci_disable_sriov(pdev); - for (i = 0; i < pci_num_vf(pdev); i++) - cancel_delayed_work_sync(&pf->vf_configs[i].link_event_work); - kfree(pf->vf_configs); - otx2_disable_flr_me_intr(pf); otx2_flr_wq_destroy(pf); otx2_disable_pfvf_mbox_intr(pf, numvfs); @@ -2682,6 +2761,7 @@ static void otx2_remove(struct pci_dev *pdev) unregister_netdev(netdev); otx2_sriov_disable(pf->pdev); + otx2_sriov_vfcfg_cleanup(pf); if (pf->otx2_wq) destroy_workqueue(pf->otx2_wq); diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c index 085be90a03eb..13a908f75ba0 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c @@ -395,6 +395,42 @@ static netdev_tx_t otx2vf_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_OK; } +static void otx2vf_set_rx_mode(struct net_device *netdev) +{ + struct otx2_nic *vf = netdev_priv(netdev); + + queue_work(vf->otx2_wq, &vf->rx_mode_work); +} + +static void otx2vf_do_set_rx_mode(struct work_struct *work) +{ + struct otx2_nic *vf = container_of(work, struct otx2_nic, rx_mode_work); + struct net_device *netdev = vf->netdev; + unsigned int flags = netdev->flags; + struct nix_rx_mode *req; + + mutex_lock(&vf->mbox.lock); + + req = otx2_mbox_alloc_msg_nix_set_rx_mode(&vf->mbox); + if (!req) { + mutex_unlock(&vf->mbox.lock); + return; + } + + req->mode = NIX_RX_MODE_UCAST; + + if (flags & IFF_PROMISC) + req->mode |= NIX_RX_MODE_PROMISC; + if (flags & (IFF_ALLMULTI | IFF_MULTICAST)) + req->mode |= NIX_RX_MODE_ALLMULTI; + + req->mode |= NIX_RX_MODE_USE_MCE; + + otx2_sync_mbox_msg(&vf->mbox); + + mutex_unlock(&vf->mbox.lock); +} + static int otx2vf_change_mtu(struct net_device *netdev, int new_mtu) { bool if_up = netif_running(netdev); @@ -432,12 +468,24 @@ static const struct net_device_ops otx2vf_netdev_ops = { .ndo_open = otx2vf_open, .ndo_stop = otx2vf_stop, .ndo_start_xmit = otx2vf_xmit, + .ndo_set_rx_mode = otx2vf_set_rx_mode, .ndo_set_mac_address = otx2_set_mac_address, .ndo_change_mtu = otx2vf_change_mtu, .ndo_get_stats64 = otx2_get_stats64, .ndo_tx_timeout = otx2_tx_timeout, }; +static int otx2_wq_init(struct otx2_nic *vf) +{ + vf->otx2_wq = create_singlethread_workqueue("otx2vf_wq"); + if (!vf->otx2_wq) + return -ENOMEM; + + INIT_WORK(&vf->rx_mode_work, otx2vf_do_set_rx_mode); + INIT_WORK(&vf->reset_task, otx2vf_reset_task); + return 0; +} + static int otx2vf_realloc_msix_vectors(struct otx2_nic *vf) { struct otx2_hw *hw = &vf->hw; @@ -588,8 +636,6 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) netdev->min_mtu = OTX2_MIN_MTU; netdev->max_mtu = otx2_get_max_mtu(vf); - INIT_WORK(&vf->reset_task, otx2vf_reset_task); - /* To distinguish, for LBK VFs set netdev name explicitly */ if (is_otx2_lbkvf(vf->pdev)) { int n; @@ -606,6 +652,10 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) goto err_detach_rsrc; } + err = otx2_wq_init(vf); + if (err) + goto err_unreg_netdev; + otx2vf_set_ethtool_ops(netdev); /* Enable pause frames by default */ @@ -614,6 +664,8 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id) return 0; +err_unreg_netdev: + unregister_netdev(netdev); err_detach_rsrc: if (hw->lmt_base) iounmap(hw->lmt_base); @@ -644,6 +696,8 @@ static void otx2vf_remove(struct pci_dev *pdev) cancel_work_sync(&vf->reset_task); unregister_netdev(netdev); + if (vf->otx2_wq) + destroy_workqueue(vf->otx2_wq); otx2vf_disable_mbox_intr(vf); otx2_detach_resources(&vf->mbox); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 64f94a3fe646..6a9fe9f7e0be 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -3508,7 +3508,6 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) rtl_eri_write(tp, 0x1b0, ERIAR_MASK_0011, 0x0000); rtl_pcie_state_l2l3_disable(tp); - rtl_hw_aspm_clkreq_enable(tp, true); } DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond) diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index fd7212afc543..6655cb8e24cf 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -75,7 +75,7 @@ struct stmmac_tx_queue { unsigned int cur_tx; unsigned int dirty_tx; dma_addr_t dma_tx_phy; - u32 tx_tail_addr; + dma_addr_t tx_tail_addr; u32 mss; }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index db97cd4b871d..4177fd6a9db5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3406,8 +3406,8 @@ static void stmmac_free_irq(struct net_device *dev, static int stmmac_request_irq_multi_msi(struct net_device *dev) { - enum request_irq_err irq_err = REQ_IRQ_ERR_NO; struct stmmac_priv *priv = netdev_priv(dev); + enum request_irq_err irq_err; cpumask_t cpu_mask; int irq_idx = 0; char *int_name; @@ -3554,8 +3554,8 @@ irq_error: static int stmmac_request_irq_single(struct net_device *dev) { - enum request_irq_err irq_err = REQ_IRQ_ERR_NO; struct stmmac_priv *priv = netdev_priv(dev); + enum request_irq_err irq_err; int ret; ret = request_irq(dev->irq, stmmac_interrupt, @@ -3565,7 +3565,7 @@ static int stmmac_request_irq_single(struct net_device *dev) "%s: ERROR: allocating the IRQ %d (error: %d)\n", __func__, dev->irq, ret); irq_err = REQ_IRQ_ERR_MAC; - return ret; + goto irq_error; } /* Request the Wake IRQ in case of another line @@ -3579,7 +3579,7 @@ static int stmmac_request_irq_single(struct net_device *dev) "%s: ERROR: allocating the WoL IRQ %d (%d)\n", __func__, priv->wol_irq, ret); irq_err = REQ_IRQ_ERR_WOL; - return ret; + goto irq_error; } } diff --git a/drivers/net/mdio/Kconfig b/drivers/net/mdio/Kconfig index d06e06f5e31a..99a6c13a11af 100644 --- a/drivers/net/mdio/Kconfig +++ b/drivers/net/mdio/Kconfig @@ -19,6 +19,13 @@ config MDIO_BUS reflects whether the mdio_bus/mdio_device code is built as a loadable module or built-in. +config FWNODE_MDIO + def_tristate PHYLIB + depends on (ACPI || OF) || COMPILE_TEST + select FIXED_PHY + help + FWNODE MDIO bus (Ethernet PHY) accessors + config OF_MDIO def_tristate PHYLIB depends on OF @@ -27,6 +34,13 @@ config OF_MDIO help OpenFirmware MDIO bus (Ethernet PHY) accessors +config ACPI_MDIO + def_tristate PHYLIB + depends on ACPI + depends on PHYLIB + help + ACPI MDIO bus (Ethernet PHY) accessors + if MDIO_BUS config MDIO_DEVRES diff --git a/drivers/net/mdio/Makefile b/drivers/net/mdio/Makefile index c3ec0ef989df..15f8dc4042ce 100644 --- a/drivers/net/mdio/Makefile +++ b/drivers/net/mdio/Makefile @@ -1,7 +1,9 @@ # SPDX-License-Identifier: GPL-2.0 # Makefile for Linux MDIO bus drivers -obj-$(CONFIG_OF_MDIO) += of_mdio.o +obj-$(CONFIG_ACPI_MDIO) += acpi_mdio.o +obj-$(CONFIG_FWNODE_MDIO) += fwnode_mdio.o +obj-$(CONFIG_OF_MDIO) += of_mdio.o obj-$(CONFIG_MDIO_ASPEED) += mdio-aspeed.o obj-$(CONFIG_MDIO_BCM_IPROC) += mdio-bcm-iproc.o diff --git a/drivers/net/mdio/acpi_mdio.c b/drivers/net/mdio/acpi_mdio.c new file mode 100644 index 000000000000..d77c987fda9c --- /dev/null +++ b/drivers/net/mdio/acpi_mdio.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * ACPI helpers for the MDIO (Ethernet PHY) API + * + * This file provides helper functions for extracting PHY device information + * out of the ACPI ASL and using it to populate an mii_bus. + */ + +#include <linux/acpi.h> +#include <linux/acpi_mdio.h> +#include <linux/bits.h> +#include <linux/dev_printk.h> +#include <linux/fwnode_mdio.h> +#include <linux/module.h> +#include <linux/types.h> + +MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>"); +MODULE_LICENSE("GPL"); + +/** + * acpi_mdiobus_register - Register mii_bus and create PHYs from the ACPI ASL. + * @mdio: pointer to mii_bus structure + * @fwnode: pointer to fwnode of MDIO bus. This fwnode is expected to represent + * an ACPI device object corresponding to the MDIO bus and its children are + * expected to correspond to the PHY devices on that bus. + * + * This function registers the mii_bus structure and registers a phy_device + * for each child node of @fwnode. + */ +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + struct fwnode_handle *child; + u32 addr; + int ret; + + /* Mask out all PHYs from auto probing. */ + mdio->phy_mask = GENMASK(31, 0); + ret = mdiobus_register(mdio); + if (ret) + return ret; + + ACPI_COMPANION_SET(&mdio->dev, to_acpi_device_node(fwnode)); + + /* Loop over the child nodes and register a phy_device for each PHY */ + fwnode_for_each_child_node(fwnode, child) { + ret = acpi_get_local_address(ACPI_HANDLE_FWNODE(child), &addr); + if (ret || addr >= PHY_MAX_ADDR) + continue; + + ret = fwnode_mdiobus_register_phy(mdio, child, addr); + if (ret == -ENODEV) + dev_err(&mdio->dev, + "MDIO device at address %d is missing.\n", + addr); + } + return 0; +} +EXPORT_SYMBOL(acpi_mdiobus_register); diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c new file mode 100644 index 000000000000..e96766da8de4 --- /dev/null +++ b/drivers/net/mdio/fwnode_mdio.c @@ -0,0 +1,144 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * fwnode helpers for the MDIO (Ethernet PHY) API + * + * This file provides helper functions for extracting PHY device information + * out of the fwnode and using it to populate an mii_bus. + */ + +#include <linux/acpi.h> +#include <linux/fwnode_mdio.h> +#include <linux/of.h> +#include <linux/phy.h> + +MODULE_AUTHOR("Calvin Johnson <calvin.johnson@oss.nxp.com>"); +MODULE_LICENSE("GPL"); + +static struct mii_timestamper * +fwnode_find_mii_timestamper(struct fwnode_handle *fwnode) +{ + struct of_phandle_args arg; + int err; + + if (is_acpi_node(fwnode)) + return NULL; + + err = of_parse_phandle_with_fixed_args(to_of_node(fwnode), + "timestamper", 1, 0, &arg); + if (err == -ENOENT) + return NULL; + else if (err) + return ERR_PTR(err); + + if (arg.args_count != 1) + return ERR_PTR(-EINVAL); + + return register_mii_timestamper(arg.np, arg.args[0]); +} + +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + int rc; + + rc = fwnode_irq_get(child, 0); + if (rc == -EPROBE_DEFER) + return rc; + + if (rc > 0) { + phy->irq = rc; + mdio->irq[addr] = rc; + } else { + phy->irq = mdio->irq[addr]; + } + + if (fwnode_property_read_bool(child, "broken-turn-around")) + mdio->phy_ignore_ta_mask |= 1 << addr; + + fwnode_property_read_u32(child, "reset-assert-us", + &phy->mdio.reset_assert_delay); + fwnode_property_read_u32(child, "reset-deassert-us", + &phy->mdio.reset_deassert_delay); + + /* Associate the fwnode with the device structure so it + * can be looked up later + */ + fwnode_handle_get(child); + phy->mdio.dev.fwnode = child; + + /* All data is now stored in the phy struct; + * register it + */ + rc = phy_device_register(phy); + if (rc) { + fwnode_handle_put(child); + return rc; + } + + dev_dbg(&mdio->dev, "registered phy %p fwnode at address %i\n", + child, addr); + return 0; +} +EXPORT_SYMBOL(fwnode_mdiobus_phy_device_register); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr) +{ + struct mii_timestamper *mii_ts = NULL; + struct phy_device *phy; + bool is_c45 = false; + u32 phy_id; + int rc; + + mii_ts = fwnode_find_mii_timestamper(child); + if (IS_ERR(mii_ts)) + return PTR_ERR(mii_ts); + + rc = fwnode_property_match_string(child, "compatible", + "ethernet-phy-ieee802.3-c45"); + if (rc >= 0) + is_c45 = true; + + if (is_c45 || fwnode_get_phy_id(child, &phy_id)) + phy = get_phy_device(bus, addr, is_c45); + else + phy = phy_device_create(bus, addr, phy_id, 0, NULL); + if (IS_ERR(phy)) { + unregister_mii_timestamper(mii_ts); + return PTR_ERR(phy); + } + + if (is_acpi_node(child)) { + phy->irq = bus->irq[addr]; + + /* Associate the fwnode with the device structure so it + * can be looked up later. + */ + phy->mdio.dev.fwnode = child; + + /* All data is now stored in the phy struct, so register it */ + rc = phy_device_register(phy); + if (rc) { + phy_device_free(phy); + fwnode_handle_put(phy->mdio.dev.fwnode); + return rc; + } + } else if (is_of_node(child)) { + rc = fwnode_mdiobus_phy_device_register(bus, phy, child, addr); + if (rc) { + unregister_mii_timestamper(mii_ts); + phy_device_free(phy); + return rc; + } + } + + /* phy->mii_ts may already be defined by the PHY driver. A + * mii_timestamper probed via the device tree will still have + * precedence. + */ + if (mii_ts) + phy->mii_ts = mii_ts; + return 0; +} +EXPORT_SYMBOL(fwnode_mdiobus_register_phy); diff --git a/drivers/net/mdio/mdio-mscc-miim.c b/drivers/net/mdio/mdio-mscc-miim.c index b36e5ea04ddf..2d67e12c8262 100644 --- a/drivers/net/mdio/mdio-mscc-miim.c +++ b/drivers/net/mdio/mdio-mscc-miim.c @@ -139,10 +139,6 @@ static int mscc_miim_probe(struct platform_device *pdev) struct mscc_miim_dev *dev; int ret; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - if (!res) - return -ENODEV; - bus = devm_mdiobus_alloc_size(&pdev->dev, sizeof(*dev)); if (!bus) return -ENOMEM; @@ -155,7 +151,7 @@ static int mscc_miim_probe(struct platform_device *pdev) bus->parent = &pdev->dev; dev = bus->priv; - dev->regs = devm_ioremap_resource(&pdev->dev, res); + dev->regs = devm_platform_get_and_ioremap_resource(pdev, 0, NULL); if (IS_ERR(dev->regs)) { dev_err(&pdev->dev, "Unable to map MIIM registers\n"); return PTR_ERR(dev->regs); diff --git a/drivers/net/mdio/of_mdio.c b/drivers/net/mdio/of_mdio.c index 8e97d5b825f5..8744b1e1c2b1 100644 --- a/drivers/net/mdio/of_mdio.c +++ b/drivers/net/mdio/of_mdio.c @@ -10,6 +10,7 @@ #include <linux/device.h> #include <linux/err.h> +#include <linux/fwnode_mdio.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/netdevice.h> @@ -29,123 +30,22 @@ MODULE_LICENSE("GPL"); * ethernet-phy-idAAAA.BBBB */ static int of_get_phy_id(struct device_node *device, u32 *phy_id) { - struct property *prop; - const char *cp; - unsigned int upper, lower; - - of_property_for_each_string(device, "compatible", prop, cp) { - if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) == 2) { - *phy_id = ((upper & 0xFFFF) << 16) | (lower & 0xFFFF); - return 0; - } - } - return -EINVAL; -} - -static struct mii_timestamper *of_find_mii_timestamper(struct device_node *node) -{ - struct of_phandle_args arg; - int err; - - err = of_parse_phandle_with_fixed_args(node, "timestamper", 1, 0, &arg); - - if (err == -ENOENT) - return NULL; - else if (err) - return ERR_PTR(err); - - if (arg.args_count != 1) - return ERR_PTR(-EINVAL); - - return register_mii_timestamper(arg.np, arg.args[0]); + return fwnode_get_phy_id(of_fwnode_handle(device), phy_id); } int of_mdiobus_phy_device_register(struct mii_bus *mdio, struct phy_device *phy, - struct device_node *child, u32 addr) + struct device_node *child, u32 addr) { - int rc; - - rc = of_irq_get(child, 0); - if (rc == -EPROBE_DEFER) - return rc; - - if (rc > 0) { - phy->irq = rc; - mdio->irq[addr] = rc; - } else { - phy->irq = mdio->irq[addr]; - } - - if (of_property_read_bool(child, "broken-turn-around")) - mdio->phy_ignore_ta_mask |= 1 << addr; - - of_property_read_u32(child, "reset-assert-us", - &phy->mdio.reset_assert_delay); - of_property_read_u32(child, "reset-deassert-us", - &phy->mdio.reset_deassert_delay); - - /* Associate the OF node with the device structure so it - * can be looked up later */ - of_node_get(child); - phy->mdio.dev.of_node = child; - phy->mdio.dev.fwnode = of_fwnode_handle(child); - - /* All data is now stored in the phy struct; - * register it */ - rc = phy_device_register(phy); - if (rc) { - of_node_put(child); - return rc; - } - - dev_dbg(&mdio->dev, "registered phy %pOFn at address %i\n", - child, addr); - return 0; + return fwnode_mdiobus_phy_device_register(mdio, phy, + of_fwnode_handle(child), + addr); } EXPORT_SYMBOL(of_mdiobus_phy_device_register); static int of_mdiobus_register_phy(struct mii_bus *mdio, struct device_node *child, u32 addr) { - struct mii_timestamper *mii_ts; - struct phy_device *phy; - bool is_c45; - int rc; - u32 phy_id; - - mii_ts = of_find_mii_timestamper(child); - if (IS_ERR(mii_ts)) - return PTR_ERR(mii_ts); - - is_c45 = of_device_is_compatible(child, - "ethernet-phy-ieee802.3-c45"); - - if (!is_c45 && !of_get_phy_id(child, &phy_id)) - phy = phy_device_create(mdio, addr, phy_id, 0, NULL); - else - phy = get_phy_device(mdio, addr, is_c45); - if (IS_ERR(phy)) { - if (mii_ts) - unregister_mii_timestamper(mii_ts); - return PTR_ERR(phy); - } - - rc = of_mdiobus_phy_device_register(mdio, phy, child, addr); - if (rc) { - if (mii_ts) - unregister_mii_timestamper(mii_ts); - phy_device_free(phy); - return rc; - } - - /* phy->mii_ts may already be defined by the PHY driver. A - * mii_timestamper probed via the device tree will still have - * precedence. - */ - if (mii_ts) - phy->mii_ts = mii_ts; - - return 0; + return fwnode_mdiobus_register_phy(mdio, of_fwnode_handle(child), addr); } static int of_mdiobus_register_device(struct mii_bus *mdio, @@ -347,16 +247,7 @@ EXPORT_SYMBOL(of_mdiobus_register); */ struct mdio_device *of_mdio_find_device(struct device_node *np) { - struct device *d; - - if (!np) - return NULL; - - d = bus_find_device_by_of_node(&mdio_bus_type, np); - if (!d) - return NULL; - - return to_mdio_device(d); + return fwnode_mdio_find_device(of_fwnode_handle(np)); } EXPORT_SYMBOL(of_mdio_find_device); @@ -369,18 +260,7 @@ EXPORT_SYMBOL(of_mdio_find_device); */ struct phy_device *of_phy_find_device(struct device_node *phy_np) { - struct mdio_device *mdiodev; - - mdiodev = of_mdio_find_device(phy_np); - if (!mdiodev) - return NULL; - - if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) - return to_phy_device(&mdiodev->dev); - - put_device(&mdiodev->dev); - - return NULL; + return fwnode_phy_find_device(of_fwnode_handle(phy_np)); } EXPORT_SYMBOL(of_phy_find_device); diff --git a/drivers/net/phy/mii_timestamper.c b/drivers/net/phy/mii_timestamper.c index b71b7456462d..51ae0593a04f 100644 --- a/drivers/net/phy/mii_timestamper.c +++ b/drivers/net/phy/mii_timestamper.c @@ -111,6 +111,9 @@ void unregister_mii_timestamper(struct mii_timestamper *mii_ts) struct mii_timestamping_desc *desc; struct list_head *this; + if (!mii_ts) + return; + /* mii_timestamper statically registered by the PHY driver won't use the * register_mii_timestamper() and thus don't have ->device set. Don't * try to unregister these. diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 495d86b4af7c..85734309b580 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -9,6 +9,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/acpi.h> #include <linux/bitmap.h> #include <linux/delay.h> #include <linux/errno.h> @@ -833,6 +834,27 @@ static int get_phy_c22_id(struct mii_bus *bus, int addr, u32 *phy_id) return 0; } +/* Extract the phy ID from the compatible string of the form + * ethernet-phy-idAAAA.BBBB. + */ +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + unsigned int upper, lower; + const char *cp; + int ret; + + ret = fwnode_property_read_string(fwnode, "compatible", &cp); + if (ret) + return ret; + + if (sscanf(cp, "ethernet-phy-id%4x.%4x", &upper, &lower) != 2) + return -EINVAL; + + *phy_id = ((upper & GENMASK(15, 0)) << 16) | (lower & GENMASK(15, 0)); + return 0; +} +EXPORT_SYMBOL(fwnode_get_phy_id); + /** * get_phy_device - reads the specified PHY device and returns its @phy_device * struct @@ -935,8 +957,7 @@ EXPORT_SYMBOL(phy_device_register); */ void phy_device_remove(struct phy_device *phydev) { - if (phydev->mii_ts) - unregister_mii_timestamper(phydev->mii_ts); + unregister_mii_timestamper(phydev->mii_ts); device_del(&phydev->mdio.dev); @@ -2876,6 +2897,90 @@ static bool phy_drv_supports_irq(struct phy_driver *phydrv) } /** + * fwnode_mdio_find_device - Given a fwnode, find the mdio_device + * @fwnode: pointer to the mdio_device's fwnode + * + * If successful, returns a pointer to the mdio_device with the embedded + * struct device refcount incremented by one, or NULL on failure. + * The caller should call put_device() on the mdio_device after its use. + */ +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + struct device *d; + + if (!fwnode) + return NULL; + + d = bus_find_device_by_fwnode(&mdio_bus_type, fwnode); + if (!d) + return NULL; + + return to_mdio_device(d); +} +EXPORT_SYMBOL(fwnode_mdio_find_device); + +/** + * fwnode_phy_find_device - For provided phy_fwnode, find phy_device. + * + * @phy_fwnode: Pointer to the phy's fwnode. + * + * If successful, returns a pointer to the phy_device with the embedded + * struct device refcount incremented by one, or NULL on failure. + */ +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + struct mdio_device *mdiodev; + + mdiodev = fwnode_mdio_find_device(phy_fwnode); + if (!mdiodev) + return NULL; + + if (mdiodev->flags & MDIO_DEVICE_FLAG_PHY) + return to_phy_device(&mdiodev->dev); + + put_device(&mdiodev->dev); + + return NULL; +} +EXPORT_SYMBOL(fwnode_phy_find_device); + +/** + * device_phy_find_device - For the given device, get the phy_device + * @dev: Pointer to the given device + * + * Refer return conditions of fwnode_phy_find_device(). + */ +struct phy_device *device_phy_find_device(struct device *dev) +{ + return fwnode_phy_find_device(dev_fwnode(dev)); +} +EXPORT_SYMBOL_GPL(device_phy_find_device); + +/** + * fwnode_get_phy_node - Get the phy_node using the named reference. + * @fwnode: Pointer to fwnode from which phy_node has to be obtained. + * + * Refer return conditions of fwnode_find_reference(). + * For ACPI, only "phy-handle" is supported. Legacy DT properties "phy" + * and "phy-device" are not supported in ACPI. DT supports all the three + * named references to the phy node. + */ +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + struct fwnode_handle *phy_node; + + /* Only phy-handle is used for ACPI */ + phy_node = fwnode_find_reference(fwnode, "phy-handle", 0); + if (is_acpi_node(fwnode) || !IS_ERR(phy_node)) + return phy_node; + phy_node = fwnode_find_reference(fwnode, "phy", 0); + if (IS_ERR(phy_node)) + phy_node = fwnode_find_reference(fwnode, "phy-device", 0); + return phy_node; +} +EXPORT_SYMBOL_GPL(fwnode_get_phy_node); + +/** * phy_probe - probe and init a PHY device * @dev: device to probe and init * diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index 96d8e88b4e46..bb9eeb74f70a 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -5,6 +5,7 @@ * * Copyright (C) 2015 Russell King */ +#include <linux/acpi.h> #include <linux/ethtool.h> #include <linux/export.h> #include <linux/gpio/consumer.h> @@ -1084,7 +1085,26 @@ EXPORT_SYMBOL_GPL(phylink_connect_phy); int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, u32 flags) { - struct device_node *phy_node; + return phylink_fwnode_phy_connect(pl, of_fwnode_handle(dn), flags); +} +EXPORT_SYMBOL_GPL(phylink_of_phy_connect); + +/** + * phylink_fwnode_phy_connect() - connect the PHY specified in the fwnode. + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @fwnode: a pointer to a &struct fwnode_handle. + * @flags: PHY-specific flags to communicate to the PHY device driver + * + * Connect the phy specified @fwnode to the phylink instance specified + * by @pl. + * + * Returns 0 on success or a negative errno. + */ +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags) +{ + struct fwnode_handle *phy_fwnode; struct phy_device *phy_dev; int ret; @@ -1094,28 +1114,25 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, phy_interface_mode_is_8023z(pl->link_interface))) return 0; - phy_node = of_parse_phandle(dn, "phy-handle", 0); - if (!phy_node) - phy_node = of_parse_phandle(dn, "phy", 0); - if (!phy_node) - phy_node = of_parse_phandle(dn, "phy-device", 0); - - if (!phy_node) { + phy_fwnode = fwnode_get_phy_node(fwnode); + if (IS_ERR(phy_fwnode)) { if (pl->cfg_link_an_mode == MLO_AN_PHY) return -ENODEV; return 0; } - phy_dev = of_phy_find_device(phy_node); + phy_dev = fwnode_phy_find_device(phy_fwnode); /* We're done with the phy_node handle */ - of_node_put(phy_node); + fwnode_handle_put(phy_fwnode); if (!phy_dev) return -ENODEV; ret = phy_attach_direct(pl->netdev, phy_dev, flags, pl->link_interface); - if (ret) + if (ret) { + phy_device_free(phy_dev); return ret; + } ret = phylink_bringup_phy(pl, phy_dev, pl->link_config.interface); if (ret) @@ -1123,7 +1140,7 @@ int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, return ret; } -EXPORT_SYMBOL_GPL(phylink_of_phy_connect); +EXPORT_SYMBOL_GPL(phylink_fwnode_phy_connect); /** * phylink_disconnect_phy() - disconnect any PHY attached to the phylink diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c index 8a477171e8f5..aec97b021a73 100644 --- a/drivers/net/usb/asix_devices.c +++ b/drivers/net/usb/asix_devices.c @@ -598,6 +598,9 @@ static void ax88772_suspend(struct usbnet *dev) struct asix_common_private *priv = dev->driver_priv; u16 medium; + if (netif_running(dev->net)) + phy_stop(priv->phydev); + /* Stop MAC operation */ medium = asix_read_medium_status(dev, 1); medium &= ~AX_MEDIUM_RE; @@ -605,14 +608,6 @@ static void ax88772_suspend(struct usbnet *dev) netdev_dbg(dev->net, "ax88772_suspend: medium=0x%04x\n", asix_read_medium_status(dev, 1)); - - /* Preserve BMCR for restoring */ - priv->presvd_phy_bmcr = - asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_BMCR); - - /* Preserve ANAR for restoring */ - priv->presvd_phy_advertise = - asix_mdio_read_nopm(dev->net, dev->mii.phy_id, MII_ADVERTISE); } static int asix_suspend(struct usb_interface *intf, pm_message_t message) @@ -626,39 +621,22 @@ static int asix_suspend(struct usb_interface *intf, pm_message_t message) return usbnet_suspend(intf, message); } -static void ax88772_restore_phy(struct usbnet *dev) -{ - struct asix_common_private *priv = dev->driver_priv; - - if (priv->presvd_phy_advertise) { - /* Restore Advertisement control reg */ - asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_ADVERTISE, - priv->presvd_phy_advertise); - - /* Restore BMCR */ - if (priv->presvd_phy_bmcr & BMCR_ANENABLE) - priv->presvd_phy_bmcr |= BMCR_ANRESTART; - - asix_mdio_write_nopm(dev->net, dev->mii.phy_id, MII_BMCR, - priv->presvd_phy_bmcr); - - priv->presvd_phy_advertise = 0; - priv->presvd_phy_bmcr = 0; - } -} - static void ax88772_resume(struct usbnet *dev) { + struct asix_common_private *priv = dev->driver_priv; int i; for (i = 0; i < 3; i++) if (!ax88772_hw_reset(dev, 1)) break; - ax88772_restore_phy(dev); + + if (netif_running(dev->net)) + phy_start(priv->phydev); } static void ax88772a_resume(struct usbnet *dev) { + struct asix_common_private *priv = dev->driver_priv; int i; for (i = 0; i < 3; i++) { @@ -666,7 +644,8 @@ static void ax88772a_resume(struct usbnet *dev) break; } - ax88772_restore_phy(dev); + if (netif_running(dev->net)) + phy_start(priv->phydev); } static int asix_resume(struct usb_interface *intf) @@ -722,6 +701,8 @@ static int ax88772_init_phy(struct usbnet *dev) return ret; } + priv->phydev->mac_managed_pm = 1; + phy_attached_info(priv->phydev); return 0; diff --git a/drivers/net/wan/pc300too.c b/drivers/net/wan/pc300too.c index 001fd378d417..7b123a771aa6 100644 --- a/drivers/net/wan/pc300too.c +++ b/drivers/net/wan/pc300too.c @@ -44,7 +44,7 @@ #define MAX_TX_BUFFERS 10 static int pci_clock_freq = 33000000; -static int use_crystal_clock = 0; +static int use_crystal_clock; static unsigned int CLOCK_BASE; /* Masks to access the init_ctrl PLX register */ @@ -52,11 +52,9 @@ static unsigned int CLOCK_BASE; #define PC300_CHMEDIA_MASK(port) (0x00000020UL << ((port) * 3)) #define PC300_CTYPE_MASK (0x00000800UL) - enum { PC300_RSV = 1, PC300_X21, PC300_TE }; /* card types */ -/* - * PLX PCI9050-1 local configuration and shared runtime registers. +/* PLX PCI9050-1 local configuration and shared runtime registers. * This structure can be used to access 9050 registers (memory mapped). */ typedef struct { @@ -69,9 +67,7 @@ typedef struct { u32 cs_base[4]; /* 3C-48h : Chip Select Base Addrs */ u32 intr_ctrl_stat; /* 4Ch : Interrupt Control/Status */ u32 init_ctrl; /* 50h : EEPROM ctrl, Init Ctrl, etc */ -}plx9050; - - +} plx9050; typedef struct port_s { struct napi_struct napi; @@ -88,9 +84,7 @@ typedef struct port_s { u16 txlast; u8 rxs, txs, tmc; /* SCA registers */ u8 chan; /* physical port # - 0 or 1 */ -}port_t; - - +} port_t; typedef struct card_s { int type; /* RSV, X21, etc. */ @@ -105,26 +99,24 @@ typedef struct card_s { u8 irq; /* interrupt request level */ port_t ports[2]; -}card_t; - +} card_t; #define get_port(card, port) ((port) < (card)->n_ports ? \ (&(card)->ports[port]) : (NULL)) #include "hd64572.c" - static void pc300_set_iface(port_t *port) { card_t *card = port->card; - u32 __iomem * init_ctrl = &card->plxbase->init_ctrl; + u32 __iomem *init_ctrl = &card->plxbase->init_ctrl; u16 msci = get_msci(port); u8 rxs = port->rxs & CLK_BRG_MASK; u8 txs = port->txs & CLK_BRG_MASK; sca_out(EXS_TES1, (port->chan ? MSCI1_OFFSET : MSCI0_OFFSET) + EXS, port->card); - switch(port->settings.clock_type) { + switch (port->settings.clock_type) { case CLOCK_INT: rxs |= CLK_BRG; /* BRG output */ txs |= CLK_PIN_OUT | CLK_TX_RXCLK; /* RX clock */ @@ -162,13 +154,11 @@ static void pc300_set_iface(port_t *port) } } - - static int pc300_open(struct net_device *dev) { port_t *port = dev_to_port(dev); - int result = hdlc_open(dev); + if (result) return result; @@ -177,8 +167,6 @@ static int pc300_open(struct net_device *dev) return 0; } - - static int pc300_close(struct net_device *dev) { sca_close(dev); @@ -186,8 +174,6 @@ static int pc300_close(struct net_device *dev) return 0; } - - static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { const size_t size = sizeof(sync_serial_settings); @@ -214,7 +200,6 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (copy_to_user(line, &port->settings, size)) return -EFAULT; return 0; - } if (port->card->type == PC300_X21 && @@ -255,8 +240,6 @@ static int pc300_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return 0; } - - static void pc300_pci_remove_one(struct pci_dev *pdev) { int i; @@ -314,7 +297,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev, } card = kzalloc(sizeof(card_t), GFP_KERNEL); - if (card == NULL) { + if (!card) { pci_release_regions(pdev); pci_disable_device(pdev); return -ENOBUFS; @@ -338,9 +321,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev, ramphys = pci_resource_start(pdev, 3) & PCI_BASE_ADDRESS_MEM_MASK; card->rambase = pci_ioremap_bar(pdev, 3); - if (card->plxbase == NULL || - card->scabase == NULL || - card->rambase == NULL) { + if (!card->plxbase || !card->scabase || !card->rambase) { pr_err("ioremap() failed\n"); pc300_pci_remove_one(pdev); return -ENOMEM; @@ -365,12 +346,14 @@ static int pc300_pci_init_one(struct pci_dev *pdev, else card->n_ports = 2; - for (i = 0; i < card->n_ports; i++) - if (!(card->ports[i].netdev = alloc_hdlcdev(&card->ports[i]))) { + for (i = 0; i < card->n_ports; i++) { + card->ports[i].netdev = alloc_hdlcdev(&card->ports[i]); + if (!card->ports[i].netdev) { pr_err("unable to allocate memory\n"); pc300_pci_remove_one(pdev); return -ENOMEM; } + } /* Reset PLX */ p = &card->plxbase->init_ctrl; @@ -442,6 +425,7 @@ static int pc300_pci_init_one(struct pci_dev *pdev, port_t *port = &card->ports[i]; struct net_device *dev = port->netdev; hdlc_device *hdlc = dev_to_hdlc(dev); + port->chan = i; spin_lock_init(&port->lock); @@ -472,8 +456,6 @@ static int pc300_pci_init_one(struct pci_dev *pdev, return 0; } - - static const struct pci_device_id pc300_pci_tbl[] = { { PCI_VENDOR_ID_CYCLADES, PCI_DEVICE_ID_PC300_RX_1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, @@ -486,7 +468,6 @@ static const struct pci_device_id pc300_pci_tbl[] = { { 0, } }; - static struct pci_driver pc300_pci_driver = { .name = "PC300", .id_table = pc300_pci_tbl, @@ -494,7 +475,6 @@ static struct pci_driver pc300_pci_driver = { .remove = pc300_pci_remove_one, }; - static int __init pc300_init_module(void) { if (pci_clock_freq < 1000000 || pci_clock_freq > 80000000) { @@ -511,8 +491,6 @@ static int __init pc300_init_module(void) return pci_register_driver(&pc300_pci_driver); } - - static void __exit pc300_cleanup_module(void) { pci_unregister_driver(&pc300_pci_driver); diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c index 7863b2536999..528745862738 100644 --- a/drivers/nfc/fdp/fdp.c +++ b/drivers/nfc/fdp/fdp.c @@ -266,7 +266,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) r = request_firmware(&info->ram_patch, FDP_RAM_PATCH_NAME, dev); if (r < 0) { nfc_err(dev, "RAM patch request error\n"); - goto error; + return r; } data = (u8 *) info->ram_patch->data; @@ -283,7 +283,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) r = request_firmware(&info->otp_patch, FDP_OTP_PATCH_NAME, dev); if (r < 0) { nfc_err(dev, "OTP patch request error\n"); - goto out; + return 0; } data = (u8 *) info->otp_patch->data; @@ -295,10 +295,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev) dev_dbg(dev, "OTP patch version: %d, size: %d\n", info->otp_patch_version, (int) info->otp_patch->size); -out: return 0; -error: - return r; } static void fdp_nci_release_firmware(struct nci_dev *ndev) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index fd9b869d278e..f4d554ea0c93 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -417,13 +417,17 @@ enum qeth_qdio_out_buffer_state { QETH_QDIO_BUF_EMPTY, /* Filled by driver; owned by hardware in order to be sent. */ QETH_QDIO_BUF_PRIMED, - /* Discovered by the TX completion code: */ - QETH_QDIO_BUF_PENDING, - /* Finished by the TX completion code: */ - QETH_QDIO_BUF_NEED_QAOB, - /* Received QAOB notification on CQ: */ - QETH_QDIO_BUF_QAOB_OK, - QETH_QDIO_BUF_QAOB_ERROR, +}; + +enum qeth_qaob_state { + QETH_QAOB_ISSUED, + QETH_QAOB_PENDING, + QETH_QAOB_DONE, +}; + +struct qeth_qaob_priv1 { + unsigned int state; + u8 queue_no; }; struct qeth_qdio_out_buffer { @@ -433,9 +437,8 @@ struct qeth_qdio_out_buffer { unsigned int frames; unsigned int bytes; struct sk_buff_head skb_list; - int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER]; + DECLARE_BITMAP(from_kmem_cache, QDIO_MAX_ELEMENTS_PER_BUFFER); - struct qeth_qdio_out_q *q; struct list_head list_entry; struct qaob *aob; }; @@ -483,6 +486,7 @@ struct qeth_out_q_stats { u64 stopped; u64 doorbell; u64 coal_frames; + u64 completion_irq; u64 completion_yield; u64 completion_timer; @@ -526,6 +530,7 @@ struct qeth_qdio_out_q { unsigned int coalesce_usecs; unsigned int max_coalesced_frames; + unsigned int rescan_usecs; }; #define qeth_for_each_output_queue(card, q, i) \ @@ -612,7 +617,6 @@ struct qeth_channel { struct ccw_device *ccwdev; struct qeth_cmd_buffer *active_cmd; enum qeth_channel_states state; - atomic_t irq_pending; }; struct qeth_reply { @@ -662,11 +666,6 @@ static inline struct ccw1 *__ccw_from_cmd(struct qeth_cmd_buffer *iob) return (struct ccw1 *)(iob->data + ALIGN(iob->length, 8)); } -static inline bool qeth_trylock_channel(struct qeth_channel *channel) -{ - return atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0; -} - /** * OSA card related definitions */ @@ -886,13 +885,24 @@ static inline bool qeth_card_hw_is_reachable(struct qeth_card *card) return card->state == CARD_STATE_SOFTSETUP; } +static inline bool qeth_use_tx_irqs(struct qeth_card *card) +{ + return !IS_IQD(card); +} + static inline void qeth_unlock_channel(struct qeth_card *card, struct qeth_channel *channel) { - atomic_set(&channel->irq_pending, 0); + xchg(&channel->active_cmd, NULL); wake_up(&card->wait_q); } +static inline bool qeth_trylock_channel(struct qeth_channel *channel, + struct qeth_cmd_buffer *cmd) +{ + return cmpxchg(&channel->active_cmd, NULL, cmd) == NULL; +} + struct qeth_trap_id { __u16 lparnr; char vmname[8]; diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index a1f08e9aa064..62f88ccbd03f 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -70,9 +70,6 @@ static void qeth_issue_next_read_cb(struct qeth_card *card, unsigned int data_length); static int qeth_qdio_establish(struct qeth_card *); static void qeth_free_qdio_queues(struct qeth_card *card); -static void qeth_notify_skbs(struct qeth_qdio_out_q *queue, - struct qeth_qdio_out_buffer *buf, - enum iucv_tx_notify notification); static void qeth_close_dev_handler(struct work_struct *work) { @@ -434,65 +431,6 @@ static enum iucv_tx_notify qeth_compute_cq_notification(int sbalf15, return n; } -static void qeth_qdio_handle_aob(struct qeth_card *card, - unsigned long phys_aob_addr) -{ - enum qeth_qdio_out_buffer_state new_state = QETH_QDIO_BUF_QAOB_OK; - struct qaob *aob; - struct qeth_qdio_out_buffer *buffer; - enum iucv_tx_notify notification; - struct qeth_qdio_out_q *queue; - unsigned int i; - - aob = (struct qaob *) phys_to_virt(phys_aob_addr); - QETH_CARD_TEXT(card, 5, "haob"); - QETH_CARD_TEXT_(card, 5, "%lx", phys_aob_addr); - buffer = (struct qeth_qdio_out_buffer *) aob->user1; - QETH_CARD_TEXT_(card, 5, "%lx", aob->user1); - - if (aob->aorc) { - QETH_CARD_TEXT_(card, 2, "aorc%02X", aob->aorc); - new_state = QETH_QDIO_BUF_QAOB_ERROR; - } - - switch (atomic_xchg(&buffer->state, new_state)) { - case QETH_QDIO_BUF_PRIMED: - /* Faster than TX completion code, let it handle the async - * completion for us. It will also recycle the QAOB. - */ - break; - case QETH_QDIO_BUF_PENDING: - /* TX completion code is active and will handle the async - * completion for us. It will also recycle the QAOB. - */ - break; - case QETH_QDIO_BUF_NEED_QAOB: - /* TX completion code is already finished. */ - notification = qeth_compute_cq_notification(aob->aorc, 1); - qeth_notify_skbs(buffer->q, buffer, notification); - - /* Free dangling allocations. The attached skbs are handled by - * qeth_tx_complete_pending_bufs(), and so is the QAOB. - */ - for (i = 0; - i < aob->sb_count && i < QETH_MAX_BUFFER_ELEMENTS(card); - i++) { - void *data = phys_to_virt(aob->sba[i]); - - if (data && buffer->is_header[i]) - kmem_cache_free(qeth_core_header_cache, data); - buffer->is_header[i] = 0; - } - - queue = buffer->q; - atomic_set(&buffer->state, QETH_QDIO_BUF_EMPTY); - napi_schedule(&queue->napi); - break; - default: - WARN_ON_ONCE(1); - } -} - static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u8 flags, u32 len, void *data) { @@ -1268,7 +1206,6 @@ static void qeth_irq(struct ccw_device *cdev, unsigned long intparm, iob = (struct qeth_cmd_buffer *) (addr_t)intparm; } - channel->active_cmd = NULL; qeth_unlock_channel(card, channel); rc = qeth_check_irb_error(card, cdev, irb); @@ -1353,10 +1290,10 @@ static void qeth_notify_skbs(struct qeth_qdio_out_q *q, } } -static void qeth_tx_complete_buf(struct qeth_qdio_out_buffer *buf, bool error, +static void qeth_tx_complete_buf(struct qeth_qdio_out_q *queue, + struct qeth_qdio_out_buffer *buf, bool error, int budget) { - struct qeth_qdio_out_q *queue = buf->q; struct sk_buff *skb; /* Empty buffer? */ @@ -1400,17 +1337,18 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue, int i; /* is PCI flag set on buffer? */ - if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ) + if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ) { atomic_dec(&queue->set_pci_flags_count); + QETH_TXQ_STAT_INC(queue, completion_irq); + } - qeth_tx_complete_buf(buf, error, budget); + qeth_tx_complete_buf(queue, buf, error, budget); for (i = 0; i < queue->max_elements; ++i) { void *data = phys_to_virt(buf->buffer->element[i].addr); - if (data && buf->is_header[i]) + if (__test_and_clear_bit(i, buf->from_kmem_cache) && data) kmem_cache_free(qeth_core_header_cache, data); - buf->is_header[i] = 0; } qeth_scrub_qdio_buffer(buf->buffer, queue->max_elements); @@ -1434,14 +1372,30 @@ static void qeth_tx_complete_pending_bufs(struct qeth_card *card, struct qeth_qdio_out_buffer *buf, *tmp; list_for_each_entry_safe(buf, tmp, &queue->pending_bufs, list_entry) { - if (drain || atomic_read(&buf->state) == QETH_QDIO_BUF_EMPTY) { + struct qeth_qaob_priv1 *priv; + struct qaob *aob = buf->aob; + enum iucv_tx_notify notify; + unsigned int i; + + priv = (struct qeth_qaob_priv1 *)&aob->user1; + if (drain || READ_ONCE(priv->state) == QETH_QAOB_DONE) { QETH_CARD_TEXT(card, 5, "fp"); QETH_CARD_TEXT_(card, 5, "%lx", (long) buf); - if (drain) - qeth_notify_skbs(queue, buf, - TX_NOTIFY_GENERALERROR); - qeth_tx_complete_buf(buf, drain, budget); + notify = drain ? TX_NOTIFY_GENERALERROR : + qeth_compute_cq_notification(aob->aorc, 1); + qeth_notify_skbs(queue, buf, notify); + qeth_tx_complete_buf(queue, buf, drain, budget); + + for (i = 0; + i < aob->sb_count && i < queue->max_elements; + i++) { + void *data = phys_to_virt(aob->sba[i]); + + if (test_bit(i, buf->from_kmem_cache) && data) + kmem_cache_free(qeth_core_header_cache, + data); + } list_del(&buf->list_entry); qeth_free_out_buf(buf); @@ -1713,11 +1667,10 @@ static int qeth_stop_channel(struct qeth_channel *channel) rc = ccw_device_set_offline(cdev); spin_lock_irq(get_ccwdev_lock(cdev)); - if (channel->active_cmd) { + if (channel->active_cmd) dev_err(&cdev->dev, "Stopped channel while cmd %px was still active\n", channel->active_cmd); - channel->active_cmd = NULL; - } + cdev->handler = NULL; spin_unlock_irq(get_ccwdev_lock(cdev)); @@ -1730,7 +1683,7 @@ static int qeth_start_channel(struct qeth_channel *channel) int rc; channel->state = CH_STATE_DOWN; - atomic_set(&channel->irq_pending, 0); + xchg(&channel->active_cmd, NULL); spin_lock_irq(get_ccwdev_lock(cdev)); cdev->handler = qeth_irq; @@ -2037,7 +1990,7 @@ static int qeth_send_control_data(struct qeth_card *card, reply->param = reply_param; timeout = wait_event_interruptible_timeout(card->wait_q, - qeth_trylock_channel(channel), + qeth_trylock_channel(channel, iob), timeout); if (timeout <= 0) { qeth_put_cmd(iob); @@ -2057,8 +2010,6 @@ static int qeth_send_control_data(struct qeth_card *card, spin_lock_irq(get_ccwdev_lock(channel->ccwdev)); rc = ccw_device_start_timeout(channel->ccwdev, __ccw_from_cmd(iob), (addr_t) iob, 0, 0, timeout); - if (!rc) - channel->active_cmd = iob; spin_unlock_irq(get_ccwdev_lock(channel->ccwdev)); if (rc) { QETH_DBF_MESSAGE(2, "qeth_send_control_data on device %x: ccw_device_start rc = %i\n", @@ -2578,7 +2529,6 @@ static int qeth_alloc_out_buf(struct qeth_qdio_out_q *q, unsigned int bidx, newbuf->buffer = q->qdio_bufs[bidx]; skb_queue_head_init(&newbuf->skb_list); lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key); - newbuf->q = q; atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY); q->bufs[bidx] = newbuf; return 0; @@ -2663,8 +2613,15 @@ static int qeth_alloc_qdio_queues(struct qeth_card *card) INIT_LIST_HEAD(&queue->pending_bufs); spin_lock_init(&queue->lock); timer_setup(&queue->timer, qeth_tx_completion_timer, 0); - queue->coalesce_usecs = QETH_TX_COALESCE_USECS; - queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES; + if (IS_IQD(card)) { + queue->coalesce_usecs = QETH_TX_COALESCE_USECS; + queue->max_coalesced_frames = QETH_TX_MAX_COALESCED_FRAMES; + queue->rescan_usecs = QETH_TX_TIMER_USECS; + } else { + queue->coalesce_usecs = USEC_PER_SEC; + queue->max_coalesced_frames = 0; + queue->rescan_usecs = 10 * USEC_PER_SEC; + } queue->priority = QETH_QIB_PQUE_PRIO_DEFAULT; } @@ -3601,8 +3558,8 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, int count) { struct qeth_qdio_out_buffer *buf = queue->bufs[index]; - unsigned int qdio_flags = QDIO_FLAG_SYNC_OUTPUT; struct qeth_card *card = queue->card; + unsigned int frames, usecs; struct qaob *aob = NULL; int rc; int i; @@ -3629,8 +3586,12 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, if (!buf->aob) buf->aob = qdio_allocate_aob(); if (buf->aob) { + struct qeth_qaob_priv1 *priv; + aob = buf->aob; - aob->user1 = (u64) buf; + priv = (struct qeth_qaob_priv1 *)&aob->user1; + priv->state = QETH_QAOB_ISSUED; + priv->queue_no = queue->queue_no; } } } else { @@ -3658,14 +3619,11 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ; } } - - if (atomic_read(&queue->set_pci_flags_count)) - qdio_flags |= QDIO_FLAG_PCI_OUT; } QETH_TXQ_STAT_INC(queue, doorbell); - rc = do_QDIO(CARD_DDEV(card), qdio_flags, queue->queue_no, index, count, - aob); + rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_OUTPUT, queue->queue_no, + index, count, aob); switch (rc) { case 0: @@ -3673,17 +3631,20 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index, /* ignore temporary SIGA errors without busy condition */ /* Fake the TX completion interrupt: */ - if (IS_IQD(card)) { - unsigned int frames = READ_ONCE(queue->max_coalesced_frames); - unsigned int usecs = READ_ONCE(queue->coalesce_usecs); + frames = READ_ONCE(queue->max_coalesced_frames); + usecs = READ_ONCE(queue->coalesce_usecs); - if (frames && queue->coalesced_frames >= frames) { - napi_schedule(&queue->napi); - queue->coalesced_frames = 0; - QETH_TXQ_STAT_INC(queue, coal_frames); - } else if (usecs) { - qeth_tx_arm_timer(queue, usecs); - } + if (frames && queue->coalesced_frames >= frames) { + napi_schedule(&queue->napi); + queue->coalesced_frames = 0; + QETH_TXQ_STAT_INC(queue, coal_frames); + } else if (qeth_use_tx_irqs(card) && + atomic_read(&queue->used_buffers) >= 32) { + /* Old behaviour carried over from the qdio layer: */ + napi_schedule(&queue->napi); + QETH_TXQ_STAT_INC(queue, coal_frames); + } else if (usecs) { + qeth_tx_arm_timer(queue, usecs); } break; @@ -3769,6 +3730,18 @@ out: } EXPORT_SYMBOL_GPL(qeth_configure_cq); +static void qeth_qdio_handle_aob(struct qeth_card *card, struct qaob *aob) +{ + struct qeth_qaob_priv1 *priv = (struct qeth_qaob_priv1 *)&aob->user1; + unsigned int queue_no = priv->queue_no; + + BUILD_BUG_ON(sizeof(*priv) > ARRAY_SIZE(aob->user1)); + + if (xchg(&priv->state, QETH_QAOB_DONE) == QETH_QAOB_PENDING && + queue_no < card->qdio.no_out_queues) + napi_schedule(&card->qdio.out_qs[queue_no]->napi); +} + static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, unsigned int queue, int first_element, int count) @@ -3795,7 +3768,7 @@ static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err, buffer->element[e].addr) { unsigned long phys_aob_addr = buffer->element[e].addr; - qeth_qdio_handle_aob(card, phys_aob_addr); + qeth_qdio_handle_aob(card, phys_to_virt(phys_aob_addr)); ++e; } qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER); @@ -3831,36 +3804,14 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev, unsigned long card_ptr) { struct qeth_card *card = (struct qeth_card *) card_ptr; - struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue]; struct net_device *dev = card->dev; - struct netdev_queue *txq; - int i; QETH_CARD_TEXT(card, 6, "qdouhdl"); if (qdio_error & QDIO_ERROR_FATAL) { QETH_CARD_TEXT(card, 2, "achkcond"); netif_tx_stop_all_queues(dev); qeth_schedule_recovery(card); - return; } - - for (i = first_element; i < (first_element + count); ++i) { - struct qeth_qdio_out_buffer *buf = queue->bufs[QDIO_BUFNR(i)]; - - qeth_handle_send_error(card, buf, qdio_error); - qeth_clear_output_buffer(queue, buf, qdio_error, 0); - } - - atomic_sub(count, &queue->used_buffers); - qeth_check_outbound_queue(queue); - - txq = netdev_get_tx_queue(dev, __queue); - /* xmit may have observed the full-condition, but not yet stopped the - * txq. In which case the code below won't trigger. So before returning, - * xmit will re-check the txq's fill level and wake it up if needed. - */ - if (netif_tx_queue_stopped(txq) && !qeth_out_queue_is_full(queue)) - netif_tx_wake_queue(txq); } /** @@ -4101,7 +4052,7 @@ static unsigned int qeth_fill_buffer(struct qeth_qdio_out_buffer *buf, /* HW header is allocated from cache: */ if ((void *)hdr != skb->data) - buf->is_header[element] = 1; + __set_bit(element, buf->from_kmem_cache); /* HW header was pushed and is contiguous with linear part: */ else if (length > 0 && !PAGE_ALIGNED(data) && (data == (char *)hdr + hd_len)) @@ -5256,7 +5207,6 @@ static int qeth_qdio_establish(struct qeth_card *card) init_data.int_parm = (unsigned long) card; init_data.input_sbal_addr_array = in_sbal_ptrs; init_data.output_sbal_addr_array = out_sbal_ptrs; - init_data.scan_threshold = IS_IQD(card) ? 0 : 32; if (atomic_cmpxchg(&card->qdio.state, QETH_QDIO_ALLOCATED, QETH_QDIO_ESTABLISHED) == QETH_QDIO_ALLOCATED) { @@ -5956,9 +5906,10 @@ static unsigned int qeth_rx_poll(struct qeth_card *card, int budget) /* Fetch completed RX buffers: */ if (!card->rx.b_count) { card->rx.qdio_err = 0; - card->rx.b_count = qdio_get_next_buffers( - card->data.ccwdev, 0, &card->rx.b_index, - &card->rx.qdio_err); + card->rx.b_count = qdio_inspect_queue(CARD_DDEV(card), + 0, true, + &card->rx.b_index, + &card->rx.qdio_err); if (card->rx.b_count <= 0) { card->rx.b_count = 0; break; @@ -6022,6 +5973,16 @@ int qeth_poll(struct napi_struct *napi, int budget) work_done = qeth_rx_poll(card, budget); + if (qeth_use_tx_irqs(card)) { + struct qeth_qdio_out_q *queue; + unsigned int i; + + qeth_for_each_output_queue(card, queue, i) { + if (!qeth_out_queue_is_empty(queue)) + napi_schedule(&queue->napi); + } + } + if (card->options.cq == QETH_CQ_ENABLED) qeth_cq_poll(card); @@ -6055,6 +6016,8 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue, if (qdio_error == QDIO_ERROR_SLSB_PENDING) { struct qaob *aob = buffer->aob; + struct qeth_qaob_priv1 *priv; + enum iucv_tx_notify notify; if (!aob) { netdev_WARN_ONCE(card->dev, @@ -6066,60 +6029,27 @@ static void qeth_iqd_tx_complete(struct qeth_qdio_out_q *queue, QETH_CARD_TEXT_(card, 5, "pel%u", bidx); - switch (atomic_cmpxchg(&buffer->state, - QETH_QDIO_BUF_PRIMED, - QETH_QDIO_BUF_PENDING)) { - case QETH_QDIO_BUF_PRIMED: - /* We have initial ownership, no QAOB (yet): */ + priv = (struct qeth_qaob_priv1 *)&aob->user1; + /* QAOB hasn't completed yet: */ + if (xchg(&priv->state, QETH_QAOB_PENDING) != QETH_QAOB_DONE) { qeth_notify_skbs(queue, buffer, TX_NOTIFY_PENDING); - /* Handle race with qeth_qdio_handle_aob(): */ - switch (atomic_xchg(&buffer->state, - QETH_QDIO_BUF_NEED_QAOB)) { - case QETH_QDIO_BUF_PENDING: - /* No concurrent QAOB notification. */ - - /* Prepare the queue slot for immediate re-use: */ - qeth_scrub_qdio_buffer(buffer->buffer, queue->max_elements); - if (qeth_alloc_out_buf(queue, bidx, - GFP_ATOMIC)) { - QETH_CARD_TEXT(card, 2, "outofbuf"); - qeth_schedule_recovery(card); - } - - list_add(&buffer->list_entry, - &queue->pending_bufs); - /* Skip clearing the buffer: */ - return; - case QETH_QDIO_BUF_QAOB_OK: - qeth_notify_skbs(queue, buffer, - TX_NOTIFY_DELAYED_OK); - error = false; - break; - case QETH_QDIO_BUF_QAOB_ERROR: - qeth_notify_skbs(queue, buffer, - TX_NOTIFY_DELAYED_GENERALERROR); - error = true; - break; - default: - WARN_ON_ONCE(1); + /* Prepare the queue slot for immediate re-use: */ + qeth_scrub_qdio_buffer(buffer->buffer, queue->max_elements); + if (qeth_alloc_out_buf(queue, bidx, GFP_ATOMIC)) { + QETH_CARD_TEXT(card, 2, "outofbuf"); + qeth_schedule_recovery(card); } - break; - case QETH_QDIO_BUF_QAOB_OK: - /* qeth_qdio_handle_aob() already received a QAOB: */ - qeth_notify_skbs(queue, buffer, TX_NOTIFY_OK); - error = false; - break; - case QETH_QDIO_BUF_QAOB_ERROR: - /* qeth_qdio_handle_aob() already received a QAOB: */ - qeth_notify_skbs(queue, buffer, TX_NOTIFY_GENERALERROR); - error = true; - break; - default: - WARN_ON_ONCE(1); + list_add(&buffer->list_entry, &queue->pending_bufs); + /* Skip clearing the buffer: */ + return; } + /* QAOB already completed: */ + notify = qeth_compute_cq_notification(aob->aorc, 0); + qeth_notify_skbs(queue, buffer, notify); + error = !!aob->aorc; memset(aob, 0, sizeof(*aob)); } else if (card->options.cq == QETH_CQ_ENABLED) { qeth_notify_skbs(queue, buffer, @@ -6138,7 +6068,10 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget) unsigned int work_done = 0; struct netdev_queue *txq; - txq = netdev_get_tx_queue(dev, qeth_iqd_translate_txq(dev, queue_no)); + if (IS_IQD(card)) + txq = netdev_get_tx_queue(dev, qeth_iqd_translate_txq(dev, queue_no)); + else + txq = netdev_get_tx_queue(dev, queue_no); while (1) { unsigned int start, error, i; @@ -6165,8 +6098,9 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget) &start, &error); if (completed <= 0) { /* Ensure we see TX completion for pending work: */ - if (napi_complete_done(napi, 0)) - qeth_tx_arm_timer(queue, QETH_TX_TIMER_USECS); + if (napi_complete_done(napi, 0) && + !atomic_read(&queue->set_pci_flags_count)) + qeth_tx_arm_timer(queue, queue->rescan_usecs); return 0; } @@ -6179,12 +6113,19 @@ static int qeth_tx_poll(struct napi_struct *napi, int budget) bytes += buffer->bytes; qeth_handle_send_error(card, buffer, error); - qeth_iqd_tx_complete(queue, bidx, error, budget); + if (IS_IQD(card)) + qeth_iqd_tx_complete(queue, bidx, error, budget); + else + qeth_clear_output_buffer(queue, buffer, error, + budget); } - netdev_tx_completed_queue(txq, packets, bytes); atomic_sub(completed, &queue->used_buffers); work_done += completed; + if (IS_IQD(card)) + netdev_tx_completed_queue(txq, packets, bytes); + else + qeth_check_outbound_queue(queue); /* xmit may have observed the full-condition, but not yet * stopped the txq. In which case the code below won't trigger. @@ -7228,6 +7169,8 @@ EXPORT_SYMBOL_GPL(qeth_iqd_select_queue); int qeth_open(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; + struct qeth_qdio_out_q *queue; + unsigned int i; QETH_CARD_TEXT(card, 4, "qethopen"); @@ -7235,16 +7178,11 @@ int qeth_open(struct net_device *dev) netif_tx_start_all_queues(dev); local_bh_disable(); - if (IS_IQD(card)) { - struct qeth_qdio_out_q *queue; - unsigned int i; - - qeth_for_each_output_queue(card, queue, i) { - netif_tx_napi_add(dev, &queue->napi, qeth_tx_poll, - QETH_NAPI_WEIGHT); - napi_enable(&queue->napi); - napi_schedule(&queue->napi); - } + qeth_for_each_output_queue(card, queue, i) { + netif_tx_napi_add(dev, &queue->napi, qeth_tx_poll, + QETH_NAPI_WEIGHT); + napi_enable(&queue->napi); + napi_schedule(&queue->napi); } napi_enable(&card->napi); @@ -7259,6 +7197,8 @@ EXPORT_SYMBOL_GPL(qeth_open); int qeth_stop(struct net_device *dev) { struct qeth_card *card = dev->ml_priv; + struct qeth_qdio_out_q *queue; + unsigned int i; QETH_CARD_TEXT(card, 4, "qethstop"); @@ -7266,24 +7206,17 @@ int qeth_stop(struct net_device *dev) cancel_delayed_work_sync(&card->buffer_reclaim_work); qdio_stop_irq(CARD_DDEV(card)); - if (IS_IQD(card)) { - struct qeth_qdio_out_q *queue; - unsigned int i; - - /* Quiesce the NAPI instances: */ - qeth_for_each_output_queue(card, queue, i) - napi_disable(&queue->napi); + /* Quiesce the NAPI instances: */ + qeth_for_each_output_queue(card, queue, i) + napi_disable(&queue->napi); - /* Stop .ndo_start_xmit, might still access queue->napi. */ - netif_tx_disable(dev); + /* Stop .ndo_start_xmit, might still access queue->napi. */ + netif_tx_disable(dev); - qeth_for_each_output_queue(card, queue, i) { - del_timer_sync(&queue->timer); - /* Queues may get re-allocated, so remove the NAPIs. */ - netif_napi_del(&queue->napi); - } - } else { - netif_tx_disable(dev); + qeth_for_each_output_queue(card, queue, i) { + del_timer_sync(&queue->timer); + /* Queues may get re-allocated, so remove the NAPIs. */ + netif_napi_del(&queue->napi); } return 0; diff --git a/drivers/s390/net/qeth_ethtool.c b/drivers/s390/net/qeth_ethtool.c index 3a51bbff0ffe..2c4cb300a8fc 100644 --- a/drivers/s390/net/qeth_ethtool.c +++ b/drivers/s390/net/qeth_ethtool.c @@ -41,6 +41,7 @@ static const struct qeth_stats txq_stats[] = { QETH_TXQ_STAT("Queue stopped", stopped), QETH_TXQ_STAT("Doorbell", doorbell), QETH_TXQ_STAT("IRQ for frames", coal_frames), + QETH_TXQ_STAT("Completion IRQ", completion_irq), QETH_TXQ_STAT("Completion yield", completion_yield), QETH_TXQ_STAT("Completion timer", completion_timer), }; @@ -79,10 +80,8 @@ static void qeth_add_stat_strings(u8 **data, const char *prefix, { unsigned int i; - for (i = 0; i < size; i++) { - snprintf(*data, ETH_GSTRING_LEN, "%s%s", prefix, stats[i].name); - *data += ETH_GSTRING_LEN; - } + for (i = 0; i < size; i++) + ethtool_sprintf(data, "%s%s", prefix, stats[i].name); } static int qeth_get_sset_count(struct net_device *dev, int stringset) diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index ca44421a6d6e..2abf86c104d5 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -805,8 +805,6 @@ static int qeth_l2_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, if (!netif_device_present(dev)) return -ENODEV; - if (!(priv->brport_hw_features)) - return -EOPNOTSUPP; nlmsg_for_each_attr(attr, nlh, sizeof(struct ifinfomsg), rem1) { if (nla_type(attr) == IFLA_PROTINFO) { @@ -832,6 +830,16 @@ static int qeth_l2_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, return 0; if (!bp_tb[IFLA_BRPORT_LEARNING_SYNC]) return -EINVAL; + if (!(priv->brport_hw_features & BR_LEARNING_SYNC)) { + NL_SET_ERR_MSG_ATTR(extack, bp_tb[IFLA_BRPORT_LEARNING_SYNC], + "Operation not supported by HW"); + return -EOPNOTSUPP; + } + if (!IS_ENABLED(CONFIG_NET_SWITCHDEV)) { + NL_SET_ERR_MSG_ATTR(extack, bp_tb[IFLA_BRPORT_LEARNING_SYNC], + "Requires NET_SWITCHDEV"); + return -EOPNOTSUPP; + } enable = !!nla_get_u8(bp_tb[IFLA_BRPORT_LEARNING_SYNC]); if (enable == !!(priv->brport_features & BR_LEARNING_SYNC)) diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c index 5e78fb719602..119f08491d3c 100644 --- a/drivers/vhost/vsock.c +++ b/drivers/vhost/vsock.c @@ -31,7 +31,8 @@ enum { VHOST_VSOCK_FEATURES = VHOST_FEATURES | - (1ULL << VIRTIO_F_ACCESS_PLATFORM) + (1ULL << VIRTIO_F_ACCESS_PLATFORM) | + (1ULL << VIRTIO_VSOCK_F_SEQPACKET) }; enum { @@ -56,6 +57,7 @@ struct vhost_vsock { atomic_t queued_replies; u32 guest_cid; + bool seqpacket_allow; }; static u32 vhost_transport_get_local_cid(void) @@ -112,6 +114,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, size_t nbytes; size_t iov_len, payload_len; int head; + bool restore_flag = false; spin_lock_bh(&vsock->send_pkt_list_lock); if (list_empty(&vsock->send_pkt_list)) { @@ -168,9 +171,26 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, /* If the packet is greater than the space available in the * buffer, we split it using multiple buffers. */ - if (payload_len > iov_len - sizeof(pkt->hdr)) + if (payload_len > iov_len - sizeof(pkt->hdr)) { payload_len = iov_len - sizeof(pkt->hdr); + /* As we are copying pieces of large packet's buffer to + * small rx buffers, headers of packets in rx queue are + * created dynamically and are initialized with header + * of current packet(except length). But in case of + * SOCK_SEQPACKET, we also must clear record delimeter + * bit(VIRTIO_VSOCK_SEQ_EOR). Otherwise, instead of one + * packet with delimeter(which marks end of record), + * there will be sequence of packets with delimeter + * bit set. After initialized header will be copied to + * rx buffer, this bit will be restored. + */ + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + pkt->hdr.flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + restore_flag = true; + } + } + /* Set the correct length in the header */ pkt->hdr.len = cpu_to_le32(payload_len); @@ -204,6 +224,9 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock, * to send it with the next available buffer. */ if (pkt->off < pkt->len) { + if (restore_flag) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); + /* We are queueing the same virtio_vsock_pkt to handle * the remaining bytes, and we want to deliver it * to monitoring devices in the next iteration. @@ -354,8 +377,7 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq, return NULL; } - if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM) - pkt->len = le32_to_cpu(pkt->hdr.len); + pkt->len = le32_to_cpu(pkt->hdr.len); /* No payload */ if (!pkt->len) @@ -398,6 +420,8 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock) return val < vq->num; } +static bool vhost_transport_seqpacket_allow(u32 remote_cid); + static struct virtio_transport vhost_transport = { .transport = { .module = THIS_MODULE, @@ -424,6 +448,11 @@ static struct virtio_transport vhost_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = vhost_transport_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -441,6 +470,22 @@ static struct virtio_transport vhost_transport = { .send_pkt = vhost_transport_send_pkt, }; +static bool vhost_transport_seqpacket_allow(u32 remote_cid) +{ + struct vhost_vsock *vsock; + bool seqpacket_allow = false; + + rcu_read_lock(); + vsock = vhost_vsock_get(remote_cid); + + if (vsock) + seqpacket_allow = vsock->seqpacket_allow; + + rcu_read_unlock(); + + return seqpacket_allow; +} + static void vhost_vsock_handle_tx_kick(struct vhost_work *work) { struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue, @@ -785,6 +830,9 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features) goto err; } + if (features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET)) + vsock->seqpacket_allow = true; + for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) { vq = &vsock->vqs[i]; mutex_lock(&vq->mutex); diff --git a/include/linux/acpi.h b/include/linux/acpi.h index c60745f657e9..6ace3a0f1415 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -710,6 +710,8 @@ static inline u64 acpi_arch_get_root_pointer(void) } #endif +int acpi_get_local_address(acpi_handle handle, u32 *addr); + #else /* !CONFIG_ACPI */ #define acpi_disabled 1 @@ -965,6 +967,11 @@ static inline struct acpi_device *acpi_resource_consumer(struct resource *res) return NULL; } +static inline int acpi_get_local_address(acpi_handle handle, u32 *addr) +{ + return -ENODEV; +} + #endif /* !CONFIG_ACPI */ #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC diff --git a/include/linux/acpi_mdio.h b/include/linux/acpi_mdio.h new file mode 100644 index 000000000000..0a24ab7cb66f --- /dev/null +++ b/include/linux/acpi_mdio.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ACPI helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_ACPI_MDIO_H +#define __LINUX_ACPI_MDIO_H + +#include <linux/phy.h> + +#if IS_ENABLED(CONFIG_ACPI_MDIO) +int acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode); +#else /* CONFIG_ACPI_MDIO */ +static inline int +acpi_mdiobus_register(struct mii_bus *mdio, struct fwnode_handle *fwnode) +{ + /* + * Fall back to mdiobus_register() function to register a bus. + * This way, we don't have to keep compat bits around in drivers. + */ + + return mdiobus_register(mdio); +} +#endif + +#endif /* __LINUX_ACPI_MDIO_H */ diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index b12b05f1c8b4..1587961f1a7b 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -37,8 +37,6 @@ struct dsa_8021q_context { #define DSA_8021Q_N_SUBVLAN 8 -#if IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) - int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled); int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, @@ -52,6 +50,9 @@ int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, u16 tpid, u16 tci); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan); + u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port); u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port); @@ -70,78 +71,4 @@ bool vid_is_dsa_8021q_txvlan(u16 vid); bool vid_is_dsa_8021q(u16 vid); -#else - -int dsa_8021q_setup(struct dsa_8021q_context *ctx, bool enabled) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_join(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -int dsa_8021q_crosschip_bridge_leave(struct dsa_8021q_context *ctx, int port, - struct dsa_8021q_context *other_ctx, - int other_port) -{ - return 0; -} - -struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, - u16 tpid, u16 tci) -{ - return NULL; -} - -u16 dsa_8021q_tx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid(struct dsa_switch *ds, int port) -{ - return 0; -} - -u16 dsa_8021q_rx_vid_subvlan(struct dsa_switch *ds, int port, u16 subvlan) -{ - return 0; -} - -int dsa_8021q_rx_switch_id(u16 vid) -{ - return 0; -} - -int dsa_8021q_rx_source_port(u16 vid) -{ - return 0; -} - -u16 dsa_8021q_rx_subvlan(u16 vid) -{ - return 0; -} - -bool vid_is_dsa_8021q_rxvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q_txvlan(u16 vid) -{ - return false; -} - -bool vid_is_dsa_8021q(u16 vid) -{ - return false; -} - -#endif /* IS_ENABLED(CONFIG_NET_DSA_TAG_8021Q) */ - #endif /* _NET_DSA_8021Q_H */ diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index 1eb84562b311..b6089b88314c 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -14,6 +14,7 @@ #define ETH_P_SJA1105 ETH_P_DSA_8021Q #define ETH_P_SJA1105_META 0x0008 +#define ETH_P_SJA1110 0xdadc /* IEEE 802.3 Annex 57A: Slow Protocols PDUs (01:80:C2:xx:xx:xx) */ #define SJA1105_LINKLOCAL_FILTER_A 0x0180C2000000ull @@ -44,11 +45,14 @@ struct sja1105_tagger_data { */ spinlock_t meta_lock; unsigned long state; + u8 ts_id; }; struct sja1105_skb_cb { struct sk_buff *clone; - u32 meta_tstamp; + u64 tstamp; + /* Only valid for packets cloned for 2-step TX timestamping */ + u8 ts_id; }; #define SJA1105_SKB_CB(skb) \ @@ -65,4 +69,24 @@ struct sja1105_port { u16 xmit_tpid; }; +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; + +#if IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) + +void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + +#else + +static inline void sja1110_process_meta_tstamp(struct dsa_switch *ds, int port, + u8 ts_id, enum sja1110_meta_tstamp dir, + u64 tstamp) +{ +} + +#endif /* IS_ENABLED(CONFIG_NET_DSA_SJA1105_PTP) */ + #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/fwnode_mdio.h b/include/linux/fwnode_mdio.h new file mode 100644 index 000000000000..faf603c48c86 --- /dev/null +++ b/include/linux/fwnode_mdio.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * FWNODE helper for the MDIO (Ethernet PHY) API + */ + +#ifndef __LINUX_FWNODE_MDIO_H +#define __LINUX_FWNODE_MDIO_H + +#include <linux/phy.h> + +#if IS_ENABLED(CONFIG_FWNODE_MDIO) +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr); + +int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, u32 addr); + +#else /* CONFIG_FWNODE_MDIO */ +int fwnode_mdiobus_phy_device_register(struct mii_bus *mdio, + struct phy_device *phy, + struct fwnode_handle *child, u32 addr) +{ + return -EINVAL; +} + +static inline int fwnode_mdiobus_register_phy(struct mii_bus *bus, + struct fwnode_handle *child, + u32 addr) +{ + return -EINVAL; +} +#endif + +#endif /* __LINUX_FWNODE_MDIO_H */ diff --git a/include/linux/phy.h b/include/linux/phy.h index ed332ac92e25..b60694734b07 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1377,10 +1377,42 @@ struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) +int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id); +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode); +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode); +struct phy_device *device_phy_find_device(struct device *dev); +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode); struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else +static inline int fwnode_get_phy_id(struct fwnode_handle *fwnode, u32 *phy_id) +{ + return 0; +} +static inline +struct mdio_device *fwnode_mdio_find_device(struct fwnode_handle *fwnode) +{ + return 0; +} + +static inline +struct phy_device *fwnode_phy_find_device(struct fwnode_handle *phy_fwnode) +{ + return NULL; +} + +static inline struct phy_device *device_phy_find_device(struct device *dev) +{ + return NULL; +} + +static inline +struct fwnode_handle *fwnode_get_phy_node(struct fwnode_handle *fwnode) +{ + return NULL; +} + static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index fd2acfd9b597..afb3ded0b691 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -441,6 +441,9 @@ void phylink_destroy(struct phylink *); int phylink_connect_phy(struct phylink *, struct phy_device *); int phylink_of_phy_connect(struct phylink *, struct device_node *, u32 flags); +int phylink_fwnode_phy_connect(struct phylink *pl, + struct fwnode_handle *fwnode, + u32 flags); void phylink_disconnect_phy(struct phylink *); void phylink_mac_change(struct phylink *, bool up); diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index dc636b727179..35d7eedb5e8e 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -36,6 +36,7 @@ struct virtio_vsock_sock { u32 rx_bytes; u32 buf_alloc; struct list_head rx_queue; + u32 msg_count; }; struct virtio_vsock_pkt { @@ -80,8 +81,17 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, size_t len, int flags); +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags); s64 virtio_transport_stream_has_data(struct vsock_sock *vsk); s64 virtio_transport_stream_has_space(struct vsock_sock *vsk); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk); int virtio_transport_do_socket_init(struct vsock_sock *vsk, struct vsock_sock *psk); diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h index b1c717286993..ab207677e0a8 100644 --- a/include/net/af_vsock.h +++ b/include/net/af_vsock.h @@ -135,6 +135,14 @@ struct vsock_transport { bool (*stream_is_active)(struct vsock_sock *); bool (*stream_allow)(u32 cid, u32 port); + /* SEQ_PACKET. */ + ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg, + int flags); + int (*seqpacket_enqueue)(struct vsock_sock *vsk, struct msghdr *msg, + size_t len); + bool (*seqpacket_allow)(u32 remote_cid); + u32 (*seqpacket_has_data)(struct vsock_sock *vsk); + /* Notification. */ int (*notify_poll_in)(struct vsock_sock *, size_t, bool *); int (*notify_poll_out)(struct vsock_sock *, size_t, bool *); diff --git a/include/net/dsa.h b/include/net/dsa.h index e1a2610a0e06..289d68e82da0 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -50,6 +50,7 @@ struct phylink_link_state; #define DSA_TAG_PROTO_OCELOT_8021Q_VALUE 20 #define DSA_TAG_PROTO_SEVILLE_VALUE 21 #define DSA_TAG_PROTO_BRCM_LEGACY_VALUE 22 +#define DSA_TAG_PROTO_SJA1110_VALUE 23 enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = DSA_TAG_PROTO_NONE_VALUE, @@ -75,6 +76,7 @@ enum dsa_tag_protocol { DSA_TAG_PROTO_XRS700X = DSA_TAG_PROTO_XRS700X_VALUE, DSA_TAG_PROTO_OCELOT_8021Q = DSA_TAG_PROTO_OCELOT_8021Q_VALUE, DSA_TAG_PROTO_SEVILLE = DSA_TAG_PROTO_SEVILLE_VALUE, + DSA_TAG_PROTO_SJA1110 = DSA_TAG_PROTO_SJA1110_VALUE, }; struct packet_type; @@ -91,7 +93,8 @@ struct dsa_device_ops { * as regular on the master net device. */ bool (*filter)(const struct sk_buff *skb, struct net_device *dev); - unsigned int overhead; + unsigned int needed_headroom; + unsigned int needed_tailroom; const char *name; enum dsa_tag_protocol proto; /* Some tagging protocols either mangle or shift the destination MAC @@ -100,7 +103,6 @@ struct dsa_device_ops { * its RX filter. */ bool promisc_on_master; - bool tail_tag; }; /* This structure defines the control interfaces that are overlayed by the @@ -926,7 +928,7 @@ static inline void dsa_tag_generic_flow_dissect(const struct sk_buff *skb, { #if IS_ENABLED(CONFIG_NET_DSA) const struct dsa_device_ops *ops = skb->dev->dsa_ptr->tag_ops; - int tag_len = ops->overhead; + int tag_len = ops->needed_headroom; *offset = tag_len; *proto = ((__be16 *)skb->data)[(tag_len / 2) - 1]; diff --git a/include/trace/events/vsock_virtio_transport_common.h b/include/trace/events/vsock_virtio_transport_common.h index 6782213778be..d0b3f0ea9ba1 100644 --- a/include/trace/events/vsock_virtio_transport_common.h +++ b/include/trace/events/vsock_virtio_transport_common.h @@ -9,9 +9,12 @@ #include <linux/tracepoint.h> TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_STREAM); +TRACE_DEFINE_ENUM(VIRTIO_VSOCK_TYPE_SEQPACKET); #define show_type(val) \ - __print_symbolic(val, { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }) + __print_symbolic(val, \ + { VIRTIO_VSOCK_TYPE_STREAM, "STREAM" }, \ + { VIRTIO_VSOCK_TYPE_SEQPACKET, "SEQPACKET" }) TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_INVALID); TRACE_DEFINE_ENUM(VIRTIO_VSOCK_OP_REQUEST); diff --git a/include/uapi/linux/virtio_vsock.h b/include/uapi/linux/virtio_vsock.h index 1d57ed3d84d2..3dd3555b2740 100644 --- a/include/uapi/linux/virtio_vsock.h +++ b/include/uapi/linux/virtio_vsock.h @@ -38,6 +38,9 @@ #include <linux/virtio_ids.h> #include <linux/virtio_config.h> +/* The feature bitmap for virtio vsock */ +#define VIRTIO_VSOCK_F_SEQPACKET 1 /* SOCK_SEQPACKET supported */ + struct virtio_vsock_config { __le64 guest_cid; } __attribute__((packed)); @@ -65,6 +68,7 @@ struct virtio_vsock_hdr { enum virtio_vsock_type { VIRTIO_VSOCK_TYPE_STREAM = 1, + VIRTIO_VSOCK_TYPE_SEQPACKET = 2, }; enum virtio_vsock_op { @@ -91,4 +95,9 @@ enum virtio_vsock_shutdown { VIRTIO_VSOCK_SHUTDOWN_SEND = 2, }; +/* VIRTIO_VSOCK_OP_RW flags values */ +enum virtio_vsock_rw { + VIRTIO_VSOCK_SEQ_EOR = 1, +}; + #endif /* _UAPI_LINUX_VIRTIO_VSOCK_H */ diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 3ed7c98a98e1..c04455981c1e 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -944,7 +944,7 @@ bool __skb_flow_dissect(const struct net *net, ops = skb->dev->dsa_ptr->tag_ops; /* Tail taggers don't break flow dissection */ - if (!ops->tail_tag) { + if (!ops->needed_headroom) { if (ops->flow_dissect) ops->flow_dissect(skb, &proto, &offset); else diff --git a/net/devres.c b/net/devres.c index 1f9be2133787..5ccf6ca311dc 100644 --- a/net/devres.c +++ b/net/devres.c @@ -60,7 +60,7 @@ static int netdev_devres_match(struct device *dev, void *this, void *match_data) * @ndev: device to register * * This is a devres variant of register_netdev() for which the unregister - * function will be call automatically when the managing device is + * function will be called automatically when the managing device is * detached. Note: the net_device used must also be resource managed by * the same struct device. */ diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 92282de54230..b8b17474b72b 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -154,6 +154,11 @@ const struct dsa_device_ops *dsa_find_tagger_by_name(const char *buf); bool dsa_schedule_work(struct work_struct *work); const char *dsa_tag_protocol_to_str(const struct dsa_device_ops *ops); +static inline int dsa_tag_protocol_overhead(const struct dsa_device_ops *ops) +{ + return ops->needed_headroom + ops->needed_tailroom; +} + /* master.c */ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp); void dsa_master_teardown(struct net_device *dev); diff --git a/net/dsa/master.c b/net/dsa/master.c index 63adbc21a735..3fc90e36772d 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -346,10 +346,12 @@ static struct lock_class_key dsa_master_addr_list_lock_key; int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) { - int mtu = ETH_DATA_LEN + cpu_dp->tag_ops->overhead; + const struct dsa_device_ops *tag_ops = cpu_dp->tag_ops; struct dsa_switch *ds = cpu_dp->ds; struct device_link *consumer_link; - int ret; + int mtu, ret; + + mtu = ETH_DATA_LEN + dsa_tag_protocol_overhead(tag_ops); /* The DSA master must use SET_NETDEV_DEV for this to work. */ consumer_link = device_link_add(ds->dev, dev->dev.parent, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index d4756b920108..3ca509eb284d 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -1569,7 +1569,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) mtu_limit = min_t(int, master->max_mtu, dev->max_mtu); old_master_mtu = master->mtu; - new_master_mtu = largest_mtu + cpu_dp->tag_ops->overhead; + new_master_mtu = largest_mtu + dsa_tag_protocol_overhead(cpu_dp->tag_ops); if (new_master_mtu > mtu_limit) return -ERANGE; @@ -1605,7 +1605,7 @@ int dsa_slave_change_mtu(struct net_device *dev, int new_mtu) out_port_failed: if (new_master_mtu != old_master_mtu) dsa_port_mtu_change(cpu_dp, old_master_mtu - - cpu_dp->tag_ops->overhead, + dsa_tag_protocol_overhead(cpu_dp->tag_ops), true); out_cpu_failed: if (new_master_mtu != old_master_mtu) @@ -1824,10 +1824,8 @@ void dsa_slave_setup_tagger(struct net_device *slave) const struct dsa_port *cpu_dp = dp->cpu_dp; struct net_device *master = cpu_dp->master; - if (cpu_dp->tag_ops->tail_tag) - slave->needed_tailroom = cpu_dp->tag_ops->overhead; - else - slave->needed_headroom = cpu_dp->tag_ops->overhead; + slave->needed_headroom = cpu_dp->tag_ops->needed_headroom; + slave->needed_tailroom = cpu_dp->tag_ops->needed_tailroom; /* Try to save one extra realloc later in the TX path (in the master) * by also inheriting the master's needed headroom and tailroom. * The 8021q driver also does this. diff --git a/net/dsa/tag_8021q.c b/net/dsa/tag_8021q.c index 122ad5833fb1..4aa29f90ecea 100644 --- a/net/dsa/tag_8021q.c +++ b/net/dsa/tag_8021q.c @@ -471,4 +471,27 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, } EXPORT_SYMBOL_GPL(dsa_8021q_xmit); +void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id, + int *subvlan) +{ + u16 vid, tci; + + skb_push_rcsum(skb, ETH_HLEN); + if (skb_vlan_tag_present(skb)) { + tci = skb_vlan_tag_get(skb); + __vlan_hwaccel_clear_tag(skb); + } else { + __skb_vlan_pop(skb, &tci); + } + skb_pull_rcsum(skb, ETH_HLEN); + + vid = tci & VLAN_VID_MASK; + + *source_port = dsa_8021q_rx_source_port(vid); + *switch_id = dsa_8021q_rx_switch_id(vid); + *subvlan = dsa_8021q_rx_subvlan(vid); + skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; +} +EXPORT_SYMBOL_GPL(dsa_8021q_rcv); + MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_ar9331.c b/net/dsa/tag_ar9331.c index 002cf7f952e2..0efae1a372b3 100644 --- a/net/dsa/tag_ar9331.c +++ b/net/dsa/tag_ar9331.c @@ -85,7 +85,7 @@ static const struct dsa_device_ops ar9331_netdev_ops = { .proto = DSA_TAG_PROTO_AR9331, .xmit = ar9331_tag_xmit, .rcv = ar9331_tag_rcv, - .overhead = AR9331_HDR_LEN, + .needed_headroom = AR9331_HDR_LEN, }; MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 40e9f3098c8d..0750af951fc9 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -205,7 +205,7 @@ static const struct dsa_device_ops brcm_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM, .xmit = brcm_tag_xmit, .rcv = brcm_tag_rcv, - .overhead = BRCM_TAG_LEN, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_netdev_ops); @@ -286,7 +286,7 @@ static const struct dsa_device_ops brcm_legacy_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM_LEGACY, .xmit = brcm_leg_tag_xmit, .rcv = brcm_leg_tag_rcv, - .overhead = BRCM_LEG_TAG_LEN, + .needed_headroom = BRCM_LEG_TAG_LEN, }; DSA_TAG_DRIVER(brcm_legacy_netdev_ops); @@ -314,7 +314,7 @@ static const struct dsa_device_ops brcm_prepend_netdev_ops = { .proto = DSA_TAG_PROTO_BRCM_PREPEND, .xmit = brcm_tag_xmit_prepend, .rcv = brcm_tag_rcv_prepend, - .overhead = BRCM_TAG_LEN, + .needed_headroom = BRCM_TAG_LEN, }; DSA_TAG_DRIVER(brcm_prepend_netdev_ops); diff --git a/net/dsa/tag_dsa.c b/net/dsa/tag_dsa.c index 7e7b7decdf39..a822355afc90 100644 --- a/net/dsa/tag_dsa.c +++ b/net/dsa/tag_dsa.c @@ -303,7 +303,7 @@ static const struct dsa_device_ops dsa_netdev_ops = { .proto = DSA_TAG_PROTO_DSA, .xmit = dsa_xmit, .rcv = dsa_rcv, - .overhead = DSA_HLEN, + .needed_headroom = DSA_HLEN, }; DSA_TAG_DRIVER(dsa_netdev_ops); @@ -346,7 +346,7 @@ static const struct dsa_device_ops edsa_netdev_ops = { .proto = DSA_TAG_PROTO_EDSA, .xmit = edsa_xmit, .rcv = edsa_rcv, - .overhead = EDSA_HLEN, + .needed_headroom = EDSA_HLEN, }; DSA_TAG_DRIVER(edsa_netdev_ops); diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index 2f5bd5e338ab..5985dab06ab8 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -103,7 +103,7 @@ static const struct dsa_device_ops gswip_netdev_ops = { .proto = DSA_TAG_PROTO_GSWIP, .xmit = gswip_tag_xmit, .rcv = gswip_tag_rcv, - .overhead = GSWIP_RX_HEADER_LEN, + .needed_headroom = GSWIP_RX_HEADER_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_hellcreek.c b/net/dsa/tag_hellcreek.c index a09805c8e1ab..424130f85f59 100644 --- a/net/dsa/tag_hellcreek.c +++ b/net/dsa/tag_hellcreek.c @@ -54,8 +54,7 @@ static const struct dsa_device_ops hellcreek_netdev_ops = { .proto = DSA_TAG_PROTO_HELLCREEK, .xmit = hellcreek_xmit, .rcv = hellcreek_rcv, - .overhead = HELLCREEK_TAG_LEN, - .tail_tag = true, + .needed_tailroom = HELLCREEK_TAG_LEN, }; MODULE_LICENSE("Dual MIT/GPL"); diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index 4820dbcedfa2..53565f48934c 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -77,8 +77,7 @@ static const struct dsa_device_ops ksz8795_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ8795, .xmit = ksz8795_xmit, .rcv = ksz8795_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz8795_netdev_ops); @@ -149,8 +148,7 @@ static const struct dsa_device_ops ksz9477_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9477, .xmit = ksz9477_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ9477_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ9477_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz9477_netdev_ops); @@ -183,8 +181,7 @@ static const struct dsa_device_ops ksz9893_netdev_ops = { .proto = DSA_TAG_PROTO_KSZ9893, .xmit = ksz9893_xmit, .rcv = ksz9477_rcv, - .overhead = KSZ_INGRESS_TAG_LEN, - .tail_tag = true, + .needed_tailroom = KSZ_INGRESS_TAG_LEN, }; DSA_TAG_DRIVER(ksz9893_netdev_ops); diff --git a/net/dsa/tag_lan9303.c b/net/dsa/tag_lan9303.c index aa1318dccaf0..26207ef39ebc 100644 --- a/net/dsa/tag_lan9303.c +++ b/net/dsa/tag_lan9303.c @@ -125,7 +125,7 @@ static const struct dsa_device_ops lan9303_netdev_ops = { .proto = DSA_TAG_PROTO_LAN9303, .xmit = lan9303_xmit, .rcv = lan9303_rcv, - .overhead = LAN9303_TAG_LEN, + .needed_headroom = LAN9303_TAG_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index f9b2966d1936..cc3ba864ad5b 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -102,7 +102,7 @@ static const struct dsa_device_ops mtk_netdev_ops = { .proto = DSA_TAG_PROTO_MTK, .xmit = mtk_tag_xmit, .rcv = mtk_tag_rcv, - .overhead = MTK_HDR_LEN, + .needed_headroom = MTK_HDR_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index 91f0fd1242cd..190f4bfd3bef 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -143,7 +143,7 @@ static const struct dsa_device_ops ocelot_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TOTAL_TAG_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, .promisc_on_master = true, }; @@ -155,7 +155,7 @@ static const struct dsa_device_ops seville_netdev_ops = { .proto = DSA_TAG_PROTO_SEVILLE, .xmit = seville_xmit, .rcv = ocelot_rcv, - .overhead = OCELOT_TOTAL_TAG_LEN, + .needed_headroom = OCELOT_TOTAL_TAG_LEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 62a93303bd63..85ac85c3af8c 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -41,29 +41,15 @@ static struct sk_buff *ocelot_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { - int src_port, switch_id, qos_class; - u16 vid, tci; + int src_port, switch_id, subvlan; - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - - vid = tci & VLAN_VID_MASK; - src_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - qos_class = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; + dsa_8021q_rcv(skb, &src_port, &switch_id, &subvlan); skb->dev = dsa_master_find_slave(netdev, switch_id, src_port); if (!skb->dev) return NULL; skb->offload_fwd_mark = 1; - skb->priority = qos_class; return skb; } @@ -73,7 +59,7 @@ static const struct dsa_device_ops ocelot_8021q_netdev_ops = { .proto = DSA_TAG_PROTO_OCELOT_8021Q, .xmit = ocelot_xmit, .rcv = ocelot_rcv, - .overhead = VLAN_HLEN, + .needed_headroom = VLAN_HLEN, .promisc_on_master = true, }; diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index 88181b52f480..693bda013065 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -91,7 +91,7 @@ static const struct dsa_device_ops qca_netdev_ops = { .proto = DSA_TAG_PROTO_QCA, .xmit = qca_tag_xmit, .rcv = qca_tag_rcv, - .overhead = QCA_HDR_LEN, + .needed_headroom = QCA_HDR_LEN, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_rtl4_a.c b/net/dsa/tag_rtl4_a.c index cf8ac316f4c7..57c46b4ab2b3 100644 --- a/net/dsa/tag_rtl4_a.c +++ b/net/dsa/tag_rtl4_a.c @@ -124,7 +124,7 @@ static const struct dsa_device_ops rtl4a_netdev_ops = { .proto = DSA_TAG_PROTO_RTL4_A, .xmit = rtl4a_tag_xmit, .rcv = rtl4a_tag_rcv, - .overhead = RTL4_A_HDR_LEN, + .needed_headroom = RTL4_A_HDR_LEN, }; module_dsa_tag_driver(rtl4a_netdev_ops); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index 50496013cdb7..9c2df9ece01b 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -7,6 +7,52 @@ #include <linux/packing.h> #include "dsa_priv.h" +/* Is this a TX or an RX header? */ +#define SJA1110_HEADER_HOST_TO_SWITCH BIT(15) + +/* RX header */ +#define SJA1110_RX_HEADER_IS_METADATA BIT(14) +#define SJA1110_RX_HEADER_HOST_ONLY BIT(13) +#define SJA1110_RX_HEADER_HAS_TRAILER BIT(12) + +/* Trap-to-host format (no trailer present) */ +#define SJA1110_RX_HEADER_SRC_PORT(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_HEADER_SWITCH_ID(x) ((x) & GENMASK(3, 0)) + +/* Timestamp format (trailer present) */ +#define SJA1110_RX_HEADER_TRAILER_POS(x) ((x) & GENMASK(11, 0)) + +#define SJA1110_RX_TRAILER_SWITCH_ID(x) (((x) & GENMASK(7, 4)) >> 4) +#define SJA1110_RX_TRAILER_SRC_PORT(x) ((x) & GENMASK(3, 0)) + +/* Meta frame format (for 2-step TX timestamps) */ +#define SJA1110_RX_HEADER_N_TS(x) (((x) & GENMASK(8, 4)) >> 4) + +/* TX header */ +#define SJA1110_TX_HEADER_UPDATE_TC BIT(14) +#define SJA1110_TX_HEADER_TAKE_TS BIT(13) +#define SJA1110_TX_HEADER_TAKE_TS_CASC BIT(12) +#define SJA1110_TX_HEADER_HAS_TRAILER BIT(11) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is false */ +#define SJA1110_TX_HEADER_PRIO(x) (((x) << 7) & GENMASK(10, 7)) +#define SJA1110_TX_HEADER_TSTAMP_ID(x) ((x) & GENMASK(7, 0)) + +/* Only valid if SJA1110_TX_HEADER_HAS_TRAILER is true */ +#define SJA1110_TX_HEADER_TRAILER_POS(x) ((x) & GENMASK(10, 0)) + +#define SJA1110_TX_TRAILER_TSTAMP_ID(x) (((x) << 24) & GENMASK(31, 24)) +#define SJA1110_TX_TRAILER_PRIO(x) (((x) << 21) & GENMASK(23, 21)) +#define SJA1110_TX_TRAILER_SWITCHID(x) (((x) << 12) & GENMASK(15, 12)) +#define SJA1110_TX_TRAILER_DESTPORTS(x) (((x) << 1) & GENMASK(11, 1)) + +#define SJA1110_META_TSTAMP_SIZE 10 + +#define SJA1110_HEADER_LEN 4 +#define SJA1110_RX_TRAILER_LEN 13 +#define SJA1110_TX_TRAILER_LEN 4 +#define SJA1110_MAX_PADDING_LEN 15 + /* Similar to is_link_local_ether_addr(hdr->h_dest) but also covers PTP */ static inline bool sja1105_is_link_local(const struct sk_buff *skb) { @@ -140,6 +186,57 @@ static struct sk_buff *sja1105_xmit(struct sk_buff *skb, ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); } +static struct sk_buff *sja1110_xmit(struct sk_buff *skb, + struct net_device *netdev) +{ + struct sk_buff *clone = SJA1105_SKB_CB(skb)->clone; + struct dsa_port *dp = dsa_slave_to_port(netdev); + 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 ethhdr *eth_hdr; + __be32 *tx_trailer; + __be16 *tx_header; + int trailer_pos; + + /* Transmitting control packets is done using in-band control + * extensions, while data packets are transmitted using + * tag_8021q TX VLANs. + */ + if (likely(!sja1105_is_link_local(skb))) + return dsa_8021q_xmit(skb, netdev, sja1105_xmit_tpid(dp->priv), + ((pcp << VLAN_PRIO_SHIFT) | tx_vid)); + + skb_push(skb, SJA1110_HEADER_LEN); + + /* Move Ethernet header to the left, making space for DSA tag */ + memmove(skb->data, skb->data + SJA1110_HEADER_LEN, 2 * ETH_ALEN); + + trailer_pos = skb->len; + + /* On TX, skb->data points to skb_mac_header(skb) */ + eth_hdr = (struct ethhdr *)skb->data; + tx_header = (__be16 *)(eth_hdr + 1); + tx_trailer = skb_put(skb, SJA1110_TX_TRAILER_LEN); + + eth_hdr->h_proto = htons(ETH_P_SJA1110); + + *tx_header = htons(SJA1110_HEADER_HOST_TO_SWITCH | + SJA1110_TX_HEADER_HAS_TRAILER | + SJA1110_TX_HEADER_TRAILER_POS(trailer_pos)); + *tx_trailer = cpu_to_be32(SJA1110_TX_TRAILER_PRIO(pcp) | + SJA1110_TX_TRAILER_SWITCHID(dp->ds->index) | + SJA1110_TX_TRAILER_DESTPORTS(BIT(dp->index))); + if (clone) { + u8 ts_id = SJA1105_SKB_CB(clone)->ts_id; + + *tx_header |= htons(SJA1110_TX_HEADER_TAKE_TS); + *tx_trailer |= cpu_to_be32(SJA1110_TX_TRAILER_TSTAMP_ID(ts_id)); + } + + return skb; +} + static void sja1105_transfer_meta(struct sk_buff *skb, const struct sja1105_meta *meta) { @@ -147,7 +244,7 @@ static void sja1105_transfer_meta(struct sk_buff *skb, hdr->h_dest[3] = meta->dmac_byte_3; hdr->h_dest[4] = meta->dmac_byte_4; - SJA1105_SKB_CB(skb)->meta_tstamp = meta->tstamp; + SJA1105_SKB_CB(skb)->tstamp = meta->tstamp; } /* This is a simple state machine which follows the hardware mechanism of @@ -275,46 +372,38 @@ static void sja1105_decode_subvlan(struct sk_buff *skb, u16 subvlan) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci); } +static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) +{ + u16 tpid = ntohs(eth_hdr(skb)->h_proto); + + return tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || + skb_vlan_tag_present(skb); +} + +static bool sja1110_skb_has_inband_control_extension(const struct sk_buff *skb) +{ + return ntohs(eth_hdr(skb)->h_proto) == ETH_P_SJA1110; +} + static struct sk_buff *sja1105_rcv(struct sk_buff *skb, struct net_device *netdev, struct packet_type *pt) { + int source_port, switch_id, subvlan = 0; struct sja1105_meta meta = {0}; - int source_port, switch_id; struct ethhdr *hdr; - u16 tpid, vid, tci; bool is_link_local; - u16 subvlan = 0; - bool is_tagged; bool is_meta; hdr = eth_hdr(skb); - tpid = ntohs(hdr->h_proto); - is_tagged = (tpid == ETH_P_SJA1105 || tpid == ETH_P_8021Q || - skb_vlan_tag_present(skb)); is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); skb->offload_fwd_mark = 1; - if (is_tagged) { + if (sja1105_skb_has_tag_8021q(skb)) { /* Normal traffic path. */ - skb_push_rcsum(skb, ETH_HLEN); - if (skb_vlan_tag_present(skb)) { - tci = skb_vlan_tag_get(skb); - __vlan_hwaccel_clear_tag(skb); - } else { - __skb_vlan_pop(skb, &tci); - } - skb_pull_rcsum(skb, ETH_HLEN); - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - - vid = tci & VLAN_VID_MASK; - source_port = dsa_8021q_rx_source_port(vid); - switch_id = dsa_8021q_rx_switch_id(vid); - skb->priority = (tci & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT; - subvlan = dsa_8021q_rx_subvlan(vid); + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); } else if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of @@ -346,6 +435,138 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_meta); } +static struct sk_buff *sja1110_rcv_meta(struct sk_buff *skb, u16 rx_header) +{ + int switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + int n_ts = SJA1110_RX_HEADER_N_TS(rx_header); + struct net_device *master = skb->dev; + struct dsa_port *cpu_dp; + u8 *buf = skb->data + 2; + struct dsa_switch *ds; + int i; + + cpu_dp = master->dsa_ptr; + ds = dsa_switch_find(cpu_dp->dst->index, switch_id); + if (!ds) { + net_err_ratelimited("%s: cannot find switch id %d\n", + master->name, switch_id); + return NULL; + } + + for (i = 0; i <= n_ts; i++) { + u8 ts_id, source_port, dir; + u64 tstamp; + + ts_id = buf[0]; + source_port = (buf[1] & GENMASK(7, 4)) >> 4; + dir = (buf[1] & BIT(3)) >> 3; + tstamp = be64_to_cpu(*(__be64 *)(buf + 2)); + + sja1110_process_meta_tstamp(ds, source_port, ts_id, dir, + tstamp); + + buf += SJA1110_META_TSTAMP_SIZE; + } + + /* Discard the meta frame, we've consumed the timestamps it contained */ + return NULL; +} + +static struct sk_buff *sja1110_rcv_inband_control_extension(struct sk_buff *skb, + int *source_port, + int *switch_id) +{ + u16 rx_header; + + if (unlikely(!pskb_may_pull(skb, SJA1110_HEADER_LEN))) + return NULL; + + /* skb->data points to skb_mac_header(skb) + ETH_HLEN, which is exactly + * what we need because the caller has checked the EtherType (which is + * located 2 bytes back) and we just need a pointer to the header that + * comes afterwards. + */ + rx_header = ntohs(*(__be16 *)skb->data); + + if (rx_header & SJA1110_RX_HEADER_IS_METADATA) + return sja1110_rcv_meta(skb, rx_header); + + /* Timestamp frame, we have a trailer */ + if (rx_header & SJA1110_RX_HEADER_HAS_TRAILER) { + int start_of_padding = SJA1110_RX_HEADER_TRAILER_POS(rx_header); + u8 *rx_trailer = skb_tail_pointer(skb) - SJA1110_RX_TRAILER_LEN; + u64 *tstamp = &SJA1105_SKB_CB(skb)->tstamp; + u8 last_byte = rx_trailer[12]; + + /* The timestamp is unaligned, so we need to use packing() + * to get it + */ + packing(rx_trailer, tstamp, 63, 0, 8, UNPACK, 0); + + *source_port = SJA1110_RX_TRAILER_SRC_PORT(last_byte); + *switch_id = SJA1110_RX_TRAILER_SWITCH_ID(last_byte); + + /* skb->len counts from skb->data, while start_of_padding + * counts from the destination MAC address. Right now skb->data + * is still as set by the DSA master, so to trim away the + * padding and trailer we need to account for the fact that + * skb->data points to skb_mac_header(skb) + ETH_HLEN. + */ + pskb_trim_rcsum(skb, start_of_padding - ETH_HLEN); + /* Trap-to-host frame, no timestamp trailer */ + } else { + *source_port = SJA1110_RX_HEADER_SRC_PORT(rx_header); + *switch_id = SJA1110_RX_HEADER_SWITCH_ID(rx_header); + } + + /* Advance skb->data past the DSA header */ + skb_pull_rcsum(skb, SJA1110_HEADER_LEN); + + /* Remove the DSA header */ + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - SJA1110_HEADER_LEN, + 2 * ETH_ALEN); + + /* With skb->data in its final place, update the MAC header + * so that eth_hdr() continues to works properly. + */ + skb_set_mac_header(skb, -ETH_HLEN); + + return skb; +} + +static struct sk_buff *sja1110_rcv(struct sk_buff *skb, + struct net_device *netdev, + struct packet_type *pt) +{ + int source_port = -1, switch_id = -1, subvlan = 0; + + skb->offload_fwd_mark = 1; + + if (sja1110_skb_has_inband_control_extension(skb)) { + skb = sja1110_rcv_inband_control_extension(skb, &source_port, + &switch_id); + if (!skb) + return NULL; + } + + /* Packets with in-band control extensions might still have RX VLANs */ + if (likely(sja1105_skb_has_tag_8021q(skb))) + dsa_8021q_rcv(skb, &source_port, &switch_id, &subvlan); + + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + if (!skb->dev) { + netdev_warn(netdev, + "Couldn't decode source port %d and switch id %d\n", + source_port, switch_id); + return NULL; + } + + if (subvlan) + sja1105_decode_subvlan(skb, subvlan); + + return skb; +} + static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, int *offset) { @@ -356,18 +577,53 @@ static void sja1105_flow_dissect(const struct sk_buff *skb, __be16 *proto, dsa_tag_generic_flow_dissect(skb, proto, offset); } +static void sja1110_flow_dissect(const struct sk_buff *skb, __be16 *proto, + int *offset) +{ + /* Management frames have 2 DSA tags on RX, so the needed_headroom we + * declared is fine for the generic dissector adjustment procedure. + */ + if (unlikely(sja1105_is_link_local(skb))) + return dsa_tag_generic_flow_dissect(skb, proto, offset); + + /* For the rest, there is a single DSA tag, the tag_8021q one */ + *offset = VLAN_HLEN; + *proto = ((__be16 *)skb->data)[(VLAN_HLEN / 2) - 1]; +} + static const struct dsa_device_ops sja1105_netdev_ops = { .name = "sja1105", .proto = DSA_TAG_PROTO_SJA1105, .xmit = sja1105_xmit, .rcv = sja1105_rcv, .filter = sja1105_filter, - .overhead = VLAN_HLEN, + .needed_headroom = VLAN_HLEN, .flow_dissect = sja1105_flow_dissect, .promisc_on_master = true, }; -MODULE_LICENSE("GPL v2"); +DSA_TAG_DRIVER(sja1105_netdev_ops); MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1105); -module_dsa_tag_driver(sja1105_netdev_ops); +static const struct dsa_device_ops sja1110_netdev_ops = { + .name = "sja1110", + .proto = DSA_TAG_PROTO_SJA1110, + .xmit = sja1110_xmit, + .rcv = sja1110_rcv, + .filter = sja1105_filter, + .flow_dissect = sja1110_flow_dissect, + .needed_headroom = SJA1110_HEADER_LEN + VLAN_HLEN, + .needed_tailroom = SJA1110_RX_TRAILER_LEN + SJA1110_MAX_PADDING_LEN, +}; + +DSA_TAG_DRIVER(sja1110_netdev_ops); +MODULE_ALIAS_DSA_TAG_DRIVER(DSA_TAG_PROTO_SJA1110); + +static struct dsa_tag_driver *sja1105_tag_driver_array[] = { + &DSA_TAG_DRIVER_NAME(sja1105_netdev_ops), + &DSA_TAG_DRIVER_NAME(sja1110_netdev_ops), +}; + +module_dsa_tag_drivers(sja1105_tag_driver_array); + +MODULE_LICENSE("GPL v2"); diff --git a/net/dsa/tag_trailer.c b/net/dsa/tag_trailer.c index 5b97ede56a0f..ba73804340a5 100644 --- a/net/dsa/tag_trailer.c +++ b/net/dsa/tag_trailer.c @@ -55,8 +55,7 @@ static const struct dsa_device_ops trailer_netdev_ops = { .proto = DSA_TAG_PROTO_TRAILER, .xmit = trailer_xmit, .rcv = trailer_rcv, - .overhead = 4, - .tail_tag = true, + .needed_tailroom = 4, }; MODULE_LICENSE("GPL"); diff --git a/net/dsa/tag_xrs700x.c b/net/dsa/tag_xrs700x.c index 858cdf9d2913..a31ff7fcb45f 100644 --- a/net/dsa/tag_xrs700x.c +++ b/net/dsa/tag_xrs700x.c @@ -56,8 +56,7 @@ static const struct dsa_device_ops xrs700x_netdev_ops = { .proto = DSA_TAG_PROTO_XRS700X, .xmit = xrs700x_xmit, .rcv = xrs700x_rcv, - .overhead = 1, - .tail_tag = true, + .needed_tailroom = 1, }; MODULE_LICENSE("GPL"); diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 92a72f0e0d94..67954afef4e1 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -415,8 +415,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk) /* Assign a transport to a socket and call the .init transport callback. * - * Note: for stream socket this must be called when vsk->remote_addr is set - * (e.g. during the connect() or when a connection request on a listener + * Note: for connection oriented socket this must be called when vsk->remote_addr + * is set (e.g. during the connect() or when a connection request on a listener * socket is received). * The vsk->remote_addr is used to decide which transport to use: * - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if @@ -452,6 +452,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) new_transport = transport_dgram; break; case SOCK_STREAM: + case SOCK_SEQPACKET: if (vsock_use_local_transport(remote_cid)) new_transport = transport_local; else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g || @@ -469,10 +470,10 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) return 0; /* transport->release() must be called with sock lock acquired. - * This path can only be taken during vsock_stream_connect(), - * where we have already held the sock lock. - * In the other cases, this function is called on a new socket - * which is not assigned to any transport. + * This path can only be taken during vsock_connect(), where we + * have already held the sock lock. In the other cases, this + * function is called on a new socket which is not assigned to + * any transport. */ vsk->transport->release(vsk); vsock_deassign_transport(vsk); @@ -484,6 +485,14 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk) if (!new_transport || !try_module_get(new_transport->module)) return -ENODEV; + if (sk->sk_type == SOCK_SEQPACKET) { + if (!new_transport->seqpacket_allow || + !new_transport->seqpacket_allow(remote_cid)) { + module_put(new_transport->module); + return -ESOCKTNOSUPPORT; + } + } + ret = new_transport->init(vsk, psk); if (ret) { module_put(new_transport->module); @@ -604,8 +613,8 @@ out: /**** SOCKET OPERATIONS ****/ -static int __vsock_bind_stream(struct vsock_sock *vsk, - struct sockaddr_vm *addr) +static int __vsock_bind_connectible(struct vsock_sock *vsk, + struct sockaddr_vm *addr) { static u32 port; struct sockaddr_vm new_addr; @@ -649,9 +658,10 @@ static int __vsock_bind_stream(struct vsock_sock *vsk, vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port); - /* Remove stream sockets from the unbound list and add them to the hash - * table for easy lookup by its address. The unbound list is simply an - * extra entry at the end of the hash table, a trick used by AF_UNIX. + /* Remove connection oriented sockets from the unbound list and add them + * to the hash table for easy lookup by its address. The unbound list + * is simply an extra entry at the end of the hash table, a trick used + * by AF_UNIX. */ __vsock_remove_bound(vsk); __vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk); @@ -684,8 +694,9 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr) switch (sk->sk_socket->type) { case SOCK_STREAM: + case SOCK_SEQPACKET: spin_lock_bh(&vsock_table_lock); - retval = __vsock_bind_stream(vsk, addr); + retval = __vsock_bind_connectible(vsk, addr); spin_unlock_bh(&vsock_table_lock); break; @@ -768,6 +779,11 @@ static struct sock *__vsock_create(struct net *net, return sk; } +static bool sock_type_connectible(u16 type) +{ + return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET); +} + static void __vsock_release(struct sock *sk, int level) { if (sk) { @@ -786,7 +802,7 @@ static void __vsock_release(struct sock *sk, int level) if (vsk->transport) vsk->transport->release(vsk); - else if (sk->sk_type == SOCK_STREAM) + else if (sock_type_connectible(sk->sk_type)) vsock_remove_sock(vsk); sock_orphan(sk); @@ -844,6 +860,16 @@ s64 vsock_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(vsock_stream_has_data); +static s64 vsock_has_data(struct vsock_sock *vsk) +{ + struct sock *sk = sk_vsock(vsk); + + if (sk->sk_type == SOCK_SEQPACKET) + return vsk->transport->seqpacket_has_data(vsk); + else + return vsock_stream_has_data(vsk); +} + s64 vsock_stream_has_space(struct vsock_sock *vsk) { return vsk->transport->stream_has_space(vsk); @@ -937,10 +963,10 @@ static int vsock_shutdown(struct socket *sock, int mode) if ((mode & ~SHUTDOWN_MASK) || !mode) return -EINVAL; - /* If this is a STREAM socket and it is not connected then bail out - * immediately. If it is a DGRAM socket then we must first kick the - * socket so that it wakes up from any sleeping calls, for example - * recv(), and then afterwards return the error. + /* If this is a connection oriented socket and it is not connected then + * bail out immediately. If it is a DGRAM socket then we must first + * kick the socket so that it wakes up from any sleeping calls, for + * example recv(), and then afterwards return the error. */ sk = sock->sk; @@ -948,7 +974,7 @@ static int vsock_shutdown(struct socket *sock, int mode) lock_sock(sk); if (sock->state == SS_UNCONNECTED) { err = -ENOTCONN; - if (sk->sk_type == SOCK_STREAM) + if (sock_type_connectible(sk->sk_type)) goto out; } else { sock->state = SS_DISCONNECTING; @@ -961,7 +987,7 @@ static int vsock_shutdown(struct socket *sock, int mode) sk->sk_shutdown |= mode; sk->sk_state_change(sk); - if (sk->sk_type == SOCK_STREAM) { + if (sock_type_connectible(sk->sk_type)) { sock_reset_flag(sk, SOCK_DONE); vsock_send_shutdown(sk, mode); } @@ -1016,7 +1042,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, if (!(sk->sk_shutdown & SEND_SHUTDOWN)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; - } else if (sock->type == SOCK_STREAM) { + } else if (sock_type_connectible(sk->sk_type)) { const struct vsock_transport *transport; lock_sock(sk); @@ -1263,8 +1289,8 @@ static void vsock_connect_timeout(struct work_struct *work) sock_put(sk); } -static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr, - int addr_len, int flags) +static int vsock_connect(struct socket *sock, struct sockaddr *addr, + int addr_len, int flags) { int err; struct sock *sk; @@ -1414,7 +1440,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, lock_sock(listener); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sock->type)) { err = -EOPNOTSUPP; goto out; } @@ -1491,7 +1517,7 @@ static int vsock_listen(struct socket *sock, int backlog) lock_sock(sk); - if (sock->type != SOCK_STREAM) { + if (!sock_type_connectible(sk->sk_type)) { err = -EOPNOTSUPP; goto out; } @@ -1535,11 +1561,11 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk, vsk->buffer_size = val; } -static int vsock_stream_setsockopt(struct socket *sock, - int level, - int optname, - sockptr_t optval, - unsigned int optlen) +static int vsock_connectible_setsockopt(struct socket *sock, + int level, + int optname, + sockptr_t optval, + unsigned int optlen) { int err; struct sock *sk; @@ -1617,10 +1643,10 @@ exit: return err; } -static int vsock_stream_getsockopt(struct socket *sock, - int level, int optname, - char __user *optval, - int __user *optlen) +static int vsock_connectible_getsockopt(struct socket *sock, + int level, int optname, + char __user *optval, + int __user *optlen) { int err; int len; @@ -1688,8 +1714,8 @@ static int vsock_stream_getsockopt(struct socket *sock, return 0; } -static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, - size_t len) +static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg, + size_t len) { struct sock *sk; struct vsock_sock *vsk; @@ -1712,7 +1738,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, transport = vsk->transport; - /* Callers should not provide a destination with stream sockets. */ + /* Callers should not provide a destination with connection oriented + * sockets. + */ if (msg->msg_namelen) { err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP; goto out; @@ -1803,9 +1831,13 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, * responsibility to check how many bytes we were able to send. */ - written = transport->stream_enqueue( - vsk, msg, - len - total_written); + if (sk->sk_type == SOCK_SEQPACKET) { + written = transport->seqpacket_enqueue(vsk, + msg, len - total_written); + } else { + written = transport->stream_enqueue(vsk, + msg, len - total_written); + } if (written < 0) { err = -ENOMEM; goto out_err; @@ -1821,72 +1853,97 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg, } out_err: - if (total_written > 0) - err = total_written; + if (total_written > 0) { + /* Return number of written bytes only if: + * 1) SOCK_STREAM socket. + * 2) SOCK_SEQPACKET socket when whole buffer is sent. + */ + if (sk->sk_type == SOCK_STREAM || total_written == len) + err = total_written; + } out: release_sock(sk); return err; } - -static int -vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, - int flags) +static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait, + long timeout, + struct vsock_transport_recv_notify_data *recv_data, + size_t target) { - struct sock *sk; - struct vsock_sock *vsk; const struct vsock_transport *transport; + struct vsock_sock *vsk; + s64 data; int err; - size_t target; - ssize_t copied; - long timeout; - struct vsock_transport_recv_notify_data recv_data; - - DEFINE_WAIT(wait); - sk = sock->sk; vsk = vsock_sk(sk); err = 0; + transport = vsk->transport; - lock_sock(sk); + while ((data = vsock_has_data(vsk)) == 0) { + prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE); - transport = vsk->transport; + if (sk->sk_err != 0 || + (sk->sk_shutdown & RCV_SHUTDOWN) || + (vsk->peer_shutdown & SEND_SHUTDOWN)) { + break; + } - if (!transport || sk->sk_state != TCP_ESTABLISHED) { - /* Recvmsg is supposed to return 0 if a peer performs an - * orderly shutdown. Differentiate between that case and when a - * peer has not connected or a local shutdown occurred with the - * SOCK_DONE flag. - */ - if (sock_flag(sk, SOCK_DONE)) - err = 0; - else - err = -ENOTCONN; + /* Don't wait for non-blocking sockets. */ + if (timeout == 0) { + err = -EAGAIN; + break; + } - goto out; - } + if (recv_data) { + err = transport->notify_recv_pre_block(vsk, target, recv_data); + if (err < 0) + break; + } - if (flags & MSG_OOB) { - err = -EOPNOTSUPP; - goto out; - } + release_sock(sk); + timeout = schedule_timeout(timeout); + lock_sock(sk); - /* We don't check peer_shutdown flag here since peer may actually shut - * down, but there can be data in the queue that a local socket can - * receive. - */ - if (sk->sk_shutdown & RCV_SHUTDOWN) { - err = 0; - goto out; + if (signal_pending(current)) { + err = sock_intr_errno(timeout); + break; + } else if (timeout == 0) { + err = -EAGAIN; + break; + } } - /* It is valid on Linux to pass in a zero-length receive buffer. This - * is not an error. We may as well bail out now. + finish_wait(sk_sleep(sk), wait); + + if (err) + return err; + + /* Internal transport error when checking for available + * data. XXX This should be changed to a connection + * reset in a later change. */ - if (!len) { - err = 0; - goto out; - } + if (data < 0) + return -ENOMEM; + + return data; +} + +static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + struct vsock_transport_recv_notify_data recv_data; + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t copied; + size_t target; + long timeout; + int err; + + DEFINE_WAIT(wait); + + vsk = vsock_sk(sk); + transport = vsk->transport; /* We must not copy less than target bytes into the user's buffer * before returning successfully, so we wait for the consume queue to @@ -1908,94 +1965,157 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, while (1) { - s64 ready; + ssize_t read; - prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - ready = vsock_stream_has_data(vsk); + err = vsock_wait_data(sk, &wait, timeout, &recv_data, target); + if (err <= 0) + break; - if (ready == 0) { - if (sk->sk_err != 0 || - (sk->sk_shutdown & RCV_SHUTDOWN) || - (vsk->peer_shutdown & SEND_SHUTDOWN)) { - finish_wait(sk_sleep(sk), &wait); - break; - } - /* Don't wait for non-blocking sockets. */ - if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } + err = transport->notify_recv_pre_dequeue(vsk, target, + &recv_data); + if (err < 0) + break; - err = transport->notify_recv_pre_block( - vsk, target, &recv_data); - if (err < 0) { - finish_wait(sk_sleep(sk), &wait); - break; - } - release_sock(sk); - timeout = schedule_timeout(timeout); - lock_sock(sk); + read = transport->stream_dequeue(vsk, msg, len - copied, flags); + if (read < 0) { + err = -ENOMEM; + break; + } - if (signal_pending(current)) { - err = sock_intr_errno(timeout); - finish_wait(sk_sleep(sk), &wait); - break; - } else if (timeout == 0) { - err = -EAGAIN; - finish_wait(sk_sleep(sk), &wait); - break; - } - } else { - ssize_t read; + copied += read; - finish_wait(sk_sleep(sk), &wait); + err = transport->notify_recv_post_dequeue(vsk, target, read, + !(flags & MSG_PEEK), &recv_data); + if (err < 0) + goto out; - if (ready < 0) { - /* Invalid queue pair content. XXX This should - * be changed to a connection reset in a later - * change. - */ + if (read >= target || flags & MSG_PEEK) + break; - err = -ENOMEM; - goto out; - } + target -= read; + } - err = transport->notify_recv_pre_dequeue( - vsk, target, &recv_data); - if (err < 0) - break; + if (sk->sk_err) + err = -sk->sk_err; + else if (sk->sk_shutdown & RCV_SHUTDOWN) + err = 0; - read = transport->stream_dequeue( - vsk, msg, - len - copied, flags); - if (read < 0) { - err = -ENOMEM; - break; - } + if (copied > 0) + err = copied; + +out: + return err; +} - copied += read; +static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg, + size_t len, int flags) +{ + const struct vsock_transport *transport; + struct vsock_sock *vsk; + ssize_t record_len; + long timeout; + int err = 0; + DEFINE_WAIT(wait); - err = transport->notify_recv_post_dequeue( - vsk, target, read, - !(flags & MSG_PEEK), &recv_data); - if (err < 0) - goto out; + vsk = vsock_sk(sk); + transport = vsk->transport; - if (read >= target || flags & MSG_PEEK) - break; + timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); - target -= read; - } + err = vsock_wait_data(sk, &wait, timeout, NULL, 0); + if (err <= 0) + goto out; + + record_len = transport->seqpacket_dequeue(vsk, msg, flags); + + if (record_len < 0) { + err = -ENOMEM; + goto out; } - if (sk->sk_err) + if (sk->sk_err) { err = -sk->sk_err; - else if (sk->sk_shutdown & RCV_SHUTDOWN) + } else if (sk->sk_shutdown & RCV_SHUTDOWN) { err = 0; + } else { + /* User sets MSG_TRUNC, so return real length of + * packet. + */ + if (flags & MSG_TRUNC) + err = record_len; + else + err = len - msg_data_left(msg); - if (copied > 0) - err = copied; + /* Always set MSG_TRUNC if real length of packet is + * bigger than user's buffer. + */ + if (record_len > len) + msg->msg_flags |= MSG_TRUNC; + } + +out: + return err; +} + +static int +vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, + int flags) +{ + struct sock *sk; + struct vsock_sock *vsk; + const struct vsock_transport *transport; + int err; + + DEFINE_WAIT(wait); + + sk = sock->sk; + vsk = vsock_sk(sk); + err = 0; + + lock_sock(sk); + + transport = vsk->transport; + + if (!transport || sk->sk_state != TCP_ESTABLISHED) { + /* Recvmsg is supposed to return 0 if a peer performs an + * orderly shutdown. Differentiate between that case and when a + * peer has not connected or a local shutdown occurred with the + * SOCK_DONE flag. + */ + if (sock_flag(sk, SOCK_DONE)) + err = 0; + else + err = -ENOTCONN; + + goto out; + } + + if (flags & MSG_OOB) { + err = -EOPNOTSUPP; + goto out; + } + + /* We don't check peer_shutdown flag here since peer may actually shut + * down, but there can be data in the queue that a local socket can + * receive. + */ + if (sk->sk_shutdown & RCV_SHUTDOWN) { + err = 0; + goto out; + } + + /* It is valid on Linux to pass in a zero-length receive buffer. This + * is not an error. We may as well bail out now. + */ + if (!len) { + err = 0; + goto out; + } + + if (sk->sk_type == SOCK_STREAM) + err = __vsock_stream_recvmsg(sk, msg, len, flags); + else + err = __vsock_seqpacket_recvmsg(sk, msg, len, flags); out: release_sock(sk); @@ -2007,7 +2127,7 @@ static const struct proto_ops vsock_stream_ops = { .owner = THIS_MODULE, .release = vsock_release, .bind = vsock_bind, - .connect = vsock_stream_connect, + .connect = vsock_connect, .socketpair = sock_no_socketpair, .accept = vsock_accept, .getname = vsock_getname, @@ -2015,10 +2135,31 @@ static const struct proto_ops vsock_stream_ops = { .ioctl = sock_no_ioctl, .listen = vsock_listen, .shutdown = vsock_shutdown, - .setsockopt = vsock_stream_setsockopt, - .getsockopt = vsock_stream_getsockopt, - .sendmsg = vsock_stream_sendmsg, - .recvmsg = vsock_stream_recvmsg, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, + .mmap = sock_no_mmap, + .sendpage = sock_no_sendpage, +}; + +static const struct proto_ops vsock_seqpacket_ops = { + .family = PF_VSOCK, + .owner = THIS_MODULE, + .release = vsock_release, + .bind = vsock_bind, + .connect = vsock_connect, + .socketpair = sock_no_socketpair, + .accept = vsock_accept, + .getname = vsock_getname, + .poll = vsock_poll, + .ioctl = sock_no_ioctl, + .listen = vsock_listen, + .shutdown = vsock_shutdown, + .setsockopt = vsock_connectible_setsockopt, + .getsockopt = vsock_connectible_getsockopt, + .sendmsg = vsock_connectible_sendmsg, + .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, }; @@ -2043,6 +2184,9 @@ static int vsock_create(struct net *net, struct socket *sock, case SOCK_STREAM: sock->ops = &vsock_stream_ops; break; + case SOCK_SEQPACKET: + sock->ops = &vsock_seqpacket_ops; + break; default: return -ESOCKTNOSUPPORT; } diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c index 2700a63ab095..e73ce652bf3c 100644 --- a/net/vmw_vsock/virtio_transport.c +++ b/net/vmw_vsock/virtio_transport.c @@ -62,6 +62,7 @@ struct virtio_vsock { struct virtio_vsock_event event_list[8]; u32 guest_cid; + bool seqpacket_allow; }; static u32 virtio_transport_get_local_cid(void) @@ -443,6 +444,8 @@ static void virtio_vsock_rx_done(struct virtqueue *vq) queue_work(virtio_vsock_workqueue, &vsock->rx_work); } +static bool virtio_transport_seqpacket_allow(u32 remote_cid); + static struct virtio_transport virtio_transport = { .transport = { .module = THIS_MODULE, @@ -469,6 +472,11 @@ static struct virtio_transport virtio_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = virtio_transport_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -485,6 +493,19 @@ static struct virtio_transport virtio_transport = { .send_pkt = virtio_transport_send_pkt, }; +static bool virtio_transport_seqpacket_allow(u32 remote_cid) +{ + struct virtio_vsock *vsock; + bool seqpacket_allow; + + rcu_read_lock(); + vsock = rcu_dereference(the_virtio_vsock); + seqpacket_allow = vsock->seqpacket_allow; + rcu_read_unlock(); + + return seqpacket_allow; +} + static void virtio_transport_rx_work(struct work_struct *work) { struct virtio_vsock *vsock = @@ -608,10 +629,14 @@ static int virtio_vsock_probe(struct virtio_device *vdev) vsock->event_run = true; mutex_unlock(&vsock->event_lock); + if (virtio_has_feature(vdev, VIRTIO_VSOCK_F_SEQPACKET)) + vsock->seqpacket_allow = true; + vdev->priv = vsock; rcu_assign_pointer(the_virtio_vsock, vsock); mutex_unlock(&the_virtio_vsock_mutex); + return 0; out: @@ -695,6 +720,7 @@ static struct virtio_device_id id_table[] = { }; static unsigned int features[] = { + VIRTIO_VSOCK_F_SEQPACKET }; static struct virtio_driver virtio_vsock_driver = { diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index 902cb6dd710b..23704a6bc437 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -74,6 +74,10 @@ virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info, err = memcpy_from_msg(pkt->buf, info->msg, len); if (err) goto out; + + if (msg_data_left(info->msg) == 0 && + info->type == VIRTIO_VSOCK_TYPE_SEQPACKET) + pkt->hdr.flags |= cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR); } trace_virtio_transport_alloc_pkt(src_cid, src_port, @@ -165,6 +169,14 @@ void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt) } EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt); +static u16 virtio_transport_get_type(struct sock *sk) +{ + if (sk->sk_type == SOCK_STREAM) + return VIRTIO_VSOCK_TYPE_STREAM; + else + return VIRTIO_VSOCK_TYPE_SEQPACKET; +} + /* This function can only be used on connecting/connected sockets, * since a socket assigned to a transport is required. * @@ -179,6 +191,8 @@ static int virtio_transport_send_pkt_info(struct vsock_sock *vsk, struct virtio_vsock_pkt *pkt; u32 pkt_len = info->pkt_len; + info->type = virtio_transport_get_type(sk_vsock(vsk)); + t_ops = virtio_transport_get_ops(vsk); if (unlikely(!t_ops)) return -EFAULT; @@ -269,13 +283,10 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit) } EXPORT_SYMBOL_GPL(virtio_transport_put_credit); -static int virtio_transport_send_credit_update(struct vsock_sock *vsk, - int type, - struct virtio_vsock_hdr *hdr) +static int virtio_transport_send_credit_update(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_CREDIT_UPDATE, - .type = type, .vsk = vsk, }; @@ -383,11 +394,8 @@ virtio_transport_stream_do_dequeue(struct vsock_sock *vsk, * messages, we set the limit to a high value. TODO: experiment * with different values. */ - if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) { - virtio_transport_send_credit_update(vsk, - VIRTIO_VSOCK_TYPE_STREAM, - NULL); - } + if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) + virtio_transport_send_credit_update(vsk); return total; @@ -397,6 +405,78 @@ out: return err; } +static int virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + struct virtio_vsock_pkt *pkt; + int dequeued_len = 0; + size_t user_buf_len = msg_data_left(msg); + bool copy_failed = false; + bool msg_ready = false; + + spin_lock_bh(&vvs->rx_lock); + + if (vvs->msg_count == 0) { + spin_unlock_bh(&vvs->rx_lock); + return 0; + } + + while (!msg_ready) { + pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list); + + if (!copy_failed) { + size_t pkt_len; + size_t bytes_to_copy; + + pkt_len = (size_t)le32_to_cpu(pkt->hdr.len); + bytes_to_copy = min(user_buf_len, pkt_len); + + if (bytes_to_copy) { + int err; + + /* sk_lock is held by caller so no one else can dequeue. + * Unlock rx_lock since memcpy_to_msg() may sleep. + */ + spin_unlock_bh(&vvs->rx_lock); + + err = memcpy_to_msg(msg, pkt->buf, bytes_to_copy); + if (err) { + /* Copy of message failed, set flag to skip + * copy path for rest of fragments. Rest of + * fragments will be freed without copy. + */ + copy_failed = true; + dequeued_len = err; + } else { + user_buf_len -= bytes_to_copy; + } + + spin_lock_bh(&vvs->rx_lock); + } + + if (dequeued_len >= 0) + dequeued_len += pkt_len; + } + + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) { + msg_ready = true; + vvs->msg_count--; + } + + virtio_transport_dec_rx_pkt(vvs, pkt); + list_del(&pkt->list); + virtio_transport_free_pkt(pkt); + } + + spin_unlock_bh(&vvs->rx_lock); + + virtio_transport_send_credit_update(vsk); + + return dequeued_len; +} + ssize_t virtio_transport_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -409,6 +489,38 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk, } EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue); +ssize_t +virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk, + struct msghdr *msg, + int flags) +{ + if (flags & MSG_PEEK) + return -EOPNOTSUPP; + + return virtio_transport_seqpacket_do_dequeue(vsk, msg, flags); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue); + +int +virtio_transport_seqpacket_enqueue(struct vsock_sock *vsk, + struct msghdr *msg, + size_t len) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + + spin_lock_bh(&vvs->tx_lock); + + if (len > vvs->peer_buf_alloc) { + spin_unlock_bh(&vvs->tx_lock); + return -EMSGSIZE; + } + + spin_unlock_bh(&vvs->tx_lock); + + return virtio_transport_stream_enqueue(vsk, msg, len); +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_enqueue); + int virtio_transport_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg, @@ -431,6 +543,19 @@ s64 virtio_transport_stream_has_data(struct vsock_sock *vsk) } EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data); +u32 virtio_transport_seqpacket_has_data(struct vsock_sock *vsk) +{ + struct virtio_vsock_sock *vvs = vsk->trans; + u32 msg_count; + + spin_lock_bh(&vvs->rx_lock); + msg_count = vvs->msg_count; + spin_unlock_bh(&vvs->rx_lock); + + return msg_count; +} +EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_has_data); + static s64 virtio_transport_has_space(struct vsock_sock *vsk) { struct virtio_vsock_sock *vvs = vsk->trans; @@ -496,8 +621,7 @@ void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val) vvs->buf_alloc = *val; - virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM, - NULL); + virtio_transport_send_credit_update(vsk); } EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size); @@ -624,7 +748,6 @@ int virtio_transport_connect(struct vsock_sock *vsk) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_REQUEST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .vsk = vsk, }; @@ -636,7 +759,6 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode) { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_SHUTDOWN, - .type = VIRTIO_VSOCK_TYPE_STREAM, .flags = (mode & RCV_SHUTDOWN ? VIRTIO_VSOCK_SHUTDOWN_RCV : 0) | (mode & SEND_SHUTDOWN ? @@ -665,7 +787,6 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RW, - .type = VIRTIO_VSOCK_TYPE_STREAM, .msg = msg, .pkt_len = len, .vsk = vsk, @@ -688,7 +809,6 @@ static int virtio_transport_reset(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RST, - .type = VIRTIO_VSOCK_TYPE_STREAM, .reply = !!pkt, .vsk = vsk, }; @@ -848,7 +968,7 @@ void virtio_transport_release(struct vsock_sock *vsk) struct sock *sk = &vsk->sk; bool remove_sock = true; - if (sk->sk_type == SOCK_STREAM) + if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET) remove_sock = virtio_transport_close(vsk); if (remove_sock) { @@ -912,6 +1032,9 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, goto out; } + if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR) + vvs->msg_count++; + /* Try to copy small packets into the buffer of last packet queued, * to avoid wasting memory queueing the entire buffer with a small * payload. @@ -923,13 +1046,18 @@ virtio_transport_recv_enqueue(struct vsock_sock *vsk, struct virtio_vsock_pkt, list); /* If there is space in the last packet queued, we copy the - * new packet in its buffer. + * new packet in its buffer. We avoid this if the last packet + * queued has VIRTIO_VSOCK_SEQ_EOR set, because this is + * delimiter of SEQPACKET record, so 'pkt' is the first packet + * of a new record. */ - if (pkt->len <= last_pkt->buf_len - last_pkt->len) { + if ((pkt->len <= last_pkt->buf_len - last_pkt->len) && + !(le32_to_cpu(last_pkt->hdr.flags) & VIRTIO_VSOCK_SEQ_EOR)) { memcpy(last_pkt->buf + last_pkt->len, pkt->buf, pkt->len); last_pkt->len += pkt->len; free_pkt = true; + last_pkt->hdr.flags |= pkt->hdr.flags; goto out; } } @@ -1000,7 +1128,6 @@ virtio_transport_send_response(struct vsock_sock *vsk, { struct virtio_vsock_pkt_info info = { .op = VIRTIO_VSOCK_OP_RESPONSE, - .type = VIRTIO_VSOCK_TYPE_STREAM, .remote_cid = le64_to_cpu(pkt->hdr.src_cid), .remote_port = le32_to_cpu(pkt->hdr.src_port), .reply = true, @@ -1096,6 +1223,12 @@ virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt, return 0; } +static bool virtio_transport_valid_type(u16 type) +{ + return (type == VIRTIO_VSOCK_TYPE_STREAM) || + (type == VIRTIO_VSOCK_TYPE_SEQPACKET); +} + /* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex * lock. */ @@ -1121,7 +1254,7 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, le32_to_cpu(pkt->hdr.buf_alloc), le32_to_cpu(pkt->hdr.fwd_cnt)); - if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) { + if (!virtio_transport_valid_type(le16_to_cpu(pkt->hdr.type))) { (void)virtio_transport_reset_no_sock(t, pkt); goto free_pkt; } @@ -1138,6 +1271,12 @@ void virtio_transport_recv_pkt(struct virtio_transport *t, } } + if (virtio_transport_get_type(sk) != le16_to_cpu(pkt->hdr.type)) { + (void)virtio_transport_reset_no_sock(t, pkt); + sock_put(sk); + goto free_pkt; + } + vsk = vsock_sk(sk); lock_sock(sk); diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c index a45f7ffca8c5..169a8cf65b39 100644 --- a/net/vmw_vsock/vsock_loopback.c +++ b/net/vmw_vsock/vsock_loopback.c @@ -63,6 +63,8 @@ static int vsock_loopback_cancel_pkt(struct vsock_sock *vsk) return 0; } +static bool vsock_loopback_seqpacket_allow(u32 remote_cid); + static struct virtio_transport loopback_transport = { .transport = { .module = THIS_MODULE, @@ -89,6 +91,11 @@ static struct virtio_transport loopback_transport = { .stream_is_active = virtio_transport_stream_is_active, .stream_allow = virtio_transport_stream_allow, + .seqpacket_dequeue = virtio_transport_seqpacket_dequeue, + .seqpacket_enqueue = virtio_transport_seqpacket_enqueue, + .seqpacket_allow = vsock_loopback_seqpacket_allow, + .seqpacket_has_data = virtio_transport_seqpacket_has_data, + .notify_poll_in = virtio_transport_notify_poll_in, .notify_poll_out = virtio_transport_notify_poll_out, .notify_recv_init = virtio_transport_notify_recv_init, @@ -105,6 +112,11 @@ static struct virtio_transport loopback_transport = { .send_pkt = vsock_loopback_send_pkt, }; +static bool vsock_loopback_seqpacket_allow(u32 remote_cid) +{ + return true; +} + static void vsock_loopback_work(struct work_struct *work) { struct vsock_loopback *vsock = diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 93cbd6f603f9..2acbb7703c6a 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -84,7 +84,7 @@ void vsock_wait_remote_close(int fd) } /* Connect to <cid, port> and return the file descriptor. */ -int vsock_stream_connect(unsigned int cid, unsigned int port) +static int vsock_connect(unsigned int cid, unsigned int port, int type) { union { struct sockaddr sa; @@ -101,7 +101,7 @@ int vsock_stream_connect(unsigned int cid, unsigned int port) control_expectln("LISTENING"); - fd = socket(AF_VSOCK, SOCK_STREAM, 0); + fd = socket(AF_VSOCK, type, 0); timeout_begin(TIMEOUT); do { @@ -120,11 +120,21 @@ int vsock_stream_connect(unsigned int cid, unsigned int port) return fd; } +int vsock_stream_connect(unsigned int cid, unsigned int port) +{ + return vsock_connect(cid, port, SOCK_STREAM); +} + +int vsock_seqpacket_connect(unsigned int cid, unsigned int port) +{ + return vsock_connect(cid, port, SOCK_SEQPACKET); +} + /* Listen on <cid, port> and return the first incoming connection. The remote * address is stored to clientaddrp. clientaddrp may be NULL. */ -int vsock_stream_accept(unsigned int cid, unsigned int port, - struct sockaddr_vm *clientaddrp) +static int vsock_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp, int type) { union { struct sockaddr sa; @@ -145,7 +155,7 @@ int vsock_stream_accept(unsigned int cid, unsigned int port, int client_fd; int old_errno; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); + fd = socket(AF_VSOCK, type, 0); if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { perror("bind"); @@ -189,6 +199,18 @@ int vsock_stream_accept(unsigned int cid, unsigned int port, return client_fd; } +int vsock_stream_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + return vsock_accept(cid, port, clientaddrp, SOCK_STREAM); +} + +int vsock_seqpacket_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp) +{ + return vsock_accept(cid, port, clientaddrp, SOCK_SEQPACKET); +} + /* Transmit one byte and check the return value. * * expected_ret: diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e53dd09d26d9..a3375ad2fb7f 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -36,8 +36,11 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_seqpacket_connect(unsigned int cid, unsigned int port); int vsock_stream_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp); +int vsock_seqpacket_accept(unsigned int cid, unsigned int port, + struct sockaddr_vm *clientaddrp); void vsock_wait_remote_close(int fd); void send_byte(int fd, int expected_ret, int flags); void recv_byte(int fd, int expected_ret, int flags); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 5a4fb80fa832..67766bfe176f 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -14,6 +14,8 @@ #include <errno.h> #include <unistd.h> #include <linux/kernel.h> +#include <sys/types.h> +#include <sys/socket.h> #include "timeout.h" #include "control.h" @@ -279,6 +281,110 @@ static void test_stream_msg_peek_server(const struct test_opts *opts) close(fd); } +#define MESSAGES_CNT 7 +static void test_seqpacket_msg_bounds_client(const struct test_opts *opts) +{ + int fd; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + /* Send several messages, one with MSG_EOR flag */ + for (int i = 0; i < MESSAGES_CNT; i++) + send_byte(fd, 1, 0); + + control_writeln("SENDDONE"); + close(fd); +} + +static void test_seqpacket_msg_bounds_server(const struct test_opts *opts) +{ + int fd; + char buf[16]; + struct msghdr msg = {0}; + struct iovec iov = {0}; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("SENDDONE"); + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + for (int i = 0; i < MESSAGES_CNT; i++) { + if (recvmsg(fd, &msg, 0) != 1) { + perror("message bound violated"); + exit(EXIT_FAILURE); + } + } + + close(fd); +} + +#define MESSAGE_TRUNC_SZ 32 +static void test_seqpacket_msg_trunc_client(const struct test_opts *opts) +{ + int fd; + char buf[MESSAGE_TRUNC_SZ]; + + fd = vsock_seqpacket_connect(opts->peer_cid, 1234); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (send(fd, buf, sizeof(buf), 0) != sizeof(buf)) { + perror("send failed"); + exit(EXIT_FAILURE); + } + + control_writeln("SENDDONE"); + close(fd); +} + +static void test_seqpacket_msg_trunc_server(const struct test_opts *opts) +{ + int fd; + char buf[MESSAGE_TRUNC_SZ / 2]; + struct msghdr msg = {0}; + struct iovec iov = {0}; + + fd = vsock_seqpacket_accept(VMADDR_CID_ANY, 1234, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + control_expectln("SENDDONE"); + iov.iov_base = buf; + iov.iov_len = sizeof(buf); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + ssize_t ret = recvmsg(fd, &msg, MSG_TRUNC); + + if (ret != MESSAGE_TRUNC_SZ) { + printf("%zi\n", ret); + perror("MSG_TRUNC doesn't work"); + exit(EXIT_FAILURE); + } + + if (!(msg.msg_flags & MSG_TRUNC)) { + fprintf(stderr, "MSG_TRUNC expected\n"); + exit(EXIT_FAILURE); + } + + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -309,6 +415,16 @@ static struct test_case test_cases[] = { .run_client = test_stream_msg_peek_client, .run_server = test_stream_msg_peek_server, }, + { + .name = "SOCK_SEQPACKET msg bounds", + .run_client = test_seqpacket_msg_bounds_client, + .run_server = test_seqpacket_msg_bounds_server, + }, + { + .name = "SOCK_SEQPACKET MSG_TRUNC flag", + .run_client = test_seqpacket_msg_trunc_client, + .run_server = test_seqpacket_msg_trunc_server, + }, {}, }; |