From 7aae6505351e4c9fc2f3108d16fd06ce76f4b475 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 6 Jan 2025 18:28:19 -0800 Subject: [PATCH 01/16] tools: ynl: print some information about attribute we can't parse When parsing throws an exception one often has to figure out which attribute couldn't be parsed from first principles. For families with large message parsing trees like rtnetlink guessing the attribute can be hard. Print a bit of information as the exception travels out, e.g.: # when dumping rt links Error decoding 'flags' from 'linkinfo-ip6tnl-attrs' Error decoding 'data' from 'linkinfo-attrs' Error decoding 'linkinfo' from 'link-attrs' Traceback (most recent call last): File "/home/kicinski/linux/./tools/net/ynl/cli.py", line 119, in main() File "/home/kicinski/linux/./tools/net/ynl/cli.py", line 100, in main reply = ynl.dump(args.dump, attrs) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 1064, in dump return self._op(method, vals, dump=True) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 1058, in _op return self._ops(ops)[0] File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 1045, in _ops rsp_msg = self._decode(decoded.raw_attrs, op.attr_set.name) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 738, in _decode subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 763, in _decode decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 714, in _decode_sub_msg subdict = self._decode(NlAttrs(attr.raw, offset), msg_format.attr_set) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 749, in _decode decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) File "/home/kicinski/linux/tools/net/ynl/lib/ynl.py", line 147, in as_scalar return format.unpack(self.raw)[0] struct.error: unpack requires a buffer of 2 bytes The Traceback is what we would previously see, the "Error..." messages are new. We print a message per level (in the stack order). Printing single combined message gets tricky quickly given sub-messages etc. Reviewed-by: Donald Hunter Acked-by: Stanislav Fomichev Link: https://patch.msgid.link/20250107022820.2087101-3-kuba@kernel.org Signed-off-by: Jakub Kicinski --- tools/net/ynl/lib/ynl.py | 74 +++++++++++++++++++++------------------- 1 file changed, 39 insertions(+), 35 deletions(-) diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py index eea29359a899..08f8bf89cfc2 100644 --- a/tools/net/ynl/lib/ynl.py +++ b/tools/net/ynl/lib/ynl.py @@ -733,41 +733,45 @@ class YnlFamily(SpecFamily): self._rsp_add(rsp, attr_name, None, self._decode_unknown(attr)) continue - if attr_spec["type"] == 'nest': - subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) - decoded = subdict - elif attr_spec["type"] == 'string': - decoded = attr.as_strz() - elif attr_spec["type"] == 'binary': - decoded = self._decode_binary(attr, attr_spec) - elif attr_spec["type"] == 'flag': - decoded = True - elif attr_spec.is_auto_scalar: - decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) - elif attr_spec["type"] in NlAttr.type_formats: - decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) - if 'enum' in attr_spec: - decoded = self._decode_enum(decoded, attr_spec) - elif attr_spec.display_hint: - decoded = self._formatted_string(decoded, attr_spec.display_hint) - elif attr_spec["type"] == 'indexed-array': - decoded = self._decode_array_attr(attr, attr_spec) - elif attr_spec["type"] == 'bitfield32': - value, selector = struct.unpack("II", attr.raw) - if 'enum' in attr_spec: - value = self._decode_enum(value, attr_spec) - selector = self._decode_enum(selector, attr_spec) - decoded = {"value": value, "selector": selector} - elif attr_spec["type"] == 'sub-message': - decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) - elif attr_spec["type"] == 'nest-type-value': - decoded = self._decode_nest_type_value(attr, attr_spec) - else: - if not self.process_unknown: - raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') - decoded = self._decode_unknown(attr) - - self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded) + try: + if attr_spec["type"] == 'nest': + subdict = self._decode(NlAttrs(attr.raw), attr_spec['nested-attributes'], search_attrs) + decoded = subdict + elif attr_spec["type"] == 'string': + decoded = attr.as_strz() + elif attr_spec["type"] == 'binary': + decoded = self._decode_binary(attr, attr_spec) + elif attr_spec["type"] == 'flag': + decoded = True + elif attr_spec.is_auto_scalar: + decoded = attr.as_auto_scalar(attr_spec['type'], attr_spec.byte_order) + elif attr_spec["type"] in NlAttr.type_formats: + decoded = attr.as_scalar(attr_spec['type'], attr_spec.byte_order) + if 'enum' in attr_spec: + decoded = self._decode_enum(decoded, attr_spec) + elif attr_spec.display_hint: + decoded = self._formatted_string(decoded, attr_spec.display_hint) + elif attr_spec["type"] == 'indexed-array': + decoded = self._decode_array_attr(attr, attr_spec) + elif attr_spec["type"] == 'bitfield32': + value, selector = struct.unpack("II", attr.raw) + if 'enum' in attr_spec: + value = self._decode_enum(value, attr_spec) + selector = self._decode_enum(selector, attr_spec) + decoded = {"value": value, "selector": selector} + elif attr_spec["type"] == 'sub-message': + decoded = self._decode_sub_msg(attr, attr_spec, search_attrs) + elif attr_spec["type"] == 'nest-type-value': + decoded = self._decode_nest_type_value(attr, attr_spec) + else: + if not self.process_unknown: + raise Exception(f'Unknown {attr_spec["type"]} with name {attr_spec["name"]}') + decoded = self._decode_unknown(attr) + + self._rsp_add(rsp, attr_spec["name"], attr_spec.is_multi, decoded) + except: + print(f"Error decoding '{attr_spec.name}' from '{space}'") + raise return rsp -- 2.50.1 From 6ffdbb93a59c60ee18bebd9acdbbca91e6bf0e64 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Mon, 6 Jan 2025 18:28:20 -0800 Subject: [PATCH 02/16] netlink: specs: rt_link: decode ip6tnl, vti and vti6 link attrs Some of our tests load vti and ip6tnl so not being able to decode the link attrs gets in the way of using Python YNL for testing. Decode link attributes for ip6tnl, vti and vti6. ip6tnl uses IFLA_IPTUN_FLAGS as u32, while ipv4 and sit expect a u16 attribute, so we have a (first?) subset type override... Reviewed-by: Donald Hunter Acked-by: Stanislav Fomichev Link: https://patch.msgid.link/20250107022820.2087101-4-kuba@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/rt_link.yaml | 87 ++++++++++++++++++++++++ 1 file changed, 87 insertions(+) diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml index 2f62d51c26cd..0d492500c7e5 100644 --- a/Documentation/netlink/specs/rt_link.yaml +++ b/Documentation/netlink/specs/rt_link.yaml @@ -1825,6 +1825,48 @@ attribute-sets: - name: erspan-hwid type: u16 + - + name: linkinfo-vti-attrs + name-prefix: ifla-vti- + attributes: + - + name: link + type: u32 + - + name: ikey + type: u32 + - + name: okey + type: u32 + - + name: local + type: binary + display-hint: ipv4 + - + name: remote + type: binary + display-hint: ipv4 + - + name: fwmark + type: u32 + - + name: linkinfo-vti6-attrs + subset-of: linkinfo-vti-attrs + attributes: + - + name: link + - + name: ikey + - + name: okey + - + name: local + display-hint: ipv6 + - + name: remote + display-hint: ipv6 + - + name: fwmark - name: linkinfo-geneve-attrs name-prefix: ifla-geneve- @@ -1941,6 +1983,42 @@ attribute-sets: - name: fwmark type: u32 + - + name: linkinfo-ip6tnl-attrs + subset-of: linkinfo-iptun-attrs + attributes: + - + name: link + - + name: local + display-hint: ipv6 + - + name: remote + display-hint: ipv6 + - + name: ttl + - + name: encap-limit + - + name: flowinfo + - + name: flags + # ip6tnl unlike ipip and sit has 32b flags + type: u32 + - + name: proto + - + name: encap-type + - + name: encap-flags + - + name: encap-sport + - + name: encap-dport + - + name: collect-metadata + - + name: fwmark - name: linkinfo-tun-attrs name-prefix: ifla-tun- @@ -2201,6 +2279,9 @@ sub-messages: - value: ipip attribute-set: linkinfo-iptun-attrs + - + value: ip6tnl + attribute-set: linkinfo-ip6tnl-attrs - value: sit attribute-set: linkinfo-iptun-attrs @@ -2213,6 +2294,12 @@ sub-messages: - value: vrf attribute-set: linkinfo-vrf-attrs + - + value: vti + attribute-set: linkinfo-vti-attrs + - + value: vti6 + attribute-set: linkinfo-vti6-attrs - value: netkit attribute-set: linkinfo-netkit-attrs -- 2.50.1 From f70b864ccc84a024c765306e95e8e390834c263d Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Mon, 6 Jan 2025 14:19:09 -0800 Subject: [PATCH 03/16] igb: Remove static qualifiers Remove static qualifiers on the following functions to be able to call from XSK specific file that is added in the later patches: - igb_xdp_tx_queue_mapping() - igb_xdp_ring_update_tail() - igb_clean_tx_ring() - igb_clean_rx_ring() - igb_xdp_xmit_back() - igb_process_skb_fields() While at it, inline igb_xdp_tx_queue_mapping() and igb_xdp_ring_update_tail(). These functions are small enough and used in XDP hot paths. Signed-off-by: Sriram Yagnaraman [Kurt: Split patches, inline small XDP functions] Signed-off-by: Kurt Kanzenbach Acked-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-2-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb.h | 29 ++++++++++++++++++ drivers/net/ethernet/intel/igb/igb_main.c | 37 ++++------------------- 2 files changed, 35 insertions(+), 31 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 3c2dc7bdebb5..1bfe703e73d9 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -18,6 +18,7 @@ #include #include #include +#include #include @@ -731,12 +732,18 @@ int igb_setup_tx_resources(struct igb_ring *); int igb_setup_rx_resources(struct igb_ring *); void igb_free_tx_resources(struct igb_ring *); void igb_free_rx_resources(struct igb_ring *); +void igb_clean_tx_ring(struct igb_ring *tx_ring); +void igb_clean_rx_ring(struct igb_ring *rx_ring); void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *); void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp); +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *); bool igb_has_link(struct igb_adapter *adapter); @@ -797,6 +804,28 @@ static inline struct netdev_queue *txring_txq(const struct igb_ring *tx_ring) return netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); } +/* This function assumes __netif_tx_lock is held by the caller. */ +static inline void igb_xdp_ring_update_tail(struct igb_ring *ring) +{ + lockdep_assert_held(&txring_txq(ring)->_xmit_lock); + + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static inline struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) +{ + unsigned int r_idx = smp_processor_id(); + + if (r_idx >= adapter->num_tx_queues) + r_idx = r_idx % adapter->num_tx_queues; + + return adapter->tx_ring[r_idx]; +} + int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input); int igb_erase_filter(struct igb_adapter *adapter, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 288a4bb2683a..77a6d1470f8b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -33,7 +33,6 @@ #include #include #include -#include #ifdef CONFIG_IGB_DCA #include #endif @@ -116,8 +115,6 @@ static void igb_configure_tx(struct igb_adapter *); static void igb_configure_rx(struct igb_adapter *); static void igb_clean_all_tx_rings(struct igb_adapter *); static void igb_clean_all_rx_rings(struct igb_adapter *); -static void igb_clean_tx_ring(struct igb_ring *); -static void igb_clean_rx_ring(struct igb_ring *); static void igb_set_rx_mode(struct net_device *); static void igb_update_phy_info(struct timer_list *); static void igb_watchdog(struct timer_list *); @@ -2919,29 +2916,7 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -/* This function assumes __netif_tx_lock is held by the caller. */ -static void igb_xdp_ring_update_tail(struct igb_ring *ring) -{ - lockdep_assert_held(&txring_txq(ring)->_xmit_lock); - - /* Force memory writes to complete before letting h/w know there - * are new descriptors to fetch. - */ - wmb(); - writel(ring->next_to_use, ring->tail); -} - -static struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adapter) -{ - unsigned int r_idx = smp_processor_id(); - - if (r_idx >= adapter->num_tx_queues) - r_idx = r_idx % adapter->num_tx_queues; - - return adapter->tx_ring[r_idx]; -} - -static int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) +int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) { struct xdp_frame *xdpf = xdp_convert_buff_to_frame(xdp); int cpu = smp_processor_id(); @@ -4888,7 +4863,7 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ -static void igb_clean_tx_ring(struct igb_ring *tx_ring) +void igb_clean_tx_ring(struct igb_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; @@ -5007,7 +4982,7 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) * igb_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from **/ -static void igb_clean_rx_ring(struct igb_ring *rx_ring) +void igb_clean_rx_ring(struct igb_ring *rx_ring) { u16 i = rx_ring->next_to_clean; @@ -8786,9 +8761,9 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, * order to populate the hash, checksum, VLAN, timestamp, protocol, and * other fields within the skb. **/ -static void igb_process_skb_fields(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +void igb_process_skb_fields(struct igb_ring *rx_ring, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) { struct net_device *dev = rx_ring->netdev; -- 2.50.1 From 6dc75fc230eceedada4adf8c2857636a9dbd00a8 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Mon, 6 Jan 2025 14:19:10 -0800 Subject: [PATCH 04/16] igb: Introduce igb_xdp_is_enabled() Introduce igb_xdp_is_enabled() to check if an XDP program is assigned to the device. Use that wherever xdp_prog is read and evaluated. Signed-off-by: Sriram Yagnaraman [Kurt: Split patches and use READ_ONCE()] Signed-off-by: Kurt Kanzenbach Acked-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-3-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb.h | 5 +++++ drivers/net/ethernet/intel/igb/igb_main.c | 8 +++++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 1bfe703e73d9..6e2b61ecff68 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -826,6 +826,11 @@ static inline struct igb_ring *igb_xdp_tx_queue_mapping(struct igb_adapter *adap return adapter->tx_ring[r_idx]; } +static inline bool igb_xdp_is_enabled(struct igb_adapter *adapter) +{ + return !!READ_ONCE(adapter->xdp_prog); +} + int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input); int igb_erase_filter(struct igb_adapter *adapter, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 77a6d1470f8b..fef58c55eb43 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2930,7 +2930,8 @@ int igb_xdp_xmit_back(struct igb_adapter *adapter, struct xdp_buff *xdp) /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return IGB_XDP_CONSUMED; @@ -2963,7 +2964,8 @@ static int igb_xdp_xmit(struct net_device *dev, int n, /* During program transitions its possible adapter->xdp_prog is assigned * but ring has not been configured yet. In this case simply abort xmit. */ - tx_ring = adapter->xdp_prog ? igb_xdp_tx_queue_mapping(adapter) : NULL; + tx_ring = igb_xdp_is_enabled(adapter) ? + igb_xdp_tx_queue_mapping(adapter) : NULL; if (unlikely(!tx_ring)) return -ENXIO; @@ -6597,7 +6599,7 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu) struct igb_adapter *adapter = netdev_priv(netdev); int max_frame = new_mtu + IGB_ETH_PKT_HDR_PAD; - if (adapter->xdp_prog) { + if (igb_xdp_is_enabled(adapter)) { int i; for (i = 0; i < adapter->num_rx_queues; i++) { -- 2.50.1 From 80f6ccf9f1160ba26cfa4bf90f3cced6f2d12268 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Mon, 6 Jan 2025 14:19:11 -0800 Subject: [PATCH 05/16] igb: Introduce XSK data structures and helpers Add the following ring flag: - IGB_RING_FLAG_TX_DISABLED (when xsk pool is being setup) Add a xdp_buff array for use with XSK receive batch API, and a pointer to xsk_pool in igb_adapter. Add enable/disable functions for TX and RX rings. Add enable/disable functions for XSK pool. Add xsk wakeup function. None of the above functionality will be active until NETDEV_XDP_ACT_XSK_ZEROCOPY is advertised in netdev->xdp_features. Signed-off-by: Sriram Yagnaraman [Kurt: Add READ/WRITE_ONCE(), synchronize_net(), remove IGB_RING_FLAG_AF_XDP_ZC] Signed-off-by: Kurt Kanzenbach Reviewed-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-4-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/Makefile | 2 +- drivers/net/ethernet/intel/igb/igb.h | 13 +- drivers/net/ethernet/intel/igb/igb_main.c | 9 + drivers/net/ethernet/intel/igb/igb_xsk.c | 207 ++++++++++++++++++++++ 4 files changed, 229 insertions(+), 2 deletions(-) create mode 100644 drivers/net/ethernet/intel/igb/igb_xsk.c diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile index 463c0d26b9d4..6c1b702fd992 100644 --- a/drivers/net/ethernet/intel/igb/Makefile +++ b/drivers/net/ethernet/intel/igb/Makefile @@ -8,4 +8,4 @@ obj-$(CONFIG_IGB) += igb.o igb-y := igb_main.o igb_ethtool.o e1000_82575.o \ e1000_mac.o e1000_nvm.o e1000_phy.o e1000_mbx.o \ - e1000_i210.o igb_ptp.o igb_hwmon.o + e1000_i210.o igb_ptp.o igb_hwmon.o igb_xsk.o diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 6e2b61ecff68..c30d6f9708f8 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -21,6 +21,7 @@ #include #include +#include struct igb_adapter; @@ -321,6 +322,7 @@ struct igb_ring { union { /* array of buffer info structs */ struct igb_tx_buffer *tx_buffer_info; struct igb_rx_buffer *rx_buffer_info; + struct xdp_buff **rx_buffer_info_zc; }; void *desc; /* descriptor ring memory */ unsigned long flags; /* ring specific flags */ @@ -358,6 +360,7 @@ struct igb_ring { }; }; struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; } ____cacheline_internodealigned_in_smp; struct igb_q_vector { @@ -385,7 +388,8 @@ enum e1000_ring_flags_t { IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, - IGB_RING_FLAG_TX_DETECT_HANG + IGB_RING_FLAG_TX_DETECT_HANG, + IGB_RING_FLAG_TX_DISABLED }; #define ring_uses_large_buffer(ring) \ @@ -841,4 +845,11 @@ int igb_add_mac_steering_filter(struct igb_adapter *adapter, int igb_del_mac_steering_filter(struct igb_adapter *adapter, const u8 *addr, u8 queue, u8 flags); +struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, + struct igb_ring *ring); +int igb_xsk_pool_setup(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid); +int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); + #endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index fef58c55eb43..8329096af8ef 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2908,9 +2908,14 @@ static int igb_xdp_setup(struct net_device *dev, struct netdev_bpf *bpf) static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp) { + struct igb_adapter *adapter = netdev_priv(dev); + switch (xdp->command) { case XDP_SETUP_PROG: return igb_xdp_setup(dev, xdp); + case XDP_SETUP_XSK_POOL: + return igb_xsk_pool_setup(adapter, xdp->xsk.pool, + xdp->xsk.queue_id); default: return -EINVAL; } @@ -3019,6 +3024,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_setup_tc = igb_setup_tc, .ndo_bpf = igb_xdp, .ndo_xdp_xmit = igb_xdp_xmit, + .ndo_xsk_wakeup = igb_xsk_wakeup, }; /** @@ -4341,6 +4347,8 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, u64 tdba = ring->dma; int reg_idx = ring->reg_idx; + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + wr32(E1000_TDLEN(reg_idx), ring->count * sizeof(union e1000_adv_tx_desc)); wr32(E1000_TDBAL(reg_idx), @@ -4736,6 +4744,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, NULL)); + WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); /* disable the queue */ wr32(E1000_RXDCTL(reg_idx), 0); diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c new file mode 100644 index 000000000000..7b632be3e7e3 --- /dev/null +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -0,0 +1,207 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include +#include +#include + +#include "e1000_hw.h" +#include "igb.h" + +static int igb_realloc_rx_buffer_info(struct igb_ring *ring, bool pool_present) +{ + int size = pool_present ? + sizeof(*ring->rx_buffer_info_zc) * ring->count : + sizeof(*ring->rx_buffer_info) * ring->count; + void *buff_info = vmalloc(size); + + if (!buff_info) + return -ENOMEM; + + if (pool_present) { + vfree(ring->rx_buffer_info); + ring->rx_buffer_info = NULL; + ring->rx_buffer_info_zc = buff_info; + } else { + vfree(ring->rx_buffer_info_zc); + ring->rx_buffer_info_zc = NULL; + ring->rx_buffer_info = buff_info; + } + + return 0; +} + +static void igb_txrx_ring_disable(struct igb_adapter *adapter, u16 qid) +{ + struct igb_ring *tx_ring = adapter->tx_ring[qid]; + struct igb_ring *rx_ring = adapter->rx_ring[qid]; + struct e1000_hw *hw = &adapter->hw; + + set_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags); + + wr32(E1000_TXDCTL(tx_ring->reg_idx), 0); + wr32(E1000_RXDCTL(rx_ring->reg_idx), 0); + + synchronize_net(); + + /* Rx/Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + + igb_clean_tx_ring(tx_ring); + igb_clean_rx_ring(rx_ring); + + memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); + memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats)); +} + +static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid) +{ + struct igb_ring *tx_ring = adapter->tx_ring[qid]; + struct igb_ring *rx_ring = adapter->rx_ring[qid]; + + igb_configure_tx_ring(adapter, tx_ring); + igb_configure_rx_ring(adapter, rx_ring); + + synchronize_net(); + + clear_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags); + + /* call igb_desc_unused which always leaves + * at least 1 descriptor unused to make sure + * next_to_use != next_to_clean + */ + igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring)); + + /* Rx/Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); +} + +struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, + struct igb_ring *ring) +{ + int qid = ring->queue_index; + struct xsk_buff_pool *pool; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + + if (!igb_xdp_is_enabled(adapter)) + return NULL; + + return (pool && pool->dev) ? pool : NULL; +} + +static int igb_xsk_pool_enable(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + struct net_device *netdev = adapter->netdev; + struct igb_ring *rx_ring; + bool if_running; + int err; + + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (qid >= netdev->real_num_rx_queues || + qid >= netdev->real_num_tx_queues) + return -EINVAL; + + err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IGB_RX_DMA_ATTR); + if (err) + return err; + + rx_ring = adapter->rx_ring[qid]; + if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter); + if (if_running) + igb_txrx_ring_disable(adapter, qid); + + if (if_running) { + err = igb_realloc_rx_buffer_info(rx_ring, true); + if (!err) { + igb_txrx_ring_enable(adapter, qid); + /* Kick start the NAPI context so that receiving will start */ + err = igb_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX); + } + + if (err) { + xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR); + return err; + } + } + + return 0; +} + +static int igb_xsk_pool_disable(struct igb_adapter *adapter, u16 qid) +{ + struct xsk_buff_pool *pool; + struct igb_ring *rx_ring; + bool if_running; + int err; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + if (!pool) + return -EINVAL; + + rx_ring = adapter->rx_ring[qid]; + if_running = netif_running(adapter->netdev) && igb_xdp_is_enabled(adapter); + if (if_running) + igb_txrx_ring_disable(adapter, qid); + + xsk_pool_dma_unmap(pool, IGB_RX_DMA_ATTR); + + if (if_running) { + err = igb_realloc_rx_buffer_info(rx_ring, false); + if (err) + return err; + + igb_txrx_ring_enable(adapter, qid); + } + + return 0; +} + +int igb_xsk_pool_setup(struct igb_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + return pool ? igb_xsk_pool_enable(adapter, pool, qid) : + igb_xsk_pool_disable(adapter, qid); +} + +int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) +{ + struct igb_adapter *adapter = netdev_priv(dev); + struct e1000_hw *hw = &adapter->hw; + struct igb_ring *ring; + u32 eics = 0; + + if (test_bit(__IGB_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!igb_xdp_is_enabled(adapter)) + return -EINVAL; + + if (qid >= adapter->num_tx_queues) + return -EINVAL; + + ring = adapter->tx_ring[qid]; + + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &ring->flags)) + return -ENETDOWN; + + if (!READ_ONCE(ring->xsk_pool)) + return -EINVAL; + + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + /* Cause software interrupt */ + if (adapter->flags & IGB_FLAG_HAS_MSIX) { + eics |= ring->q_vector->eims_value; + wr32(E1000_EICS, eics); + } else { + wr32(E1000_ICS, E1000_ICS_RXDMT0); + } + } + + return 0; +} -- 2.50.1 From 0fe7cce6000c0976e3cd3e2d8cd4c9f1f24a55a3 Mon Sep 17 00:00:00 2001 From: Kurt Kanzenbach Date: Mon, 6 Jan 2025 14:19:12 -0800 Subject: [PATCH 06/16] igb: Add XDP finalize and stats update functions Move XDP finalize and Rx statistics update into separate functions. This way, they can be reused by the XDP and XDP/ZC code later. Signed-off-by: Kurt Kanzenbach Acked-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-5-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb.h | 3 ++ drivers/net/ethernet/intel/igb/igb_main.c | 54 +++++++++++++++-------- 2 files changed, 38 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index c30d6f9708f8..1e65b41a48d8 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -740,6 +740,9 @@ void igb_clean_tx_ring(struct igb_ring *tx_ring); void igb_clean_rx_ring(struct igb_ring *rx_ring); void igb_configure_tx_ring(struct igb_adapter *, struct igb_ring *); void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status); +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); void igb_setup_srrctl(struct igb_adapter *, struct igb_ring *); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 8329096af8ef..be914b44e39d 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8856,6 +8856,38 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring, rx_buffer->page = NULL; } +void igb_finalize_xdp(struct igb_adapter *adapter, unsigned int status) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + + if (status & IGB_XDP_REDIR) + xdp_do_flush(); + + if (status & IGB_XDP_TX) { + struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + igb_xdp_ring_update_tail(tx_ring); + __netif_tx_unlock(nq); + } +} + +void igb_update_rx_stats(struct igb_q_vector *q_vector, unsigned int packets, + unsigned int bytes) +{ + struct igb_ring *ring = q_vector->rx.ring; + + u64_stats_update_begin(&ring->rx_syncp); + ring->rx_stats.packets += packets; + ring->rx_stats.bytes += bytes; + u64_stats_update_end(&ring->rx_syncp); + + q_vector->rx.total_packets += packets; + q_vector->rx.total_bytes += bytes; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { unsigned int total_bytes = 0, total_packets = 0; @@ -8863,9 +8895,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) struct igb_ring *rx_ring = q_vector->rx.ring; u16 cleaned_count = igb_desc_unused(rx_ring); struct sk_buff *skb = rx_ring->skb; - int cpu = smp_processor_id(); unsigned int xdp_xmit = 0; - struct netdev_queue *nq; struct xdp_buff xdp; u32 frame_sz = 0; int rx_buf_pgcnt; @@ -8987,24 +9017,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* place incomplete frames back on ring for completion */ rx_ring->skb = skb; - if (xdp_xmit & IGB_XDP_REDIR) - xdp_do_flush(); - - if (xdp_xmit & IGB_XDP_TX) { - struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter); - - nq = txring_txq(tx_ring); - __netif_tx_lock(nq, cpu); - igb_xdp_ring_update_tail(tx_ring); - __netif_tx_unlock(nq); - } + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); - u64_stats_update_begin(&rx_ring->rx_syncp); - rx_ring->rx_stats.packets += total_packets; - rx_ring->rx_stats.bytes += total_bytes; - u64_stats_update_end(&rx_ring->rx_syncp); - q_vector->rx.total_packets += total_packets; - q_vector->rx.total_bytes += total_bytes; + igb_update_rx_stats(q_vector, total_packets, total_bytes); if (cleaned_count) igb_alloc_rx_buffers(rx_ring, cleaned_count); -- 2.50.1 From 2c6196013f84651772388a86dfd4bb033d0c0d45 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Mon, 6 Jan 2025 14:19:13 -0800 Subject: [PATCH 07/16] igb: Add AF_XDP zero-copy Rx support Add support for AF_XDP zero-copy receive path. When AF_XDP zero-copy is enabled, the rx buffers are allocated from the xsk buff pool using igb_alloc_rx_buffers_zc(). Use xsk_pool_get_rx_frame_size() to set SRRCTL rx buf size when zero-copy is enabled. Signed-off-by: Sriram Yagnaraman [Kurt: Port to v6.12 and provide napi_id for xdp_rxq_info_reg(), RCT, remove NETDEV_XDP_ACT_XSK_ZEROCOPY, update NTC handling, READ_ONCE() xsk_pool, likelyfy for XDP_REDIRECT case] Signed-off-by: Kurt Kanzenbach Acked-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-6-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb.h | 6 + drivers/net/ethernet/intel/igb/igb_main.c | 79 ++++-- drivers/net/ethernet/intel/igb/igb_xsk.c | 294 +++++++++++++++++++++- 3 files changed, 360 insertions(+), 19 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 1e65b41a48d8..e4a85867aa18 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -88,6 +88,7 @@ struct igb_adapter; #define IGB_XDP_CONSUMED BIT(0) #define IGB_XDP_TX BIT(1) #define IGB_XDP_REDIR BIT(2) +#define IGB_XDP_EXIT BIT(3) struct vf_data_storage { unsigned char vf_mac_addresses[ETH_ALEN]; @@ -853,6 +854,11 @@ struct xsk_buff_pool *igb_xsk_pool(struct igb_adapter *adapter, int igb_xsk_pool_setup(struct igb_adapter *adapter, struct xsk_buff_pool *pool, u16 qid); +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count); +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring); +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, + struct xsk_buff_pool *xsk_pool, const int budget); int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); #endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index be914b44e39d..b478b7818adb 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -472,12 +472,17 @@ rx_ring_summary: for (i = 0; i < rx_ring->count; i++) { const char *next_desc; - struct igb_rx_buffer *buffer_info; - buffer_info = &rx_ring->rx_buffer_info[i]; + dma_addr_t dma = (dma_addr_t)0; + struct igb_rx_buffer *buffer_info = NULL; rx_desc = IGB_RX_DESC(rx_ring, i); u0 = (struct my_u0 *)rx_desc; staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + if (!rx_ring->xsk_pool) { + buffer_info = &rx_ring->rx_buffer_info[i]; + dma = buffer_info->dma; + } + if (i == rx_ring->next_to_use) next_desc = " NTU"; else if (i == rx_ring->next_to_clean) @@ -497,11 +502,11 @@ rx_ring_summary: "R ", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - (u64)buffer_info->dma, + (u64)dma, next_desc); if (netif_msg_pktdata(adapter) && - buffer_info->dma && buffer_info->page) { + buffer_info && dma && buffer_info->page) { print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, @@ -1987,7 +1992,11 @@ static void igb_configure(struct igb_adapter *adapter) */ for (i = 0; i < adapter->num_rx_queues; i++) { struct igb_ring *ring = adapter->rx_ring[i]; - igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); + if (ring->xsk_pool) + igb_alloc_rx_buffers_zc(ring, ring->xsk_pool, + igb_desc_unused(ring)); + else + igb_alloc_rx_buffers(ring, igb_desc_unused(ring)); } } @@ -4409,7 +4418,8 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) xdp_rxq_info_unreg(&rx_ring->xdp_rxq); res = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index, 0); + rx_ring->queue_index, + rx_ring->q_vector->napi.napi_id); if (res < 0) { dev_err(dev, "Failed to register xdp_rxq index %u\n", rx_ring->queue_index); @@ -4705,12 +4715,17 @@ void igb_setup_srrctl(struct igb_adapter *adapter, struct igb_ring *ring) struct e1000_hw *hw = &adapter->hw; int reg_idx = ring->reg_idx; u32 srrctl = 0; + u32 buf_size; - srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - if (ring_uses_large_buffer(ring)) - srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring->xsk_pool) + buf_size = xsk_pool_get_rx_frame_size(ring->xsk_pool); + else if (ring_uses_large_buffer(ring)) + buf_size = IGB_RXBUFFER_3072; else - srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + buf_size = IGB_RXBUFFER_2048; + + srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; + srrctl |= buf_size >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -4742,9 +4757,17 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, u32 rxdctl = 0; xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); - WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, - MEM_TYPE_PAGE_SHARED, NULL)); WRITE_ONCE(ring->xsk_pool, igb_xsk_pool(adapter, ring)); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL)); + } /* disable the queue */ wr32(E1000_RXDCTL(reg_idx), 0); @@ -4771,9 +4794,12 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; - /* initialize rx_buffer_info */ - memset(ring->rx_buffer_info, 0, - sizeof(struct igb_rx_buffer) * ring->count); + if (ring->xsk_pool) + memset(ring->rx_buffer_info_zc, 0, + sizeof(*ring->rx_buffer_info_zc) * ring->count); + else + memset(ring->rx_buffer_info, 0, + sizeof(*ring->rx_buffer_info) * ring->count); /* initialize Rx descriptor 0 */ rx_desc = IGB_RX_DESC(ring, 0); @@ -4961,8 +4987,13 @@ void igb_free_rx_resources(struct igb_ring *rx_ring) rx_ring->xdp_prog = NULL; xdp_rxq_info_unreg(&rx_ring->xdp_rxq); - vfree(rx_ring->rx_buffer_info); - rx_ring->rx_buffer_info = NULL; + if (rx_ring->xsk_pool) { + vfree(rx_ring->rx_buffer_info_zc); + rx_ring->rx_buffer_info_zc = NULL; + } else { + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + } /* if not set, then don't free */ if (!rx_ring->desc) @@ -5000,6 +5031,11 @@ void igb_clean_rx_ring(struct igb_ring *rx_ring) dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; + if (rx_ring->xsk_pool) { + igb_clean_rx_ring_zc(rx_ring); + goto skip_for_xsk; + } + /* Free all the Rx ring sk_buffs */ while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; @@ -5027,6 +5063,7 @@ void igb_clean_rx_ring(struct igb_ring *rx_ring) i = 0; } +skip_for_xsk: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -8181,6 +8218,7 @@ static int igb_poll(struct napi_struct *napi, int budget) struct igb_q_vector *q_vector = container_of(napi, struct igb_q_vector, napi); + struct xsk_buff_pool *xsk_pool; bool clean_complete = true; int work_done = 0; @@ -8192,7 +8230,12 @@ static int igb_poll(struct napi_struct *napi, int budget) clean_complete = igb_clean_tx_irq(q_vector, budget); if (q_vector->rx.ring) { - int cleaned = igb_clean_rx_irq(q_vector, budget); + int cleaned; + + xsk_pool = READ_ONCE(q_vector->rx.ring->xsk_pool); + cleaned = xsk_pool ? + igb_clean_rx_irq_zc(q_vector, xsk_pool, budget) : + igb_clean_rx_irq(q_vector, budget); work_done += cleaned; if (cleaned >= budget) diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c index 7b632be3e7e3..3d64a9f6360c 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -70,7 +70,11 @@ static void igb_txrx_ring_enable(struct igb_adapter *adapter, u16 qid) * at least 1 descriptor unused to make sure * next_to_use != next_to_clean */ - igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring)); + if (rx_ring->xsk_pool) + igb_alloc_rx_buffers_zc(rx_ring, rx_ring->xsk_pool, + igb_desc_unused(rx_ring)); + else + igb_alloc_rx_buffers(rx_ring, igb_desc_unused(rx_ring)); /* Rx/Tx share the same napi context. */ napi_enable(&rx_ring->q_vector->napi); @@ -169,6 +173,294 @@ int igb_xsk_pool_setup(struct igb_adapter *adapter, igb_xsk_pool_disable(adapter, qid); } +static u16 igb_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp, + union e1000_adv_rx_desc *rx_desc, u16 count) +{ + dma_addr_t dma; + u16 buffs; + int i; + + /* nothing to do */ + if (!count) + return 0; + + buffs = xsk_buff_alloc_batch(pool, xdp, count); + for (i = 0; i < buffs; i++) { + dma = xsk_buff_xdp_get_dma(*xdp); + rx_desc->read.pkt_addr = cpu_to_le64(dma); + rx_desc->wb.upper.length = 0; + + rx_desc++; + xdp++; + } + + return buffs; +} + +bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, + struct xsk_buff_pool *xsk_pool, u16 count) +{ + u32 nb_buffs_extra = 0, nb_buffs = 0; + union e1000_adv_rx_desc *rx_desc; + u16 ntu = rx_ring->next_to_use; + u16 total_count = count; + struct xdp_buff **xdp; + + rx_desc = IGB_RX_DESC(rx_ring, ntu); + xdp = &rx_ring->rx_buffer_info_zc[ntu]; + + if (ntu + count >= rx_ring->count) { + nb_buffs_extra = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, + rx_ring->count - ntu); + if (nb_buffs_extra != rx_ring->count - ntu) { + ntu += nb_buffs_extra; + goto exit; + } + rx_desc = IGB_RX_DESC(rx_ring, 0); + xdp = rx_ring->rx_buffer_info_zc; + ntu = 0; + count -= nb_buffs_extra; + } + + nb_buffs = igb_fill_rx_descs(xsk_pool, xdp, rx_desc, count); + ntu += nb_buffs; + if (ntu == rx_ring->count) + ntu = 0; + + /* clear the length for the next_to_use descriptor */ + rx_desc = IGB_RX_DESC(rx_ring, ntu); + rx_desc->wb.upper.length = 0; + +exit: + if (rx_ring->next_to_use != ntu) { + rx_ring->next_to_use = ntu; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. (Only + * applicable for weak-ordered memory model archs, + * such as IA-64). + */ + wmb(); + writel(ntu, rx_ring->tail); + } + + return total_count == (nb_buffs + nb_buffs_extra); +} + +void igb_clean_rx_ring_zc(struct igb_ring *rx_ring) +{ + u16 ntc = rx_ring->next_to_clean; + u16 ntu = rx_ring->next_to_use; + + while (ntc != ntu) { + struct xdp_buff *xdp = rx_ring->rx_buffer_info_zc[ntc]; + + xsk_buff_free(xdp); + ntc++; + if (ntc >= rx_ring->count) + ntc = 0; + } +} + +static struct sk_buff *igb_construct_skb_zc(struct igb_ring *rx_ring, + struct xdp_buff *xdp, + ktime_t timestamp) +{ + unsigned int totalsize = xdp->data_end - xdp->data_meta; + unsigned int metasize = xdp->data - xdp->data_meta; + struct sk_buff *skb; + + net_prefetch(xdp->data_meta); + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, totalsize); + if (unlikely(!skb)) + return NULL; + + if (timestamp) + skb_hwtstamps(skb)->hwtstamp = timestamp; + + memcpy(__skb_put(skb, totalsize), xdp->data_meta, + ALIGN(totalsize, sizeof(long))); + + if (metasize) { + skb_metadata_set(skb, metasize); + __skb_pull(skb, metasize); + } + + return skb; +} + +static int igb_run_xdp_zc(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp, struct xsk_buff_pool *xsk_pool, + struct bpf_prog *xdp_prog) +{ + int err, result = IGB_XDP_PASS; + u32 act; + + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + + act = bpf_prog_run_xdp(xdp_prog, xdp); + + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (!err) + return IGB_XDP_REDIR; + + if (xsk_uses_need_wakeup(xsk_pool) && + err == -ENOBUFS) + result = IGB_XDP_EXIT; + else + result = IGB_XDP_CONSUMED; + goto out_failure; + } + + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + result = igb_xdp_xmit_back(adapter, xdp); + if (result == IGB_XDP_CONSUMED) + goto out_failure; + break; + default: + bpf_warn_invalid_xdp_action(adapter->netdev, xdp_prog, act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; + case XDP_DROP: + result = IGB_XDP_CONSUMED; + break; + } + + return result; +} + +int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, + struct xsk_buff_pool *xsk_pool, const int budget) +{ + struct igb_adapter *adapter = q_vector->adapter; + unsigned int total_bytes = 0, total_packets = 0; + struct igb_ring *rx_ring = q_vector->rx.ring; + u32 ntc = rx_ring->next_to_clean; + struct bpf_prog *xdp_prog; + unsigned int xdp_xmit = 0; + bool failure = false; + u16 entries_to_alloc; + struct sk_buff *skb; + + /* xdp_prog cannot be NULL in the ZC path */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + while (likely(total_packets < budget)) { + union e1000_adv_rx_desc *rx_desc; + ktime_t timestamp = 0; + struct xdp_buff *xdp; + unsigned int size; + int xdp_res = 0; + + rx_desc = IGB_RX_DESC(rx_ring, ntc); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + xdp = rx_ring->rx_buffer_info_zc[ntc]; + xsk_buff_set_size(xdp, size); + xsk_buff_dma_sync_for_cpu(xdp); + + /* pull rx packet timestamp if available and valid */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + int ts_hdr_len; + + ts_hdr_len = igb_ptp_rx_pktstamp(rx_ring->q_vector, + xdp->data, + ×tamp); + + xdp->data += ts_hdr_len; + xdp->data_meta += ts_hdr_len; + size -= ts_hdr_len; + } + + xdp_res = igb_run_xdp_zc(adapter, rx_ring, xdp, xsk_pool, + xdp_prog); + + if (xdp_res) { + if (likely(xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR))) { + xdp_xmit |= xdp_res; + } else if (xdp_res == IGB_XDP_EXIT) { + failure = true; + break; + } else if (xdp_res == IGB_XDP_CONSUMED) { + xsk_buff_free(xdp); + } + + total_packets++; + total_bytes += size; + ntc++; + if (ntc == rx_ring->count) + ntc = 0; + continue; + } + + skb = igb_construct_skb_zc(rx_ring, xdp, timestamp); + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + break; + } + + xsk_buff_free(xdp); + ntc++; + if (ntc == rx_ring->count) + ntc = 0; + + if (eth_skb_pad(skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_bytes += skb->len; + + /* populate checksum, timestamp, VLAN, and protocol */ + igb_process_skb_fields(rx_ring, rx_desc, skb); + + napi_gro_receive(&q_vector->napi, skb); + + /* update budget accounting */ + total_packets++; + } + + rx_ring->next_to_clean = ntc; + + if (xdp_xmit) + igb_finalize_xdp(adapter, xdp_xmit); + + igb_update_rx_stats(q_vector, total_packets, total_bytes); + + entries_to_alloc = igb_desc_unused(rx_ring); + if (entries_to_alloc >= IGB_RX_BUFFER_WRITE) + failure |= !igb_alloc_rx_buffers_zc(rx_ring, xsk_pool, + entries_to_alloc); + + if (xsk_uses_need_wakeup(xsk_pool)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(xsk_pool); + else + xsk_clear_rx_need_wakeup(xsk_pool); + + return (int)total_packets; + } + return failure ? budget : (int)total_packets; +} + int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct igb_adapter *adapter = netdev_priv(dev); -- 2.50.1 From f8e284a02afc9797d5f626fc7dfb6f7d381d4e77 Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Mon, 6 Jan 2025 14:19:14 -0800 Subject: [PATCH 08/16] igb: Add AF_XDP zero-copy Tx support Add support for AF_XDP zero-copy transmit path. A new TX buffer type IGB_TYPE_XSK is introduced to indicate that the Tx frame was allocated from the xsk buff pool, so igb_clean_tx_ring() and igb_clean_tx_irq() can clean the buffers correctly based on type. igb_xmit_zc() performs the actual packet transmit when AF_XDP zero-copy is enabled. We share the TX ring between slow path, XDP and AF_XDP zero-copy, so we use the netdev queue lock to ensure mutual exclusion. Signed-off-by: Sriram Yagnaraman [Kurt: Set olinfo_status in igb_xmit_zc() so that frames are transmitted, Use READ_ONCE() for xsk_pool and check Tx disabled and carrier in igb_xmit_zc(), Add FIXME for RS bit] Signed-off-by: Kurt Kanzenbach Reviewed-by: Maciej Fijalkowski Tested-by: George Kuruvinakunnel Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-7-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb.h | 2 + drivers/net/ethernet/intel/igb/igb_main.c | 61 ++++++++++++++++++---- drivers/net/ethernet/intel/igb/igb_xsk.c | 63 +++++++++++++++++++++++ 3 files changed, 116 insertions(+), 10 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index e4a85867aa18..02f340280d20 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -258,6 +258,7 @@ enum igb_tx_flags { enum igb_tx_buf_type { IGB_TYPE_SKB = 0, IGB_TYPE_XDP, + IGB_TYPE_XSK }; /* wrapper around a pointer to a socket buffer, @@ -859,6 +860,7 @@ bool igb_alloc_rx_buffers_zc(struct igb_ring *rx_ring, void igb_clean_rx_ring_zc(struct igb_ring *rx_ring); int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, struct xsk_buff_pool *xsk_pool, const int budget); +bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool); int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); #endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b478b7818adb..a466e97d8ccd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2983,6 +2983,9 @@ static int igb_xdp_xmit(struct net_device *dev, int n, if (unlikely(!tx_ring)) return -ENXIO; + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return -ENXIO; + nq = txring_txq(tx_ring); __netif_tx_lock(nq, cpu); @@ -3330,7 +3333,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) netdev->priv_flags |= IFF_SUPP_NOFCS; netdev->priv_flags |= IFF_UNICAST_FLT; - netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT; + netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_XSK_ZEROCOPY; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; @@ -4904,15 +4908,20 @@ void igb_clean_tx_ring(struct igb_ring *tx_ring) { u16 i = tx_ring->next_to_clean; struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + u32 xsk_frames = 0; while (i != tx_ring->next_to_use) { union e1000_adv_tx_desc *eop_desc, *tx_desc; /* Free all the Tx ring sk_buffs or xdp frames */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { dev_kfree_skb_any(tx_buffer->skb); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -4943,6 +4952,7 @@ void igb_clean_tx_ring(struct igb_ring *tx_ring) DMA_TO_DEVICE); } +skip_for_xsk: tx_buffer->next_to_watch = NULL; /* move us one more past the eop_desc for start of next pkt */ @@ -4957,6 +4967,9 @@ void igb_clean_tx_ring(struct igb_ring *tx_ring) /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); + if (tx_ring->xsk_pool && xsk_frames) + xsk_tx_completed(tx_ring->xsk_pool, xsk_frames); + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -6490,6 +6503,9 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_BUSY; } + if (unlikely(test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags))) + return NETDEV_TX_BUSY; + /* record the location of the first descriptor for this packet */ first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; first->type = IGB_TYPE_SKB; @@ -8264,13 +8280,18 @@ static int igb_poll(struct napi_struct *napi, int budget) **/ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) { - struct igb_adapter *adapter = q_vector->adapter; - struct igb_ring *tx_ring = q_vector->tx.ring; - struct igb_tx_buffer *tx_buffer; - union e1000_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; + struct igb_adapter *adapter = q_vector->adapter; unsigned int budget = q_vector->tx.work_limit; + struct igb_ring *tx_ring = q_vector->tx.ring; unsigned int i = tx_ring->next_to_clean; + union e1000_adv_tx_desc *tx_desc; + struct igb_tx_buffer *tx_buffer; + struct xsk_buff_pool *xsk_pool; + int cpu = smp_processor_id(); + bool xsk_xmit_done = true; + struct netdev_queue *nq; + u32 xsk_frames = 0; if (test_bit(__IGB_DOWN, &adapter->state)) return true; @@ -8301,10 +8322,14 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) total_packets += tx_buffer->gso_segs; /* free the skb */ - if (tx_buffer->type == IGB_TYPE_SKB) + if (tx_buffer->type == IGB_TYPE_SKB) { napi_consume_skb(tx_buffer->skb, napi_budget); - else + } else if (tx_buffer->type == IGB_TYPE_XDP) { xdp_return_frame(tx_buffer->xdpf); + } else if (tx_buffer->type == IGB_TYPE_XSK) { + xsk_frames++; + goto skip_for_xsk; + } /* unmap skb header data */ dma_unmap_single(tx_ring->dev, @@ -8336,6 +8361,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } +skip_for_xsk: /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; tx_desc++; @@ -8364,6 +8390,21 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) q_vector->tx.total_bytes += total_bytes; q_vector->tx.total_packets += total_packets; + xsk_pool = READ_ONCE(tx_ring->xsk_pool); + if (xsk_pool) { + if (xsk_frames) + xsk_tx_completed(xsk_pool, xsk_frames); + if (xsk_uses_need_wakeup(xsk_pool)) + xsk_set_tx_need_wakeup(xsk_pool); + + nq = txring_txq(tx_ring); + __netif_tx_lock(nq, cpu); + /* Avoid transmit queue timeout since we share it with the slow path */ + txq_trans_cond_update(nq); + xsk_xmit_done = igb_xmit_zc(tx_ring, xsk_pool); + __netif_tx_unlock(nq); + } + if (test_bit(IGB_RING_FLAG_TX_DETECT_HANG, &tx_ring->flags)) { struct e1000_hw *hw = &adapter->hw; @@ -8426,7 +8467,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) } } - return !!budget; + return !!budget && xsk_xmit_done; } /** diff --git a/drivers/net/ethernet/intel/igb/igb_xsk.c b/drivers/net/ethernet/intel/igb/igb_xsk.c index 3d64a9f6360c..157d43787fa0 100644 --- a/drivers/net/ethernet/intel/igb/igb_xsk.c +++ b/drivers/net/ethernet/intel/igb/igb_xsk.c @@ -461,6 +461,69 @@ int igb_clean_rx_irq_zc(struct igb_q_vector *q_vector, return failure ? budget : (int)total_packets; } +bool igb_xmit_zc(struct igb_ring *tx_ring, struct xsk_buff_pool *xsk_pool) +{ + unsigned int budget = igb_desc_unused(tx_ring); + u32 cmd_type, olinfo_status, nb_pkts, i = 0; + struct xdp_desc *descs = xsk_pool->tx_descs; + union e1000_adv_tx_desc *tx_desc = NULL; + struct igb_tx_buffer *tx_buffer_info; + unsigned int total_bytes = 0; + dma_addr_t dma; + + if (!netif_carrier_ok(tx_ring->netdev)) + return true; + + if (test_bit(IGB_RING_FLAG_TX_DISABLED, &tx_ring->flags)) + return true; + + nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget); + if (!nb_pkts) + return true; + + while (nb_pkts-- > 0) { + dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); + xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len); + + tx_buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + tx_buffer_info->bytecount = descs[i].len; + tx_buffer_info->type = IGB_TYPE_XSK; + tx_buffer_info->xdpf = NULL; + tx_buffer_info->gso_segs = 1; + tx_buffer_info->time_stamp = jiffies; + + tx_desc = IGB_TX_DESC(tx_ring, tx_ring->next_to_use); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = E1000_ADVTXD_DTYP_DATA | E1000_ADVTXD_DCMD_DEXT | + E1000_ADVTXD_DCMD_IFCS; + olinfo_status = descs[i].len << E1000_ADVTXD_PAYLEN_SHIFT; + + /* FIXME: This sets the Report Status (RS) bit for every + * descriptor. One nice to have optimization would be to set it + * only for the last descriptor in the whole batch. See Intel + * ice driver for an example on how to do it. + */ + cmd_type |= descs[i].len | IGB_TXD_DCMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); + + total_bytes += descs[i].len; + + i++; + tx_ring->next_to_use++; + tx_buffer_info->next_to_watch = tx_desc; + if (tx_ring->next_to_use == tx_ring->count) + tx_ring->next_to_use = 0; + } + + netdev_tx_sent_queue(txring_txq(tx_ring), total_bytes); + igb_xdp_ring_update_tail(tx_ring); + + return nb_pkts < budget; +} + int igb_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct igb_adapter *adapter = netdev_priv(dev); -- 2.50.1 From 484d3675f2aa7710a4092411a203b719486e8666 Mon Sep 17 00:00:00 2001 From: Song Yoong Siang Date: Mon, 6 Jan 2025 14:19:15 -0800 Subject: [PATCH 09/16] igc: Allow hot-swapping XDP program Currently, the driver would always close and reopen the network interface when setting/removing the XDP program, regardless of the presence of XDP resources. This could cause unnecessary disruptions. To avoid this, introduces a check to determine if there is a need to close and reopen the interface, allowing for seamless hot-swapping of XDP programs. Signed-off-by: Song Yoong Siang Acked-by: Maciej Fijalkowski Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-8-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_xdp.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index e27af72aada8..869815f48ac1 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -13,6 +13,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, struct net_device *dev = adapter->netdev; bool if_running = netif_running(dev); struct bpf_prog *old_prog; + bool need_update; if (dev->mtu > ETH_DATA_LEN) { /* For now, the driver doesn't support XDP functionality with @@ -22,7 +23,8 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, return -EOPNOTSUPP; } - if (if_running) + need_update = !!adapter->xdp_prog != !!prog; + if (if_running && need_update) igc_close(dev); old_prog = xchg(&adapter->xdp_prog, prog); @@ -34,7 +36,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, else xdp_features_clear_redirect_target(dev); - if (if_running) + if (if_running && need_update) igc_open(dev); return 0; -- 2.50.1 From 8b6237e1f4d405737237882a19ee5f316763dff7 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 6 Jan 2025 14:19:16 -0800 Subject: [PATCH 10/16] igc: Fix passing 0 to ERR_PTR in igc_xdp_run_prog() igc_xdp_run_prog() converts customed xdp action to a negative error code with the sk_buff pointer type which be checked with IS_ERR in igc_clean_rx_irq(). Remove this error pointer handing instead use plain int return value to fix this smatch warnings: drivers/net/ethernet/intel/igc/igc_main.c:2533 igc_xdp_run_prog() warn: passing zero to 'ERR_PTR' Reviewed-by: Maciej Fijalkowski Reviewed-by: Jacob Keller Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-9-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_main.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index f58cd6940434..6832a8229a83 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2123,10 +2123,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) { struct net_device *netdev = rx_ring->netdev; @@ -2515,8 +2511,7 @@ out_failure: } } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp) { struct bpf_prog *prog; int res; @@ -2530,7 +2525,7 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, res = __igc_xdp_run_prog(adapter, prog, xdp); out: - return ERR_PTR(-res); + return res; } /* This function assumes __netif_tx_lock is held by the caller. */ @@ -2585,6 +2580,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = igc_desc_unused(rx_ring); int xdp_status = 0, rx_buffer_pgcnt; + int xdp_res = 0; while (likely(total_packets < budget)) { struct igc_xdp_buff ctx = { .rx_ts = NULL }; @@ -2630,12 +2626,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) xdp_buff_clear_frags_flag(&ctx.xdp); ctx.rx_desc = rx_desc; - skb = igc_xdp_run_prog(adapter, &ctx.xdp); + xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { switch (xdp_res) { case IGC_XDP_CONSUMED: rx_buffer->pagecnt_bias++; @@ -2657,7 +2651,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) skb = igc_construct_skb(rx_ring, rx_buffer, &ctx); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); @@ -2672,7 +2666,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igc_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } -- 2.50.1 From 8ae94669b1f3aca9079095415544f3e8b0e60e7e Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 6 Jan 2025 14:19:17 -0800 Subject: [PATCH 11/16] igb: Fix passing 0 to ERR_PTR in igb_run_xdp() igb_run_xdp() converts customed xdp action to a negative error code with the sk_buff pointer type which be checked with IS_ERR in igb_clean_rx_irq(). Remove this error pointer handing instead use plain int return value. Reviewed-by: Maciej Fijalkowski Reviewed-by: Jacob Keller Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-10-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igb/igb_main.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a466e97d8ccd..d368b753a467 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -8658,9 +8658,8 @@ static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, return skb; } -static struct sk_buff *igb_run_xdp(struct igb_adapter *adapter, - struct igb_ring *rx_ring, - struct xdp_buff *xdp) +static int igb_run_xdp(struct igb_adapter *adapter, struct igb_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IGB_XDP_PASS; struct bpf_prog *xdp_prog; @@ -8700,7 +8699,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int igb_rx_frame_truesize(struct igb_ring *rx_ring, @@ -8826,10 +8825,6 @@ static bool igb_cleanup_headers(struct igb_ring *rx_ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely((igb_test_staterr(rx_desc, E1000_RXDEXT_ERR_FRAME_ERR_MASK)))) { struct net_device *netdev = rx_ring->netdev; @@ -8983,6 +8978,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) struct xdp_buff xdp; u32 frame_sz = 0; int rx_buf_pgcnt; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -9040,12 +9036,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = igb_rx_frame_truesize(rx_ring, size); #endif - skb = igb_run_xdp(adapter, rx_ring, &xdp); + xdp_res = igb_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IGB_XDP_TX | IGB_XDP_REDIR)) { xdp_xmit |= xdp_res; igb_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -9064,7 +9058,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) &xdp, timestamp); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; break; @@ -9078,7 +9072,7 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igb_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igb_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } -- 2.50.1 From c824125cbb181507d2c5488232399d0767e143c7 Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 6 Jan 2025 14:19:18 -0800 Subject: [PATCH 12/16] ixgbe: Fix passing 0 to ERR_PTR in ixgbe_run_xdp() ixgbe_run_xdp() converts customed xdp action to a negative error code with the sk_buff pointer type which be checked with IS_ERR in ixgbe_clean_rx_irq(). Remove this error pointer handing instead use plain int return value. Reviewed-by: Jacob Keller Reviewed-by: Maciej Fijalkowski Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-11-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 23 ++++++++----------- 1 file changed, 9 insertions(+), 14 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 336e08d35f97..7236f20c9a30 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1923,10 +1923,6 @@ bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, { struct net_device *netdev = rx_ring->netdev; - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* Verify netdev is present, and that packet does not have any * errors that would be unacceptable to the netdev. */ @@ -2234,9 +2230,9 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, return skb; } -static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, - struct ixgbe_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) { int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; @@ -2286,7 +2282,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring, @@ -2344,6 +2340,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, unsigned int offset = rx_ring->rx_offset; unsigned int xdp_xmit = 0; struct xdp_buff xdp; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -2389,12 +2386,10 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size); #endif - skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + xdp_res = ixgbe_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { xdp_xmit |= xdp_res; ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -2414,7 +2409,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; @@ -2428,7 +2423,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) + if (xdp_res || ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) continue; /* probably a little skewed due to removing CRC */ -- 2.50.1 From 35f715cb77c3cb6e2033e71bf518b30705ab95ba Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Mon, 6 Jan 2025 14:19:19 -0800 Subject: [PATCH 13/16] ixgbevf: Fix passing 0 to ERR_PTR in ixgbevf_run_xdp() ixgbevf_run_xdp() converts customed xdp action to a negative error code with the sk_buff pointer type which be checked with IS_ERR in ixgbevf_clean_rx_irq(). Remove this error pointer handing instead use plain int return value. Reviewed-by: Jacob Keller Reviewed-by: Maciej Fijalkowski Signed-off-by: Yue Haibing Reviewed-by: Simon Horman Tested-by: Chandan Kumar Rout (A Contingent Worker at Intel) Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-12-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- .../net/ethernet/intel/ixgbevf/ixgbevf_main.c | 23 ++++++++----------- 1 file changed, 10 insertions(+), 13 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 2829bac9af94..6442f115a262 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -737,10 +737,6 @@ static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring, union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - /* verify that the packet does not have any known errors */ if (unlikely(ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) { @@ -1049,9 +1045,9 @@ static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring, return IXGBEVF_XDP_TX; } -static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, - struct ixgbevf_ring *rx_ring, - struct xdp_buff *xdp) +static int ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring, + struct xdp_buff *xdp) { int result = IXGBEVF_XDP_PASS; struct ixgbevf_ring *xdp_ring; @@ -1085,7 +1081,7 @@ out_failure: break; } xdp_out: - return ERR_PTR(-result); + return result; } static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring, @@ -1127,6 +1123,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, struct sk_buff *skb = rx_ring->skb; bool xdp_xmit = false; struct xdp_buff xdp; + int xdp_res = 0; /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ #if (PAGE_SIZE < 8192) @@ -1170,11 +1167,11 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, /* At larger PAGE_SIZE, frame_sz depend on len size */ xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size); #endif - skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp); + xdp_res = ixgbevf_run_xdp(adapter, rx_ring, &xdp); } - if (IS_ERR(skb)) { - if (PTR_ERR(skb) == -IXGBEVF_XDP_TX) { + if (xdp_res) { + if (xdp_res == IXGBEVF_XDP_TX) { xdp_xmit = true; ixgbevf_rx_buffer_flip(rx_ring, rx_buffer, size); @@ -1194,7 +1191,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, } /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_rx_buff_failed++; rx_buffer->pagecnt_bias++; break; @@ -1208,7 +1205,7 @@ static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, continue; /* verify the packet layout is correct */ - if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } -- 2.50.1 From 07af482e646539d3cc12bc85040fe02f39ae3761 Mon Sep 17 00:00:00 2001 From: Aleksandr Loktionov Date: Mon, 6 Jan 2025 14:19:20 -0800 Subject: [PATCH 14/16] i40e: add ability to reset VF for Tx and Rx MDD events Implement "mdd-auto-reset-vf" priv-flag to handle Tx and Rx MDD events for VFs. This flag is also used in other network adapters like ICE. Usage: - "on" - The problematic VF will be automatically reset if a malformed descriptor is detected. - "off" - The problematic VF will be disabled. In cases where a VF sends malformed packets classified as malicious, it can cause the Tx queue to freeze, rendering it unusable for several minutes. When an MDD event occurs, this new implementation allows for a graceful VF reset to quickly restore operational state. Currently, VF queues are disabled if an MDD event occurs. This patch adds the ability to reset the VF if a Tx or Rx MDD event occurs. It also includes MDD event logging throttling to avoid dmesg pollution and unifies the format of Tx and Rx MDD messages. Note: Standard message rate limiting functions like dev_info_ratelimited() do not meet our requirements. Custom rate limiting is implemented, please see the code for details. Co-developed-by: Jan Sokolowski Signed-off-by: Jan Sokolowski Co-developed-by: Padraig J Connolly Signed-off-by: Padraig J Connolly Signed-off-by: Aleksandr Loktionov Reviewed-by: Michal Schmidt Tested-by: Rafal Romanowski Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-13-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- .../device_drivers/ethernet/intel/i40e.rst | 12 ++ drivers/net/ethernet/intel/i40e/i40e.h | 4 +- .../net/ethernet/intel/i40e/i40e_debugfs.c | 2 +- .../net/ethernet/intel/i40e/i40e_ethtool.c | 2 + drivers/net/ethernet/intel/i40e/i40e_main.c | 107 +++++++++++++++--- .../ethernet/intel/i40e/i40e_virtchnl_pf.c | 2 +- .../ethernet/intel/i40e/i40e_virtchnl_pf.h | 11 +- 7 files changed, 123 insertions(+), 17 deletions(-) diff --git a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst index 4fbaa1a2d674..53d9d5829d69 100644 --- a/Documentation/networking/device_drivers/ethernet/intel/i40e.rst +++ b/Documentation/networking/device_drivers/ethernet/intel/i40e.rst @@ -299,6 +299,18 @@ Use ethtool to view and set link-down-on-close, as follows:: ethtool --show-priv-flags ethX ethtool --set-priv-flags ethX link-down-on-close [on|off] +Setting the mdd-auto-reset-vf Private Flag +------------------------------------------ + +When the mdd-auto-reset-vf private flag is set to "on", the problematic VF will +be automatically reset if a malformed descriptor is detected. If the flag is +set to "off", the problematic VF will be disabled. + +Use ethtool to view and set mdd-auto-reset-vf, as follows:: + + ethtool --show-priv-flags ethX + ethtool --set-priv-flags ethX mdd-auto-reset-vf [on|off] + Viewing Link Messages --------------------- Link messages will not be displayed to the console if the distribution is diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index ce63a7cfe955..c67963bfe14e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -88,6 +88,7 @@ enum i40e_state { __I40E_SERVICE_SCHED, __I40E_ADMINQ_EVENT_PENDING, __I40E_MDD_EVENT_PENDING, + __I40E_MDD_VF_PRINT_PENDING, __I40E_VFLR_EVENT_PENDING, __I40E_RESET_RECOVERY_PENDING, __I40E_TIMEOUT_RECOVERY_PENDING, @@ -191,6 +192,7 @@ enum i40e_pf_flags { */ I40E_FLAG_TOTAL_PORT_SHUTDOWN_ENA, I40E_FLAG_VF_VLAN_PRUNING_ENA, + I40E_FLAG_MDD_AUTO_RESET_VF, I40E_PF_FLAGS_NBITS, /* must be last */ }; @@ -572,7 +574,7 @@ struct i40e_pf { int num_alloc_vfs; /* actual number of VFs allocated */ u32 vf_aq_requests; u32 arq_overflows; /* Not fatal, possibly indicative of problems */ - + struct ratelimit_state mdd_message_rate_limit; /* DCBx/DCBNL capability for PF that indicates * whether DCBx is managed by firmware or host * based agent (LLDPAD). Also, indicates what diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 208c2f0857b6..6cd9da662ae1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -722,7 +722,7 @@ static void i40e_dbg_dump_vf(struct i40e_pf *pf, int vf_id) dev_info(&pf->pdev->dev, "vf %2d: VSI id=%d, seid=%d, qps=%d\n", vf_id, vf->lan_vsi_id, vsi->seid, vf->num_queue_pairs); dev_info(&pf->pdev->dev, " num MDD=%lld\n", - vf->num_mdd_events); + vf->mdd_tx_events.count + vf->mdd_rx_events.count); } else { dev_info(&pf->pdev->dev, "invalid VF id %d\n", vf_id); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index bce5b76f1e7a..8a7a83f83ee5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -459,6 +459,8 @@ static const struct i40e_priv_flags i40e_gstrings_priv_flags[] = { I40E_PRIV_FLAG("base-r-fec", I40E_FLAG_BASE_R_FEC, 0), I40E_PRIV_FLAG("vf-vlan-pruning", I40E_FLAG_VF_VLAN_PRUNING_ENA, 0), + I40E_PRIV_FLAG("mdd-auto-reset-vf", + I40E_FLAG_MDD_AUTO_RESET_VF, 0), }; #define I40E_PRIV_FLAGS_STR_LEN ARRAY_SIZE(i40e_gstrings_priv_flags) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 8a333d0e2218..65a702668e21 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -11179,6 +11179,67 @@ static void i40e_handle_reset_warning(struct i40e_pf *pf, bool lock_acquired) i40e_reset_and_rebuild(pf, false, lock_acquired); } +/** + * i40e_print_vf_mdd_event - print VF Tx/Rx malicious driver detect event + * @pf: board private structure + * @vf: pointer to the VF structure + * @is_tx: true - for Tx event, false - for Rx + */ +static void i40e_print_vf_mdd_event(struct i40e_pf *pf, struct i40e_vf *vf, + bool is_tx) +{ + dev_err(&pf->pdev->dev, is_tx ? + "%lld Tx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n" : + "%lld Rx Malicious Driver Detection events detected on PF %d VF %d MAC %pm. mdd-auto-reset-vfs=%s\n", + is_tx ? vf->mdd_tx_events.count : vf->mdd_rx_events.count, + pf->hw.pf_id, + vf->vf_id, + vf->default_lan_addr.addr, + str_on_off(test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags))); +} + +/** + * i40e_print_vfs_mdd_events - print VFs malicious driver detect event + * @pf: pointer to the PF structure + * + * Called from i40e_handle_mdd_event to rate limit and print VFs MDD events. + */ +static void i40e_print_vfs_mdd_events(struct i40e_pf *pf) +{ + unsigned int i; + + /* check that there are pending MDD events to print */ + if (!test_and_clear_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state)) + return; + + if (!__ratelimit(&pf->mdd_message_rate_limit)) + return; + + for (i = 0; i < pf->num_alloc_vfs; i++) { + struct i40e_vf *vf = &pf->vf[i]; + bool is_printed = false; + + /* only print Rx MDD event message if there are new events */ + if (vf->mdd_rx_events.count != vf->mdd_rx_events.last_printed) { + vf->mdd_rx_events.last_printed = vf->mdd_rx_events.count; + i40e_print_vf_mdd_event(pf, vf, false); + is_printed = true; + } + + /* only print Tx MDD event message if there are new events */ + if (vf->mdd_tx_events.count != vf->mdd_tx_events.last_printed) { + vf->mdd_tx_events.last_printed = vf->mdd_tx_events.count; + i40e_print_vf_mdd_event(pf, vf, true); + is_printed = true; + } + + if (is_printed && !test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) + dev_info(&pf->pdev->dev, + "Use PF Control I/F to re-enable the VF #%d\n", + i); + } +} + /** * i40e_handle_mdd_event * @pf: pointer to the PF structure @@ -11193,8 +11254,13 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) u32 reg; int i; - if (!test_bit(__I40E_MDD_EVENT_PENDING, pf->state)) + if (!test_and_clear_bit(__I40E_MDD_EVENT_PENDING, pf->state)) { + /* Since the VF MDD event logging is rate limited, check if + * there are pending MDD events. + */ + i40e_print_vfs_mdd_events(pf); return; + } /* find what triggered the MDD event */ reg = rd32(hw, I40E_GL_MDET_TX); @@ -11238,36 +11304,48 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) /* see if one of the VFs needs its hand slapped */ for (i = 0; i < pf->num_alloc_vfs && mdd_detected; i++) { + bool is_mdd_on_tx = false; + bool is_mdd_on_rx = false; + vf = &(pf->vf[i]); reg = rd32(hw, I40E_VP_MDET_TX(i)); if (reg & I40E_VP_MDET_TX_VALID_MASK) { + set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state); wr32(hw, I40E_VP_MDET_TX(i), 0xFFFF); - vf->num_mdd_events++; - dev_info(&pf->pdev->dev, "TX driver issue detected on VF %d\n", - i); - dev_info(&pf->pdev->dev, - "Use PF Control I/F to re-enable the VF\n"); + vf->mdd_tx_events.count++; set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + is_mdd_on_tx = true; } reg = rd32(hw, I40E_VP_MDET_RX(i)); if (reg & I40E_VP_MDET_RX_VALID_MASK) { + set_bit(__I40E_MDD_VF_PRINT_PENDING, pf->state); wr32(hw, I40E_VP_MDET_RX(i), 0xFFFF); - vf->num_mdd_events++; - dev_info(&pf->pdev->dev, "RX driver issue detected on VF %d\n", - i); - dev_info(&pf->pdev->dev, - "Use PF Control I/F to re-enable the VF\n"); + vf->mdd_rx_events.count++; set_bit(I40E_VF_STATE_DISABLED, &vf->vf_states); + is_mdd_on_rx = true; + } + + if ((is_mdd_on_tx || is_mdd_on_rx) && + test_bit(I40E_FLAG_MDD_AUTO_RESET_VF, pf->flags)) { + /* VF MDD event counters will be cleared by + * reset, so print the event prior to reset. + */ + if (is_mdd_on_rx) + i40e_print_vf_mdd_event(pf, vf, false); + if (is_mdd_on_tx) + i40e_print_vf_mdd_event(pf, vf, true); + + i40e_vc_reset_vf(vf, true); } } - /* re-enable mdd interrupt cause */ - clear_bit(__I40E_MDD_EVENT_PENDING, pf->state); reg = rd32(hw, I40E_PFINT_ICR0_ENA); reg |= I40E_PFINT_ICR0_ENA_MAL_DETECT_MASK; wr32(hw, I40E_PFINT_ICR0_ENA, reg); i40e_flush(hw); + + i40e_print_vfs_mdd_events(pf); } /** @@ -15878,6 +15956,9 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ERR_PTR(err), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); + /* VF MDD event logs are rate limited to one second intervals */ + ratelimit_state_init(&pf->mdd_message_rate_limit, 1 * HZ, 1); + /* Reconfigure hardware for allowing smaller MSS in the case * of TSO, so that we avoid the MDD being fired and causing * a reset in the case of small MSS+TSO. diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index dfa785e39458..1120f8e4bb67 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -216,7 +216,7 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf) * @notify_vf: notify vf about reset or not * Reset VF handler. **/ -static void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) +void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf) { struct i40e_pf *pf = vf->pf; int i; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 66f95e2f3146..5cf74f16f433 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -64,6 +64,12 @@ struct i40evf_channel { u64 max_tx_rate; /* bandwidth rate allocation for VSIs */ }; +struct i40e_mdd_vf_events { + u64 count; /* total count of Rx|Tx events */ + /* count number of the last printed event */ + u64 last_printed; +}; + /* VF information structure */ struct i40e_vf { struct i40e_pf *pf; @@ -92,7 +98,9 @@ struct i40e_vf { u8 num_queue_pairs; /* num of qps assigned to VF vsis */ u8 num_req_queues; /* num of requested qps */ - u64 num_mdd_events; /* num of mdd events detected */ + /* num of mdd tx and rx events detected */ + struct i40e_mdd_vf_events mdd_rx_events; + struct i40e_mdd_vf_events mdd_tx_events; unsigned long vf_caps; /* vf's adv. capabilities */ unsigned long vf_states; /* vf's runtime states */ @@ -120,6 +128,7 @@ int i40e_alloc_vfs(struct i40e_pf *pf, u16 num_alloc_vfs); int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen); int i40e_vc_process_vflr_event(struct i40e_pf *pf); +void i40e_vc_reset_vf(struct i40e_vf *vf, bool notify_vf); bool i40e_reset_vf(struct i40e_vf *vf, bool flr); bool i40e_reset_all_vfs(struct i40e_pf *pf, bool flr); void i40e_vc_notify_vf_reset(struct i40e_vf *vf); -- 2.50.1 From 1a63399c13fe557e791e73468e90b3484faa1e84 Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Mon, 6 Jan 2025 14:19:21 -0800 Subject: [PATCH 15/16] igc: Link IRQs to NAPI instances Link IRQs to NAPI instances via netdev-genl API so that users can query this information with netlink. Compare the output of /proc/interrupts (noting that IRQ 128 is the "other" IRQ which does not appear to have a NAPI instance): $ cat /proc/interrupts | grep enp86s0 | cut --delimiter=":" -f1 128 129 130 131 132 The output from netlink shows the mapping of NAPI IDs to IRQs (again noting that 128 is absent as it is the "other" IRQ): $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \ --dump napi-get --json='{"ifindex": 2}' [{'defer-hard-irqs': 0, 'gro-flush-timeout': 0, 'id': 8196, 'ifindex': 2, 'irq': 132}, {'defer-hard-irqs': 0, 'gro-flush-timeout': 0, 'id': 8195, 'ifindex': 2, 'irq': 131}, {'defer-hard-irqs': 0, 'gro-flush-timeout': 0, 'id': 8194, 'ifindex': 2, 'irq': 130}, {'defer-hard-irqs': 0, 'gro-flush-timeout': 0, 'id': 8193, 'ifindex': 2, 'irq': 129}] Signed-off-by: Joe Damato Reviewed-by: Vitaly Lifshits Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-14-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc_main.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 6832a8229a83..d9542015e871 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5570,6 +5570,9 @@ static int igc_request_msix(struct igc_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igc_configure_msix(adapter); -- 2.50.1 From b65969856d4f98fa9142c107e3f6c9ab4b6c71cf Mon Sep 17 00:00:00 2001 From: Joe Damato Date: Mon, 6 Jan 2025 14:19:22 -0800 Subject: [PATCH 16/16] igc: Link queues to NAPI instances Link queues to NAPI instances via netdev-genl API so that users can query this information with netlink. Handle a few cases in the driver: 1. Link/unlink the NAPIs when XDP is enabled/disabled 2. Handle IGC_FLAG_QUEUE_PAIRS enabled and disabled Example output when IGC_FLAG_QUEUE_PAIRS is enabled: $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \ --dump queue-get --json='{"ifindex": 2}' [{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'}, {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'rx'}, {'id': 2, 'ifindex': 2, 'napi-id': 8195, 'type': 'rx'}, {'id': 3, 'ifindex': 2, 'napi-id': 8196, 'type': 'rx'}, {'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'tx'}, {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'tx'}, {'id': 2, 'ifindex': 2, 'napi-id': 8195, 'type': 'tx'}, {'id': 3, 'ifindex': 2, 'napi-id': 8196, 'type': 'tx'}] Since IGC_FLAG_QUEUE_PAIRS is enabled, you'll note that the same NAPI ID is present for both rx and tx queues at the same index, for example index 0: {'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'}, {'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'tx'}, To test IGC_FLAG_QUEUE_PAIRS disabled, a test system was booted using the grub command line option "maxcpus=2" to force igc_set_interrupt_capability to disable IGC_FLAG_QUEUE_PAIRS. Example output when IGC_FLAG_QUEUE_PAIRS is disabled: $ lscpu | grep "On-line CPU" On-line CPU(s) list: 0,2 $ ethtool -l enp86s0 | tail -5 Current hardware settings: RX: n/a TX: n/a Other: 1 Combined: 2 $ cat /proc/interrupts | grep enp 144: [...] enp86s0 145: [...] enp86s0-rx-0 146: [...] enp86s0-rx-1 147: [...] enp86s0-tx-0 148: [...] enp86s0-tx-1 1 "other" IRQ, and 2 IRQs for each of RX and Tx, so we expect netlink to report 4 IRQs with unique NAPI IDs: $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \ --dump napi-get --json='{"ifindex": 2}' [{'id': 8196, 'ifindex': 2, 'irq': 148}, {'id': 8195, 'ifindex': 2, 'irq': 147}, {'id': 8194, 'ifindex': 2, 'irq': 146}, {'id': 8193, 'ifindex': 2, 'irq': 145}] Now we examine which queues these NAPIs are associated with, expecting that since IGC_FLAG_QUEUE_PAIRS is disabled each RX and TX queue will have its own NAPI instance: $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \ --dump queue-get --json='{"ifindex": 2}' [{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'}, {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'rx'}, {'id': 0, 'ifindex': 2, 'napi-id': 8195, 'type': 'tx'}, {'id': 1, 'ifindex': 2, 'napi-id': 8196, 'type': 'tx'}] Signed-off-by: Joe Damato Reviewed-by: Vitaly Lifshits Tested-by: Avigail Dahan Signed-off-by: Tony Nguyen Link: https://patch.msgid.link/20250106221929.956999-15-anthony.l.nguyen@intel.com Signed-off-by: Jakub Kicinski --- drivers/net/ethernet/intel/igc/igc.h | 2 + drivers/net/ethernet/intel/igc/igc_main.c | 56 +++++++++++++++++++---- drivers/net/ethernet/intel/igc/igc_xdp.c | 2 + 3 files changed, 51 insertions(+), 9 deletions(-) diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index eac0f966e0e4..b8111ad9a9a8 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -337,6 +337,8 @@ struct igc_adapter { struct igc_led_classdev *leds; }; +void igc_set_queue_napi(struct igc_adapter *adapter, int q_idx, + struct napi_struct *napi); void igc_up(struct igc_adapter *adapter); void igc_down(struct igc_adapter *adapter); int igc_open(struct net_device *netdev); diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index d9542015e871..56a35d58e7a6 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4942,6 +4942,22 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } +void igc_set_queue_napi(struct igc_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igc_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -4949,6 +4965,7 @@ static int igc_sw_init(struct igc_adapter *adapter) void igc_up(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int i = 0; /* hardware has been reset, we need to reload some things */ @@ -4956,8 +4973,11 @@ void igc_up(struct igc_adapter *adapter) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } if (adapter->msix_entries) igc_configure_msix(adapter); @@ -5186,6 +5206,7 @@ void igc_down(struct igc_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igc_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } @@ -6015,6 +6036,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) struct igc_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int err = 0; int i = 0; @@ -6050,8 +6072,11 @@ static int __igc_open(struct net_device *netdev, bool resuming) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(IGC_ICR); @@ -7296,7 +7321,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int igc_resume(struct device *dev) +static int __igc_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7339,7 +7364,11 @@ static int igc_resume(struct device *dev) wr32(IGC_WUS, ~0); if (netif_running(netdev)) { + if (!rpm) + rtnl_lock(); err = __igc_open(netdev, true); + if (!rpm) + rtnl_unlock(); if (!err) netif_device_attach(netdev); } @@ -7347,9 +7376,14 @@ static int igc_resume(struct device *dev) return err; } +static int igc_resume(struct device *dev) +{ + return __igc_resume(dev, false); +} + static int igc_runtime_resume(struct device *dev) { - return igc_resume(dev); + return __igc_resume(dev, true); } static int igc_suspend(struct device *dev) @@ -7394,14 +7428,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igc_adapter *adapter = netdev_priv(netdev); + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) igc_down(adapter); pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -7412,7 +7450,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igc_resume routine. + * resembles the first-half of the __igc_resume routine. **/ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) { @@ -7451,7 +7489,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the igc_resume routine. + * second-half of the __igc_resume routine. */ static void igc_io_resume(struct pci_dev *pdev) { diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index 869815f48ac1..13bbd3346e01 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -86,6 +86,7 @@ static int igc_xdp_enable_pool(struct igc_adapter *adapter, napi_disable(napi); } + igc_set_queue_napi(adapter, queue_id, NULL); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); set_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); @@ -135,6 +136,7 @@ static int igc_xdp_disable_pool(struct igc_adapter *adapter, u16 queue_id) xsk_pool_dma_unmap(pool, IGC_RX_DMA_ATTR); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &rx_ring->flags); clear_bit(IGC_RING_FLAG_AF_XDP_ZC, &tx_ring->flags); + igc_set_queue_napi(adapter, queue_id, napi); if (needs_reset) { napi_enable(napi); -- 2.50.1