diff options
Diffstat (limited to 'include')
147 files changed, 3174 insertions, 1145 deletions
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 1dfadb2e878d..76a0f16e56cf 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -130,18 +130,24 @@ static inline bool init_section_intersects(void *virt, size_t size) /** * is_kernel_core_data - checks if the pointer address is located in the - * .data section + * .data or .bss section * * @addr: address to check * - * Returns: true if the address is located in .data, false otherwise. + * Returns: true if the address is located in .data or .bss, false otherwise. * Note: On some archs it may return true for core RODATA, and false * for others. But will always be true for core RW data. */ static inline bool is_kernel_core_data(unsigned long addr) { - return addr >= (unsigned long)_sdata && - addr < (unsigned long)_edata; + if (addr >= (unsigned long)_sdata && addr < (unsigned long)_edata) + return true; + + if (addr >= (unsigned long)__bss_start && + addr < (unsigned long)__bss_stop) + return true; + + return false; } /** diff --git a/include/linux/atalk.h b/include/linux/atalk.h index f6034ba774be..a55bfc6567d0 100644 --- a/include/linux/atalk.h +++ b/include/linux/atalk.h @@ -113,7 +113,7 @@ extern int aarp_proto_init(void); /* Inter module exports */ /* Give a device find its atif control structure */ -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) static inline struct atalk_iface *atalk_find_dev(struct net_device *dev) { return dev->atalk_ptr; diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index b30a1bc74fc7..2ce27e8e4f19 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -141,6 +141,13 @@ enum virtchnl_ops { VIRTCHNL_OP_DEL_RSS_CFG = 46, VIRTCHNL_OP_ADD_FDIR_FILTER = 47, VIRTCHNL_OP_DEL_FDIR_FILTER = 48, + VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS = 51, + VIRTCHNL_OP_ADD_VLAN_V2 = 52, + VIRTCHNL_OP_DEL_VLAN_V2 = 53, + VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 = 54, + VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55, + VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56, + VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57, VIRTCHNL_OP_MAX, }; @@ -246,6 +253,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) #define VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 BIT(18) @@ -475,6 +483,351 @@ struct virtchnl_vlan_filter_list { VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list); +/* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related + * structures and opcodes. + * + * VIRTCHNL_VLAN_UNSUPPORTED - This field is not supported and if a VF driver + * populates it the PF should return VIRTCHNL_STATUS_ERR_NOT_SUPPORTED. + * + * VIRTCHNL_VLAN_ETHERTYPE_8100 - This field supports 0x8100 ethertype. + * VIRTCHNL_VLAN_ETHERTYPE_88A8 - This field supports 0x88A8 ethertype. + * VIRTCHNL_VLAN_ETHERTYPE_9100 - This field supports 0x9100 ethertype. + * + * VIRTCHNL_VLAN_ETHERTYPE_AND - Used when multiple ethertypes can be supported + * by the PF concurrently. For example, if the PF can support + * VIRTCHNL_VLAN_ETHERTYPE_8100 AND VIRTCHNL_VLAN_ETHERTYPE_88A8 filters it + * would OR the following bits: + * + * VIRTHCNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * The VF would interpret this as VLAN filtering can be supported on both 0x8100 + * and 0x88A8 VLAN ethertypes. + * + * VIRTCHNL_ETHERTYPE_XOR - Used when only a single ethertype can be supported + * by the PF concurrently. For example if the PF can support + * VIRTCHNL_VLAN_ETHERTYPE_8100 XOR VIRTCHNL_VLAN_ETHERTYPE_88A8 stripping + * offload it would OR the following bits: + * + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * The VF would interpret this as VLAN stripping can be supported on either + * 0x8100 or 0x88a8 VLAN ethertypes. So when requesting VLAN stripping via + * VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 the specified ethertype will override + * the previously set value. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1 - Used to tell the VF to insert and/or + * strip the VLAN tag using the L2TAG1 field of the Tx/Rx descriptors. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 - Used to tell the VF to insert hardware + * offloaded VLAN tags using the L2TAG2 field of the Tx descriptor. + * + * VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 - Used to tell the VF to strip hardware + * offloaded VLAN tags using the L2TAG2_2 field of the Rx descriptor. + * + * VIRTCHNL_VLAN_PRIO - This field supports VLAN priority bits. This is used for + * VLAN filtering if the underlying PF supports it. + * + * VIRTCHNL_VLAN_TOGGLE_ALLOWED - This field is used to say whether a + * certain VLAN capability can be toggled. For example if the underlying PF/CP + * allows the VF to toggle VLAN filtering, stripping, and/or insertion it should + * set this bit along with the supported ethertypes. + */ +enum virtchnl_vlan_support { + VIRTCHNL_VLAN_UNSUPPORTED = 0, + VIRTCHNL_VLAN_ETHERTYPE_8100 = BIT(0), + VIRTCHNL_VLAN_ETHERTYPE_88A8 = BIT(1), + VIRTCHNL_VLAN_ETHERTYPE_9100 = BIT(2), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1 = BIT(8), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2 = BIT(9), + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2 = BIT(10), + VIRTCHNL_VLAN_PRIO = BIT(24), + VIRTCHNL_VLAN_FILTER_MASK = BIT(28), + VIRTCHNL_VLAN_ETHERTYPE_AND = BIT(29), + VIRTCHNL_VLAN_ETHERTYPE_XOR = BIT(30), + VIRTCHNL_VLAN_TOGGLE = BIT(31), +}; + +/* This structure is used as part of the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS + * for filtering, insertion, and stripping capabilities. + * + * If only outer capabilities are supported (for filtering, insertion, and/or + * stripping) then this refers to the outer most or single VLAN from the VF's + * perspective. + * + * If only inner capabilities are supported (for filtering, insertion, and/or + * stripping) then this refers to the outer most or single VLAN from the VF's + * perspective. Functionally this is the same as if only outer capabilities are + * supported. The VF driver is just forced to use the inner fields when + * adding/deleting filters and enabling/disabling offloads (if supported). + * + * If both outer and inner capabilities are supported (for filtering, insertion, + * and/or stripping) then outer refers to the outer most or single VLAN and + * inner refers to the second VLAN, if it exists, in the packet. + * + * There is no support for tunneled VLAN offloads, so outer or inner are never + * referring to a tunneled packet from the VF's perspective. + */ +struct virtchnl_vlan_supported_caps { + u32 outer; + u32 inner; +}; + +/* The PF populates these fields based on the supported VLAN filtering. If a + * field is VIRTCHNL_VLAN_UNSUPPORTED then it's not supported and the PF will + * reject any VIRTCHNL_OP_ADD_VLAN_V2 or VIRTCHNL_OP_DEL_VLAN_V2 messages using + * the unsupported fields. + * + * Also, a VF is only allowed to toggle its VLAN filtering setting if the + * VIRTCHNL_VLAN_TOGGLE bit is set. + * + * The ethertype(s) specified in the ethertype_init field are the ethertypes + * enabled for VLAN filtering. VLAN filtering in this case refers to the outer + * most VLAN from the VF's perspective. If both inner and outer filtering are + * allowed then ethertype_init only refers to the outer most VLAN as only + * VLAN ethertype supported for inner VLAN filtering is + * VIRTCHNL_VLAN_ETHERTYPE_8100. By default, inner VLAN filtering is disabled + * when both inner and outer filtering are allowed. + * + * The max_filters field tells the VF how many VLAN filters it's allowed to have + * at any one time. If it exceeds this amount and tries to add another filter, + * then the request will be rejected by the PF. To prevent failures, the VF + * should keep track of how many VLAN filters it has added and not attempt to + * add more than max_filters. + */ +struct virtchnl_vlan_filtering_caps { + struct virtchnl_vlan_supported_caps filtering_support; + u32 ethertype_init; + u16 max_filters; + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vlan_filtering_caps); + +/* This enum is used for the virtchnl_vlan_offload_caps structure to specify + * if the PF supports a different ethertype for stripping and insertion. + * + * VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION - The ethertype(s) specified + * for stripping affect the ethertype(s) specified for insertion and visa versa + * as well. If the VF tries to configure VLAN stripping via + * VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 with VIRTCHNL_VLAN_ETHERTYPE_8100 then + * that will be the ethertype for both stripping and insertion. + * + * VIRTCHNL_ETHERTYPE_MATCH_NOT_REQUIRED - The ethertype(s) specified for + * stripping do not affect the ethertype(s) specified for insertion and visa + * versa. + */ +enum virtchnl_vlan_ethertype_match { + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION = 0, + VIRTCHNL_ETHERTYPE_MATCH_NOT_REQUIRED = 1, +}; + +/* The PF populates these fields based on the supported VLAN offloads. If a + * field is VIRTCHNL_VLAN_UNSUPPORTED then it's not supported and the PF will + * reject any VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 or + * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 messages using the unsupported fields. + * + * Also, a VF is only allowed to toggle its VLAN offload setting if the + * VIRTCHNL_VLAN_TOGGLE_ALLOWED bit is set. + * + * The VF driver needs to be aware of how the tags are stripped by hardware and + * inserted by the VF driver based on the level of offload support. The PF will + * populate these fields based on where the VLAN tags are expected to be + * offloaded via the VIRTHCNL_VLAN_TAG_LOCATION_* bits. The VF will need to + * interpret these fields. See the definition of the + * VIRTCHNL_VLAN_TAG_LOCATION_* bits above the virtchnl_vlan_support + * enumeration. + */ +struct virtchnl_vlan_offload_caps { + struct virtchnl_vlan_supported_caps stripping_support; + struct virtchnl_vlan_supported_caps insertion_support; + u32 ethertype_init; + u8 ethertype_match; + u8 pad[3]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_vlan_offload_caps); + +/* VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS + * VF sends this message to determine its VLAN capabilities. + * + * PF will mark which capabilities it supports based on hardware support and + * current configuration. For example, if a port VLAN is configured the PF will + * not allow outer VLAN filtering, stripping, or insertion to be configured so + * it will block these features from the VF. + * + * The VF will need to cross reference its capabilities with the PFs + * capabilities in the response message from the PF to determine the VLAN + * support. + */ +struct virtchnl_vlan_caps { + struct virtchnl_vlan_filtering_caps filtering; + struct virtchnl_vlan_offload_caps offloads; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_caps); + +struct virtchnl_vlan { + u16 tci; /* tci[15:13] = PCP and tci[11:0] = VID */ + u16 tci_mask; /* only valid if VIRTCHNL_VLAN_FILTER_MASK set in + * filtering caps + */ + u16 tpid; /* 0x8100, 0x88a8, etc. and only type(s) set in + * filtering caps. Note that tpid here does not refer to + * VIRTCHNL_VLAN_ETHERTYPE_*, but it refers to the + * actual 2-byte VLAN TPID + */ + u8 pad[2]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan); + +struct virtchnl_vlan_filter { + struct virtchnl_vlan inner; + struct virtchnl_vlan outer; + u8 pad[16]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(32, virtchnl_vlan_filter); + +/* VIRTCHNL_OP_ADD_VLAN_V2 + * VIRTCHNL_OP_DEL_VLAN_V2 + * + * VF sends these messages to add/del one or more VLAN tag filters for Rx + * traffic. + * + * The PF attempts to add the filters and returns status. + * + * The VF should only ever attempt to add/del virtchnl_vlan_filter(s) using the + * supported fields negotiated via VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS. + */ +struct virtchnl_vlan_filter_list_v2 { + u16 vport_id; + u16 num_elements; + u8 pad[4]; + struct virtchnl_vlan_filter filters[1]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2); + +/* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 + * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 + * VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 + * VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 + * + * VF sends this message to enable or disable VLAN stripping or insertion. It + * also needs to specify an ethertype. The VF knows which VLAN ethertypes are + * allowed and whether or not it's allowed to enable/disable the specific + * offload via the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS message. The VF needs to + * parse the virtchnl_vlan_caps.offloads fields to determine which offload + * messages are allowed. + * + * For example, if the PF populates the virtchnl_vlan_caps.offloads in the + * following manner the VF will be allowed to enable and/or disable 0x8100 inner + * VLAN insertion and/or stripping via the opcodes listed above. Inner in this + * case means the outer most or single VLAN from the VF's perspective. This is + * because no outer offloads are supported. See the comments above the + * virtchnl_vlan_supported_caps structure for more details. + * + * virtchnl_vlan_caps.offloads.stripping_support.inner = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * virtchnl_vlan_caps.offloads.insertion_support.inner = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * In order to enable inner (again note that in this case inner is the outer + * most or single VLAN from the VF's perspective) VLAN stripping for 0x8100 + * VLANs, the VF would populate the virtchnl_vlan_setting structure in the + * following manner and send the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 message. + * + * virtchnl_vlan_setting.inner_ethertype_setting = + * VIRTCHNL_VLAN_ETHERTYPE_8100; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + * + * The reason that VLAN TPID(s) are not being used for the + * outer_ethertype_setting and inner_ethertype_setting fields is because it's + * possible a device could support VLAN insertion and/or stripping offload on + * multiple ethertypes concurrently, so this method allows a VF to request + * multiple ethertypes in one message using the virtchnl_vlan_support + * enumeration. + * + * For example, if the PF populates the virtchnl_vlan_caps.offloads in the + * following manner the VF will be allowed to enable 0x8100 and 0x88a8 outer + * VLAN insertion and stripping simultaneously. The + * virtchnl_vlan_caps.offloads.ethertype_match field will also have to be + * populated based on what the PF can support. + * + * virtchnl_vlan_caps.offloads.stripping_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * virtchnl_vlan_caps.offloads.insertion_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_AND; + * + * In order to enable outer VLAN stripping for 0x8100 and 0x88a8 VLANs, the VF + * would populate the virthcnl_vlan_offload_structure in the following manner + * and send the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2 message. + * + * virtchnl_vlan_setting.outer_ethertype_setting = + * VIRTHCNL_VLAN_ETHERTYPE_8100 | + * VIRTHCNL_VLAN_ETHERTYPE_88A8; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + * + * There is also the case where a PF and the underlying hardware can support + * VLAN offloads on multiple ethertypes, but not concurrently. For example, if + * the PF populates the virtchnl_vlan_caps.offloads in the following manner the + * VF will be allowed to enable and/or disable 0x8100 XOR 0x88a8 outer VLAN + * offloads. The ethertypes must match for stripping and insertion. + * + * virtchnl_vlan_caps.offloads.stripping_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * virtchnl_vlan_caps.offloads.insertion_support.outer = + * VIRTCHNL_VLAN_TOGGLE | + * VIRTCHNL_VLAN_ETHERTYPE_8100 | + * VIRTCHNL_VLAN_ETHERTYPE_88A8 | + * VIRTCHNL_VLAN_ETHERTYPE_XOR; + * + * virtchnl_vlan_caps.offloads.ethertype_match = + * VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION; + * + * In order to enable outer VLAN stripping for 0x88a8 VLANs, the VF would + * populate the virtchnl_vlan_setting structure in the following manner and send + * the VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2. Also, this will change the + * ethertype for VLAN insertion if it's enabled. So, for completeness, a + * VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 with the same ethertype should be sent. + * + * virtchnl_vlan_setting.outer_ethertype_setting = VIRTHCNL_VLAN_ETHERTYPE_88A8; + * + * virtchnl_vlan_setting.vport_id = vport_id or vsi_id assigned to the VF on + * initialization. + */ +struct virtchnl_vlan_setting { + u32 outer_ethertype_setting; + u32 inner_ethertype_setting; + u16 vport_id; + u8 pad[6]; +}; + +VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vlan_setting); + /* VIRTCHNL_OP_CONFIG_PROMISCUOUS_MODE * VF sends VSI id and flags. * PF returns status code in retval. @@ -1156,6 +1509,30 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode, case VIRTCHNL_OP_DEL_FDIR_FILTER: valid_len = sizeof(struct virtchnl_fdir_del); break; + case VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS: + break; + case VIRTCHNL_OP_ADD_VLAN_V2: + case VIRTCHNL_OP_DEL_VLAN_V2: + valid_len = sizeof(struct virtchnl_vlan_filter_list_v2); + if (msglen >= valid_len) { + struct virtchnl_vlan_filter_list_v2 *vfl = + (struct virtchnl_vlan_filter_list_v2 *)msg; + + valid_len += (vfl->num_elements - 1) * + sizeof(struct virtchnl_vlan_filter); + + if (vfl->num_elements == 0) { + err_msg_format = true; + break; + } + } + break; + case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2: + case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2: + case VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2: + case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2: + valid_len = sizeof(struct virtchnl_vlan_setting); + break; /* These are always errors coming from the VF. */ case VIRTCHNL_OP_EVENT: case VIRTCHNL_OP_UNKNOWN: diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h new file mode 100644 index 000000000000..695d1224a71b --- /dev/null +++ b/include/linux/bpf-cgroup-defs.h @@ -0,0 +1,70 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _BPF_CGROUP_DEFS_H +#define _BPF_CGROUP_DEFS_H + +#ifdef CONFIG_CGROUP_BPF + +#include <linux/list.h> +#include <linux/percpu-refcount.h> +#include <linux/workqueue.h> + +struct bpf_prog_array; + +enum cgroup_bpf_attach_type { + CGROUP_BPF_ATTACH_TYPE_INVALID = -1, + CGROUP_INET_INGRESS = 0, + CGROUP_INET_EGRESS, + CGROUP_INET_SOCK_CREATE, + CGROUP_SOCK_OPS, + CGROUP_DEVICE, + CGROUP_INET4_BIND, + CGROUP_INET6_BIND, + CGROUP_INET4_CONNECT, + CGROUP_INET6_CONNECT, + CGROUP_INET4_POST_BIND, + CGROUP_INET6_POST_BIND, + CGROUP_UDP4_SENDMSG, + CGROUP_UDP6_SENDMSG, + CGROUP_SYSCTL, + CGROUP_UDP4_RECVMSG, + CGROUP_UDP6_RECVMSG, + CGROUP_GETSOCKOPT, + CGROUP_SETSOCKOPT, + CGROUP_INET4_GETPEERNAME, + CGROUP_INET6_GETPEERNAME, + CGROUP_INET4_GETSOCKNAME, + CGROUP_INET6_GETSOCKNAME, + CGROUP_INET_SOCK_RELEASE, + MAX_CGROUP_BPF_ATTACH_TYPE +}; + +struct cgroup_bpf { + /* array of effective progs in this cgroup */ + struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; + + /* attached progs to this cgroup and attach flags + * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will + * have either zero or one element + * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS + */ + struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; + u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; + + /* list of cgroup shared storages */ + struct list_head storages; + + /* temp storage for effective prog array used by prog_attach/detach */ + struct bpf_prog_array *inactive; + + /* reference counter used to detach bpf programs after cgroup removal */ + struct percpu_ref refcnt; + + /* cgroup_bpf is released using a work queue */ + struct work_struct release_work; +}; + +#else /* CONFIG_CGROUP_BPF */ +struct cgroup_bpf {}; +#endif /* CONFIG_CGROUP_BPF */ + +#endif diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 11820a430d6c..b525d8cdc25b 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -3,10 +3,10 @@ #define _BPF_CGROUP_H #include <linux/bpf.h> +#include <linux/bpf-cgroup-defs.h> #include <linux/errno.h> #include <linux/jump_label.h> #include <linux/percpu.h> -#include <linux/percpu-refcount.h> #include <linux/rbtree.h> #include <uapi/linux/bpf.h> @@ -23,33 +23,6 @@ struct ctl_table_header; struct task_struct; #ifdef CONFIG_CGROUP_BPF -enum cgroup_bpf_attach_type { - CGROUP_BPF_ATTACH_TYPE_INVALID = -1, - CGROUP_INET_INGRESS = 0, - CGROUP_INET_EGRESS, - CGROUP_INET_SOCK_CREATE, - CGROUP_SOCK_OPS, - CGROUP_DEVICE, - CGROUP_INET4_BIND, - CGROUP_INET6_BIND, - CGROUP_INET4_CONNECT, - CGROUP_INET6_CONNECT, - CGROUP_INET4_POST_BIND, - CGROUP_INET6_POST_BIND, - CGROUP_UDP4_SENDMSG, - CGROUP_UDP6_SENDMSG, - CGROUP_SYSCTL, - CGROUP_UDP4_RECVMSG, - CGROUP_UDP6_RECVMSG, - CGROUP_GETSOCKOPT, - CGROUP_SETSOCKOPT, - CGROUP_INET4_GETPEERNAME, - CGROUP_INET6_GETPEERNAME, - CGROUP_INET4_GETSOCKNAME, - CGROUP_INET6_GETSOCKNAME, - CGROUP_INET_SOCK_RELEASE, - MAX_CGROUP_BPF_ATTACH_TYPE -}; #define CGROUP_ATYPE(type) \ case BPF_##type: return type @@ -127,33 +100,6 @@ struct bpf_prog_list { struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; }; -struct bpf_prog_array; - -struct cgroup_bpf { - /* array of effective progs in this cgroup */ - struct bpf_prog_array __rcu *effective[MAX_CGROUP_BPF_ATTACH_TYPE]; - - /* attached progs to this cgroup and attach flags - * when flags == 0 or BPF_F_ALLOW_OVERRIDE the progs list will - * have either zero or one element - * when BPF_F_ALLOW_MULTI the list can have up to BPF_CGROUP_MAX_PROGS - */ - struct list_head progs[MAX_CGROUP_BPF_ATTACH_TYPE]; - u32 flags[MAX_CGROUP_BPF_ATTACH_TYPE]; - - /* list of cgroup shared storages */ - struct list_head storages; - - /* temp storage for effective prog array used by prog_attach/detach */ - struct bpf_prog_array *inactive; - - /* reference counter used to detach bpf programs after cgroup removal */ - struct percpu_ref refcnt; - - /* cgroup_bpf is released using a work queue */ - struct work_struct release_work; -}; - int cgroup_bpf_inherit(struct cgroup *cgrp); void cgroup_bpf_offline(struct cgroup *cgrp); @@ -451,7 +397,6 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr); #else -struct cgroup_bpf {}; static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; } static inline void cgroup_bpf_offline(struct cgroup *cgrp) {} diff --git a/include/linux/bpf-netns.h b/include/linux/bpf-netns.h index 722f799c1a2e..413cfa5e4b07 100644 --- a/include/linux/bpf-netns.h +++ b/include/linux/bpf-netns.h @@ -3,15 +3,9 @@ #define _BPF_NETNS_H #include <linux/mutex.h> +#include <net/netns/bpf.h> #include <uapi/linux/bpf.h> -enum netns_bpf_attach_type { - NETNS_BPF_INVALID = -1, - NETNS_BPF_FLOW_DISSECTOR = 0, - NETNS_BPF_SK_LOOKUP, - MAX_NETNS_BPF_ATTACH_TYPE -}; - static inline enum netns_bpf_attach_type to_netns_bpf_attach_type(enum bpf_attach_type attach_type) { diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 755f38e893be..6e947cd91152 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -297,6 +297,34 @@ bool bpf_map_meta_equal(const struct bpf_map *meta0, extern const struct bpf_map_ops bpf_map_offload_ops; +/* bpf_type_flag contains a set of flags that are applicable to the values of + * arg_type, ret_type and reg_type. For example, a pointer value may be null, + * or a memory is read-only. We classify types into two categories: base types + * and extended types. Extended types are base types combined with a type flag. + * + * Currently there are no more than 32 base types in arg_type, ret_type and + * reg_types. + */ +#define BPF_BASE_TYPE_BITS 8 + +enum bpf_type_flag { + /* PTR may be NULL. */ + PTR_MAYBE_NULL = BIT(0 + BPF_BASE_TYPE_BITS), + + /* MEM is read-only. When applied on bpf_arg, it indicates the arg is + * compatible with both mutable and immutable memory. + */ + MEM_RDONLY = BIT(1 + BPF_BASE_TYPE_BITS), + + __BPF_TYPE_LAST_FLAG = MEM_RDONLY, +}; + +/* Max number of base types. */ +#define BPF_BASE_TYPE_LIMIT (1UL << BPF_BASE_TYPE_BITS) + +/* Max number of all types. */ +#define BPF_TYPE_LIMIT (__BPF_TYPE_LAST_FLAG | (__BPF_TYPE_LAST_FLAG - 1)) + /* function argument constraints */ enum bpf_arg_type { ARG_DONTCARE = 0, /* unused argument in helper function */ @@ -308,13 +336,11 @@ enum bpf_arg_type { ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */ ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */ - ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */ /* the following constraints used to prototype bpf_memcmp() and other * functions that access data on eBPF program stack */ ARG_PTR_TO_MEM, /* pointer to valid memory (stack, packet, map value) */ - ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */ ARG_PTR_TO_UNINIT_MEM, /* pointer to memory does not need to be initialized, * helper function must fill all bytes or clear * them in error case. @@ -324,42 +350,65 @@ enum bpf_arg_type { ARG_CONST_SIZE_OR_ZERO, /* number of bytes accessed from memory or 0 */ ARG_PTR_TO_CTX, /* pointer to context */ - ARG_PTR_TO_CTX_OR_NULL, /* pointer to context or NULL */ ARG_ANYTHING, /* any (initialized) argument is ok */ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */ ARG_PTR_TO_INT, /* pointer to int */ ARG_PTR_TO_LONG, /* pointer to long */ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */ - ARG_PTR_TO_SOCKET_OR_NULL, /* pointer to bpf_sock (fullsock) or NULL */ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */ ARG_PTR_TO_ALLOC_MEM, /* pointer to dynamically allocated memory */ - ARG_PTR_TO_ALLOC_MEM_OR_NULL, /* pointer to dynamically allocated memory or NULL */ ARG_CONST_ALLOC_SIZE_OR_ZERO, /* number of allocated bytes requested */ ARG_PTR_TO_BTF_ID_SOCK_COMMON, /* pointer to in-kernel sock_common or bpf-mirrored bpf_sock */ ARG_PTR_TO_PERCPU_BTF_ID, /* pointer to in-kernel percpu type */ ARG_PTR_TO_FUNC, /* pointer to a bpf program function */ - ARG_PTR_TO_STACK_OR_NULL, /* pointer to stack or NULL */ + ARG_PTR_TO_STACK, /* pointer to stack */ ARG_PTR_TO_CONST_STR, /* pointer to a null terminated read-only string */ ARG_PTR_TO_TIMER, /* pointer to bpf_timer */ __BPF_ARG_TYPE_MAX, + + /* Extended arg_types. */ + ARG_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MAP_VALUE, + ARG_PTR_TO_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_MEM, + ARG_PTR_TO_CTX_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_CTX, + ARG_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET, + ARG_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_ALLOC_MEM, + ARG_PTR_TO_STACK_OR_NULL = PTR_MAYBE_NULL | ARG_PTR_TO_STACK, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_ARG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_ARG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* type of values returned from helper functions */ enum bpf_return_type { RET_INTEGER, /* function returns integer */ RET_VOID, /* function doesn't return anything */ RET_PTR_TO_MAP_VALUE, /* returns a pointer to map elem value */ - RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */ - RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */ - RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */ - RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common or NULL */ - RET_PTR_TO_ALLOC_MEM_OR_NULL, /* returns a pointer to dynamically allocated memory or NULL */ - RET_PTR_TO_BTF_ID_OR_NULL, /* returns a pointer to a btf_id or NULL */ - RET_PTR_TO_MEM_OR_BTF_ID_OR_NULL, /* returns a pointer to a valid memory or a btf_id or NULL */ + RET_PTR_TO_SOCKET, /* returns a pointer to a socket */ + RET_PTR_TO_TCP_SOCK, /* returns a pointer to a tcp_sock */ + RET_PTR_TO_SOCK_COMMON, /* returns a pointer to a sock_common */ + RET_PTR_TO_ALLOC_MEM, /* returns a pointer to dynamically allocated memory */ RET_PTR_TO_MEM_OR_BTF_ID, /* returns a pointer to a valid memory or a btf_id */ RET_PTR_TO_BTF_ID, /* returns a pointer to a btf_id */ + __BPF_RET_TYPE_MAX, + + /* Extended ret_types. */ + RET_PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_MAP_VALUE, + RET_PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCKET, + RET_PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK, + RET_PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON, + RET_PTR_TO_ALLOC_MEM_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_ALLOC_MEM, + RET_PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_RET_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_RET_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL @@ -421,18 +470,15 @@ enum bpf_reg_type { PTR_TO_CTX, /* reg points to bpf_context */ CONST_PTR_TO_MAP, /* reg points to struct bpf_map */ PTR_TO_MAP_VALUE, /* reg points to map element value */ - PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */ + PTR_TO_MAP_KEY, /* reg points to a map element key */ PTR_TO_STACK, /* reg == frame_pointer + offset */ PTR_TO_PACKET_META, /* skb->data - meta_len */ PTR_TO_PACKET, /* reg points to skb->data */ PTR_TO_PACKET_END, /* skb->data + headlen */ PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */ PTR_TO_SOCKET, /* reg points to struct bpf_sock */ - PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */ PTR_TO_SOCK_COMMON, /* reg points to sock_common */ - PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */ PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */ - PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */ PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */ PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */ /* PTR_TO_BTF_ID points to a kernel struct that does not need @@ -450,18 +496,25 @@ enum bpf_reg_type { * been checked for null. Used primarily to inform the verifier * an explicit null check is required for this struct. */ - PTR_TO_BTF_ID_OR_NULL, PTR_TO_MEM, /* reg points to valid memory region */ - PTR_TO_MEM_OR_NULL, /* reg points to valid memory region or NULL */ - PTR_TO_RDONLY_BUF, /* reg points to a readonly buffer */ - PTR_TO_RDONLY_BUF_OR_NULL, /* reg points to a readonly buffer or NULL */ - PTR_TO_RDWR_BUF, /* reg points to a read/write buffer */ - PTR_TO_RDWR_BUF_OR_NULL, /* reg points to a read/write buffer or NULL */ + PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_PERCPU_BTF_ID, /* reg points to a percpu kernel variable */ PTR_TO_FUNC, /* reg points to a bpf program function */ - PTR_TO_MAP_KEY, /* reg points to a map element key */ __BPF_REG_TYPE_MAX, + + /* Extended reg_types. */ + PTR_TO_MAP_VALUE_OR_NULL = PTR_MAYBE_NULL | PTR_TO_MAP_VALUE, + PTR_TO_SOCKET_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCKET, + PTR_TO_SOCK_COMMON_OR_NULL = PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON, + PTR_TO_TCP_SOCK_OR_NULL = PTR_MAYBE_NULL | PTR_TO_TCP_SOCK, + PTR_TO_BTF_ID_OR_NULL = PTR_MAYBE_NULL | PTR_TO_BTF_ID, + + /* This must be the last entry. Its purpose is to ensure the enum is + * wide enough to hold the higher bits reserved for bpf_type_flag. + */ + __BPF_REG_TYPE_LIMIT = BPF_TYPE_LIMIT, }; +static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT); /* The information passed from prog-specific *_is_valid_access * back to the verifier. @@ -777,6 +830,7 @@ void bpf_ksym_add(struct bpf_ksym *ksym); void bpf_ksym_del(struct bpf_ksym *ksym); int bpf_jit_charge_modmem(u32 pages); void bpf_jit_uncharge_modmem(u32 pages); +bool bpf_prog_has_trampoline(const struct bpf_prog *prog); #else static inline int bpf_trampoline_link_prog(struct bpf_prog *prog, struct bpf_trampoline *tr) @@ -805,6 +859,10 @@ static inline bool is_bpf_image_address(unsigned long address) { return false; } +static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog) +{ + return false; +} #endif struct bpf_func_info_aux { @@ -1082,7 +1140,7 @@ struct bpf_array { }; #define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */ -#define MAX_TAIL_CALL_CNT 32 +#define MAX_TAIL_CALL_CNT 33 #define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \ BPF_F_RDONLY_PROG | \ @@ -1611,17 +1669,17 @@ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth); struct btf *bpf_get_btf_vmlinux(void); /* Map specifics */ -struct xdp_buff; +struct xdp_frame; struct sk_buff; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; void __dev_flush(void); -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx); -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress); int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, struct bpf_prog *xdp_prog); @@ -1630,7 +1688,7 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, bool exclude_ingress); void __cpu_map_flush(void); -int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, +int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf, struct net_device *dev_rx); int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu, struct sk_buff *skb); @@ -1722,6 +1780,14 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, const struct bpf_insn *insn); +struct bpf_core_ctx { + struct bpf_verifier_log *log; + const struct btf *btf; +}; + +int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo, + int relo_idx, void *insn); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@ -1800,26 +1866,26 @@ static inline void __dev_flush(void) { } -struct xdp_buff; +struct xdp_frame; struct bpf_dtab_netdev; struct bpf_cpu_map_entry; static inline -int dev_xdp_enqueue(struct net_device *dev, struct xdp_buff *xdp, +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; } static inline -int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx, +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, struct bpf_map *map, bool exclude_ingress) { return 0; @@ -1847,7 +1913,7 @@ static inline void __cpu_map_flush(void) } static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, - struct xdp_buff *xdp, + struct xdp_frame *xdpf, struct net_device *dev_rx) { return 0; @@ -2153,6 +2219,9 @@ extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; +extern const struct bpf_func_proto bpf_find_vma_proto; +extern const struct bpf_func_proto bpf_loop_proto; +extern const struct bpf_func_proto bpf_strncmp_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h index 24496bc28e7b..37b3906af8b1 100644 --- a/include/linux/bpf_local_storage.h +++ b/include/linux/bpf_local_storage.h @@ -8,6 +8,7 @@ #define _BPF_LOCAL_STORAGE_H #include <linux/bpf.h> +#include <linux/filter.h> #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> @@ -16,6 +17,9 @@ #define BPF_LOCAL_STORAGE_CACHE_SIZE 16 +#define bpf_rcu_lock_held() \ + (rcu_read_lock_held() || rcu_read_lock_trace_held() || \ + rcu_read_lock_bh_held()) struct bpf_local_storage_map_bucket { struct hlist_head list; raw_spinlock_t lock; @@ -161,4 +165,6 @@ struct bpf_local_storage_data * bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap, void *value, u64 map_flags); +void bpf_local_storage_free_rcu(struct rcu_head *rcu); + #endif /* _BPF_LOCAL_STORAGE_H */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index c8a78e830fca..143401d4c9d9 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -18,6 +18,8 @@ * that converting umax_value to int cannot overflow. */ #define BPF_MAX_VAR_SIZ (1 << 29) +/* size of type_str_buf in bpf_verifier. */ +#define TYPE_STR_BUF_LEN 64 /* Liveness marks, used for registers and spilled-regs (in stack slots). * Read marks propagate upwards until they find a write mark; they record that @@ -388,6 +390,8 @@ static inline bool bpf_verifier_log_full(const struct bpf_verifier_log *log) #define BPF_LOG_LEVEL (BPF_LOG_LEVEL1 | BPF_LOG_LEVEL2) #define BPF_LOG_MASK (BPF_LOG_LEVEL | BPF_LOG_STATS) #define BPF_LOG_KERNEL (BPF_LOG_MASK + 1) /* kernel internal flag */ +#define BPF_LOG_MIN_ALIGNMENT 8U +#define BPF_LOG_ALIGNMENT 40U static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) { @@ -396,6 +400,13 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) log->level == BPF_LOG_KERNEL); } +static inline bool +bpf_verifier_log_attr_valid(const struct bpf_verifier_log *log) +{ + return log->len_total >= 128 && log->len_total <= UINT_MAX >> 2 && + log->level && log->ubuf && !(log->level & ~BPF_LOG_MASK); +} + #define BPF_MAX_SUBPROGS 256 struct bpf_subprog_info { @@ -467,6 +478,16 @@ struct bpf_verifier_env { /* longest register parentage chain walked for liveness marking */ u32 longest_mark_read_walk; bpfptr_t fd_array; + + /* bit mask to keep track of whether a register has been accessed + * since the last time the function state was printed + */ + u32 scratched_regs; + /* Same as scratched_regs but for stack slots */ + u64 scratched_stack_slots; + u32 prev_log_len, prev_insn_print_len; + /* buffer used in reg_type_str() to generate reg_type string */ + char type_str_buf[TYPE_STR_BUF_LEN]; }; __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log, @@ -529,5 +550,18 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, struct bpf_attach_target_info *tgt_info); void bpf_free_kfunc_btf_tab(struct bpf_kfunc_btf_tab *tab); +#define BPF_BASE_TYPE_MASK GENMASK(BPF_BASE_TYPE_BITS - 1, 0) + +/* extract base type from bpf_{arg, return, reg}_type. */ +static inline u32 base_type(u32 type) +{ + return type & BPF_BASE_TYPE_MASK; +} + +/* extract flags from an extended type. See bpf_type_flag in bpf.h. */ +static inline u32 type_flag(u32 type) +{ + return type & ~BPF_BASE_TYPE_MASK; +} #endif /* _LINUX_BPF_VERIFIER_H */ diff --git a/include/linux/btf.h b/include/linux/btf.h index 0e1b6281fd8f..0c74348cbc9d 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -144,6 +144,53 @@ static inline bool btf_type_is_enum(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_ENUM; } +static inline bool str_is_empty(const char *s) +{ + return !s || !s[0]; +} + +static inline u16 btf_kind(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info); +} + +static inline bool btf_is_enum(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ENUM; +} + +static inline bool btf_is_composite(const struct btf_type *t) +{ + u16 kind = btf_kind(t); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static inline bool btf_is_array(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_ARRAY; +} + +static inline bool btf_is_int(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_INT; +} + +static inline bool btf_is_ptr(const struct btf_type *t) +{ + return btf_kind(t) == BTF_KIND_PTR; +} + +static inline u8 btf_int_offset(const struct btf_type *t) +{ + return BTF_INT_OFFSET(*(u32 *)(t + 1)); +} + +static inline u8 btf_int_encoding(const struct btf_type *t) +{ + return BTF_INT_ENCODING(*(u32 *)(t + 1)); +} + static inline bool btf_type_is_scalar(const struct btf_type *t) { return btf_type_is_int(t) || btf_type_is_enum(t); @@ -184,6 +231,11 @@ static inline u16 btf_type_vlen(const struct btf_type *t) return BTF_INFO_VLEN(t->info); } +static inline u16 btf_vlen(const struct btf_type *t) +{ + return btf_type_vlen(t); +} + static inline u16 btf_func_linkage(const struct btf_type *t) { return BTF_INFO_VLEN(t->info); @@ -194,25 +246,54 @@ static inline bool btf_type_kflag(const struct btf_type *t) return BTF_INFO_KFLAG(t->info); } -static inline u32 btf_member_bit_offset(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bit_offset(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BIT_OFFSET(member->offset) : member->offset; } -static inline u32 btf_member_bitfield_size(const struct btf_type *struct_type, - const struct btf_member *member) +static inline u32 __btf_member_bitfield_size(const struct btf_type *struct_type, + const struct btf_member *member) { return btf_type_kflag(struct_type) ? BTF_MEMBER_BITFIELD_SIZE(member->offset) : 0; } +static inline struct btf_member *btf_members(const struct btf_type *t) +{ + return (struct btf_member *)(t + 1); +} + +static inline u32 btf_member_bit_offset(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bit_offset(t, m); +} + +static inline u32 btf_member_bitfield_size(const struct btf_type *t, u32 member_idx) +{ + const struct btf_member *m = btf_members(t) + member_idx; + + return __btf_member_bitfield_size(t, m); +} + static inline const struct btf_member *btf_type_member(const struct btf_type *t) { return (const struct btf_member *)(t + 1); } +static inline struct btf_array *btf_array(const struct btf_type *t) +{ + return (struct btf_array *)(t + 1); +} + +static inline struct btf_enum *btf_enum(const struct btf_type *t) +{ + return (struct btf_enum *)(t + 1); +} + static inline const struct btf_var_secinfo *btf_type_var_secinfo( const struct btf_type *t) { diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h index 47d9abfbdb55..919c0fde1c51 100644 --- a/include/linux/btf_ids.h +++ b/include/linux/btf_ids.h @@ -73,7 +73,7 @@ asm( \ __BTF_ID_LIST(name, local) \ extern u32 name[]; -#define BTF_ID_LIST_GLOBAL(name) \ +#define BTF_ID_LIST_GLOBAL(name, n) \ __BTF_ID_LIST(name, globl) /* The BTF_ID_LIST_SINGLE macro defines a BTF_ID_LIST with @@ -83,7 +83,7 @@ __BTF_ID_LIST(name, globl) BTF_ID_LIST(name) \ BTF_ID(prefix, typename) #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) \ - BTF_ID_LIST_GLOBAL(name) \ + BTF_ID_LIST_GLOBAL(name, 1) \ BTF_ID(prefix, typename) /* @@ -149,7 +149,7 @@ extern struct btf_id_set name; #define BTF_ID_LIST(name) static u32 name[5]; #define BTF_ID(prefix, name) #define BTF_ID_UNUSED -#define BTF_ID_LIST_GLOBAL(name) u32 name[1]; +#define BTF_ID_LIST_GLOBAL(name, n) u32 name[n]; #define BTF_ID_LIST_SINGLE(name, prefix, typename) static u32 name[1]; #define BTF_ID_LIST_GLOBAL_SINGLE(name, prefix, typename) u32 name[1]; #define BTF_SET_START(name) static struct btf_id_set name = { 0 }; @@ -189,6 +189,18 @@ MAX_BTF_SOCK_TYPE, extern u32 btf_sock_ids[]; #endif -extern u32 btf_task_struct_ids[]; +#define BTF_TRACING_TYPE_xxx \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_TASK, task_struct) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_FILE, file) \ + BTF_TRACING_TYPE(BTF_TRACING_TYPE_VMA, vm_area_struct) + +enum { +#define BTF_TRACING_TYPE(name, type) name, +BTF_TRACING_TYPE_xxx +#undef BTF_TRACING_TYPE +MAX_BTF_TRACING_TYPE, +}; + +extern u32 btf_tracing_ids[]; #endif diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 20b50baf3a02..a81652d1c6f3 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -12,13 +12,6 @@ #define CAN_SYNC_SEG 1 -/* Kilobits and Megabits per second */ -#define CAN_KBPS 1000UL -#define CAN_MBPS 1000000UL - -/* Megahertz */ -#define CAN_MHZ 1000000UL - #define CAN_CTRLMODE_TDC_MASK \ (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 45f19d9db5ca..c2ea47f30046 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -64,12 +64,14 @@ struct can_priv { struct gpio_desc *termination_gpio; u16 termination_gpio_ohms[CAN_TERMINATION_GPIO_MAX]; + unsigned int echo_skb_max; + struct sk_buff **echo_skb; + enum can_state state; /* CAN controller features - see include/uapi/linux/can/netlink.h */ u32 ctrlmode; /* current options setting */ u32 ctrlmode_supported; /* options that can be modified by netlink */ - u32 ctrlmode_static; /* static enabled options for driver/hardware */ int restart_ms; struct delayed_work restart_work; @@ -84,9 +86,6 @@ struct can_priv { struct can_berr_counter *bec); int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv); - unsigned int echo_skb_max; - struct sk_buff **echo_skb; - #ifdef CONFIG_CAN_LEDS struct led_trigger *tx_led_trig; char tx_led_trig_name[CAN_LED_NAME_SZ]; @@ -132,18 +131,29 @@ static inline s32 can_get_relative_tdco(const struct can_priv *priv) } /* helper to define static CAN controller features at device creation time */ -static inline void can_set_static_ctrlmode(struct net_device *dev, - u32 static_mode) +static inline int __must_check can_set_static_ctrlmode(struct net_device *dev, + u32 static_mode) { struct can_priv *priv = netdev_priv(dev); /* alloc_candev() succeeded => netdev_priv() is valid at this point */ + if (priv->ctrlmode_supported & static_mode) { + netdev_warn(dev, + "Controller features can not be supported and static at the same time\n"); + return -EINVAL; + } priv->ctrlmode = static_mode; - priv->ctrlmode_static = static_mode; /* override MTU which was set by default in can_setup()? */ if (static_mode & CAN_CTRLMODE_FD) dev->mtu = CANFD_MTU; + + return 0; +} + +static inline u32 can_get_static_ctrlmode(struct can_priv *priv) +{ + return priv->ctrlmode & ~priv->ctrlmode_supported; } void can_setup(struct net_device *dev); diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h index d311bc369a39..fdb22b00674a 100644 --- a/include/linux/can/skb.h +++ b/include/linux/can/skb.h @@ -21,8 +21,9 @@ int can_put_echo_skb(struct sk_buff *skb, struct net_device *dev, unsigned int idx, unsigned int frame_len); struct sk_buff *__can_get_echo_skb(struct net_device *dev, unsigned int idx, u8 *len_ptr, unsigned int *frame_len_ptr); -unsigned int can_get_echo_skb(struct net_device *dev, unsigned int idx, - unsigned int *frame_len_ptr); +unsigned int __must_check can_get_echo_skb(struct net_device *dev, + unsigned int idx, + unsigned int *frame_len_ptr); void can_free_echo_skb(struct net_device *dev, unsigned int idx, unsigned int *frame_len_ptr); struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index db2e147e069f..411684c80cf3 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -19,7 +19,7 @@ #include <linux/percpu-rwsem.h> #include <linux/u64_stats_sync.h> #include <linux/workqueue.h> -#include <linux/bpf-cgroup.h> +#include <linux/bpf-cgroup-defs.h> #include <linux/psi_types.h> #ifdef CONFIG_CGROUPS diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h index 254b165f2b44..939a1beaddf7 100644 --- a/include/linux/dsa/8021q.h +++ b/include/linux/dsa/8021q.h @@ -7,6 +7,7 @@ #include <linux/refcount.h> #include <linux/types.h> +#include <net/dsa.h> struct dsa_switch; struct dsa_port; @@ -37,14 +38,12 @@ struct sk_buff *dsa_8021q_xmit(struct sk_buff *skb, struct net_device *netdev, void dsa_8021q_rcv(struct sk_buff *skb, int *source_port, int *switch_id); int dsa_tag_8021q_bridge_tx_fwd_offload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num); + struct dsa_bridge bridge); void dsa_tag_8021q_bridge_tx_fwd_unoffload(struct dsa_switch *ds, int port, - struct net_device *br, - int bridge_num); + struct dsa_bridge bridge); -u16 dsa_8021q_bridge_tx_fwd_offload_vid(int bridge_num); +u16 dsa_8021q_bridge_tx_fwd_offload_vid(unsigned int bridge_num); u16 dsa_tag_8021q_tx_vid(const struct dsa_port *dp); diff --git a/include/linux/dsa/loop.h b/include/linux/dsa/loop.h index 5a3470bcc8a7..b8fef35591aa 100644 --- a/include/linux/dsa/loop.h +++ b/include/linux/dsa/loop.h @@ -2,6 +2,7 @@ #ifndef DSA_LOOP_H #define DSA_LOOP_H +#include <linux/if_vlan.h> #include <linux/types.h> #include <linux/ethtool.h> #include <net/dsa.h> diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index 7ee708ad7df2..dca2969015d8 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -8,6 +8,7 @@ #include <linux/kthread.h> #include <linux/packing.h> #include <linux/skbuff.h> +#include <net/dsa.h> struct ocelot_skb_cb { struct sk_buff *clone; @@ -168,11 +169,18 @@ struct felix_deferred_xmit_work { struct kthread_work work; }; -struct felix_port { +struct ocelot_8021q_tagger_data { void (*xmit_work_fn)(struct kthread_work *work); - struct kthread_worker *xmit_worker; }; +static inline struct ocelot_8021q_tagger_data * +ocelot_8021q_tagger_data(struct dsa_switch *ds) +{ + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_OCELOT_8021Q); + + return ds->tagger_data; +} + static inline void ocelot_xfh_get_rew_val(void *extraction, u64 *rew_val) { packing(extraction, rew_val, 116, 85, OCELOT_TAG_LEN, UNPACK, 0); diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index e6c78be40bde..159e43171ccc 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -35,23 +35,26 @@ #define SJA1105_META_SMAC 0x222222222222ull #define SJA1105_META_DMAC 0x0180C200000Eull -#define SJA1105_HWTS_RX_EN 0 +enum sja1110_meta_tstamp { + SJA1110_META_TSTAMP_TX = 0, + SJA1110_META_TSTAMP_RX = 1, +}; -/* Global tagger data: each struct sja1105_port has a reference to - * the structure defined in struct sja1105_private. - */ +struct sja1105_deferred_xmit_work { + struct dsa_port *dp; + struct sk_buff *skb; + struct kthread_work work; +}; + +/* Global tagger data */ struct sja1105_tagger_data { - struct sk_buff *stampable_skb; - /* Protects concurrent access to the meta state machine - * from taggers running on multiple ports on SMP systems - */ - spinlock_t meta_lock; - unsigned long state; - u8 ts_id; - /* Used on SJA1110 where meta frames are generated only for - * 2-step TX timestamps - */ - struct sk_buff_head skb_txtstamp_queue; + /* Tagger to switch */ + void (*xmit_work_fn)(struct kthread_work *work); + void (*meta_tstamp_handler)(struct dsa_switch *ds, int port, u8 ts_id, + enum sja1110_meta_tstamp dir, u64 tstamp); + /* Switch to tagger */ + bool (*rxtstamp_get_state)(struct dsa_switch *ds); + void (*rxtstamp_set_state)(struct dsa_switch *ds, bool on); }; struct sja1105_skb_cb { @@ -64,32 +67,13 @@ struct sja1105_skb_cb { #define SJA1105_SKB_CB(skb) \ ((struct sja1105_skb_cb *)((skb)->cb)) -struct sja1105_port { - struct kthread_worker *xmit_worker; - struct kthread_work xmit_work; - struct sk_buff_head xmit_queue; - struct sja1105_tagger_data *data; - bool hwts_tx_en; -}; - -/* Timestamps are in units of 8 ns clock ticks (equivalent to - * a fixed 125 MHz clock). - */ -#define SJA1105_TICK_NS 8 - -static inline s64 ns_to_sja1105_ticks(s64 ns) +static inline struct sja1105_tagger_data * +sja1105_tagger_data(struct dsa_switch *ds) { - return ns / SJA1105_TICK_NS; -} + BUG_ON(ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1105 && + ds->dst->tag_ops->proto != DSA_TAG_PROTO_SJA1110); -static inline s64 sja1105_ticks_to_ns(s64 ticks) -{ - return ticks * SJA1105_TICK_NS; -} - -static inline bool dsa_port_is_sja1105(struct dsa_port *dp) -{ - return true; + return ds->tagger_data; } #endif /* _NET_DSA_SJA1105_H */ diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 845a0ffc16ee..a26f37a27167 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -67,6 +67,22 @@ enum { ETH_RSS_HASH_FUNCS_COUNT }; +/** + * struct kernel_ethtool_ringparam - RX/TX ring configuration + * @rx_buf_len: Current length of buffers on the rx ring. + */ +struct kernel_ethtool_ringparam { + u32 rx_buf_len; +}; + +/** + * enum ethtool_supported_ring_param - indicator caps for setting ring params + * @ETHTOOL_RING_USE_RX_BUF_LEN: capture for setting rx_buf_len + */ +enum ethtool_supported_ring_param { + ETHTOOL_RING_USE_RX_BUF_LEN = BIT(0), +}; + #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) #define __ETH_RSS_HASH(name) __ETH_RSS_HASH_BIT(ETH_RSS_HASH_##name##_BIT) @@ -432,6 +448,7 @@ struct ethtool_module_power_mode_params { * @cap_link_lanes_supported: indicates if the driver supports lanes * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. + * @supported_ring_params: supported ring params. * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in @@ -613,6 +630,7 @@ struct ethtool_module_power_mode_params { struct ethtool_ops { u32 cap_link_lanes_supported:1; u32 supported_coalesce_params; + u32 supported_ring_params; void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); @@ -638,9 +656,13 @@ struct ethtool_ops { struct kernel_ethtool_coalesce *, struct netlink_ext_ack *); void (*get_ringparam)(struct net_device *, - struct ethtool_ringparam *); + struct ethtool_ringparam *, + struct kernel_ethtool_ringparam *, + struct netlink_ext_ack *); int (*set_ringparam)(struct net_device *, - struct ethtool_ringparam *); + struct ethtool_ringparam *, + struct kernel_ethtool_ringparam *, + struct netlink_ext_ack *); void (*get_pause_stats)(struct net_device *dev, struct ethtool_pause_stats *pause_stats); void (*get_pauseparam)(struct net_device *, diff --git a/include/linux/filter.h b/include/linux/filter.h index 7f1e88e3e2b5..71fa57b88bfc 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1019,6 +1019,10 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); +int xdp_do_redirect_frame(struct net_device *dev, + struct xdp_buff *xdp, + struct xdp_frame *xdpf, + struct bpf_prog *prog); void xdp_do_flush(void); /* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as @@ -1027,7 +1031,7 @@ void xdp_do_flush(void); */ #define xdp_do_flush_map xdp_do_flush -void bpf_warn_invalid_xdp_action(u32 act); +void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, @@ -1371,6 +1375,7 @@ struct bpf_sk_lookup_kern { const struct in6_addr *daddr; } v6; struct sock *selected_sk; + u32 ingress_ifindex; bool no_reuseport; }; @@ -1433,7 +1438,7 @@ extern struct static_key_false bpf_sk_lookup_enabled; static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1449,6 +1454,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, .v4.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; @@ -1471,7 +1477,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const __be16 sport, const struct in6_addr *daddr, const u16 dport, - struct sock **psk) + const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; @@ -1487,6 +1493,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, .v6.daddr = daddr, .sport = sport, .dport = dport, + .ingress_ifindex = ifindex, }; u32 act; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 11d7af260f20..559b6c644938 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -2258,11 +2258,12 @@ enum ieee80211_client_reg_power { #define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU 0x08 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB 0x10 #define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB 0x20 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_0US 0x00 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_8US 0x40 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_16US 0x80 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_RESERVED 0xc0 -#define IEEE80211_HE_PHY_CAP9_NOMIMAL_PKT_PADDING_MASK 0xc0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US 0x0 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US 0x1 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US 0x2 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED 0x3 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS 6 +#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK 0xc0 #define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF 0x01 diff --git a/include/linux/if_eql.h b/include/linux/if_eql.h index d984694c384d..d75601d613cc 100644 --- a/include/linux/if_eql.h +++ b/include/linux/if_eql.h @@ -26,6 +26,7 @@ typedef struct slave { struct list_head list; struct net_device *dev; + netdevice_tracker dev_tracker; long priority; long priority_bps; long priority_Bps; diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index 41a518336673..8420fe504927 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -162,6 +162,7 @@ struct netpoll; * @vlan_id: VLAN identifier * @flags: device flags * @real_dev: underlying netdevice + * @dev_tracker: refcount tracker for @real_dev reference * @real_dev_addr: address of underlying netdevice * @dent: proc dir entry * @vlan_pcpu_stats: ptr to percpu rx stats @@ -177,6 +178,8 @@ struct vlan_dev_priv { u16 flags; struct net_device *real_dev; + netdevice_tracker dev_tracker; + unsigned char real_dev_addr[ETH_ALEN]; struct proc_dir_entry *dent; diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index 518b484a7f07..674aeead6260 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -24,6 +24,8 @@ struct ipv4_devconf { struct in_device { struct net_device *dev; + netdevice_tracker dev_tracker; + refcount_t refcnt; int dead; struct in_ifaddr __rcu *ifa_list;/* IP ifaddr chain */ diff --git a/include/linux/mdio.h b/include/linux/mdio.h index 9f3587a61e14..ecac96d52e01 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -7,6 +7,7 @@ #define __LINUX_MDIO_H__ #include <uapi/linux/mdio.h> +#include <linux/bitfield.h> #include <linux/mod_devicetable.h> /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit @@ -14,6 +15,7 @@ */ #define MII_ADDR_C45 (1<<30) #define MII_DEVADDR_C45_SHIFT 16 +#define MII_DEVADDR_C45_MASK GENMASK(20, 16) #define MII_REGADDR_C45_MASK GENMASK(15, 0) struct gpio_desc; @@ -381,6 +383,16 @@ static inline u32 mdiobus_c45_addr(int devad, u16 regnum) return MII_ADDR_C45 | devad << MII_DEVADDR_C45_SHIFT | regnum; } +static inline u16 mdiobus_c45_regad(u32 regnum) +{ + return FIELD_GET(MII_REGADDR_C45_MASK, regnum); +} + +static inline u16 mdiobus_c45_devad(u32 regnum) +{ + return FIELD_GET(MII_DEVADDR_C45_MASK, regnum); +} + static inline int __mdiobus_c45_read(struct mii_bus *bus, int prtad, int devad, u16 regnum) { diff --git a/include/linux/mdio/mdio-mscc-miim.h b/include/linux/mdio/mdio-mscc-miim.h new file mode 100644 index 000000000000..5b4ed2c3cbb9 --- /dev/null +++ b/include/linux/mdio/mdio-mscc-miim.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Driver for the MDIO interface of Microsemi network switches. + * + * Author: Colin Foster <colin.foster@in-advantage.com> + * Copyright (C) 2021 Innovative Advantage + */ +#ifndef MDIO_MSCC_MIIM_H +#define MDIO_MSCC_MIIM_H + +#include <linux/device.h> +#include <linux/phy.h> +#include <linux/regmap.h> + +int mscc_miim_setup(struct device *device, struct mii_bus **bus, + const char *name, struct regmap *mii_regmap, + int status_offset); + +#endif diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h index c6786c12b207..df1fab44ea5c 100644 --- a/include/linux/mei_cl_bus.h +++ b/include/linux/mei_cl_bus.h @@ -117,4 +117,7 @@ int mei_cldev_enable(struct mei_cl_device *cldev); int mei_cldev_disable(struct mei_cl_device *cldev); bool mei_cldev_enabled(const struct mei_cl_device *cldev); +void *mei_cldev_dma_map(struct mei_cl_device *cldev, u8 buffer_id, size_t size); +int mei_cldev_dma_unmap(struct mei_cl_device *cldev); + #endif /* _LINUX_MEI_CL_BUS_H */ diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 9c25edfd59a6..604b85dd770a 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1117,6 +1117,7 @@ enum { MLX5_MATCH_MISC_PARAMETERS_2 = 1 << 3, MLX5_MATCH_MISC_PARAMETERS_3 = 1 << 4, MLX5_MATCH_MISC_PARAMETERS_4 = 1 << 5, + MLX5_MATCH_MISC_PARAMETERS_5 = 1 << 6, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index a623ec635947..78655d8d13a7 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -478,6 +478,10 @@ struct mlx5_fc_stats { unsigned long next_query; unsigned long sampling_interval; /* jiffies */ u32 *bulk_query_out; + int bulk_query_len; + size_t num_counters; + bool bulk_query_alloc_failed; + unsigned long next_bulk_query_alloc; struct mlx5_fc_pool fc_pool; }; diff --git a/include/linux/mlx5/eq.h b/include/linux/mlx5/eq.h index ea3ff5a8ced3..3705a382276b 100644 --- a/include/linux/mlx5/eq.h +++ b/include/linux/mlx5/eq.h @@ -9,13 +9,13 @@ #define MLX5_NUM_SPARE_EQE (0x80) struct mlx5_eq; +struct mlx5_irq; struct mlx5_core_dev; struct mlx5_eq_param { - u8 irq_index; int nent; u64 mask[4]; - cpumask_var_t affinity; + struct mlx5_irq *irq; }; struct mlx5_eq * diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index cd2d4c572367..b1aad14689e3 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -73,6 +73,7 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_KERNEL, MLX5_FLOW_NAMESPACE_LEFTOVERS, MLX5_FLOW_NAMESPACE_ANCHOR, + MLX5_FLOW_NAMESPACE_FDB_BYPASS, MLX5_FLOW_NAMESPACE_FDB, MLX5_FLOW_NAMESPACE_ESW_EGRESS, MLX5_FLOW_NAMESPACE_ESW_INGRESS, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fbaab440a484..598ac3bcc901 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -372,7 +372,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits { u8 reserved_at_37[0x9]; u8 geneve_tlv_option_0_data[0x1]; - u8 reserved_at_41[0x4]; + u8 geneve_tlv_option_0_exist[0x1]; + u8 reserved_at_42[0x3]; u8 outer_first_mpls_over_udp[0x4]; u8 outer_first_mpls_over_gre[0x4]; u8 inner_first_mpls[0x4]; @@ -551,7 +552,8 @@ struct mlx5_ifc_fte_match_set_misc_bits { u8 bth_opcode[0x8]; u8 geneve_vni[0x18]; - u8 reserved_at_d8[0x7]; + u8 reserved_at_d8[0x6]; + u8 geneve_tlv_option_0_exist[0x1]; u8 geneve_oam[0x1]; u8 reserved_at_e0[0xc]; @@ -670,6 +672,26 @@ struct mlx5_ifc_fte_match_set_misc4_bits { u8 reserved_at_100[0x100]; }; +struct mlx5_ifc_fte_match_set_misc5_bits { + u8 macsec_tag_0[0x20]; + + u8 macsec_tag_1[0x20]; + + u8 macsec_tag_2[0x20]; + + u8 macsec_tag_3[0x20]; + + u8 tunnel_header_0[0x20]; + + u8 tunnel_header_1[0x20]; + + u8 tunnel_header_2[0x20]; + + u8 tunnel_header_3[0x20]; + + u8 reserved_at_100[0x100]; +}; + struct mlx5_ifc_cmd_pas_bits { u8 pa_h[0x20]; @@ -811,7 +833,7 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits { u8 fdb_to_vport_reg_c_id[0x8]; u8 reserved_at_8[0xd]; u8 fdb_modify_header_fwd_to_table[0x1]; - u8 reserved_at_16[0x1]; + u8 fdb_ipv4_ttl_modify[0x1]; u8 flow_source[0x1]; u8 reserved_at_18[0x2]; u8 multi_fdb_encap[0x1]; @@ -1291,7 +1313,7 @@ enum { enum { MLX5_FLEX_PARSER_GENEVE_ENABLED = 1 << 3, MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED = 1 << 4, - mlx5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, + MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED = 1 << 5, MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED = 1 << 7, MLX5_FLEX_PARSER_ICMP_V4_ENABLED = 1 << 8, MLX5_FLEX_PARSER_ICMP_V6_ENABLED = 1 << 9, @@ -1621,7 +1643,7 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 ext_stride_num_range[0x1]; u8 roce_rw_supported[0x1]; - u8 reserved_at_3a2[0x1]; + u8 log_max_current_uc_list_wr_supported[0x1]; u8 log_max_stride_sz_rq[0x5]; u8 reserved_at_3a8[0x3]; u8 log_min_stride_sz_rq[0x5]; @@ -1839,7 +1861,9 @@ struct mlx5_ifc_fte_match_param_bits { struct mlx5_ifc_fte_match_set_misc4_bits misc_parameters_4; - u8 reserved_at_c00[0x400]; + struct mlx5_ifc_fte_match_set_misc5_bits misc_parameters_5; + + u8 reserved_at_e00[0x200]; }; enum { @@ -5977,6 +6001,7 @@ enum { MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_2 = 0x3, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_3 = 0x4, MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_4 = 0x5, + MLX5_QUERY_FLOW_GROUP_IN_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS_5 = 0x6, }; struct mlx5_ifc_query_flow_group_out_bits { diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h index a85c9f0bd470..53f0efa0bccf 100644 --- a/include/linux/mmc/sdio_ids.h +++ b/include/linux/mmc/sdio_ids.h @@ -105,6 +105,7 @@ #define SDIO_VENDOR_ID_MEDIATEK 0x037a #define SDIO_DEVICE_ID_MEDIATEK_MT7663 0x7663 #define SDIO_DEVICE_ID_MEDIATEK_MT7668 0x7668 +#define SDIO_DEVICE_ID_MEDIATEK_MT7961 0x7961 #define SDIO_VENDOR_ID_MICROCHIP_WILC 0x0296 #define SDIO_DEVICE_ID_MICROCHIP_WILC1000 0x5347 diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h index 8071148f29a6..e05ee9f001ff 100644 --- a/include/linux/mroute_base.h +++ b/include/linux/mroute_base.h @@ -12,6 +12,7 @@ /** * struct vif_device - interface representor for multicast routing * @dev: network device being used + * @dev_tracker: refcount tracker for @dev reference * @bytes_in: statistic; bytes ingressing * @bytes_out: statistic; bytes egresing * @pkt_in: statistic; packets ingressing @@ -26,6 +27,7 @@ */ struct vif_device { struct net_device *dev; + netdevice_tracker dev_tracker; unsigned long bytes_in, bytes_out; unsigned long pkt_in, pkt_out; unsigned long rate_limit; diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h index e32f6712aee0..1289593411d3 100644 --- a/include/linux/net/intel/iidc.h +++ b/include/linux/net/intel/iidc.h @@ -26,6 +26,11 @@ enum iidc_reset_type { IIDC_GLOBR, }; +enum iidc_rdma_protocol { + IIDC_RDMA_PROTOCOL_IWARP = BIT(0), + IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1), +}; + #define IIDC_MAX_USER_PRIORITY 8 /* Struct to hold per RDMA Qset info */ @@ -70,8 +75,6 @@ int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type); int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable); void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos); -#define IIDC_RDMA_ROCE_NAME "roce" - /* Structure representing auxiliary driver tailored information about the core * PCI dev, each auxiliary driver using the IIDC interface will have an * instance of this struct dedicated to it. diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6aadcc0ecb5b..3213c7227b59 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -48,6 +48,7 @@ #include <uapi/linux/pkt_cls.h> #include <linux/hashtable.h> #include <linux/rbtree.h> +#include <net/net_trackers.h> struct netpoll_info; struct device; @@ -299,7 +300,6 @@ enum netdev_state_t { __LINK_STATE_TESTING, }; - struct gro_list { struct list_head list; int count; @@ -579,6 +579,8 @@ struct netdev_queue { * read-mostly part */ struct net_device *dev; + netdevice_tracker dev_tracker; + struct Qdisc __rcu *qdisc; struct Qdisc *qdisc_sleeping; #ifdef CONFIG_SYSFS @@ -592,7 +594,7 @@ struct netdev_queue { * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ - unsigned long trans_timeout; + atomic_long_t trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; @@ -734,6 +736,8 @@ struct netdev_rx_queue { #endif struct kobject kobj; struct net_device *dev; + netdevice_tracker dev_tracker; + #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif @@ -916,6 +920,7 @@ enum tc_setup_type { TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, TC_SETUP_QDISC_HTB, + TC_SETUP_ACT, }; /* These structures hold the attributes of bpf state that are being passed @@ -1297,11 +1302,6 @@ struct netdev_net_notifier { * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. - * void (*ndo_change_proto_down)(struct net_device *dev, - * bool proto_down); - * This function is used to pass protocol port error state information - * to the switch driver. The switch driver can react to the proto_down - * by doing a phys down on the associated switch port. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while @@ -1542,8 +1542,6 @@ struct net_device_ops { int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); - int (*ndo_change_proto_down)(struct net_device *dev, - bool proto_down); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, @@ -1612,6 +1610,7 @@ struct net_device_ops { * @IFF_LIVE_RENAME_OK: rename is allowed while device is up and running * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) + * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, @@ -1646,6 +1645,7 @@ enum netdev_priv_flags { IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_LIVE_RENAME_OK = 1<<30, IFF_TX_SKB_NO_LINEAR = 1<<31, + IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN @@ -1870,6 +1870,7 @@ enum netdev_ml_priv_type { * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @dev_refcnt: Number of references to this device + * @refcnt_tracker: Tracker directory for tracked references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * @@ -1941,6 +1942,12 @@ enum netdev_ml_priv_type { * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. + * @gro_max_size: Maximum size of aggregated packet in generic + * receive offload (GRO) + * + * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. + * @linkwatch_dev_tracker: refcount tracker used by linkwatch. + * @watchdog_dev_tracker: refcount tracker used by watchdog. * * FIXME: cleanup struct net_device such that network protocol info * moves out. @@ -1980,7 +1987,7 @@ struct net_device { /* Read-mostly cache-line for fast-path access */ unsigned int flags; - unsigned int priv_flags; + unsigned long long priv_flags; const struct net_device_ops *netdev_ops; int ifindex; unsigned short gflags; @@ -2093,7 +2100,7 @@ struct net_device { #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif -#if IS_ENABLED(CONFIG_IRDA) || IS_ENABLED(CONFIG_ATALK) +#if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif struct in_device __rcu *ip_ptr; @@ -2117,7 +2124,7 @@ struct net_device { * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ - unsigned char *dev_addr; + const unsigned char *dev_addr; struct netdev_rx_queue *_rx; unsigned int num_rx_queues; @@ -2126,6 +2133,8 @@ struct net_device { struct bpf_prog __rcu *xdp_prog; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; +#define GRO_MAX_SIZE 65536 + unsigned int gro_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; @@ -2181,6 +2190,7 @@ struct net_device { #else refcount_t dev_refcnt; #endif + struct ref_tracker_dir refcnt_tracker; struct list_head link_watch_list; @@ -2268,6 +2278,10 @@ struct net_device { /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; + + u8 dev_addr_shadow[MAX_ADDR_LEN]; + netdevice_tracker linkwatch_dev_tracker; + netdevice_tracker watchdog_dev_tracker; }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -2520,113 +2534,11 @@ static inline void netif_napi_del(struct napi_struct *napi) synchronize_net(); } -struct napi_gro_cb { - /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ - void *frag0; - - /* Length of frag0. */ - unsigned int frag0_len; - - /* This indicates where we are processing relative to skb->data. */ - int data_offset; - - /* This is non-zero if the packet cannot be merged with the new skb. */ - u16 flush; - - /* Save the IP ID here and check when we get to the transport layer */ - u16 flush_id; - - /* Number of segments aggregated. */ - u16 count; - - /* Start offset for remote checksum offload */ - u16 gro_remcsum_start; - - /* jiffies when first packet was created/queued */ - unsigned long age; - - /* Used in ipv6_gro_receive() and foo-over-udp */ - u16 proto; - - /* This is non-zero if the packet may be of the same flow. */ - u8 same_flow:1; - - /* Used in tunnel GRO receive */ - u8 encap_mark:1; - - /* GRO checksum is valid */ - u8 csum_valid:1; - - /* Number of checksums via CHECKSUM_UNNECESSARY */ - u8 csum_cnt:3; - - /* Free the skb? */ - u8 free:2; -#define NAPI_GRO_FREE 1 -#define NAPI_GRO_FREE_STOLEN_HEAD 2 - - /* Used in foo-over-udp, set in udp[46]_gro_receive */ - u8 is_ipv6:1; - - /* Used in GRE, set in fou/gue_gro_receive */ - u8 is_fou:1; - - /* Used to determine if flush_id can be ignored */ - u8 is_atomic:1; - - /* Number of gro_receive callbacks this packet already went through */ - u8 recursion_counter:4; - - /* GRO is done by frag_list pointer chaining. */ - u8 is_flist:1; - - /* used to support CHECKSUM_COMPLETE for tunneling protocols */ - __wsum csum; - - /* used in skb_gro_receive() slow path */ - struct sk_buff *last; -}; - -#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) - -#define GRO_RECURSION_LIMIT 15 -static inline int gro_recursion_inc_test(struct sk_buff *skb) -{ - return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; -} - -typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); -static inline struct sk_buff *call_gro_receive(gro_receive_t cb, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(head, skb); -} - -typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, - struct sk_buff *); -static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, - struct sock *sk, - struct list_head *head, - struct sk_buff *skb) -{ - if (unlikely(gro_recursion_inc_test(skb))) { - NAPI_GRO_CB(skb)->flush |= 1; - return NULL; - } - - return cb(sk, head, skb); -} - struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ + netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, @@ -3005,254 +2917,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); int netdev_get_name(struct net *net, char *name, int ifindex); int dev_restart(struct net_device *dev); -int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); -int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb); -static inline unsigned int skb_gro_offset(const struct sk_buff *skb) -{ - return NAPI_GRO_CB(skb)->data_offset; -} - -static inline unsigned int skb_gro_len(const struct sk_buff *skb) -{ - return skb->len - NAPI_GRO_CB(skb)->data_offset; -} - -static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) -{ - NAPI_GRO_CB(skb)->data_offset += len; -} - -static inline void *skb_gro_header_fast(struct sk_buff *skb, - unsigned int offset) -{ - return NAPI_GRO_CB(skb)->frag0 + offset; -} - -static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) -{ - return NAPI_GRO_CB(skb)->frag0_len < hlen; -} - -static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) -{ - NAPI_GRO_CB(skb)->frag0 = NULL; - NAPI_GRO_CB(skb)->frag0_len = 0; -} - -static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, - unsigned int offset) -{ - if (!pskb_may_pull(skb, hlen)) - return NULL; - - skb_gro_frag0_invalidate(skb); - return skb->data + offset; -} - -static inline void *skb_gro_network_header(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + - skb_network_offset(skb); -} - -static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, - const void *start, unsigned int len) -{ - if (NAPI_GRO_CB(skb)->csum_valid) - NAPI_GRO_CB(skb)->csum = csum_sub(NAPI_GRO_CB(skb)->csum, - csum_partial(start, len, 0)); -} - -/* GRO checksum functions. These are logical equivalents of the normal - * checksum functions (in skbuff.h) except that they operate on the GRO - * offsets and fields in sk_buff. - */ - -__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); - -static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); -} - -static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, - bool zero_okay, - __sum16 check) -{ - return ((skb->ip_summed != CHECKSUM_PARTIAL || - skb_checksum_start_offset(skb) < - skb_gro_offset(skb)) && - !skb_at_gro_remcsum_start(skb) && - NAPI_GRO_CB(skb)->csum_cnt == 0 && - (!zero_okay || check)); -} - -static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, - __wsum psum) -{ - if (NAPI_GRO_CB(skb)->csum_valid && - !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) - return 0; - - NAPI_GRO_CB(skb)->csum = psum; - - return __skb_gro_checksum_complete(skb); -} - -static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) -{ - if (NAPI_GRO_CB(skb)->csum_cnt > 0) { - /* Consume a checksum from CHECKSUM_UNNECESSARY */ - NAPI_GRO_CB(skb)->csum_cnt--; - } else { - /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we - * verified a new top level checksum or an encapsulated one - * during GRO. This saves work if we fallback to normal path. - */ - __skb_incr_checksum_unnecessary(skb); - } -} - -#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ - compute_pseudo) \ -({ \ - __sum16 __ret = 0; \ - if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ - __ret = __skb_gro_checksum_validate_complete(skb, \ - compute_pseudo(skb, proto)); \ - if (!__ret) \ - skb_gro_incr_csum_unnecessary(skb); \ - __ret; \ -}) - -#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) - -#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ - compute_pseudo) \ - __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) - -#define skb_gro_checksum_simple_validate(skb) \ - __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) - -static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) -{ - return (NAPI_GRO_CB(skb)->csum_cnt == 0 && - !NAPI_GRO_CB(skb)->csum_valid); -} - -static inline void __skb_gro_checksum_convert(struct sk_buff *skb, - __wsum pseudo) -{ - NAPI_GRO_CB(skb)->csum = ~pseudo; - NAPI_GRO_CB(skb)->csum_valid = 1; -} - -#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ -do { \ - if (__skb_gro_checksum_convert_check(skb)) \ - __skb_gro_checksum_convert(skb, \ - compute_pseudo(skb, proto)); \ -} while (0) - -struct gro_remcsum { - int offset; - __wsum delta; -}; - -static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) -{ - grc->offset = 0; - grc->delta = 0; -} - -static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, - unsigned int off, size_t hdrlen, - int start, int offset, - struct gro_remcsum *grc, - bool nopartial) -{ - __wsum delta; - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); - - BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); - - if (!nopartial) { - NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; - return ptr; - } - - ptr = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, off + plen)) { - ptr = skb_gro_header_slow(skb, off + plen, off); - if (!ptr) - return NULL; - } - - delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, - start, offset); - - /* Adjust skb->csum since we changed the packet */ - NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); - - grc->offset = off + hdrlen + offset; - grc->delta = delta; - - return ptr; -} - -static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, - struct gro_remcsum *grc) -{ - void *ptr; - size_t plen = grc->offset + sizeof(u16); - - if (!grc->delta) - return; - - ptr = skb_gro_header_fast(skb, grc->offset); - if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { - ptr = skb_gro_header_slow(skb, plen, grc->offset); - if (!ptr) - return; - } - - remcsum_unadjust((__sum16 *)ptr, grc->delta); -} - -#ifdef CONFIG_XFRM_OFFLOAD -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - if (PTR_ERR(pp) != -EINPROGRESS) - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - if (PTR_ERR(pp) != -EINPROGRESS) { - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; - } -} -#else -static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) -{ - NAPI_GRO_CB(skb)->flush |= flush; -} -static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, - struct sk_buff *pp, - int flush, - struct gro_remcsum *grc) -{ - NAPI_GRO_CB(skb)->flush |= flush; - skb_gro_remcsum_cleanup(skb, grc); - skb->remcsum_offload = 0; -} -#endif static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, @@ -4007,6 +3672,7 @@ int netif_rx_ni(struct sk_buff *skb); int netif_rx_any_context(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); +void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); @@ -4080,7 +3746,6 @@ int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); int dev_change_proto_down(struct net_device *dev, bool proto_down); -int dev_change_proto_down_generic(struct net_device *dev, bool proto_down); void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask, u32 value); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); @@ -4156,6 +3821,7 @@ void netdev_run_todo(void); * @dev: network device * * Release reference to device to allow it to be freed. + * Try using dev_put_track() instead. */ static inline void dev_put(struct net_device *dev) { @@ -4173,6 +3839,7 @@ static inline void dev_put(struct net_device *dev) * @dev: network device * * Hold reference to device to keep it from being freed. + * Try using dev_hold_track() instead. */ static inline void dev_hold(struct net_device *dev) { @@ -4185,6 +3852,55 @@ static inline void dev_hold(struct net_device *dev) } } +static inline void netdev_tracker_alloc(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); +#endif +} + +static inline void netdev_tracker_free(struct net_device *dev, + netdevice_tracker *tracker) +{ +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER + ref_tracker_free(&dev->refcnt_tracker, tracker); +#endif +} + +static inline void dev_hold_track(struct net_device *dev, + netdevice_tracker *tracker, gfp_t gfp) +{ + if (dev) { + dev_hold(dev); + netdev_tracker_alloc(dev, tracker, gfp); + } +} + +static inline void dev_put_track(struct net_device *dev, + netdevice_tracker *tracker) +{ + if (dev) { + netdev_tracker_free(dev, tracker); + dev_put(dev); + } +} + +static inline void dev_replace_track(struct net_device *odev, + struct net_device *ndev, + netdevice_tracker *tracker, + gfp_t gfp) +{ + if (odev) + netdev_tracker_free(odev, tracker); + + dev_hold(ndev); + dev_put(odev); + + if (ndev) + netdev_tracker_alloc(ndev, tracker, gfp); +} + /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. @@ -4451,10 +4167,21 @@ static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) spin_unlock_bh(&txq->_xmit_lock); } +/* + * txq->trans_start can be read locklessly from dev_watchdog() + */ static inline void txq_trans_update(struct netdev_queue *txq) { if (txq->xmit_lock_owner != -1) - txq->trans_start = jiffies; + WRITE_ONCE(txq->trans_start, jiffies); +} + +static inline void txq_trans_cond_update(struct netdev_queue *txq) +{ + unsigned long now = jiffies; + + if (READ_ONCE(txq->trans_start) != now) + WRITE_ONCE(txq->trans_start, now); } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ @@ -4462,8 +4189,7 @@ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); - if (txq->trans_start != jiffies) - txq->trans_start = jiffies; + txq_trans_cond_update(txq); } /** @@ -4472,27 +4198,7 @@ static inline void netif_trans_update(struct net_device *dev) * * Get network device transmit lock */ -static inline void netif_tx_lock(struct net_device *dev) -{ - unsigned int i; - int cpu; - - spin_lock(&dev->tx_global_lock); - cpu = smp_processor_id(); - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* We are the only thread of execution doing a - * freeze, but we have to grab the _xmit_lock in - * order to synchronize with threads which are in - * the ->hard_start_xmit() handler and already - * checked the frozen bit. - */ - __netif_tx_lock(txq, cpu); - set_bit(__QUEUE_STATE_FROZEN, &txq->state); - __netif_tx_unlock(txq); - } -} +void netif_tx_lock(struct net_device *dev); static inline void netif_tx_lock_bh(struct net_device *dev) { @@ -4500,22 +4206,7 @@ static inline void netif_tx_lock_bh(struct net_device *dev) netif_tx_lock(dev); } -static inline void netif_tx_unlock(struct net_device *dev) -{ - unsigned int i; - - for (i = 0; i < dev->num_tx_queues; i++) { - struct netdev_queue *txq = netdev_get_tx_queue(dev, i); - - /* No need to grab the _xmit_lock here. If the - * queue is not stopped for another reason, we - * force a schedule. - */ - clear_bit(__QUEUE_STATE_FROZEN, &txq->state); - netif_schedule_queue(txq); - } - spin_unlock(&dev->tx_global_lock); -} +void netif_tx_unlock(struct net_device *dev); static inline void netif_tx_unlock_bh(struct net_device *dev) { @@ -4649,10 +4340,13 @@ void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ +void dev_addr_mod(struct net_device *dev, unsigned int offset, + const void *addr, size_t len); + static inline void __dev_addr_set(struct net_device *dev, const void *addr, size_t len) { - memcpy(dev->dev_addr, addr, len); + dev_addr_mod(dev, 0, addr, len); } static inline void dev_addr_set(struct net_device *dev, const u8 *addr) @@ -4660,19 +4354,13 @@ static inline void dev_addr_set(struct net_device *dev, const u8 *addr) __dev_addr_set(dev, addr, dev->addr_len); } -static inline void -dev_addr_mod(struct net_device *dev, unsigned int offset, - const void *addr, size_t len) -{ - memcpy(&dev->dev_addr[offset], addr, len); -} - int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); void dev_addr_flush(struct net_device *dev); int dev_addr_init(struct net_device *dev); +void dev_addr_check(struct net_device *dev); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); @@ -5111,7 +4799,22 @@ static inline bool netif_needs_gso(struct sk_buff *skb, static inline void netif_set_gso_max_size(struct net_device *dev, unsigned int size) { - dev->gso_max_size = size; + /* dev->gso_max_size is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_max_size, size); +} + +static inline void netif_set_gso_max_segs(struct net_device *dev, + unsigned int segs) +{ + /* dev->gso_max_segs is read locklessly from sk_setup_caps() */ + WRITE_ONCE(dev->gso_max_segs, segs); +} + +static inline void netif_set_gro_max_size(struct net_device *dev, + unsigned int size) +{ + /* This pairs with the READ_ONCE() in skb_gro_receive() */ + WRITE_ONCE(dev->gro_max_size, size); } static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, @@ -5298,7 +5001,7 @@ void netdev_info(const struct net_device *dev, const char *format, ...); #define netdev_level_once(level, dev, fmt, ...) \ do { \ - static bool __print_once __read_mostly; \ + static bool __section(".data.once") __print_once; \ \ if (!__print_once) { \ __print_once = true; \ diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 3fda1a508733..15e71bfff726 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -381,13 +381,13 @@ struct nf_nat_hook { enum ip_conntrack_dir dir); }; -extern struct nf_nat_hook __rcu *nf_nat_hook; +extern const struct nf_nat_hook __rcu *nf_nat_hook; static inline void nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) { #if IS_ENABLED(CONFIG_NF_NAT) - struct nf_nat_hook *nat_hook; + const struct nf_nat_hook *nat_hook; rcu_read_lock(); nat_hook = rcu_dereference(nf_nat_hook); @@ -440,7 +440,6 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #if IS_ENABLED(CONFIG_NF_CONNTRACK) #include <linux/netfilter/nf_conntrack_zones_common.h> -extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu; void nf_ct_attach(struct sk_buff *, const struct sk_buff *); struct nf_conntrack_tuple; bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, @@ -463,8 +462,9 @@ struct nf_ct_hook { void (*destroy)(struct nf_conntrack *); bool (*get_tuple_skb)(struct nf_conntrack_tuple *, const struct sk_buff *); + void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb); }; -extern struct nf_ct_hook __rcu *nf_ct_hook; +extern const struct nf_ct_hook __rcu *nf_ct_hook; struct nlattr; @@ -479,7 +479,7 @@ struct nfnl_ct_hook { void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, s32 off); }; -extern struct nfnl_ct_hook __rcu *nfnl_ct_hook; +extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook; /** * nf_skb_duplicated - TEE target has sent a packet diff --git a/include/linux/netfilter/nf_conntrack_common.h b/include/linux/netfilter/nf_conntrack_common.h index 700ea077ce2d..2770db2fa080 100644 --- a/include/linux/netfilter/nf_conntrack_common.h +++ b/include/linux/netfilter/nf_conntrack_common.h @@ -2,7 +2,7 @@ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H -#include <linux/atomic.h> +#include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { @@ -25,19 +25,21 @@ struct ip_conntrack_stat { #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { - atomic_t use; + refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); + +/* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { - if (nfct && atomic_dec_and_test(&nfct->use)) + if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) - atomic_inc(&nfct->use); + refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index b71b57a83bb4..b4dd96e4dc8d 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -94,7 +94,7 @@ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, return skb; #endif - e = rcu_dereference(dev->nf_hooks_egress); + e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index e6a2d72e0dc7..bd19c4b91e31 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -24,6 +24,7 @@ union inet_addr { struct netpoll { struct net_device *dev; + netdevice_tracker dev_tracker; char dev_name[IFNAMSIZ]; const char *name; diff --git a/include/linux/once.h b/include/linux/once.h index d361fb14ac3a..f54523052bbc 100644 --- a/include/linux/once.h +++ b/include/linux/once.h @@ -38,7 +38,7 @@ void __do_once_done(bool *done, struct static_key_true *once_key, #define DO_ONCE(func, ...) \ ({ \ bool ___ret = false; \ - static bool ___done = false; \ + static bool __section(".data.once") ___done = false; \ static DEFINE_STATIC_KEY_TRUE(___once_key); \ if (static_branch_unlikely(&___once_key)) { \ unsigned long ___flags; \ diff --git a/include/linux/pcs-lynx.h b/include/linux/pcs-lynx.h index a6440d6ebe95..5712cc2ce775 100644 --- a/include/linux/pcs-lynx.h +++ b/include/linux/pcs-lynx.h @@ -9,13 +9,10 @@ #include <linux/mdio.h> #include <linux/phylink.h> -struct lynx_pcs { - struct phylink_pcs pcs; - struct mdio_device *mdio; -}; +struct mdio_device *lynx_get_mdio_device(struct phylink_pcs *pcs); -struct lynx_pcs *lynx_pcs_create(struct mdio_device *mdio); +struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio); -void lynx_pcs_destroy(struct lynx_pcs *pcs); +void lynx_pcs_destroy(struct phylink_pcs *pcs); #endif /* __LINUX_PCS_LYNX_H */ diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 411e34210fbf..474eaecd63ba 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -620,6 +620,7 @@ struct swevent_hlist { #define PERF_ATTACH_SCHED_CB 0x20 #define PERF_ATTACH_CHILD 0x40 +struct bpf_prog; struct perf_cgroup; struct perf_buffer; diff --git a/include/linux/phy.h b/include/linux/phy.h index cbf03a5f9cf5..6de8d7a90d78 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -99,7 +99,7 @@ extern const int phy_10gbit_features_array[1]; * @PHY_INTERFACE_MODE_RGMII_RXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RGMII_TXID: RGMII with Internal RX delay * @PHY_INTERFACE_MODE_RTBI: Reduced TBI - * @PHY_INTERFACE_MODE_SMII: ??? MII + * @PHY_INTERFACE_MODE_SMII: Serial MII * @PHY_INTERFACE_MODE_XGMII: 10 gigabit media-independent interface * @PHY_INTERFACE_MODE_XLGMII:40 gigabit media-independent interface * @PHY_INTERFACE_MODE_MOCA: Multimedia over Coax diff --git a/include/linux/phylink.h b/include/linux/phylink.h index f037470b6fb3..713a0c928b7c 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -20,6 +20,29 @@ enum { MLO_AN_PHY = 0, /* Conventional PHY */ MLO_AN_FIXED, /* Fixed-link mode */ MLO_AN_INBAND, /* In-band protocol */ + + MAC_SYM_PAUSE = BIT(0), + MAC_ASYM_PAUSE = BIT(1), + MAC_10HD = BIT(2), + MAC_10FD = BIT(3), + MAC_10 = MAC_10HD | MAC_10FD, + MAC_100HD = BIT(4), + MAC_100FD = BIT(5), + MAC_100 = MAC_100HD | MAC_100FD, + MAC_1000HD = BIT(6), + MAC_1000FD = BIT(7), + MAC_1000 = MAC_1000HD | MAC_1000FD, + MAC_2500FD = BIT(8), + MAC_5000FD = BIT(9), + MAC_10000FD = BIT(10), + MAC_20000FD = BIT(11), + MAC_25000FD = BIT(12), + MAC_40000FD = BIT(13), + MAC_50000FD = BIT(14), + MAC_56000FD = BIT(15), + MAC_100000FD = BIT(16), + MAC_200000FD = BIT(17), + MAC_400000FD = BIT(18), }; static inline bool phylink_autoneg_inband(unsigned int mode) @@ -61,6 +84,8 @@ enum phylink_op_type { * struct phylink_config - PHYLINK configuration structure * @dev: a pointer to a struct device associated with the MAC * @type: operation type of PHYLINK instance + * @legacy_pre_march2020: driver has not been updated for March 2020 updates + * (See commit 7cceb599d15d ("net: phylink: avoid mac_config calls") * @pcs_poll: MAC PCS cannot provide link change interrupt * @poll_fixed_state: if true, starts link_poll, * if MAC link is at %MLO_AN_FIXED mode. @@ -69,21 +94,25 @@ enum phylink_op_type { * if MAC link is at %MLO_AN_FIXED mode. * @supported_interfaces: bitmap describing which PHY_INTERFACE_MODE_xxx * are supported by the MAC/PCS. + * @mac_capabilities: MAC pause/speed/duplex capabilities. */ struct phylink_config { struct device *dev; enum phylink_op_type type; + bool legacy_pre_march2020; bool pcs_poll; bool poll_fixed_state; bool ovr_an_inband; void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + unsigned long mac_capabilities; }; /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. + * @mac_select_pcs: Select a PCS for the interface mode. * @mac_pcs_get_state: Read the current link state from the hardware. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. @@ -98,6 +127,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); + struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, + phy_interface_t interface); void (*mac_pcs_get_state)(struct phylink_config *config, struct phylink_link_state *state); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, @@ -150,6 +181,21 @@ struct phylink_mac_ops { */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); +/** + * mac_select_pcs: Select a PCS for the interface mode. + * @config: a pointer to a &struct phylink_config. + * @interface: PHY interface mode for PCS + * + * Return the &struct phylink_pcs for the specified interface mode, or + * NULL if none is required, or an error pointer on error. + * + * This must not modify any state. It is used to query which PCS should + * be used. Phylink will use this during validation to ensure that the + * configuration is valid, and when setting a configuration to internally + * set the PCS that will be used. + */ +struct phylink_pcs *mac_select_pcs(struct phylink_config *config, + phy_interface_t interface); /** * mac_pcs_get_state() - Read the current inband link state from the hardware @@ -162,6 +208,10 @@ void validate(struct phylink_config *config, unsigned long *supported, * negotiation completion state in @state->an_complete, and link up state * in @state->link. If possible, @state->lp_advertising should also be * populated. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_pcs_get_state(struct phylink_config *config, struct phylink_link_state *state); @@ -202,6 +252,15 @@ int mac_prepare(struct phylink_config *config, unsigned int mode, * guaranteed to be correct, and so any mac_config() implementation must * never reference these fields. * + * Note: For legacy March 2020 drivers (drivers with legacy_pre_march2020 set + * in their &phylnk_config and which don't have a PCS), this function will be + * called on each link up event, and to also change the in-band advert. For + * non-legacy drivers, it will only be called to reconfigure the MAC for a + * "major" change in e.g. interface mode. It will not be called for changes + * in speed, duplex or pause modes or to change the in-band advertisement. + * In any case, it is strongly preferred that speed, duplex and pause settings + * are handled in the mac_link_up() method and not in this method. + * * (this requires a rewrite - please refer to mac_link_up() for situations * where the PCS and MAC are not tightly integrated.) * @@ -286,6 +345,10 @@ int mac_finish(struct phylink_config *config, unsigned int mode, /** * mac_an_restart() - restart 802.3z BaseX autonegotiation * @config: a pointer to a &struct phylink_config. + * + * Note: This is a legacy method. This function will not be called unless + * legacy_pre_march2020 is set in &struct phylink_config and there is no + * PCS attached. */ void mac_an_restart(struct phylink_config *config); @@ -353,6 +416,7 @@ struct phylink_pcs { /** * struct phylink_pcs_ops - MAC PCS operations structure. + * @pcs_validate: validate the link configuration. * @pcs_get_state: read the current MAC PCS link state from the hardware. * @pcs_config: configure the MAC PCS for the selected mode and state. * @pcs_an_restart: restart 802.3z BaseX autonegotiation. @@ -360,6 +424,8 @@ struct phylink_pcs { * (where necessary). */ struct phylink_pcs_ops { + int (*pcs_validate)(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); void (*pcs_get_state)(struct phylink_pcs *pcs, struct phylink_link_state *state); int (*pcs_config)(struct phylink_pcs *pcs, unsigned int mode, @@ -373,6 +439,23 @@ struct phylink_pcs_ops { #if 0 /* For kernel-doc purposes only. */ /** + * pcs_validate() - validate the link configuration. + * @pcs: a pointer to a &struct phylink_pcs. + * @supported: ethtool bitmask for supported link modes. + * @state: a const pointer to a &struct phylink_link_state. + * + * Validate the interface mode, and advertising's autoneg bit, removing any + * media ethtool link modes that would not be supportable from the supported + * mask. Phylink will propagate the changes to the advertising mask. See the + * &struct phylink_mac_ops validate() method. + * + * Returns -EINVAL if the interface mode/autoneg mode is not supported. + * Returns non-zero positive if the link state can be supported. + */ +int pcs_validate(struct phylink_pcs *pcs, unsigned long *supported, + const struct phylink_link_state *state); + +/** * pcs_get_state() - Read the current inband link state from the hardware * @pcs: a pointer to a &struct phylink_pcs. * @state: a pointer to a &struct phylink_link_state. @@ -442,6 +525,12 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int mode, phy_interface_t interface, int speed, int duplex); #endif +void phylink_get_linkmodes(unsigned long *linkmodes, phy_interface_t interface, + unsigned long mac_capabilities); +void phylink_generic_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state); + struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, phy_interface_t iface, const struct phylink_mac_ops *mac_ops); @@ -496,11 +585,12 @@ void phylink_set_port_modes(unsigned long *bits); void phylink_set_10g_modes(unsigned long *mask); void phylink_helper_basex_speed(struct phylink_link_state *state); +void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state, + u16 bmsr, u16 lpa); void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs, struct phylink_link_state *state); -int phylink_mii_c22_pcs_set_advertisement(struct mdio_device *pcs, - phy_interface_t interface, - const unsigned long *advertising); +int phylink_mii_c22_pcs_encode_advertisement(phy_interface_t interface, + const unsigned long *advertising); int phylink_mii_c22_pcs_config(struct mdio_device *pcs, unsigned int mode, phy_interface_t interface, const unsigned long *advertising); diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h index 2e5565067355..554454cb8693 100644 --- a/include/linux/ptp_clock_kernel.h +++ b/include/linux/ptp_clock_kernel.h @@ -351,15 +351,17 @@ int ptp_get_vclocks_index(int pclock_index, int **vclock_index); * * @hwtstamps: skb_shared_hwtstamps structure pointer * @vclock_index: phc index of ptp vclock. + * + * Returns converted timestamp, or 0 on error. */ -void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index); +ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index); #else static inline int ptp_get_vclocks_index(int pclock_index, int **vclock_index) { return 0; } -static inline void ptp_convert_timestamp(struct skb_shared_hwtstamps *hwtstamps, - int vclock_index) -{ } +static inline ktime_t ptp_convert_timestamp(const struct skb_shared_hwtstamps *hwtstamps, + int vclock_index) +{ return 0; } #endif diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index 0dae7fcc5ef2..6dc4943d8aec 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -652,6 +652,7 @@ struct qed_dev_info { bool wol_support; bool smart_an; + bool esl; /* MBI version */ u32 mbi_version; @@ -807,6 +808,12 @@ struct qed_devlink { struct devlink_health_reporter *fw_reporter; }; +struct qed_sb_info_dbg { + u32 igu_prod; + u32 igu_cons; + u16 pi[PIS_PER_SB]; +}; + struct qed_common_cb_ops { void (*arfs_filter_op)(void *dev, void *fltr, u8 fw_rc); void (*link_update)(void *dev, struct qed_link_output *link); @@ -1194,6 +1201,13 @@ struct qed_common_ops { struct devlink* (*devlink_register)(struct qed_dev *cdev); void (*devlink_unregister)(struct devlink *devlink); + + __printf(2, 3) void (*mfw_report)(struct qed_dev *cdev, char *fmt, ...); + + int (*get_sb_info)(struct qed_dev *cdev, struct qed_sb_info *sb, + u16 qid, struct qed_sb_info_dbg *sb_dbg); + + int (*get_esl_status)(struct qed_dev *cdev, bool *esl_active); }; #define MASK_FIELD(_name, _value) \ diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h new file mode 100644 index 000000000000..c11c9db5825c --- /dev/null +++ b/include/linux/ref_tracker.h @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +#ifndef _LINUX_REF_TRACKER_H +#define _LINUX_REF_TRACKER_H +#include <linux/refcount.h> +#include <linux/types.h> +#include <linux/spinlock.h> + +struct ref_tracker; + +struct ref_tracker_dir { +#ifdef CONFIG_REF_TRACKER + spinlock_t lock; + unsigned int quarantine_avail; + refcount_t untracked; + struct list_head list; /* List of active trackers */ + struct list_head quarantine; /* List of dead trackers */ +#endif +}; + +#ifdef CONFIG_REF_TRACKER +static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, + unsigned int quarantine_count) +{ + INIT_LIST_HEAD(&dir->list); + INIT_LIST_HEAD(&dir->quarantine); + spin_lock_init(&dir->lock); + dir->quarantine_avail = quarantine_count; + refcount_set(&dir->untracked, 1); +} + +void ref_tracker_dir_exit(struct ref_tracker_dir *dir); + +void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit); + +int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, gfp_t gfp); + +int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp); + +#else /* CONFIG_REF_TRACKER */ + +static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir, + unsigned int quarantine_count) +{ +} + +static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir) +{ +} + +static inline void ref_tracker_dir_print(struct ref_tracker_dir *dir, + unsigned int display_limit) +{ +} + +static inline int ref_tracker_alloc(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp, + gfp_t gfp) +{ + return 0; +} + +static inline int ref_tracker_free(struct ref_tracker_dir *dir, + struct ref_tracker **trackerp) +{ + return 0; +} + +#endif + +#endif /* _LINUX_REF_TRACKER_H */ diff --git a/include/linux/regmap.h b/include/linux/regmap.h index e3c9a25a853a..22652e5fbc38 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -290,6 +290,11 @@ typedef void (*regmap_unlock)(void *); * read operation on a bus such as SPI, I2C, etc. Most of the * devices do not need this. * @reg_write: Same as above for writing. + * @reg_update_bits: Optional callback that if filled will be used to perform + * all the update_bits(rmw) operation. Should only be provided + * if the function require special handling with lock and reg + * handling and the operation cannot be represented as a simple + * update_bits operation on a bus such as SPI, I2C, etc. * @fast_io: Register IO is fast. Use a spinlock instead of a mutex * to perform locking. This field is ignored if custom lock/unlock * functions are used (see fields lock/unlock of struct regmap_config). @@ -372,6 +377,8 @@ struct regmap_config { int (*reg_read)(void *context, unsigned int reg, unsigned int *val); int (*reg_write)(void *context, unsigned int reg, unsigned int val); + int (*reg_update_bits)(void *context, unsigned int reg, + unsigned int mask, unsigned int val); bool fast_io; diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h index 231e06b74b50..c35f3962dc4f 100644 --- a/include/linux/rfkill.h +++ b/include/linux/rfkill.h @@ -230,6 +230,13 @@ void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw); bool rfkill_blocked(struct rfkill *rfkill); /** + * rfkill_soft_blocked - Query soft rfkill block state + * + * @rfkill: rfkill struct to query + */ +bool rfkill_soft_blocked(struct rfkill *rfkill); + +/** * rfkill_find_type - Helper for finding rfkill type by name * @name: the name of the type * diff --git a/include/linux/seq_file_net.h b/include/linux/seq_file_net.h index 0fdbe1ddd8d1..b97912fdbae7 100644 --- a/include/linux/seq_file_net.h +++ b/include/linux/seq_file_net.h @@ -9,7 +9,8 @@ extern struct net init_net; struct seq_net_private { #ifdef CONFIG_NET_NS - struct net *net; + struct net *net; + netns_tracker ns_tracker; #endif }; diff --git a/include/linux/siphash.h b/include/linux/siphash.h index 0cda61855d90..cce8a9acc76c 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -21,6 +21,8 @@ typedef struct { u64 key[2]; } siphash_key_t; +#define siphash_aligned_key_t siphash_key_t __aligned(16) + static inline bool siphash_key_is_zero(const siphash_key_t *key) { return !(key->key[0] | key->key[1]); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 4507d77d6941..bf11e1fbd69b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -36,6 +36,7 @@ #include <linux/splice.h> #include <linux/in6.h> #include <linux/if_packet.h> +#include <linux/llist.h> #include <net/flow.h> #include <net/page_pool.h> #if IS_ENABLED(CONFIG_NF_CONNTRACK) @@ -287,14 +288,18 @@ struct tc_skb_ext { __u32 chain; __u16 mru; __u16 zone; - bool post_ct; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; }; #endif struct sk_buff_head { - /* These two members must be first. */ - struct sk_buff *next; - struct sk_buff *prev; + /* These two members must be first to match sk_buff. */ + struct_group_tagged(sk_buff_list, list, + struct sk_buff *next; + struct sk_buff *prev; + ); __u32 qlen; spinlock_t lock; @@ -302,6 +307,22 @@ struct sk_buff_head { struct sk_buff; +/* The reason of skb drop, which is used in kfree_skb_reason(). + * en...maybe they should be splited by group? + * + * Each item here should also be in 'TRACE_SKB_DROP_REASON', which is + * used to translate the reason to string. + */ +enum skb_drop_reason { + SKB_DROP_REASON_NOT_SPECIFIED, + SKB_DROP_REASON_NO_SOCKET, + SKB_DROP_REASON_PKT_TOO_SMALL, + SKB_DROP_REASON_TCP_CSUM, + SKB_DROP_REASON_TCP_FILTER, + SKB_DROP_REASON_UDP_CSUM, + SKB_DROP_REASON_MAX, +}; + /* To allow 64K frame to be packed as single skb without frag_list we * require 64K/PAGE_SIZE pages plus 1 additional page to allow for * buffers which do not start on a page boundary. @@ -627,6 +648,7 @@ typedef unsigned char *sk_buff_data_t; * for retransmit timer * @rbnode: RB tree node, alternative to next/prev for netem/tcp * @list: queue head + * @ll_node: anchor in an llist (eg socket defer_list) * @sk: Socket we are owned by * @ip_defrag_offset: (aka @sk) alternate use of @sk, used in * fragmentation management @@ -729,7 +751,7 @@ typedef unsigned char *sk_buff_data_t; struct sk_buff { union { struct { - /* These two members must be first. */ + /* These two members must be first to match sk_buff_head. */ struct sk_buff *next; struct sk_buff *prev; @@ -744,6 +766,7 @@ struct sk_buff { }; struct rb_node rbnode; /* used in netem, ip4 defrag, and tcp stack */ struct list_head list; + struct llist_node ll_node; }; union { @@ -793,7 +816,7 @@ struct sk_buff { #else #define CLONED_MASK 1 #endif -#define CLONED_OFFSET() offsetof(struct sk_buff, __cloned_offset) +#define CLONED_OFFSET offsetof(struct sk_buff, __cloned_offset) /* private: */ __u8 __cloned_offset[0]; @@ -809,25 +832,15 @@ struct sk_buff { __u8 active_extensions; #endif - /* fields enclosed in headers_start/headers_end are copied + /* Fields enclosed in headers group are copied * using a single memcpy() in __copy_skb_header() */ - /* private: */ - __u32 headers_start[0]; - /* public: */ - -/* if you move pkt_type around you also must adapt those constants */ -#ifdef __BIG_ENDIAN_BITFIELD -#define PKT_TYPE_MAX (7 << 5) -#else -#define PKT_TYPE_MAX 7 -#endif -#define PKT_TYPE_OFFSET() offsetof(struct sk_buff, __pkt_type_offset) + struct_group(headers, /* private: */ __u8 __pkt_type_offset[0]; /* public: */ - __u8 pkt_type:3; + __u8 pkt_type:3; /* see PKT_TYPE_MAX */ __u8 ignore_df:1; __u8 nf_trace:1; __u8 ip_summed:2; @@ -843,16 +856,10 @@ struct sk_buff { __u8 encap_hdr_csum:1; __u8 csum_valid:1; -#ifdef __BIG_ENDIAN_BITFIELD -#define PKT_VLAN_PRESENT_BIT 7 -#else -#define PKT_VLAN_PRESENT_BIT 0 -#endif -#define PKT_VLAN_PRESENT_OFFSET() offsetof(struct sk_buff, __pkt_vlan_present_offset) /* private: */ __u8 __pkt_vlan_present_offset[0]; /* public: */ - __u8 vlan_present:1; + __u8 vlan_present:1; /* See PKT_VLAN_PRESENT_BIT */ __u8 csum_complete_sw:1; __u8 csum_level:2; __u8 csum_not_inet:1; @@ -933,9 +940,7 @@ struct sk_buff { u64 kcov_handle; #endif - /* private: */ - __u32 headers_end[0]; - /* public: */ + ); /* end headers group */ /* These elements must be at the end, see alloc_skb() for details. */ sk_buff_data_t tail; @@ -951,6 +956,22 @@ struct sk_buff { #endif }; +/* if you move pkt_type around you also must adapt those constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_TYPE_MAX (7 << 5) +#else +#define PKT_TYPE_MAX 7 +#endif +#define PKT_TYPE_OFFSET offsetof(struct sk_buff, __pkt_type_offset) + +/* if you move pkt_vlan_present around you also must adapt these constants */ +#ifdef __BIG_ENDIAN_BITFIELD +#define PKT_VLAN_PRESENT_BIT 7 +#else +#define PKT_VLAN_PRESENT_BIT 0 +#endif +#define PKT_VLAN_PRESENT_OFFSET offsetof(struct sk_buff, __pkt_vlan_present_offset) + #ifdef __KERNEL__ /* * Handling routines are only of interest to the kernel @@ -1082,8 +1103,18 @@ static inline bool skb_unref(struct sk_buff *skb) return true; } +void kfree_skb_reason(struct sk_buff *skb, enum skb_drop_reason reason); + +/** + * kfree_skb - free an sk_buff with 'NOT_SPECIFIED' reason + * @skb: buffer to free + */ +static inline void kfree_skb(struct sk_buff *skb) +{ + kfree_skb_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); +} + void skb_release_head_state(struct sk_buff *skb); -void kfree_skb(struct sk_buff *skb); void kfree_skb_list(struct sk_buff *segs); void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt); void skb_tx_error(struct sk_buff *skb); @@ -1976,8 +2007,8 @@ static inline void __skb_insert(struct sk_buff *newsk, */ WRITE_ONCE(newsk->next, next); WRITE_ONCE(newsk->prev, prev); - WRITE_ONCE(next->prev, newsk); - WRITE_ONCE(prev->next, newsk); + WRITE_ONCE(((struct sk_buff_list *)next)->prev, newsk); + WRITE_ONCE(((struct sk_buff_list *)prev)->next, newsk); WRITE_ONCE(list->qlen, list->qlen + 1); } @@ -2073,7 +2104,7 @@ static inline void __skb_queue_after(struct sk_buff_head *list, struct sk_buff *prev, struct sk_buff *newsk) { - __skb_insert(newsk, prev, prev->next, list); + __skb_insert(newsk, prev, ((struct sk_buff_list *)prev)->next, list); } void skb_append(struct sk_buff *old, struct sk_buff *newsk, @@ -2083,7 +2114,7 @@ static inline void __skb_queue_before(struct sk_buff_head *list, struct sk_buff *next, struct sk_buff *newsk) { - __skb_insert(newsk, next->prev, next, list); + __skb_insert(newsk, ((struct sk_buff_list *)next)->prev, next, list); } /** @@ -2373,6 +2404,8 @@ static inline void *skb_pull_inline(struct sk_buff *skb, unsigned int len) return unlikely(len > skb->len) ? NULL : __skb_pull(skb, len); } +void *skb_pull_data(struct sk_buff *skb, size_t len); + void *__pskb_pull_tail(struct sk_buff *skb, int delta); static inline void *__pskb_pull(struct sk_buff *skb, unsigned int len) @@ -3485,7 +3518,12 @@ __skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - __skb_postpull_rcsum(skb, start, len, 0); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = wsum_negate(csum_partial(start, len, + wsum_negate(skb->csum))); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; } static __always_inline void diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 584d94be9c8b..18a717fe62eb 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -507,12 +507,6 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock) return !!psock->saved_data_ready; } -static inline bool sk_is_tcp(const struct sock *sk) -{ - return sk->sk_type == SOCK_STREAM && - sk->sk_protocol == IPPROTO_TCP; -} - static inline bool sk_is_udp(const struct sock *sk) { return sk->sk_type == SOCK_DGRAM && diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index a6f03b36fc4f..24eea1b05ca2 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -233,6 +233,7 @@ struct plat_stmmacenet_data { int (*clks_config)(void *priv, bool enabled); int (*crosststamp)(ktime_t *device, struct system_counterval_t *system, void *ctx); + void (*dump_debug_regs)(void *priv); void *bsp_priv; struct clk *stmmac_clk; struct clk *pclk; @@ -241,6 +242,7 @@ struct plat_stmmacenet_data { unsigned int clk_ref_rate; unsigned int mult_fact_100ns; s32 ptp_max_adj; + u32 cdc_error_adj; struct reset_control *stmmac_rst; struct reset_control *stmmac_ahb_rst; struct stmmac_axi *axi; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 48d8a363319e..78b91bb92f0d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -512,11 +512,13 @@ static inline u16 tcp_mss_clamp(const struct tcp_sock *tp, u16 mss) int tcp_skb_shift(struct sk_buff *to, struct sk_buff *from, int pcount, int shiftlen); +void __tcp_sock_set_cork(struct sock *sk, bool on); void tcp_sock_set_cork(struct sock *sk, bool on); int tcp_sock_set_keepcnt(struct sock *sk, int val); int tcp_sock_set_keepidle_locked(struct sock *sk, int val); int tcp_sock_set_keepidle(struct sock *sk, int val); int tcp_sock_set_keepintvl(struct sock *sk, int val); +void __tcp_sock_set_nodelay(struct sock *sk, bool on); void tcp_sock_set_nodelay(struct sock *sk); void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index e8ec116c916b..6ad4e9032d53 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -66,7 +66,7 @@ #include <linux/seqlock.h> struct u64_stats_sync { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) seqcount_t seq; #endif }; @@ -125,7 +125,7 @@ static inline void u64_stats_inc(u64_stats_t *p) } #endif -#if BITS_PER_LONG == 32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) #define u64_stats_init(syncp) seqcount_init(&(syncp)->seq) #else static inline void u64_stats_init(struct u64_stats_sync *syncp) @@ -135,15 +135,19 @@ static inline void u64_stats_init(struct u64_stats_sync *syncp) static inline void u64_stats_update_begin(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); write_seqcount_begin(&syncp->seq); #endif } static inline void u64_stats_update_end(struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); #endif } @@ -152,8 +156,11 @@ u64_stats_update_begin_irqsave(struct u64_stats_sync *syncp) { unsigned long flags = 0; -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - local_irq_save(flags); +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_disable(); + else + local_irq_save(flags); write_seqcount_begin(&syncp->seq); #endif return flags; @@ -163,15 +170,18 @@ static inline void u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, unsigned long flags) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) write_seqcount_end(&syncp->seq); - local_irq_restore(flags); + if (IS_ENABLED(CONFIG_PREEMPT_RT)) + preempt_enable(); + else + local_irq_restore(flags); #endif } static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_begin(&syncp->seq); #else return 0; @@ -180,7 +190,7 @@ static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync * static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -189,7 +199,7 @@ static inline unsigned int u64_stats_fetch_begin(const struct u64_stats_sync *sy static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT)) return read_seqcount_retry(&syncp->seq, start); #else return false; @@ -199,7 +209,7 @@ static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp, static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && (!defined(CONFIG_SMP) && !defined(CONFIG_PREEMPT_RT)) preempt_enable(); #endif return __u64_stats_fetch_retry(syncp, start); @@ -213,7 +223,9 @@ static inline bool u64_stats_fetch_retry(const struct u64_stats_sync *syncp, */ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync *syncp) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_disable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_disable(); #endif return __u64_stats_fetch_begin(syncp); @@ -222,7 +234,9 @@ static inline unsigned int u64_stats_fetch_begin_irq(const struct u64_stats_sync static inline bool u64_stats_fetch_retry_irq(const struct u64_stats_sync *syncp, unsigned int start) { -#if BITS_PER_LONG==32 && !defined(CONFIG_SMP) +#if BITS_PER_LONG == 32 && defined(CONFIG_PREEMPT_RT) + preempt_enable(); +#elif BITS_PER_LONG == 32 && !defined(CONFIG_SMP) local_irq_enable(); #endif return __u64_stats_fetch_retry(syncp, start); diff --git a/include/linux/wwan.h b/include/linux/wwan.h index 9fac819f92e3..afb3334ec8c5 100644 --- a/include/linux/wwan.h +++ b/include/linux/wwan.h @@ -4,12 +4,9 @@ #ifndef __WWAN_H #define __WWAN_H -#include <linux/device.h> -#include <linux/kernel.h> #include <linux/poll.h> -#include <linux/skbuff.h> -#include <linux/netlink.h> #include <linux/netdevice.h> +#include <linux/types.h> /** * enum wwan_port_type - WWAN port types @@ -37,6 +34,10 @@ enum wwan_port_type { WWAN_PORT_UNKNOWN, }; +struct device; +struct file; +struct netlink_ext_ack; +struct sk_buff; struct wwan_port; /** struct wwan_port_ops - The WWAN port operations @@ -171,4 +172,13 @@ int wwan_register_ops(struct device *parent, const struct wwan_ops *ops, void wwan_unregister_ops(struct device *parent); +#ifdef CONFIG_WWAN_DEBUGFS +struct dentry *wwan_get_debugfs_dir(struct device *parent); +#else +static inline struct dentry *wwan_get_debugfs_dir(struct device *parent) +{ + return ERR_PTR(-ENODEV); +} +#endif + #endif /* __WWAN_H */ diff --git a/include/net/act_api.h b/include/net/act_api.h index b5b624c7e488..3049cb69c025 100644 --- a/include/net/act_api.h +++ b/include/net/act_api.h @@ -7,6 +7,7 @@ */ #include <linux/refcount.h> +#include <net/flow_offload.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/net_namespace.h> @@ -44,6 +45,7 @@ struct tc_action { u8 hw_stats; u8 used_hw_stats; bool used_hw_stats_valid; + u32 in_hw_count; }; #define tcf_index common.tcfa_index #define tcf_refcnt common.tcfa_refcnt @@ -88,6 +90,16 @@ static inline void tcf_tm_dump(struct tcf_t *dtm, const struct tcf_t *stm) dtm->expires = jiffies_to_clock_t(stm->expires); } +static inline enum flow_action_hw_stats tc_act_hw_stats(u8 hw_stats) +{ + if (WARN_ON_ONCE(hw_stats > TCA_ACT_HW_STATS_ANY)) + return FLOW_ACTION_HW_STATS_DONT_CARE; + else if (!hw_stats) + return FLOW_ACTION_HW_STATS_DISABLED; + + return hw_stats; +} + #ifdef CONFIG_NET_CLS_ACT #define ACT_P_CREATED 1 @@ -121,6 +133,8 @@ struct tc_action_ops { struct psample_group * (*get_psample_group)(const struct tc_action *a, tc_action_priv_destructor *destructor); + int (*offload_act_setup)(struct tc_action *act, void *entry_data, + u32 *index_inc, bool bind); }; struct tc_action_net { @@ -189,7 +203,7 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions, int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla, struct nlattr *est, struct tc_action *actions[], int init_res[], size_t *attr_size, - u32 flags, struct netlink_ext_ack *extack); + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); struct tc_action_ops *tc_action_load_ops(struct nlattr *nla, bool police, bool rtnl_held, struct netlink_ext_ack *extack); @@ -240,6 +254,9 @@ void tcf_action_update_stats(struct tc_action *a, u64 bytes, u64 packets, u64 drops, bool hw); int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int); +int tcf_action_update_hw_stats(struct tc_action *action); +int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, + void *cb_priv, bool add); int tcf_action_check_ctrlact(int action, struct tcf_proto *tp, struct tcf_chain **handle, struct netlink_ext_ack *newchain); @@ -251,6 +268,14 @@ DECLARE_STATIC_KEY_FALSE(tcf_frag_xmit_count); #endif int tcf_dev_queue_xmit(struct sk_buff *skb, int (*xmit)(struct sk_buff *skb)); + +#else /* !CONFIG_NET_CLS_ACT */ + +static inline int tcf_action_reoffload_cb(flow_indr_block_bind_cb_t *cb, + void *cb_priv, bool add) { + return 0; +} + #endif /* CONFIG_NET_CLS_ACT */ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes, diff --git a/include/net/af_unix.h b/include/net/af_unix.h index 7d142e8a0550..a7ef624ed726 100644 --- a/include/net/af_unix.h +++ b/include/net/af_unix.h @@ -20,13 +20,12 @@ struct sock *unix_peer_get(struct sock *sk); #define UNIX_HASH_BITS 8 extern unsigned int unix_tot_inflight; -extern spinlock_t unix_table_lock; +extern spinlock_t unix_table_locks[2 * UNIX_HASH_SIZE]; extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; struct unix_address { refcount_t refcnt; int len; - unsigned int hash; struct sockaddr_un name[]; }; diff --git a/include/net/arp.h b/include/net/arp.h index 4950191f6b2b..031374ac2f22 100644 --- a/include/net/arp.h +++ b/include/net/arp.h @@ -53,13 +53,7 @@ static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); - if (n) { - unsigned long now = jiffies; - - /* avoid dirtying neighbour */ - if (READ_ONCE(n->confirmed) != now) - WRITE_ONCE(n->confirmed, now); - } + neigh_confirm(n); rcu_read_unlock_bh(); } diff --git a/include/net/ax25.h b/include/net/ax25.h index 03d409de61ad..526e49589197 100644 --- a/include/net/ax25.h +++ b/include/net/ax25.h @@ -229,7 +229,10 @@ struct ctl_table; typedef struct ax25_dev { struct ax25_dev *next; + struct net_device *dev; + netdevice_tracker dev_tracker; + struct net_device *forward; struct ctl_table_header *sysheader; int values[AX25_MAX_VALUES]; diff --git a/include/net/bareudp.h b/include/net/bareudp.h index dc65a0d71d9b..17610c8d6361 100644 --- a/include/net/bareudp.h +++ b/include/net/bareudp.h @@ -3,21 +3,10 @@ #ifndef __NET_BAREUDP_H #define __NET_BAREUDP_H +#include <linux/netdevice.h> #include <linux/types.h> -#include <linux/skbuff.h> #include <net/rtnetlink.h> -struct bareudp_conf { - __be16 ethertype; - __be16 port; - u16 sport_min; - bool multi_proto_mode; -}; - -struct net_device *bareudp_dev_create(struct net *net, const char *name, - u8 name_assign_type, - struct bareudp_conf *info); - static inline bool netif_is_bareudp(const struct net_device *dev) { return dev->rtnl_link_ops && diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 3271870fd85e..4b3d0b16c185 100644 --- a/include/net/bluetooth/bluetooth.h +++ b/include/net/bluetooth/bluetooth.h @@ -380,6 +380,7 @@ typedef void (*hci_req_complete_skb_t)(struct hci_dev *hdev, u8 status, #define HCI_REQ_SKB BIT(1) struct hci_ctrl { + struct sock *sk; u16 opcode; u8 req_flags; u8 req_event; @@ -389,6 +390,11 @@ struct hci_ctrl { }; }; +struct mgmt_ctrl { + struct hci_dev *hdev; + u16 opcode; +}; + struct bt_skb_cb { u8 pkt_type; u8 force_active; @@ -398,6 +404,7 @@ struct bt_skb_cb { struct l2cap_ctrl l2cap; struct sco_ctrl sco; struct hci_ctrl hci; + struct mgmt_ctrl mgmt; }; }; #define bt_cb(skb) ((struct bt_skb_cb *)((skb)->cb)) @@ -405,6 +412,8 @@ struct bt_skb_cb { #define hci_skb_pkt_type(skb) bt_cb((skb))->pkt_type #define hci_skb_expect(skb) bt_cb((skb))->expect #define hci_skb_opcode(skb) bt_cb((skb))->hci.opcode +#define hci_skb_event(skb) bt_cb((skb))->hci.req_event +#define hci_skb_sk(skb) bt_cb((skb))->hci.sk static inline struct sk_buff *bt_skb_alloc(unsigned int len, gfp_t how) { diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 63065bc01b76..35c073d44ec5 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -246,6 +246,15 @@ enum { * HCI after resume. */ HCI_QUIRK_NO_SUSPEND_NOTIFIER, + + /* + * When this quirk is set, LE tx power is not queried on startup + * and the min/max tx power values default to HCI_TX_POWER_INVALID. + * + * This quirk can be set before hci_register_dev is called or + * during the hdev->setup vendor callback. + */ + HCI_QUIRK_BROKEN_READ_TRANSMIT_POWER, }; /* HCI device flags */ @@ -332,6 +341,7 @@ enum { HCI_FORCE_NO_MITM, HCI_QUALITY_REPORT, HCI_OFFLOAD_CODECS_ENABLED, + HCI_LE_SIMULTANEOUS_ROLES, __HCI_NUM_FLAGS, }; @@ -566,6 +576,7 @@ enum { #define HCI_ERROR_INVALID_LL_PARAMS 0x1e #define HCI_ERROR_UNSPECIFIED 0x1f #define HCI_ERROR_ADVERTISING_TIMEOUT 0x3c +#define HCI_ERROR_CANCELLED_BY_HOST 0x44 /* Flow control modes */ #define HCI_FLOW_CTL_MODE_PACKET_BASED 0x00 @@ -1046,8 +1057,8 @@ struct hci_cp_read_stored_link_key { } __packed; struct hci_rp_read_stored_link_key { __u8 status; - __u8 max_keys; - __u8 num_keys; + __le16 max_keys; + __le16 num_keys; } __packed; #define HCI_OP_DELETE_STORED_LINK_KEY 0x0c12 @@ -1057,7 +1068,7 @@ struct hci_cp_delete_stored_link_key { } __packed; struct hci_rp_delete_stored_link_key { __u8 status; - __u8 num_keys; + __le16 num_keys; } __packed; #define HCI_MAX_NAME_LENGTH 248 @@ -1930,6 +1941,16 @@ struct hci_rp_le_read_transmit_power { __s8 max_le_tx_power; } __packed; +#define HCI_NETWORK_PRIVACY 0x00 +#define HCI_DEVICE_PRIVACY 0x01 + +#define HCI_OP_LE_SET_PRIVACY_MODE 0x204e +struct hci_cp_le_set_privacy_mode { + __u8 bdaddr_type; + bdaddr_t bdaddr; + __u8 mode; +} __packed; + #define HCI_OP_LE_READ_BUFFER_SIZE_V2 0x2060 struct hci_rp_le_read_buffer_size_v2 { __u8 status; @@ -2011,6 +2032,10 @@ struct hci_cp_le_reject_cis { } __packed; /* ---- HCI Events ---- */ +struct hci_ev_status { + __u8 status; +} __packed; + #define HCI_EV_INQUIRY_COMPLETE 0x01 #define HCI_EV_INQUIRY_RESULT 0x02 @@ -2023,6 +2048,11 @@ struct inquiry_info { __le16 clock_offset; } __packed; +struct hci_ev_inquiry_result { + __u8 num; + struct inquiry_info info[]; +}; + #define HCI_EV_CONN_COMPLETE 0x03 struct hci_ev_conn_complete { __u8 status; @@ -2134,7 +2164,7 @@ struct hci_comp_pkts_info { } __packed; struct hci_ev_num_comp_pkts { - __u8 num_hndl; + __u8 num; struct hci_comp_pkts_info handles[]; } __packed; @@ -2184,7 +2214,7 @@ struct hci_ev_pscan_rep_mode { } __packed; #define HCI_EV_INQUIRY_RESULT_WITH_RSSI 0x22 -struct inquiry_info_with_rssi { +struct inquiry_info_rssi { bdaddr_t bdaddr; __u8 pscan_rep_mode; __u8 pscan_period_mode; @@ -2192,7 +2222,7 @@ struct inquiry_info_with_rssi { __le16 clock_offset; __s8 rssi; } __packed; -struct inquiry_info_with_rssi_and_pscan_mode { +struct inquiry_info_rssi_pscan { bdaddr_t bdaddr; __u8 pscan_rep_mode; __u8 pscan_period_mode; @@ -2201,6 +2231,10 @@ struct inquiry_info_with_rssi_and_pscan_mode { __le16 clock_offset; __s8 rssi; } __packed; +struct hci_ev_inquiry_result_rssi { + __u8 num; + __u8 data[]; +} __packed; #define HCI_EV_REMOTE_EXT_FEATURES 0x23 struct hci_ev_remote_ext_features { @@ -2255,6 +2289,11 @@ struct extended_inquiry_info { __u8 data[240]; } __packed; +struct hci_ev_ext_inquiry_result { + __u8 num; + struct extended_inquiry_info info[]; +} __packed; + #define HCI_EV_KEY_REFRESH_COMPLETE 0x30 struct hci_ev_key_refresh_complete { __u8 status; @@ -2422,13 +2461,18 @@ struct hci_ev_le_conn_complete { #define HCI_EV_LE_ADVERTISING_REPORT 0x02 struct hci_ev_le_advertising_info { - __u8 evt_type; + __u8 type; __u8 bdaddr_type; bdaddr_t bdaddr; __u8 length; __u8 data[]; } __packed; +struct hci_ev_le_advertising_report { + __u8 num; + struct hci_ev_le_advertising_info info[]; +} __packed; + #define HCI_EV_LE_CONN_UPDATE_COMPLETE 0x03 struct hci_ev_le_conn_update_complete { __u8 status; @@ -2472,7 +2516,7 @@ struct hci_ev_le_data_len_change { #define HCI_EV_LE_DIRECT_ADV_REPORT 0x0B struct hci_ev_le_direct_adv_info { - __u8 evt_type; + __u8 type; __u8 bdaddr_type; bdaddr_t bdaddr; __u8 direct_addr_type; @@ -2480,6 +2524,11 @@ struct hci_ev_le_direct_adv_info { __s8 rssi; } __packed; +struct hci_ev_le_direct_adv_report { + __u8 num; + struct hci_ev_le_direct_adv_info info[]; +} __packed; + #define HCI_EV_LE_PHY_UPDATE_COMPLETE 0x0c struct hci_ev_le_phy_update_complete { __u8 status; @@ -2489,8 +2538,8 @@ struct hci_ev_le_phy_update_complete { } __packed; #define HCI_EV_LE_EXT_ADV_REPORT 0x0d -struct hci_ev_le_ext_adv_report { - __le16 evt_type; +struct hci_ev_le_ext_adv_info { + __le16 type; __u8 bdaddr_type; bdaddr_t bdaddr; __u8 primary_phy; @@ -2498,11 +2547,16 @@ struct hci_ev_le_ext_adv_report { __u8 sid; __u8 tx_power; __s8 rssi; - __le16 interval; - __u8 direct_addr_type; + __le16 interval; + __u8 direct_addr_type; bdaddr_t direct_addr; - __u8 length; - __u8 data[]; + __u8 length; + __u8 data[]; +} __packed; + +struct hci_ev_le_ext_adv_report { + __u8 num; + struct hci_ev_le_ext_adv_info info[]; } __packed; #define HCI_EV_LE_ENHANCED_CONN_COMPLETE 0x0a diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index dd8840e70e25..586f69d084a2 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -30,6 +30,7 @@ #include <linux/rculist.h> #include <net/bluetooth/hci.h> +#include <net/bluetooth/hci_sync.h> #include <net/bluetooth/hci_sock.h> /* HCI priority */ @@ -87,6 +88,7 @@ struct discovery_state { u8 (*uuids)[16]; unsigned long scan_start; unsigned long scan_duration; + unsigned long name_resolve_timeout; }; #define SUSPEND_NOTIFIER_TIMEOUT msecs_to_jiffies(2000) /* 2 seconds */ @@ -150,22 +152,22 @@ struct bdaddr_list_with_irk { u8 local_irk[16]; }; -struct bdaddr_list_with_flags { - struct list_head list; - bdaddr_t bdaddr; - u8 bdaddr_type; - u32 current_flags; -}; - enum hci_conn_flags { HCI_CONN_FLAG_REMOTE_WAKEUP, - HCI_CONN_FLAG_MAX -}; + HCI_CONN_FLAG_DEVICE_PRIVACY, -#define hci_conn_test_flag(nr, flags) ((flags) & (1U << nr)) + __HCI_CONN_NUM_FLAGS, +}; /* Make sure number of flags doesn't exceed sizeof(current_flags) */ -static_assert(HCI_CONN_FLAG_MAX < 32); +static_assert(__HCI_CONN_NUM_FLAGS < 32); + +struct bdaddr_list_with_flags { + struct list_head list; + bdaddr_t bdaddr; + u8 bdaddr_type; + DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); +}; struct bt_uuid { struct list_head list; @@ -351,8 +353,8 @@ struct hci_dev { __u16 lmp_subver; __u16 voice_setting; __u8 num_iac; - __u8 stored_max_keys; - __u8 stored_num_keys; + __u16 stored_max_keys; + __u16 stored_num_keys; __u8 io_capability; __s8 inq_tx_power; __u8 err_data_reporting; @@ -475,6 +477,10 @@ struct hci_dev { struct work_struct power_on; struct delayed_work power_off; struct work_struct error_reset; + struct work_struct cmd_sync_work; + struct list_head cmd_sync_work_list; + struct mutex cmd_sync_work_lock; + struct work_struct cmd_sync_cancel_work; __u16 discov_timeout; struct delayed_work discov_off; @@ -489,10 +495,7 @@ struct hci_dev { struct work_struct tx_work; struct work_struct discov_update; - struct work_struct bg_scan_update; struct work_struct scan_update; - struct work_struct connectable_update; - struct work_struct discoverable_update; struct delayed_work le_scan_disable; struct delayed_work le_scan_restart; @@ -519,7 +522,6 @@ struct hci_dev { bool advertising_paused; struct notifier_block suspend_notifier; - struct work_struct suspend_prepare; enum suspended_state suspend_state_next; enum suspended_state suspend_state; bool scanning_paused; @@ -528,9 +530,6 @@ struct hci_dev { bdaddr_t wake_addr; u8 wake_addr_type; - wait_queue_head_t suspend_wait_q; - DECLARE_BITMAP(suspend_tasks, __SUSPEND_NUM_TASKS); - struct hci_conn_hash conn_hash; struct list_head mgmt_pending; @@ -562,6 +561,7 @@ struct hci_dev { struct rfkill *rfkill; DECLARE_BITMAP(dev_flags, __HCI_NUM_FLAGS); + DECLARE_BITMAP(conn_flags, __HCI_CONN_NUM_FLAGS); __s8 adv_tx_power; __u8 adv_data[HCI_MAX_EXT_AD_LENGTH]; @@ -603,6 +603,7 @@ struct hci_dev { #if IS_ENABLED(CONFIG_BT_AOSPEXT) bool aosp_capable; + bool aosp_quality_report; #endif int (*open)(struct hci_dev *hdev); @@ -756,7 +757,8 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; - u32 current_flags; + DECLARE_BITMAP(flags, __HCI_CONN_NUM_FLAGS); + u8 privacy_mode; }; extern struct list_head hci_dev_list; @@ -781,6 +783,12 @@ extern struct mutex hci_cb_list_lock; hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT); \ } while (0) +#define hci_dev_le_state_simultaneous(hdev) \ + (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \ + (hdev->le_states[4] & 0x08) && /* Central */ \ + (hdev->le_states[4] & 0x40) && /* Peripheral */ \ + (hdev->le_states[3] & 0x10)) /* Simultaneous */ + /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); @@ -1119,8 +1127,7 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, enum conn_reasons conn_reason); struct hci_conn *hci_connect_le(struct hci_dev *hdev, bdaddr_t *dst, u8 dst_type, bool dst_resolved, u8 sec_level, - u16 conn_timeout, u8 role, - bdaddr_t *direct_rpa); + u16 conn_timeout, u8 role); struct hci_conn *hci_connect_acl(struct hci_dev *hdev, bdaddr_t *dst, u8 sec_level, u8 auth_type, enum conn_reasons conn_reason); @@ -1461,8 +1468,14 @@ void hci_conn_del_sysfs(struct hci_conn *conn); #define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \ ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED)) +#define ll_privacy_capable(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) + /* Use LL Privacy based address resolution if supported */ -#define use_ll_privacy(dev) ((dev)->le_features[0] & HCI_LE_LL_PRIVACY) +#define use_ll_privacy(dev) (ll_privacy_capable(dev) && \ + hci_dev_test_flag(dev, HCI_ENABLE_LL_PRIVACY)) + +#define privacy_mode_capable(dev) (use_ll_privacy(dev) && \ + (hdev->commands[39] & 0x04)) /* Use enhanced synchronous connection if command is supported */ #define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08) @@ -1690,10 +1703,6 @@ static inline int hci_check_conn_params(u16 min, u16 max, u16 latency, int hci_register_cb(struct hci_cb *hcb); int hci_unregister_cb(struct hci_cb *hcb); -struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, - const void *param, u32 timeout); -struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, - const void *param, u8 event, u32 timeout); int __hci_cmd_send(struct hci_dev *hdev, u16 opcode, u32 plen, const void *param); @@ -1704,9 +1713,6 @@ void hci_send_sco(struct hci_conn *conn, struct sk_buff *skb); void *hci_sent_cmd_data(struct hci_dev *hdev, __u16 opcode); -struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, - const void *param, u32 timeout); - u32 hci_conn_get_phy(struct hci_conn *conn); /* ----- HCI Sockets ----- */ @@ -1765,6 +1771,8 @@ void hci_mgmt_chan_unregister(struct hci_mgmt_chan *c); #define DISCOV_LE_FAST_ADV_INT_MIN 0x00A0 /* 100 msec */ #define DISCOV_LE_FAST_ADV_INT_MAX 0x00F0 /* 150 msec */ +#define NAME_RESOLVE_DURATION msecs_to_jiffies(10240) /* 10.24 sec */ + void mgmt_fill_version_info(void *ver); int mgmt_new_settings(struct hci_dev *hdev); void mgmt_index_added(struct hci_dev *hdev); @@ -1806,7 +1814,6 @@ int mgmt_user_passkey_notify(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 entered); void mgmt_auth_failed(struct hci_conn *conn, u8 status); void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status); -void mgmt_ssp_enable_complete(struct hci_dev *hdev, u8 enable, u8 status); void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class, u8 status); void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status); @@ -1831,8 +1838,6 @@ void mgmt_new_conn_param(struct hci_dev *hdev, bdaddr_t *bdaddr, u16 max_interval, u16 latency, u16 timeout); void mgmt_smp_complete(struct hci_conn *conn, bool complete); bool mgmt_get_connectable(struct hci_dev *hdev); -void mgmt_set_connectable_complete(struct hci_dev *hdev, u8 status); -void mgmt_set_discoverable_complete(struct hci_dev *hdev, u8 status); u8 mgmt_get_adv_discov_flags(struct hci_dev *hdev); void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev, u8 instance); diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h new file mode 100644 index 000000000000..2492e3b46a8f --- /dev/null +++ b/include/net/bluetooth/hci_sync.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * BlueZ - Bluetooth protocol stack for Linux + * + * Copyright (C) 2021 Intel Corporation + */ + +typedef int (*hci_cmd_sync_work_func_t)(struct hci_dev *hdev, void *data); +typedef void (*hci_cmd_sync_work_destroy_t)(struct hci_dev *hdev, void *data, + int err); + +struct hci_cmd_sync_work_entry { + struct list_head list; + hci_cmd_sync_work_func_t func; + void *data; + hci_cmd_sync_work_destroy_t destroy; +}; + +/* Function with sync suffix shall not be called with hdev->lock held as they + * wait the command to complete and in the meantime an event could be received + * which could attempt to acquire hdev->lock causing a deadlock. + */ +struct sk_buff *__hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout); +struct sk_buff *hci_cmd_sync(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout); +struct sk_buff *__hci_cmd_sync_ev(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u8 event, u32 timeout); +struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u8 event, u32 timeout, + struct sock *sk); +int __hci_cmd_sync_status(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u32 timeout); +int __hci_cmd_sync_status_sk(struct hci_dev *hdev, u16 opcode, u32 plen, + const void *param, u8 event, u32 timeout, + struct sock *sk); + +void hci_cmd_sync_init(struct hci_dev *hdev); +void hci_cmd_sync_clear(struct hci_dev *hdev); +void hci_cmd_sync_cancel(struct hci_dev *hdev, int err); +void __hci_cmd_sync_cancel(struct hci_dev *hdev, int err); + +int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func, + void *data, hci_cmd_sync_work_destroy_t destroy); + +int hci_update_eir_sync(struct hci_dev *hdev); +int hci_update_class_sync(struct hci_dev *hdev); + +int hci_update_eir_sync(struct hci_dev *hdev); +int hci_update_class_sync(struct hci_dev *hdev); +int hci_update_name_sync(struct hci_dev *hdev); +int hci_write_ssp_mode_sync(struct hci_dev *hdev, u8 mode); + +int hci_update_random_address_sync(struct hci_dev *hdev, bool require_privacy, + bool rpa, u8 *own_addr_type); + +int hci_update_scan_rsp_data_sync(struct hci_dev *hdev, u8 instance); +int hci_update_adv_data_sync(struct hci_dev *hdev, u8 instance); +int hci_schedule_adv_instance_sync(struct hci_dev *hdev, u8 instance, + bool force); + +int hci_setup_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance); +int hci_start_ext_adv_sync(struct hci_dev *hdev, u8 instance); +int hci_enable_ext_advertising_sync(struct hci_dev *hdev, u8 instance); +int hci_enable_advertising_sync(struct hci_dev *hdev); +int hci_enable_advertising(struct hci_dev *hdev); + +int hci_remove_advertising_sync(struct hci_dev *hdev, struct sock *sk, + u8 instance, bool force); +int hci_disable_advertising_sync(struct hci_dev *hdev); + +int hci_update_passive_scan_sync(struct hci_dev *hdev); +int hci_update_passive_scan(struct hci_dev *hdev); +int hci_read_rssi_sync(struct hci_dev *hdev, __le16 handle); +int hci_read_tx_power_sync(struct hci_dev *hdev, __le16 handle, u8 type); +int hci_write_sc_support_sync(struct hci_dev *hdev, u8 val); +int hci_read_clock_sync(struct hci_dev *hdev, struct hci_cp_read_clock *cp); + +int hci_write_fast_connectable_sync(struct hci_dev *hdev, bool enable); +int hci_update_scan_sync(struct hci_dev *hdev); + +int hci_write_le_host_supported_sync(struct hci_dev *hdev, u8 le, u8 simul); +int hci_remove_ext_adv_instance_sync(struct hci_dev *hdev, u8 instance, + struct sock *sk); +struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, bool ext, + struct sock *sk); + +int hci_reset_sync(struct hci_dev *hdev); +int hci_dev_open_sync(struct hci_dev *hdev); +int hci_dev_close_sync(struct hci_dev *hdev); + +int hci_powered_update_sync(struct hci_dev *hdev); +int hci_set_powered_sync(struct hci_dev *hdev, u8 val); + +int hci_update_discoverable_sync(struct hci_dev *hdev); +int hci_update_discoverable(struct hci_dev *hdev); + +int hci_update_connectable_sync(struct hci_dev *hdev); + +int hci_start_discovery_sync(struct hci_dev *hdev); +int hci_stop_discovery_sync(struct hci_dev *hdev); + +int hci_suspend_sync(struct hci_dev *hdev); +int hci_resume_sync(struct hci_dev *hdev); + +struct hci_conn; + +int hci_le_create_conn_sync(struct hci_dev *hdev, struct hci_conn *conn); diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 23a0524061b7..107b25deae68 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -936,10 +936,11 @@ struct mgmt_ev_auth_failed { __u8 status; } __packed; -#define MGMT_DEV_FOUND_CONFIRM_NAME 0x01 -#define MGMT_DEV_FOUND_LEGACY_PAIRING 0x02 -#define MGMT_DEV_FOUND_NOT_CONNECTABLE 0x04 -#define MGMT_DEV_FOUND_INITIATED_CONN 0x08 +#define MGMT_DEV_FOUND_CONFIRM_NAME 0x01 +#define MGMT_DEV_FOUND_LEGACY_PAIRING 0x02 +#define MGMT_DEV_FOUND_NOT_CONNECTABLE 0x04 +#define MGMT_DEV_FOUND_INITIATED_CONN 0x08 +#define MGMT_DEV_FOUND_NAME_REQUEST_FAILED 0x10 #define MGMT_EV_DEVICE_FOUND 0x0012 struct mgmt_ev_device_found { diff --git a/include/net/bond_options.h b/include/net/bond_options.h index e64833a674eb..dd75c071f67e 100644 --- a/include/net/bond_options.h +++ b/include/net/bond_options.h @@ -65,6 +65,7 @@ enum { BOND_OPT_NUM_PEER_NOTIF_ALIAS, BOND_OPT_PEER_NOTIF_DELAY, BOND_OPT_LACP_ACTIVE, + BOND_OPT_MISSED_MAX, BOND_OPT_LAST }; diff --git a/include/net/bonding.h b/include/net/bonding.h index 15e083e18f75..f6ae3a4baea4 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -121,6 +121,7 @@ struct bond_params { int xmit_policy; int miimon; u8 num_peer_notif; + u8 missed_max; int arp_interval; int arp_validate; int arp_all_targets; diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 423f97b982ff..d19e48f9fdc6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1188,17 +1188,6 @@ struct cfg80211_unsol_bcast_probe_resp { }; /** - * enum cfg80211_ap_settings_flags - AP settings flags - * - * Used by cfg80211_ap_settings - * - * @AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external authentication - */ -enum cfg80211_ap_settings_flags { - AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = BIT(0), -}; - -/** * struct cfg80211_ap_settings - AP configuration * * Used to configure an AP interface. @@ -4072,6 +4061,15 @@ struct mgmt_frame_regs { * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use * those to decrypt (Re)Association Request and encrypt (Re)Association * Response frame. + * + * @set_radar_background: Configure dedicated offchannel chain available for + * radar/CAC detection on some hw. This chain can't be used to transmit + * or receive frames and it is bounded to a running wdev. + * Background radar/CAC detection allows to avoid the CAC downtime + * switching to a different channel during CAC detection on the selected + * radar channel. + * The caller is expected to set chandef pointer to NULL in order to + * disable background CAC/radar detection. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4404,6 +4402,8 @@ struct cfg80211_ops { struct cfg80211_color_change_settings *params); int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_fils_aad *fils_aad); + int (*set_radar_background)(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef); }; /* @@ -6375,17 +6375,6 @@ static inline void cfg80211_gen_new_bssid(const u8 *bssid, u8 max_bssid, } /** - * cfg80211_get_ies_channel_number - returns the channel number from ies - * @ie: IEs - * @ielen: length of IEs - * @band: enum nl80211_band of the channel - * - * Returns the channel number, or -1 if none could be determined. - */ -int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, - enum nl80211_band band); - -/** * cfg80211_is_element_inherited - returns if element ID should be inherited * @element: element to check * @non_inherit_element: non inheritance element @@ -6421,6 +6410,19 @@ enum cfg80211_bss_frame_type { }; /** + * cfg80211_get_ies_channel_number - returns the channel number from ies + * @ie: IEs + * @ielen: length of IEs + * @band: enum nl80211_band of the channel + * @ftype: frame type + * + * Returns the channel number, or -1 if none could be determined. + */ +int cfg80211_get_ies_channel_number(const u8 *ie, size_t ielen, + enum nl80211_band band, + enum cfg80211_bss_frame_type ftype); + +/** * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS @@ -7594,15 +7596,33 @@ void cfg80211_cqm_txe_notify(struct net_device *dev, const u8 *peer, void cfg80211_cqm_beacon_loss_notify(struct net_device *dev, gfp_t gfp); /** - * cfg80211_radar_event - radar detection event + * __cfg80211_radar_event - radar detection event * @wiphy: the wiphy * @chandef: chandef for the current channel + * @offchan: the radar has been detected on the offchannel chain * @gfp: context flags * * This function is called when a radar is detected on the current chanenl. */ -void cfg80211_radar_event(struct wiphy *wiphy, - struct cfg80211_chan_def *chandef, gfp_t gfp); +void __cfg80211_radar_event(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + bool offchan, gfp_t gfp); + +static inline void +cfg80211_radar_event(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + gfp_t gfp) +{ + __cfg80211_radar_event(wiphy, chandef, false, gfp); +} + +static inline void +cfg80211_background_radar_event(struct wiphy *wiphy, + struct cfg80211_chan_def *chandef, + gfp_t gfp) +{ + __cfg80211_radar_event(wiphy, chandef, true, gfp); +} /** * cfg80211_sta_opmode_change_notify - STA's ht/vht operation mode change event @@ -7633,6 +7653,14 @@ void cfg80211_cac_event(struct net_device *netdev, const struct cfg80211_chan_def *chandef, enum nl80211_radar_event event, gfp_t gfp); +/** + * cfg80211_background_cac_abort - Channel Availability Check offchan abort event + * @wiphy: the wiphy + * + * This function is called by the driver when a Channel Availability Check + * (CAC) is aborted by a offchannel dedicated chain. + */ +void cfg80211_background_cac_abort(struct wiphy *wiphy); /** * cfg80211_gtk_rekey_notify - notify userspace about driver rekeying @@ -8250,6 +8278,18 @@ bool cfg80211_iftype_allowed(struct wiphy *wiphy, enum nl80211_iftype iftype, bool is_4addr, u8 check_swif); +/** + * cfg80211_assoc_comeback - notification of association that was + * temporarly rejected with a comeback + * @netdev: network device + * @bss: the bss entry with which association is in progress. + * @timeout: timeout interval value TUs. + * + * this function may sleep. the caller must hold the corresponding wdev's mutex. + */ +void cfg80211_assoc_comeback(struct net_device *netdev, + struct cfg80211_bss *bss, u32 timeout); + /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* wiphy_printk helpers, similar to dev_printk */ diff --git a/include/net/checksum.h b/include/net/checksum.h index 5b96d5bd6e54..5218041e5c8f 100644 --- a/include/net/checksum.h +++ b/include/net/checksum.h @@ -180,4 +180,8 @@ static inline void remcsum_unadjust(__sum16 *psum, __wsum delta) *psum = csum_fold(csum_sub(delta, (__force __wsum)*psum)); } +static inline __wsum wsum_negate(__wsum val) +{ + return (__force __wsum)-((__force u32)val); +} #endif diff --git a/include/net/codel.h b/include/net/codel.h index a6c9e34e62b8..5fed2f16cb8d 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -44,8 +44,6 @@ #include <linux/types.h> #include <linux/ktime.h> #include <linux/skbuff.h> -#include <net/pkt_sched.h> -#include <net/inet_ecn.h> /* Controlling Queue Delay (CoDel) algorithm * ========================================= diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index 137d40d8cbeb..78a27ac73070 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -49,6 +49,8 @@ * Implemented on linux by Dave Taht and Eric Dumazet */ +#include <net/inet_ecn.h> + static void codel_params_init(struct codel_params *params) { params->interval = MS2TIME(100); diff --git a/include/net/codel_qdisc.h b/include/net/codel_qdisc.h index 098630f83a55..58b6d0ebea10 100644 --- a/include/net/codel_qdisc.h +++ b/include/net/codel_qdisc.h @@ -49,6 +49,8 @@ * Implemented on linux by Dave Taht and Eric Dumazet */ +#include <net/pkt_sched.h> + /* Qdiscs using codel plugin must use codel_skb_cb in their own cb[] */ struct codel_skb_cb { codel_time_t enqueue_time; diff --git a/include/net/devlink.h b/include/net/devlink.h index aab3d007c577..8d5349d2fb68 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -361,33 +361,6 @@ devlink_resource_size_params_init(struct devlink_resource_size_params *size_para typedef u64 devlink_resource_occ_get_t(void *priv); -/** - * struct devlink_resource - devlink resource - * @name: name of the resource - * @id: id, per devlink instance - * @size: size of the resource - * @size_new: updated size of the resource, reload is needed - * @size_valid: valid in case the total size of the resource is valid - * including its children - * @parent: parent resource - * @size_params: size parameters - * @list: parent list - * @resource_list: list of child resources - */ -struct devlink_resource { - const char *name; - u64 id; - u64 size; - u64 size_new; - bool size_valid; - struct devlink_resource *parent; - struct devlink_resource_size_params size_params; - struct list_head list; - struct list_head resource_list; - devlink_resource_occ_get_t *occ_get; - void *occ_get_priv; -}; - #define DEVLINK_RESOURCE_ID_PARENT_TOP 0 #define DEVLINK_RESOURCE_GENERIC_NAME_PORTS "physical_ports" @@ -485,6 +458,9 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_ENABLE_ETH, DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, DEVLINK_PARAM_GENERIC_ID_ENABLE_VNET, + DEVLINK_PARAM_GENERIC_ID_ENABLE_IWARP, + DEVLINK_PARAM_GENERIC_ID_IO_EQ_SIZE, + DEVLINK_PARAM_GENERIC_ID_EVENT_EQ_SIZE, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -534,6 +510,15 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_ENABLE_VNET_NAME "enable_vnet" #define DEVLINK_PARAM_GENERIC_ENABLE_VNET_TYPE DEVLINK_PARAM_TYPE_BOOL +#define DEVLINK_PARAM_GENERIC_ENABLE_IWARP_NAME "enable_iwarp" +#define DEVLINK_PARAM_GENERIC_ENABLE_IWARP_TYPE DEVLINK_PARAM_TYPE_BOOL + +#define DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_NAME "io_eq_size" +#define DEVLINK_PARAM_GENERIC_IO_EQ_SIZE_TYPE DEVLINK_PARAM_TYPE_U32 + +#define DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_NAME "event_eq_size" +#define DEVLINK_PARAM_GENERIC_EVENT_EQ_SIZE_TYPE DEVLINK_PARAM_TYPE_U32 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ @@ -687,13 +672,17 @@ struct devlink_health_reporter_ops { * @trap_name: Trap name. * @trap_group_name: Trap group name. * @input_dev: Input netdevice. + * @dev_tracker: refcount tracker for @input_dev. * @fa_cookie: Flow action user cookie. * @trap_type: Trap type. */ struct devlink_trap_metadata { const char *trap_name; const char *trap_group_name; + struct net_device *input_dev; + netdevice_tracker dev_tracker; + const struct flow_action_cookie *fa_cookie; enum devlink_trap_type trap_type; }; @@ -1567,8 +1556,7 @@ int devlink_resource_register(struct devlink *devlink, u64 resource_id, u64 parent_resource_id, const struct devlink_resource_size_params *size_params); -void devlink_resources_unregister(struct devlink *devlink, - struct devlink_resource *resource); +void devlink_resources_unregister(struct devlink *devlink); int devlink_resource_size_get(struct devlink *devlink, u64 resource_id, u64 *p_resource_size); diff --git a/include/net/dsa.h b/include/net/dsa.h index eff5c44ba377..57b3e4e7413b 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -88,6 +88,8 @@ struct dsa_device_ops { struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); void (*flow_dissect)(const struct sk_buff *skb, __be16 *proto, int *offset); + int (*connect)(struct dsa_switch *ds); + void (*disconnect)(struct dsa_switch *ds); unsigned int needed_headroom; unsigned int needed_tailroom; const char *name; @@ -117,6 +119,9 @@ struct dsa_netdevice_ops { struct dsa_switch_tree { struct list_head list; + /* List of switch ports */ + struct list_head ports; + /* Notifier chain for switch-wide events */ struct raw_notifier_head nh; @@ -126,8 +131,10 @@ struct dsa_switch_tree { /* Number of switches attached to this tree */ struct kref refcount; - /* Has this tree been applied to the hardware? */ - bool setup; + /* Maps offloaded LAG netdevs to a zero-based linear ID for + * drivers that need it. + */ + struct net_device **lags; /* Tagging protocol operations */ const struct dsa_device_ops *tag_ops; @@ -137,22 +144,19 @@ struct dsa_switch_tree { */ enum dsa_tag_protocol default_proto; + /* Has this tree been applied to the hardware? */ + bool setup; + /* * Configuration data for the platform device that owns * this dsa switch tree instance. */ struct dsa_platform_data *pd; - /* List of switch ports */ - struct list_head ports; - /* List of DSA links composing the routing table */ struct list_head rtable; - /* Maps offloaded LAG netdevs to a zero-based linear ID for - * drivers that need it. - */ - struct net_device **lags; + /* Length of "lags" array */ unsigned int lags_len; /* Track the largest switch index within a tree */ @@ -219,6 +223,12 @@ struct dsa_mall_tc_entry { }; }; +struct dsa_bridge { + struct net_device *dev; + unsigned int num; + bool tx_fwd_offload; + refcount_t refcount; +}; struct dsa_port { /* A CPU port is physically connected to a master device. @@ -238,6 +248,10 @@ struct dsa_port { struct dsa_switch_tree *dst; struct sk_buff *(*rcv)(struct sk_buff *skb, struct net_device *dev); + struct dsa_switch *ds; + + unsigned int index; + enum { DSA_PORT_TYPE_UNUSED = 0, DSA_PORT_TYPE_CPU, @@ -245,36 +259,40 @@ struct dsa_port { DSA_PORT_TYPE_USER, } type; - struct dsa_switch *ds; - unsigned int index; const char *name; struct dsa_port *cpu_dp; u8 mac[ETH_ALEN]; + + u8 stp_state; + + /* Warning: the following bit fields are not atomic, and updating them + * can only be done from code paths where concurrency is not possible + * (probe time or under rtnl_lock). + */ + u8 vlan_filtering:1; + + /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ + u8 learning:1; + + u8 lag_tx_enabled:1; + + u8 devlink_port_setup:1; + + u8 setup:1; + struct device_node *dn; unsigned int ageing_time; - bool vlan_filtering; - /* Managed by DSA on user ports and by drivers on CPU and DSA ports */ - bool learning; - u8 stp_state; - struct net_device *bridge_dev; - int bridge_num; + + struct dsa_bridge *bridge; struct devlink_port devlink_port; - bool devlink_port_setup; struct phylink *pl; struct phylink_config pl_config; struct net_device *lag_dev; - bool lag_tx_enabled; struct net_device *hsr_dev; struct list_head list; /* - * Give the switch driver somewhere to hang its per-port private data - * structures (accessible from the tagger). - */ - void *priv; - - /* * Original copy of the master netdev ethtool_ops */ const struct ethtool_ops *orig_ethtool_ops; @@ -290,8 +308,6 @@ struct dsa_port { struct mutex addr_lists_lock; struct list_head fdbs; struct list_head mdbs; - - bool setup; }; /* TODO: ideally DSA ports would have a single dp->link_dp member, @@ -313,8 +329,6 @@ struct dsa_mac_addr { }; struct dsa_switch { - bool setup; - struct device *dev; /* @@ -323,6 +337,57 @@ struct dsa_switch { struct dsa_switch_tree *dst; unsigned int index; + /* Warning: the following bit fields are not atomic, and updating them + * can only be done from code paths where concurrency is not possible + * (probe time or under rtnl_lock). + */ + u32 setup:1; + + /* Disallow bridge core from requesting different VLAN awareness + * settings on ports if not hardware-supported + */ + u32 vlan_filtering_is_global:1; + + /* Keep VLAN filtering enabled on ports not offloading any upper */ + u32 needs_standalone_vlan_filtering:1; + + /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges + * that have vlan_filtering=0. All drivers should ideally set this (and + * then the option would get removed), but it is unknown whether this + * would break things or not. + */ + u32 configure_vlan_while_not_filtering:1; + + /* If the switch driver always programs the CPU port as egress tagged + * despite the VLAN configuration indicating otherwise, then setting + * @untag_bridge_pvid will force the DSA receive path to pop the + * bridge's default_pvid VLAN tagged frames to offer a consistent + * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge + * device. + */ + u32 untag_bridge_pvid:1; + + /* Let DSA manage the FDB entries towards the + * CPU, based on the software bridge database. + */ + u32 assisted_learning_on_cpu_port:1; + + /* In case vlan_filtering_is_global is set, the VLAN awareness state + * should be retrieved from here and not from the per-port settings. + */ + u32 vlan_filtering:1; + + /* MAC PCS does not provide link state change interrupt, and requires + * polling. Flag passed on to PHYLINK. + */ + u32 pcs_poll:1; + + /* For switches that only have the MRU configurable. To ensure the + * configured MTU is not exceeded, normalization of MRU on all bridged + * interfaces is needed. + */ + u32 mtu_enforcement_ingress:1; + /* Listener for switch fabric events */ struct notifier_block nb; @@ -332,6 +397,8 @@ struct dsa_switch { */ void *priv; + void *tagger_data; + /* * Configuration data for this switch. */ @@ -361,50 +428,6 @@ struct dsa_switch { /* Number of switch port queues */ unsigned int num_tx_queues; - /* Disallow bridge core from requesting different VLAN awareness - * settings on ports if not hardware-supported - */ - bool vlan_filtering_is_global; - - /* Keep VLAN filtering enabled on ports not offloading any upper. */ - bool needs_standalone_vlan_filtering; - - /* Pass .port_vlan_add and .port_vlan_del to drivers even for bridges - * that have vlan_filtering=0. All drivers should ideally set this (and - * then the option would get removed), but it is unknown whether this - * would break things or not. - */ - bool configure_vlan_while_not_filtering; - - /* If the switch driver always programs the CPU port as egress tagged - * despite the VLAN configuration indicating otherwise, then setting - * @untag_bridge_pvid will force the DSA receive path to pop the bridge's - * default_pvid VLAN tagged frames to offer a consistent behavior - * between a vlan_filtering=0 and vlan_filtering=1 bridge device. - */ - bool untag_bridge_pvid; - - /* Let DSA manage the FDB entries towards the CPU, based on the - * software bridge database. - */ - bool assisted_learning_on_cpu_port; - - /* In case vlan_filtering_is_global is set, the VLAN awareness state - * should be retrieved from here and not from the per-port settings. - */ - bool vlan_filtering; - - /* MAC PCS does not provide link state change interrupt, and requires - * polling. Flag passed on to PHYLINK. - */ - bool pcs_poll; - - /* For switches that only have the MRU configurable. To ensure the - * configured MTU is not exceeded, normalization of MRU on all bridged - * interfaces is needed. - */ - bool mtu_enforcement_ingress; - /* Drivers that benefit from having an ID associated with each * offloaded LAG should set this to the maximum number of * supported IDs. DSA will then maintain a mapping of _at @@ -413,14 +436,14 @@ struct dsa_switch { */ unsigned int num_lag_ids; - /* Drivers that support bridge forwarding offload should set this to - * the maximum number of bridges spanning the same switch tree (or all - * trees, in the case of cross-tree bridging support) that can be - * offloaded. + /* Drivers that support bridge forwarding offload or FDB isolation + * should set this to the maximum number of bridges spanning the same + * switch tree (or all trees, in the case of cross-tree bridging + * support) that can be offloaded. */ - unsigned int num_fwd_offloading_bridges; + unsigned int max_num_bridges; - size_t num_ports; + unsigned int num_ports; }; static inline struct dsa_port *dsa_to_port(struct dsa_switch *ds, int p) @@ -588,7 +611,7 @@ static inline bool dsa_port_is_vlan_filtering(const struct dsa_port *dp) static inline struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) { - if (!dp->bridge_dev) + if (!dp->bridge) return NULL; if (dp->lag_dev) @@ -599,6 +622,76 @@ struct net_device *dsa_port_to_bridge_port(const struct dsa_port *dp) return dp->slave; } +static inline struct net_device * +dsa_port_bridge_dev_get(const struct dsa_port *dp) +{ + return dp->bridge ? dp->bridge->dev : NULL; +} + +static inline unsigned int dsa_port_bridge_num_get(struct dsa_port *dp) +{ + return dp->bridge ? dp->bridge->num : 0; +} + +static inline bool dsa_port_bridge_same(const struct dsa_port *a, + const struct dsa_port *b) +{ + struct net_device *br_a = dsa_port_bridge_dev_get(a); + struct net_device *br_b = dsa_port_bridge_dev_get(b); + + /* Standalone ports are not in the same bridge with one another */ + return (!br_a || !br_b) ? false : (br_a == br_b); +} + +static inline bool dsa_port_offloads_bridge_port(struct dsa_port *dp, + const struct net_device *dev) +{ + return dsa_port_to_bridge_port(dp) == dev; +} + +static inline bool +dsa_port_offloads_bridge_dev(struct dsa_port *dp, + const struct net_device *bridge_dev) +{ + /* DSA ports connected to a bridge, and event was emitted + * for the bridge. + */ + return dsa_port_bridge_dev_get(dp) == bridge_dev; +} + +static inline bool dsa_port_offloads_bridge(struct dsa_port *dp, + const struct dsa_bridge *bridge) +{ + return dsa_port_bridge_dev_get(dp) == bridge->dev; +} + +/* Returns true if any port of this tree offloads the given net_device */ +static inline bool dsa_tree_offloads_bridge_port(struct dsa_switch_tree *dst, + const struct net_device *dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_bridge_port(dp, dev)) + return true; + + return false; +} + +/* Returns true if any port of this tree offloads the given bridge */ +static inline bool +dsa_tree_offloads_bridge_dev(struct dsa_switch_tree *dst, + const struct net_device *bridge_dev) +{ + struct dsa_port *dp; + + list_for_each_entry(dp, &dst->ports, list) + if (dsa_port_offloads_bridge_dev(dp, bridge_dev)) + return true; + + return false; +} + typedef int dsa_fdb_dump_cb_t(const unsigned char *addr, u16 vid, bool is_static, void *data); struct dsa_switch_ops { @@ -614,6 +707,13 @@ struct dsa_switch_ops { enum dsa_tag_protocol mprot); int (*change_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol proto); + /* + * Method for switch drivers to connect to the tagging protocol driver + * in current use. The switch driver can provide handlers for certain + * types of packets for switch management. + */ + int (*connect_tag_protocol)(struct dsa_switch *ds, + enum dsa_tag_protocol proto); /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); @@ -645,8 +745,8 @@ struct dsa_switch_ops { /* * PHYLINK integration */ - void (*phylink_get_interfaces)(struct dsa_switch *ds, int port, - unsigned long *supported_interfaces); + void (*phylink_get_caps)(struct dsa_switch *ds, int port, + struct phylink_config *config); void (*phylink_validate)(struct dsa_switch *ds, int port, unsigned long *supported, struct phylink_link_state *state); @@ -748,17 +848,10 @@ struct dsa_switch_ops { */ int (*set_ageing_time)(struct dsa_switch *ds, unsigned int msecs); int (*port_bridge_join)(struct dsa_switch *ds, int port, - struct net_device *bridge); + struct dsa_bridge bridge, + bool *tx_fwd_offload); void (*port_bridge_leave)(struct dsa_switch *ds, int port, - struct net_device *bridge); - /* Called right after .port_bridge_join() */ - int (*port_bridge_tx_fwd_offload)(struct dsa_switch *ds, int port, - struct net_device *bridge, - int bridge_num); - /* Called right before .port_bridge_leave() */ - void (*port_bridge_tx_fwd_unoffload)(struct dsa_switch *ds, int port, - struct net_device *bridge, - int bridge_num); + struct dsa_bridge bridge); void (*port_stp_state_set)(struct dsa_switch *ds, int port, u8 state); void (*port_fast_age)(struct dsa_switch *ds, int port); @@ -830,10 +923,10 @@ struct dsa_switch_ops { */ int (*crosschip_bridge_join)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct net_device *br); + struct dsa_bridge bridge); void (*crosschip_bridge_leave)(struct dsa_switch *ds, int tree_index, int sw_index, int port, - struct net_device *br); + struct dsa_bridge bridge); int (*crosschip_lag_change)(struct dsa_switch *ds, int sw_index, int port); int (*crosschip_lag_join)(struct dsa_switch *ds, int sw_index, diff --git a/include/net/dst.h b/include/net/dst.h index a057319aabef..6aa252c3fc55 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -77,6 +77,7 @@ struct dst_entry { #ifndef CONFIG_64BIT atomic_t __refcnt; /* 32-bit offset 64 */ #endif + netdevice_tracker dev_tracker; }; struct dst_metrics { diff --git a/include/net/failover.h b/include/net/failover.h index bb15438f39c7..f2b42b4b9cd6 100644 --- a/include/net/failover.h +++ b/include/net/failover.h @@ -25,6 +25,7 @@ struct failover_ops { struct failover { struct list_head list; struct net_device __rcu *failover_dev; + netdevice_tracker dev_tracker; struct failover_ops __rcu *ops; }; diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index bd07484ab9dd..82da359bca03 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -91,7 +91,6 @@ struct fib_rules_ops { void (*flush_cache)(struct fib_rules_ops *ops); int nlgroup; - const struct nla_policy *policy; struct list_head rules_list; struct module *owner; struct net *fro_net; @@ -103,26 +102,6 @@ struct fib_rule_notifier_info { struct fib_rule *rule; }; -#define FRA_GENERIC_POLICY \ - [FRA_UNSPEC] = { .strict_start_type = FRA_DPORT_RANGE + 1 }, \ - [FRA_IIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ - [FRA_OIFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, \ - [FRA_PRIORITY] = { .type = NLA_U32 }, \ - [FRA_FWMARK] = { .type = NLA_U32 }, \ - [FRA_TUN_ID] = { .type = NLA_U64 }, \ - [FRA_FWMASK] = { .type = NLA_U32 }, \ - [FRA_TABLE] = { .type = NLA_U32 }, \ - [FRA_SUPPRESS_PREFIXLEN] = { .type = NLA_U32 }, \ - [FRA_SUPPRESS_IFGROUP] = { .type = NLA_U32 }, \ - [FRA_GOTO] = { .type = NLA_U32 }, \ - [FRA_L3MDEV] = { .type = NLA_U8 }, \ - [FRA_UID_RANGE] = { .len = sizeof(struct fib_rule_uid_range) }, \ - [FRA_PROTOCOL] = { .type = NLA_U8 }, \ - [FRA_IP_PROTO] = { .type = NLA_U8 }, \ - [FRA_SPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) }, \ - [FRA_DPORT_RANGE] = { .len = sizeof(struct fib_rule_port_range) } - - static inline void fib_rule_get(struct fib_rule *rule) { refcount_inc(&rule->refcnt); diff --git a/include/net/flow_offload.h b/include/net/flow_offload.h index 3961461d9c8b..5b8c54eb7a6b 100644 --- a/include/net/flow_offload.h +++ b/include/net/flow_offload.h @@ -197,6 +197,7 @@ void flow_action_cookie_destroy(struct flow_action_cookie *cookie); struct flow_action_entry { enum flow_action_id id; + u32 hw_index; enum flow_action_hw_stats hw_stats; action_destr destructor; void *destructor_priv; @@ -232,7 +233,6 @@ struct flow_action_entry { bool truncate; } sample; struct { /* FLOW_ACTION_POLICE */ - u32 index; u32 burst; u64 rate_bytes_ps; u64 burst_pkt; @@ -267,7 +267,6 @@ struct flow_action_entry { u8 ttl; } mpls_mangle; struct { - u32 index; s32 prio; u64 basetime; u64 cycletime; @@ -552,6 +551,23 @@ struct flow_cls_offload { u32 classid; }; +enum offload_act_command { + FLOW_ACT_REPLACE, + FLOW_ACT_DESTROY, + FLOW_ACT_STATS, +}; + +struct flow_offload_action { + struct netlink_ext_ack *extack; /* NULL in FLOW_ACT_STATS process*/ + enum offload_act_command command; + enum flow_action_id id; + u32 index; + struct flow_stats stats; + struct flow_action action; +}; + +struct flow_offload_action *offload_action_alloc(unsigned int num_actions); + static inline struct flow_rule * flow_cls_offload_flow_rule(struct flow_cls_offload *flow_cmd) { diff --git a/include/net/gro.h b/include/net/gro.h index 01edaf3fdda0..8f75802d50fd 100644 --- a/include/net/gro.h +++ b/include/net/gro.h @@ -4,9 +4,368 @@ #define _NET_IPV6_GRO_H #include <linux/indirect_call_wrapper.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <net/ip6_checksum.h> +#include <linux/skbuff.h> +#include <net/udp.h> -struct list_head; -struct sk_buff; +struct napi_gro_cb { + /* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */ + void *frag0; + + /* Length of frag0. */ + unsigned int frag0_len; + + /* This indicates where we are processing relative to skb->data. */ + int data_offset; + + /* This is non-zero if the packet cannot be merged with the new skb. */ + u16 flush; + + /* Save the IP ID here and check when we get to the transport layer */ + u16 flush_id; + + /* Number of segments aggregated. */ + u16 count; + + /* Start offset for remote checksum offload */ + u16 gro_remcsum_start; + + /* jiffies when first packet was created/queued */ + unsigned long age; + + /* Used in ipv6_gro_receive() and foo-over-udp */ + u16 proto; + + /* This is non-zero if the packet may be of the same flow. */ + u8 same_flow:1; + + /* Used in tunnel GRO receive */ + u8 encap_mark:1; + + /* GRO checksum is valid */ + u8 csum_valid:1; + + /* Number of checksums via CHECKSUM_UNNECESSARY */ + u8 csum_cnt:3; + + /* Free the skb? */ + u8 free:2; +#define NAPI_GRO_FREE 1 +#define NAPI_GRO_FREE_STOLEN_HEAD 2 + + /* Used in foo-over-udp, set in udp[46]_gro_receive */ + u8 is_ipv6:1; + + /* Used in GRE, set in fou/gue_gro_receive */ + u8 is_fou:1; + + /* Used to determine if flush_id can be ignored */ + u8 is_atomic:1; + + /* Number of gro_receive callbacks this packet already went through */ + u8 recursion_counter:4; + + /* GRO is done by frag_list pointer chaining. */ + u8 is_flist:1; + + /* used to support CHECKSUM_COMPLETE for tunneling protocols */ + __wsum csum; + + /* used in skb_gro_receive() slow path */ + struct sk_buff *last; +}; + +#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb) + +#define GRO_RECURSION_LIMIT 15 +static inline int gro_recursion_inc_test(struct sk_buff *skb) +{ + return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT; +} + +typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *); +static inline struct sk_buff *call_gro_receive(gro_receive_t cb, + struct list_head *head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(head, skb); +} + +typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *, + struct sk_buff *); +static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb, + struct sock *sk, + struct list_head *head, + struct sk_buff *skb) +{ + if (unlikely(gro_recursion_inc_test(skb))) { + NAPI_GRO_CB(skb)->flush |= 1; + return NULL; + } + + return cb(sk, head, skb); +} + +static inline unsigned int skb_gro_offset(const struct sk_buff *skb) +{ + return NAPI_GRO_CB(skb)->data_offset; +} + +static inline unsigned int skb_gro_len(const struct sk_buff *skb) +{ + return skb->len - NAPI_GRO_CB(skb)->data_offset; +} + +static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len) +{ + NAPI_GRO_CB(skb)->data_offset += len; +} + +static inline void *skb_gro_header_fast(struct sk_buff *skb, + unsigned int offset) +{ + return NAPI_GRO_CB(skb)->frag0 + offset; +} + +static inline int skb_gro_header_hard(struct sk_buff *skb, unsigned int hlen) +{ + return NAPI_GRO_CB(skb)->frag0_len < hlen; +} + +static inline void skb_gro_frag0_invalidate(struct sk_buff *skb) +{ + NAPI_GRO_CB(skb)->frag0 = NULL; + NAPI_GRO_CB(skb)->frag0_len = 0; +} + +static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen, + unsigned int offset) +{ + if (!pskb_may_pull(skb, hlen)) + return NULL; + + skb_gro_frag0_invalidate(skb); + return skb->data + offset; +} + +static inline void *skb_gro_network_header(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->frag0 ?: skb->data) + + skb_network_offset(skb); +} + +static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct iphdr *iph = skb_gro_network_header(skb); + + return csum_tcpudp_nofold(iph->saddr, iph->daddr, + skb_gro_len(skb), proto, 0); +} + +static inline void skb_gro_postpull_rcsum(struct sk_buff *skb, + const void *start, unsigned int len) +{ + if (NAPI_GRO_CB(skb)->csum_valid) + NAPI_GRO_CB(skb)->csum = wsum_negate(csum_partial(start, len, + wsum_negate(NAPI_GRO_CB(skb)->csum))); +} + +/* GRO checksum functions. These are logical equivalents of the normal + * checksum functions (in skbuff.h) except that they operate on the GRO + * offsets and fields in sk_buff. + */ + +__sum16 __skb_gro_checksum_complete(struct sk_buff *skb); + +static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb)); +} + +static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb, + bool zero_okay, + __sum16 check) +{ + return ((skb->ip_summed != CHECKSUM_PARTIAL || + skb_checksum_start_offset(skb) < + skb_gro_offset(skb)) && + !skb_at_gro_remcsum_start(skb) && + NAPI_GRO_CB(skb)->csum_cnt == 0 && + (!zero_okay || check)); +} + +static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb, + __wsum psum) +{ + if (NAPI_GRO_CB(skb)->csum_valid && + !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum))) + return 0; + + NAPI_GRO_CB(skb)->csum = psum; + + return __skb_gro_checksum_complete(skb); +} + +static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb) +{ + if (NAPI_GRO_CB(skb)->csum_cnt > 0) { + /* Consume a checksum from CHECKSUM_UNNECESSARY */ + NAPI_GRO_CB(skb)->csum_cnt--; + } else { + /* Update skb for CHECKSUM_UNNECESSARY and csum_level when we + * verified a new top level checksum or an encapsulated one + * during GRO. This saves work if we fallback to normal path. + */ + __skb_incr_checksum_unnecessary(skb); + } +} + +#define __skb_gro_checksum_validate(skb, proto, zero_okay, check, \ + compute_pseudo) \ +({ \ + __sum16 __ret = 0; \ + if (__skb_gro_checksum_validate_needed(skb, zero_okay, check)) \ + __ret = __skb_gro_checksum_validate_complete(skb, \ + compute_pseudo(skb, proto)); \ + if (!__ret) \ + skb_gro_incr_csum_unnecessary(skb); \ + __ret; \ +}) + +#define skb_gro_checksum_validate(skb, proto, compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo) + +#define skb_gro_checksum_validate_zero_check(skb, proto, check, \ + compute_pseudo) \ + __skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo) + +#define skb_gro_checksum_simple_validate(skb) \ + __skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo) + +static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb) +{ + return (NAPI_GRO_CB(skb)->csum_cnt == 0 && + !NAPI_GRO_CB(skb)->csum_valid); +} + +static inline void __skb_gro_checksum_convert(struct sk_buff *skb, + __wsum pseudo) +{ + NAPI_GRO_CB(skb)->csum = ~pseudo; + NAPI_GRO_CB(skb)->csum_valid = 1; +} + +#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo) \ +do { \ + if (__skb_gro_checksum_convert_check(skb)) \ + __skb_gro_checksum_convert(skb, \ + compute_pseudo(skb, proto)); \ +} while (0) + +struct gro_remcsum { + int offset; + __wsum delta; +}; + +static inline void skb_gro_remcsum_init(struct gro_remcsum *grc) +{ + grc->offset = 0; + grc->delta = 0; +} + +static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr, + unsigned int off, size_t hdrlen, + int start, int offset, + struct gro_remcsum *grc, + bool nopartial) +{ + __wsum delta; + size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + + BUG_ON(!NAPI_GRO_CB(skb)->csum_valid); + + if (!nopartial) { + NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start; + return ptr; + } + + ptr = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, off + plen)) { + ptr = skb_gro_header_slow(skb, off + plen, off); + if (!ptr) + return NULL; + } + + delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum, + start, offset); + + /* Adjust skb->csum since we changed the packet */ + NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta); + + grc->offset = off + hdrlen + offset; + grc->delta = delta; + + return ptr; +} + +static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb, + struct gro_remcsum *grc) +{ + void *ptr; + size_t plen = grc->offset + sizeof(u16); + + if (!grc->delta) + return; + + ptr = skb_gro_header_fast(skb, grc->offset); + if (skb_gro_header_hard(skb, grc->offset + sizeof(u16))) { + ptr = skb_gro_header_slow(skb, plen, grc->offset); + if (!ptr) + return; + } + + remcsum_unadjust((__sum16 *)ptr, grc->delta); +} + +#ifdef CONFIG_XFRM_OFFLOAD +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) +{ + if (PTR_ERR(pp) != -EINPROGRESS) + NAPI_GRO_CB(skb)->flush |= flush; +} +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + if (PTR_ERR(pp) != -EINPROGRESS) { + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; + } +} +#else +static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush) +{ + NAPI_GRO_CB(skb)->flush |= flush; +} +static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb, + struct sk_buff *pp, + int flush, + struct gro_remcsum *grc) +{ + NAPI_GRO_CB(skb)->flush |= flush; + skb_gro_remcsum_cleanup(skb, grc); + skb->remcsum_offload = 0; +} +#endif INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *, struct sk_buff *)); @@ -15,6 +374,14 @@ INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *, struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); +INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); + +INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, + struct sk_buff *)); +INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); + #define indirect_call_gro_receive_inet(cb, f2, f1, head, skb) \ ({ \ unlikely(gro_recursion_inc_test(skb)) ? \ @@ -22,4 +389,54 @@ INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int)); INDIRECT_CALL_INET(cb, f2, f1, head, skb); \ }) +struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, + struct udphdr *uh, struct sock *sk); +int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); + +static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) +{ + struct udphdr *uh; + unsigned int hlen, off; + + off = skb_gro_offset(skb); + hlen = off + sizeof(*uh); + uh = skb_gro_header_fast(skb, off); + if (skb_gro_header_hard(skb, hlen)) + uh = skb_gro_header_slow(skb, hlen, off); + + return uh; +} + +static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) +{ + const struct ipv6hdr *iph = skb_gro_network_header(skb); + + return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, + skb_gro_len(skb), proto, 0)); +} + +int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb); + +/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static inline void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs) +{ + list_add_tail(&skb->list, &napi->rx_list); + napi->rx_count += segs; + if (napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + + #endif /* _NET_IPV6_GRO_H */ diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index 653e7d0f65cb..f026cf08a8e8 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -160,6 +160,7 @@ struct ipv6_devstat { struct inet6_dev { struct net_device *dev; + netdevice_tracker dev_tracker; struct list_head addr_list; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index fa6a87246a7b..4ad47d9f9d27 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -304,7 +304,7 @@ static inline __poll_t inet_csk_listen_poll(const struct sock *sk) (EPOLLIN | EPOLLRDNORM) : 0; } -int inet_csk_listen_start(struct sock *sk, int backlog); +int inet_csk_listen_start(struct sock *sk); void inet_csk_listen_stop(struct sock *sk); void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr); diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 9e1111f5915b..234d70ae5f4c 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -372,4 +372,16 @@ static inline bool inet_can_nonlocal_bind(struct net *net, inet->freebind || inet->transparent; } +static inline bool inet_addr_valid_or_nonlocal(struct net *net, + struct inet_sock *inet, + __be32 addr, + int addr_type) +{ + return inet_can_nonlocal_bind(net, inet) || + addr == htonl(INADDR_ANY) || + addr_type == RTN_LOCAL || + addr_type == RTN_MULTICAST || + addr_type == RTN_BROADCAST; +} + #endif /* _INET_SOCK_H */ diff --git a/include/net/ip.h b/include/net/ip.h index b71e88507c4a..81e23a102a0d 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -568,14 +568,6 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } -static inline __wsum inet_gro_compute_pseudo(struct sk_buff *skb, int proto) -{ - const struct iphdr *iph = skb_gro_network_header(skb); - - return csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb_gro_len(skb), proto, 0); -} - /* * Map a multicast IP onto multicast MAC for type ethernet. */ @@ -791,5 +783,6 @@ int ip_sock_set_mtu_discover(struct sock *sk, int val); void ip_sock_set_pktinfo(struct sock *sk); void ip_sock_set_recverr(struct sock *sk); void ip_sock_set_tos(struct sock *sk, int val); +void __ip_sock_set_tos(struct sock *sk, int val); #endif /* _IP_H */ diff --git a/include/net/ip6_checksum.h b/include/net/ip6_checksum.h index b3f4eaa88672..c8a96b888277 100644 --- a/include/net/ip6_checksum.h +++ b/include/net/ip6_checksum.h @@ -43,14 +43,6 @@ static inline __wsum ip6_compute_pseudo(struct sk_buff *skb, int proto) skb->len, proto, 0)); } -static inline __wsum ip6_gro_compute_pseudo(struct sk_buff *skb, int proto) -{ - const struct ipv6hdr *iph = skb_gro_network_header(skb); - - return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr, - skb_gro_len(skb), proto, 0)); -} - static __inline__ __sum16 tcp_v6_check(int len, const struct in6_addr *saddr, const struct in6_addr *daddr, @@ -65,15 +57,9 @@ static inline void __tcp_v6_send_check(struct sk_buff *skb, { struct tcphdr *th = tcp_hdr(skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) { - th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); - skb->csum_start = skb_transport_header(skb) - skb->head; - skb->csum_offset = offsetof(struct tcphdr, check); - } else { - th->check = tcp_v6_check(skb->len, saddr, daddr, - csum_partial(th, th->doff << 2, - skb->csum)); - } + th->check = ~tcp_v6_check(skb->len, saddr, daddr, 0); + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); } static inline void tcp_v6_gso_csum_prep(struct sk_buff *skb) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 83b8070d1cc9..a9a4ccc0cdb5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -20,6 +20,7 @@ #include <net/inetpeer.h> #include <net/fib_notifier.h> #include <linux/indirect_call_wrapper.h> +#include <uapi/linux/bpf.h> #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_HASHSZ 256 diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 5efd0b71dc67..ca2d6b60e1ec 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -263,19 +263,19 @@ static inline bool ipv6_anycast_destination(const struct dst_entry *dst, int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, int (*output)(struct net *, struct sock *, struct sk_buff *)); -static inline unsigned int ip6_skb_dst_mtu(struct sk_buff *skb) +static inline unsigned int ip6_skb_dst_mtu(const struct sk_buff *skb) { - unsigned int mtu; - - struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? + const struct ipv6_pinfo *np = skb->sk && !dev_recursion_level() ? inet6_sk(skb->sk) : NULL; + const struct dst_entry *dst = skb_dst(skb); + unsigned int mtu; if (np && np->pmtudisc >= IPV6_PMTUDISC_PROBE) { - mtu = READ_ONCE(skb_dst(skb)->dev->mtu); - mtu -= lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu); - } else - mtu = dst_mtu(skb_dst(skb)); - + mtu = READ_ONCE(dst->dev->mtu); + mtu -= lwtunnel_headroom(dst->lwtstate, mtu); + } else { + mtu = dst_mtu(dst); + } return mtu; } diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index 028eaea1c854..a38c4f1e4e5c 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -46,6 +46,7 @@ struct __ip6_tnl_parm { struct ip6_tnl { struct ip6_tnl __rcu *next; /* next tunnel in list */ struct net_device *dev; /* virtual device associated with tunnel */ + netdevice_tracker dev_tracker; struct net *net; /* netns for packet i/o */ struct __ip6_tnl_parm parms; /* tunnel configuration parameters */ struct flowi fl; /* flowi template for xmit */ diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 3417ba2d27ad..c4297704bbcb 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -79,6 +79,7 @@ struct fnhe_hash_bucket { struct fib_nh_common { struct net_device *nhc_dev; + netdevice_tracker nhc_dev_tracker; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; @@ -111,6 +112,7 @@ struct fib_nh { int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev +#define fib_nh_dev_tracker nh_common.nhc_dev_tracker #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index bc3b13ec93c9..0219fe907b26 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -104,7 +104,10 @@ struct metadata_dst; struct ip_tunnel { struct ip_tunnel __rcu *next; struct hlist_node hash_node; + struct net_device *dev; + netdevice_tracker dev_tracker; + struct net *net; /* netns for packet i/o */ unsigned long err_time; /* Time when the last ICMP error diff --git a/include/net/ipv6.h b/include/net/ipv6.h index c19bf51ded1d..3afcb128e064 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -21,6 +21,8 @@ #include <net/snmp.h> #include <net/netns/hash.h> +struct ip_tunnel_info; + #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 @@ -345,9 +347,9 @@ struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; + __u16 gso_size; __s8 dontfrag; struct ipv6_txoptions *opt; - __u16 gso_size; }; static inline void ipcm6_init(struct ipcm6_cookie *ipc6) diff --git a/include/net/iucv/af_iucv.h b/include/net/iucv/af_iucv.h index ff06246dbbb9..df85d19fbf84 100644 --- a/include/net/iucv/af_iucv.h +++ b/include/net/iucv/af_iucv.h @@ -112,10 +112,12 @@ enum iucv_tx_notify { struct iucv_sock { struct sock sk; - char src_user_id[8]; - char src_name[8]; - char dst_user_id[8]; - char dst_name[8]; + struct_group(init, + char src_user_id[8]; + char src_name[8]; + char dst_user_id[8]; + char dst_name[8]; + ); struct list_head accept_q; spinlock_t accept_q_lock; struct sock *parent; diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index ea985aa7a6c5..2c1ea3414640 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -38,6 +38,7 @@ struct llc_sock { struct llc_addr laddr; /* lsap/mac pair */ struct llc_addr daddr; /* dsap/mac pair */ struct net_device *dev; /* device to send to remote */ + netdevice_tracker dev_tracker; u32 copied_seq; /* head of yet unread data */ u8 retry_count; /* number of retries */ u8 ack_must_be_send; diff --git a/include/net/mac80211.h b/include/net/mac80211.h index dd757f0987b0..c50221d7e82c 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1205,12 +1205,7 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info) /* clear the rate counts */ for (i = 0; i < IEEE80211_TX_MAX_RATES; i++) info->status.rates[i].count = 0; - - BUILD_BUG_ON( - offsetof(struct ieee80211_tx_info, status.ack_signal) != 20); - memset(&info->status.ampdu_ack_len, 0, - sizeof(struct ieee80211_tx_info) - - offsetof(struct ieee80211_tx_info, status.ampdu_ack_len)); + memset_after(&info->status, 0, rates); } @@ -3944,6 +3939,16 @@ struct ieee80211_prep_tx_info { * twt structure. * @twt_teardown_request: Update the hw with TWT teardown request received * from the peer. + * @set_radar_background: Configure dedicated offchannel chain available for + * radar/CAC detection on some hw. This chain can't be used to transmit + * or receive frames and it is bounded to a running wdev. + * Background radar/CAC detection allows to avoid the CAC downtime + * switching to a different channel during CAC detection on the selected + * radar channel. + * The caller is expected to set chandef pointer to NULL in order to + * disable background CAC/radar detection. + * @net_fill_forward_path: Called from .ndo_fill_forward_path in order to + * resolve a path for hardware flow offloading */ struct ieee80211_ops { void (*tx)(struct ieee80211_hw *hw, @@ -4272,6 +4277,13 @@ struct ieee80211_ops { struct ieee80211_twt_setup *twt); void (*twt_teardown_request)(struct ieee80211_hw *hw, struct ieee80211_sta *sta, u8 flowid); + int (*set_radar_background)(struct ieee80211_hw *hw, + struct cfg80211_chan_def *chandef); + int (*net_fill_forward_path)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct net_device_path_ctx *ctx, + struct net_device_path *path); }; /** @@ -5602,6 +5614,9 @@ void ieee80211_iterate_active_interfaces_atomic(struct ieee80211_hw *hw, * This function iterates over the interfaces associated with a given * hardware that are currently active and calls the callback for them. * This version can only be used while holding the wiphy mutex. + * The driver must not call this with a lock held that it can also take in + * response to callbacks from mac80211, and it must not call this within + * callbacks made by mac80211 - both would result in deadlocks. * * @hw: the hardware struct of which the interfaces should be iterated over * @iter_flags: iteration flags, see &enum ieee80211_interface_iteration_flags @@ -5616,6 +5631,24 @@ void ieee80211_iterate_active_interfaces_mtx(struct ieee80211_hw *hw, void *data); /** + * ieee80211_iterate_stations - iterate stations + * + * This function iterates over all stations associated with a given + * hardware that are currently uploaded to the driver and calls the callback + * function for them. + * This function allows the iterator function to sleep, when the iterator + * function is atomic @ieee80211_iterate_stations_atomic can be used. + * + * @hw: the hardware struct of which the interfaces should be iterated over + * @iterator: the iterator function to call, cannot sleep + * @data: first argument of the iterator function + */ +void ieee80211_iterate_stations(struct ieee80211_hw *hw, + void (*iterator)(void *data, + struct ieee80211_sta *sta), + void *data); + +/** * ieee80211_iterate_stations_atomic - iterate stations * * This function iterates over all stations associated with a given @@ -6064,6 +6097,18 @@ void ieee80211_radar_detected(struct ieee80211_hw *hw); void ieee80211_chswitch_done(struct ieee80211_vif *vif, bool success); /** + * ieee80211_channel_switch_disconnect - disconnect due to channel switch error + * @vif &struct ieee80211_vif pointer from the add_interface callback. + * @block_tx: if %true, do not send deauth frame. + * + * Instruct mac80211 to disconnect due to a channel switch error. The channel + * switch can request to block the tx and so, we need to make sure we do not send + * a deauth frame in this case. + */ +void ieee80211_channel_switch_disconnect(struct ieee80211_vif *vif, + bool block_tx); + +/** * ieee80211_request_smps - request SM PS transition * @vif: &struct ieee80211_vif pointer from the add_interface callback. * @smps_mode: new SM PS mode diff --git a/include/net/ndisc.h b/include/net/ndisc.h index 04341d86585d..53cb8de0e589 100644 --- a/include/net/ndisc.h +++ b/include/net/ndisc.h @@ -411,13 +411,7 @@ static inline void __ipv6_confirm_neigh(struct net_device *dev, rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(dev, pkey); - if (n) { - unsigned long now = jiffies; - - /* avoid dirtying neighbour */ - if (READ_ONCE(n->confirmed) != now) - WRITE_ONCE(n->confirmed, now); - } + neigh_confirm(n); rcu_read_unlock_bh(); } @@ -428,13 +422,7 @@ static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref_stub(dev, pkey); - if (n) { - unsigned long now = jiffies; - - /* avoid dirtying neighbour */ - if (READ_ONCE(n->confirmed) != now) - WRITE_ONCE(n->confirmed, now); - } + neigh_confirm(n); rcu_read_unlock_bh(); } diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 38a0c1d24570..937389e04c8e 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -70,6 +70,7 @@ enum { struct neigh_parms { possible_net_t net; struct net_device *dev; + netdevice_tracker dev_tracker; struct list_head list; int (*neigh_setup)(struct neighbour *); struct neigh_table *tbl; @@ -158,6 +159,7 @@ struct neighbour { struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; + netdevice_tracker dev_tracker; u8 primary_key[0]; } __randomize_layout; @@ -173,6 +175,7 @@ struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; + netdevice_tracker dev_tracker; u32 flags; u8 protocol; u8 key[]; @@ -321,6 +324,17 @@ static inline struct neighbour *__neigh_lookup_noref(struct neigh_table *tbl, return ___neigh_lookup_noref(tbl, tbl->key_eq, tbl->hash, pkey, dev); } +static inline void neigh_confirm(struct neighbour *n) +{ + if (n) { + unsigned long now = jiffies; + + /* avoid dirtying neighbour */ + if (READ_ONCE(n->confirmed) != now) + WRITE_ONCE(n->confirmed, now); + } +} + void neigh_table_init(int index, struct neigh_table *tbl); int neigh_table_clear(int index, struct neigh_table *tbl); struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index bb5fa5914032..5b61c462e534 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -34,6 +34,7 @@ #include <net/netns/smc.h> #include <net/netns/bpf.h> #include <net/netns/mctp.h> +#include <net/net_trackers.h> #include <linux/ns_common.h> #include <linux/idr.h> #include <linux/skbuff.h> @@ -87,6 +88,7 @@ struct net { struct idr netns_ids; struct ns_common ns; + struct ref_tracker_dir refcnt_tracker; struct list_head dev_base_head; struct proc_dir_entry *proc_net; @@ -240,6 +242,7 @@ void ipx_unregister_sysctl(void); #ifdef CONFIG_NET_NS void __put_net(struct net *net); +/* Try using get_net_track() instead */ static inline struct net *get_net(struct net *net) { refcount_inc(&net->ns.count); @@ -258,6 +261,7 @@ static inline struct net *maybe_get_net(struct net *net) return net; } +/* Try using put_net_track() instead */ static inline void put_net(struct net *net) { if (refcount_dec_and_test(&net->ns.count)) @@ -308,6 +312,36 @@ static inline int check_net(const struct net *net) #endif +static inline void netns_tracker_alloc(struct net *net, + netns_tracker *tracker, gfp_t gfp) +{ +#ifdef CONFIG_NET_NS_REFCNT_TRACKER + ref_tracker_alloc(&net->refcnt_tracker, tracker, gfp); +#endif +} + +static inline void netns_tracker_free(struct net *net, + netns_tracker *tracker) +{ +#ifdef CONFIG_NET_NS_REFCNT_TRACKER + ref_tracker_free(&net->refcnt_tracker, tracker); +#endif +} + +static inline struct net *get_net_track(struct net *net, + netns_tracker *tracker, gfp_t gfp) +{ + get_net(net); + netns_tracker_alloc(net, tracker, gfp); + return net; +} + +static inline void put_net_track(struct net *net, netns_tracker *tracker) +{ + netns_tracker_free(net, tracker); + put_net(net); +} + typedef struct { #ifdef CONFIG_NET_NS struct net *net; diff --git a/include/net/net_trackers.h b/include/net/net_trackers.h new file mode 100644 index 000000000000..d94c76cf15a9 --- /dev/null +++ b/include/net/net_trackers.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NET_TRACKERS_H +#define __NET_NET_TRACKERS_H +#include <linux/ref_tracker.h> + +#ifdef CONFIG_NET_DEV_REFCNT_TRACKER +typedef struct ref_tracker *netdevice_tracker; +#else +typedef struct {} netdevice_tracker; +#endif + +#ifdef CONFIG_NET_NS_REFCNT_TRACKER +typedef struct ref_tracker *netns_tracker; +#else +typedef struct {} netns_tracker; +#endif + +#endif /* __NET_NET_TRACKERS_H */ diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d24b0a34c8f0..8731d5bcb47d 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -76,6 +76,8 @@ struct nf_conn { * Hint, SKB address this struct and refcnt via skb->_nfct and * helpers nf_conntrack_get() and nf_conntrack_put(). * Helper nf_ct_put() equals nf_conntrack_put() by dec refcnt, + * except that the latter uses internal indirection and does not + * result in a conntrack module dependency. * beware nf_ct_get() is different and don't inc refcnt. */ struct nf_conntrack ct_general; @@ -95,6 +97,7 @@ struct nf_conn { unsigned long status; u16 cpu; + u16 local_origin:1; possible_net_t ct_net; #if IS_ENABLED(CONFIG_NF_NAT) @@ -169,11 +172,13 @@ nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo) return (struct nf_conn *)(nfct & NFCT_PTRMASK); } +void nf_ct_destroy(struct nf_conntrack *nfct); + /* decrement reference count on a conntrack */ static inline void nf_ct_put(struct nf_conn *ct) { - WARN_ON(!ct); - nf_conntrack_put(&ct->ct_general); + if (ct && refcount_dec_and_test(&ct->ct_general.use)) + nf_ct_destroy(&ct->ct_general); } /* Protocol module loading */ @@ -278,7 +283,7 @@ static inline unsigned long nf_ct_expires(const struct nf_conn *ct) { s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp; - return timeout > 0 ? timeout : 0; + return max(timeout, 0); } static inline bool nf_ct_is_expired(const struct nf_conn *ct) diff --git a/include/net/netfilter/nf_conntrack_act_ct.h b/include/net/netfilter/nf_conntrack_act_ct.h new file mode 100644 index 000000000000..078d3c52c03f --- /dev/null +++ b/include/net/netfilter/nf_conntrack_act_ct.h @@ -0,0 +1,50 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef _NF_CONNTRACK_ACT_CT_H +#define _NF_CONNTRACK_ACT_CT_H + +#include <net/netfilter/nf_conntrack.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <net/netfilter/nf_conntrack_extend.h> + +struct nf_conn_act_ct_ext { + int ifindex[IP_CT_DIR_MAX]; +}; + +static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_find(const struct nf_conn *ct) +{ +#if IS_ENABLED(CONFIG_NET_ACT_CT) + return nf_ct_ext_find(ct, NF_CT_EXT_ACT_CT); +#else + return NULL; +#endif +} + +static inline struct nf_conn_act_ct_ext *nf_conn_act_ct_ext_add(struct nf_conn *ct) +{ +#if IS_ENABLED(CONFIG_NET_ACT_CT) + struct nf_conn_act_ct_ext *act_ct = nf_ct_ext_find(ct, NF_CT_EXT_ACT_CT); + + if (act_ct) + return act_ct; + + act_ct = nf_ct_ext_add(ct, NF_CT_EXT_ACT_CT, GFP_ATOMIC); + return act_ct; +#else + return NULL; +#endif +} + +static inline void nf_conn_act_ct_ext_fill(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ +#if IS_ENABLED(CONFIG_NET_ACT_CT) + struct nf_conn_act_ct_ext *act_ct_ext; + + act_ct_ext = nf_conn_act_ct_ext_find(ct); + if (dev_net(skb->dev) == &init_net && act_ct_ext) + act_ct_ext->ifindex[CTINFO2DIR(ctinfo)] = skb->dev->ifindex; +#endif +} + +#endif /* _NF_CONNTRACK_ACT_CT_H */ diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index e1e588387103..c7515d82ab06 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -28,6 +28,9 @@ enum nf_ct_ext_id { #if IS_ENABLED(CONFIG_NETFILTER_SYNPROXY) NF_CT_EXT_SYNPROXY, #endif +#if IS_ENABLED(CONFIG_NET_ACT_CT) + NF_CT_EXT_ACT_CT, +#endif NF_CT_EXT_NUM, }; @@ -40,6 +43,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_TIMEOUT_TYPE struct nf_conn_timeout #define NF_CT_EXT_LABELS_TYPE struct nf_conn_labels #define NF_CT_EXT_SYNPROXY_TYPE struct nf_conn_synproxy +#define NF_CT_EXT_ACT_CT_TYPE struct nf_conn_act_ct_ext /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index a0d9e0b47ab8..eaf55da9a205 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -105,6 +105,8 @@ struct nft_data { }; } __attribute__((aligned(__alignof__(u64)))); +#define NFT_REG32_NUM 20 + /** * struct nft_regs - nf_tables register set * @@ -115,11 +117,21 @@ struct nft_data { */ struct nft_regs { union { - u32 data[20]; + u32 data[NFT_REG32_NUM]; struct nft_verdict verdict; }; }; +struct nft_regs_track { + struct { + const struct nft_expr *selector; + const struct nft_expr *bitwise; + } regs[NFT_REG32_NUM]; + + const struct nft_expr *cur; + const struct nft_expr *last; +}; + /* Store/load an u8, u16 or u64 integer to/from the u32 data register. * * Note, when using concatenations, register allocation happens at 32-bit @@ -346,6 +358,8 @@ int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, const struct nft_expr *expr); +bool nft_expr_reduce_bitwise(struct nft_regs_track *track, + const struct nft_expr *expr); struct nft_set_ext; @@ -884,6 +898,8 @@ struct nft_expr_ops { int (*validate)(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data); + bool (*reduce)(struct nft_regs_track *track, + const struct nft_expr *expr); bool (*gc)(struct net *net, const struct nft_expr *expr); int (*offload)(struct nft_offload_ctx *ctx, @@ -974,6 +990,20 @@ static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, #define NFT_CHAIN_POLICY_UNSET U8_MAX +struct nft_rule_dp { + u64 is_last:1, + dlen:12, + handle:42; /* for tracing */ + unsigned char data[] + __attribute__((aligned(__alignof__(struct nft_expr)))); +}; + +struct nft_rule_blob { + unsigned long size; + unsigned char data[] + __attribute__((aligned(__alignof__(struct nft_rule_dp)))); +}; + /** * struct nft_chain - nf_tables chain * @@ -987,8 +1017,8 @@ static inline void nft_set_elem_update_expr(const struct nft_set_ext *ext, * @name: name of the chain */ struct nft_chain { - struct nft_rule *__rcu *rules_gen_0; - struct nft_rule *__rcu *rules_gen_1; + struct nft_rule_blob __rcu *blob_gen_0; + struct nft_rule_blob __rcu *blob_gen_1; struct list_head rules; struct list_head list; struct rhlist_head rhlhead; @@ -1003,7 +1033,7 @@ struct nft_chain { u8 *udata; /* Only used during control plane commit phase: */ - struct nft_rule **rules_next; + struct nft_rule_blob *blob_next; }; int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain); @@ -1321,7 +1351,7 @@ struct nft_traceinfo { const struct nft_pktinfo *pkt; const struct nft_base_chain *basechain; const struct nft_chain *chain; - const struct nft_rule *rule; + const struct nft_rule_dp *rule; const struct nft_verdict *verdict; enum nft_trace_types type; bool packet_dumped; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 0fa5a6d98a00..b6fb1fdff9b2 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -7,6 +7,7 @@ extern struct nft_expr_type nft_imm_type; extern struct nft_expr_type nft_cmp_type; +extern struct nft_expr_type nft_counter_type; extern struct nft_expr_type nft_lookup_type; extern struct nft_expr_type nft_bitwise_type; extern struct nft_expr_type nft_byteorder_type; @@ -21,6 +22,7 @@ extern struct nft_expr_type nft_last_type; #ifdef CONFIG_NETWORK_SECMARK extern struct nft_object_type nft_secmark_obj_type; #endif +extern struct nft_object_type nft_counter_obj_type; int nf_tables_core_module_init(void); void nf_tables_core_module_exit(void); @@ -120,6 +122,8 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext); +void nft_counter_init_seqcount(void); + struct nft_expr; struct nft_regs; struct nft_pktinfo; @@ -143,4 +147,6 @@ void nft_dynset_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_rt_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); +void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt); #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/net/netns/bpf.h b/include/net/netns/bpf.h index 0ca6a1b87185..2c01a278d1eb 100644 --- a/include/net/netns/bpf.h +++ b/include/net/netns/bpf.h @@ -6,11 +6,18 @@ #ifndef __NETNS_BPF_H__ #define __NETNS_BPF_H__ -#include <linux/bpf-netns.h> +#include <linux/list.h> struct bpf_prog; struct bpf_prog_array; +enum netns_bpf_attach_type { + NETNS_BPF_INVALID = -1, + NETNS_BPF_FLOW_DISSECTOR = 0, + NETNS_BPF_SK_LOOKUP, + MAX_NETNS_BPF_ATTACH_TYPE +}; + struct netns_bpf { /* Array of programs to run compiled from progs or links */ struct bpf_prog_array __rcu *run_array[MAX_NETNS_BPF_ATTACH_TYPE]; diff --git a/include/net/netns/core.h b/include/net/netns/core.h index 36c2d998a43c..552bc25b1933 100644 --- a/include/net/netns/core.h +++ b/include/net/netns/core.h @@ -12,7 +12,6 @@ struct netns_core { int sysctl_somaxconn; #ifdef CONFIG_PROC_FS - int __percpu *sock_inuse; struct prot_inuse __percpu *prot_inuse; #endif }; diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 6c5b2efc4f17..78557643526e 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -85,6 +85,9 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; + u32 ip_rt_min_pmtu; + int ip_rt_mtu_expires; + struct local_ports ip_local_ports; u8 sysctl_tcp_ecn; diff --git a/include/net/page_pool.h b/include/net/page_pool.h index a4082406a003..79a805542d0f 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -80,6 +80,8 @@ struct page_pool_params { enum dma_data_direction dma_dir; /* DMA mapping direction */ unsigned int max_len; /* max DMA sync memory size */ unsigned int offset; /* DMA addr offset */ + void (*init_callback)(struct page *page, void *arg); + void *init_arg; }; struct page_pool { @@ -94,6 +96,7 @@ struct page_pool { unsigned int frag_offset; struct page *frag_page; long frag_users; + u32 xdp_mem_id; /* * Data structure for allocation side @@ -168,9 +171,12 @@ bool page_pool_return_skb_page(struct page *page); struct page_pool *page_pool_create(const struct page_pool_params *params); +struct xdp_mem_info; + #ifdef CONFIG_PAGE_POOL void page_pool_destroy(struct page_pool *pool); -void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *)); +void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *), + struct xdp_mem_info *mem); void page_pool_release_page(struct page_pool *pool, struct page *page); void page_pool_put_page_bulk(struct page_pool *pool, void **data, int count); @@ -180,7 +186,8 @@ static inline void page_pool_destroy(struct page_pool *pool) } static inline void page_pool_use_xdp_mem(struct page_pool *pool, - void (*disconnect)(void *)) + void (*disconnect)(void *), + struct xdp_mem_info *mem) { } static inline void page_pool_release_page(struct page_pool *pool, diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index 193f88ebf629..ebef45e821af 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -202,7 +202,8 @@ struct tcf_exts { __u32 type; /* for backward compat(TCA_OLD_COMPAT) */ int nr_actions; struct tc_action **actions; - struct net *net; + struct net *net; + netns_tracker ns_tracker; #endif /* Map to export classifier specific extension TLV types to the * generic extensions API. Unsupported extensions must be set to 0. @@ -218,6 +219,7 @@ static inline int tcf_exts_init(struct tcf_exts *exts, struct net *net, exts->type = 0; exts->nr_actions = 0; exts->net = net; + netns_tracker_alloc(net, &exts->ns_tracker, GFP_KERNEL); exts->actions = kcalloc(TCA_ACT_MAX_PRIO, sizeof(struct tc_action *), GFP_KERNEL); if (!exts->actions) @@ -236,6 +238,8 @@ static inline bool tcf_exts_get_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT exts->net = maybe_get_net(exts->net); + if (exts->net) + netns_tracker_alloc(exts->net, &exts->ns_tracker, GFP_KERNEL); return exts->net != NULL; #else return true; @@ -246,7 +250,7 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts) { #ifdef CONFIG_NET_CLS_ACT if (exts->net) - put_net(exts->net); + put_net_track(exts->net, &exts->ns_tracker); #endif } @@ -258,26 +262,31 @@ static inline void tcf_exts_put_net(struct tcf_exts *exts) for (; 0; (void)(i), (void)(a), (void)(exts)) #endif +#define tcf_act_for_each_action(i, a, actions) \ + for (i = 0; i < TCA_ACT_MAX_PRIO && ((a) = actions[i]); i++) + static inline void -tcf_exts_stats_update(const struct tcf_exts *exts, - u64 bytes, u64 packets, u64 drops, u64 lastuse, - u8 used_hw_stats, bool used_hw_stats_valid) +tcf_exts_hw_stats_update(const struct tcf_exts *exts, + u64 bytes, u64 packets, u64 drops, u64 lastuse, + u8 used_hw_stats, bool used_hw_stats_valid) { #ifdef CONFIG_NET_CLS_ACT int i; - preempt_disable(); - for (i = 0; i < exts->nr_actions; i++) { struct tc_action *a = exts->actions[i]; - tcf_action_stats_update(a, bytes, packets, drops, - lastuse, true); - a->used_hw_stats = used_hw_stats; - a->used_hw_stats_valid = used_hw_stats_valid; - } + /* if stats from hw, just skip */ + if (tcf_action_update_hw_stats(a)) { + preempt_disable(); + tcf_action_stats_update(a, bytes, packets, drops, + lastuse, true); + preempt_enable(); - preempt_enable(); + a->used_hw_stats = used_hw_stats; + a->used_hw_stats_valid = used_hw_stats_valid; + } + } #endif } @@ -321,6 +330,9 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, u32 flags, struct netlink_ext_ack *extack); +int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **tb, + struct nlattr *rate_tlv, struct tcf_exts *exts, + u32 flags, u32 fl_flags, struct netlink_ext_ack *extack); void tcf_exts_destroy(struct tcf_exts *exts); void tcf_exts_change(struct tcf_exts *dst, struct tcf_exts *src); int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts); @@ -532,9 +544,11 @@ tcf_match_indev(struct sk_buff *skb, int ifindex) return ifindex == skb->skb_iif; } -int tc_setup_flow_action(struct flow_action *flow_action, - const struct tcf_exts *exts); -void tc_cleanup_flow_action(struct flow_action *flow_action); +int tc_setup_offload_action(struct flow_action *flow_action, + const struct tcf_exts *exts); +void tc_cleanup_offload_action(struct flow_action *flow_action); +int tc_setup_action(struct flow_action *flow_action, + struct tc_action *actions[]); int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, void *type_data, bool err_stop, bool rtnl_held); diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h index 9e71691c491b..9e7b21c0b3a6 100644 --- a/include/net/pkt_sched.h +++ b/include/net/pkt_sched.h @@ -197,7 +197,9 @@ struct tc_skb_cb { struct qdisc_skb_cb qdisc_cb; u16 mru; - bool post_ct; + u8 post_ct:1; + u8 post_ct_snat:1; + u8 post_ct_dnat:1; u16 zone; /* Only valid if post_ct = true */ }; diff --git a/include/net/route.h b/include/net/route.h index 2e6c0e153e3a..4c858dcf1aa8 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -43,6 +43,7 @@ #define RT_CONN_FLAGS(sk) (RT_TOS(inet_sk(sk)->tos) | sock_flag(sk, SOCK_LOCALROUTE)) #define RT_CONN_FLAGS_TOS(sk,tos) (RT_TOS(tos) | sock_flag(sk, SOCK_LOCALROUTE)) +struct ip_tunnel_info; struct fib_nh; struct fib_info; struct uncached_list; diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index c70e6d2b2fdd..c11dbac5abb2 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -125,7 +125,7 @@ struct Qdisc { spinlock_t seqlock; struct rcu_head rcu; - + netdevice_tracker dev_tracker; /* private data */ long privdata[] ____cacheline_aligned; }; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 3ae61ce2eabd..bf3716fe83e0 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -509,8 +509,8 @@ static inline int sctp_ep_hashfn(struct net *net, __u16 lport) return (net_hash_mix(net) + lport) & (sctp_ep_hashsize - 1); } -#define sctp_for_each_hentry(epb, head) \ - hlist_for_each_entry(epb, head, node) +#define sctp_for_each_hentry(ep, head) \ + hlist_for_each_entry(ep, head, node) /* Is a socket of this style? */ #define sctp_style(sk, style) __sctp_style((sk), (SCTP_SOCKET_##style)) diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 8dabd8800006..350f250b0dc7 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -984,12 +984,10 @@ struct sctp_transport { } cacc; struct { - __u32 last_rtx_chunks; __u16 pmtu; __u16 probe_size; __u16 probe_high; - __u8 probe_count:3; - __u8 raise_count:5; + __u8 probe_count; __u8 state; } pl; /* plpmtud related */ @@ -1011,6 +1009,7 @@ void sctp_transport_reset_t3_rtx(struct sctp_transport *); void sctp_transport_reset_hb_timer(struct sctp_transport *); void sctp_transport_reset_reconf_timer(struct sctp_transport *transport); void sctp_transport_reset_probe_timer(struct sctp_transport *transport); +void sctp_transport_reset_raise_timer(struct sctp_transport *transport); int sctp_transport_hold(struct sctp_transport *); void sctp_transport_put(struct sctp_transport *); void sctp_transport_update_rto(struct sctp_transport *, __u32); @@ -1025,7 +1024,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); -bool sctp_transport_pl_send(struct sctp_transport *t); +void sctp_transport_pl_send(struct sctp_transport *t); bool sctp_transport_pl_recv(struct sctp_transport *t); @@ -1244,10 +1243,6 @@ enum sctp_endpoint_type { */ struct sctp_ep_common { - /* Fields to help us manage our entries in the hash tables. */ - struct hlist_node node; - int hashent; - /* Runtime type information. What kind of endpoint is this? */ enum sctp_endpoint_type type; @@ -1299,6 +1294,10 @@ struct sctp_endpoint { /* Common substructure for endpoint and association. */ struct sctp_ep_common base; + /* Fields to help us manage our entries in the hash tables. */ + struct hlist_node node; + int hashent; + /* Associations: A list of current associations and mappings * to the data consumers for each association. This * may be in the form of a hash table or other diff --git a/include/net/sock.h b/include/net/sock.h index d47e9658da28..ff9b508d9c5f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -56,13 +56,13 @@ #include <linux/wait.h> #include <linux/cgroup-defs.h> #include <linux/rbtree.h> -#include <linux/filter.h> #include <linux/rculist_nulls.h> #include <linux/poll.h> #include <linux/sockptr.h> #include <linux/indirect_call_wrapper.h> #include <linux/atomic.h> #include <linux/refcount.h> +#include <linux/llist.h> #include <net/dst.h> #include <net/checksum.h> #include <net/tcp_states.h> @@ -248,6 +248,7 @@ struct sock_common { }; struct bpf_local_storage; +struct sk_filter; /** * struct sock - network layer representation of sockets @@ -284,15 +285,14 @@ struct bpf_local_storage; * @sk_no_check_tx: %SO_NO_CHECK setting, set checksum in TX packets * @sk_no_check_rx: allow zero checksum in RX packets * @sk_route_caps: route capabilities (e.g. %NETIF_F_TSO) - * @sk_route_nocaps: forbidden route capabilities (e.g NETIF_F_GSO_MASK) - * @sk_route_forced_caps: static, forced route capabilities - * (set in tcp_init_sock()) + * @sk_gso_disabled: if set, NETIF_F_GSO_MASK is forbidden. * @sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4) * @sk_gso_max_size: Maximum GSO segment size to build * @sk_gso_max_segs: Maximum number of GSO segments * @sk_pacing_shift: scaling factor for TCP Small Queues * @sk_lingertime: %SO_LINGER l_linger setting * @sk_backlog: always used with the per-socket spinlock held + * @defer_list: head of llist storing skbs to be freed * @sk_callback_lock: used with the callbacks in the end of this struct * @sk_error_queue: rarely used * @sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt, @@ -350,6 +350,7 @@ struct bpf_local_storage; * @sk_txtime_deadline_mode: set deadline mode for SO_TXTIME * @sk_txtime_report_errors: set report errors mode for SO_TXTIME * @sk_txtime_unused: unused txtime flags + * @ns_tracker: tracker for netns reference */ struct sock { /* @@ -391,6 +392,11 @@ struct sock { #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash + /* early demux fields */ + struct dst_entry __rcu *sk_rx_dst; + int sk_rx_dst_ifindex; + u32 sk_rx_dst_cookie; + socket_lock_t sk_lock; atomic_t sk_drops; int sk_rcvlowat; @@ -410,6 +416,8 @@ struct sock { struct sk_buff *head; struct sk_buff *tail; } sk_backlog; + struct llist_head defer_list; + #define sk_rmem_alloc sk_backlog.rmem_alloc int sk_forward_alloc; @@ -431,9 +439,6 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif - struct dst_entry __rcu *sk_rx_dst; - int sk_rx_dst_ifindex; - u32 sk_rx_dst_cookie; struct dst_entry __rcu *sk_dst_cache; atomic_t sk_omem_alloc; @@ -460,8 +465,6 @@ struct sock { unsigned long sk_max_pacing_rate; struct page_frag sk_frag; netdev_features_t sk_route_caps; - netdev_features_t sk_route_nocaps; - netdev_features_t sk_route_forced_caps; int sk_gso_type; unsigned int sk_gso_max_size; gfp_t sk_allocation; @@ -471,7 +474,7 @@ struct sock { * Because of non atomicity rules, all * changes are protected by socket lock. */ - u8 sk_padding : 1, + u8 sk_gso_disabled : 1, sk_kern_sock : 1, sk_no_check_tx : 1, sk_no_check_rx : 1, @@ -493,6 +496,7 @@ struct sock { u16 sk_busy_poll_budget; #endif spinlock_t sk_peer_lock; + int sk_bind_phc; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; @@ -502,7 +506,6 @@ struct sock { seqlock_t sk_stamp_seq; #endif u16 sk_tsflags; - int sk_bind_phc; u8 sk_shutdown; u32 sk_tskey; atomic_t sk_zckey; @@ -536,6 +539,7 @@ struct sock { struct bpf_local_storage __rcu *sk_bpf_storage; #endif struct rcu_head sk_rcu; + netns_tracker ns_tracker; }; enum sk_pacing { @@ -1022,12 +1026,18 @@ static inline __must_check int sk_add_backlog(struct sock *sk, struct sk_buff *s int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb); +INDIRECT_CALLABLE_DECLARE(int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)); +INDIRECT_CALLABLE_DECLARE(int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)); + static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) { if (sk_memalloc_socks() && skb_pfmemalloc(skb)) return __sk_backlog_rcv(sk, skb); - return sk->sk_backlog_rcv(sk, skb); + return INDIRECT_CALL_INET(sk->sk_backlog_rcv, + tcp_v6_do_rcv, + tcp_v4_do_rcv, + sk, skb); } static inline void sk_incoming_cpu_update(struct sock *sk) @@ -1199,6 +1209,7 @@ struct proto { void (*unhash)(struct sock *sk); void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); + void (*put_port)(struct sock *sk); #ifdef CONFIG_BPF_SYSCALL int (*psock_update_sk_prot)(struct sock *sk, struct sk_psock *psock, @@ -1210,7 +1221,9 @@ struct proto { unsigned int inuse_idx; #endif +#if IS_ENABLED(CONFIG_MPTCP) int (*forward_alloc_get)(const struct sock *sk); +#endif bool (*stream_memory_free)(const struct sock *sk, int wake); bool (*sock_is_readable)(struct sock *sk); @@ -1299,10 +1312,11 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int static inline int sk_forward_alloc_get(const struct sock *sk) { - if (!sk->sk_prot->forward_alloc_get) - return sk->sk_forward_alloc; - - return sk->sk_prot->forward_alloc_get(sk); +#if IS_ENABLED(CONFIG_MPTCP) + if (sk->sk_prot->forward_alloc_get) + return sk->sk_prot->forward_alloc_get(sk); +#endif + return sk->sk_forward_alloc; } static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) @@ -1419,13 +1433,32 @@ proto_memory_pressure(struct proto *prot) #ifdef CONFIG_PROC_FS -/* Called with local bh disabled */ -void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); +#define PROTO_INUSE_NR 64 /* should be enough for the first time */ +struct prot_inuse { + int all; + int val[PROTO_INUSE_NR]; +}; + +static inline void sock_prot_inuse_add(const struct net *net, + const struct proto *prot, int val) +{ + this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); +} + +static inline void sock_inuse_add(const struct net *net, int val) +{ + this_cpu_add(net->core.prot_inuse->all, val); +} + int sock_prot_inuse_get(struct net *net, struct proto *proto); int sock_inuse_get(struct net *net); #else -static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, - int inc) +static inline void sock_prot_inuse_add(const struct net *net, + const struct proto *prot, int val) +{ +} + +static inline void sock_inuse_add(const struct net *net, int val) { } #endif @@ -1603,16 +1636,6 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) __sk_mem_reclaim(sk, SK_RECLAIM_CHUNK); } -static inline void sock_release_ownership(struct sock *sk) -{ - if (sk->sk_lock.owned) { - sk->sk_lock.owned = 0; - - /* The sk_lock has mutex_unlock() semantics: */ - mutex_release(&sk->sk_lock.dep_map, _RET_IP_); - } -} - /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -1739,12 +1762,23 @@ static inline bool sock_owned_by_user_nocheck(const struct sock *sk) return sk->sk_lock.owned; } +static inline void sock_release_ownership(struct sock *sk) +{ + if (sock_owned_by_user_nocheck(sk)) { + sk->sk_lock.owned = 0; + + /* The sk_lock has mutex_unlock() semantics: */ + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); + } +} + /* no reclassification while locks are held */ static inline bool sock_allow_reclassification(const struct sock *csk) { struct sock *sk = (struct sock *)csk; - return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock); + return !sock_owned_by_user_nocheck(sk) && + !spin_is_locked(&sk->sk_lock.slock); } struct sock *sk_alloc(struct net *net, int family, gfp_t priority, @@ -2118,13 +2152,10 @@ static inline void sock_confirm_neigh(struct sk_buff *skb, struct neighbour *n) { if (skb_get_dst_pending_confirm(skb)) { struct sock *sk = skb->sk; - unsigned long now = jiffies; - /* avoid dirtying neighbour */ - if (READ_ONCE(n->confirmed) != now) - WRITE_ONCE(n->confirmed, now); if (sk && READ_ONCE(sk->sk_dst_pending_confirm)) WRITE_ONCE(sk->sk_dst_pending_confirm, 0); + neigh_confirm(n); } } @@ -2137,10 +2168,10 @@ static inline bool sk_can_gso(const struct sock *sk) void sk_setup_caps(struct sock *sk, struct dst_entry *dst); -static inline void sk_nocaps_add(struct sock *sk, netdev_features_t flags) +static inline void sk_gso_disable(struct sock *sk) { - sk->sk_route_nocaps |= flags; - sk->sk_route_caps &= ~flags; + sk->sk_gso_disabled = 1; + sk->sk_route_caps &= ~NETIF_F_GSO_MASK; } static inline int skb_do_copy_data_nocache(struct sock *sk, struct sk_buff *skb, @@ -2654,6 +2685,11 @@ static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) &skb_shinfo(skb)->tskey); } +static inline bool sk_is_tcp(const struct sock *sk) +{ + return sk->sk_type == SOCK_STREAM && sk->sk_protocol == IPPROTO_TCP; +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/tc_act/tc_gate.h b/include/net/tc_act/tc_gate.h index 8bc6be81a7ad..c8fa11ebb397 100644 --- a/include/net/tc_act/tc_gate.h +++ b/include/net/tc_act/tc_gate.h @@ -60,11 +60,6 @@ static inline bool is_tcf_gate(const struct tc_action *a) return false; } -static inline u32 tcf_gate_index(const struct tc_action *a) -{ - return a->tcfa_index; -} - static inline s32 tcf_gate_prio(const struct tc_action *a) { s32 tcfg_prio; diff --git a/include/net/tc_act/tc_mirred.h b/include/net/tc_act/tc_mirred.h index 1cace4c69e44..32ce8ea36950 100644 --- a/include/net/tc_act/tc_mirred.h +++ b/include/net/tc_act/tc_mirred.h @@ -10,6 +10,7 @@ struct tcf_mirred { int tcfm_eaction; bool tcfm_mac_header_xmit; struct net_device __rcu *tcfm_dev; + netdevice_tracker tcfm_dev_tracker; struct list_head tcfm_list; }; #define to_mirred(a) ((struct tcf_mirred *)a) diff --git a/include/net/tcp.h b/include/net/tcp.h index 4da22b41bde6..44e442bf23f9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1368,6 +1368,16 @@ static inline bool tcp_checksum_complete(struct sk_buff *skb) } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb); + +void __sk_defer_free_flush(struct sock *sk); + +static inline void sk_defer_free_flush(struct sock *sk) +{ + if (llist_empty(&sk->defer_list)) + return; + __sk_defer_free_flush(sk); +} + int tcp_filter(struct sock *sk, struct sk_buff *skb); void tcp_set_state(struct sock *sk, int state); void tcp_done(struct sock *sk); @@ -2172,9 +2182,13 @@ static inline void tcp_segs_in(struct tcp_sock *tp, const struct sk_buff *skb) u16 segs_in; segs_in = max_t(u16, 1, skb_shinfo(skb)->gso_segs); - tp->segs_in += segs_in; + + /* We update these fields while other threads might + * read them from tcp_get_info() + */ + WRITE_ONCE(tp->segs_in, tp->segs_in + segs_in); if (skb->len > tcp_hdrlen(skb)) - tp->data_segs_in += segs_in; + WRITE_ONCE(tp->data_segs_in, tp->data_segs_in + segs_in); } /* diff --git a/include/net/udp.h b/include/net/udp.h index 909ecf447e0f..f1c2a88c9005 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -167,36 +167,12 @@ static inline void udp_csum_pull_header(struct sk_buff *skb) typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport, __be16 dport); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int)); -INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *, - struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int)); INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *)); INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *)); -struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, - struct udphdr *uh, struct sock *sk); -int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); - struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, netdev_features_t features, bool is_ipv6); -static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) -{ - struct udphdr *uh; - unsigned int hlen, off; - - off = skb_gro_offset(skb); - hlen = off + sizeof(*uh); - uh = skb_gro_header_fast(skb, off); - if (skb_gro_header_hard(skb, hlen)) - uh = skb_gro_header_slow(skb, hlen, off); - - return uh; -} - /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */ static inline int udp_lib_hash(struct sock *sk) { diff --git a/include/net/vxlan.h b/include/net/vxlan.h index 08537aa14f7c..5a934bebe630 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -10,6 +10,7 @@ #include <net/nexthop.h> #define IANA_VXLAN_UDP_PORT 4789 +#define IANA_VXLAN_GPE_UDP_PORT 4790 /* VXLAN protocol (RFC 7348) header: * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ diff --git a/include/net/xdp.h b/include/net/xdp.h index 447f9b1578f3..8f0812e4996d 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -260,6 +260,9 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); +int xdp_reg_mem_model(struct xdp_mem_info *mem, + enum xdp_mem_type type, void *allocator); +void xdp_unreg_mem_model(struct xdp_mem_info *mem); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/include/net/xdp_priv.h b/include/net/xdp_priv.h index a9d5b7603b89..a2d58b1a12e1 100644 --- a/include/net/xdp_priv.h +++ b/include/net/xdp_priv.h @@ -10,7 +10,6 @@ struct xdp_mem_allocator { union { void *allocator; struct page_pool *page_pool; - struct zero_copy_allocator *zc_alloc; }; struct rhash_head node; struct rcu_head rcu; diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index fff069d2ed1b..3057e1a4a11c 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -6,6 +6,7 @@ #ifndef _LINUX_XDP_SOCK_H #define _LINUX_XDP_SOCK_H +#include <linux/bpf.h> #include <linux/workqueue.h> #include <linux/if_xdp.h> #include <linux/mutex.h> diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 2308210793a0..fdb41e8bb626 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -128,6 +128,7 @@ struct xfrm_state_walk { struct xfrm_state_offload { struct net_device *dev; + netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; unsigned int num_exthdrs; @@ -200,6 +201,11 @@ struct xfrm_state { struct xfrm_algo_aead *aead; const char *geniv; + /* mapping change rate limiting */ + __be16 new_mapping_sport; + u32 new_mapping; /* seconds */ + u32 mapping_maxage; /* seconds for input SA */ + /* Data for encapsulator */ struct xfrm_encap_tmpl *encap; struct sock __rcu *encap_sk; @@ -1162,7 +1168,7 @@ static inline int xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); - if (xfrm_default_allow(net, XFRM_POLICY_FWD)) + if (xfrm_default_allow(net, XFRM_POLICY_OUT)) return !net->xfrm.policy_count[XFRM_POLICY_OUT] || (skb_dst(skb)->flags & DST_NOXFRM) || __xfrm_route_forward(skb, family); @@ -1913,7 +1919,7 @@ static inline void xfrm_dev_state_free(struct xfrm_state *x) if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(x); xso->dev = NULL; - dev_put(dev); + dev_put_track(dev, &xso->dev_tracker); } } #else diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index fef3a36b0210..5c3a3597f1d2 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -118,6 +118,7 @@ enum ocelot_target { S2, HSIO, PTP, + FDMA, GCB, DEV_GMII, TARGET_MAX, @@ -555,12 +556,26 @@ struct ocelot_ops { u16 (*wm_enc)(u16 value); u16 (*wm_dec)(u16 value); void (*wm_stat)(u32 val, u32 *inuse, u32 *maxuse); + void (*psfp_init)(struct ocelot *ocelot); + int (*psfp_filter_add)(struct ocelot *ocelot, int port, + struct flow_cls_offload *f); + int (*psfp_filter_del)(struct ocelot *ocelot, struct flow_cls_offload *f); + int (*psfp_stats_get)(struct ocelot *ocelot, struct flow_cls_offload *f, + struct flow_stats *stats); + void (*cut_through_fwd)(struct ocelot *ocelot); +}; + +struct ocelot_vcap_policer { + struct list_head pol_list; + u16 base; + u16 max; + u16 base2; + u16 max2; }; struct ocelot_vcap_block { struct list_head rules; int count; - int pol_lpr; }; struct ocelot_bridge_vlan { @@ -581,6 +596,12 @@ enum ocelot_port_tag_config { OCELOT_PORT_TAG_TRUNK = 3, }; +struct ocelot_psfp_list { + struct list_head stream_list; + struct list_head sfi_list; + struct list_head sgi_list; +}; + enum ocelot_sb { OCELOT_SB_BUF, OCELOT_SB_REF, @@ -593,6 +614,19 @@ enum ocelot_sb_pool { OCELOT_SB_POOL_NUM, }; +/* MAC table entry types. + * ENTRYTYPE_NORMAL is subject to aging. + * ENTRYTYPE_LOCKED is not subject to aging. + * ENTRYTYPE_MACv4 is not subject to aging. For IPv4 multicast. + * ENTRYTYPE_MACv6 is not subject to aging. For IPv6 multicast. + */ +enum macaccess_entry_type { + ENTRYTYPE_NORMAL = 0, + ENTRYTYPE_LOCKED, + ENTRYTYPE_MACv4, + ENTRYTYPE_MACv6, +}; + #define OCELOT_QUIRK_PCS_PERFORMS_RATE_ADAPTATION BIT(0) #define OCELOT_QUIRK_QSGMII_PORTS_MUST_BE_UP BIT(1) @@ -623,6 +657,8 @@ struct ocelot_port { struct net_device *bridge; u8 stp_state; + + int speed; }; struct ocelot { @@ -667,8 +703,11 @@ struct ocelot { struct list_head dummy_rules; struct ocelot_vcap_block block[3]; + struct ocelot_vcap_policer vcap_pol; struct vcap_props *vcap; + struct ocelot_psfp_list psfp; + /* Workqueue to check statistics for overflow with its lock */ struct mutex stats_lock; u64 *stats; @@ -677,6 +716,8 @@ struct ocelot { /* Lock for serializing access to the MAC table */ struct mutex mact_lock; + /* Lock for serializing forwarding domain changes */ + struct mutex fwd_domain_lock; struct workqueue_struct *owq; @@ -692,6 +733,8 @@ struct ocelot { /* Protects the PTP clock */ spinlock_t ptp_clock_lock; struct ptp_pin_desc ptp_pins[OCELOT_PTP_PINS_NUM]; + + struct ocelot_fdma *fdma; }; struct ocelot_policer { @@ -754,8 +797,11 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target, bool ocelot_can_inject(struct ocelot *ocelot, int grp); void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp, u32 rew_op, struct sk_buff *skb); +void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag); int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb); void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp); +void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb, + u64 timestamp); /* Hardware initialization */ int ocelot_regfields_init(struct ocelot *ocelot, @@ -776,7 +822,9 @@ void ocelot_set_ageing_time(struct ocelot *ocelot, unsigned int msecs); int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port, bool enabled, struct netlink_ext_ack *extack); void ocelot_bridge_stp_state_set(struct ocelot *ocelot, int port, u8 state); -void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot); +u32 ocelot_get_dsa_8021q_cpu_mask(struct ocelot *ocelot); +u32 ocelot_get_bridge_fwd_mask(struct ocelot *ocelot, int src_port); +void ocelot_apply_bridge_fwd_mask(struct ocelot *ocelot, bool joining); int ocelot_port_pre_bridge_flags(struct ocelot *ocelot, int port, struct switchdev_brport_flags val); void ocelot_port_bridge_flags(struct ocelot *ocelot, int port, @@ -785,6 +833,7 @@ void ocelot_port_bridge_join(struct ocelot *ocelot, int port, struct net_device *bridge); void ocelot_port_bridge_leave(struct ocelot *ocelot, int port, struct net_device *bridge); +int ocelot_mact_flush(struct ocelot *ocelot, int port); int ocelot_fdb_dump(struct ocelot *ocelot, int port, dsa_fdb_dump_cb_t *cb, void *data); int ocelot_fdb_add(struct ocelot *ocelot, int port, @@ -870,6 +919,19 @@ void ocelot_phylink_mac_link_up(struct ocelot *ocelot, int port, bool tx_pause, bool rx_pause, unsigned long quirks); +int ocelot_mact_lookup(struct ocelot *ocelot, int *dst_idx, + const unsigned char mac[ETH_ALEN], + unsigned int vid, enum macaccess_entry_type *type); +int ocelot_mact_learn_streamdata(struct ocelot *ocelot, int dst_idx, + const unsigned char mac[ETH_ALEN], + unsigned int vid, + enum macaccess_entry_type type, + int sfid, int ssid); + +int ocelot_vcap_policer_add(struct ocelot *ocelot, u32 pol_ix, + struct ocelot_policer *pol); +int ocelot_vcap_policer_del(struct ocelot *ocelot, u32 pol_ix); + #if IS_ENABLED(CONFIG_BRIDGE_MRP) int ocelot_mrp_add(struct ocelot *ocelot, int port, const struct switchdev_obj_mrp *mrp); diff --git a/include/soc/mscc/ocelot_ana.h b/include/soc/mscc/ocelot_ana.h index 1669481d9779..67e0ae05a5ab 100644 --- a/include/soc/mscc/ocelot_ana.h +++ b/include/soc/mscc/ocelot_ana.h @@ -227,6 +227,11 @@ #define ANA_TABLES_SFIDACCESS_SFID_TBL_CMD(x) ((x) & GENMASK(1, 0)) #define ANA_TABLES_SFIDACCESS_SFID_TBL_CMD_M GENMASK(1, 0) +#define SFIDACCESS_CMD_IDLE 0 +#define SFIDACCESS_CMD_READ 1 +#define SFIDACCESS_CMD_WRITE 2 +#define SFIDACCESS_CMD_INIT 3 + #define ANA_TABLES_SFIDTIDX_SGID_VALID BIT(26) #define ANA_TABLES_SFIDTIDX_SGID(x) (((x) << 18) & GENMASK(25, 18)) #define ANA_TABLES_SFIDTIDX_SGID_M GENMASK(25, 18) @@ -255,6 +260,11 @@ #define ANA_SG_CONFIG_REG_3_INIT_IPS(x) (((x) << 21) & GENMASK(24, 21)) #define ANA_SG_CONFIG_REG_3_INIT_IPS_M GENMASK(24, 21) #define ANA_SG_CONFIG_REG_3_INIT_IPS_X(x) (((x) & GENMASK(24, 21)) >> 21) +#define ANA_SG_CONFIG_REG_3_IPV_VALID BIT(24) +#define ANA_SG_CONFIG_REG_3_IPV_INVALID(x) (((x) << 24) & GENMASK(24, 24)) +#define ANA_SG_CONFIG_REG_3_INIT_IPV(x) (((x) << 21) & GENMASK(23, 21)) +#define ANA_SG_CONFIG_REG_3_INIT_IPV_M GENMASK(23, 21) +#define ANA_SG_CONFIG_REG_3_INIT_IPV_X(x) (((x) & GENMASK(23, 21)) >> 21) #define ANA_SG_CONFIG_REG_3_INIT_GATE_STATE BIT(25) #define ANA_SG_GCL_GS_CONFIG_RSZ 0x4 diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h index 4d1dfa1136b2..709cbc198fd2 100644 --- a/include/soc/mscc/ocelot_vcap.h +++ b/include/soc/mscc/ocelot_vcap.h @@ -656,6 +656,7 @@ enum ocelot_vcap_filter_type { OCELOT_VCAP_FILTER_DUMMY, OCELOT_VCAP_FILTER_PAG, OCELOT_VCAP_FILTER_OFFLOAD, + OCELOT_PSFP_FILTER_OFFLOAD, }; struct ocelot_vcap_id { diff --git a/include/soc/mscc/vsc7514_regs.h b/include/soc/mscc/vsc7514_regs.h new file mode 100644 index 000000000000..ceee26c96959 --- /dev/null +++ b/include/soc/mscc/vsc7514_regs.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Microsemi Ocelot Switch driver + * + * Copyright (c) 2021 Innovative Advantage Inc. + */ + +#ifndef VSC7514_REGS_H +#define VSC7514_REGS_H + +#include <soc/mscc/ocelot_vcap.h> + +extern const u32 vsc7514_ana_regmap[]; +extern const u32 vsc7514_qs_regmap[]; +extern const u32 vsc7514_qsys_regmap[]; +extern const u32 vsc7514_rew_regmap[]; +extern const u32 vsc7514_sys_regmap[]; +extern const u32 vsc7514_vcap_regmap[]; +extern const u32 vsc7514_ptp_regmap[]; +extern const u32 vsc7514_dev_gmii_regmap[]; + +extern const struct vcap_field vsc7514_vcap_es0_keys[]; +extern const struct vcap_field vsc7514_vcap_es0_actions[]; +extern const struct vcap_field vsc7514_vcap_is1_keys[]; +extern const struct vcap_field vsc7514_vcap_is1_actions[]; +extern const struct vcap_field vsc7514_vcap_is2_keys[]; +extern const struct vcap_field vsc7514_vcap_is2_actions[]; + +#endif diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h index 9e92f22eb086..3e042ca2cedb 100644 --- a/include/trace/events/skb.h +++ b/include/trace/events/skb.h @@ -9,29 +9,56 @@ #include <linux/netdevice.h> #include <linux/tracepoint.h> +#define TRACE_SKB_DROP_REASON \ + EM(SKB_DROP_REASON_NOT_SPECIFIED, NOT_SPECIFIED) \ + EM(SKB_DROP_REASON_NO_SOCKET, NO_SOCKET) \ + EM(SKB_DROP_REASON_PKT_TOO_SMALL, PKT_TOO_SMALL) \ + EM(SKB_DROP_REASON_TCP_CSUM, TCP_CSUM) \ + EM(SKB_DROP_REASON_TCP_FILTER, TCP_FILTER) \ + EM(SKB_DROP_REASON_UDP_CSUM, UDP_CSUM) \ + EMe(SKB_DROP_REASON_MAX, MAX) + +#undef EM +#undef EMe + +#define EM(a, b) TRACE_DEFINE_ENUM(a); +#define EMe(a, b) TRACE_DEFINE_ENUM(a); + +TRACE_SKB_DROP_REASON + +#undef EM +#undef EMe +#define EM(a, b) { a, #b }, +#define EMe(a, b) { a, #b } + /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, - TP_PROTO(struct sk_buff *skb, void *location), + TP_PROTO(struct sk_buff *skb, void *location, + enum skb_drop_reason reason), - TP_ARGS(skb, location), + TP_ARGS(skb, location, reason), TP_STRUCT__entry( - __field( void *, skbaddr ) - __field( void *, location ) - __field( unsigned short, protocol ) + __field(void *, skbaddr) + __field(void *, location) + __field(unsigned short, protocol) + __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->protocol = ntohs(skb->protocol); + __entry->reason = reason; ), - TP_printk("skbaddr=%p protocol=%u location=%p", - __entry->skbaddr, __entry->protocol, __entry->location) + TP_printk("skbaddr=%p protocol=%u location=%p reason: %s", + __entry->skbaddr, __entry->protocol, __entry->location, + __print_symbolic(__entry->reason, + TRACE_SKB_DROP_REASON)) ); TRACE_EVENT(consume_skb, diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba5af15e25f5..b0383d371b9a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1342,8 +1342,10 @@ union bpf_attr { /* or valid module BTF object fd or 0 to attach to vmlinux */ __u32 attach_btf_obj_fd; }; - __u32 :32; /* pad */ + __u32 core_relo_cnt; /* number of bpf_core_relo */ __aligned_u64 fd_array; /* array of FDs */ + __aligned_u64 core_relos; + __u32 core_relo_rec_size; /* sizeof(struct bpf_core_relo) */ }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -1744,7 +1746,7 @@ union bpf_attr { * if the maximum number of tail calls has been reached for this * chain of programs. This limit is defined in the kernel by the * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), - * which is currently set to 32. + * which is currently set to 33. * Return * 0 on success, or a negative error in case of failure. * @@ -4938,6 +4940,84 @@ union bpf_attr { * **-ENOENT** if symbol is not found. * * **-EPERM** if caller does not have permission to obtain kernel address. + * + * long bpf_find_vma(struct task_struct *task, u64 addr, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * Find vma of *task* that contains *addr*, call *callback_fn* + * function with *task*, *vma*, and *callback_ctx*. + * The *callback_fn* should be a static function and + * the *callback_ctx* should be a pointer to the stack. + * The *flags* is used to control certain aspects of the helper. + * Currently, the *flags* must be 0. + * + * The expected callback signature is + * + * long (\*callback_fn)(struct task_struct \*task, struct vm_area_struct \*vma, void \*callback_ctx); + * + * Return + * 0 on success. + * **-ENOENT** if *task->mm* is NULL, or no vma contains *addr*. + * **-EBUSY** if failed to try lock mmap_lock. + * **-EINVAL** for invalid **flags**. + * + * long bpf_loop(u32 nr_loops, void *callback_fn, void *callback_ctx, u64 flags) + * Description + * For **nr_loops**, call **callback_fn** function + * with **callback_ctx** as the context parameter. + * The **callback_fn** should be a static function and + * the **callback_ctx** should be a pointer to the stack. + * The **flags** is used to control certain aspects of the helper. + * Currently, the **flags** must be 0. Currently, nr_loops is + * limited to 1 << 23 (~8 million) loops. + * + * long (\*callback_fn)(u32 index, void \*ctx); + * + * where **index** is the current index in the loop. The index + * is zero-indexed. + * + * If **callback_fn** returns 0, the helper will continue to the next + * loop. If return value is 1, the helper will skip the rest of + * the loops and return. Other return values are not used now, + * and will be rejected by the verifier. + * + * Return + * The number of loops performed, **-EINVAL** for invalid **flags**, + * **-E2BIG** if **nr_loops** exceeds the maximum number of loops. + * + * long bpf_strncmp(const char *s1, u32 s1_sz, const char *s2) + * Description + * Do strncmp() between **s1** and **s2**. **s1** doesn't need + * to be null-terminated and **s1_sz** is the maximum storage + * size of **s1**. **s2** must be a read-only string. + * Return + * An integer less than, equal to, or greater than zero + * if the first **s1_sz** bytes of **s1** is found to be + * less than, to match, or be greater than **s2**. + * + * long bpf_get_func_arg(void *ctx, u32 n, u64 *value) + * Description + * Get **n**-th argument (zero based) of the traced function (for tracing programs) + * returned in **value**. + * + * Return + * 0 on success. + * **-EINVAL** if n >= arguments count of traced function. + * + * long bpf_get_func_ret(void *ctx, u64 *value) + * Description + * Get return value of the traced function (for tracing programs) + * in **value**. + * + * Return + * 0 on success. + * **-EOPNOTSUPP** for tracing programs other than BPF_TRACE_FEXIT or BPF_MODIFY_RETURN. + * + * long bpf_get_func_arg_cnt(void *ctx) + * Description + * Get number of arguments of the traced function (for tracing programs). + * + * Return + * The number of arguments of the traced function. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5120,6 +5200,12 @@ union bpf_attr { FN(trace_vprintk), \ FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ + FN(find_vma), \ + FN(loop), \ + FN(strncmp), \ + FN(get_func_arg), \ + FN(get_func_ret), \ + FN(get_func_arg_cnt), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6296,6 +6382,7 @@ struct bpf_sk_lookup { __u32 local_ip4; /* Network byte order */ __u32 local_ip6[4]; /* Network byte order */ __u32 local_port; /* Host byte order */ + __u32 ingress_ifindex; /* The arriving interface. Determined by inet_iif. */ }; /* @@ -6328,4 +6415,78 @@ enum { BTF_F_ZERO = (1ULL << 3), }; +/* bpf_core_relo_kind encodes which aspect of captured field/type/enum value + * has to be adjusted by relocations. It is emitted by llvm and passed to + * libbpf and later to the kernel. + */ +enum bpf_core_relo_kind { + BPF_CORE_FIELD_BYTE_OFFSET = 0, /* field byte offset */ + BPF_CORE_FIELD_BYTE_SIZE = 1, /* field size in bytes */ + BPF_CORE_FIELD_EXISTS = 2, /* field existence in target kernel */ + BPF_CORE_FIELD_SIGNED = 3, /* field signedness (0 - unsigned, 1 - signed) */ + BPF_CORE_FIELD_LSHIFT_U64 = 4, /* bitfield-specific left bitshift */ + BPF_CORE_FIELD_RSHIFT_U64 = 5, /* bitfield-specific right bitshift */ + BPF_CORE_TYPE_ID_LOCAL = 6, /* type ID in local BPF object */ + BPF_CORE_TYPE_ID_TARGET = 7, /* type ID in target kernel */ + BPF_CORE_TYPE_EXISTS = 8, /* type existence in target kernel */ + BPF_CORE_TYPE_SIZE = 9, /* type size in bytes */ + BPF_CORE_ENUMVAL_EXISTS = 10, /* enum value existence in target kernel */ + BPF_CORE_ENUMVAL_VALUE = 11, /* enum value integer value */ +}; + +/* + * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf + * and from libbpf to the kernel. + * + * CO-RE relocation captures the following data: + * - insn_off - instruction offset (in bytes) within a BPF program that needs + * its insn->imm field to be relocated with actual field info; + * - type_id - BTF type ID of the "root" (containing) entity of a relocatable + * type or field; + * - access_str_off - offset into corresponding .BTF string section. String + * interpretation depends on specific relocation kind: + * - for field-based relocations, string encodes an accessed field using + * a sequence of field and array indices, separated by colon (:). It's + * conceptually very close to LLVM's getelementptr ([0]) instruction's + * arguments for identifying offset to a field. + * - for type-based relocations, strings is expected to be just "0"; + * - for enum value-based relocations, string contains an index of enum + * value within its enum type; + * - kind - one of enum bpf_core_relo_kind; + * + * Example: + * struct sample { + * int a; + * struct { + * int b[10]; + * }; + * }; + * + * struct sample *s = ...; + * int *x = &s->a; // encoded as "0:0" (a is field #0) + * int *y = &s->b[5]; // encoded as "0:1:0:5" (anon struct is field #1, + * // b is field #0 inside anon struct, accessing elem #5) + * int *z = &s[10]->b; // encoded as "10:1" (ptr is used as an array) + * + * type_id for all relocs in this example will capture BTF type id of + * `struct sample`. + * + * Such relocation is emitted when using __builtin_preserve_access_index() + * Clang built-in, passing expression that captures field address, e.g.: + * + * bpf_probe_read(&dst, sizeof(dst), + * __builtin_preserve_access_index(&src->a.b.c)); + * + * In this case Clang will emit field relocation recording necessary data to + * be able to find offset of embedded `a.b.c` field within `src` struct. + * + * [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction + */ +struct bpf_core_relo { + __u32 insn_off; + __u32 type_id; + __u32 access_str_off; + enum bpf_core_relo_kind kind; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index deb12f755f0f..b0d8fea1951d 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and DECL_TAG. + * FUNC, FUNC_PROTO, VAR, DECL_TAG and TYPE_TAG. * "type" is a type_id referring to another type. */ union { @@ -75,6 +75,7 @@ enum { BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ BTF_KIND_DECL_TAG = 17, /* Decl Tag */ + BTF_KIND_TYPE_TAG = 18, /* Type Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 75b85c60efb2..02ec32d69474 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -137,6 +137,7 @@ enum { IFLA_CAN_DATA_BITRATE_CONST, IFLA_CAN_BITRATE_MAX, IFLA_CAN_TDC, + IFLA_CAN_CTRLMODE_EXT, /* add new constants above here */ __IFLA_CAN_MAX, @@ -166,6 +167,18 @@ enum { IFLA_CAN_TDC_MAX = __IFLA_CAN_TDC - 1 }; +/* + * IFLA_CAN_CTRLMODE_EXT nest: controller mode extended parameters + */ +enum { + IFLA_CAN_CTRLMODE_UNSPEC, + IFLA_CAN_CTRLMODE_SUPPORTED, /* u32 */ + + /* add new constants above here */ + __IFLA_CAN_CTRLMODE, + IFLA_CAN_CTRLMODE_MAX = __IFLA_CAN_CTRLMODE - 1 +}; + /* u16 termination range: 1..65535 Ohms */ #define CAN_TERMINATION_DISABLED 0 diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index a2223b685451..7bc4b8def12c 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -231,6 +231,7 @@ enum tunable_id { ETHTOOL_RX_COPYBREAK, ETHTOOL_TX_COPYBREAK, ETHTOOL_PFC_PREVENTION_TOUT, /* timeout in msecs */ + ETHTOOL_TX_COPYBREAK_BUF_SIZE, /* * Add your fresh new tunable attribute above and remember to update * tunable_strings[] in net/ethtool/common.c diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 999777d32dcf..cca6e474a085 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -329,6 +329,7 @@ enum { ETHTOOL_A_RINGS_RX_MINI, /* u32 */ ETHTOOL_A_RINGS_RX_JUMBO, /* u32 */ ETHTOOL_A_RINGS_TX, /* u32 */ + ETHTOOL_A_RINGS_RX_BUF_LEN, /* u32 */ /* add new constants above here */ __ETHTOOL_A_RINGS_CNT, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index eebd3894fe89..6218f93f5c1a 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -347,6 +347,7 @@ enum { */ IFLA_PARENT_DEV_NAME, IFLA_PARENT_DEV_BUS_NAME, + IFLA_GRO_MAX_SIZE, __IFLA_MAX }; @@ -858,6 +859,7 @@ enum { IFLA_BOND_TLB_DYNAMIC_LB, IFLA_BOND_PEER_NOTIF_DELAY, IFLA_BOND_AD_LACP_ACTIVE, + IFLA_BOND_MISSED_MAX, __IFLA_BOND_MAX, }; diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index fcc61c73a666..55501e5e7ac8 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -62,7 +62,7 @@ struct so_timestamping { /** * struct hwtstamp_config - %SIOCGHWTSTAMP and %SIOCSHWTSTAMP parameter * - * @flags: no flags defined right now, must be zero for %SIOCSHWTSTAMP + * @flags: one of HWTSTAMP_FLAG_* * @tx_type: one of HWTSTAMP_TX_* * @rx_filter: one of HWTSTAMP_FILTER_* * @@ -78,6 +78,21 @@ struct hwtstamp_config { int rx_filter; }; +/* possible values for hwtstamp_config->flags */ +enum hwtstamp_flags { + /* + * With this flag, the user could get bond active interface's + * PHC index. Note this PHC index is not stable as when there + * is a failover, the bond active interface will be changed, so + * will be the PHC index. + */ + HWTSTAMP_FLAG_BONDED_PHC_INDEX = (1<<0), +#define HWTSTAMP_FLAG_BONDED_PHC_INDEX HWTSTAMP_FLAG_BONDED_PHC_INDEX + + HWTSTAMP_FLAG_LAST = HWTSTAMP_FLAG_BONDED_PHC_INDEX, + HWTSTAMP_FLAG_MASK = (HWTSTAMP_FLAG_LAST - 1) | HWTSTAMP_FLAG_LAST +}; + /* possible values for hwtstamp_config->tx_type */ enum hwtstamp_tx_types { /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 61cab81e920d..195a238a322e 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -1232,6 +1232,11 @@ * &NL80211_ATTR_FILS_NONCES - for FILS Nonces * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) * + * @NL80211_CMD_ASSOC_COMEBACK: notification about an association + * temporal rejection with comeback. The event includes %NL80211_ATTR_MAC + * to describe the BSSID address of the AP and %NL80211_ATTR_TIMEOUT to + * specify the timeout value. + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1474,6 +1479,8 @@ enum nl80211_commands { NL80211_CMD_SET_FILS_AAD, + NL80211_CMD_ASSOC_COMEBACK, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -2470,7 +2477,9 @@ enum nl80211_commands { * space supports external authentication. This attribute shall be used * with %NL80211_CMD_CONNECT and %NL80211_CMD_START_AP request. The driver * may offload authentication processing to user space if this capability - * is indicated in the respective requests from the user space. + * is indicated in the respective requests from the user space. (This flag + * attribute deprecated for %NL80211_CMD_START_AP, use + * %NL80211_ATTR_AP_SETTINGS_FLAGS) * * @NL80211_ATTR_NSS: Station's New/updated RX_NSS value notified using this * u8 attribute. This is used with %NL80211_CMD_STA_OPMODE_CHANGED. @@ -2639,6 +2648,17 @@ enum nl80211_commands { * Mandatory parameter for the transmitting interface to enable MBSSID. * Optional for the non-transmitting interfaces. * + * @NL80211_ATTR_RADAR_BACKGROUND: Configure dedicated offchannel chain + * available for radar/CAC detection on some hw. This chain can't be used + * to transmit or receive frames and it is bounded to a running wdev. + * Background radar/CAC detection allows to avoid the CAC downtime + * switching on a different channel during CAC detection on the selected + * radar channel. + * + * @NL80211_ATTR_AP_SETTINGS_FLAGS: u32 attribute contains ap settings flags, + * enumerated in &enum nl80211_ap_settings_flags. This attribute shall be + * used with %NL80211_CMD_START_AP request. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3145,6 +3165,10 @@ enum nl80211_attrs { NL80211_ATTR_MBSSID_CONFIG, NL80211_ATTR_MBSSID_ELEMS, + NL80211_ATTR_RADAR_BACKGROUND, + + NL80211_ATTR_AP_SETTINGS_FLAGS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -3738,13 +3762,12 @@ enum nl80211_mpath_info { * capabilities IE * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE: HE PPE thresholds information as * defined in HE capabilities IE - * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently - * defined * @NL80211_BAND_IFTYPE_ATTR_HE_6GHZ_CAPA: HE 6GHz band capabilities (__le16), * given for all 6 GHz band channels * @NL80211_BAND_IFTYPE_ATTR_VENDOR_ELEMS: vendor element capabilities that are * advertised on this band/for this iftype (binary) * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use + * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band attribute currently defined */ enum nl80211_band_iftype_attr { __NL80211_BAND_IFTYPE_ATTR_INVALID, @@ -5555,7 +5578,7 @@ enum nl80211_iface_limit_attrs { * => allows 8 of AP/GO that can have BI gcd >= min gcd * * numbers = [ #{STA} <= 2 ], channels = 2, max = 2 - * => allows two STAs on different channels + * => allows two STAs on the same or on different channels * * numbers = [ #{STA} <= 1, #{P2P-client,P2P-GO} <= 3 ], max = 4 * => allows a STA plus three P2P interfaces @@ -5600,7 +5623,7 @@ enum nl80211_if_combination_attrs { * @NL80211_PLINK_ESTAB: mesh peer link is established * @NL80211_PLINK_HOLDING: mesh peer link is being closed or cancelled * @NL80211_PLINK_BLOCKED: all frames transmitted from this mesh - * plink are discarded + * plink are discarded, except for authentication frames * @NUM_NL80211_PLINK_STATES: number of peer link states * @MAX_NL80211_PLINK_STATES: highest numerical value of plink states */ @@ -5737,13 +5760,15 @@ enum nl80211_tdls_operation { NL80211_TDLS_DISABLE_LINK, }; -/* +/** * enum nl80211_ap_sme_features - device-integrated AP features - * Reserved for future use, no bits are defined in - * NL80211_ATTR_DEVICE_AP_SME yet. + * @NL80211_AP_SME_SA_QUERY_OFFLOAD: SA Query procedures offloaded to driver + * when user space indicates support for SA Query procedures offload during + * "start ap" with %NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT. + */ enum nl80211_ap_sme_features { + NL80211_AP_SME_SA_QUERY_OFFLOAD = 1 << 0, }; - */ /** * enum nl80211_feature_flags - device/driver features @@ -6051,6 +6076,9 @@ enum nl80211_feature_flags { * frames. Userspace has to share FILS AAD details to the driver by using * @NL80211_CMD_SET_FILS_AAD. * + * @NL80211_EXT_FEATURE_RADAR_BACKGROUND: Device supports background radar/CAC + * detection. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6117,6 +6145,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_PROT_RANGE_NEGO_AND_MEASURE, NL80211_EXT_FEATURE_BSS_COLOR, NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, + NL80211_EXT_FEATURE_RADAR_BACKGROUND, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, @@ -7462,4 +7491,20 @@ enum nl80211_mbssid_config_attributes { NL80211_MBSSID_CONFIG_ATTR_MAX = __NL80211_MBSSID_CONFIG_ATTR_LAST - 1, }; +/** + * enum nl80211_ap_settings_flags - AP settings flags + * + * @NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT: AP supports external + * authentication. + * @NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT: Userspace supports SA Query + * procedures offload to driver. If driver advertises + * %NL80211_AP_SME_SA_QUERY_OFFLOAD in AP SME features, userspace shall + * ignore SA Query procedures and validations when this flag is set by + * userspace. + */ +enum nl80211_ap_settings_flags { + NL80211_AP_SETTINGS_EXTERNAL_AUTH_SUPPORT = 1 << 0, + NL80211_AP_SETTINGS_SA_QUERY_OFFLOAD_SUPPORT = 1 << 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/include/uapi/linux/pfkeyv2.h b/include/uapi/linux/pfkeyv2.h index d65b11785260..8abae1f6749c 100644 --- a/include/uapi/linux/pfkeyv2.h +++ b/include/uapi/linux/pfkeyv2.h @@ -309,6 +309,7 @@ struct sadb_x_filter { #define SADB_X_AALG_SHA2_512HMAC 7 #define SADB_X_AALG_RIPEMD160HMAC 8 #define SADB_X_AALG_AES_XCBC_MAC 9 +#define SADB_X_AALG_SM3_256HMAC 10 #define SADB_X_AALG_NULL 251 /* kame */ #define SADB_AALG_MAX 251 @@ -329,6 +330,7 @@ struct sadb_x_filter { #define SADB_X_EALG_AES_GCM_ICV16 20 #define SADB_X_EALG_CAMELLIACBC 22 #define SADB_X_EALG_NULL_AES_GMAC 23 +#define SADB_X_EALG_SM4CBC 24 #define SADB_EALG_MAX 253 /* last EALG */ /* private allocations should use 249-255 (RFC2407) */ #define SADB_X_EALG_SERPENTCBC 252 /* draft-ietf-ipsec-ciph-aes-cbc-00 */ diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h index 6836ccb9c45d..ee38b35c3f57 100644 --- a/include/uapi/linux/pkt_cls.h +++ b/include/uapi/linux/pkt_cls.h @@ -19,13 +19,16 @@ enum { TCA_ACT_FLAGS, TCA_ACT_HW_STATS, TCA_ACT_USED_HW_STATS, + TCA_ACT_IN_HW_COUNT, __TCA_ACT_MAX }; /* See other TCA_ACT_FLAGS_ * flags in include/net/act_api.h. */ -#define TCA_ACT_FLAGS_NO_PERCPU_STATS 1 /* Don't use percpu allocator for - * actions stats. - */ +#define TCA_ACT_FLAGS_NO_PERCPU_STATS (1 << 0) /* Don't use percpu allocator for + * actions stats. + */ +#define TCA_ACT_FLAGS_SKIP_HW (1 << 1) /* don't offload action to HW */ +#define TCA_ACT_FLAGS_SKIP_SW (1 << 2) /* don't use action in SW */ /* tca HW stats type * When user does not pass the attribute, he does not care. diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 5888492a5257..93d934cc4613 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -754,6 +754,8 @@ enum rtnetlink_groups { #define RTNLGRP_NEXTHOP RTNLGRP_NEXTHOP RTNLGRP_BRVLAN, #define RTNLGRP_BRVLAN RTNLGRP_BRVLAN + RTNLGRP_MCTP_IFADDR, +#define RTNLGRP_MCTP_IFADDR RTNLGRP_MCTP_IFADDR __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 20f33b27787f..6c2874fd2c00 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -119,6 +119,8 @@ enum { SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ SMC_NLA_LGR_R_V2_COMMON, /* nest */ SMC_NLA_LGR_R_V2, /* nest */ + SMC_NLA_LGR_R_NET_COOKIE, /* u64 */ + SMC_NLA_LGR_R_PAD, /* flag */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h index 8cb3a6fef553..c7008d87f1a4 100644 --- a/include/uapi/linux/smc_diag.h +++ b/include/uapi/linux/smc_diag.h @@ -84,11 +84,12 @@ struct smc_diag_conninfo { /* SMC_DIAG_LINKINFO */ struct smc_diag_linkinfo { - __u8 link_id; /* link identifier */ - __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ - __u8 ibport; /* RDMA device port number */ - __u8 gid[40]; /* local GID */ - __u8 peer_gid[40]; /* peer GID */ + __u8 link_id; /* link identifier */ + __u8 ibname[IB_DEVICE_NAME_MAX]; /* name of the RDMA device */ + __u8 ibport; /* RDMA device port number */ + __u8 gid[40]; /* local GID */ + __u8 peer_gid[40]; /* peer GID */ + __aligned_u64 net_cookie; /* RDMA device net namespace */ }; struct smc_diag_lgrinfo { diff --git a/include/uapi/linux/tty.h b/include/uapi/linux/tty.h index 376cccf397be..a58deb3061eb 100644 --- a/include/uapi/linux/tty.h +++ b/include/uapi/linux/tty.h @@ -38,5 +38,6 @@ #define N_NCI 25 /* NFC NCI UART */ #define N_SPEAKUP 26 /* Speakup communication with synths */ #define N_NULL 27 /* Null ldisc used for error handling */ +#define N_MCTP 28 /* MCTP-over-serial */ #endif /* _UAPI_LINUX_TTY_H */ diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index eda0426ec4c2..4e29d7851890 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -313,6 +313,7 @@ enum xfrm_attr_type_t { XFRMA_SET_MARK, /* __u32 */ XFRMA_SET_MARK_MASK, /* __u32 */ XFRMA_IF_ID, /* __u32 */ + XFRMA_MTIMER_THRESH, /* __u32 in seconds for input SA */ __XFRMA_MAX #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK /* Compatibility */ diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h index ca2372864b70..e539c84d63f1 100644 --- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h +++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h @@ -252,7 +252,7 @@ enum mlx5_ib_device_query_context_attrs { MLX5_IB_ATTR_QUERY_CONTEXT_RESP_UCTX = (1U << UVERBS_ID_NS_SHIFT), }; -#define MLX5_IB_DW_MATCH_PARAM 0x90 +#define MLX5_IB_DW_MATCH_PARAM 0xA0 struct mlx5_ib_match_params { __u32 match_params[MLX5_IB_DW_MATCH_PARAM]; |