diff options
| author | Johannes Berg <johannes.berg@intel.com> | 2025-03-18 09:45:23 +0100 |
|---|---|---|
| committer | Johannes Berg <johannes.berg@intel.com> | 2025-03-18 09:46:36 +0100 |
| commit | c924c5e9b8c65b3a479a90e5e37d74cc8cd9fe0a (patch) | |
| tree | 9626c13418dd3770f2772980a7dacdc110c442b6 /include | |
| parent | 54be64fdf3ba6dbad2f5c48e466e1db43ad74bca (diff) | |
| parent | 50698b298b3995d253bd0b85ff7f60cae6f51e6a (diff) | |
| download | lwn-c924c5e9b8c65b3a479a90e5e37d74cc8cd9fe0a.tar.gz lwn-c924c5e9b8c65b3a479a90e5e37d74cc8cd9fe0a.zip | |
Merge net-next/main to resolve conflicts
There are a few conflicts between the work that went
into wireless and that's here now, resolve them.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Diffstat (limited to 'include')
40 files changed, 613 insertions, 441 deletions
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index f42133dae68e..2afc95bf1655 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -90,7 +90,7 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, #ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, - unsigned long addr, pte_t *ptep) + unsigned long addr, pte_t *ptep, unsigned long sz) { return ptep_get_and_clear(mm, addr, ptep); } diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 02a4adb4a999..0d5b186abee8 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -457,7 +457,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) . = ALIGN((align)); \ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \ __start_rodata = .; \ - *(.rodata) *(.rodata.*) \ + *(.rodata) *(.rodata.*) *(.data.rel.ro*) \ SCHED_DATA \ RO_AFTER_INIT_DATA /* Read only after init */ \ . = ALIGN(8); \ diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index fa2a76cc2f73..71f4f0cc3dac 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -28,7 +28,7 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t); typedef __u32 __bitwise req_flags_t; /* Keep rqf_name[] in sync with the definitions below */ -enum { +enum rqf_flags { /* drive already may have started this one */ __RQF_STARTED, /* request for flush sequence */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 248416ecd01c..d37751789bf5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -196,10 +196,11 @@ struct gendisk { unsigned int zone_capacity; unsigned int last_zone_capacity; unsigned long __rcu *conv_zones_bitmap; - unsigned int zone_wplugs_hash_bits; - spinlock_t zone_wplugs_lock; + unsigned int zone_wplugs_hash_bits; + atomic_t nr_zone_wplugs; + spinlock_t zone_wplugs_lock; struct mempool_s *zone_wplugs_pool; - struct hlist_head *zone_wplugs_hash; + struct hlist_head *zone_wplugs_hash; struct workqueue_struct *zone_wplugs_wq; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -367,6 +368,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_user_sectors; unsigned int max_segment_size; + unsigned int min_segment_size; unsigned int physical_block_size; unsigned int logical_block_size; unsigned int alignment_offset; diff --git a/include/linux/call_once.h b/include/linux/call_once.h index 6261aa0b3fb0..13cd6469e7e5 100644 --- a/include/linux/call_once.h +++ b/include/linux/call_once.h @@ -26,20 +26,41 @@ do { \ __once_init((once), #once, &__key); \ } while (0) -static inline void call_once(struct once *once, void (*cb)(struct once *)) +/* + * call_once - Ensure a function has been called exactly once + * + * @once: Tracking struct + * @cb: Function to be called + * + * If @once has never completed successfully before, call @cb and, if + * it returns a zero or positive value, mark @once as completed. Return + * the value returned by @cb + * + * If @once has completed succesfully before, return 0. + * + * The call to @cb is implicitly surrounded by a mutex, though for + * efficiency the * function avoids taking it after the first call. + */ +static inline int call_once(struct once *once, int (*cb)(struct once *)) { - /* Pairs with atomic_set_release() below. */ - if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) - return; - - guard(mutex)(&once->lock); - WARN_ON(atomic_read(&once->state) == ONCE_RUNNING); - if (atomic_read(&once->state) != ONCE_NOT_STARTED) - return; - - atomic_set(&once->state, ONCE_RUNNING); - cb(once); - atomic_set_release(&once->state, ONCE_COMPLETED); + int r, state; + + /* Pairs with atomic_set_release() below. */ + if (atomic_read_acquire(&once->state) == ONCE_COMPLETED) + return 0; + + guard(mutex)(&once->lock); + state = atomic_read(&once->state); + if (unlikely(state != ONCE_NOT_STARTED)) + return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0; + + atomic_set(&once->state, ONCE_RUNNING); + r = cb(once); + if (r < 0) + atomic_set(&once->state, ONCE_NOT_STARTED); + else + atomic_set_release(&once->state, ONCE_COMPLETED); + return r; } #endif /* _LINUX_CALL_ONCE_H */ diff --git a/include/linux/compaction.h b/include/linux/compaction.h index e94776496049..7bf0c521db63 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order) return 2UL << order; } +static inline int current_is_kcompactd(void) +{ + return current->flags & PF_KCOMPACTD; +} + #ifdef CONFIG_COMPACTION extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order); diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 200fd3c5bc70..155385754824 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -110,7 +110,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Unreachable code */ #ifdef CONFIG_OBJTOOL /* Annotate a C jump table to allow objtool to follow the code flow */ -#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #") +#define __annotate_jump_table __section(".data.rel.ro.c_jump_table") #else /* !CONFIG_OBJTOOL */ #define __annotate_jump_table #endif /* CONFIG_OBJTOOL */ diff --git a/include/linux/cred.h b/include/linux/cred.h index 0c3c4b16b469..5658a3bfe803 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -172,18 +172,12 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred) static inline const struct cred *override_creds(const struct cred *override_cred) { - const struct cred *old = current->cred; - - rcu_assign_pointer(current->cred, override_cred); - return old; + return rcu_replace_pointer(current->cred, override_cred, 1); } static inline const struct cred *revert_creds(const struct cred *revert_cred) { - const struct cred *override_cred = current->cred; - - rcu_assign_pointer(current->cred, revert_cred); - return override_cred; + return rcu_replace_pointer(current->cred, revert_cred, 1); } /** diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 7f222dccc7d1..8210ece94fa6 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -210,6 +210,14 @@ static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx) void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id); +struct link_mode_info { + int speed; + u8 lanes; + u8 duplex; +}; + +extern const struct link_mode_info link_mode_params[]; + /* declare a link mode bitmap */ #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index ec8c0ccc8f95..76a75ec03dd6 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -682,6 +682,7 @@ struct huge_bootmem_page { int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); +void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, @@ -1004,7 +1005,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm) static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); + unsigned long psize = huge_page_size(hstate_vma(vma)); + + return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize); } #endif @@ -1066,6 +1069,10 @@ static inline int replace_free_hugepage_folios(unsigned long start_pfn, return 0; } +static inline void wait_for_freed_hugetlb_folios(void) +{ +} + static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index a6e2aadbb91b..5aeeed22f35b 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -207,6 +207,7 @@ struct inet6_cork { struct ipv6_txoptions *opt; u8 hop_limit; u8 tclass; + u8 dontfrag:1; }; /* struct ipv6_pinfo - ipv6 private area */ diff --git a/include/linux/log2.h b/include/linux/log2.h index 9f30d087a128..1366cb688a6d 100644 --- a/include/linux/log2.h +++ b/include/linux/log2.h @@ -41,7 +41,7 @@ int __ilog2_u64(u64 n) * *not* considered a power of two. * Return: true if @n is a power of 2, otherwise false. */ -static inline __attribute__((const)) +static __always_inline __attribute__((const)) bool is_power_of_2(unsigned long n) { return (n != 0 && ((n & (n - 1)) == 0)); diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index fd37f4e54d76..904804e995aa 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -1251,6 +1251,7 @@ enum mlx5_cap_type { MLX5_CAP_GENERAL_2 = 0x20, MLX5_CAP_PORT_SELECTION = 0x25, MLX5_CAP_ADV_VIRTUALIZATION = 0x26, + MLX5_CAP_ADV_RDMA = 0x28, /* NUM OF CAP Types */ MLX5_CAP_NUM }; @@ -1345,6 +1346,12 @@ enum mlx5_qcam_feature_groups { #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \ MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap) +#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) \ + MLX5_CAP_ADV_RDMA(mdev, rdma_transport_rx_flow_table_properties.cap) + +#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) \ + MLX5_CAP_ADV_RDMA(mdev, rdma_transport_tx_flow_table_properties.cap) + #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \ MLX5_GET(flow_table_eswitch_cap, \ mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap) @@ -1384,6 +1391,10 @@ enum mlx5_qcam_feature_groups { MLX5_GET(adv_virtualization_cap, \ mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap) +#define MLX5_CAP_ADV_RDMA(mdev, cap) \ + MLX5_GET(adv_rdma_cap, \ + mdev->caps.hca[MLX5_CAP_ADV_RDMA]->cur, cap) + #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \ MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap) @@ -1506,6 +1517,7 @@ enum { MLX5_PHYSICAL_LAYER_COUNTERS_GROUP = 0x12, MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16, + MLX5_PHYSICAL_LAYER_RECOVERY_GROUP = 0x1a, MLX5_INFINIBAND_PORT_COUNTERS_GROUP = 0x20, MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21, }; diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 46bd7550adf8..d1dfbad9a447 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -304,6 +304,8 @@ struct mlx5_cmd { struct semaphore sem; struct semaphore pages_sem; struct semaphore throttle_sem; + struct semaphore unprivileged_sem; + struct xarray privileged_uids; } vars; enum mlx5_cmdif_state state; void *cmd_alloc_buf; @@ -964,6 +966,8 @@ struct mlx5_async_work { mlx5_async_cbk_t user_callback; u16 opcode; /* cmd opcode */ u16 op_mod; /* cmd op_mod */ + u8 throttle_locked:1; + u8 unpriv_locked:1; void *out; /* pointer to the cmd output buffer */ }; @@ -994,6 +998,8 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size); bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); +int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid); +void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid); void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev); void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev); diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 01cb72d68c23..939e58c2f386 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -40,6 +40,7 @@ #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) +#define MLX5_RDMA_TRANSPORT_BYPASS_PRIO 0 #define MLX5_FS_MAX_POOL_SIZE BIT(30) enum mlx5_flow_destination_type { @@ -110,6 +111,8 @@ enum mlx5_flow_namespace_type { MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC, MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC, MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC, + MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX, + MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX, }; enum { @@ -194,9 +197,9 @@ struct mlx5_flow_namespace * mlx5_get_flow_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type type); struct mlx5_flow_namespace * -mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev, - enum mlx5_flow_namespace_type type, - int vport); +mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev, + enum mlx5_flow_namespace_type type, + int vport_idx); struct mlx5_flow_table_attr { int prio; @@ -204,6 +207,7 @@ struct mlx5_flow_table_attr { u32 level; u32 flags; u16 uid; + u16 vport; struct mlx5_flow_table *next_ft; struct { @@ -240,6 +244,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg); struct mlx5_exe_aso { u32 object_id; + int base_id; u8 type; u8 return_reg_id; union { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index cc2875e843f7..2c09df4ee574 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1570,6 +1570,8 @@ enum { enum { MLX5_UCTX_CAP_RAW_TX = 1UL << 0, MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1, + MLX5_UCTX_CAP_RDMA_CTRL = 1UL << 3, + MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA = 1UL << 4, }; #define MLX5_FC_BULK_SIZE_FACTOR 128 @@ -1991,7 +1993,9 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 max_geneve_tlv_options[0x8]; u8 reserved_at_568[0x3]; u8 max_geneve_tlv_option_data_len[0x5]; - u8 reserved_at_570[0x9]; + u8 reserved_at_570[0x1]; + u8 adv_rdma[0x1]; + u8 reserved_at_572[0x7]; u8 adv_virtualization[0x1]; u8 reserved_at_57a[0x6]; @@ -2140,7 +2144,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 log_min_mkey_entity_size[0x5]; u8 reserved_at_1b0[0x10]; - u8 reserved_at_1c0[0x60]; + u8 general_obj_types_127_64[0x40]; + u8 reserved_at_200[0x20]; u8 reserved_at_220[0x1]; u8 sw_vhca_id_valid[0x1]; @@ -2640,6 +2645,12 @@ struct mlx5_ifc_field_select_802_1qau_rp_bits { u8 field_select_8021qaurp[0x20]; }; +struct mlx5_ifc_phys_layer_recovery_cntrs_bits { + u8 total_successful_recovery_events[0x20]; + + u8 reserved_at_20[0x7a0]; +}; + struct mlx5_ifc_phys_layer_cntrs_bits { u8 time_since_last_clear_high[0x20]; @@ -4841,6 +4852,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits { struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_port_cntrs_grp_data_layout; struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs; struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs; + struct mlx5_ifc_phys_layer_recovery_cntrs_bits phys_layer_recovery_cntrs; u8 reserved_at_0[0x7c0]; }; @@ -10579,7 +10591,9 @@ struct mlx5_ifc_mtutc_reg_bits { }; struct mlx5_ifc_pcam_enhanced_features_bits { - u8 reserved_at_0[0x1d]; + u8 reserved_at_0[0x10]; + u8 ppcnt_recovery_counters[0x1]; + u8 reserved_at_11[0xc]; u8 fec_200G_per_lane_in_pplm[0x1]; u8 reserved_at_1e[0x2a]; u8 fec_100G_per_lane_in_pplm[0x1]; @@ -12495,12 +12509,17 @@ enum { }; enum { + MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL = BIT_ULL(0x13), +}; + +enum { MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc, MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13, MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20, MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24, MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27, MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47, + MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL = 0x53, MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15, }; @@ -13068,6 +13087,44 @@ struct mlx5_ifc_load_vhca_state_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_adv_rdma_cap_bits { + u8 rdma_transport_manager[0x1]; + u8 rdma_transport_manager_other_eswitch[0x1]; + u8 reserved_at_2[0x1e]; + + u8 rcx_type[0x8]; + u8 reserved_at_28[0x2]; + u8 ps_entry_log_max_value[0x6]; + u8 reserved_at_30[0x6]; + u8 qp_max_ps_num_entry[0xa]; + + u8 mp_max_num_queues[0x8]; + u8 ps_user_context_max_log_size[0x8]; + u8 message_based_qp_and_striding_wq[0x8]; + u8 reserved_at_58[0x8]; + + u8 max_receive_send_message_size_stride[0x10]; + u8 reserved_at_70[0x10]; + + u8 max_receive_send_message_size_byte[0x20]; + + u8 reserved_at_a0[0x160]; + + struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_rx_flow_table_properties; + + struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_tx_flow_table_properties; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_support_2; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_support_2; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_bitmask_support_2; + + struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_bitmask_support_2; + + u8 reserved_at_800[0x3800]; +}; + struct mlx5_ifc_adv_virtualization_cap_bits { u8 reserved_at_0[0x3]; u8 pg_track_log_max_num[0x5]; diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h index fd625e0dd869..58770b86f793 100644 --- a/include/linux/mlx5/port.h +++ b/include/linux/mlx5/port.h @@ -61,15 +61,6 @@ enum mlx5_an_status { #define MLX5_EEPROM_PAGE_LENGTH 256 #define MLX5_EEPROM_HIGH_PAGE_LENGTH 128 -struct mlx5_module_eeprom_query_params { - u16 size; - u16 offset; - u16 i2c_address; - u32 page; - u32 bank; - u32 module_number; -}; - enum mlx5e_link_mode { MLX5E_1000BASE_CX_SGMII = 0, MLX5E_1000BASE_KX = 1, @@ -145,12 +136,6 @@ enum mlx5_ptys_width { MLX5_PTYS_WIDTH_12X = 1 << 4, }; -struct mlx5_port_eth_proto { - u32 cap; - u32 admin; - u32 oper; -}; - #define MLX5E_PROT_MASK(link_mode) (1U << link_mode) #define MLX5_GET_ETH_PROTO(reg, out, ext, field) \ (ext ? MLX5_GET(reg, out, ext_##field) : \ @@ -163,14 +148,7 @@ int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys, int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper, u16 *proto_oper, u8 local_port, u8 plane_index); -void mlx5_toggle_port_link(struct mlx5_core_dev *dev); -int mlx5_set_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status status); -int mlx5_query_port_admin_status(struct mlx5_core_dev *dev, - enum mlx5_port_status *status); -int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration); - -int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port); + void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port); void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, u8 port); @@ -178,65 +156,4 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu, int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev, u8 *vl_hw_cap, u8 local_port); -int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause); -int mlx5_query_port_pause(struct mlx5_core_dev *dev, - u32 *rx_pause, u32 *tx_pause); - -int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx); -int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, - u8 *pfc_en_rx); - -int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev, - u16 stall_critical_watermark, - u16 stall_minor_watermark); -int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev, - u16 *stall_critical_watermark, u16 *stall_minor_watermark); - -int mlx5_max_tc(struct mlx5_core_dev *mdev); - -int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc); -int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev, - u8 prio, u8 *tc); -int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group); -int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev, - u8 tc, u8 *tc_group); -int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw); -int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev, - u8 tc, u8 *bw_pct); -int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev, - u8 *max_bw_value, - u8 *max_bw_unit); -int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev, - u8 *max_bw_value, - u8 *max_bw_unit); -int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode); -int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode); - -int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen); -int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen); -int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable); -void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported, - bool *enabled); -int mlx5_query_module_eeprom(struct mlx5_core_dev *dev, - u16 offset, u16 size, u8 *data); -int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev, - struct mlx5_module_eeprom_query_params *params, u8 *data); - -int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out); -int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in); - -int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state); -int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state); -int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio); -int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio); - -int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext, - struct mlx5_port_eth_proto *eproto); -bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev); -u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper, - bool force_legacy); -u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed, - bool force_legacy); -int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed); - #endif /* __MLX5_PORT_H__ */ diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 11be70a7929f..7a01c518e573 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -53,12 +53,12 @@ enum { NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */ NETIF_F_GSO_FRAGLIST_BIT, /* ... Fraglist GSO */ + NETIF_F_GSO_ACCECN_BIT, /* TCP AccECN w/ TSO (no clear CWR) */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_FRAGLIST_BIT, + NETIF_F_GSO_ACCECN_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ - __UNUSED_NETIF_F_37, NETIF_F_NTUPLE_BIT, /* N-tuple filters supported */ NETIF_F_RXHASH_BIT, /* Receive hashing offload */ NETIF_F_RXCSUM_BIT, /* Receive checksumming offload */ @@ -128,6 +128,7 @@ enum { #define NETIF_F_SG __NETIF_F(SG) #define NETIF_F_TSO6 __NETIF_F(TSO6) #define NETIF_F_TSO_ECN __NETIF_F(TSO_ECN) +#define NETIF_F_GSO_ACCECN __NETIF_F(GSO_ACCECN) #define NETIF_F_TSO __NETIF_F(TSO) #define NETIF_F_VLAN_CHALLENGED __NETIF_F(VLAN_CHALLENGED) #define NETIF_F_RXFCS __NETIF_F(RXFCS) @@ -210,7 +211,8 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start) NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID) /* List of features with software fallbacks. */ -#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP | \ +#define NETIF_F_GSO_SOFTWARE (NETIF_F_ALL_TSO | \ + NETIF_F_GSO_ACCECN | NETIF_F_GSO_SCTP | \ NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST) /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7ab86ec228b7..67527243459b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2486,19 +2486,29 @@ struct net_device { bool up; /** + * @request_ops_lock: request the core to run all @netdev_ops and + * @ethtool_ops under the @lock. + */ + bool request_ops_lock; + + /** * @lock: netdev-scope lock, protects a small selection of fields. * Should always be taken using netdev_lock() / netdev_unlock() helpers. * Drivers are free to use it for other protection. * * Protects: * @gro_flush_timeout, @napi_defer_hard_irqs, @napi_list, - * @net_shaper_hierarchy, @reg_state, @threaded + * @net_shaper_hierarchy, @reg_state, @threaded, @dev_addr * * Partially protects (writers must hold both @lock and rtnl_lock): * @up * * Also protects some fields in struct napi_struct. * + * For the drivers that implement shaper or queue API, the scope + * of this lock is expanded to cover most ndo/queue/ethtool/sysfs + * operations. + * * Ordering: take after rtnl_lock. */ struct mutex lock; @@ -2620,21 +2630,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, f(dev, &dev->_tx[i], arg); } -#define netdev_lockdep_set_classes(dev) \ -{ \ - static struct lock_class_key qdisc_tx_busylock_key; \ - static struct lock_class_key qdisc_xmit_lock_key; \ - static struct lock_class_key dev_addr_list_lock_key; \ - unsigned int i; \ - \ - (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ - lockdep_set_class(&(dev)->addr_list_lock, \ - &dev_addr_list_lock_key); \ - for (i = 0; i < (dev)->num_tx_queues; i++) \ - lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ - &qdisc_xmit_lock_key); \ -} - u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, @@ -2740,18 +2735,7 @@ static inline void netdev_unlock(struct net_device *dev) { mutex_unlock(&dev->lock); } - -static inline void netdev_assert_locked(struct net_device *dev) -{ - lockdep_assert_held(&dev->lock); -} - -static inline void netdev_assert_locked_or_invisible(struct net_device *dev) -{ - if (dev->reg_state == NETREG_REGISTERED || - dev->reg_state == NETREG_UNREGISTERING) - netdev_assert_locked(dev); -} +/* Additional netdev_lock()-related helpers are in net/netdev_lock.h */ void netif_napi_set_irq_locked(struct napi_struct *napi, int irq); @@ -3327,9 +3311,12 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); +int netif_open(struct net_device *dev, struct netlink_ext_ack *extack); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); +void netif_close(struct net_device *dev); void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); +void netif_disable_lro(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, @@ -4177,6 +4164,8 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); +int dev_eth_ioctl(struct net_device *dev, + struct ifreq *ifr, unsigned int cmd); int generic_hwtstamp_get_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg); int generic_hwtstamp_set_lower(struct net_device *dev, @@ -4186,27 +4175,27 @@ int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); +int netif_change_flags(struct net_device *dev, unsigned int flags, + struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); +int netif_set_alias(struct net_device *dev, const char *alias, size_t len); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); -int __dev_change_net_namespace(struct net_device *dev, struct net *net, +int netif_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex, struct netlink_ext_ack *extack); -static inline int dev_change_net_namespace(struct net_device *dev, struct net *net, - const char *pat) -{ - return __dev_change_net_namespace(dev, net, pat, 0, NULL); -} + const char *pat); int __dev_set_mtu(struct net_device *, int); +int netif_set_mtu(struct net_device *dev, int new_mtu); int dev_set_mtu(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); +int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa, + struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); -int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, - struct netlink_ext_ack *extack); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); @@ -4218,6 +4207,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); +int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf); u8 dev_xdp_sb_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); @@ -4960,6 +4950,7 @@ static inline void __dev_mc_unsync(struct net_device *dev, /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); +int netif_set_allmulti(struct net_device *dev, int inc, bool notify); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); void __netdev_notify_peers(struct net_device *dev); @@ -5278,6 +5269,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_TCP_ACCECN != + (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h index f91e50a76efd..f6e8abe0b1f1 100644 --- a/include/linux/netpoll.h +++ b/include/linux/netpoll.h @@ -33,6 +33,7 @@ struct netpoll { u16 local_port, remote_port; u8 remote_mac[ETH_ALEN]; struct sk_buff_head skb_pool; + struct work_struct refill_wq; }; struct netpoll_info { diff --git a/include/linux/phy.h b/include/linux/phy.h index 7bfbae51070a..c24e1a565819 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -320,41 +320,6 @@ struct mdio_bus_stats { }; /** - * struct phy_package_shared - Shared information in PHY packages - * @base_addr: Base PHY address of PHY package used to combine PHYs - * in one package and for offset calculation of phy_package_read/write - * @np: Pointer to the Device Node if PHY package defined in DT - * @refcnt: Number of PHYs connected to this shared data - * @flags: Initialization of PHY package - * @priv_size: Size of the shared private data @priv - * @priv: Driver private data shared across a PHY package - * - * Represents a shared structure between different phydev's in the same - * package, for example a quad PHY. See phy_package_join() and - * phy_package_leave(). - */ -struct phy_package_shared { - u8 base_addr; - /* With PHY package defined in DT this points to the PHY package node */ - struct device_node *np; - refcount_t refcnt; - unsigned long flags; - size_t priv_size; - - /* private data pointer */ - /* note that this pointer is shared between different phydevs and - * the user has to take care of appropriate locking. It is allocated - * and freed automatically by phy_package_join() and - * phy_package_leave(). - */ - void *priv; -}; - -/* used as bit number in atomic bitops */ -#define PHY_SHARED_F_INIT_DONE 0 -#define PHY_SHARED_F_PROBE_DONE 1 - -/** * struct mii_bus - Represents an MDIO bus * * @owner: Who owns this device @@ -1310,21 +1275,6 @@ const char *phy_rate_matching_to_str(int rate_matching); int phy_interface_num_ports(phy_interface_t interface); -/* A structure for mapping a particular speed and duplex - * combination to a particular SUPPORTED and ADVERTISED value - */ -struct phy_setting { - u32 speed; - u8 duplex; - u8 bit; -}; - -const struct phy_setting * -phy_lookup_setting(int speed, int duplex, const unsigned long *mask, - bool exact); -size_t phy_speeds(unsigned int *speeds, size_t size, - unsigned long *mask); - /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct @@ -2113,13 +2063,6 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev, int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); -int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size); -int of_phy_package_join(struct phy_device *phydev, size_t priv_size); -void phy_package_leave(struct phy_device *phydev); -int devm_phy_package_join(struct device *dev, struct phy_device *phydev, - int base_addr, size_t priv_size); -int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev, - size_t priv_size); int __init mdio_bus_init(void); void mdio_bus_exit(void); @@ -2149,104 +2092,6 @@ int __phy_hwtstamp_set(struct phy_device *phydev, struct kernel_hwtstamp_config *config, struct netlink_ext_ack *extack); -static inline int phy_package_address(struct phy_device *phydev, - unsigned int addr_offset) -{ - struct phy_package_shared *shared = phydev->shared; - u8 base_addr = shared->base_addr; - - if (addr_offset >= PHY_MAX_ADDR - base_addr) - return -EIO; - - /* we know that addr will be in the range 0..31 and thus the - * implicit cast to a signed int is not a problem. - */ - return base_addr + addr_offset; -} - -static inline int phy_package_read(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return mdiobus_read(phydev->mdio.bus, addr, regnum); -} - -static inline int __phy_package_read(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return __mdiobus_read(phydev->mdio.bus, addr, regnum); -} - -static inline int phy_package_write(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum, - u16 val) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return mdiobus_write(phydev->mdio.bus, addr, regnum, val); -} - -static inline int __phy_package_write(struct phy_device *phydev, - unsigned int addr_offset, u32 regnum, - u16 val) -{ - int addr = phy_package_address(phydev, addr_offset); - - if (addr < 0) - return addr; - - return __mdiobus_write(phydev->mdio.bus, addr, regnum, val); -} - -int __phy_package_read_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum); - -int phy_package_read_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum); - -int __phy_package_write_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum, u16 val); - -int phy_package_write_mmd(struct phy_device *phydev, - unsigned int addr_offset, int devad, - u32 regnum, u16 val); - -static inline bool __phy_package_set_once(struct phy_device *phydev, - unsigned int b) -{ - struct phy_package_shared *shared = phydev->shared; - - if (!shared) - return false; - - return !test_and_set_bit(b, &shared->flags); -} - -static inline bool phy_package_init_once(struct phy_device *phydev) -{ - return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE); -} - -static inline bool phy_package_probe_once(struct phy_device *phydev) -{ - return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE); -} - extern const struct bus_type mdio_bus_type; struct mdio_board_info { diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 08df65f6867a..79876c84ae81 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -595,6 +595,14 @@ void pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode, * The %neg_mode argument should be tested via the phylink_mode_*() family of * functions, or for PCS that set pcs->neg_mode true, should be tested * against the PHYLINK_PCS_NEG_* definitions. + * + * pcs_config() will be called when configuration of the PCS is required + * or when the advertisement is possibly updated. It must not unnecessarily + * disrupt an established link. + * + * When an autonegotiation restart is required for 802.3z modes, .pcs_config() + * should return a positive non-zero integer (e.g. 1) to indicate to phylink + * to call the pcs_an_restart() method. */ int pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, const unsigned long *advertising, @@ -714,7 +722,6 @@ void phylink_ethtool_get_pauseparam(struct phylink *, int phylink_ethtool_set_pauseparam(struct phylink *, struct ethtool_pauseparam *); int phylink_get_eee_err(struct phylink *); -int phylink_init_eee(struct phylink *, bool); int phylink_ethtool_get_eee(struct phylink *link, struct ethtool_keee *eee); int phylink_ethtool_set_eee(struct phylink *link, struct ethtool_keee *eee); int phylink_mii_ioctl(struct phylink *, struct ifreq *, int); diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 8ff23bf5a819..b698758000f8 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -31,6 +31,33 @@ struct pipe_buffer { unsigned long private; }; +/* + * Really only alpha needs 32-bit fields, but + * might as well do it for 64-bit architectures + * since that's what we've historically done, + * and it makes 'head_tail' always be a simple + * 'unsigned long'. + */ +#ifdef CONFIG_64BIT +typedef unsigned int pipe_index_t; +#else +typedef unsigned short pipe_index_t; +#endif + +/* + * We have to declare this outside 'struct pipe_inode_info', + * but then we can't use 'union pipe_index' for an anonymous + * union, so we end up having to duplicate this declaration + * below. Annoying. + */ +union pipe_index { + unsigned long head_tail; + struct { + pipe_index_t head; + pipe_index_t tail; + }; +}; + /** * struct pipe_inode_info - a linux kernel pipe * @mutex: mutex protecting the whole thing @@ -38,6 +65,7 @@ struct pipe_buffer { * @wr_wait: writer wait point in case of full pipe * @head: The point of buffer production * @tail: The point of buffer consumption + * @head_tail: unsigned long union of @head and @tail * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) @@ -58,8 +86,16 @@ struct pipe_buffer { struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; - unsigned int head; - unsigned int tail; + + /* This has to match the 'union pipe_index' above */ + union { + unsigned long head_tail; + struct { + pipe_index_t head; + pipe_index_t tail; + }; + }; + unsigned int max_usage; unsigned int ring_size; unsigned int nr_accounted; @@ -141,23 +177,23 @@ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe) } /** - * pipe_empty - Return true if the pipe is empty + * pipe_occupancy - Return number of slots used in the pipe * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ -static inline bool pipe_empty(unsigned int head, unsigned int tail) +static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) { - return head == tail; + return (pipe_index_t)(head - tail); } /** - * pipe_occupancy - Return number of slots used in the pipe + * pipe_empty - Return true if the pipe is empty * @head: The pipe ring head pointer * @tail: The pipe ring tail pointer */ -static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail) +static inline bool pipe_empty(unsigned int head, unsigned int tail) { - return head - tail; + return !pipe_occupancy(head, tail); } /** @@ -173,6 +209,33 @@ static inline bool pipe_full(unsigned int head, unsigned int tail, } /** + * pipe_is_full - Return true if the pipe is full + * @pipe: the pipe + */ +static inline bool pipe_is_full(const struct pipe_inode_info *pipe) +{ + return pipe_full(pipe->head, pipe->tail, pipe->max_usage); +} + +/** + * pipe_is_empty - Return true if the pipe is empty + * @pipe: the pipe + */ +static inline bool pipe_is_empty(const struct pipe_inode_info *pipe) +{ + return pipe_empty(pipe->head, pipe->tail); +} + +/** + * pipe_buf_usage - Return how many pipe buffers are in use + * @pipe: the pipe + */ +static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe) +{ + return pipe_occupancy(pipe->head, pipe->tail); +} + +/** * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring * @pipe: The pipe to access * @slot: The slot of interest @@ -245,15 +308,6 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe, return buf->ops->try_steal(pipe, buf); } -static inline void pipe_discard_from(struct pipe_inode_info *pipe, - unsigned int old_head) -{ - unsigned int mask = pipe->ring_size - 1; - - while (pipe->head > old_head) - pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]); -} - /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual memory allocation, whereas PIPE_BUF makes atomicity guarantees. */ #define PIPE_SIZE PAGE_SIZE diff --git a/include/linux/platform_data/x86/intel_pmc_ipc.h b/include/linux/platform_data/x86/intel_pmc_ipc.h new file mode 100644 index 000000000000..6e603a8c075f --- /dev/null +++ b/include/linux/platform_data/x86/intel_pmc_ipc.h @@ -0,0 +1,94 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Intel Core SoC Power Management Controller Header File + * + * Copyright (c) 2025, Intel Corporation. + * All Rights Reserved. + * + */ +#ifndef INTEL_PMC_IPC_H +#define INTEL_PMC_IPC_H +#include <linux/acpi.h> + +#define IPC_SOC_REGISTER_ACCESS 0xAA +#define IPC_SOC_SUB_CMD_READ 0x00 +#define IPC_SOC_SUB_CMD_WRITE 0x01 +#define PMC_IPCS_PARAM_COUNT 7 +#define VALID_IPC_RESPONSE 5 + +struct pmc_ipc_cmd { + u32 cmd; + u32 sub_cmd; + u32 size; + u32 wbuf[4]; +}; + +struct pmc_ipc_rbuf { + u32 buf[4]; +}; + +/** + * intel_pmc_ipc() - PMC IPC Mailbox accessor + * @ipc_cmd: Prepared input command to send + * @rbuf: Allocated array for returned IPC data + * + * Return: 0 on success. Non-zero on mailbox error + */ +static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf *rbuf) +{ + struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; + union acpi_object params[PMC_IPCS_PARAM_COUNT] = { + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + {.type = ACPI_TYPE_INTEGER,}, + }; + struct acpi_object_list arg_list = { PMC_IPCS_PARAM_COUNT, params }; + union acpi_object *obj; + int status; + + if (!ipc_cmd || !rbuf) + return -EINVAL; + + /* + * 0: IPC Command + * 1: IPC Sub Command + * 2: Size + * 3-6: Write Buffer for offset + */ + params[0].integer.value = ipc_cmd->cmd; + params[1].integer.value = ipc_cmd->sub_cmd; + params[2].integer.value = ipc_cmd->size; + params[3].integer.value = ipc_cmd->wbuf[0]; + params[4].integer.value = ipc_cmd->wbuf[1]; + params[5].integer.value = ipc_cmd->wbuf[2]; + params[6].integer.value = ipc_cmd->wbuf[3]; + + status = acpi_evaluate_object(NULL, "\\IPCS", &arg_list, &buffer); + if (ACPI_FAILURE(status)) + return -ENODEV; + + obj = buffer.pointer; + + if (obj && obj->type == ACPI_TYPE_PACKAGE && + obj->package.count == VALID_IPC_RESPONSE) { + const union acpi_object *objs = obj->package.elements; + + if ((u8)objs[0].integer.value != 0) + return -EINVAL; + + rbuf->buf[0] = objs[1].integer.value; + rbuf->buf[1] = objs[2].integer.value; + rbuf->buf[2] = objs[3].integer.value; + rbuf->buf[3] = objs[4].integer.value; + } else { + return -EINVAL; + } + + return 0; +} + +#endif /* INTEL_PMC_IPC_H */ diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h index 8ab5b0e8eb2c..8c9df7dadd5d 100644 --- a/include/linux/platform_profile.h +++ b/include/linux/platform_profile.h @@ -33,6 +33,8 @@ enum platform_profile_option { * @probe: Callback to setup choices available to the new class device. These * choices will only be enforced when setting a new profile, not when * getting the current one. + * @hidden_choices: Callback to setup choices that are not visible to the user + * but can be set by the driver. * @profile_get: Callback that will be called when showing the current platform * profile in sysfs. * @profile_set: Callback that will be called when storing a new platform @@ -40,6 +42,7 @@ enum platform_profile_option { */ struct platform_profile_ops { int (*probe)(void *drvdata, unsigned long *choices); + int (*hidden_choices)(void *drvdata, unsigned long *choices); int (*profile_get)(struct device *dev, enum platform_profile_option *profile); int (*profile_set)(struct device *dev, enum platform_profile_option profile); }; diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index ef8619f48920..a500d3160fe8 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -95,10 +95,13 @@ struct posix_clock { * struct posix_clock_context - represents clock file operations context * * @clk: Pointer to the clock + * @fp: Pointer to the file used to open the clock * @private_clkdata: Pointer to user data * * Drivers should use struct posix_clock_context during specific character - * device file operation methods to access the posix clock. + * device file operation methods to access the posix clock. In particular, + * the file pointer can be used to verify correct access mode for ioctl() + * calls. * * Drivers can store a private data structure during the open operation * if they have specific information that is required in other file @@ -106,6 +109,7 @@ struct posix_clock { */ struct posix_clock_context { struct posix_clock *clk; + struct file *fp; void *private_clkdata; }; diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h index 45e6e427ceb8..f73fbea0dbc2 100644 --- a/include/linux/ppp_channel.h +++ b/include/linux/ppp_channel.h @@ -42,8 +42,7 @@ struct ppp_channel { int hdrlen; /* amount of headroom channel needs */ void *ppp; /* opaque to channel */ int speed; /* transfer rate (bytes/second) */ - /* the following is not used at present */ - int latency; /* overhead time in milliseconds */ + bool direct_xmit; /* no qdisc, xmit directly */ }; #ifdef __KERNEL__ diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h index 2c8bfd0f1b6b..6322d8c1c6b4 100644 --- a/include/linux/rcuref.h +++ b/include/linux/rcuref.h @@ -71,27 +71,30 @@ static inline __must_check bool rcuref_get(rcuref_t *ref) return rcuref_get_slowpath(ref); } -extern __must_check bool rcuref_put_slowpath(rcuref_t *ref); +extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt); /* * Internal helper. Do not invoke directly. */ static __always_inline __must_check bool __rcuref_put(rcuref_t *ref) { + int cnt; + RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(), "suspicious rcuref_put_rcusafe() usage"); /* * Unconditionally decrease the reference count. The saturation and * dead zones provide enough tolerance for this. */ - if (likely(!atomic_add_negative_release(-1, &ref->refcnt))) + cnt = atomic_sub_return_release(1, &ref->refcnt); + if (likely(cnt >= 0)) return false; /* * Handle the last reference drop and cases inside the saturation * and dead zones. */ - return rcuref_put_slowpath(ref); + return rcuref_put_slowpath(ref, cnt); } /** diff --git a/include/linux/sched.h b/include/linux/sched.h index 9632e3318e0d..9c15365a30c0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1701,7 +1701,7 @@ extern struct pid *cad_pid; #define PF_USED_MATH 0x00002000 /* If unset the fpu must be initialized before use */ #define PF_USER_WORKER 0x00004000 /* Kernel thread cloned from userspace thread */ #define PF_NOFREEZE 0x00008000 /* This thread should not be frozen */ -#define PF__HOLE__00010000 0x00010000 +#define PF_KCOMPACTD 0x00010000 /* I am kcompactd */ #define PF_KSWAPD 0x00020000 /* I am kswapd */ #define PF_MEMALLOC_NOFS 0x00040000 /* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */ #define PF_MEMALLOC_NOIO 0x00080000 /* All allocations inherit GFP_NOIO. See memalloc_noio_save() */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 14517e95a46c..b8a1343d6785 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -708,6 +708,8 @@ enum { SKB_GSO_UDP_L4 = 1 << 17, SKB_GSO_FRAGLIST = 1 << 18, + + SKB_GSO_TCP_ACCECN = 1 << 19, }; #if BITS_PER_LONG > 32 diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index cd0d1383df87..b6f03ab12595 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -239,6 +239,10 @@ struct plat_stmmacenet_data { int (*serdes_powerup)(struct net_device *ndev, void *priv); void (*serdes_powerdown)(struct net_device *ndev, void *priv); void (*speed_mode_2500)(struct net_device *ndev, void *priv); + int (*mac_finish)(struct net_device *ndev, + void *priv, + unsigned int mode, + phy_interface_t interface); void (*ptp_clk_freq_config)(struct stmmac_priv *priv); int (*init)(struct platform_device *pdev, void *priv); void (*exit)(struct platform_device *pdev, void *priv); diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index f756fac95488..6281063cbd8e 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -804,6 +804,7 @@ struct hci_conn_params { extern struct list_head hci_dev_list; extern struct list_head hci_cb_list; extern rwlock_t hci_dev_list_lock; +extern struct mutex hci_cb_list_lock; #define hci_dev_set_flag(hdev, nr) set_bit((nr), (hdev)->dev_flags) #define hci_dev_clear_flag(hdev, nr) clear_bit((nr), (hdev)->dev_flags) @@ -2010,47 +2011,24 @@ struct hci_cb { char *name; - bool (*match) (struct hci_conn *conn); void (*connect_cfm) (struct hci_conn *conn, __u8 status); void (*disconn_cfm) (struct hci_conn *conn, __u8 status); void (*security_cfm) (struct hci_conn *conn, __u8 status, - __u8 encrypt); + __u8 encrypt); void (*key_change_cfm) (struct hci_conn *conn, __u8 status); void (*role_switch_cfm) (struct hci_conn *conn, __u8 status, __u8 role); }; -static inline void hci_cb_lookup(struct hci_conn *conn, struct list_head *list) -{ - struct hci_cb *cb, *cpy; - - rcu_read_lock(); - list_for_each_entry_rcu(cb, &hci_cb_list, list) { - if (cb->match && cb->match(conn)) { - cpy = kmalloc(sizeof(*cpy), GFP_ATOMIC); - if (!cpy) - break; - - *cpy = *cb; - INIT_LIST_HEAD(&cpy->list); - list_add_rcu(&cpy->list, list); - } - } - rcu_read_unlock(); -} - static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) { - struct list_head list; - struct hci_cb *cb, *tmp; - - INIT_LIST_HEAD(&list); - hci_cb_lookup(conn, &list); + struct hci_cb *cb; - list_for_each_entry_safe(cb, tmp, &list, list) { + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { if (cb->connect_cfm) cb->connect_cfm(conn, status); - kfree(cb); } + mutex_unlock(&hci_cb_list_lock); if (conn->connect_cfm_cb) conn->connect_cfm_cb(conn, status); @@ -2058,43 +2036,22 @@ static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status) static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason) { - struct list_head list; - struct hci_cb *cb, *tmp; - - INIT_LIST_HEAD(&list); - hci_cb_lookup(conn, &list); + struct hci_cb *cb; - list_for_each_entry_safe(cb, tmp, &list, list) { + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { if (cb->disconn_cfm) cb->disconn_cfm(conn, reason); - kfree(cb); } + mutex_unlock(&hci_cb_list_lock); if (conn->disconn_cfm_cb) conn->disconn_cfm_cb(conn, reason); } -static inline void hci_security_cfm(struct hci_conn *conn, __u8 status, - __u8 encrypt) -{ - struct list_head list; - struct hci_cb *cb, *tmp; - - INIT_LIST_HEAD(&list); - hci_cb_lookup(conn, &list); - - list_for_each_entry_safe(cb, tmp, &list, list) { - if (cb->security_cfm) - cb->security_cfm(conn, status, encrypt); - kfree(cb); - } - - if (conn->security_cfm_cb) - conn->security_cfm_cb(conn, status); -} - static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) { + struct hci_cb *cb; __u8 encrypt; if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags)) @@ -2102,11 +2059,20 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status) encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00; - hci_security_cfm(conn, status, encrypt); + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { + if (cb->security_cfm) + cb->security_cfm(conn, status, encrypt); + } + mutex_unlock(&hci_cb_list_lock); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) { + struct hci_cb *cb; __u8 encrypt; if (conn->state == BT_CONFIG) { @@ -2133,38 +2099,40 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status) conn->sec_level = conn->pending_sec_level; } - hci_security_cfm(conn, status, encrypt); + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { + if (cb->security_cfm) + cb->security_cfm(conn, status, encrypt); + } + mutex_unlock(&hci_cb_list_lock); + + if (conn->security_cfm_cb) + conn->security_cfm_cb(conn, status); } static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status) { - struct list_head list; - struct hci_cb *cb, *tmp; - - INIT_LIST_HEAD(&list); - hci_cb_lookup(conn, &list); + struct hci_cb *cb; - list_for_each_entry_safe(cb, tmp, &list, list) { + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { if (cb->key_change_cfm) cb->key_change_cfm(conn, status); - kfree(cb); } + mutex_unlock(&hci_cb_list_lock); } static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status, __u8 role) { - struct list_head list; - struct hci_cb *cb, *tmp; - - INIT_LIST_HEAD(&list); - hci_cb_lookup(conn, &list); + struct hci_cb *cb; - list_for_each_entry_safe(cb, tmp, &list, list) { + mutex_lock(&hci_cb_list_lock); + list_for_each_entry(cb, &hci_cb_list, list) { if (cb->role_switch_cfm) cb->role_switch_cfm(conn, status, role); - kfree(cb); } + mutex_unlock(&hci_cb_list_lock); } static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type) diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h index da818fb0205f..949641e92539 100644 --- a/include/net/inet_hashtables.h +++ b/include/net/inet_hashtables.h @@ -89,6 +89,7 @@ struct inet_bind_bucket { bool fast_ipv6_only; struct hlist_node node; struct hlist_head bhash2; + struct rcu_head rcu; }; struct inet_bind2_bucket { @@ -226,8 +227,7 @@ struct inet_bind_bucket * inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net, struct inet_bind_hashbucket *head, const unsigned short snum, int l3mdev); -void inet_bind_bucket_destroy(struct kmem_cache *cachep, - struct inet_bind_bucket *tb); +void inet_bind_bucket_destroy(struct inet_bind_bucket *tb); bool inet_bind_bucket_match(const struct inet_bind_bucket *tb, const struct net *net, unsigned short port, @@ -527,9 +527,12 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr) int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk, u64 port_offset, + u32 hash_port0, int (*check_established)(struct inet_timewait_death_row *, struct sock *, __u16, - struct inet_timewait_sock **)); + struct inet_timewait_sock **, + bool rcu_lookup, + u32 hash)); int inet_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); diff --git a/include/net/ip.h b/include/net/ip.h index ce5e59957dd5..8a48ade24620 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -357,7 +357,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high); #ifdef CONFIG_SYSCTL -static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port) +static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port) { if (!net->ipv4.sysctl_local_reserved_ports) return false; diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h index 53bd2d02a4f0..39cd50300a18 100644 --- a/include/net/lwtunnel.h +++ b/include/net/lwtunnel.h @@ -116,9 +116,11 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op, int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, unsigned int num); int lwtunnel_valid_encap_type(u16 encap_type, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, + bool rtnl_is_held); int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, - struct netlink_ext_ack *extack); + struct netlink_ext_ack *extack, + bool rtnl_is_held); int lwtunnel_build_state(struct net *net, u16 encap_type, struct nlattr *encap, unsigned int family, const void *cfg, @@ -201,13 +203,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op, } static inline int lwtunnel_valid_encap_type(u16 encap_type, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + bool rtnl_is_held) { NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel"); return -EOPNOTSUPP; } static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len, - struct netlink_ext_ack *extack) + struct netlink_ext_ack *extack, + bool rtnl_is_held) { /* return 0 since we are not walking attr looking for * RTA_ENCAP_TYPE attribute on nexthops. diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h new file mode 100644 index 000000000000..99631fbd7f54 --- /dev/null +++ b/include/net/netdev_lock.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef _NET_NETDEV_LOCK_H +#define _NET_NETDEV_LOCK_H + +#include <linux/lockdep.h> +#include <linux/netdevice.h> + +static inline bool netdev_trylock(struct net_device *dev) +{ + return mutex_trylock(&dev->lock); +} + +static inline void netdev_assert_locked(struct net_device *dev) +{ + lockdep_assert_held(&dev->lock); +} + +static inline void netdev_assert_locked_or_invisible(struct net_device *dev) +{ + if (dev->reg_state == NETREG_REGISTERED || + dev->reg_state == NETREG_UNREGISTERING) + netdev_assert_locked(dev); +} + +static inline bool netdev_need_ops_lock(struct net_device *dev) +{ + bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops; + +#if IS_ENABLED(CONFIG_NET_SHAPER) + ret |= !!dev->netdev_ops->net_shaper_ops; +#endif + + return ret; +} + +static inline void netdev_lock_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_lock(dev); +} + +static inline void netdev_unlock_ops(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + netdev_unlock(dev); +} + +static inline void netdev_ops_assert_locked(struct net_device *dev) +{ + if (netdev_need_ops_lock(dev)) + lockdep_assert_held(&dev->lock); +} + +static inline int netdev_lock_cmp_fn(const struct lockdep_map *a, + const struct lockdep_map *b) +{ + /* Only lower devices currently grab the instance lock, so no + * real ordering issues can occur. In the near future, only + * hardware devices will grab instance lock which also does not + * involve any ordering. Suppress lockdep ordering warnings + * until (if) we start grabbing instance lock on pure SW + * devices (bond/team/veth/etc). + */ + if (a == b) + return 0; + return -1; +} + +#define netdev_lockdep_set_classes(dev) \ +{ \ + static struct lock_class_key qdisc_tx_busylock_key; \ + static struct lock_class_key qdisc_xmit_lock_key; \ + static struct lock_class_key dev_addr_list_lock_key; \ + static struct lock_class_key dev_instance_lock_key; \ + unsigned int i; \ + \ + (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ + lockdep_set_class(&(dev)->addr_list_lock, \ + &dev_addr_list_lock_key); \ + lockdep_set_class(&(dev)->lock, \ + &dev_instance_lock_key); \ + lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL); \ + for (i = 0; i < (dev)->num_tx_queues; i++) \ + lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ + &qdisc_xmit_lock_key); \ +} + +#endif diff --git a/include/net/netdev_netlink.h b/include/net/netdev_netlink.h new file mode 100644 index 000000000000..075962dbe743 --- /dev/null +++ b/include/net/netdev_netlink.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __NET_NETDEV_NETLINK_H +#define __NET_NETDEV_NETLINK_H + +#include <linux/list.h> + +struct netdev_nl_sock { + struct mutex lock; + struct list_head bindings; +}; + +#endif /* __NET_NETDEV_NETLINK_H */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 60d5dcdb289c..803d5f1601f9 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -1891,7 +1891,7 @@ void nft_chain_filter_fini(void); void __init nft_chain_route_init(void); void nft_chain_route_fini(void); -void nf_tables_trans_destroy_flush_work(void); +void nf_tables_trans_destroy_flush_work(struct net *net); int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result); __be64 nf_jiffies64_to_msecs(u64 input); @@ -1905,6 +1905,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re struct nftables_pernet { struct list_head tables; struct list_head commit_list; + struct list_head destroy_list; struct list_head commit_set_list; struct list_head binding_list; struct list_head module_list; @@ -1915,6 +1916,7 @@ struct nftables_pernet { unsigned int base_seq; unsigned int gc_seq; u8 validate_state; + struct work_struct destroy_work; }; extern unsigned int nf_tables_net_id; diff --git a/include/net/tcp.h b/include/net/tcp.h index a9bc959fb102..d08fbf90495d 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -26,6 +26,7 @@ #include <linux/kref.h> #include <linux/ktime.h> #include <linux/indirect_call_wrapper.h> +#include <linux/bits.h> #include <net/inet_connection_sock.h> #include <net/inet_timewait_sock.h> @@ -373,16 +374,53 @@ static inline void tcp_dec_quickack_mode(struct sock *sk) } } -#define TCP_ECN_OK 1 -#define TCP_ECN_QUEUE_CWR 2 -#define TCP_ECN_DEMAND_CWR 4 -#define TCP_ECN_SEEN 8 +#define TCP_ECN_MODE_RFC3168 BIT(0) +#define TCP_ECN_QUEUE_CWR BIT(1) +#define TCP_ECN_DEMAND_CWR BIT(2) +#define TCP_ECN_SEEN BIT(3) +#define TCP_ECN_MODE_ACCECN BIT(4) + +#define TCP_ECN_DISABLED 0 +#define TCP_ECN_MODE_PENDING (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) +#define TCP_ECN_MODE_ANY (TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN) + +static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp) +{ + return tp->ecn_flags & TCP_ECN_MODE_ANY; +} + +static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168; +} + +static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN; +} + +static inline bool tcp_ecn_disabled(const struct tcp_sock *tp) +{ + return !tcp_ecn_mode_any(tp); +} + +static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp) +{ + return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING; +} + +static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode) +{ + tp->ecn_flags &= ~TCP_ECN_MODE_ANY; + tp->ecn_flags |= mode; +} enum tcp_tw_status { TCP_TW_SUCCESS = 0, TCP_TW_RST = 1, TCP_TW_ACK = 2, - TCP_TW_SYN = 3 + TCP_TW_SYN = 3, + TCP_TW_ACK_OOW = 4 }; @@ -669,7 +707,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority, enum sk_rst_reason reason); int tcp_send_synack(struct sock *); void tcp_push_one(struct sock *, unsigned int mss_now); -void __tcp_send_ack(struct sock *sk, u32 rcv_nxt); +void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags); void tcp_send_ack(struct sock *sk); void tcp_send_delayed_ack(struct sock *sk); void tcp_send_loss_probe(struct sock *sk); @@ -934,15 +972,22 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq) #define tcp_flag_byte(th) (((u_int8_t *)th)[13]) -#define TCPHDR_FIN 0x01 -#define TCPHDR_SYN 0x02 -#define TCPHDR_RST 0x04 -#define TCPHDR_PSH 0x08 -#define TCPHDR_ACK 0x10 -#define TCPHDR_URG 0x20 -#define TCPHDR_ECE 0x40 -#define TCPHDR_CWR 0x80 - +#define TCPHDR_FIN BIT(0) +#define TCPHDR_SYN BIT(1) +#define TCPHDR_RST BIT(2) +#define TCPHDR_PSH BIT(3) +#define TCPHDR_ACK BIT(4) +#define TCPHDR_URG BIT(5) +#define TCPHDR_ECE BIT(6) +#define TCPHDR_CWR BIT(7) +#define TCPHDR_AE BIT(8) +#define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \ + TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \ + TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) +#define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \ + TCPHDR_FLAGS_MASK) + +#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE) #define TCPHDR_SYN_ECN (TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR) /* State flags for sacked in struct tcp_skb_cb */ @@ -977,7 +1022,7 @@ struct tcp_skb_cb { u16 tcp_gso_size; }; }; - __u8 tcp_flags; /* TCP header flags. (tcp[13]) */ + __u16 tcp_flags; /* TCP header flags (tcp[12-13])*/ __u8 sacked; /* State flags for SACK. */ __u8 ip_dsfield; /* IPv4 tos or IPv6 dsfield */ @@ -1132,9 +1177,9 @@ enum tcp_ca_ack_event_flags { #define TCP_CA_UNSPEC 0 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */ -#define TCP_CONG_NON_RESTRICTED 0x1 +#define TCP_CONG_NON_RESTRICTED BIT(0) /* Requires ECN/ECT set on all packets */ -#define TCP_CONG_NEEDS_ECN 0x2 +#define TCP_CONG_NEEDS_ECN BIT(1) #define TCP_CONG_MASK (TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN) union tcp_cc_info; @@ -2598,8 +2643,8 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(struct sock *sk, struct sk_buff *skb); - size_t (*get_info_size)(const struct sock *sk); + int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin); + size_t (*get_info_size)(const struct sock *sk, bool net_admin); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, const gfp_t priority); diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 32a27b4a5020..92a2e79222ea 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -28,7 +28,8 @@ struct tcphdr { __be32 seq; __be32 ack_seq; #if defined(__LITTLE_ENDIAN_BITFIELD) - __u16 res1:4, + __u16 ae:1, + res1:3, doff:4, fin:1, syn:1, @@ -40,7 +41,8 @@ struct tcphdr { cwr:1; #elif defined(__BIG_ENDIAN_BITFIELD) __u16 doff:4, - res1:4, + res1:3, + ae:1, cwr:1, ece:1, urg:1, @@ -70,6 +72,7 @@ union tcp_word_hdr { #define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3]) enum { + TCP_FLAG_AE = __constant_cpu_to_be32(0x01000000), TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000), TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000), TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000), @@ -78,7 +81,7 @@ enum { TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000), TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000), TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000), - TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000), + TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0E000000), TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000) }; |
