diff options
Diffstat (limited to 'include')
39 files changed, 825 insertions, 524 deletions
diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f715e8863f4d..3de38d7f0ced 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -193,7 +193,7 @@ struct bpf_map { atomic64_t usercnt; struct work_struct work; struct mutex freeze_mutex; - u64 writecnt; /* writable mmap cnt; protected by freeze_mutex */ + atomic64_t writecnt; }; static inline bool map_value_has_spin_lock(const struct bpf_map *map) @@ -1419,6 +1419,7 @@ void bpf_map_put(struct bpf_map *map); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); +bool bpf_map_write_active(const struct bpf_map *map); void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr); int generic_map_lookup_batch(struct bpf_map *map, const union bpf_attr *attr, @@ -2163,6 +2164,7 @@ 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; 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/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/filter.h b/include/linux/filter.h index 24b7ed2677af..b6a216eb217a 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1374,6 +1374,7 @@ struct bpf_sk_lookup_kern { const struct in6_addr *daddr; } v6; struct sock *selected_sk; + u32 ingress_ifindex; bool no_reuseport; }; @@ -1436,7 +1437,7 @@ 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; @@ -1452,6 +1453,7 @@ 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; @@ -1474,7 +1476,7 @@ 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; @@ -1490,6 +1492,7 @@ 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/kvm_host.h b/include/linux/kvm_host.h index 9e0667e3723e..c310648cc8f1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -874,7 +874,7 @@ void kvm_release_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_dirty(kvm_pfn_t pfn); void kvm_set_pfn_accessed(kvm_pfn_t pfn); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache); +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty); int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len); @@ -950,12 +950,8 @@ struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn); int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map); -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty); -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn); unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 2237abb93ccd..234eab059839 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -53,13 +53,6 @@ struct gfn_to_hva_cache { struct kvm_memory_slot *memslot; }; -struct gfn_to_pfn_cache { - u64 generation; - gfn_t gfn; - kvm_pfn_t pfn; - bool dirty; -}; - #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE /* * Memory caches are used to preallocate memory ahead of various MMU flows, diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h index 97afcea39a7b..8b18fe9771f9 100644 --- a/include/linux/mlx5/eswitch.h +++ b/include/linux/mlx5/eswitch.h @@ -145,13 +145,13 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw, GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \ ESW_TUN_OPTS_OFFSET + 1) -u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev); +u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev); u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev); struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw); #else /* CONFIG_MLX5_ESWITCH */ -static inline u8 mlx5_eswitch_mode(struct mlx5_core_dev *dev) +static inline u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev) { return MLX5_ESWITCH_NONE; } diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bb8c6f5f19bc..c3a6e6209600 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -105,7 +105,18 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - atomic_long_t pp_frag_count; + union { + /** + * dma_addr_upper: might require a 64-bit + * value on 32-bit architectures. + */ + unsigned long dma_addr_upper; + /** + * For frag page support, not supported in + * 32-bit architectures with 64-bit DMA. + */ + atomic_long_t pp_frag_count; + }; }; struct { /* slab, slob and slub */ union { 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/netdevice.h b/include/linux/netdevice.h index 3ec42495a43a..4f4a299e92de 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -592,7 +592,7 @@ 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; @@ -2520,109 +2520,6 @@ 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; @@ -3005,254 +2902,7 @@ 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 +3657,7 @@ 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); @@ -4444,10 +4095,21 @@ 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 */ @@ -4455,8 +4117,7 @@ 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); } /** @@ -4465,27 +4126,7 @@ 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) { @@ -4493,22 +4134,7 @@ 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) { @@ -5291,7 +4917,7 @@ 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/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/percpu.h b/include/linux/percpu.h index 98a9371133f8..ae4004e7957e 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -6,7 +6,6 @@ #include <linux/preempt.h> #include <linux/smp.h> #include <linux/cpumask.h> -#include <linux/printk.h> #include <linux/pfn.h> #include <linux/init.h> diff --git a/include/linux/phy.h b/include/linux/phy.h index 96e43fbb2dd8..1e57cdd95da3 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..3563820a1765 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) @@ -69,6 +92,7 @@ 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; @@ -79,6 +103,7 @@ struct phylink_config { void (*get_fixed_state)(struct phylink_config *config, struct phylink_link_state *state); DECLARE_PHY_INTERFACE_MASK(supported_interfaces); + unsigned long mac_capabilities; }; /** @@ -442,6 +467,12 @@ 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); diff --git a/include/linux/printk.h b/include/linux/printk.h index 85b656f82d75..9497f6b98339 100644 --- a/include/linux/printk.h +++ b/include/linux/printk.h @@ -198,6 +198,7 @@ void dump_stack_print_info(const char *log_lvl); void show_regs_print_info(const char *log_lvl); extern asmlinkage void dump_stack_lvl(const char *log_lvl) __cold; extern asmlinkage void dump_stack(void) __cold; +void printk_trigger_flush(void); #else static inline __printf(1, 0) int vprintk(const char *s, va_list args) @@ -274,6 +275,9 @@ static inline void dump_stack_lvl(const char *log_lvl) static inline void dump_stack(void) { } +static inline void printk_trigger_flush(void) +{ +} #endif #ifdef CONFIG_SMP diff --git a/include/linux/siphash.h b/include/linux/siphash.h index bf21591a9e5e..3f7427b9e935 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 686a666d073d..059b6266dcd7 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) @@ -626,6 +627,7 @@ 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 @@ -743,6 +745,7 @@ 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 { @@ -4226,7 +4229,7 @@ static inline void skb_remcsum_process(struct sk_buff *skb, void *ptr, return; } - if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { + if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE)) { __skb_checksum_complete(skb); skb_postpull_rcsum(skb, skb->data, ptr - (void *)skb->data); } 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/trace_events.h b/include/linux/trace_events.h index 50453b287615..2d167ac3452c 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -673,7 +673,7 @@ struct trace_event_file { #define PERF_MAX_TRACE_SIZE 8192 -#define MAX_FILTER_STR_VAL 256 /* Should handle KSYM_SYMBOL_LEN */ +#define MAX_FILTER_STR_VAL 256U /* Should handle KSYM_SYMBOL_LEN */ enum event_trigger_type { ETT_NONE = (0), diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index b465f8f3e554..04e87f4b9417 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -120,10 +120,15 @@ retry: if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) { u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size); + unsigned int nh_off = p_off; struct skb_shared_info *shinfo = skb_shinfo(skb); + /* UFO may not include transport header in gso_size. */ + if (gso_type & SKB_GSO_UDP) + nh_off -= thlen; + /* Too small packets are not really GSO ones. */ - if (skb->len - p_off > gso_size) { + if (skb->len - nh_off > gso_size) { shinfo->gso_size = gso_size; shinfo->gso_type = gso_type; diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h index 3271870fd85e..2f31e571f34c 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; @@ -405,6 +406,7 @@ 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_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..84db6b275231 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -566,6 +566,7 @@ 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 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index dd8840e70e25..2560cfe80db8 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 */ @@ -475,6 +476,9 @@ 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; __u16 discov_timeout; struct delayed_work discov_off; @@ -489,10 +493,7 @@ 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 +520,6 @@ 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 +528,6 @@ 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; @@ -603,6 +600,7 @@ struct hci_dev { #if IS_ENABLED(CONFIG_BT_AOSPEXT) bool aosp_capable; + bool aosp_quality_report; #endif int (*open)(struct hci_dev *hdev); @@ -1461,8 +1459,11 @@ 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)) /* Use enhanced synchronous connection if command is supported */ #define enhanced_sco_capable(dev) ((dev)->commands[29] & 0x08) @@ -1690,10 +1691,6 @@ 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 +1701,6 @@ 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 ----- */ @@ -1806,7 +1800,6 @@ 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 +1824,6 @@ 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..0336c1bc5d25 --- /dev/null +++ b/include/net/bluetooth/hci_sync.h @@ -0,0 +1,102 @@ +/* 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); + +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); diff --git a/include/net/gro.h b/include/net/gro.h index 01edaf3fdda0..9c22a010369c 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 = 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 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/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..7d1088888c10 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. */ 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/ipv6.h b/include/net/ipv6.h index c19bf51ded1d..53ac7707ca70 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -345,9 +345,9 @@ 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/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/nfc/nci_core.h b/include/net/nfc/nci_core.h index a964daedc17b..ea8595651c38 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -30,6 +30,7 @@ enum nci_flag { NCI_UP, NCI_DATA_EXCHANGE, NCI_DATA_EXCHANGE_TO, + NCI_UNREG, }; /* NCI device states */ diff --git a/include/net/page_pool.h b/include/net/page_pool.h index 3855f069627f..a4082406a003 100644 --- a/include/net/page_pool.h +++ b/include/net/page_pool.h @@ -216,14 +216,24 @@ static inline void page_pool_recycle_direct(struct page_pool *pool, page_pool_put_full_page(pool, page, true); } +#define PAGE_POOL_DMA_USE_PP_FRAG_COUNT \ + (sizeof(dma_addr_t) > sizeof(unsigned long)) + static inline dma_addr_t page_pool_get_dma_addr(struct page *page) { - return page->dma_addr; + dma_addr_t ret = page->dma_addr; + + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + ret |= (dma_addr_t)page->dma_addr_upper << 16 << 16; + + return ret; } static inline void page_pool_set_dma_addr(struct page *page, dma_addr_t addr) { page->dma_addr = addr; + if (PAGE_POOL_DMA_USE_PP_FRAG_COUNT) + page->dma_addr_upper = upper_32_bits(addr); } static inline void page_pool_set_frag_count(struct page *page, long nr) diff --git a/include/net/sock.h b/include/net/sock.h index b32906e1ab55..a79fc772324e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -63,6 +63,7 @@ #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> @@ -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, @@ -391,6 +391,11 @@ struct sock { #define sk_flags __sk_common.skc_flags #define sk_rxhash __sk_common.skc_rxhash + /* early demux fields */ + struct dst_entry *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 +415,8 @@ 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 +438,6 @@ struct sock { #ifdef CONFIG_XFRM struct xfrm_policy __rcu *sk_policy[2]; #endif - struct dst_entry *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 +464,6 @@ 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 +473,7 @@ 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 +495,7 @@ 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 +505,6 @@ 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; @@ -1022,12 +1024,18 @@ 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) @@ -1210,7 +1218,9 @@ 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 +1309,11 @@ 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 +1430,32 @@ 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 @@ -2124,10 +2154,10 @@ 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, @@ -2638,6 +2668,11 @@ 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/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/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h index fef3a36b0210..89d17629efe5 100644 --- a/include/soc/mscc/ocelot.h +++ b/include/soc/mscc/ocelot.h @@ -555,12 +555,25 @@ 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); +}; + +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 +594,12 @@ 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 +612,19 @@ 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) @@ -667,8 +699,11 @@ 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; @@ -870,6 +905,19 @@ 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 eeb1142aa1b1..9cca2f8e61a2 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/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ba5af15e25f5..6297eafdc40f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4938,6 +4938,25 @@ 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**. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5120,6 +5139,7 @@ union bpf_attr { FN(trace_vprintk), \ FN(skc_to_unix_sock), \ FN(kallsyms_lookup_name), \ + FN(find_vma), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -6296,6 +6316,7 @@ 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. */ }; /* 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, |