From 41a5db8d8161457b121a03fde999ff6e00090ee2 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 27 Aug 2023 08:27:34 -0700 Subject: bpf: Add support for non-fix-size percpu mem allocation This is needed for later percpu mem allocation when the allocation is done by bpf program. For such cases, a global bpf_global_percpu_ma is added where a flexible allocation size is needed. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230827152734.1995725-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 024e8b28c34b..440dd1f59a1c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -55,8 +55,8 @@ struct cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; extern struct kobject *btf_kobj; -extern struct bpf_mem_alloc bpf_global_ma; -extern bool bpf_global_ma_set; +extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma; +extern bool bpf_global_ma_set, bpf_global_percpu_ma_set; typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64); typedef int (*bpf_iter_init_seq_priv_t)(void *private_data, -- cgit v1.2.3 From 55db92f42fe4a4ef7b4c2b4960c6212c8512dd53 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 27 Aug 2023 08:27:39 -0700 Subject: bpf: Add BPF_KPTR_PERCPU as a field type BPF_KPTR_PERCPU represents a percpu field type like below struct val_t { ... fields ... }; struct t { ... struct val_t __percpu_kptr *percpu_data_ptr; ... }; where #define __percpu_kptr __attribute__((btf_type_tag("percpu_kptr"))) While BPF_KPTR_REF points to a trusted kernel object or a trusted local object, BPF_KPTR_PERCPU points to a trusted local percpu object. This patch added basic support for BPF_KPTR_PERCPU related to percpu_kptr field parsing, recording and free operations. BPF_KPTR_PERCPU also supports the same map types as BPF_KPTR_REF does. Note that unlike a local kptr, it is possible that a BPF_KTPR_PERCPU struct may not contain any special fields like other kptr, bpf_spin_lock, bpf_list_head, etc. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230827152739.1996391-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 18 ++++++++++++------ 1 file changed, 12 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 440dd1f59a1c..87eeb3a46a1d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -180,14 +180,15 @@ enum btf_field_type { BPF_TIMER = (1 << 1), BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), - BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, - BPF_LIST_HEAD = (1 << 4), - BPF_LIST_NODE = (1 << 5), - BPF_RB_ROOT = (1 << 6), - BPF_RB_NODE = (1 << 7), + BPF_KPTR_PERCPU = (1 << 4), + BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU, + BPF_LIST_HEAD = (1 << 5), + BPF_LIST_NODE = (1 << 6), + BPF_RB_ROOT = (1 << 7), + BPF_RB_NODE = (1 << 8), BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD | BPF_RB_NODE | BPF_RB_ROOT, - BPF_REFCOUNT = (1 << 8), + BPF_REFCOUNT = (1 << 9), }; typedef void (*btf_dtor_kfunc_t)(void *); @@ -300,6 +301,8 @@ static inline const char *btf_field_type_name(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return "kptr"; + case BPF_KPTR_PERCPU: + return "percpu_kptr"; case BPF_LIST_HEAD: return "bpf_list_head"; case BPF_LIST_NODE: @@ -325,6 +328,7 @@ static inline u32 btf_field_type_size(enum btf_field_type type) return sizeof(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: return sizeof(u64); case BPF_LIST_HEAD: return sizeof(struct bpf_list_head); @@ -351,6 +355,7 @@ static inline u32 btf_field_type_align(enum btf_field_type type) return __alignof__(struct bpf_timer); case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: return __alignof__(u64); case BPF_LIST_HEAD: return __alignof__(struct bpf_list_head); @@ -389,6 +394,7 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr) case BPF_TIMER: case BPF_KPTR_UNREF: case BPF_KPTR_REF: + case BPF_KPTR_PERCPU: break; default: WARN_ON_ONCE(1); -- cgit v1.2.3 From 01cc55af93884f1ff5a883426e1924378dfcc62a Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Sun, 27 Aug 2023 08:27:49 -0700 Subject: bpf: Add bpf_this_cpu_ptr/bpf_per_cpu_ptr support for allocated percpu obj The bpf helpers bpf_this_cpu_ptr() and bpf_per_cpu_ptr() are re-purposed for allocated percpu objects. For an allocated percpu obj, the reg type is 'PTR_TO_BTF_ID | MEM_PERCPU | MEM_RCU'. The return type for these two re-purposed helpera is 'PTR_TO_MEM | MEM_RCU | MEM_ALLOC'. The MEM_ALLOC allows that the per-cpu data can be read and written. Since the memory allocator bpf_mem_alloc() returns a ptr to a percpu ptr for percpu data, the first argument of bpf_this_cpu_ptr() and bpf_per_cpu_ptr() is patched with a dereference before passing to the helper func. Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20230827152749.1997202-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index b6e58dab8e27..a3236651ec64 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -480,6 +480,7 @@ struct bpf_insn_aux_data { bool zext_dst; /* this insn zero extends dst reg */ bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */ bool is_iter_next; /* bpf_iter__next() kfunc call */ + bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */ u8 alu_state; /* used in combination with alu_limit */ /* below fields are initialized once */ -- cgit v1.2.3 From 2ae5c9248e06dac2c2360be26b4e25f673238337 Mon Sep 17 00:00:00 2001 From: Jeff Johnson Date: Thu, 31 Aug 2023 11:22:58 -0700 Subject: wifi: mac80211: Use flexible array in struct ieee80211_tim_ie Currently struct ieee80211_tim_ie defines: u8 virtual_map[1]; Per the guidance in [1] change this to be a flexible array. Per the discussion in [2] wrap the virtual_map in a union with a u8 item in order to preserve the existing expectation that the virtual_map must contain at least one octet (at least when used in a non-S1G PPDU). This means that no driver changes are required. [1] https://docs.kernel.org/process/deprecated.html#zero-length-and-one-element-arrays [2] https://lore.kernel.org/linux-wireless/202308301529.AC90A9EF98@keescook/ Suggested-by: Kees Cook Signed-off-by: Jeff Johnson Reviewed-by: Kees Cook Link: https://lore.kernel.org/r/20230831-ieee80211_tim_ie-v3-2-e10ff584ab5d@quicinc.com [add wifi prefix] Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index bd2f6e19c357..340d7e0f6bf7 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -951,17 +951,24 @@ struct ieee80211_wide_bw_chansw_ie { * @dtim_count: DTIM Count * @dtim_period: DTIM Period * @bitmap_ctrl: Bitmap Control + * @required_octet: "Syntatic sugar" to force the struct size to the + * minimum valid size when carried in a non-S1G PPDU * @virtual_map: Partial Virtual Bitmap * * This structure represents the payload of the "TIM element" as - * described in IEEE Std 802.11-2020 section 9.4.2.5. + * described in IEEE Std 802.11-2020 section 9.4.2.5. Note that this + * definition is only applicable when the element is carried in a + * non-S1G PPDU. When the TIM is carried in an S1G PPDU, the Bitmap + * Control and Partial Virtual Bitmap may not be present. */ struct ieee80211_tim_ie { u8 dtim_count; u8 dtim_period; u8 bitmap_ctrl; - /* variable size: 1 - 251 bytes */ - u8 virtual_map[1]; + union { + u8 required_octet; + DECLARE_FLEX_ARRAY(u8, virtual_map); + }; } __packed; /** -- cgit v1.2.3 From 133c4c0d37175f510a10fa9bed51e223936073fc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 11 Sep 2023 17:05:31 +0000 Subject: tcp: defer regular ACK while processing socket backlog This idea came after a particular workload requested the quickack attribute set on routes, and a performance drop was noticed for large bulk transfers. For high throughput flows, it is best to use one cpu running the user thread issuing socket system calls, and a separate cpu to process incoming packets from BH context. (With TSO/GRO, bottleneck is usually the 'user' cpu) Problem is the user thread can spend a lot of time while holding the socket lock, forcing BH handler to queue most of incoming packets in the socket backlog. Whenever the user thread releases the socket lock, it must first process all accumulated packets in the backlog, potentially adding latency spikes. Due to flood mitigation, having too many packets in the backlog increases chance of unexpected drops. Backlog processing unfortunately shifts a fair amount of cpu cycles from the BH cpu to the 'user' cpu, thus reducing max throughput. This patch takes advantage of the backlog processing, and the fact that ACK are mostly cumulative. The idea is to detect we are in the backlog processing and defer all eligible ACK into a single one, sent from tcp_release_cb(). This saves cpu cycles on both sides, and network resources. Performance of a single TCP flow on a 200Gbit NIC: - Throughput is increased by 20% (100Gbit -> 120Gbit). - Number of generated ACK per second shrinks from 240,000 to 40,000. - Number of backlog drops per second shrinks from 230 to 0. Benchmark context: - Regular netperf TCP_STREAM (no zerocopy) - Intel(R) Xeon(R) Platinum 8481C (Saphire Rapids) - MAX_SKB_FRAGS = 17 (~60KB per GRO packet) This feature is guarded by a new sysctl, and enabled by default: /proc/sys/net/ipv4/tcp_backlog_ack_defer Signed-off-by: Eric Dumazet Acked-by: Yuchung Cheng Acked-by: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Acked-by: Dave Taht Signed-off-by: Paolo Abeni --- include/linux/tcp.h | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3c5efeeb024f..44d946161d4a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -463,15 +463,17 @@ enum tsq_enum { TCP_MTU_REDUCED_DEFERRED, /* tcp_v{4|6}_err() could not call * tcp_v{4|6}_mtu_reduced() */ + TCP_ACK_DEFERRED, /* TX pure ack is deferred */ }; enum tsq_flags { - TSQF_THROTTLED = (1UL << TSQ_THROTTLED), - TSQF_QUEUED = (1UL << TSQ_QUEUED), - TCPF_TSQ_DEFERRED = (1UL << TCP_TSQ_DEFERRED), - TCPF_WRITE_TIMER_DEFERRED = (1UL << TCP_WRITE_TIMER_DEFERRED), - TCPF_DELACK_TIMER_DEFERRED = (1UL << TCP_DELACK_TIMER_DEFERRED), - TCPF_MTU_REDUCED_DEFERRED = (1UL << TCP_MTU_REDUCED_DEFERRED), + TSQF_THROTTLED = BIT(TSQ_THROTTLED), + TSQF_QUEUED = BIT(TSQ_QUEUED), + TCPF_TSQ_DEFERRED = BIT(TCP_TSQ_DEFERRED), + TCPF_WRITE_TIMER_DEFERRED = BIT(TCP_WRITE_TIMER_DEFERRED), + TCPF_DELACK_TIMER_DEFERRED = BIT(TCP_DELACK_TIMER_DEFERRED), + TCPF_MTU_REDUCED_DEFERRED = BIT(TCP_MTU_REDUCED_DEFERRED), + TCPF_ACK_DEFERRED = BIT(TCP_ACK_DEFERRED), }; #define tcp_sk(ptr) container_of_const(ptr, struct tcp_sock, inet_conn.icsk_inet.sk) -- cgit v1.2.3 From 2b5dcb31a19a2e0acd869b12c9db9b2d696ef544 Mon Sep 17 00:00:00 2001 From: Leon Hwang Date: Tue, 12 Sep 2023 23:04:41 +0800 Subject: bpf, x64: Fix tailcall infinite loop From commit ebf7d1f508a73871 ("bpf, x64: rework pro/epilogue and tailcall handling in JIT"), the tailcall on x64 works better than before. From commit e411901c0b775a3a ("bpf: allow for tailcalls in BPF subprograms for x64 JIT"), tailcall is able to run in BPF subprograms on x64. From commit 5b92a28aae4dd0f8 ("bpf: Support attaching tracing BPF program to other BPF programs"), BPF program is able to trace other BPF programs. How about combining them all together? 1. FENTRY/FEXIT on a BPF subprogram. 2. A tailcall runs in the BPF subprogram. 3. The tailcall calls the subprogram's caller. As a result, a tailcall infinite loop comes up. And the loop would halt the machine. As we know, in tail call context, the tail_call_cnt propagates by stack and rax register between BPF subprograms. So do in trampolines. Fixes: ebf7d1f508a7 ("bpf, x64: rework pro/epilogue and tailcall handling in JIT") Fixes: e411901c0b77 ("bpf: allow for tailcalls in BPF subprograms for x64 JIT") Reviewed-by: Maciej Fijalkowski Signed-off-by: Leon Hwang Link: https://lore.kernel.org/r/20230912150442.2009-3-hffilwlqm@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 87eeb3a46a1d..b9e573159432 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1035,6 +1035,11 @@ struct btf_func_model { */ #define BPF_TRAMP_F_SHARE_IPMODIFY BIT(6) +/* Indicate that current trampoline is in a tail call context. Then, it has to + * cache and restore tail_call_cnt to avoid infinite tail call loop. + */ +#define BPF_TRAMP_F_TAIL_CALL_CTX BIT(7) + /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50 * bytes on x86. */ -- cgit v1.2.3 From 89de9921dfa77e43b985bde99a6031ab66511020 Mon Sep 17 00:00:00 2001 From: Paul M Stillwell Jr Date: Wed, 6 Sep 2023 13:57:01 -0600 Subject: virtchnl: Add CRC stripping capability Some VFs may want to disable CRC stripping on incoming packets so create an offload for that. The VF already sends information about configuring its RX queues so use that structure to indicate that the CRC stripping should be enabled or not. Signed-off-by: Paul M Stillwell Jr Reviewed-by: Jesse Brandeburg Reviewed-by: Paul Menzel Signed-off-by: Ahmed Zaki Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index d0807ad43f93..dd71d3009771 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -240,6 +240,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource); #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES BIT(6) /* used to negotiate communicating link speeds in Mbps */ #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED BIT(7) +#define VIRTCHNL_VF_OFFLOAD_CRC BIT(10) #define VIRTCHNL_VF_OFFLOAD_VLAN_V2 BIT(15) #define VIRTCHNL_VF_OFFLOAD_VLAN BIT(16) #define VIRTCHNL_VF_OFFLOAD_RX_POLLING BIT(17) @@ -295,7 +296,13 @@ VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info); /* VIRTCHNL_OP_CONFIG_RX_QUEUE * VF sends this message to set up parameters for one RX queue. * External data buffer contains one instance of virtchnl_rxq_info. - * PF configures requested queue and returns a status code. + * PF configures requested queue and returns a status code. The + * crc_disable flag disables CRC stripping on the VF. Setting + * the crc_disable flag to 1 will disable CRC stripping for each + * queue in the VF where the flag is set. The VIRTCHNL_VF_OFFLOAD_CRC + * offload must have been set prior to sending this info or the PF + * will ignore the request. This flag should be set the same for + * all of the queues for a VF. */ /* Rx queue config info */ @@ -307,7 +314,7 @@ struct virtchnl_rxq_info { u16 splithdr_enabled; /* deprecated with AVF 1.0 */ u32 databuffer_size; u32 max_pkt_size; - u8 pad0; + u8 crc_disable; u8 rxdid; u8 pad1[2]; u64 dma_ring_addr; -- cgit v1.2.3 From 81b36803ac139827538ac5ce4028e750a3c53f53 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:21 +0000 Subject: udp: introduce udp->udp_flags According to syzbot, it is time to use proper atomic flags for various UDP flags. Add udp_flags field, and convert udp->corkflag to first bit in it. Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 28 +++++++++++++++++++++------- 1 file changed, 21 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 43c1fb2d2c21..23f0693e0d9c 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -32,14 +32,20 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) return (num + net_hash_mix(net)) & mask; } +enum { + UDP_FLAGS_CORK, /* Cork is required */ +}; + struct udp_sock { /* inet_sock has to be the first member */ struct inet_sock inet; #define udp_port_hash inet.sk.__sk_common.skc_u16hashes[0] #define udp_portaddr_hash inet.sk.__sk_common.skc_u16hashes[1] #define udp_portaddr_node inet.sk.__sk_common.skc_portaddr_node + + unsigned long udp_flags; + int pending; /* Any pending frames ? */ - unsigned int corkflag; /* Cork is required */ __u8 encap_type; /* Is this an Encapsulation socket? */ unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ @@ -51,6 +57,11 @@ struct udp_sock { gro_enabled:1, /* Request GRO aggregation */ accept_udp_l4:1, accept_udp_fraglist:1; +/* indicator bits used by pcflag: */ +#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ +#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ +#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ + __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. @@ -62,12 +73,6 @@ struct udp_sock { */ __u16 pcslen; __u16 pcrlen; -/* indicator bits used by pcflag: */ -#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ -#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ -#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ - __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ - __u8 unused[3]; /* * For encapsulation sockets. */ @@ -95,6 +100,15 @@ struct udp_sock { int forward_threshold; }; +#define udp_test_bit(nr, sk) \ + test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_set_bit(nr, sk) \ + set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_clear_bit(nr, sk) \ + clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_assign_bit(nr, sk, val) \ + assign_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags, val) + #define UDP_MAX_SEGMENTS (1 << 6UL) #define udp_sk(ptr) container_of_const(ptr, struct udp_sock, inet.sk) -- cgit v1.2.3 From a0002127cd746fcaa182ad3386ef6931c37f3bda Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:22 +0000 Subject: udp: move udp->no_check6_tx to udp->udp_flags syzbot reported that udp->no_check6_tx can be read locklessly. Use one atomic bit from udp->udp_flags Fixes: 1c19448c9ba6 ("net: Make enabling of zero UDP6 csums more restrictive") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 23f0693e0d9c..e3f2a6c7ac1d 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -34,6 +34,7 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) enum { UDP_FLAGS_CORK, /* Cork is required */ + UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ }; struct udp_sock { @@ -47,8 +48,7 @@ struct udp_sock { int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char no_check6_tx:1,/* Send zero UDP6 checksums on TX? */ - no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ + unsigned char no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ encap_enabled:1, /* This socket enabled encap * processing; UDP tunnels and * different encapsulation layer set @@ -115,7 +115,7 @@ struct udp_sock { static inline void udp_set_no_check6_tx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_tx = val; + udp_assign_bit(NO_CHECK6_TX, sk, val); } static inline void udp_set_no_check6_rx(struct sock *sk, bool val) @@ -123,9 +123,9 @@ static inline void udp_set_no_check6_rx(struct sock *sk, bool val) udp_sk(sk)->no_check6_rx = val; } -static inline bool udp_get_no_check6_tx(struct sock *sk) +static inline bool udp_get_no_check6_tx(const struct sock *sk) { - return udp_sk(sk)->no_check6_tx; + return udp_test_bit(NO_CHECK6_TX, sk); } static inline bool udp_get_no_check6_rx(struct sock *sk) -- cgit v1.2.3 From bcbc1b1de884647aa0318bf74eb7f293d72a1e40 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:23 +0000 Subject: udp: move udp->no_check6_rx to udp->udp_flags syzbot reported that udp->no_check6_rx can be read locklessly. Use one atomic bit from udp->udp_flags. Fixes: 1c19448c9ba6 ("net: Make enabling of zero UDP6 csums more restrictive") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index e3f2a6c7ac1d..8d4c3835b1b2 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -35,6 +35,7 @@ static inline u32 udp_hashfn(const struct net *net, u32 num, u32 mask) enum { UDP_FLAGS_CORK, /* Cork is required */ UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ + UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ }; struct udp_sock { @@ -48,8 +49,7 @@ struct udp_sock { int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char no_check6_rx:1,/* Allow zero UDP6 checksums on RX? */ - encap_enabled:1, /* This socket enabled encap + unsigned char encap_enabled:1, /* This socket enabled encap * processing; UDP tunnels and * different encapsulation layer set * this @@ -120,7 +120,7 @@ static inline void udp_set_no_check6_tx(struct sock *sk, bool val) static inline void udp_set_no_check6_rx(struct sock *sk, bool val) { - udp_sk(sk)->no_check6_rx = val; + udp_assign_bit(NO_CHECK6_RX, sk, val); } static inline bool udp_get_no_check6_tx(const struct sock *sk) @@ -128,9 +128,9 @@ static inline bool udp_get_no_check6_tx(const struct sock *sk) return udp_test_bit(NO_CHECK6_TX, sk); } -static inline bool udp_get_no_check6_rx(struct sock *sk) +static inline bool udp_get_no_check6_rx(const struct sock *sk) { - return udp_sk(sk)->no_check6_rx; + return udp_test_bit(NO_CHECK6_RX, sk); } static inline void udp_cmsg_recv(struct msghdr *msg, struct sock *sk, -- cgit v1.2.3 From e1dc0615c6b08ef36414f08c011965b8fb56198b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:24 +0000 Subject: udp: move udp->gro_enabled to udp->udp_flags syzbot reported that udp->gro_enabled can be read locklessly. Use one atomic bit from udp->udp_flags. Fixes: e20cf8d3f1f7 ("udp: implement GRO for plain UDP sockets.") Reported-by: syzbot Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 8d4c3835b1b2..b344bd2e41fc 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -36,6 +36,7 @@ enum { UDP_FLAGS_CORK, /* Cork is required */ UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ + UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ }; struct udp_sock { @@ -54,7 +55,6 @@ struct udp_sock { * different encapsulation layer set * this */ - gro_enabled:1, /* Request GRO aggregation */ accept_udp_l4:1, accept_udp_fraglist:1; /* indicator bits used by pcflag: */ -- cgit v1.2.3 From f5f52f0884a595ff99ab1a608643fe4025fca2d5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:26 +0000 Subject: udp: move udp->accept_udp_{l4|fraglist} to udp->udp_flags These are read locklessly, move them to udp_flags to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index b344bd2e41fc..bb2b87adfbea 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -37,6 +37,8 @@ enum { UDP_FLAGS_NO_CHECK6_TX, /* Send zero UDP6 checksums on TX? */ UDP_FLAGS_NO_CHECK6_RX, /* Allow zero UDP6 checksums on RX? */ UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ + UDP_FLAGS_ACCEPT_FRAGLIST, + UDP_FLAGS_ACCEPT_L4, }; struct udp_sock { @@ -50,13 +52,11 @@ struct udp_sock { int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char encap_enabled:1, /* This socket enabled encap + unsigned char encap_enabled:1; /* This socket enabled encap * processing; UDP tunnels and * different encapsulation layer set * this */ - accept_udp_l4:1, - accept_udp_fraglist:1; /* indicator bits used by pcflag: */ #define UDPLITE_BIT 0x1 /* set by udplite proto init function */ #define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ @@ -149,10 +149,12 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) if (!skb_is_gso(skb)) return false; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && !udp_sk(sk)->accept_udp_l4) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && + !udp_test_bit(ACCEPT_L4, sk)) return true; - if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && !udp_sk(sk)->accept_udp_fraglist) + if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST && + !udp_test_bit(ACCEPT_FRAGLIST, sk)) return true; return false; @@ -160,8 +162,8 @@ static inline bool udp_unexpected_gso(struct sock *sk, struct sk_buff *skb) static inline void udp_allow_gso(struct sock *sk) { - udp_sk(sk)->accept_udp_l4 = 1; - udp_sk(sk)->accept_udp_fraglist = 1; + udp_set_bit(ACCEPT_L4, sk); + udp_set_bit(ACCEPT_FRAGLIST, sk); } #define udp_portaddr_for_each_entry(__sk, list) \ -- cgit v1.2.3 From ac9a7f4ce5dda1472e8f44096f33066c6ec1a3b4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:27 +0000 Subject: udp: lockless UDP_ENCAP_L2TPINUDP / UDP_GRO Move udp->encap_enabled to udp->udp_flags. Add udp_test_and_set_bit() helper to allow lockless udp_tunnel_encap_enable() implementation. Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index bb2b87adfbea..0cf83270a4a2 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -39,6 +39,7 @@ enum { UDP_FLAGS_GRO_ENABLED, /* Request GRO aggregation */ UDP_FLAGS_ACCEPT_FRAGLIST, UDP_FLAGS_ACCEPT_L4, + UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */ }; struct udp_sock { @@ -52,11 +53,7 @@ struct udp_sock { int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ - unsigned char encap_enabled:1; /* This socket enabled encap - * processing; UDP tunnels and - * different encapsulation layer set - * this - */ + /* indicator bits used by pcflag: */ #define UDPLITE_BIT 0x1 /* set by udplite proto init function */ #define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ @@ -104,6 +101,8 @@ struct udp_sock { test_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_set_bit(nr, sk) \ set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) +#define udp_test_and_set_bit(nr, sk) \ + test_and_set_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_clear_bit(nr, sk) \ clear_bit(UDP_FLAGS_##nr, &udp_sk(sk)->udp_flags) #define udp_assign_bit(nr, sk, val) \ -- cgit v1.2.3 From 729549aa350c56a777bb342941ed4d69b6585769 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:29 +0000 Subject: udplite: remove UDPLITE_BIT This flag is set but never read, we can remove it. Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 0cf83270a4a2..58156edec009 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -55,9 +55,8 @@ struct udp_sock { __u8 encap_type; /* Is this an Encapsulation socket? */ /* indicator bits used by pcflag: */ -#define UDPLITE_BIT 0x1 /* set by udplite proto init function */ -#define UDPLITE_SEND_CC 0x2 /* set via udplite setsockopt */ -#define UDPLITE_RECV_CC 0x4 /* set via udplite setsocktopt */ +#define UDPLITE_SEND_CC 0x1 /* set via udplite setsockopt */ +#define UDPLITE_RECV_CC 0x2 /* set via udplite setsocktopt */ __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ /* * Following member retains the information to create a UDP header -- cgit v1.2.3 From 882af43a0fc37e26d85fb0df0c9edd3bed928de4 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 09:17:30 +0000 Subject: udplite: fix various data-races udp->pcflag, udp->pcslen and udp->pcrlen reads/writes are racy. Move udp->pcflag to udp->udp_flags for atomicity, and add READ_ONCE()/WRITE_ONCE() annotations for pcslen and pcrlen. Fixes: ba4e58eca8aa ("[NET]: Supporting UDP-Lite (RFC 3828) in Linux") Signed-off-by: Eric Dumazet Reviewed-by: Willem de Bruijn Signed-off-by: Paolo Abeni --- include/linux/udp.h | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/udp.h b/include/linux/udp.h index 58156edec009..d04188714dca 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -40,6 +40,8 @@ enum { UDP_FLAGS_ACCEPT_FRAGLIST, UDP_FLAGS_ACCEPT_L4, UDP_FLAGS_ENCAP_ENABLED, /* This socket enabled encap */ + UDP_FLAGS_UDPLITE_SEND_CC, /* set via udplite setsockopt */ + UDP_FLAGS_UDPLITE_RECV_CC, /* set via udplite setsockopt */ }; struct udp_sock { @@ -54,10 +56,6 @@ struct udp_sock { int pending; /* Any pending frames ? */ __u8 encap_type; /* Is this an Encapsulation socket? */ -/* indicator bits used by pcflag: */ -#define UDPLITE_SEND_CC 0x1 /* set via udplite setsockopt */ -#define UDPLITE_RECV_CC 0x2 /* set via udplite setsocktopt */ - __u8 pcflag; /* marks socket as UDP-Lite if > 0 */ /* * Following member retains the information to create a UDP header * when the socket is uncorked. -- cgit v1.2.3 From b0adfba7ee770fef20b1b6d86706c28f7fccfb07 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:01:59 +0000 Subject: ipv6: lockless IPV6_UNICAST_HOPS implementation Some np->hop_limit accesses are racy, when socket lock is not held. Add missing annotations and switch to full lockless implementation. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 12 +----------- 1 file changed, 1 insertion(+), 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index af8a771a053c..c2e087071384 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -213,17 +213,7 @@ struct ipv6_pinfo { __be32 flow_label; __u32 frag_size; - /* - * Packed in 16bits. - * Omit one shift by putting the signed field at MSB. - */ -#if defined(__BIG_ENDIAN_BITFIELD) - __s16 hop_limit:9; - __u16 __unused_1:7; -#else - __u16 __unused_1:7; - __s16 hop_limit:9; -#endif + s16 hop_limit; #if defined(__BIG_ENDIAN_BITFIELD) /* Packed in 16bits. */ -- cgit v1.2.3 From d986f52124e062753e33b6fe303be5904a997eac Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:00 +0000 Subject: ipv6: lockless IPV6_MULTICAST_LOOP implementation Add inet6_{test|set|clear|assign}_bit() helpers. Note that I am using bits from inet->inet_flags, this might change in the future if we need more flags. While solving data-races accessing np->mc_loop, this patch also allows to implement lockless accesses to np->mcast_hops in the following patch. Also constify sk_mc_loop() argument. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c2e087071384..68cf1ca94914 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -218,11 +218,9 @@ struct ipv6_pinfo { #if defined(__BIG_ENDIAN_BITFIELD) /* Packed in 16bits. */ __s16 mcast_hops:9; - __u16 __unused_2:6, - mc_loop:1; + __u16 __unused_2:7, #else - __u16 mc_loop:1, - __unused_2:6; + __u16 __unused_2:7; __s16 mcast_hops:9; #endif int ucast_oif; @@ -283,6 +281,18 @@ struct ipv6_pinfo { struct inet6_cork cork; }; +/* We currently use available bits from inet_sk(sk)->inet_flags, + * this could change in the future. + */ +#define inet6_test_bit(nr, sk) \ + test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet6_set_bit(nr, sk) \ + set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet6_clear_bit(nr, sk) \ + clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags) +#define inet6_assign_bit(nr, sk, val) \ + assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val) + /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */ struct raw6_sock { /* inet_sock has to be the first member of raw6_sock */ -- cgit v1.2.3 From 2da23eb07c91241d962f3ff05565065484cd8929 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:01 +0000 Subject: ipv6: lockless IPV6_MULTICAST_HOPS implementation This fixes data-races around np->mcast_hops, and make IPV6_MULTICAST_HOPS lockless. Note that np->mcast_hops is never negative, thus can fit an u8 field instead of s16. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 9 +-------- 1 file changed, 1 insertion(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 68cf1ca94914..9cc278b5e4f4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -214,15 +214,8 @@ struct ipv6_pinfo { __u32 frag_size; s16 hop_limit; + u8 mcast_hops; -#if defined(__BIG_ENDIAN_BITFIELD) - /* Packed in 16bits. */ - __s16 mcast_hops:9; - __u16 __unused_2:7, -#else - __u16 __unused_2:7; - __s16 mcast_hops:9; -#endif int ucast_oif; int mcast_oif; -- cgit v1.2.3 From dcae74622c051b219ee628669a31716473efda2c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:04 +0000 Subject: ipv6: lockless IPV6_RECVERR_RFC4884 implementation Move np->recverr_rfc4884 to an atomic flag to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 9cc278b5e4f4..0d2b0a1b2dae 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -256,7 +256,6 @@ struct ipv6_pinfo { autoflowlabel:1, autoflowlabel_set:1, mc_all:1, - recverr_rfc4884:1, rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; -- cgit v1.2.3 From 6559c0ff3bc27d7e4d447d31c1d7e8eae0e959f5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:05 +0000 Subject: ipv6: lockless IPV6_MULTICAST_ALL implementation Move np->mc_all to an atomic flags to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 0d2b0a1b2dae..d88e91b7f0a3 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -255,7 +255,6 @@ struct ipv6_pinfo { dontfrag:1, autoflowlabel:1, autoflowlabel_set:1, - mc_all:1, rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; -- cgit v1.2.3 From 5121516b0c4736b7977d977b239e36d23ec64401 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:06 +0000 Subject: ipv6: lockless IPV6_AUTOFLOWLABEL implementation Move np->autoflowlabel and np->autoflowlabel_set in inet->inet_flags, to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index d88e91b7f0a3..e3be5dc21b7d 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -253,8 +253,6 @@ struct ipv6_pinfo { * 100: prefer care-of address */ dontfrag:1, - autoflowlabel:1, - autoflowlabel_set:1, rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; -- cgit v1.2.3 From 1086ca7cce292bb498d7f8f85f4593c9ef4902b7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:07 +0000 Subject: ipv6: lockless IPV6_DONTFRAG implementation Move np->dontfrag flag to inet->inet_flags to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e3be5dc21b7d..57d563f1d4b1 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -252,7 +252,6 @@ struct ipv6_pinfo { * 010: prefer public address * 100: prefer care-of address */ - dontfrag:1, rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; -- cgit v1.2.3 From 3fa29971c69519629370b119b0b618ee88ade6b9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:08 +0000 Subject: ipv6: lockless IPV6_RECVERR implemetation np->recverr is moved to inet->inet_flags to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 57d563f1d4b1..53f4f1b97a78 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -243,8 +243,7 @@ struct ipv6_pinfo { } rxopt; /* sockopt flags */ - __u16 recverr:1, - sndflow:1, + __u16 sndflow:1, repflow:1, pmtudisc:3, padding:1, /* 1 bit hole */ -- cgit v1.2.3 From 3cccda8db2cf2f2a224d55d5b6e2251d478c58ca Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:09 +0000 Subject: ipv6: move np->repflow to atomic flags Move np->repflow to inet->inet_flags to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 53f4f1b97a78..e62413371ea4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -244,7 +244,6 @@ struct ipv6_pinfo { /* sockopt flags */ __u16 sndflow:1, - repflow:1, pmtudisc:3, padding:1, /* 1 bit hole */ srcprefs:3, /* 001: prefer temporary address -- cgit v1.2.3 From 83cd5eb654b320c1972254f243531f3f3cebcccf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:10 +0000 Subject: ipv6: lockless IPV6_ROUTER_ALERT_ISOLATE implementation Reads from np->rtalert_isolate are racy. Move this flag to inet->inet_flags to fix data-races. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e62413371ea4..f288a35f157f 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -246,11 +246,10 @@ struct ipv6_pinfo { __u16 sndflow:1, pmtudisc:3, padding:1, /* 1 bit hole */ - srcprefs:3, /* 001: prefer temporary address + srcprefs:3; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ - rtalert_isolate:1; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; -- cgit v1.2.3 From 6b724bc4300b431443f3b99520994a5aece347cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:11 +0000 Subject: ipv6: lockless IPV6_MTU_DISCOVER implementation Most np->pmtudisc reads are racy. Move this 3bit field on a full byte, add annotations and make IPV6_MTU_DISCOVER setsockopt() lockless. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index f288a35f157f..10f521a6a9c8 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -243,13 +243,12 @@ struct ipv6_pinfo { } rxopt; /* sockopt flags */ - __u16 sndflow:1, - pmtudisc:3, - padding:1, /* 1 bit hole */ + __u8 sndflow:1, srcprefs:3; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ + __u8 pmtudisc; __u8 min_hopcount; __u8 tclass; __be32 rcv_flowinfo; -- cgit v1.2.3 From 859f8b265fc2a11af0fb0c52b4087e0409250592 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Sep 2023 16:02:12 +0000 Subject: ipv6: lockless IPV6_FLOWINFO_SEND implementation np->sndflow reads are racy. Use one bit ftom atomic inet->inet_flags instead, IPV6_FLOWINFO_SEND setsockopt() can be lockless. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 10f521a6a9c8..09253825c99c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -243,8 +243,7 @@ struct ipv6_pinfo { } rxopt; /* sockopt flags */ - __u8 sndflow:1, - srcprefs:3; /* 001: prefer temporary address + __u8 srcprefs:3; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ -- cgit v1.2.3 From daabb2b098e04753fa3d1b1feed13e5a61bef61c Mon Sep 17 00:00:00 2001 From: Puranjay Mohan Date: Thu, 7 Sep 2023 23:05:49 +0000 Subject: bpf/tests: add tests for cpuv4 instructions The BPF JITs now support cpuv4 instructions. Add tests for these new instructions to the test suite: 1. Sign extended Load 2. Sign extended Mov 3. Unconditional byte swap 4. Unconditional jump with 32-bit offset 5. Signed division and modulo Signed-off-by: Puranjay Mohan Link: https://lore.kernel.org/r/20230907230550.1417590-9-puranjay12@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 50 ++++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 46 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 761af6b3cf2b..0138832ad571 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -117,21 +117,25 @@ struct ctl_table_header; /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ -#define BPF_ALU64_IMM(OP, DST, IMM) \ +#define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ - .off = 0, \ + .off = OFF, \ .imm = IMM }) +#define BPF_ALU64_IMM(OP, DST, IMM) \ + BPF_ALU64_IMM_OFF(OP, DST, IMM, 0) -#define BPF_ALU32_IMM(OP, DST, IMM) \ +#define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ - .off = 0, \ + .off = OFF, \ .imm = IMM }) +#define BPF_ALU32_IMM(OP, DST, IMM) \ + BPF_ALU32_IMM_OFF(OP, DST, IMM, 0) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ @@ -143,6 +147,16 @@ struct ctl_table_header; .off = 0, \ .imm = LEN }) +/* Byte Swap, bswap16/32/64 */ + +#define BPF_BSWAP(DST, LEN) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ + .dst_reg = DST, \ + .src_reg = 0, \ + .off = 0, \ + .imm = LEN }) + /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ @@ -179,6 +193,24 @@ struct ctl_table_header; .off = 0, \ .imm = IMM }) +/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ + +#define BPF_MOVSX64_REG(DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_ALU64 | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + +#define BPF_MOVSX32_REG(DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_ALU | BPF_MOV | BPF_X, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ @@ -263,6 +295,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn) .off = OFF, \ .imm = 0 }) +/* Memory load, dst_reg = *(signed size *) (src_reg + off16) */ + +#define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ + ((struct bpf_insn) { \ + .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ + .dst_reg = DST, \ + .src_reg = SRC, \ + .off = OFF, \ + .imm = 0 }) + /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ -- cgit v1.2.3 From 3868ab0f192581eff978501a05f3dc2e01541d77 Mon Sep 17 00:00:00 2001 From: Aananth V Date: Thu, 14 Sep 2023 14:36:21 +0000 Subject: tcp: new TCP_INFO stats for RTO events The 2023 SIGCOMM paper "Improving Network Availability with Protective ReRoute" has indicated Linux TCP's RTO-triggered txhash rehashing can effectively reduce application disruption during outages. To better measure the efficacy of this feature, this patch adds three more detailed stats during RTO recovery and exports via TCP_INFO. Applications and monitoring systems can leverage this data to measure the network path diversity and end-to-end repair latency during network outages to improve their network infrastructure. The following counters are added to tcp_sock in order to track RTO events over the lifetime of a TCP socket. 1. u16 total_rto - Counts the total number of RTO timeouts. 2. u16 total_rto_recoveries - Counts the total number of RTO recoveries. 3. u32 total_rto_time - Counts the total time spent (ms) in RTO recoveries. (time spent in CA_Loss and CA_Recovery states) To compute total_rto_time, we add a new u32 rto_stamp field to tcp_sock. rto_stamp records the start timestamp (ms) of the last RTO recovery (CA_Loss). Corresponding fields are also added to the tcp_info struct. Signed-off-by: Aananth V Signed-off-by: Neal Cardwell Signed-off-by: Yuchung Cheng Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 44d946161d4a..e15452df9804 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -377,6 +377,14 @@ struct tcp_sock { * Total data bytes retransmitted */ u32 total_retrans; /* Total retransmits for entire connection */ + u32 rto_stamp; /* Start time (ms) of last CA_Loss recovery */ + u16 total_rto; /* Total number of RTO timeouts, including + * SYN/SYN-ACK and recurring timeouts. + */ + u16 total_rto_recoveries; /* Total number of RTO recoveries, + * including any unfinished recovery. + */ + u32 total_rto_time; /* ms spent in (completed) RTO recoveries. */ u32 urg_seq; /* Seq of received urgent pointer */ unsigned int keepalive_time; /* time before keep alive takes place */ -- cgit v1.2.3 From 9af27da6313c8f8c6a26c7ea3fe23d6b9664a3a8 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 13 Sep 2023 01:31:58 +0200 Subject: bpf: Use bpf_is_subprog to check for subprogs We would like to know whether a bpf_prog corresponds to the main prog or one of the subprogs. The current JIT implementations simply check this using the func_idx in bpf_prog->aux->func_idx. When the index is 0, it belongs to the main program, otherwise it corresponds to some subprogram. This will also be necessary to halt exception propagation while walking the stack when an exception is thrown, so we add a simple helper function to check this, named bpf_is_subprog, and convert existing JIT implementations to also make use of it. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230912233214.1518551-2-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b9e573159432..9171b0b6a590 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -3194,4 +3194,9 @@ static inline gfp_t bpf_memcg_flags(gfp_t flags) return flags; } +static inline bool bpf_is_subprog(const struct bpf_prog *prog) +{ + return prog->aux->func_idx != 0; +} + #endif /* _LINUX_BPF_H */ -- cgit v1.2.3 From fd5d27b70188379bb441d404c29a0afb111e1753 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 13 Sep 2023 01:31:59 +0200 Subject: arch/x86: Implement arch_bpf_stack_walk The plumbing for offline unwinding when we throw an exception in programs would require walking the stack, hence introduce a new arch_bpf_stack_walk function. This is provided when the JIT supports exceptions, i.e. bpf_jit_supports_exceptions is true. The arch-specific code is really minimal, hence it should be straightforward to extend this support to other architectures as well, as it reuses the logic of arch_stack_walk, but allowing access to unwind_state data. Once the stack pointer and frame pointer are known for the main subprog during the unwinding, we know the stack layout and location of any callee-saved registers which must be restored before we return back to the kernel. This handling will be added in the subsequent patches. Note that while we primarily unwind through BPF frames, which are effectively CONFIG_UNWINDER_FRAME_POINTER, we still need one of this or CONFIG_UNWINDER_ORC to be able to unwind through the bpf_throw frame from which we begin walking the stack. We also require both sp and bp (stack and frame pointers) from the unwind_state structure, which are only available when one of these two options are enabled. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230912233214.1518551-3-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/filter.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 0138832ad571..88874de974cb 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -954,6 +954,8 @@ bool bpf_jit_needs_zext(void); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); +bool bpf_jit_supports_exceptions(void); +void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) -- cgit v1.2.3 From 335d1c5b545284d75ef96ee42e461eacefe865bb Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 13 Sep 2023 01:32:00 +0200 Subject: bpf: Implement support for adding hidden subprogs Introduce support in the verifier for generating a subprogram and include it as part of a BPF program dynamically after the do_check phase is complete. The first user will be the next patch which generates default exception callbacks if none are set for the program. The phase of invocation will be do_misc_fixups. Note that this is an internal verifier function, and should be used with instruction blocks which uphold the invariants stated in check_subprogs. Since these subprogs are always appended to the end of the instruction sequence of the program, it becomes relatively inexpensive to do the related adjustments to the subprog_info of the program. Only the fake exit subprogram is shifted forward, making room for our new subprog. This is useful to insert a new subprogram, get it JITed, and obtain its function pointer. The next patch will use this functionality to insert a default exception callback which will be invoked after unwinding the stack. Note that these added subprograms are invisible to userspace, and never reported in BPF_OBJ_GET_INFO_BY_ID etc. For now, only a single subprogram is supported, but more can be easily supported in the future. To this end, two function counts are introduced now, the existing func_cnt, and real_func_cnt, the latter including hidden programs. This allows us to conver the JIT code to use the real_func_cnt for management of resources while syscall path continues working with existing func_cnt. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230912233214.1518551-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + include/linux/bpf_verifier.h | 3 ++- 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 9171b0b6a590..c3667e95af59 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1389,6 +1389,7 @@ struct bpf_prog_aux { u32 stack_depth; u32 id; u32 func_cnt; /* used by non-func prog as the number of func progs */ + u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */ u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */ u32 attach_btf_id; /* in-kernel BTF type id to attach to */ u32 ctx_arg_info_size; diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index a3236651ec64..3c2a8636ab29 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -588,6 +588,7 @@ struct bpf_verifier_env { u32 used_map_cnt; /* number of used maps */ u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ + u32 hidden_subprog_cnt; /* number of hidden subprogs */ bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; @@ -598,7 +599,7 @@ struct bpf_verifier_env { struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; - struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; + struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */ union { struct bpf_idmap idmap_scratch; struct bpf_idset idset_scratch; -- cgit v1.2.3 From f18b03fabaa9b7c80e80b72a621f481f0d706ae0 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 13 Sep 2023 01:32:01 +0200 Subject: bpf: Implement BPF exceptions This patch implements BPF exceptions, and introduces a bpf_throw kfunc to allow programs to throw exceptions during their execution at runtime. A bpf_throw invocation is treated as an immediate termination of the program, returning back to its caller within the kernel, unwinding all stack frames. This allows the program to simplify its implementation, by testing for runtime conditions which the verifier has no visibility into, and assert that they are true. In case they are not, the program can simply throw an exception from the other branch. BPF exceptions are explicitly *NOT* an unlikely slowpath error handling primitive, and this objective has guided design choices of the implementation of the them within the kernel (with the bulk of the cost for unwinding the stack offloaded to the bpf_throw kfunc). The implementation of this mechanism requires use of add_hidden_subprog mechanism introduced in the previous patch, which generates a couple of instructions to move R1 to R0 and exit. The JIT then rewrites the prologue of this subprog to take the stack pointer and frame pointer as inputs and reset the stack frame, popping all callee-saved registers saved by the main subprog. The bpf_throw function then walks the stack at runtime, and invokes this exception subprog with the stack and frame pointers as parameters. Reviewers must take note that currently the main program is made to save all callee-saved registers on x86_64 during entry into the program. This is because we must do an equivalent of a lightweight context switch when unwinding the stack, therefore we need the callee-saved registers of the caller of the BPF program to be able to return with a sane state. Note that we have to additionally handle r12, even though it is not used by the program, because when throwing the exception the program makes an entry into the kernel which could clobber r12 after saving it on the stack. To be able to preserve the value we received on program entry, we push r12 and restore it from the generated subprogram when unwinding the stack. For now, bpf_throw invocation fails when lingering resources or locks exist in that path of the program. In a future followup, bpf_throw will be extended to perform frame-by-frame unwinding to release lingering resources for each stack frame, removing this limitation. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230912233214.1518551-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 3 +++ include/linux/bpf_verifier.h | 4 ++++ include/linux/filter.h | 6 ++++++ 3 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c3667e95af59..16740ee82082 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1410,6 +1410,8 @@ struct bpf_prog_aux { bool sleepable; bool tail_call_reachable; bool xdp_has_frags; + bool exception_cb; + bool exception_boundary; /* BTF_KIND_FUNC_PROTO for valid attach_btf_id */ const struct btf_type *attach_func_proto; /* function name for valid attach_btf_id */ @@ -1432,6 +1434,7 @@ struct bpf_prog_aux { int cgroup_atype; /* enum cgroup_bpf_attach_type */ struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; + unsigned int (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp); #ifdef CONFIG_SECURITY void *security; #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 3c2a8636ab29..da21a3ec5027 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -541,7 +541,9 @@ struct bpf_subprog_info { bool has_tail_call; bool tail_call_reachable; bool has_ld_abs; + bool is_cb; bool is_async_cb; + bool is_exception_cb; }; struct bpf_verifier_env; @@ -589,6 +591,7 @@ struct bpf_verifier_env { u32 used_btf_cnt; /* number of used BTF objects */ u32 id_gen; /* used to generate unique reg IDs */ u32 hidden_subprog_cnt; /* number of hidden subprogs */ + int exception_callback_subprog; bool explore_alu_limits; bool allow_ptr_leaks; bool allow_uninit_stack; @@ -596,6 +599,7 @@ struct bpf_verifier_env { bool bypass_spec_v1; bool bypass_spec_v4; bool seen_direct_write; + bool seen_exception; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ const struct bpf_line_info *prev_linfo; struct bpf_verifier_log log; diff --git a/include/linux/filter.h b/include/linux/filter.h index 88874de974cb..27406aee2d40 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1171,6 +1171,7 @@ const char *__bpf_address_lookup(unsigned long addr, unsigned long *size, bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); +struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, @@ -1238,6 +1239,11 @@ static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, return -ERANGE; } +static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) +{ + return NULL; +} + static inline const char * bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) -- cgit v1.2.3 From b9ae0c9dd0aca79bffc17be51c2dc148d1f72708 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 13 Sep 2023 01:32:03 +0200 Subject: bpf: Add support for custom exception callbacks By default, the subprog generated by the verifier to handle a thrown exception hardcodes a return value of 0. To allow user-defined logic and modification of the return value when an exception is thrown, introduce the 'exception_callback:' declaration tag, which marks a callback as the default exception handler for the program. The format of the declaration tag is 'exception_callback:', where is the name of the exception callback. Each main program can be tagged using this BTF declaratiion tag to associate it with an exception callback. In case the tag is absent, the default callback is used. As such, the exception callback cannot be modified at runtime, only set during verification. Allowing modification of the callback for the current program execution at runtime leads to issues when the programs begin to nest, as any per-CPU state maintaing this information will have to be saved and restored. We don't want it to stay in bpf_prog_aux as this takes a global effect for all programs. An alternative solution is spilling the callback pointer at a known location on the program stack on entry, and then passing this location to bpf_throw as a parameter. However, since exceptions are geared more towards a use case where they are ideally never invoked, optimizing for this use case and adding to the complexity has diminishing returns. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20230912233214.1518551-7-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 +++- include/linux/bpf_verifier.h | 1 + 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 16740ee82082..30063a760b5a 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2422,9 +2422,11 @@ int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog, int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog, struct bpf_reg_state *regs); int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog, - struct bpf_reg_state *reg); + struct bpf_reg_state *reg, bool is_ex_cb); int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog, struct btf *btf, const struct btf_type *t); +const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt, + int comp_idx, const char *tag_key); struct bpf_prog *bpf_prog_by_id(u32 id); struct bpf_link *bpf_link_by_id(u32 id); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index da21a3ec5027..94ec766432f5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -300,6 +300,7 @@ struct bpf_func_state { bool in_callback_fn; struct tnum callback_ret_range; bool in_async_callback_fn; + bool in_exception_callback_fn; /* The following fields should be last. See copy_func_state() */ int acquired_refs; -- cgit v1.2.3 From 7ccb84f04cda1dd6f64f352e9795db308e9cdc0c Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Wed, 13 Sep 2023 01:32:06 +0200 Subject: mm: kasan: Declare kasan_unpoison_task_stack_below in kasan.h We require access to this kasan helper in BPF code in the next patch where we have to unpoison the task stack when we unwind and reset the stack frame from bpf_throw, and it never really unpoisons the poisoned stack slots on entry when compiler instrumentation is generated by CONFIG_KASAN_STACK and inline instrumentation is supported. Also, remove the declaration from mm/kasan/kasan.h as we put it in the header file kasan.h. Cc: Andrey Ryabinin Cc: Alexander Potapenko Cc: Andrey Konovalov Cc: Dmitry Vyukov Cc: Vincenzo Frascino Suggested-by: Andrey Konovalov Signed-off-by: Kumar Kartikeya Dwivedi Reviewed-by: Andrey Konovalov Link: https://lore.kernel.org/r/20230912233214.1518551-10-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/kasan.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kasan.h b/include/linux/kasan.h index 819b6bc8ac08..7a463f814db2 100644 --- a/include/linux/kasan.h +++ b/include/linux/kasan.h @@ -283,8 +283,10 @@ static inline bool kasan_check_byte(const void *address) #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK) void kasan_unpoison_task_stack(struct task_struct *task); +asmlinkage void kasan_unpoison_task_stack_below(const void *watermark); #else static inline void kasan_unpoison_task_stack(struct task_struct *task) {} +static inline void kasan_unpoison_task_stack_below(const void *watermark) {} #endif #ifdef CONFIG_KASAN_GENERIC -- cgit v1.2.3 From 9431063ad323ac864750aeba4d304389bc42ca4e Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Wed, 13 Sep 2023 21:49:37 +0100 Subject: dpll: core: Add DPLL framework base functions DPLL framework is used to represent and configure DPLL devices in systems. Each device that has DPLL and can configure inputs and outputs can use this framework. Implement core framework functions for further interactions with device drivers implementing dpll subsystem, as well as for interactions of DPLL netlink framework part with the subsystem itself. Co-developed-by: Milena Olech Signed-off-by: Milena Olech Co-developed-by: Michal Michalik Signed-off-by: Michal Michalik Signed-off-by: Vadim Fedorenko Co-developed-by: Arkadiusz Kubalewski Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/dpll.h | 133 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 133 insertions(+) create mode 100644 include/linux/dpll.h (limited to 'include/linux') diff --git a/include/linux/dpll.h b/include/linux/dpll.h new file mode 100644 index 000000000000..b47c3560b937 --- /dev/null +++ b/include/linux/dpll.h @@ -0,0 +1,133 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (c) 2023 Meta Platforms, Inc. and affiliates + * Copyright (c) 2023 Intel and affiliates + */ + +#ifndef __DPLL_H__ +#define __DPLL_H__ + +#include +#include +#include + +struct dpll_device; +struct dpll_pin; + +struct dpll_device_ops { + int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_mode *mode, struct netlink_ext_ack *extack); + bool (*mode_supported)(const struct dpll_device *dpll, void *dpll_priv, + const enum dpll_mode mode, + struct netlink_ext_ack *extack); + int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv, + enum dpll_lock_status *status, + struct netlink_ext_ack *extack); + int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv, + s32 *temp, struct netlink_ext_ack *extack); +}; + +struct dpll_pin_ops { + int (*frequency_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const u64 frequency, + struct netlink_ext_ack *extack); + int (*frequency_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u64 *frequency, struct netlink_ext_ack *extack); + int (*direction_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const enum dpll_pin_direction direction, + struct netlink_ext_ack *extack); + int (*direction_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + enum dpll_pin_direction *direction, + struct netlink_ext_ack *extack); + int (*state_on_pin_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + enum dpll_pin_state *state, + struct netlink_ext_ack *extack); + int (*state_on_dpll_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, + void *dpll_priv, enum dpll_pin_state *state, + struct netlink_ext_ack *extack); + int (*state_on_pin_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_pin *parent_pin, + void *parent_pin_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack); + int (*state_on_dpll_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, + void *dpll_priv, + const enum dpll_pin_state state, + struct netlink_ext_ack *extack); + int (*prio_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + u32 *prio, struct netlink_ext_ack *extack); + int (*prio_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const u32 prio, struct netlink_ext_ack *extack); +}; + +struct dpll_pin_frequency { + u64 min; + u64 max; +}; + +#define DPLL_PIN_FREQUENCY_RANGE(_min, _max) \ + { \ + .min = _min, \ + .max = _max, \ + } + +#define DPLL_PIN_FREQUENCY(_val) DPLL_PIN_FREQUENCY_RANGE(_val, _val) +#define DPLL_PIN_FREQUENCY_1PPS \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_1_HZ) +#define DPLL_PIN_FREQUENCY_10MHZ \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_MHZ) +#define DPLL_PIN_FREQUENCY_IRIG_B \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_KHZ) +#define DPLL_PIN_FREQUENCY_DCF77 \ + DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_77_5_KHZ) + +struct dpll_pin_properties { + const char *board_label; + const char *panel_label; + const char *package_label; + enum dpll_pin_type type; + unsigned long capabilities; + u32 freq_supported_num; + struct dpll_pin_frequency *freq_supported; +}; + +struct dpll_device * +dpll_device_get(u64 clock_id, u32 dev_driver_id, struct module *module); + +void dpll_device_put(struct dpll_device *dpll); + +int dpll_device_register(struct dpll_device *dpll, enum dpll_type type, + const struct dpll_device_ops *ops, void *priv); + +void dpll_device_unregister(struct dpll_device *dpll, + const struct dpll_device_ops *ops, void *priv); + +struct dpll_pin * +dpll_pin_get(u64 clock_id, u32 dev_driver_id, struct module *module, + const struct dpll_pin_properties *prop); + +int dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +void dpll_pin_put(struct dpll_pin *pin); + +int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, + const struct dpll_pin_ops *ops, void *priv); + +#endif -- cgit v1.2.3 From 9d71b54b65b1fb6c0d3a6c5c88ba9b915c783fbc Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Wed, 13 Sep 2023 21:49:38 +0100 Subject: dpll: netlink: Add DPLL framework base functions DPLL framework is used to represent and configure DPLL devices in systems. Each device that has DPLL and can configure inputs and outputs can use this framework. Implement dpll netlink framework functions for enablement of dpll subsystem netlink family. Co-developed-by: Milena Olech Signed-off-by: Milena Olech Co-developed-by: Michal Michalik Signed-off-by: Michal Michalik Signed-off-by: Vadim Fedorenko Co-developed-by: Arkadiusz Kubalewski Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/dpll.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dpll.h b/include/linux/dpll.h index b47c3560b937..2202310c10cd 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -130,4 +130,8 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin, void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin, const struct dpll_pin_ops *ops, void *priv); +int dpll_device_change_ntf(struct dpll_device *dpll); + +int dpll_pin_change_ntf(struct dpll_pin *pin); + #endif -- cgit v1.2.3 From 5f18426928800c59fb0f9bc8fb0c182bb6f5ee24 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 13 Sep 2023 21:49:39 +0100 Subject: netdev: expose DPLL pin handle for netdevice In case netdevice represents a SyncE port, the user needs to understand the connection between netdevice and associated DPLL pin. There might me multiple netdevices pointing to the same pin, in case of VF/SF implementation. Add a IFLA Netlink attribute to nest the DPLL pin handle, similar to how it is implemented for devlink port. Add a struct dpll_pin pointer to netdev and protect access to it by RTNL. Expose netdev_dpll_pin_set() and netdev_dpll_pin_clear() helpers to the drivers so they can set/clear the DPLL pin relationship to netdev. Note that during the lifetime of struct dpll_pin the pin handle does not change. Therefore it is save to access it lockless. It is drivers responsibility to call netdev_dpll_pin_clear() before dpll_pin_put(). Signed-off-by: Jiri Pirko Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- include/linux/dpll.h | 15 +++++++++++++++ include/linux/netdevice.h | 21 +++++++++++++++++++++ 2 files changed, 36 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dpll.h b/include/linux/dpll.h index 2202310c10cd..bbc480cd2932 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -101,6 +101,21 @@ struct dpll_pin_properties { struct dpll_pin_frequency *freq_supported; }; +#if IS_ENABLED(CONFIG_DPLL) +size_t dpll_msg_pin_handle_size(struct dpll_pin *pin); +int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin); +#else +static inline size_t dpll_msg_pin_handle_size(struct dpll_pin *pin) +{ + return 0; +} + +static inline int dpll_msg_add_pin_handle(struct sk_buff *msg, struct dpll_pin *pin) +{ + return 0; +} +#endif + struct dpll_device * dpll_device_get(u64 clock_id, u32 dev_driver_id, struct module *module); diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0896aaa91dd7..db3d8429d50d 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -79,6 +79,8 @@ struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; +/* DPLL specific */ +struct dpll_pin; typedef u32 xdp_features_t; @@ -2049,6 +2051,9 @@ enum netdev_ml_priv_type { * SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * + * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, + * where the clock is recovered. + * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ @@ -2405,6 +2410,10 @@ struct net_device { struct rtnl_hw_stats64 *offload_xstats_l3; struct devlink_port *devlink_port; + +#if IS_ENABLED(CONFIG_DPLL) + struct dpll_pin *dpll_pin; +#endif }; #define to_net_dev(d) container_of(d, struct net_device, dev) @@ -3940,6 +3949,18 @@ 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); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); +void netdev_dpll_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin); +void netdev_dpll_pin_clear(struct net_device *dev); + +static inline struct dpll_pin *netdev_dpll_pin(const struct net_device *dev) +{ +#if IS_ENABLED(CONFIG_DPLL) + return dev->dpll_pin; +#else + return NULL; +#endif +} + struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); -- cgit v1.2.3 From 496fd0a26bbf73b6b12407ee4fbe5ff49d659a6d Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 13 Sep 2023 21:49:43 +0100 Subject: mlx5: Implement SyncE support using DPLL infrastructure Implement SyncE support using newly introduced DPLL support. Make sure that each PFs/VFs/SFs probed with appropriate capability will spawn a dpll auxiliary device and register appropriate dpll device and pin instances. Signed-off-by: Jiri Pirko Signed-off-by: Arkadiusz Kubalewski Signed-off-by: Vadim Fedorenko Signed-off-by: David S. Miller --- include/linux/mlx5/driver.h | 2 ++ include/linux/mlx5/mlx5_ifc.h | 59 ++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 60 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3033bbaeac81..92434814c855 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -155,6 +155,8 @@ enum { MLX5_REG_MCC = 0x9062, MLX5_REG_MCDA = 0x9063, MLX5_REG_MCAM = 0x907f, + MLX5_REG_MSECQ = 0x9155, + MLX5_REG_MSEES = 0x9156, MLX5_REG_MIRC = 0x9162, MLX5_REG_SBCAM = 0xB01F, MLX5_REG_RESOURCE_DUMP = 0xC000, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fc3db401f8a2..dd8421d021cf 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10176,7 +10176,9 @@ struct mlx5_ifc_mcam_access_reg_bits2 { u8 mirc[0x1]; u8 regs_97_to_96[0x2]; - u8 regs_95_to_64[0x20]; + u8 regs_95_to_87[0x09]; + u8 synce_registers[0x2]; + u8 regs_84_to_64[0x15]; u8 regs_63_to_32[0x20]; @@ -12549,4 +12551,59 @@ struct mlx5_ifc_modify_page_track_obj_in_bits { struct mlx5_ifc_page_track_bits obj_context; }; +struct mlx5_ifc_msecq_reg_bits { + u8 reserved_at_0[0x20]; + + u8 reserved_at_20[0x12]; + u8 network_option[0x2]; + u8 local_ssm_code[0x4]; + u8 local_enhanced_ssm_code[0x8]; + + u8 local_clock_identity[0x40]; + + u8 reserved_at_80[0x180]; +}; + +enum { + MLX5_MSEES_FIELD_SELECT_ENABLE = BIT(0), + MLX5_MSEES_FIELD_SELECT_ADMIN_STATUS = BIT(1), + MLX5_MSEES_FIELD_SELECT_ADMIN_FREQ_MEASURE = BIT(2), +}; + +enum mlx5_msees_admin_status { + MLX5_MSEES_ADMIN_STATUS_FREE_RUNNING = 0x0, + MLX5_MSEES_ADMIN_STATUS_TRACK = 0x1, +}; + +enum mlx5_msees_oper_status { + MLX5_MSEES_OPER_STATUS_FREE_RUNNING = 0x0, + MLX5_MSEES_OPER_STATUS_SELF_TRACK = 0x1, + MLX5_MSEES_OPER_STATUS_OTHER_TRACK = 0x2, + MLX5_MSEES_OPER_STATUS_HOLDOVER = 0x3, + MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER = 0x4, + MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING = 0x5, +}; + +struct mlx5_ifc_msees_reg_bits { + u8 reserved_at_0[0x8]; + u8 local_port[0x8]; + u8 pnat[0x2]; + u8 lp_msb[0x2]; + u8 reserved_at_14[0xc]; + + u8 field_select[0x20]; + + u8 admin_status[0x4]; + u8 oper_status[0x4]; + u8 ho_acq[0x1]; + u8 reserved_at_49[0xc]; + u8 admin_freq_measure[0x1]; + u8 oper_freq_measure[0x1]; + u8 failure_reason[0x9]; + + u8 frequency_diff[0x20]; + + u8 reserved_at_80[0x180]; +}; + #endif /* MLX5_IFC_H */ -- cgit v1.2.3 From ac5f395685bd16ca30c1c834dcbf8b555605ccae Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 13 Sep 2023 09:12:40 +0200 Subject: net/mlx5: SF, Implement peer devlink set for SF representor devlink port Benefit from the existence of internal mlx5 notifier and extend it by event MLX5_DRIVER_EVENT_SF_PEER_DEVLINK. Use this event from SF auxiliary device probe/remove functions to pass the registered SF devlink instance to the SF representor. Process the new event in SF representor code and call devl_port_fn_devlink_set() to do the assignments. Implement this in work to avoid possible deadlock when probe/remove function of SF may be called with devlink instance lock held during devlink reload. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/linux/mlx5/device.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4d5be378fa8c..8fbe22de16ef 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -366,6 +366,7 @@ enum mlx5_driver_event { MLX5_DRIVER_EVENT_UPLINK_NETDEV, MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, + MLX5_DRIVER_EVENT_SF_PEER_DEVLINK, }; enum { -- cgit v1.2.3 From f7b5bd725b737de3f2c4a836e07c82ba156d75df Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Thu, 14 Sep 2023 15:31:57 -0700 Subject: pds_core: check health in devcmd wait Similar to what we do in the AdminQ, check for devcmd health while waiting for an answer. Signed-off-by: Shannon Nelson Reviewed-by: Brett Creeley Signed-off-by: David S. Miller --- include/linux/pds/pds_core_if.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pds/pds_core_if.h b/include/linux/pds/pds_core_if.h index e838a2b90440..17a87c1a55d7 100644 --- a/include/linux/pds/pds_core_if.h +++ b/include/linux/pds/pds_core_if.h @@ -79,6 +79,7 @@ enum pds_core_status_code { PDS_RC_EVFID = 31, /* VF ID does not exist */ PDS_RC_BAD_FW = 32, /* FW file is invalid or corrupted */ PDS_RC_ECLIENT = 33, /* No such client id */ + PDS_RC_BAD_PCI = 255, /* Broken PCI when reading status */ }; /** -- cgit v1.2.3 From 1cb6422ecac8804ebe0b71f4b3440674955fec73 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 15 Sep 2023 13:15:10 -0700 Subject: ceph: Annotate struct ceph_monmap with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct ceph_monmap. Additionally, since the element count member must be set before accessing the annotated flexible array member, move its initialization earlier. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Ilya Dryomov Cc: Xiubo Li Cc: Jeff Layton Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: ceph-devel@vger.kernel.org Cc: netdev@vger.kernel.org Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Reviewed-by: Xiubo Li Signed-off-by: David S. Miller --- include/linux/ceph/mon_client.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h index b658961156a0..7a9a40163c0f 100644 --- a/include/linux/ceph/mon_client.h +++ b/include/linux/ceph/mon_client.h @@ -19,7 +19,7 @@ struct ceph_monmap { struct ceph_fsid fsid; u32 epoch; u32 num_mon; - struct ceph_entity_inst mon_inst[]; + struct ceph_entity_inst mon_inst[] __counted_by(num_mon); }; struct ceph_mon_client; -- cgit v1.2.3 From 8452a05b2c633b708dbe3e742f71b24bf21fe42d Mon Sep 17 00:00:00 2001 From: Rohan G Thomas Date: Sat, 16 Sep 2023 14:33:12 +0800 Subject: net: stmmac: Tx coe sw fallback Add sw fallback of tx checksum calculation for those tx queues that don't support tx checksum offloading. DW xGMAC IP can be synthesized such that it can support tx checksum offloading only for a few initial tx queues. Also as Serge pointed out, for the DW QoS IP, tx coe can be individually configured for each tx queue. So when tx coe is enabled, for any tx queue that doesn't support tx coe with 'coe-unsupported' flag set will have a sw fallback happen in the driver for tx checksum calculation when any packets to be transmitted on these tx queues. Signed-off-by: Rohan G Thomas Signed-off-by: David S. Miller --- include/linux/stmmac.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index ce89cc3e4913..c0079a7574ae 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -139,6 +139,7 @@ struct stmmac_rxq_cfg { struct stmmac_txq_cfg { u32 weight; + bool coe_unsupported; u8 mode_to_use; /* Credit Base Shaper parameters */ u32 send_slope; -- cgit v1.2.3 From 6a23c555f7eb436d6799533675ffa179db3d5834 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 18 Sep 2023 14:25:36 +0100 Subject: net: phy: fix regression with AX88772A PHY driver Marek reports that a deadlock occurs with the AX88772A PHY used on the ASIX USB network driver: asix 1-1.4:1.0 (unnamed net_device) (uninitialized): PHY [usb-001:003:10] driver [Asix Electronics AX88772A] (irq=POLL) Asix Electronics AX88772A usb-001:003:10: attached PHY driver(mii_bus:phy_addr=usb-001:003:10, irq=POLL) asix 1-1.4:1.0 eth0: register 'asix' at usb-12110000.usb-1.4, ASIX AX88772 USB 2.0 Ethernet, a2:99:b6:cd:11:eb asix 1-1.4:1.0 eth0: configuring for phy/internal link mode ============================================ WARNING: possible recursive locking detected 6.6.0-rc1-00239-g8da77df649c4-dirty #13949 Not tainted -------------------------------------------- kworker/3:3/71 is trying to acquire lock: c6c704cc (&dev->lock){+.+.}-{3:3}, at: phy_start_aneg+0x1c/0x38 but task is already holding lock: c6c704cc (&dev->lock){+.+.}-{3:3}, at: phy_state_machine+0x100/0x2b8 This is because we now consistently call phy_process_state_change() while holding phydev->lock, but the AX88772A PHY driver then goes on to call phy_start_aneg() which tries to grab the same lock - causing deadlock. Fix this by exporting the unlocked version, and use this in the PHY driver instead. Reported-by: Marek Szyprowski Tested-by: Marek Szyprowski Fixes: ef113a60d0a9 ("net: phy: call phy_error_precise() while holding the lock") Signed-off-by: Russell King (Oracle) Reviewed-by: Andrew Lunn Link: https://lore.kernel.org/r/E1qiEFs-007g7b-Lq@rmk-PC.armlinux.org.uk Signed-off-by: Paolo Abeni --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 1351b802ffcf..3cc52826f18e 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1736,6 +1736,7 @@ void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_config_aneg(struct phy_device *phydev); +int _phy_start_aneg(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_speed_down(struct phy_device *phydev, bool sync); -- cgit v1.2.3 From fa17a6d8a5bd0cd7565b613cb804242cd0f6b7ab Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 18 Sep 2023 14:23:21 +0000 Subject: ipv6: lockless IPV6_ADDR_PREFERENCES implementation We have data-races while reading np->srcprefs Switch the field to a plain byte, add READ_ONCE() and WRITE_ONCE() annotations where needed, and IPV6_ADDR_PREFERENCES setsockopt() can now be lockless. Signed-off-by: Eric Dumazet Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230918142321.1794107-1-edumazet@google.com Signed-off-by: Paolo Abeni --- include/linux/ipv6.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 09253825c99c..e400ff757f13 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -243,7 +243,7 @@ struct ipv6_pinfo { } rxopt; /* sockopt flags */ - __u8 srcprefs:3; /* 001: prefer temporary address + __u8 srcprefs; /* 001: prefer temporary address * 010: prefer public address * 100: prefer care-of address */ -- cgit v1.2.3 From bafd764a8baa87e19e6beeaa58eb85fcbbdd6b20 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 18 Sep 2023 12:29:07 +0200 Subject: net: ethernet: mtk_wed: rename mtk_rxbm_desc in mtk_wed_bm_desc Rename mtk_rxbm_desc structure in mtk_wed_bm_desc since it will be used even on tx side by MT7988 SoC. Signed-off-by: Lorenzo Bianconi Signed-off-by: Paolo Abeni --- include/linux/soc/mediatek/mtk_wed.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index b2b28180dff7..c6512c216b27 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -45,7 +45,7 @@ enum mtk_wed_wo_cmd { MTK_WED_WO_CMD_WED_END }; -struct mtk_rxbm_desc { +struct mtk_wed_bm_desc { __le32 buf0; __le32 token; } __packed __aligned(4); @@ -104,7 +104,7 @@ struct mtk_wed_device { struct { int size; - struct mtk_rxbm_desc *desc; + struct mtk_wed_bm_desc *desc; dma_addr_t desc_phys; } rx_buf_ring; -- cgit v1.2.3 From ff0ea57fa30e860d3373acd1383e9d9599144b58 Mon Sep 17 00:00:00 2001 From: Lorenzo Bianconi Date: Mon, 18 Sep 2023 12:29:08 +0200 Subject: net: ethernet: mtk_wed: introduce mtk_wed_buf structure Introduce mtk_wed_buf structure to store both virtual and physical addresses allocated in mtk_wed_tx_buffer_alloc() routine. This is a preliminary patch to add WED support for MT7988 SoC since it relies on a different dma descriptor layout not storing page dma addresses. Co-developed-by: Sujuan Chen Signed-off-by: Sujuan Chen Signed-off-by: Lorenzo Bianconi Signed-off-by: Paolo Abeni --- include/linux/soc/mediatek/mtk_wed.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index c6512c216b27..5f00dc26582b 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -76,6 +76,11 @@ struct mtk_wed_wo_rx_stats { __le32 rx_drop_cnt; }; +struct mtk_wed_buf { + void *p; + dma_addr_t phy_addr; +}; + struct mtk_wed_device { #ifdef CONFIG_NET_MEDIATEK_SOC_WED const struct mtk_wed_ops *ops; @@ -97,7 +102,7 @@ struct mtk_wed_device { struct { int size; - void **pages; + struct mtk_wed_buf *pages; struct mtk_wdma_desc *desc; dma_addr_t desc_phys; } tx_buf_ring; -- cgit v1.2.3 From e2f64db13aa1d08e32621067e4fe16bbc114b375 Mon Sep 17 00:00:00 2001 From: Sujuan Chen Date: Mon, 18 Sep 2023 12:29:13 +0200 Subject: net: ethernet: mtk_wed: introduce WED support for MT7988 Similar to MT7986 and MT7622, enable Wireless Ethernet Ditpatcher for MT7988 in order to offload traffic forwarded from LAN/WLAN to WLAN/LAN Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Sujuan Chen Signed-off-by: Paolo Abeni --- include/linux/soc/mediatek/mtk_wed.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 5f00dc26582b..5b096f9f1975 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -138,6 +138,8 @@ struct mtk_wed_device { u32 wpdma_rx; bool wcid_512; + bool hw_rro; + bool msi; u16 token_start; unsigned int nbuf; @@ -211,10 +213,12 @@ mtk_wed_device_attach(struct mtk_wed_device *dev) return ret; } -static inline bool -mtk_wed_get_rx_capa(struct mtk_wed_device *dev) +static inline bool mtk_wed_get_rx_capa(struct mtk_wed_device *dev) { #ifdef CONFIG_NET_MEDIATEK_SOC_WED + if (dev->version == 3) + return dev->wlan.hw_rro; + return dev->version != 1; #else return false; -- cgit v1.2.3 From b230812b9dda125e69ab0a5a11cda88d9c0d18a9 Mon Sep 17 00:00:00 2001 From: Sujuan Chen Date: Mon, 18 Sep 2023 12:29:15 +0200 Subject: net: ethernet: mtk_wed: introduce partial AMSDU offload support for MT7988 Introduce partial AMSDU offload support for MT7988 SoC in order to merge in hw packets belonging to the same AMSDU before passing them to the WLAN nic. Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Sujuan Chen Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 1 + include/linux/soc/mediatek/mtk_wed.h | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index db3d8429d50d..7e520c14eb8c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -919,6 +919,7 @@ struct net_device_path { u8 queue; u16 wcid; u8 bss; + u8 amsdu; } mtk_wdma; }; }; diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 5b096f9f1975..90d9c9ead3bc 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -128,6 +128,7 @@ struct mtk_wed_device { enum mtk_wed_bus_tye bus_type; void __iomem *base; u32 phy_base; + u32 id; u32 wpdma_phys; u32 wpdma_int; @@ -146,10 +147,12 @@ struct mtk_wed_device { unsigned int rx_nbuf; unsigned int rx_npkt; unsigned int rx_size; + unsigned int amsdu_max_len; u8 tx_tbit[MTK_WED_TX_QUEUES]; u8 rx_tbit[MTK_WED_RX_QUEUES]; u8 txfree_tbit; + u8 amsdu_max_subframes; u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); int (*offload_enable)(struct mtk_wed_device *wed); @@ -225,6 +228,15 @@ static inline bool mtk_wed_get_rx_capa(struct mtk_wed_device *dev) #endif } +static inline bool mtk_wed_is_amsdu_supported(struct mtk_wed_device *dev) +{ +#ifdef CONFIG_NET_MEDIATEK_SOC_WED + return dev->version == 3; +#else + return false; +#endif +} + #ifdef CONFIG_NET_MEDIATEK_SOC_WED #define mtk_wed_device_active(_dev) !!(_dev)->ops #define mtk_wed_device_detach(_dev) (_dev)->ops->detach(_dev) -- cgit v1.2.3 From 6757d345dd7dba795f5af44d4442d55a83c4b1b4 Mon Sep 17 00:00:00 2001 From: Sujuan Chen Date: Mon, 18 Sep 2023 12:29:16 +0200 Subject: net: ethernet: mtk_wed: introduce hw_rro support for MT7988 MT7988 SoC support 802.11 receive reordering offload in hw while MT7986 SoC implements it through the firmware running on the mcu. Co-developed-by: Lorenzo Bianconi Signed-off-by: Lorenzo Bianconi Signed-off-by: Sujuan Chen Signed-off-by: Paolo Abeni --- include/linux/soc/mediatek/mtk_wed.h | 45 ++++++++++++++++++++++++++++++++++++ 1 file changed, 45 insertions(+) (limited to 'include/linux') diff --git a/include/linux/soc/mediatek/mtk_wed.h b/include/linux/soc/mediatek/mtk_wed.h index 90d9c9ead3bc..a476648858a6 100644 --- a/include/linux/soc/mediatek/mtk_wed.h +++ b/include/linux/soc/mediatek/mtk_wed.h @@ -10,6 +10,7 @@ #define MTK_WED_TX_QUEUES 2 #define MTK_WED_RX_QUEUES 2 +#define MTK_WED_RX_PAGE_QUEUES 3 #define WED_WO_STA_REC 0x6 @@ -99,6 +100,9 @@ struct mtk_wed_device { struct mtk_wed_ring txfree_ring; struct mtk_wed_ring tx_wdma[MTK_WED_TX_QUEUES]; struct mtk_wed_ring rx_wdma[MTK_WED_RX_QUEUES]; + struct mtk_wed_ring rx_rro_ring[MTK_WED_RX_QUEUES]; + struct mtk_wed_ring rx_page_ring[MTK_WED_RX_PAGE_QUEUES]; + struct mtk_wed_ring ind_cmd_ring; struct { int size; @@ -119,6 +123,13 @@ struct mtk_wed_device { dma_addr_t fdbk_phys; } rro; + struct { + int size; + struct mtk_wed_buf *pages; + struct mtk_wed_bm_desc *desc; + dma_addr_t desc_phys; + } hw_rro; + /* filled by driver: */ struct { union { @@ -137,6 +148,8 @@ struct mtk_wed_device { u32 wpdma_txfree; u32 wpdma_rx_glo; u32 wpdma_rx; + u32 wpdma_rx_rro[MTK_WED_RX_QUEUES]; + u32 wpdma_rx_pg; bool wcid_512; bool hw_rro; @@ -151,9 +164,20 @@ struct mtk_wed_device { u8 tx_tbit[MTK_WED_TX_QUEUES]; u8 rx_tbit[MTK_WED_RX_QUEUES]; + u8 rro_rx_tbit[MTK_WED_RX_QUEUES]; + u8 rx_pg_tbit[MTK_WED_RX_PAGE_QUEUES]; u8 txfree_tbit; u8 amsdu_max_subframes; + struct { + u8 se_group_nums; + u16 win_size; + u16 particular_sid; + u32 ack_sn_addr; + dma_addr_t particular_se_phys; + dma_addr_t addr_elem_phys[1024]; + } ind_cmd; + u32 (*init_buf)(void *ptr, dma_addr_t phys, int token_id); int (*offload_enable)(struct mtk_wed_device *wed); void (*offload_disable)(struct mtk_wed_device *wed); @@ -192,6 +216,14 @@ struct mtk_wed_ops { void (*irq_set_mask)(struct mtk_wed_device *dev, u32 mask); int (*setup_tc)(struct mtk_wed_device *wed, struct net_device *dev, enum tc_setup_type type, void *type_data); + void (*start_hw_rro)(struct mtk_wed_device *dev, u32 irq_mask, + bool reset); + void (*rro_rx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + void (*msdu_pg_rx_ring_setup)(struct mtk_wed_device *dev, int ring, + void __iomem *regs); + int (*ind_rx_ring_setup)(struct mtk_wed_device *dev, + void __iomem *regs); }; extern const struct mtk_wed_ops __rcu *mtk_soc_wed_ops; @@ -263,6 +295,15 @@ static inline bool mtk_wed_is_amsdu_supported(struct mtk_wed_device *dev) #define mtk_wed_device_dma_reset(_dev) (_dev)->ops->reset_dma(_dev) #define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) \ (_dev)->ops->setup_tc(_dev, _netdev, _type, _type_data) +#define mtk_wed_device_start_hw_rro(_dev, _mask, _reset) \ + (_dev)->ops->start_hw_rro(_dev, _mask, _reset) +#define mtk_wed_device_rro_rx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->rro_rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_msdu_pg_rx_ring_setup(_dev, _ring, _regs) \ + (_dev)->ops->msdu_pg_rx_ring_setup(_dev, _ring, _regs) +#define mtk_wed_device_ind_rx_ring_setup(_dev, _regs) \ + (_dev)->ops->ind_rx_ring_setup(_dev, _regs) + #else static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) { @@ -282,6 +323,10 @@ static inline bool mtk_wed_device_active(struct mtk_wed_device *dev) #define mtk_wed_device_stop(_dev) do {} while (0) #define mtk_wed_device_dma_reset(_dev) do {} while (0) #define mtk_wed_device_setup_tc(_dev, _netdev, _type, _type_data) -EOPNOTSUPP +#define mtk_wed_device_start_hw_rro(_dev, _mask, _reset) do {} while (0) +#define mtk_wed_device_rro_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_msdu_pg_rx_ring_setup(_dev, _ring, _regs) -ENODEV +#define mtk_wed_device_ind_rx_ring_setup(_dev, _regs) -ENODEV #endif #endif -- cgit v1.2.3 From 653b7eb9d74426397c95061fd57da3063625af65 Mon Sep 17 00:00:00 2001 From: Erez Shitrit Date: Mon, 28 Aug 2023 14:20:00 +0300 Subject: net/mlx5: Bridge, Enable mcast in smfs steering mode In order to have mcast offloads the driver needs the following: It should know if that mcast comes from wire port, in addition the flow should not be marked as any specific source, that way it will give the flexibility for the driver not to be depended on the way iterator implemented in the FW. Signed-off-by: Erez Shitrit Reviewed-by: Moshe Shemesh Reviewed-by: Vlad Buslov Signed-off-by: Saeed Mahameed --- include/linux/mlx5/fs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h index 1e00c2436377..6f7725238abc 100644 --- a/include/linux/mlx5/fs.h +++ b/include/linux/mlx5/fs.h @@ -67,6 +67,7 @@ enum { MLX5_FLOW_TABLE_TERMINATION = BIT(2), MLX5_FLOW_TABLE_UNMANAGED = BIT(3), MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4), + MLX5_FLOW_TABLE_UPLINK_VPORT = BIT(5), }; #define LEFTOVERS_RULE_NUM 2 -- cgit v1.2.3 From e0cc92fd945a9c8e43d4268cf1ea985d0e99a90f Mon Sep 17 00:00:00 2001 From: Moshe Shemesh Date: Thu, 3 Aug 2023 16:39:40 +0300 Subject: net/mlx5: Add a health error syndrome for pci data poisoned Add new health error syndrome to indicate that pci data poisoned error has been received while fetching device ICM data. Signed-off-by: Moshe Shemesh Reviewed-by: Shay Drory Signed-off-by: Saeed Mahameed --- include/linux/mlx5/mlx5_ifc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index dd8421d021cf..b23d8ff286a1 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10574,6 +10574,7 @@ enum { MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV = 0xe, MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR = 0xf, MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR = 0x10, + MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR = 0x12, }; struct mlx5_ifc_initial_seg_bits { -- cgit v1.2.3 From 0df7cd3c13e44d01f9f28e29cbce74e2931b00fe Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Sat, 16 Sep 2023 16:09:15 +0300 Subject: vsock/virtio/vhost: read data from non-linear skb This is preparation patch for MSG_ZEROCOPY support. It adds handling of non-linear skbs by replacing direct calls of 'memcpy_to_msg()' with 'skb_copy_datagram_iter()'. Main advantage of the second one is that it can handle paged part of the skb by using 'kmap()' on each page, but if there are no pages in the skb, it behaves like simple copying to iov iterator. This patch also adds new field to the control block of skb - this value shows current offset in the skb to read next portion of data (it doesn't matter linear it or not). Idea behind this field is that 'skb_copy_datagram_iter()' handles both types of skb internally - it just needs an offset from which to copy data from the given skb. This offset is incremented on each read from skb. This approach allows to simplify handling of both linear and non-linear skbs, because for linear skb we need to call 'skb_pull()' after reading data from it, while in non-linear case we need to update 'data_len'. Signed-off-by: Arseniy Krasnov Reviewed-by: Stefano Garzarella Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- include/linux/virtio_vsock.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index c58453699ee9..a91fbdf233e4 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -12,6 +12,7 @@ struct virtio_vsock_skb_cb { bool reply; bool tap_delivered; + u32 offset; }; #define VIRTIO_VSOCK_SKB_CB(skb) ((struct virtio_vsock_skb_cb *)((skb)->cb)) -- cgit v1.2.3 From 581512a6dc939ef122e49336626ae159f3b8a345 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Sat, 16 Sep 2023 16:09:18 +0300 Subject: vsock/virtio: MSG_ZEROCOPY flag support This adds handling of MSG_ZEROCOPY flag on transmission path: 1) If this flag is set and zerocopy transmission is possible (enabled in socket options and transport allows zerocopy), then non-linear skb will be created and filled with the pages of user's buffer. Pages of user's buffer are locked in memory by 'get_user_pages()'. 2) Replaces way of skb owning: instead of 'skb_set_owner_sk_safe()' it calls 'skb_set_owner_w()'. Reason of this change is that '__zerocopy_sg_from_iter()' increments 'sk_wmem_alloc' of socket, so to decrease this field correctly, proper skb destructor is needed: 'sock_wfree()'. This destructor is set by 'skb_set_owner_w()'. 3) Adds new callback to 'struct virtio_transport': 'can_msgzerocopy'. If this callback is set, then transport needs extra check to be able to send provided number of buffers in zerocopy mode. Currently, the only transport that needs this callback set is virtio, because this transport adds new buffers to the virtio queue and we need to check, that number of these buffers is less than size of the queue (it is required by virtio spec). vhost and loopback transports don't need this check. Signed-off-by: Arseniy Krasnov Reviewed-by: Stefano Garzarella Acked-by: Michael S. Tsirkin Signed-off-by: Paolo Abeni --- include/linux/virtio_vsock.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h index a91fbdf233e4..ebb3ce63d64d 100644 --- a/include/linux/virtio_vsock.h +++ b/include/linux/virtio_vsock.h @@ -160,6 +160,15 @@ struct virtio_transport { /* Takes ownership of the packet */ int (*send_pkt)(struct sk_buff *skb); + + /* Used in MSG_ZEROCOPY mode. Checks, that provided data + * (number of buffers) could be transmitted with zerocopy + * mode. If this callback is not implemented for the current + * transport - this means that this transport doesn't need + * extra checks and can perform zerocopy transmission by + * default. + */ + bool (*can_msgzerocopy)(int bufs_num); }; ssize_t -- cgit v1.2.3 From b3239498353484fd6ddeb513df89c4628cd623d0 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Sep 2023 21:25:12 +0300 Subject: wifi: mac80211: use bandwidth indication element for CSA In CSA, parse the (EHT) bandwidth indication element and use it (in fact prefer it if present). Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230920211508.43ef01920556.If4f24a61cd634ab1e50eba43899b9e992bf25602@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 340d7e0f6bf7..f11b7022d9eb 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -3139,6 +3139,28 @@ ieee80211_eht_oper_size_ok(const u8 *data, u8 len) return len >= needed; } +#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT BIT(1) + +struct ieee80211_bandwidth_indication { + u8 params; + struct ieee80211_eht_operation_info info; +} __packed; + +static inline bool +ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len) +{ + const struct ieee80211_bandwidth_indication *bwi = (const void *)data; + + if (len < sizeof(*bwi)) + return false; + + if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT && + len < sizeof(*bwi) + 2) + return false; + + return true; +} + #define LISTEN_INT_USF GENMASK(15, 14) #define LISTEN_INT_UI GENMASK(13, 0) @@ -3596,6 +3618,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_EHT_OPERATION = 106, WLAN_EID_EXT_EHT_MULTI_LINK = 107, WLAN_EID_EXT_EHT_CAPABILITY = 108, + WLAN_EID_EXT_BANDWIDTH_INDICATION = 135, }; /* Action category code */ -- cgit v1.2.3 From 62e9c64eedfeb697ba28081ccaac59a45f9a96e1 Mon Sep 17 00:00:00 2001 From: Ayala Beker Date: Wed, 20 Sep 2023 21:25:24 +0300 Subject: wifi: mac80211: add support for parsing TID to Link mapping element Add the relevant definitions for TID to Link mapping element according to the P802.11be_D4.0. Signed-off-by: Ayala Beker Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230920211508.9ea9b0b4412a.I2281ab2c70e8b43a39032dc115db6a80f1f0b3f4@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 58 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f11b7022d9eb..f2965ff3d7c1 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1246,6 +1246,30 @@ struct ieee80211_twt_setup { u8 params[]; } __packed; +#define IEEE80211_TTLM_MAX_CNT 2 +#define IEEE80211_TTLM_CONTROL_DIRECTION 0x03 +#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP 0x04 +#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT 0x08 +#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT 0x10 +#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE 0x20 + +#define IEEE80211_TTLM_DIRECTION_DOWN 0 +#define IEEE80211_TTLM_DIRECTION_UP 1 +#define IEEE80211_TTLM_DIRECTION_BOTH 2 + +/** + * struct ieee80211_ttlm_elem - TID-To-Link Mapping element + * + * Defined in section 9.4.2.314 in P802.11be_D4 + * + * @control: the first part of control field + * @optional: the second part of control field + */ +struct ieee80211_ttlm_elem { + u8 control; + u8 optional[]; +} __packed; + struct ieee80211_mgmt { __le16 frame_control; __le16 duration; @@ -3618,6 +3642,7 @@ enum ieee80211_eid_ext { WLAN_EID_EXT_EHT_OPERATION = 106, WLAN_EID_EXT_EHT_MULTI_LINK = 107, WLAN_EID_EXT_EHT_CAPABILITY = 108, + WLAN_EID_EXT_TID_TO_LINK_MAPPING = 109, WLAN_EID_EXT_BANDWIDTH_INDICATION = 135, }; @@ -5155,6 +5180,39 @@ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data, fixed + prof->sta_info_len - 1 <= len; } +static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len) +{ + const struct ieee80211_ttlm_elem *t2l = (const void *)data; + u8 control, fixed = sizeof(*t2l), elem_len = 0; + + if (len < fixed) + return false; + + control = t2l->control; + + if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT) + elem_len += 2; + if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT) + elem_len += 3; + + if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) { + u8 bm_size; + + elem_len += 1; + if (len < fixed + elem_len) + return false; + + if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE) + bm_size = 1; + else + bm_size = 2; + + elem_len += hweight8(t2l->optional[0]) * bm_size; + } + + return len >= fixed + elem_len; +} + #define for_each_mle_subelement(_elem, _data, _len) \ if (ieee80211_mle_size_ok(_data, _len)) \ for_each_element(_elem, \ -- cgit v1.2.3 From ef246a1480cc484cd2aeda75737cb0848616ddf3 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Wed, 20 Sep 2023 21:25:26 +0300 Subject: wifi: mac80211: support antenna control in injection Support antenna control for injection by parsing the antenna radiotap field (which may be presented multiple times) and telling the driver about the resulting antenna bitmap. Of course there's no guarantee the driver will actually honour this, just like any other injection control. If misconfigured, i.e. the injected HT/VHT MCS needs more chains than antennas are configured, the bitmap is reset to zero, indicating no selection. For now this is only set up for two anntenas so we keep more free bits, but that can be trivially extended if any driver implements support for it that can deal with hardware with more antennas. Signed-off-by: Johannes Berg Signed-off-by: Gregory Greenman Link: https://lore.kernel.org/r/20230920211508.f71001aa4da9.I00ccb762a806ea62bc3d728fa3a0d29f4f285eeb@changeid Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index f2965ff3d7c1..3b02f038d509 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1705,6 +1705,8 @@ struct ieee80211_mcs_info { #define IEEE80211_HT_MCS_TX_MAX_STREAMS 4 #define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION 0x10 +#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3))) + /* * 802.11n D5.0 20.3.5 / 20.6 says: * - indices 0 to 7 and 32 are single spatial stream -- cgit v1.2.3 From 823a0258912b1a4f627e455bee7e78d349c29c5b Mon Sep 17 00:00:00 2001 From: Po-Hao Huang Date: Mon, 25 Sep 2023 16:08:59 +0800 Subject: wifi: ieee80211: add UL-bandwidth definition of trigger frame Define UL-bandwidth values of trigger frame according to 802.11 std. Signed-off-by: Po-Hao Huang Signed-off-by: Ping-Ke Shih Link: https://lore.kernel.org/r/20230925080902.51449-2-pkshih@realtek.com Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 3b02f038d509..62b4469c6866 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -307,6 +307,13 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2) #define IEEE80211_TRIGGER_TYPE_BQRP 0x6 #define IEEE80211_TRIGGER_TYPE_NFRP 0x7 +/* UL-bandwidth within common_info of trigger frame */ +#define IEEE80211_TRIGGER_ULBW_MASK 0xc0000 +#define IEEE80211_TRIGGER_ULBW_20MHZ 0x0 +#define IEEE80211_TRIGGER_ULBW_40MHZ 0x1 +#define IEEE80211_TRIGGER_ULBW_80MHZ 0x2 +#define IEEE80211_TRIGGER_ULBW_160_80P80MHZ 0x3 + struct ieee80211_hdr { __le16 frame_control; __le16 duration_id; -- cgit v1.2.3 From 3acf8ace68230e9558cf916847f1cc9f208abdf1 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:39 +0200 Subject: bpf: Add missed value to kprobe perf link info Add missed value to kprobe attached through perf link info to hold the stats of missed kprobe handler execution. The kprobe's missed counter gets incremented when kprobe handler is not executed due to another kprobe running on the same cpu. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20230920213145.1941596-4-jolsa@kernel.org --- include/linux/trace_events.h | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index 21ae37e49319..5eb88a66eb68 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -761,7 +761,8 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name); void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp); int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, - u64 *probe_offset, u64 *probe_addr); + u64 *probe_offset, u64 *probe_addr, + unsigned long *missed); int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); #else @@ -801,7 +802,7 @@ static inline void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) static inline int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, u32 *fd_type, const char **buf, u64 *probe_offset, - u64 *probe_addr) + u64 *probe_addr, unsigned long *missed) { return -EOPNOTSUPP; } @@ -877,6 +878,7 @@ extern void perf_kprobe_destroy(struct perf_event *event); extern int bpf_get_kprobe_info(const struct perf_event *event, u32 *fd_type, const char **symbol, u64 *probe_offset, u64 *probe_addr, + unsigned long *missed, bool perf_type_tracepoint); #endif #ifdef CONFIG_UPROBE_EVENTS -- cgit v1.2.3 From dd8657894c11b03c6eb0fd53fe9d7fec2072d18b Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Wed, 20 Sep 2023 23:31:40 +0200 Subject: bpf: Count missed stats in trace_call_bpf Increase misses stats in case bpf array execution is skipped because of recursion check in trace_call_bpf. Adding bpf_prog_inc_misses_counters that increase misses counts for all bpf programs in bpf_prog_array. Signed-off-by: Jiri Olsa Signed-off-by: Andrii Nakryiko Tested-by: Song Liu Reviewed-by: Song Liu Link: https://lore.kernel.org/bpf/20230920213145.1941596-5-jolsa@kernel.org --- include/linux/bpf.h | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 30063a760b5a..a82efd34b741 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2922,6 +2922,22 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr, #endif /* CONFIG_BPF_SYSCALL */ #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */ +static __always_inline void +bpf_prog_inc_misses_counters(const struct bpf_prog_array *array) +{ + const struct bpf_prog_array_item *item; + struct bpf_prog *prog; + + if (unlikely(!array)) + return; + + item = &array->items[0]; + while ((prog = READ_ONCE(item->prog))) { + bpf_prog_inc_misses_counter(prog); + item++; + } +} + #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) void bpf_sk_reuseport_detach(struct sock *sk); int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key, -- cgit v1.2.3 From 5aa4c9608d2d5fea29e211a80c29696f7d94e9f7 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Mon, 11 Sep 2023 12:38:48 +0300 Subject: net/mlx5: Introduce ifc bits for migration in a chunk mode Introduce ifc related stuff to enable migration in a chunk mode. Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20230911093856.81910-2-yishaih@nvidia.com Reviewed-by: Jason Gunthorpe Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index fc3db401f8a2..3265bfcb3156 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1948,7 +1948,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_c0[0x8]; u8 migration_multi_load[0x1]; u8 migration_tracking_state[0x1]; - u8 reserved_at_ca[0x16]; + u8 reserved_at_ca[0x6]; + u8 migration_in_chunks[0x1]; + u8 reserved_at_d1[0xf]; u8 reserved_at_e0[0xc0]; @@ -12392,7 +12394,8 @@ struct mlx5_ifc_query_vhca_migration_state_in_bits { u8 op_mod[0x10]; u8 incremental[0x1]; - u8 reserved_at_41[0xf]; + u8 chunk[0x1]; + u8 reserved_at_42[0xe]; u8 vhca_id[0x10]; u8 reserved_at_60[0x20]; @@ -12408,7 +12411,11 @@ struct mlx5_ifc_query_vhca_migration_state_out_bits { u8 required_umem_size[0x20]; - u8 reserved_at_a0[0x160]; + u8 reserved_at_a0[0x20]; + + u8 remaining_total_size[0x40]; + + u8 reserved_at_100[0x100]; }; struct mlx5_ifc_save_vhca_state_in_bits { @@ -12440,7 +12447,7 @@ struct mlx5_ifc_save_vhca_state_out_bits { u8 actual_image_size[0x20]; - u8 reserved_at_60[0x20]; + u8 next_required_umem_size[0x20]; }; struct mlx5_ifc_load_vhca_state_in_bits { -- cgit v1.2.3 From fce9c967820a72f600abbf061d7077861685a14d Mon Sep 17 00:00:00 2001 From: Ingo Rohloff Date: Sat, 26 Aug 2023 22:02:41 +0200 Subject: wifi: mt76: mt7921e: Support MT7992 IP in Xiaomi Redmibook 15 Pro (2023) In the Xiaomi Redmibook 15 Pro (2023) laptop I have got, a wifi chip is used, which according to its PCI Vendor ID is from "ITTIM Technology". This chip works flawlessly with the mt7921e module. The driver doesn't bind to this PCI device, because the Vendor ID from "ITTIM Technology" is not recognized. This patch adds the PCI Vendor ID from "ITTIM Technology" to the list of PCI Vendor IDs and lets the mt7921e driver bind to the mentioned wifi chip. Signed-off-by: Ingo Rohloff Signed-off-by: Felix Fietkau --- include/linux/pci_ids.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index 2dc75df1437f..6ae1803bcd2f 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -180,6 +180,8 @@ #define PCI_DEVICE_ID_BERKOM_A4T 0xffa4 #define PCI_DEVICE_ID_BERKOM_SCITEL_QUADRO 0xffa8 +#define PCI_VENDOR_ID_ITTIM 0x0b48 + #define PCI_VENDOR_ID_COMPAQ 0x0e11 #define PCI_DEVICE_ID_COMPAQ_TOKENRING 0x0508 #define PCI_DEVICE_ID_COMPAQ_TACHYON 0xa0fc -- cgit v1.2.3 From 0b068c714ca9479d2783cc333fff5bc2d4a6d45c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 21 Sep 2023 08:52:16 +0000 Subject: net: add DEV_STATS_READ() helper Companion of DEV_STATS_INC() & DEV_STATS_ADD(). This is going to be used in the series. Use it in macsec_get_stats64(). Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7e520c14eb8c..e070a4540fba 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -5236,5 +5236,6 @@ extern struct net_device *blackhole_netdev; #define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) #define DEV_STATS_ADD(DEV, FIELD, VAL) \ atomic_long_add((VAL), &(DEV)->stats.__##FIELD) +#define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD) #endif /* _LINUX_NETDEVICE_H */ -- cgit v1.2.3 From 0d293714ac32650bfb669ceadf7cc2fad8161401 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 21 Sep 2023 15:10:27 +0300 Subject: RDMA/mlx5: Send events from IB driver about device affiliation state Send blocking events from IB driver whenever the device is done being affiliated or if it is removed from an affiliation. This is useful since now the EN driver can register to those event and know when a device is affiliated or not. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://lore.kernel.org/r/a7491c3e483cfd8d962f5f75b9a25f253043384a.1695296682.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/device.h | 2 ++ include/linux/mlx5/driver.h | 2 ++ 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 4d5be378fa8c..26333d602a50 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -366,6 +366,8 @@ enum mlx5_driver_event { MLX5_DRIVER_EVENT_UPLINK_NETDEV, MLX5_DRIVER_EVENT_MACSEC_SA_ADDED, MLX5_DRIVER_EVENT_MACSEC_SA_DELETED, + MLX5_DRIVER_EVENT_AFFILIATION_DONE, + MLX5_DRIVER_EVENT_AFFILIATION_REMOVED, }; enum { diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 3033bbaeac81..5ca4e085d813 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1027,6 +1027,8 @@ bool mlx5_cmd_is_down(struct mlx5_core_dev *dev); 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); +void mlx5_core_mp_event_replay(struct mlx5_core_dev *dev, u32 event, void *data); + void mlx5_health_cleanup(struct mlx5_core_dev *dev); int mlx5_health_init(struct mlx5_core_dev *dev); void mlx5_start_health_poll(struct mlx5_core_dev *dev); -- cgit v1.2.3 From ef36ffcb381096ed32c309c342a02bf62939c503 Mon Sep 17 00:00:00 2001 From: Patrisious Haddad Date: Thu, 21 Sep 2023 15:10:30 +0300 Subject: net/mlx5: Add alias flow table bits Add all the capabilities needed to check for alias object support. As well as all the fields or commands needed for its creation and the creation of flow table that is able to jump to an alias object. Signed-off-by: Patrisious Haddad Reviewed-by: Mark Bloch Link: https://lore.kernel.org/r/544c030f2a78c4adf3fe6b64f97a39cc1bbdabb9.1695296682.git.leon@kernel.org Signed-off-by: Leon Romanovsky --- include/linux/mlx5/mlx5_ifc.h | 56 ++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 55 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 3265bfcb3156..23f9780adb83 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -312,6 +312,7 @@ enum { MLX5_CMD_OP_QUERY_VHCA_STATE = 0xb0d, MLX5_CMD_OP_MODIFY_VHCA_STATE = 0xb0e, MLX5_CMD_OP_SYNC_CRYPTO = 0xb12, + MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS = 0xb16, MLX5_CMD_OP_MAX }; @@ -1934,6 +1935,14 @@ struct mlx5_ifc_cmd_hca_cap_bits { u8 match_definer_format_supported[0x40]; }; +enum { + MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS = 0x80000, +}; + +enum { + MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE = 0x200, +}; + struct mlx5_ifc_cmd_hca_cap_2_bits { u8 reserved_at_0[0x80]; @@ -1952,7 +1961,11 @@ struct mlx5_ifc_cmd_hca_cap_2_bits { u8 migration_in_chunks[0x1]; u8 reserved_at_d1[0xf]; - u8 reserved_at_e0[0xc0]; + u8 cross_vhca_object_to_object_supported[0x20]; + + u8 allowed_object_for_other_vhca_access[0x40]; + + u8 reserved_at_140[0x60]; u8 flow_table_type_2_type[0x8]; u8 reserved_at_1a8[0x3]; @@ -6371,6 +6384,28 @@ struct mlx5_ifc_general_obj_out_cmd_hdr_bits { u8 reserved_at_60[0x20]; }; +struct mlx5_ifc_allow_other_vhca_access_in_bits { + u8 opcode[0x10]; + u8 uid[0x10]; + u8 reserved_at_20[0x10]; + u8 op_mod[0x10]; + u8 reserved_at_40[0x50]; + u8 object_type_to_be_accessed[0x10]; + u8 object_id_to_be_accessed[0x20]; + u8 reserved_at_c0[0x40]; + union { + u8 access_key_raw[0x100]; + u8 access_key[8][0x20]; + }; +}; + +struct mlx5_ifc_allow_other_vhca_access_out_bits { + u8 status[0x8]; + u8 reserved_at_8[0x18]; + u8 syndrome[0x20]; + u8 reserved_at_40[0x40]; +}; + struct mlx5_ifc_modify_header_arg_bits { u8 reserved_at_0[0x80]; @@ -6393,6 +6428,24 @@ struct mlx5_ifc_create_match_definer_out_bits { struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr; }; +struct mlx5_ifc_alias_context_bits { + u8 vhca_id_to_be_accessed[0x10]; + u8 reserved_at_10[0xd]; + u8 status[0x3]; + u8 object_id_to_be_accessed[0x20]; + u8 reserved_at_40[0x40]; + union { + u8 access_key_raw[0x100]; + u8 access_key[8][0x20]; + }; + u8 metadata[0x80]; +}; + +struct mlx5_ifc_create_alias_obj_in_bits { + struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr; + struct mlx5_ifc_alias_context_bits alias_ctx; +}; + enum { MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS = 0x0, MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS = 0x1, @@ -11919,6 +11972,7 @@ enum { 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_FLOW_TABLE_ALIAS = 0xff15, }; enum { -- cgit v1.2.3 From 210d4e9c732fa87b584af72faae96c037d9d7957 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 22 Sep 2023 10:28:44 -0700 Subject: ipv4/igmp: Annotate struct ip_sf_socklist with __counted_by Prepare for the coming implementation by GCC and Clang of the __counted_by attribute. Flexible array members annotated with __counted_by can have their accesses bounds-checked at run-time checking via CONFIG_UBSAN_BOUNDS (for array indexing) and CONFIG_FORTIFY_SOURCE (for strcpy/memcpy-family functions). As found with Coccinelle[1], add __counted_by for struct ip_sf_socklist. [1] https://github.com/kees/kernel-tools/blob/trunk/coccinelle/examples/counted_by.cocci Cc: Martin KaFai Lau Cc: Alexei Starovoitov Signed-off-by: Kees Cook Reviewed-by: Gustavo A. R. Silva Link: https://lore.kernel.org/r/20230922172858.3822653-2-keescook@chromium.org Signed-off-by: Jakub Kicinski --- include/linux/igmp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/igmp.h b/include/linux/igmp.h index ebf4349a53af..5171231f70a8 100644 --- a/include/linux/igmp.h +++ b/include/linux/igmp.h @@ -39,7 +39,7 @@ struct ip_sf_socklist { unsigned int sl_max; unsigned int sl_count; struct rcu_head rcu; - __be32 sl_addr[]; + __be32 sl_addr[] __counted_by(sl_max); }; #define IP_SFBLOCK 10 /* allocate this many at once */ -- cgit v1.2.3 From 75cec20345fa8e05a2b5f861fada95ad8e165257 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Fri, 8 Sep 2023 16:32:15 +0200 Subject: bpf: Remove xdp_do_flush_map(). MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit xdp_do_flush_map() can be removed because there is no more user in tree. Remove xdp_do_flush_map(). Signed-off-by: Sebastian Andrzej Siewior Acked-by: Toke Høiland-Jørgensen Acked-by: Jesper Dangaard Brouer Link: https://lore.kernel.org/r/20230908143215.869913-3-bigeasy@linutronix.de Signed-off-by: Jakub Kicinski --- include/linux/filter.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 27406aee2d40..e8822bd595f9 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1025,12 +1025,6 @@ int xdp_do_redirect_frame(struct net_device *dev, struct bpf_prog *prog); void xdp_do_flush(void); -/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as - * it is no longer only flushing maps. Keep this define for compatibility - * until all drivers are updated - do not use xdp_do_flush_map() in new code! - */ -#define xdp_do_flush_map xdp_do_flush - void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET -- cgit v1.2.3 From 26dd68d293fd1c5ac966fb5dd5f6d89de322a541 Mon Sep 17 00:00:00 2001 From: Przemek Kitszel Date: Tue, 12 Sep 2023 07:59:31 -0400 Subject: overflow: add DEFINE_FLEX() for on-stack allocs Add DEFINE_FLEX() macro for on-stack allocations of structs with flexible array member. Expose __struct_size() macro outside of fortify-string.h, as it could be used to read size of structs allocated by DEFINE_FLEX(). Move __member_size() alongside it. -Kees Using underlying array for on-stack storage lets us to declare known-at-compile-time structures without kzalloc(). Actual usage for ice driver is in following patches of the series. Missing __has_builtin() workaround is moved up to serve also assembly compilation with m68k-linux-gcc, see [1]. Error was (note the .S file extension): In file included from ../include/linux/linkage.h:5, from ../arch/m68k/fpsp040/skeleton.S:40: ../include/linux/compiler_types.h:331:5: warning: "__has_builtin" is not defined, evaluates to 0 [-Wundef] 331 | #if __has_builtin(__builtin_dynamic_object_size) | ^~~~~~~~~~~~~ ../include/linux/compiler_types.h:331:18: error: missing binary operator before token "(" 331 | #if __has_builtin(__builtin_dynamic_object_size) | ^ [1] https://lore.kernel.org/netdev/202308112122.OuF0YZqL-lkp@intel.com/ Co-developed-by: Kees Cook Signed-off-by: Kees Cook Signed-off-by: Przemek Kitszel Link: https://lore.kernel.org/r/20230912115937.1645707-2-przemyslaw.kitszel@intel.com Signed-off-by: Jakub Kicinski --- include/linux/compiler_types.h | 32 +++++++++++++++++++++----------- include/linux/fortify-string.h | 4 ---- include/linux/overflow.h | 35 +++++++++++++++++++++++++++++++++++ 3 files changed, 56 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index c523c6683789..6f1ca49306d2 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -2,6 +2,15 @@ #ifndef __LINUX_COMPILER_TYPES_H #define __LINUX_COMPILER_TYPES_H +/* + * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21. + * In the meantime, to support gcc < 10, we implement __has_builtin + * by hand. + */ +#ifndef __has_builtin +#define __has_builtin(x) (0) +#endif + #ifndef __ASSEMBLY__ /* @@ -134,17 +143,6 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { } # define __preserve_most #endif -/* Builtins */ - -/* - * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21. - * In the meantime, to support gcc < 10, we implement __has_builtin - * by hand. - */ -#ifndef __has_builtin -#define __has_builtin(x) (0) -#endif - /* Compiler specific macros. */ #ifdef __clang__ #include @@ -352,6 +350,18 @@ struct ftrace_likely_data { # define __realloc_size(x, ...) #endif +/* + * When the size of an allocated object is needed, use the best available + * mechanism to find it. (For cases where sizeof() cannot be used.) + */ +#if __has_builtin(__builtin_dynamic_object_size) +#define __struct_size(p) __builtin_dynamic_object_size(p, 0) +#define __member_size(p) __builtin_dynamic_object_size(p, 1) +#else +#define __struct_size(p) __builtin_object_size(p, 0) +#define __member_size(p) __builtin_object_size(p, 1) +#endif + #ifndef asm_volatile_goto #define asm_volatile_goto(x...) asm goto(x) #endif diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h index da51a83b2829..1e7711185ec6 100644 --- a/include/linux/fortify-string.h +++ b/include/linux/fortify-string.h @@ -93,13 +93,9 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) #if __has_builtin(__builtin_dynamic_object_size) #define POS __pass_dynamic_object_size(1) #define POS0 __pass_dynamic_object_size(0) -#define __struct_size(p) __builtin_dynamic_object_size(p, 0) -#define __member_size(p) __builtin_dynamic_object_size(p, 1) #else #define POS __pass_object_size(1) #define POS0 __pass_object_size(0) -#define __struct_size(p) __builtin_object_size(p, 0) -#define __member_size(p) __builtin_object_size(p, 1) #endif #define __compiletime_lessthan(bounds, length) ( \ diff --git a/include/linux/overflow.h b/include/linux/overflow.h index f9b60313eaea..7b5cf4a5cd19 100644 --- a/include/linux/overflow.h +++ b/include/linux/overflow.h @@ -309,4 +309,39 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend) #define struct_size_t(type, member, count) \ struct_size((type *)NULL, member, count) +/** + * _DEFINE_FLEX() - helper macro for DEFINE_FLEX() family. + * Enables caller macro to pass (different) initializer. + * + * @type: structure type name, including "struct" keyword. + * @name: Name for a variable to define. + * @member: Name of the array member. + * @count: Number of elements in the array; must be compile-time const. + * @initializer: initializer expression (could be empty for no init). + */ +#define _DEFINE_FLEX(type, name, member, count, initializer) \ + _Static_assert(__builtin_constant_p(count), \ + "onstack flex array members require compile-time const count"); \ + union { \ + u8 bytes[struct_size_t(type, member, count)]; \ + type obj; \ + } name##_u initializer; \ + type *name = (type *)&name##_u + +/** + * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing + * flexible array member. + * + * @type: structure type name, including "struct" keyword. + * @name: Name for a variable to define. + * @member: Name of the array member. + * @count: Number of elements in the array; must be compile-time const. + * + * Define a zeroed, on-stack, instance of @type structure with a trailing + * flexible array member. + * Use __struct_size(@name) to get compile-time size of it afterwards. + */ +#define DEFINE_FLEX(type, name, member, count) \ + _DEFINE_FLEX(type, name, member, count, = {}) + #endif /* __LINUX_OVERFLOW_H */ -- cgit v1.2.3 From 473267a4911f2469722c74ca58087d951072f72a Mon Sep 17 00:00:00 2001 From: Patrick Rohr Date: Mon, 25 Sep 2023 14:47:11 -0700 Subject: net: add sysctl to disable rfc4862 5.5.3e lifetime handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This change adds a sysctl to opt-out of RFC4862 section 5.5.3e's valid lifetime derivation mechanism. RFC4862 section 5.5.3e prescribes that the valid lifetime in a Router Advertisement PIO shall be ignored if it less than 2 hours and to reset the lifetime of the corresponding address to 2 hours. An in-progress 6man draft (see draft-ietf-6man-slaac-renum-07 section 4.2) is currently looking to remove this mechanism. While this draft has not been moving particularly quickly for other reasons, there is widespread consensus on section 4.2 which updates RFC4862 section 5.5.3e. Cc: Maciej Żenczykowski Cc: Lorenzo Colitti Cc: Jen Linkova Signed-off-by: Patrick Rohr Reviewed-by: Jiri Pirko Reviewed-by: David Ahern Link: https://lore.kernel.org/r/20230925214711.959704-1-prohr@google.com Signed-off-by: Jakub Kicinski --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index e400ff757f13..5e605e384aac 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -82,6 +82,7 @@ struct ipv6_devconf { __u32 ioam6_id_wide; __u8 ioam6_enabled; __u8 ndisc_evict_nocarrier; + __u8 ra_honor_pio_life; struct ctl_table_header *sysctl_header; }; -- cgit v1.2.3 From 7151d87a175c6618fe81705755eb3dc4199cad4e Mon Sep 17 00:00:00 2001 From: Ivan Vecera Date: Wed, 27 Sep 2023 10:31:30 +0200 Subject: virtchnl: Add header dependencies The uses BIT, struct_size and ETH_ALEN macros but does not include appropriate header files that defines them. Add these dependencies so this header file can be included anywhere. Signed-off-by: Ivan Vecera Reviewed-by: Przemek Kitszel Reviewed-by: Jesse Brandeburg Reviewed-by: Aleksandr Loktionov Signed-off-by: Tony Nguyen --- include/linux/avf/virtchnl.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h index dd71d3009771..6b3acf15be5c 100644 --- a/include/linux/avf/virtchnl.h +++ b/include/linux/avf/virtchnl.h @@ -4,6 +4,10 @@ #ifndef _VIRTCHNL_H_ #define _VIRTCHNL_H_ +#include +#include +#include + /* Description: * This header file describes the Virtual Function (VF) - Physical Function * (PF) communication protocol used by the drivers for all devices starting -- cgit v1.2.3 From 9beebc2b5d0038a65977a7a14909598c64ce070f Mon Sep 17 00:00:00 2001 From: Marc Kleine-Budde Date: Thu, 28 Sep 2023 09:24:28 +0200 Subject: can: dev: add can_state_get_by_berr_counter() to return the CAN state based on the current error counters Some CAN controllers do not have a register that contains the current CAN state, but only a register that contains the error counters. Introduce a new function can_state_get_by_berr_counter() that returns the current TX and RX state depending on the provided CAN bit error counters. Link: https://lore.kernel.org/all/20231005-at91_can-rx_offload-v2-1-9987d53600e0@pengutronix.de Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 982ba245eb41..1b92aed49363 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -195,6 +195,10 @@ int can_restart_now(struct net_device *dev); void can_bus_off(struct net_device *dev); const char *can_get_state_str(const enum can_state state); +void can_state_get_by_berr_counter(const struct net_device *dev, + const struct can_berr_counter *bec, + enum can_state *tx_state, + enum can_state *rx_state); void can_change_state(struct net_device *dev, struct can_frame *cf, enum can_state tx_state, enum can_state rx_state); -- cgit v1.2.3 From 9c8c3fa3a52bc55696ccc4dfcb8a49f969b5fb0e Mon Sep 17 00:00:00 2001 From: Akihiko Odaki Date: Thu, 5 Oct 2023 16:21:36 +0900 Subject: bpf: Fix the comment for bpf_restore_data_end() The comment used to say: > Restore data saved by bpf_compute_data_pointers(). But bpf_compute_data_pointers() does not save the data; bpf_compute_and_save_data_end() does. Signed-off-by: Akihiko Odaki Acked-by: Stanislav Fomichev Link: https://lore.kernel.org/r/20231005072137.29870-1-akihiko.odaki@daynix.com Signed-off-by: Martin KaFai Lau --- include/linux/filter.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/filter.h b/include/linux/filter.h index 27406aee2d40..ff7ecc89d3dd 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -736,7 +736,7 @@ static inline void bpf_compute_and_save_data_end( cb->data_end = skb->data + skb_headlen(skb); } -/* Restore data saved by bpf_compute_data_pointers(). */ +/* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { -- cgit v1.2.3 From bc5bc309db45a7ab218ce8259ba9bc7659be61ca Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Thu, 5 Oct 2023 08:41:23 +0000 Subject: bpf: Inherit system settings for CPU security mitigations Currently, there exists a system-wide setting related to CPU security mitigations, denoted as 'mitigations='. When set to 'mitigations=off', it deactivates all optional CPU mitigations. Therefore, if we implement a system-wide 'mitigations=off' setting, it should inherently bypass Spectre v1 and Spectre v4 in the BPF subsystem. Please note that there is also a more specific 'nospectre_v1' setting on x86 and ppc architectures, though it is not currently exported. For the time being, let's disregard more fine-grained options. This idea emerged during our discussion about potential Spectre v1 attacks with Luis [0]. [0] https://lore.kernel.org/bpf/b4fc15f7-b204-767e-ebb9-fdb4233961fb@iogearbox.net Signed-off-by: Yafang Shao Signed-off-by: Daniel Borkmann Acked-by: Stanislav Fomichev Acked-by: Song Liu Acked-by: KP Singh Cc: Luis Gerhorst Link: https://lore.kernel.org/bpf/20231005084123.1338-1-laoar.shao@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a82efd34b741..61bde4520f5c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2164,12 +2164,12 @@ static inline bool bpf_allow_uninit_stack(void) static inline bool bpf_bypass_spec_v1(void) { - return perfmon_capable(); + return perfmon_capable() || cpu_mitigations_off(); } static inline bool bpf_bypass_spec_v4(void) { - return perfmon_capable(); + return perfmon_capable() || cpu_mitigations_off(); } int bpf_map_new_fd(struct bpf_map *map, int flags); -- cgit v1.2.3 From 3abbd0699b678fc48e0100704338cff9180fe4bb Mon Sep 17 00:00:00 2001 From: Giulio Benetti Date: Thu, 5 Oct 2023 20:29:15 +0200 Subject: net: phy: broadcom: add support for BCM5221 phy This patch adds the BCM5221 PHY support by reusing brcm_fet_*() callbacks and adding quirks for BCM5221 when needed. Cc: Jim Reinhart Cc: James Autry Cc: Matthew Maron Signed-off-by: Giulio Benetti Reviewed-by: Florian Fainelli Link: https://lore.kernel.org/r/20231005182915.153815-1-giulio.benetti@benettiengineering.com Signed-off-by: Jakub Kicinski --- include/linux/brcmphy.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index c55810a43541..1394ba302367 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -11,6 +11,7 @@ #define PHY_ID_BCM50610 0x0143bd60 #define PHY_ID_BCM50610M 0x0143bd70 +#define PHY_ID_BCM5221 0x004061e0 #define PHY_ID_BCM5241 0x0143bc30 #define PHY_ID_BCMAC131 0x0143bc70 #define PHY_ID_BCM5481 0x0143bca0 @@ -331,6 +332,15 @@ #define BCM54XX_WOL_INT_STATUS (MII_BCM54XX_EXP_SEL_WOL + 0x94) +/* BCM5221 Registers */ +#define BCM5221_AEGSR 0x1C +#define BCM5221_AEGSR_MDIX_STATUS BIT(13) +#define BCM5221_AEGSR_MDIX_MAN_SWAP BIT(12) +#define BCM5221_AEGSR_MDIX_DIS BIT(11) + +#define BCM5221_SHDW_AM4_EN_CLK_LPM BIT(2) +#define BCM5221_SHDW_AM4_FORCE_LPM BIT(1) + /*****************************************************************************/ /* Fast Ethernet Transceiver definitions. */ /*****************************************************************************/ -- cgit v1.2.3 From 5247dbf16cee4e83eb89e4d3b87bd5e79c5d1655 Mon Sep 17 00:00:00 2001 From: Yajun Deng Date: Mon, 9 Oct 2023 19:16:33 +0800 Subject: net/core: Introduce netdev_core_stats_inc() Although there is a kfree_skb_reason() helper function that can be used to find the reason why this skb is dropped, but most callers didn't increase one of rx_dropped, tx_dropped, rx_nohandler and rx_otherhost_dropped. For the users, people are more concerned about why the dropped in ip is increasing. Introduce netdev_core_stats_inc() for trace the caller of dev_core_stats_*_inc(). Also, add __code to netdev_core_stats_alloc(), as it's called with small probability. And add noinline make sure netdev_core_stats_inc was never inlined. Signed-off-by: Yajun Deng Suggested-by: Alexander Lobakin Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/netdevice.h | 21 ++++----------------- 1 file changed, 4 insertions(+), 17 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e070a4540fba..11d704bfec9b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -4002,32 +4002,19 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev, return false; } -struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev); - -static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev) -{ - /* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */ - struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats); - - if (likely(p)) - return p; - - return netdev_core_stats_alloc(dev); -} +void netdev_core_stats_inc(struct net_device *dev, u32 offset); #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ - struct net_device_core_stats __percpu *p; \ - \ - p = dev_core_stats(dev); \ - if (p) \ - this_cpu_inc(p->FIELD); \ + netdev_core_stats_inc(dev, \ + offsetof(struct net_device_core_stats, FIELD)); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) DEV_CORE_STATS_INC(rx_nohandler) DEV_CORE_STATS_INC(rx_otherhost_dropped) +#undef DEV_CORE_STATS_INC static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, -- cgit v1.2.3 From fefba7d1ae198dcbf8b3b432de46a4e29f8dbd8c Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:04 +0200 Subject: bpf: Propagate modified uaddrlen from cgroup sockaddr programs As prep for adding unix socket support to the cgroup sockaddr hooks, let's propagate the sockaddr length back to the caller after running a bpf cgroup sockaddr hook program. While not important for AF_INET or AF_INET6, the sockaddr length is important when working with AF_UNIX sockaddrs as the size of the sockaddr cannot be determined just from the address family or the sockaddr's contents. __cgroup_bpf_run_filter_sock_addr() is modified to take the uaddrlen as an input/output argument. After running the program, the modified sockaddr length is stored in the uaddrlen pointer. Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-3-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup.h | 73 +++++++++++++++++++++++----------------------- include/linux/filter.h | 1 + 2 files changed, 38 insertions(+), 36 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 8506690dbb9c..31561e789715 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -120,6 +120,7 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk, int __cgroup_bpf_run_filter_sock_addr(struct sock *sk, struct sockaddr *uaddr, + int *uaddrlen, enum cgroup_bpf_attach_type atype, void *t_ctx, u32 *flags); @@ -230,22 +231,22 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) \ BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) \ +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, NULL); \ __ret; \ }) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) \ +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) \ ({ \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - t_ctx, NULL); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, t_ctx, NULL); \ release_sock(sk); \ } \ __ret; \ @@ -256,14 +257,14 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE). */ -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags) \ +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \ ({ \ u32 __flags = 0; \ int __ret = 0; \ if (cgroup_bpf_enabled(atype)) { \ lock_sock(sk); \ - __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype, \ - NULL, &__flags); \ + __ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, uaddrlen, \ + atype, NULL, &__flags); \ release_sock(sk); \ if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE) \ *bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE; \ @@ -276,29 +277,29 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) && \ (sk)->sk_prot->pre_connect) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by @@ -477,24 +478,24 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, } #define cgroup_bpf_enabled(atype) (0) -#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; }) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0) #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) diff --git a/include/linux/filter.h b/include/linux/filter.h index ff7ecc89d3dd..bcd2bc15ff56 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -1335,6 +1335,7 @@ struct bpf_sock_addr_kern { */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ + u32 uaddrlen; }; struct bpf_sock_ops_kern { -- cgit v1.2.3 From 859051dd165ec6cc915f0f2114699021144fd249 Mon Sep 17 00:00:00 2001 From: Daan De Meyer Date: Wed, 11 Oct 2023 20:51:06 +0200 Subject: bpf: Implement cgroup sockaddr hooks for unix sockets These hooks allows intercepting connect(), getsockname(), getpeername(), sendmsg() and recvmsg() for unix sockets. The unix socket hooks get write access to the address length because the address length is not fixed when dealing with unix sockets and needs to be modified when a unix socket address is modified by the hook. Because abstract socket unix addresses start with a NUL byte, we cannot recalculate the socket address in kernelspace after running the hook by calculating the length of the unix socket path using strlen(). These hooks can be used when users want to multiplex syscall to a single unix socket to multiple different processes behind the scenes by redirecting the connect() and other syscalls to process specific sockets. We do not implement support for intercepting bind() because when using bind() with unix sockets with a pathname address, this creates an inode in the filesystem which must be cleaned up. If we rewrite the address, the user might try to clean up the wrong file, leaking the socket in the filesystem where it is never cleaned up. Until we figure out a solution for this (and a use case for intercepting bind()), we opt to not allow rewriting the sockaddr in bind() calls. We also implement recvmsg() support for connected streams so that after a connect() that is modified by a sockaddr hook, any corresponding recmvsg() on the connected socket can also be modified to make the connected program think it is connected to the "intended" remote. Reviewed-by: Kuniyuki Iwashima Signed-off-by: Daan De Meyer Link: https://lore.kernel.org/r/20231011185113.140426-5-daan.j.demeyer@gmail.com Signed-off-by: Martin KaFai Lau --- include/linux/bpf-cgroup-defs.h | 5 +++++ include/linux/bpf-cgroup.h | 17 +++++++++++++++++ 2 files changed, 22 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h index 7b121bd780eb..0985221d5478 100644 --- a/include/linux/bpf-cgroup-defs.h +++ b/include/linux/bpf-cgroup-defs.h @@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type { CGROUP_INET6_BIND, CGROUP_INET4_CONNECT, CGROUP_INET6_CONNECT, + CGROUP_UNIX_CONNECT, CGROUP_INET4_POST_BIND, CGROUP_INET6_POST_BIND, CGROUP_UDP4_SENDMSG, CGROUP_UDP6_SENDMSG, + CGROUP_UNIX_SENDMSG, CGROUP_SYSCTL, CGROUP_UDP4_RECVMSG, CGROUP_UDP6_RECVMSG, + CGROUP_UNIX_RECVMSG, CGROUP_GETSOCKOPT, CGROUP_SETSOCKOPT, CGROUP_INET4_GETPEERNAME, CGROUP_INET6_GETPEERNAME, + CGROUP_UNIX_GETPEERNAME, CGROUP_INET4_GETSOCKNAME, CGROUP_INET6_GETSOCKNAME, + CGROUP_UNIX_GETSOCKNAME, CGROUP_INET_SOCK_RELEASE, CGROUP_LSM_START, CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1, diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index 31561e789715..98b8cea904fe 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type) CGROUP_ATYPE(CGROUP_INET6_BIND); CGROUP_ATYPE(CGROUP_INET4_CONNECT); CGROUP_ATYPE(CGROUP_INET6_CONNECT); + CGROUP_ATYPE(CGROUP_UNIX_CONNECT); CGROUP_ATYPE(CGROUP_INET4_POST_BIND); CGROUP_ATYPE(CGROUP_INET6_POST_BIND); CGROUP_ATYPE(CGROUP_UDP4_SENDMSG); CGROUP_ATYPE(CGROUP_UDP6_SENDMSG); + CGROUP_ATYPE(CGROUP_UNIX_SENDMSG); CGROUP_ATYPE(CGROUP_SYSCTL); CGROUP_ATYPE(CGROUP_UDP4_RECVMSG); CGROUP_ATYPE(CGROUP_UDP6_RECVMSG); + CGROUP_ATYPE(CGROUP_UNIX_RECVMSG); CGROUP_ATYPE(CGROUP_GETSOCKOPT); CGROUP_ATYPE(CGROUP_SETSOCKOPT); CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME); CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME); + CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME); CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE); default: return CGROUP_BPF_ATTACH_TYPE_INVALID; @@ -289,18 +294,27 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk, #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL) + #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx) + #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL) + /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a * fullsock and its parent fullsock cannot be traced by * sk_to_full_sk(). @@ -492,10 +506,13 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; }) -- cgit v1.2.3 From 0a779003213b589d7b3eef72f69e19a30f603ebc Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 9 Oct 2023 15:37:51 +0200 Subject: netdev: make napi_schedule return bool on NAPI successful schedule Change napi_schedule to return a bool on NAPI successful schedule. This might be useful for some driver to do additional steps after a NAPI has been scheduled. Suggested-by: Eric Dumazet Signed-off-by: Christian Marangi Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20231009133754.9834-2-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 11d704bfec9b..2874770a0a74 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -490,11 +490,18 @@ bool napi_schedule_prep(struct napi_struct *n); * * Schedule NAPI poll routine to be called if it is not already * running. + * Return true if we schedule a NAPI or false if not. + * Refer to napi_schedule_prep() for additional reason on why + * a NAPI might not be scheduled. */ -static inline void napi_schedule(struct napi_struct *n) +static inline bool napi_schedule(struct napi_struct *n) { - if (napi_schedule_prep(n)) + if (napi_schedule_prep(n)) { __napi_schedule(n); + return true; + } + + return false; } /** -- cgit v1.2.3 From 73382e919f3d938554dadd01d95760f90d1c25c1 Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Mon, 9 Oct 2023 15:37:52 +0200 Subject: netdev: replace napi_reschedule with napi_schedule Now that napi_schedule return a bool, we can drop napi_reschedule that does the same exact function. The function comes from a very old commit bfe13f54f502 ("ibm_emac: Convert to use napi_struct independent of struct net_device") and the purpose is actually deprecated in favour of different logic. Convert every user of napi_reschedule to napi_schedule. Signed-off-by: Christian Marangi Acked-by: Jeff Johnson # ath10k Acked-by: Nick Child # ibm Acked-by: Marc Kleine-Budde # for can/dev/rx-offload.c Reviewed-by: Eric Dumazet Acked-by: Tariq Toukan Link: https://lore.kernel.org/r/20231009133754.9834-3-ansuelsmth@gmail.com Signed-off-by: Jakub Kicinski --- include/linux/netdevice.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 2874770a0a74..ae553f886796 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -516,16 +516,6 @@ static inline void napi_schedule_irqoff(struct napi_struct *n) __napi_schedule_irqoff(n); } -/* Try to reschedule poll. Called by dev->poll() after napi_complete(). */ -static inline bool napi_reschedule(struct napi_struct *napi) -{ - if (napi_schedule_prep(napi)) { - __napi_schedule(napi); - return true; - } - return false; -} - /** * napi_complete_done - NAPI processing complete * @n: NAPI context -- cgit v1.2.3 From 38985e8c278b82e6d4d62d4acd57c761cc23ce63 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Mon, 9 Oct 2023 13:06:08 +0300 Subject: net: Handle bulk delete policy in bridge driver The merge commit 92716869375b ("Merge branch 'br-flush-filtering'") added support for FDB flushing in bridge driver. The following patches will extend VXLAN driver to support FDB flushing as well. The netlink message for bulk delete is shared between the drivers. With the existing implementation, there is no way to prevent user from flushing with attributes that are not supported per driver. For example, when VNI will be added, user will not get an error for flush FDB entries in bridge with VNI, although this attribute is not relevant for bridge. As preparation for support of FDB flush in VXLAN driver, move the policy to be handled in bridge driver, later a new policy for VXLAN will be added in VXLAN driver. Do not pass 'vid' as part of ndo_fdb_del_bulk(), as this field is relevant only for bridge. Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ae553f886796..1c7681263d30 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1287,9 +1287,7 @@ struct netdev_net_notifier { * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. - * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[], - * struct net_device *dev, - * u16 vid, + * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, @@ -1564,10 +1562,8 @@ struct net_device_ops { struct net_device *dev, const unsigned char *addr, u16 vid, struct netlink_ext_ack *extack); - int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, - struct nlattr *tb[], + int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, - u16 vid, struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, -- cgit v1.2.3 From 236334aeec0f93217cf9235f2004e61a0a1a5985 Mon Sep 17 00:00:00 2001 From: Yafang Shao Date: Fri, 13 Oct 2023 08:39:16 +0000 Subject: bpf: Avoid unnecessary audit log for CPU security mitigations Check cpu_mitigations_off() first to avoid calling capable() if it is off. This can avoid unnecessary audit log. Fixes: bc5bc309db45 ("bpf: Inherit system settings for CPU security mitigations") Suggested-by: Andrii Nakryiko Signed-off-by: Yafang Shao Signed-off-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/CAEf4Bza6UVUWqcWQ-66weZ-nMDr+TFU3Mtq=dumZFD-pSqU7Ow@mail.gmail.com/ Link: https://lore.kernel.org/bpf/20231013083916.4199-1-laoar.shao@gmail.com --- include/linux/bpf.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 61bde4520f5c..f0891ba24cb1 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2164,12 +2164,12 @@ static inline bool bpf_allow_uninit_stack(void) static inline bool bpf_bypass_spec_v1(void) { - return perfmon_capable() || cpu_mitigations_off(); + return cpu_mitigations_off() || perfmon_capable(); } static inline bool bpf_bypass_spec_v4(void) { - return perfmon_capable() || cpu_mitigations_off(); + return cpu_mitigations_off() || perfmon_capable(); } int bpf_map_new_fd(struct bpf_map *map, int flags); -- cgit v1.2.3 From 3f7f31fff2510272334f3d0374c432bdaa4f1536 Mon Sep 17 00:00:00 2001 From: Wei Zhang Date: Thu, 12 Oct 2023 12:27:36 -0700 Subject: net/mlx5: Parallelize vhca event handling At present, mlx5 driver have a general purpose event handler which not only handles vhca event but also many other events. This incurs a huge bottleneck because the event handler is implemented by single threaded workqueue and all events are forced to be handled in serial manner even though application tries to create multiple SFs simultaneously. Introduce a dedicated vhca event handler which manages SFs parallel creation. Signed-off-by: Wei Zhang Reviewed-by: Moshe Shemesh Reviewed-by: Shay Drory Reviewed-by: Jacob Keller Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 52e982bc0f50..7968c5ee85c4 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -615,6 +615,7 @@ struct mlx5_priv { int adev_idx; int sw_vhca_id; struct mlx5_events *events; + struct mlx5_vhca_events *vhca_events; struct mlx5_flow_steering *steering; struct mlx5_mpfs *mpfs; -- cgit v1.2.3 From e534552c92a44690e48593f9567fe689545ded73 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Thu, 12 Oct 2023 12:27:39 -0700 Subject: net/mlx5: Refactor LAG peer device lookout bus logic to mlx5 devcom LAG peer device lookout bus logic required the usage of global lock, mlx5_intf_mutex. As part of the effort to remove this global lock, refactor LAG peer device lookout to use mlx5 devcom layer. Signed-off-by: Shay Drory Reviewed-by: Mark Bloch Reviewed-by: Jacob Keller Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index 7968c5ee85c4..f60cdc9bd40f 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -624,6 +624,7 @@ struct mlx5_priv { struct mlx5_lag *lag; u32 flags; struct mlx5_devcom_dev *devc; + struct mlx5_devcom_comp_dev *hca_devcom_comp; struct mlx5_fw_reset *fw_reset; struct mlx5_core_roce roce; struct mlx5_fc_stats fc_stats; -- cgit v1.2.3 From 0d2d6bc7e74fee586f587d33484b797bb78f334c Mon Sep 17 00:00:00 2001 From: Yue Haibing Date: Thu, 12 Oct 2023 12:27:41 -0700 Subject: net/mlx5: Remove unused declaration Commit 2ac9cfe78223 ("net/mlx5e: IPSec, Add Innova IPSec offload TX data path") declared mlx5e_ipsec_inverse_table_init() but never implemented it. Commit f52f2faee581 ("net/mlx5e: Introduce flow steering API") declared mlx5e_fs_set_tc() but never implemented it. Commit f2f3df550139 ("net/mlx5: EQ, Privatize eq_table and friends") declared mlx5_eq_comp_cpumask() but never implemented it. Commit cac1eb2cf2e3 ("net/mlx5: Lag, properly lock eswitch if needed") removed mlx5_lag_update() but not its declaration. Commit 35ba005d820b ("net/mlx5: DR, Set flex parser for TNL_MPLS dynamically") removed mlx5dr_ste_build_tnl_mpls() but not its declaration. Commit e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters") declared but never implemented mlx5_alloc_cmd_mailbox_chain() and mlx5_free_cmd_mailbox_chain(). Commit 0cf53c124756 ("net/mlx5: FWPage, Use async events chain") removed mlx5_core_req_pages_handler() but not its declaration. Commit 938fe83c8dcb ("net/mlx5_core: New device capabilities handling") removed mlx5_query_odp_caps() but not its declaration. Commit f6a8a19bb11b ("RDMA/netdev: Hoist alloc_netdev_mqs out of the driver") removed mlx5_rdma_netdev_alloc() but not its declaration. Signed-off-by: Yue Haibing Reviewed-by: Leon Romanovsky Reviewed-by: Simon Horman Reviewed-by: Jacob Keller Signed-off-by: Saeed Mahameed --- include/linux/mlx5/driver.h | 14 -------------- 1 file changed, 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h index f60cdc9bd40f..d2b8d4a74a30 100644 --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -1043,10 +1043,6 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev); int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_frag_buf *buf, int node); void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf); -struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev, - gfp_t flags, int npages); -void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev, - struct mlx5_cmd_mailbox *head); int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in, int inlen); int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey); @@ -1060,8 +1056,6 @@ void mlx5_pagealloc_start(struct mlx5_core_dev *dev); void mlx5_pagealloc_stop(struct mlx5_core_dev *dev); void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev); void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev); -void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id, - s32 npages, bool ec_function); int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot); int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev); void mlx5_register_debugfs(void); @@ -1101,8 +1095,6 @@ int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn, int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num); __be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev); void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common); -int mlx5_query_odp_caps(struct mlx5_core_dev *dev, - struct mlx5_odp_caps *odp_caps); int mlx5_init_rl_table(struct mlx5_core_dev *dev); void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev); @@ -1204,12 +1196,6 @@ int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev, void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev, int vf_id, struct notifier_block *nb); -#ifdef CONFIG_MLX5_CORE_IPOIB -struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev, - struct ib_device *ibdev, - const char *name, - void (*setup)(struct net_device *)); -#endif /* CONFIG_MLX5_CORE_IPOIB */ int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev, struct ib_device *device, struct rdma_netdev_alloc_params *params); -- cgit v1.2.3 From 49dbe25adac42d3e06f65d1420946bec65896222 Mon Sep 17 00:00:00 2001 From: Arseniy Krasnov Date: Tue, 10 Oct 2023 22:15:14 +0300 Subject: vsock: read from socket's error queue This adds handling of MSG_ERRQUEUE input flag in receive call. This flag is used to read socket's error queue instead of data queue. Possible scenario of error queue usage is receiving completions for transmission with MSG_ZEROCOPY flag. This patch also adds new defines: 'SOL_VSOCK' and 'VSOCK_RECVERR'. Signed-off-by: Arseniy Krasnov Reviewed-by: Stefano Garzarella Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 39b74d83c7c4..cfcb7e2c3813 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -383,6 +383,7 @@ struct ucred { #define SOL_MPTCP 284 #define SOL_MCTP 285 #define SOL_SMC 286 +#define SOL_VSOCK 287 /* IPX options */ #define IPX_TYPE 1 -- cgit v1.2.3 From d7fbc0b7e846e9e0e70ae766d274b8720fbab412 Mon Sep 17 00:00:00 2001 From: Arkadiusz Kubalewski Date: Wed, 11 Oct 2023 12:12:34 +0200 Subject: dpll: netlink/core: add support for pin-dpll signal phase offset/adjust Add callback ops for pin-dpll phase measurement. Add callback for pin signal phase adjustment. Add min and max phase adjustment values to pin proprties. Invoke callbacks in dpll_netlink.c when filling the pin details to provide user with phase related attribute values. Signed-off-by: Arkadiusz Kubalewski Signed-off-by: David S. Miller --- include/linux/dpll.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dpll.h b/include/linux/dpll.h index bbc480cd2932..578fc5fa3750 100644 --- a/include/linux/dpll.h +++ b/include/linux/dpll.h @@ -68,6 +68,18 @@ struct dpll_pin_ops { int (*prio_set)(const struct dpll_pin *pin, void *pin_priv, const struct dpll_device *dpll, void *dpll_priv, const u32 prio, struct netlink_ext_ack *extack); + int (*phase_offset_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s64 *phase_offset, + struct netlink_ext_ack *extack); + int (*phase_adjust_get)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + s32 *phase_adjust, + struct netlink_ext_ack *extack); + int (*phase_adjust_set)(const struct dpll_pin *pin, void *pin_priv, + const struct dpll_device *dpll, void *dpll_priv, + const s32 phase_adjust, + struct netlink_ext_ack *extack); }; struct dpll_pin_frequency { @@ -91,6 +103,11 @@ struct dpll_pin_frequency { #define DPLL_PIN_FREQUENCY_DCF77 \ DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_77_5_KHZ) +struct dpll_pin_phase_adjust_range { + s32 min; + s32 max; +}; + struct dpll_pin_properties { const char *board_label; const char *panel_label; @@ -99,6 +116,7 @@ struct dpll_pin_properties { unsigned long capabilities; u32 freq_supported_num; struct dpll_pin_frequency *freq_supported; + struct dpll_pin_phase_adjust_range phase_range; }; #if IS_ENABLED(CONFIG_DPLL) -- cgit v1.2.3 From 60c6946675fc06dd2fd2b7a4b6fd1c1f046f1056 Mon Sep 17 00:00:00 2001 From: Xabier Marquiegui Date: Thu, 12 Oct 2023 00:39:53 +0200 Subject: posix-clock: introduce posix_clock_context concept Add the necessary structure to support custom private-data per posix-clock user. The previous implementation of posix-clock assumed all file open instances need access to the same clock structure on private_data. The need for individual data structures per file open instance has been identified when developing support for multiple timestamp event queue users for ptp_clock. Signed-off-by: Xabier Marquiegui Suggested-by: Richard Cochran Suggested-by: Vinicius Costa Gomes Signed-off-by: David S. Miller --- include/linux/posix-clock.h | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h index 468328b1e1dd..ef8619f48920 100644 --- a/include/linux/posix-clock.h +++ b/include/linux/posix-clock.h @@ -14,6 +14,7 @@ #include struct posix_clock; +struct posix_clock_context; /** * struct posix_clock_operations - functional interface to the clock @@ -50,18 +51,18 @@ struct posix_clock_operations { /* * Optional character device methods: */ - long (*ioctl) (struct posix_clock *pc, - unsigned int cmd, unsigned long arg); + long (*ioctl)(struct posix_clock_context *pccontext, unsigned int cmd, + unsigned long arg); - int (*open) (struct posix_clock *pc, fmode_t f_mode); + int (*open)(struct posix_clock_context *pccontext, fmode_t f_mode); - __poll_t (*poll) (struct posix_clock *pc, - struct file *file, poll_table *wait); + __poll_t (*poll)(struct posix_clock_context *pccontext, struct file *file, + poll_table *wait); - int (*release) (struct posix_clock *pc); + int (*release)(struct posix_clock_context *pccontext); - ssize_t (*read) (struct posix_clock *pc, - uint flags, char __user *buf, size_t cnt); + ssize_t (*read)(struct posix_clock_context *pccontext, uint flags, + char __user *buf, size_t cnt); }; /** @@ -90,6 +91,24 @@ struct posix_clock { bool zombie; }; +/** + * struct posix_clock_context - represents clock file operations context + * + * @clk: Pointer to 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. + * + * Drivers can store a private data structure during the open operation + * if they have specific information that is required in other file + * operations. + */ +struct posix_clock_context { + struct posix_clock *clk; + void *private_clkdata; +}; + /** * posix_clock_register() - register a new clock * @clk: Pointer to the clock. Caller must provide 'ops' field -- cgit v1.2.3 From 90de47f020db086f7929e09f64efd0cf627d6869 Mon Sep 17 00:00:00 2001 From: Yunsheng Lin Date: Fri, 13 Oct 2023 14:48:21 +0800 Subject: page_pool: fragment API support for 32-bit arch with 64-bit DMA Currently page_pool_alloc_frag() is not supported in 32-bit arch with 64-bit DMA because of the overlap issue between pp_frag_count and dma_addr_upper in 'struct page' for those arches, which seems to be quite common, see [1], which means driver may need to handle it when using fragment API. It is assumed that the combination of the above arch with an address space >16TB does not exist, as all those arches have 64b equivalent, it seems logical to use the 64b version for a system with a large address space. It is also assumed that dma address is page aligned when we are dma mapping a page aligned buffer, see [2]. That means we're storing 12 bits of 0 at the lower end for a dma address, we can reuse those bits for the above arches to support 32b+12b, which is 16TB of memory. If we make a wrong assumption, a warning is emitted so that user can report to us. 1. https://lore.kernel.org/all/20211117075652.58299-1-linyunsheng@huawei.com/ 2. https://lore.kernel.org/all/20230818145145.4b357c89@kernel.org/ Tested-by: Alexander Lobakin Signed-off-by: Yunsheng Lin CC: Lorenzo Bianconi CC: Alexander Duyck CC: Liang Chen CC: Guillaume Tucker CC: Matthew Wilcox CC: Linux-MM Link: https://lore.kernel.org/r/20231013064827.61135-2-linyunsheng@huawei.com Signed-off-by: Jakub Kicinski --- include/linux/mm_types.h | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 36c5b43999e6..74b49c4c7a52 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -125,18 +125,7 @@ struct page { struct page_pool *pp; unsigned long _pp_mapping_pad; unsigned long dma_addr; - 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; - }; + atomic_long_t pp_frag_count; }; struct { /* Tail pages of compound page */ unsigned long compound_head; /* Bit zero is set */ -- cgit v1.2.3 From 0ac6486e5cbd1af682d3b52fcd3615247e13cb57 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Fri, 13 Oct 2023 12:06:24 +0800 Subject: i3c: Add support for bus enumeration & notification This allows other drivers to be notified when new i3c busses are attached, referring to a whole i3c bus as opposed to individual devices. Signed-off-by: Jeremy Kerr Signed-off-by: Matt Johnston Acked-by: Alexandre Belloni Signed-off-by: Paolo Abeni --- include/linux/i3c/master.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h index 0b52da4f2346..db909ef79be4 100644 --- a/include/linux/i3c/master.h +++ b/include/linux/i3c/master.h @@ -24,6 +24,12 @@ struct i2c_client; +/* notifier actions. notifier call data is the struct i3c_bus */ +enum { + I3C_NOTIFY_BUS_ADD, + I3C_NOTIFY_BUS_REMOVE, +}; + struct i3c_master_controller; struct i3c_bus; struct i3c_device; @@ -652,4 +658,9 @@ void i3c_master_queue_ibi(struct i3c_dev_desc *dev, struct i3c_ibi_slot *slot); struct i3c_ibi_slot *i3c_master_get_free_ibi_slot(struct i3c_dev_desc *dev); +void i3c_for_each_bus_locked(int (*fn)(struct i3c_bus *bus, void *data), + void *data); +int i3c_register_notifier(struct notifier_block *nb); +int i3c_unregister_notifier(struct notifier_block *nb); + #endif /* I3C_MASTER_H */ -- cgit v1.2.3 From 9a675ba55a96a45a9fb69e6a5c43f80c6682e541 Mon Sep 17 00:00:00 2001 From: Sebastian Andrzej Siewior Date: Mon, 16 Oct 2023 14:57:38 +0200 Subject: net, bpf: Add a warning if NAPI cb missed xdp_do_flush(). MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit A few drivers were missing a xdp_do_flush() invocation after XDP_REDIRECT. Add three helper functions each for one of the per-CPU lists. Return true if the per-CPU list is non-empty and flush the list. Add xdp_do_check_flushed() which invokes each helper functions and creates a warning if one of the functions had a non-empty list. Hide everything behind CONFIG_DEBUG_NET. Suggested-by: Jesper Dangaard Brouer Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: Daniel Borkmann Reviewed-by: Toke Høiland-Jørgensen Acked-by: Jakub Kicinski Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20231016125738.Yt79p1uF@linutronix.de --- include/linux/bpf.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d3c51a507508..b4b40b45962b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2478,6 +2478,9 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data, enum bpf_dynptr_type type, u32 offset, u32 size); void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr); void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr); + +bool dev_check_flush(void); +bool cpu_map_check_flush(void); #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { -- cgit v1.2.3 From b6f9774719e5601b32f47021b40fee446b356490 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 16 Oct 2023 16:42:53 +0100 Subject: net: phylink: provide mac_get_caps() method Provide a new method, mac_get_caps() to get the MAC capabilities for the specified interface mode. This is for MACs which have special requirements, such as not supporting half-duplex in certain interface modes, and will replace the validate() method. Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1qsPk5-009wiX-G5@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- include/linux/phylink.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 2b886ea654bb..0798198a09ef 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -228,6 +228,7 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. + * @mac_get_caps: Get MAC capabilities for interface mode. * @mac_select_pcs: Select a PCS for the interface mode. * @mac_prepare: prepare for a major reconfiguration of the interface. * @mac_config: configure the MAC for the selected mode and state. @@ -241,6 +242,8 @@ struct phylink_mac_ops { void (*validate)(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); + unsigned long (*mac_get_caps)(struct phylink_config *config, + phy_interface_t interface); struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, phy_interface_t interface); int (*mac_prepare)(struct phylink_config *config, unsigned int mode, @@ -292,6 +295,18 @@ struct phylink_mac_ops { */ void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state); +/** + * mac_get_caps: Get MAC capabilities for interface mode. + * @config: a pointer to a &struct phylink_config. + * @interface: PHY interface mode. + * + * Optional method. When not provided, config->mac_capabilities will be used. + * When implemented, this returns the MAC capabilities for the specified + * interface mode where there is some special handling required by the MAC + * driver (e.g. not supporting half-duplex in certain interface modes.) + */ +unsigned long mac_get_caps(struct phylink_config *config, + phy_interface_t interface); /** * mac_select_pcs: Select a PCS for the interface mode. * @config: a pointer to a &struct phylink_config. -- cgit v1.2.3 From da5f6b80ad6417f7cf50d273c1c0ecb885e511e8 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 16 Oct 2023 16:43:03 +0100 Subject: net: phylink: remove .validate() method The MAC .validate() method is no longer used, so remove it from the phylink_mac_ops structure, and remove the callsite in phylink_validate_mac_and_pcs(). Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1qsPkF-009wij-QM@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- include/linux/phylink.h | 38 -------------------------------------- 1 file changed, 38 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 0798198a09ef..0cf559bae1ff 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -227,7 +227,6 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); /** * struct phylink_mac_ops - MAC operations structure. - * @validate: Validate and update the link configuration. * @mac_get_caps: Get MAC capabilities for interface mode. * @mac_select_pcs: Select a PCS for the interface mode. * @mac_prepare: prepare for a major reconfiguration of the interface. @@ -239,9 +238,6 @@ void phylink_limit_mac_speed(struct phylink_config *config, u32 max_speed); * The individual methods are described more fully below. */ struct phylink_mac_ops { - void (*validate)(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state); unsigned long (*mac_get_caps)(struct phylink_config *config, phy_interface_t interface); struct phylink_pcs *(*mac_select_pcs)(struct phylink_config *config, @@ -261,40 +257,6 @@ struct phylink_mac_ops { }; #if 0 /* For kernel-doc purposes only. */ -/** - * validate - Validate and update the link configuration - * @config: a pointer to a &struct phylink_config. - * @supported: ethtool bitmask for supported link modes. - * @state: a pointer to a &struct phylink_link_state. - * - * Clear bits in the @supported and @state->advertising masks that - * are not supportable by the MAC. - * - * Note that the PHY may be able to transform from one connection - * technology to another, so, eg, don't clear 1000BaseX just - * because the MAC is unable to BaseX mode. This is more about - * clearing unsupported speeds and duplex settings. The port modes - * should not be cleared; phylink_set_port_modes() will help with this. - * - * When @config->supported_interfaces has been set, phylink will iterate - * over the supported interfaces to determine the full capability of the - * MAC. The validation function must not print errors if @state->interface - * is set to an unexpected value. - * - * When @config->supported_interfaces is empty, phylink will call this - * function with @state->interface set to %PHY_INTERFACE_MODE_NA, and - * expects the MAC driver to return all supported link modes. - * - * If the @state->interface mode is not supported, then the @supported - * mask must be cleared. - * - * This member is optional; if not set, the generic validator will be - * used making use of @config->mac_capabilities and - * @config->supported_interfaces to determine which link modes are - * supported. - */ -void validate(struct phylink_config *config, unsigned long *supported, - struct phylink_link_state *state); /** * mac_get_caps: Get MAC capabilities for interface mode. * @config: a pointer to a &struct phylink_config. -- cgit v1.2.3 From 743f6397623edc708eda76ecc20e70032166e573 Mon Sep 17 00:00:00 2001 From: "Russell King (Oracle)" Date: Mon, 16 Oct 2023 16:43:08 +0100 Subject: net: phylink: remove a bunch of unused validation methods Remove exports for phylink_caps_to_linkmodes(), phylink_get_capabilities(), phylink_validate_mask_caps() and phylink_generic_validate(). Also, as phylink_generic_validate() is no longer called, we can remove its implementation as well. Signed-off-by: Russell King (Oracle) Link: https://lore.kernel.org/r/E1qsPkK-009wip-W9@rmk-PC.armlinux.org.uk Signed-off-by: Jakub Kicinski --- include/linux/phylink.h | 11 ----------- 1 file changed, 11 deletions(-) (limited to 'include/linux') diff --git a/include/linux/phylink.h b/include/linux/phylink.h index 0cf559bae1ff..875439ab45de 100644 --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@ -613,17 +613,6 @@ void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode, phy_interface_t interface, int speed, int duplex); #endif -void phylink_caps_to_linkmodes(unsigned long *linkmodes, unsigned long caps); -unsigned long phylink_get_capabilities(phy_interface_t interface, - unsigned long mac_capabilities, - int rate_matching); -void phylink_validate_mask_caps(unsigned long *supported, - struct phylink_link_state *state, - unsigned long caps); -void phylink_generic_validate(struct phylink_config *config, - unsigned long *supported, - struct phylink_link_state *state); - struct phylink *phylink_create(struct phylink_config *, const struct fwnode_handle *, phy_interface_t, -- cgit v1.2.3 From e0d4593140b01b8da513a0c88c26da28b4906413 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 11 Oct 2023 09:59:38 +0200 Subject: netfilter: make nftables drops visible in net dropmonitor net_dropmonitor blames core.c:nf_hook_slow. Add NF_DROP_REASON() helper and use it in nft_do_chain(). The helper releases the skb, so exact drop location becomes available. Calling code will observe the NF_STOLEN verdict instead. Adjust nf_hook_slow so we can embed an erro value wih NF_STOLEN verdicts, just like we do for NF_DROP. After this, drop in nftables can be pinpointed to a drop due to a rule or the chain policy. Signed-off-by: Florian Westphal --- include/linux/netfilter.h | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index d68644b7c299..80900d910992 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -22,6 +22,16 @@ static inline int NF_DROP_GETERR(int verdict) return -(verdict >> NF_VERDICT_QBITS); } +static __always_inline int +NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err) +{ + BUILD_BUG_ON(err > 0xffff); + + kfree_skb_reason(skb, reason); + + return ((err << 16) | NF_STOLEN); +} + static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) { -- cgit v1.2.3 From 26c5334d344db7a9bffa1f5ce87d9045b5e90383 Mon Sep 17 00:00:00 2001 From: Paul Greenwalt Date: Sun, 15 Oct 2023 19:43:02 -0400 Subject: ethtool: Add forced speed to supported link modes maps The need to map Ethtool forced speeds to Ethtool supported link modes is common among drivers. To support this, add a common structure for forced speed maps and a function to init them. This is solution was originally introduced in commit 1d4e4ecccb11 ("qede: populate supported link modes maps on module init") for qede driver. ethtool_forced_speed_maps_init() should be called during driver init with an array of struct ethtool_forced_speed_map to populate the mapping. Definitions for maps themselves are left in the driver code, as the sets of supported link modes may vary between the devices. Suggested-by: Andrew Lunn Reviewed-by: Jacob Keller Reviewed-by: Przemek Kitszel Signed-off-by: Pawel Chmielewski Signed-off-by: Paul Greenwalt Reviewed-by: Simon Horman Signed-off-by: David S. Miller --- include/linux/ethtool.h | 37 +++++++++++++++++++++++++++++++++++++ include/linux/linkmode.h | 29 +++++++++++++++-------------- 2 files changed, 52 insertions(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 62b61527bcc4..8e91e8b8a693 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -13,6 +13,7 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H +#include #include #include #include @@ -1052,4 +1053,40 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add, * next string. */ extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...); + +/* Link mode to forced speed capabilities maps */ +struct ethtool_forced_speed_map { + u32 speed; + __ETHTOOL_DECLARE_LINK_MODE_MASK(caps); + + const u32 *cap_arr; + u32 arr_size; +}; + +#define ETHTOOL_FORCED_SPEED_MAP(prefix, value) \ +{ \ + .speed = SPEED_##value, \ + .cap_arr = prefix##_##value, \ + .arr_size = ARRAY_SIZE(prefix##_##value), \ +} + +/** + * ethtool_forced_speed_maps_init + * @maps: Pointer to an array of Ethtool forced speed map + * @size: Array size + * + * Initialize an array of Ethtool forced speed map to Ethtool link modes. This + * should be called during driver module init. + */ +static inline void +ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) +{ + for (u32 i = 0; i < size; i++) { + struct ethtool_forced_speed_map *map = &maps[i]; + + linkmode_set_bit_array(map->cap_arr, map->arr_size, map->caps); + map->cap_arr = NULL; + map->arr_size = 0; + } +} #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index 15e0e0209da4..cd38f89553e6 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -2,6 +2,21 @@ #define __LINKMODE_H #include + +static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) +{ + __set_bit(nr, addr); +} + +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + #include #include @@ -38,20 +53,6 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_set_bit_array(const int *array, int array_size, - unsigned long *addr) -{ - int i; - - for (i = 0; i < array_size; i++) - linkmode_set_bit(array[i], addr); -} - static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); -- cgit v1.2.3 From 1dbfe73bd648bdc3a2d8c9e5b23ae70e3333b592 Mon Sep 17 00:00:00 2001 From: Johannes Zink Date: Wed, 18 Oct 2023 09:09:55 +0200 Subject: net: stmmac: intel: remove unnecessary field struct plat_stmmacenet_data::ext_snapshot_num Do not store bitmask for enabling AUX_SNAPSHOT0. The previous commit ("net: stmmac: fix PPS capture input index") takes care of calculating the proper bit mask from the request data's extts.index field, which is 0 if not explicitly specified otherwise. Signed-off-by: Johannes Zink Signed-off-by: Paolo Abeni --- include/linux/stmmac.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h index c0079a7574ae..0b4658a7eceb 100644 --- a/include/linux/stmmac.h +++ b/include/linux/stmmac.h @@ -303,7 +303,6 @@ struct plat_stmmacenet_data { unsigned int eee_usecs_rate; struct pci_dev *pdev; int int_snapshot_num; - int ext_snapshot_num; int msi_mac_vec; int msi_wol_vec; int msi_lpi_vec; -- cgit v1.2.3 From 7f3eb2174512fe6c9c0f062e96eccb0d3cc6d5cd Mon Sep 17 00:00:00 2001 From: Christian Marangi Date: Wed, 18 Oct 2023 14:35:47 +0200 Subject: net: introduce napi_is_scheduled helper We currently have napi_if_scheduled_mark_missed that can be used to check if napi is scheduled but that does more thing than simply checking it and return a bool. Some driver already implement custom function to check if napi is scheduled. Drop these custom function and introduce napi_is_scheduled that simply check if napi is scheduled atomically. Update any driver and code that implement a similar check and instead use this new helper. Signed-off-by: Christian Marangi Signed-off-by: Paolo Abeni --- include/linux/netdevice.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 1c7681263d30..b8bf669212cc 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -482,6 +482,29 @@ static inline bool napi_prefer_busy_poll(struct napi_struct *n) return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); } +/** + * napi_is_scheduled - test if NAPI is scheduled + * @n: NAPI context + * + * This check is "best-effort". With no locking implemented, + * a NAPI can be scheduled or terminate right after this check + * and produce not precise results. + * + * NAPI_STATE_SCHED is an internal state, napi_is_scheduled + * should not be used normally and napi_schedule should be + * used instead. + * + * Use only if the driver really needs to check if a NAPI + * is scheduled for example in the context of delayed timer + * that can be skipped if a NAPI is already scheduled. + * + * Return True if NAPI is scheduled, False otherwise. + */ +static inline bool napi_is_scheduled(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_SCHED, &n->state); +} + bool napi_schedule_prep(struct napi_struct *n); /** -- cgit v1.2.3 From 6da88306811b40a207c94c9da9faf07bdb20776e Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:39 +0800 Subject: cgroup: Prepare for using css_task_iter_*() in BPF This patch makes some preparations for using css_task_iter_*() in BPF Program. 1. Flags CSS_TASK_ITER_* are #define-s and it's not easy for bpf prog to use them. Convert them to enum so bpf prog can take them from vmlinux.h. 2. In the next patch we will add css_task_iter_*() in common kfuncs which is not safe. Since css_task_iter_*() does spin_unlock_irq() which might screw up irq flags depending on the context where bpf prog is running. So we should use irqsave/irqrestore here and the switching is harmless. Suggested-by: Alexei Starovoitov Signed-off-by: Chuyi Zhou Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20231018061746.111364-2-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/cgroup.h | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b307013b9c6c..0ef0af66080e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -40,13 +40,11 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 -/* walk only threadgroup leaders */ -#define CSS_TASK_ITER_PROCS (1U << 0) -/* walk all threaded css_sets in the domain */ -#define CSS_TASK_ITER_THREADED (1U << 1) - -/* internal flags */ -#define CSS_TASK_ITER_SKIPPED (1U << 16) +enum { + CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ + CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ +}; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { -- cgit v1.2.3 From dfab99df147b0d364f0c199f832ff2aedfb2265a Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:43 +0800 Subject: bpf: teach the verifier to enforce css_iter and task_iter in RCU CS css_iter and task_iter should be used in rcu section. Specifically, in sleepable progs explicit bpf_rcu_read_lock() is needed before use these iters. In normal bpf progs that have implicit rcu_read_lock(), it's OK to use them directly. This patch adds a new a KF flag KF_RCU_PROTECTED for bpf_iter_task_new and bpf_iter_css_new. It means the kfunc should be used in RCU CS. We check whether we are in rcu cs before we want to invoke this kfunc. If the rcu protection is guaranteed, we would let st->type = PTR_TO_STACK | MEM_RCU. Once user do rcu_unlock during the iteration, state MEM_RCU of regs would be cleared. is_iter_reg_valid_init() will reject if reg->type is UNTRUSTED. It is worth noting that currently, bpf_rcu_read_unlock does not clear the state of the STACK_ITER reg, since bpf_for_each_spilled_reg only considers STACK_SPILL. This patch also let bpf_for_each_spilled_reg search STACK_ITER. Signed-off-by: Chuyi Zhou Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231018061746.111364-6-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 19 +++++++++++-------- include/linux/btf.h | 1 + 2 files changed, 12 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 94ec766432f5..e67cd45a85be 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -386,19 +386,18 @@ struct bpf_verifier_state { u32 jmp_history_cnt; }; -#define bpf_get_spilled_reg(slot, frame) \ +#define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -#define bpf_for_each_spilled_reg(iter, frame, reg) \ - for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ +#define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ - iter++, reg = bpf_get_spilled_reg(iter, frame)) + iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) -/* Invoke __expr over regsiters in __vst, setting __state and __reg */ -#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ +#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ @@ -410,7 +409,7 @@ struct bpf_verifier_state { __reg = &___regs[___j]; \ (void)(__expr); \ } \ - bpf_for_each_spilled_reg(___j, __state, __reg) { \ + bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ @@ -418,6 +417,10 @@ struct bpf_verifier_state { } \ }) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; diff --git a/include/linux/btf.h b/include/linux/btf.h index 928113a80a95..c2231c64d60b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -74,6 +74,7 @@ #define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ +#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the -- cgit v1.2.3 From f600bb612b06adf70ccdefbd3294c71275b650c2 Mon Sep 17 00:00:00 2001 From: Oleksij Rempel Date: Thu, 19 Oct 2023 13:14:58 +0200 Subject: net: dsa: microchip: ksz8: Enable MIIM PHY Control reg access Provide access to MIIM PHY Control register (Reg. 31) through ksz8_r_phy_ctrl() and ksz8_w_phy_ctrl() functions. Necessary for upcoming micrel.c patch to address forced link mode configuration. Closes: https://lore.kernel.org/oe-kbuild-all/202310112224.iYgvjBUy-lkp@intel.com/ Reported-by: kernel test robot Signed-off-by: Oleksij Rempel Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index 4e27ca7c49de..591bf5b5e8dc 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -64,6 +64,10 @@ #define KSZ886X_BMCR_DISABLE_TRANSMIT BIT(1) #define KSZ886X_BMCR_DISABLE_LED BIT(0) +/* PHY Special Control/Status Register (Reg 31) */ #define KSZ886X_CTRL_MDIX_STAT BIT(4) +#define KSZ886X_CTRL_FORCE_LINK BIT(3) +#define KSZ886X_CTRL_PWRSAVE BIT(2) +#define KSZ886X_CTRL_REMOTE_LOOPBACK BIT(1) #endif /* _MICREL_PHY_H */ -- cgit v1.2.3 From 20c6e05bd33deaa6fa890252d7ffc5ad54a0942c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 19 Oct 2023 08:28:15 -0700 Subject: ethtool: untangle the linkmode and ethtool headers Commit 26c5334d344d ("ethtool: Add forced speed to supported link modes maps") added a dependency between ethtool.h and linkmode.h. The dependency in the opposite direction already exists so the new code was inserted in an awkward place. The reason for ethtool.h to include linkmode.h, is that ethtool_forced_speed_maps_init() is a static inline helper. That's not really necessary. Signed-off-by: Jakub Kicinski Reviewed-by: Paul Greenwalt Reviewed-by: Russell King (Oracle) Reviewed-by: Vladimir Oltean Signed-off-by: David S. Miller --- include/linux/ethtool.h | 22 ++-------------------- include/linux/linkmode.h | 29 ++++++++++++++--------------- 2 files changed, 16 insertions(+), 35 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 8e91e8b8a693..226a36ed5aa1 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -13,7 +13,6 @@ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H -#include #include #include #include @@ -1070,23 +1069,6 @@ struct ethtool_forced_speed_map { .arr_size = ARRAY_SIZE(prefix##_##value), \ } -/** - * ethtool_forced_speed_maps_init - * @maps: Pointer to an array of Ethtool forced speed map - * @size: Array size - * - * Initialize an array of Ethtool forced speed map to Ethtool link modes. This - * should be called during driver module init. - */ -static inline void -ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size) -{ - for (u32 i = 0; i < size; i++) { - struct ethtool_forced_speed_map *map = &maps[i]; - - linkmode_set_bit_array(map->cap_arr, map->arr_size, map->caps); - map->cap_arr = NULL; - map->arr_size = 0; - } -} +void +ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size); #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h index cd38f89553e6..7303b4bc2ce0 100644 --- a/include/linux/linkmode.h +++ b/include/linux/linkmode.h @@ -2,21 +2,6 @@ #define __LINKMODE_H #include - -static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) -{ - __set_bit(nr, addr); -} - -static inline void linkmode_set_bit_array(const int *array, int array_size, - unsigned long *addr) -{ - int i; - - for (i = 0; i < array_size; i++) - linkmode_set_bit(array[i], addr); -} - #include #include @@ -53,6 +38,11 @@ static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1, return bitmap_andnot(dst, src1, src2, __ETHTOOL_LINK_MODE_MASK_NBITS); } +static inline void linkmode_set_bit(int nr, volatile unsigned long *addr) +{ + __set_bit(nr, addr); +} + static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr) { __clear_bit(nr, addr); @@ -72,6 +62,15 @@ static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr) return test_bit(nr, addr); } +static inline void linkmode_set_bit_array(const int *array, int array_size, + unsigned long *addr) +{ + int i; + + for (i = 0; i < array_size; i++) + linkmode_set_bit(array[i], addr); +} + static inline int linkmode_equal(const unsigned long *src1, const unsigned long *src2) { -- cgit v1.2.3 From b460bc8302f222d346f0c15bba980eb8c36d6278 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 20 Oct 2023 21:31:57 +0800 Subject: mm/percpu.c: introduce pcpu_alloc_size() Introduce pcpu_alloc_size() to get the size of the dynamic per-cpu area. It will be used by bpf memory allocator in the following patches. BPF memory allocator maintains per-cpu area caches for multiple area sizes and its free API only has the to-be-freed per-cpu pointer, so it needs the size of dynamic per-cpu area to select the corresponding cache when bpf program frees the dynamic per-cpu pointer. Acked-by: Dennis Zhou Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20231020133202.4043247-3-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/percpu.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/percpu.h b/include/linux/percpu.h index 68fac2e7cbe6..8c677f185901 100644 --- a/include/linux/percpu.h +++ b/include/linux/percpu.h @@ -132,6 +132,7 @@ extern void __init setup_per_cpu_areas(void); extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __alloc_size(1); extern void __percpu *__alloc_percpu(size_t size, size_t align) __alloc_size(1); extern void free_percpu(void __percpu *__pdata); +extern size_t pcpu_alloc_size(void __percpu *__pdata); DEFINE_FREE(free_percpu, void __percpu *, free_percpu(_T)) -- cgit v1.2.3 From 3f2189e4f77b7a3e979d143dc4ff586488c7e8a5 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 20 Oct 2023 21:31:59 +0800 Subject: bpf: Use pcpu_alloc_size() in bpf_mem_free{_rcu}() For bpf_global_percpu_ma, the pointer passed to bpf_mem_free_rcu() is allocated by kmalloc() and its size is fixed (16-bytes on x86-64). So no matter which cache allocates the dynamic per-cpu area, on x86-64 cache[2] will always be used to free the per-cpu area. Fix the unbalance by checking whether the bpf memory allocator is per-cpu or not and use pcpu_alloc_size() instead of ksize() to find the correct cache for per-cpu free. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20231020133202.4043247-5-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_mem_alloc.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h index d644bbb298af..bb1223b21308 100644 --- a/include/linux/bpf_mem_alloc.h +++ b/include/linux/bpf_mem_alloc.h @@ -11,6 +11,7 @@ struct bpf_mem_caches; struct bpf_mem_alloc { struct bpf_mem_caches __percpu *caches; struct bpf_mem_cache __percpu *cache; + bool percpu; struct work_struct work; }; -- cgit v1.2.3 From e581a3461de3f129cfe888a67d9f31086328271f Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 20 Oct 2023 21:32:00 +0800 Subject: bpf: Move the declaration of __bpf_obj_drop_impl() to bpf.h both syscall.c and helpers.c have the declaration of __bpf_obj_drop_impl(), so just move it to a common header file. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20231020133202.4043247-6-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index b4b40b45962b..ebd412179771 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2058,6 +2058,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); -- cgit v1.2.3 From e383a45902337356d9ccad797094a27c6b2150f9 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 20 Oct 2023 21:32:01 +0800 Subject: bpf: Use bpf_global_percpu_ma for per-cpu kptr in __bpf_obj_drop_impl() The following warning was reported when running "./test_progs -t test_bpf_ma/percpu_free_through_map_free": ------------[ cut here ]------------ WARNING: CPU: 1 PID: 68 at kernel/bpf/memalloc.c:342 CPU: 1 PID: 68 Comm: kworker/u16:2 Not tainted 6.6.0-rc2+ #222 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996) Workqueue: events_unbound bpf_map_free_deferred RIP: 0010:bpf_mem_refill+0x21c/0x2a0 ...... Call Trace: ? bpf_mem_refill+0x21c/0x2a0 irq_work_single+0x27/0x70 irq_work_run_list+0x2a/0x40 irq_work_run+0x18/0x40 __sysvec_irq_work+0x1c/0xc0 sysvec_irq_work+0x73/0x90 asm_sysvec_irq_work+0x1b/0x20 RIP: 0010:unit_free+0x50/0x80 ...... bpf_mem_free+0x46/0x60 __bpf_obj_drop_impl+0x40/0x90 bpf_obj_free_fields+0x17d/0x1a0 array_map_free+0x6b/0x170 bpf_map_free_deferred+0x54/0xa0 process_scheduled_works+0xba/0x370 worker_thread+0x16d/0x2e0 kthread+0x105/0x140 ret_from_fork+0x39/0x60 ret_from_fork_asm+0x1b/0x30 ---[ end trace 0000000000000000 ]--- The reason is simple: __bpf_obj_drop_impl() does not know the freeing field is a per-cpu pointer and it uses bpf_global_ma to free the pointer. Because bpf_global_ma is not a per-cpu allocator, so ksize() is used to select the corresponding cache. The bpf_mem_cache with 16-bytes unit_size will always be selected to do the unmatched free and it will trigger the warning in free_bulk() eventually. Because per-cpu kptr doesn't support list or rb-tree now, so fix the problem by only checking whether or not the type of kptr is per-cpu in bpf_obj_free_fields(), and using bpf_global_percpu_ma to these kptrs. Signed-off-by: Hou Tao Link: https://lore.kernel.org/r/20231020133202.4043247-7-houtao@huaweicloud.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index ebd412179771..b4825d3cdb29 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2058,7 +2058,7 @@ struct btf_record *btf_record_dup(const struct btf_record *rec); bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b); void bpf_obj_free_timer(const struct btf_record *rec, void *obj); void bpf_obj_free_fields(const struct btf_record *rec, void *obj); -void __bpf_obj_drop_impl(void *p, const struct btf_record *rec); +void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu); struct bpf_map *bpf_map_get(u32 ufd); struct bpf_map *bpf_map_get_with_uref(u32 ufd); -- cgit v1.2.3 From 3d44de9a10ea2b1658dfaed8ea6d3d7b6e0defbb Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Oct 2023 12:57:45 +0000 Subject: tcp: add RTAX_FEATURE_TCP_USEC_TS This new dst feature flag will be used to allow TCP to use usec based timestamps instead of msec ones. ip route .... feature tcp_usec_ts Also document that RTAX_FEATURE_SACK and RTAX_FEATURE_TIMESTAMP are unused. RTAX_FEATURE_ALLFRAG is also going away soon. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index e15452df9804..04a0e647ef74 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -576,4 +576,9 @@ void tcp_sock_set_quickack(struct sock *sk, int val); int tcp_sock_set_syncnt(struct sock *sk, int val); int tcp_sock_set_user_timeout(struct sock *sk, int val); +static inline bool dst_tcp_usec_ts(const struct dst_entry *dst) +{ + return dst_feature(dst, RTAX_FEATURE_TCP_USEC_TS); +} + #endif /* _LINUX_TCP_H */ -- cgit v1.2.3 From 614e8316aa4cafba3e204cb8ee48bd12b92f3d93 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 20 Oct 2023 12:57:47 +0000 Subject: tcp: add support for usec resolution in TCP TS values Back in 2015, Van Jacobson suggested to use usec resolution in TCP TS values. This has been implemented in our private kernels. Goals were : 1) better observability of delays in networking stacks. 2) better disambiguation of events based on TSval/ecr values. 3) building block for congestion control modules needing usec resolution. Back then we implemented a schem based on private SYN options to negotiate the feature. For upstream submission, we chose to use a route attribute, because this feature is probably going to be used in private networks [1] [2]. ip route add 10/8 ... features tcp_usec_ts Note that RFC 7323 recommends a "timestamp clock frequency in the range 1 ms to 1 sec per tick.", but also mentions "the maximum acceptable clock frequency is one tick every 59 ns." [1] Unfortunately RFC 7323 5.5 (Outdated Timestamps) suggests to invalidate TS.Recent values after a flow was idle for more than 24 days. This is the part making usec_ts a problem for peers following this recommendation for long living idle flows. [2] Attempts to standardize usec ts went nowhere: https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-tcp-options-for-low-latency-00.pdf https://datatracker.ietf.org/doc/draft-wang-tcpm-low-latency-opt/ Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 04a0e647ef74..6df715b6e51d 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -152,6 +152,7 @@ struct tcp_request_sock { u64 snt_synack; /* first SYNACK sent time */ bool tfo_listener; bool is_mptcp; + s8 req_usec_ts; #if IS_ENABLED(CONFIG_MPTCP) bool drop_req; #endif @@ -257,7 +258,8 @@ struct tcp_sock { u8 compressed_ack; u8 dup_ack_counter:2, tlp_retrans:1, /* TLP is a retransmission */ - unused:5; + tcp_usec_ts:1, /* TSval values in usec */ + unused:4; u32 chrono_start; /* Start time in jiffies of a TCP chrono */ u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */ u8 chrono_type:2, /* current chronograph type */ -- cgit v1.2.3 From 89141f965325de9aac3805cd506df788179b2809 Mon Sep 17 00:00:00 2001 From: Dmitry Antipov Date: Wed, 4 Oct 2023 18:30:29 +0300 Subject: wifi: remove unused argument of ieee80211_get_tdls_action() Remove unused 'hdr_size' argument of 'ieee80211_get_tdls_action()' and adjust 'ieee80211_report_used_skb()' accordingly. Signed-off-by: Dmitry Antipov Link: https://lore.kernel.org/r/20231004153032.206134-1-dmantipov@yandex.ru Signed-off-by: Johannes Berg --- include/linux/ieee80211.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 62b4469c6866..045a776ee547 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -4490,12 +4490,11 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim, /** * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet) * @skb: the skb containing the frame, length will not be checked - * @hdr_size: the size of the ieee80211_hdr that starts at skb->data * * This function assumes the frame is a data frame, and that the network header * is in the correct place. */ -static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size) +static inline int ieee80211_get_tdls_action(struct sk_buff *skb) { if (!skb_is_nonlinear(skb) && skb->len > (skb_network_offset(skb) + 2)) { -- cgit v1.2.3 From 2793a8b015f7f1caadb9bce9c63dc659f7522676 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 24 Oct 2023 03:09:13 +0300 Subject: bpf: exact states comparison for iterator convergence checks Convergence for open coded iterators is computed in is_state_visited() by examining states with branches count > 1 and using states_equal(). states_equal() computes sub-state relation using read and precision marks. Read and precision marks are propagated from children states, thus are not guaranteed to be complete inside a loop when branches count > 1. This could be demonstrated using the following unsafe program: 1. r7 = -16 2. r6 = bpf_get_prandom_u32() 3. while (bpf_iter_num_next(&fp[-8])) { 4. if (r6 != 42) { 5. r7 = -32 6. r6 = bpf_get_prandom_u32() 7. continue 8. } 9. r0 = r10 10. r0 += r7 11. r8 = *(u64 *)(r0 + 0) 12. r6 = bpf_get_prandom_u32() 13. } Here verifier would first visit path 1-3, create a checkpoint at 3 with r7=-16, continue to 4-7,3 with r7=-32. Because instructions at 9-12 had not been visitied yet existing checkpoint at 3 does not have read or precision mark for r7. Thus states_equal() would return true and verifier would discard current state, thus unsafe memory access at 11 would not be caught. This commit fixes this loophole by introducing exact state comparisons for iterator convergence logic: - registers are compared using regs_exact() regardless of read or precision marks; - stack slots have to have identical type. Unfortunately, this is too strict even for simple programs like below: i = 0; while(iter_next(&it)) i++; At each iteration step i++ would produce a new distinct state and eventually instruction processing limit would be reached. To avoid such behavior speculatively forget (widen) range for imprecise scalar registers, if those registers were not precise at the end of the previous iteration and do not match exactly. This a conservative heuristic that allows to verify wide range of programs, however it precludes verification of programs that conjure an imprecise value on the first loop iteration and use it as precise on the second. Test case iter_task_vma_for_each() presents one of such cases: unsigned int seen = 0; ... bpf_for_each(task_vma, vma, task, 0) { if (seen >= 1000) break; ... seen++; } Here clang generates the following code: : 24: r8 = r6 ; stash current value of ... body ... 'seen' 29: r1 = r10 30: r1 += -0x8 31: call bpf_iter_task_vma_next 32: r6 += 0x1 ; seen++; 33: if r0 == 0x0 goto +0x2 ; exit on next() == NULL 34: r7 += 0x10 35: if r8 < 0x3e7 goto -0xc ; loop on seen < 1000 : ... exit ... Note that counter in r6 is copied to r8 and then incremented, conditional jump is done using r8. Because of this precision mark for r6 lags one state behind of precision mark on r8 and widening logic kicks in. Adding barrier_var(seen) after conditional is sufficient to force clang use the same register for both counting and conditional jump. This issue was discussed in the thread [1] which was started by Andrew Werner demonstrating a similar bug in callback functions handling. The callbacks would be addressed in a followup patch. [1] https://lore.kernel.org/bpf/97a90da09404c65c8e810cf83c94ac703705dc0e.camel@gmail.com/ Co-developed-by: Andrii Nakryiko Co-developed-by: Alexei Starovoitov Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20231024000917.12153-4-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index e67cd45a85be..38b788228594 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -384,6 +384,7 @@ struct bpf_verifier_state { */ struct bpf_idx_pair *jmp_history; u32 jmp_history_cnt; + u32 dfs_depth; }; #define bpf_get_spilled_reg(slot, frame, mask) \ -- cgit v1.2.3 From 2a0992829ea3864939d917a5c7b48be6629c6217 Mon Sep 17 00:00:00 2001 From: Eduard Zingerman Date: Tue, 24 Oct 2023 03:09:15 +0300 Subject: bpf: correct loop detection for iterators convergence It turns out that .branches > 0 in is_state_visited() is not a sufficient condition to identify if two verifier states form a loop when iterators convergence is computed. This commit adds logic to distinguish situations like below: (I) initial (II) initial | | V V .---------> hdr .. | | | | V V | .------... .------.. | | | | | | V V V V | ... ... .-> hdr .. | | | | | | | V V | V V | succ <- cur | succ <- cur | | | | | V | V | ... | ... | | | | '----' '----' For both (I) and (II) successor 'succ' of the current state 'cur' was previously explored and has branches count at 0. However, loop entry 'hdr' corresponding to 'succ' might be a part of current DFS path. If that is the case 'succ' and 'cur' are members of the same loop and have to be compared exactly. Co-developed-by: Andrii Nakryiko Co-developed-by: Alexei Starovoitov Reviewed-by: Andrii Nakryiko Signed-off-by: Eduard Zingerman Link: https://lore.kernel.org/r/20231024000917.12153-6-eddyz87@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 15 +++++++++++++++ 1 file changed, 15 insertions(+) (limited to 'include/linux') diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b788228594..24213a99cc79 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -373,10 +373,25 @@ struct bpf_verifier_state { struct bpf_active_lock active_lock; bool speculative; bool active_rcu_lock; + /* If this state was ever pointed-to by other state's loop_entry field + * this flag would be set to true. Used to avoid freeing such states + * while they are still in use. + */ + bool used_as_loop_entry; /* first and last insn idx of this verifier state */ u32 first_insn_idx; u32 last_insn_idx; + /* If this state is a part of states loop this field points to some + * parent of this state such that: + * - it is also a member of the same states loop; + * - DFS states traversal starting from initial state visits loop_entry + * state before this state. + * Used to compute topmost loop entry for state loops. + * State loops might appear because of open coded iterators logic. + * See get_loop_entry() for more information. + */ + struct bpf_verifier_state *loop_entry; /* jmp history recorded from first to last. * backtracking is using it to go from last to first. * For most states jmp_history_cnt is [0-3]. -- cgit v1.2.3 From 6ca80638b90cec66547011ee1ef79e534589989a Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Mon, 23 Oct 2023 11:17:28 -0700 Subject: net: dsa: Use conduit and user terms Use more inclusive terms throughout the DSA subsystem by moving away from "master" which is replaced by "conduit" and "slave" which is replaced by "user". No functional changes. Acked-by: Rob Herring Acked-by: Stephen Hemminger Reviewed-by: Vladimir Oltean Signed-off-by: Florian Fainelli Link: https://lore.kernel.org/r/20231023181729.1191071-2-florian.fainelli@broadcom.com Signed-off-by: Jakub Kicinski --- include/linux/dsa/sja1105.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h index c177322f793d..b9dd35d4b8f5 100644 --- a/include/linux/dsa/sja1105.h +++ b/include/linux/dsa/sja1105.h @@ -28,7 +28,7 @@ /* Source and Destination MAC of follow-up meta frames. * Whereas the choice of SMAC only affects the unique identification of the * switch as sender of meta frames, the DMAC must be an address that is present - * in the DSA master port's multicast MAC filter. + * in the DSA conduit port's multicast MAC filter. * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588 * over L2 use this address for some purpose already. */ -- cgit v1.2.3 From c845f5f3590ef4669fe5464f8a42be6442cd174b Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:21:54 +0100 Subject: net/tcp: Add TCP-AO config and structures Introduce new kernel config option and common structures as well as helpers to be used by TCP-AO code. Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/tcp.h | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 6df715b6e51d..64e7b560fa79 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -447,13 +447,18 @@ struct tcp_sock { bool syn_smc; /* SYN includes SMC */ #endif -#ifdef CONFIG_TCP_MD5SIG -/* TCP AF-Specific parts; only used by MD5 Signature support so far */ +#if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO) +/* TCP AF-Specific parts; only used by TCP-AO/MD5 Signature support so far */ const struct tcp_sock_af_ops *af_specific; +#ifdef CONFIG_TCP_MD5SIG /* TCP MD5 Signature Option information */ struct tcp_md5sig_info __rcu *md5sig_info; #endif +#ifdef CONFIG_TCP_AO + struct tcp_ao_info __rcu *ao_info; +#endif +#endif /* TCP fastopen related information */ struct tcp_fastopen_request *fastopen_req; -- cgit v1.2.3 From 4954f17ddefc51d218625dcdfaf422a253dad3fa Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:21:55 +0100 Subject: net/tcp: Introduce TCP_AO setsockopt()s Add 3 setsockopt()s: 1. TCP_AO_ADD_KEY to add a new Master Key Tuple (MKT) on a socket 2. TCP_AO_DEL_KEY to delete present MKT from a socket 3. TCP_AO_INFO to change flags, Current_key/RNext_key on a TCP-AO sk Userspace has to introduce keys on every socket it wants to use TCP-AO option on, similarly to TCP_MD5SIG/TCP_MD5SIG_EXT. RFC5925 prohibits definition of MKTs that would match the same peer, so do sanity checks on the data provided by userspace. Be as conservative as possible, including refusal of defining MKT on an established connection with no AO, removing the key in-use and etc. (1) and (2) are to be used by userspace key manager to add/remove keys. (3) main purpose is to set RNext_key, which (as prescribed by RFC5925) is the KeyID that will be requested in TCP-AO header from the peer to sign their segments with. At this moment the life of ao_info ends in tcp_v4_destroy_sock(). Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/sockptr.h | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sockptr.h b/include/linux/sockptr.h index bae5e2369b4f..307961b41541 100644 --- a/include/linux/sockptr.h +++ b/include/linux/sockptr.h @@ -55,6 +55,29 @@ static inline int copy_from_sockptr(void *dst, sockptr_t src, size_t size) return copy_from_sockptr_offset(dst, src, 0, size); } +static inline int copy_struct_from_sockptr(void *dst, size_t ksize, + sockptr_t src, size_t usize) +{ + size_t size = min(ksize, usize); + size_t rest = max(ksize, usize) - size; + + if (!sockptr_is_kernel(src)) + return copy_struct_from_user(dst, ksize, src.user, size); + + if (usize < ksize) { + memset(dst + size, 0, rest); + } else if (usize > ksize) { + char *p = src.kernel; + + while (rest--) { + if (*p++) + return -E2BIG; + } + } + memcpy(dst, src.kernel, size); + return 0; +} + static inline int copy_to_sockptr_offset(sockptr_t dst, size_t offset, const void *src, size_t size) { -- cgit v1.2.3 From decde2586b34b99684faff1eab41e5c496c27fb6 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:01 +0100 Subject: net/tcp: Add TCP-AO sign to twsk Add support for sockets in time-wait state. ao_info as well as all keys are inherited on transition to time-wait socket. The lifetime of ao_info is now protected by ref counter, so that tcp_ao_destroy_sock() will destruct it only when the last user is gone. Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/tcp.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 64e7b560fa79..eec6e7e5312e 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -514,6 +514,9 @@ struct tcp_timewait_sock { #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *tw_md5_key; #endif +#ifdef CONFIG_TCP_AO + struct tcp_ao_info __rcu *ao_info; +#endif }; static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk) -- cgit v1.2.3 From 06b22ef29591f625ef877ae00d82192938e29e60 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 23 Oct 2023 20:22:02 +0100 Subject: net/tcp: Wire TCP-AO to request sockets Now when the new request socket is created from the listening socket, it's recorded what MKT was used by the peer. tcp_rsk_used_ao() is a new helper for checking if TCP-AO option was used to create the request socket. tcp_ao_copy_all_matching() will copy all keys that match the peer on the request socket, as well as preparing them for the usage (creating traffic keys). Co-developed-by: Francesco Ruggeri Signed-off-by: Francesco Ruggeri Co-developed-by: Salam Noureddine Signed-off-by: Salam Noureddine Signed-off-by: Dmitry Safonov Acked-by: David Ahern Signed-off-by: David S. Miller --- include/linux/tcp.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'include/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index eec6e7e5312e..ec4e9367f5b0 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -166,6 +166,11 @@ struct tcp_request_sock { * after data-in-SYN. */ u8 syn_tos; +#ifdef CONFIG_TCP_AO + u8 ao_keyid; + u8 ao_rcv_next; + u8 maclen; +#endif }; static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) @@ -173,6 +178,19 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) return (struct tcp_request_sock *)req; } +static inline bool tcp_rsk_used_ao(const struct request_sock *req) +{ + /* The real length of MAC is saved in the request socket, + * signing anything with zero-length makes no sense, so here is + * a little hack.. + */ +#ifndef CONFIG_TCP_AO + return false; +#else + return tcp_rsk(req)->maclen != 0; +#endif +} + #define TCP_RMEM_TO_WIN_SCALE 8 struct tcp_sock { -- cgit v1.2.3 From 62f47bf9e2c00eea457cad8fa43c24ed0282b37a Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 25 Oct 2023 15:30:15 +0300 Subject: net: Add MDB get device operation Add MDB net device operation that will be invoked by rtnetlink code in response to received RTM_GETMDB messages. Subsequent patches will implement the operation in the bridge and VXLAN drivers. Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index b8bf669212cc..a16c9cc063fe 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1609,6 +1609,10 @@ struct net_device_ops { int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb); + int (*ndo_mdb_get)(struct net_device *dev, + struct nlattr *tb[], u32 portid, + u32 seq, + struct netlink_ext_ack *extack); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, -- cgit v1.2.3