From 8a76145a2ec2a81dfe34d7ac42e8c242f095e8c8 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 5 Oct 2022 21:24:51 -0700 Subject: bpf: explicitly define BPF_FUNC_xxx integer values MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Historically enum bpf_func_id's BPF_FUNC_xxx enumerators relied on implicit sequential values being assigned by compiler. This is convenient, as new BPF helpers are always added at the very end, but it also has its downsides, some of them being: - with over 200 helpers now it's very hard to know what's each helper's ID, which is often important to know when working with BPF assembly (e.g., by dumping raw bpf assembly instructions with llvm-objdump -d command). it's possible to work around this by looking into vmlinux.h, dumping /sys/btf/kernel/vmlinux, looking at libbpf-provided bpf_helper_defs.h, etc. But it always feels like an unnecessary step and one should be able to quickly figure this out from UAPI header. - when backporting and cherry-picking only some BPF helpers onto older kernels it's important to be able to skip some enum values for helpers that weren't backported, but preserve absolute integer IDs to keep BPF helper IDs stable so that BPF programs stay portable across upstream and backported kernels. While neither problem is insurmountable, they come up frequently enough and are annoying enough to warrant improving the situation. And for the backporting the problem can easily go unnoticed for a while, especially if backport is done with people not very familiar with BPF subsystem overall. Anyways, it's easy to fix this by making sure that __BPF_FUNC_MAPPER macro provides explicit helper IDs. Unfortunately that would potentially break existing users that use UAPI-exposed __BPF_FUNC_MAPPER and are expected to pass macro that accepts only symbolic helper identifier (e.g., map_lookup_elem for bpf_map_lookup_elem() helper). As such, we need to introduce a new macro (___BPF_FUNC_MAPPER) which would specify both identifier and integer ID, but in such a way as to allow existing __BPF_FUNC_MAPPER be expressed in terms of new ___BPF_FUNC_MAPPER macro. And that's what this patch is doing. To avoid duplication and allow __BPF_FUNC_MAPPER stay *exactly* the same, ___BPF_FUNC_MAPPER accepts arbitrary "context" arguments, which can be used to pass any extra macros, arguments, and whatnot. In our case we use this to pass original user-provided macro that expects single argument and __BPF_FUNC_MAPPER is using it's own three-argument __BPF_FUNC_MAPPER_APPLY intermediate macro to impedance-match new and old "callback" macros. Once we resolve this, we use new ___BPF_FUNC_MAPPER to define enum bpf_func_id with explicit values. The other users of __BPF_FUNC_MAPPER in kernel (namely in kernel/bpf/disasm.c) are kept exactly the same both as demonstration that backwards compat works, but also to avoid unnecessary code churn. Note that new ___BPF_FUNC_MAPPER() doesn't forcefully insert comma between values, as that might not be appropriate in all possible cases where ___BPF_FUNC_MAPPER might be used by users. This doesn't reduce usability, as it's trivial to insert that comma inside "callback" macro. To validate all the manually specified IDs are exactly right, we used BTF to compare before and after values: $ bpftool btf dump file ~/linux-build/default/vmlinux | rg bpf_func_id -A 211 > after.txt $ git stash # stach UAPI changes $ make -j90 ... re-building kernel without UAPI changes ... $ bpftool btf dump file ~/linux-build/default/vmlinux | rg bpf_func_id -A 211 > before.txt $ diff -u before.txt after.txt --- before.txt 2022-10-05 10:48:18.119195916 -0700 +++ after.txt 2022-10-05 10:46:49.446615025 -0700 @@ -1,4 +1,4 @@ -[14576] ENUM 'bpf_func_id' encoding=UNSIGNED size=4 vlen=211 +[9560] ENUM 'bpf_func_id' encoding=UNSIGNED size=4 vlen=211 'BPF_FUNC_unspec' val=0 'BPF_FUNC_map_lookup_elem' val=1 'BPF_FUNC_map_update_elem' val=2 As can be seen from diff above, the only thing that changed was resulting BTF type ID of ENUM bpf_func_id, not any of the enumerators, their names or integer values. The only other place that needed fixing was scripts/bpf_doc.py used to generate man pages and bpf_helper_defs.h header for libbpf and selftests. That script is tightly-coupled to exact shape of ___BPF_FUNC_MAPPER macro definition, so had to be trivially adapted. Cc: Quentin Monnet Reported-by: Andrea Terzolo Signed-off-by: Andrii Nakryiko Reviewed-by: Quentin Monnet Acked-by: Jiri Olsa Acked-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221006042452.2089843-1-andrii@kernel.org Signed-off-by: Alexei Starovoitov --- include/uapi/linux/bpf.h | 432 ++++++++++++++++++++++++----------------------- 1 file changed, 219 insertions(+), 213 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 51b9aa640ad2..17f61338f8f8 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5436,225 +5436,231 @@ union bpf_attr { * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. */ -#define __BPF_FUNC_MAPPER(FN) \ - FN(unspec), \ - FN(map_lookup_elem), \ - FN(map_update_elem), \ - FN(map_delete_elem), \ - FN(probe_read), \ - FN(ktime_get_ns), \ - FN(trace_printk), \ - FN(get_prandom_u32), \ - FN(get_smp_processor_id), \ - FN(skb_store_bytes), \ - FN(l3_csum_replace), \ - FN(l4_csum_replace), \ - FN(tail_call), \ - FN(clone_redirect), \ - FN(get_current_pid_tgid), \ - FN(get_current_uid_gid), \ - FN(get_current_comm), \ - FN(get_cgroup_classid), \ - FN(skb_vlan_push), \ - FN(skb_vlan_pop), \ - FN(skb_get_tunnel_key), \ - FN(skb_set_tunnel_key), \ - FN(perf_event_read), \ - FN(redirect), \ - FN(get_route_realm), \ - FN(perf_event_output), \ - FN(skb_load_bytes), \ - FN(get_stackid), \ - FN(csum_diff), \ - FN(skb_get_tunnel_opt), \ - FN(skb_set_tunnel_opt), \ - FN(skb_change_proto), \ - FN(skb_change_type), \ - FN(skb_under_cgroup), \ - FN(get_hash_recalc), \ - FN(get_current_task), \ - FN(probe_write_user), \ - FN(current_task_under_cgroup), \ - FN(skb_change_tail), \ - FN(skb_pull_data), \ - FN(csum_update), \ - FN(set_hash_invalid), \ - FN(get_numa_node_id), \ - FN(skb_change_head), \ - FN(xdp_adjust_head), \ - FN(probe_read_str), \ - FN(get_socket_cookie), \ - FN(get_socket_uid), \ - FN(set_hash), \ - FN(setsockopt), \ - FN(skb_adjust_room), \ - FN(redirect_map), \ - FN(sk_redirect_map), \ - FN(sock_map_update), \ - FN(xdp_adjust_meta), \ - FN(perf_event_read_value), \ - FN(perf_prog_read_value), \ - FN(getsockopt), \ - FN(override_return), \ - FN(sock_ops_cb_flags_set), \ - FN(msg_redirect_map), \ - FN(msg_apply_bytes), \ - FN(msg_cork_bytes), \ - FN(msg_pull_data), \ - FN(bind), \ - FN(xdp_adjust_tail), \ - FN(skb_get_xfrm_state), \ - FN(get_stack), \ - FN(skb_load_bytes_relative), \ - FN(fib_lookup), \ - FN(sock_hash_update), \ - FN(msg_redirect_hash), \ - FN(sk_redirect_hash), \ - FN(lwt_push_encap), \ - FN(lwt_seg6_store_bytes), \ - FN(lwt_seg6_adjust_srh), \ - FN(lwt_seg6_action), \ - FN(rc_repeat), \ - FN(rc_keydown), \ - FN(skb_cgroup_id), \ - FN(get_current_cgroup_id), \ - FN(get_local_storage), \ - FN(sk_select_reuseport), \ - FN(skb_ancestor_cgroup_id), \ - FN(sk_lookup_tcp), \ - FN(sk_lookup_udp), \ - FN(sk_release), \ - FN(map_push_elem), \ - FN(map_pop_elem), \ - FN(map_peek_elem), \ - FN(msg_push_data), \ - FN(msg_pop_data), \ - FN(rc_pointer_rel), \ - FN(spin_lock), \ - FN(spin_unlock), \ - FN(sk_fullsock), \ - FN(tcp_sock), \ - FN(skb_ecn_set_ce), \ - FN(get_listener_sock), \ - FN(skc_lookup_tcp), \ - FN(tcp_check_syncookie), \ - FN(sysctl_get_name), \ - FN(sysctl_get_current_value), \ - FN(sysctl_get_new_value), \ - FN(sysctl_set_new_value), \ - FN(strtol), \ - FN(strtoul), \ - FN(sk_storage_get), \ - FN(sk_storage_delete), \ - FN(send_signal), \ - FN(tcp_gen_syncookie), \ - FN(skb_output), \ - FN(probe_read_user), \ - FN(probe_read_kernel), \ - FN(probe_read_user_str), \ - FN(probe_read_kernel_str), \ - FN(tcp_send_ack), \ - FN(send_signal_thread), \ - FN(jiffies64), \ - FN(read_branch_records), \ - FN(get_ns_current_pid_tgid), \ - FN(xdp_output), \ - FN(get_netns_cookie), \ - FN(get_current_ancestor_cgroup_id), \ - FN(sk_assign), \ - FN(ktime_get_boot_ns), \ - FN(seq_printf), \ - FN(seq_write), \ - FN(sk_cgroup_id), \ - FN(sk_ancestor_cgroup_id), \ - FN(ringbuf_output), \ - FN(ringbuf_reserve), \ - FN(ringbuf_submit), \ - FN(ringbuf_discard), \ - FN(ringbuf_query), \ - FN(csum_level), \ - FN(skc_to_tcp6_sock), \ - FN(skc_to_tcp_sock), \ - FN(skc_to_tcp_timewait_sock), \ - FN(skc_to_tcp_request_sock), \ - FN(skc_to_udp6_sock), \ - FN(get_task_stack), \ - FN(load_hdr_opt), \ - FN(store_hdr_opt), \ - FN(reserve_hdr_opt), \ - FN(inode_storage_get), \ - FN(inode_storage_delete), \ - FN(d_path), \ - FN(copy_from_user), \ - FN(snprintf_btf), \ - FN(seq_printf_btf), \ - FN(skb_cgroup_classid), \ - FN(redirect_neigh), \ - FN(per_cpu_ptr), \ - FN(this_cpu_ptr), \ - FN(redirect_peer), \ - FN(task_storage_get), \ - FN(task_storage_delete), \ - FN(get_current_task_btf), \ - FN(bprm_opts_set), \ - FN(ktime_get_coarse_ns), \ - FN(ima_inode_hash), \ - FN(sock_from_file), \ - FN(check_mtu), \ - FN(for_each_map_elem), \ - FN(snprintf), \ - FN(sys_bpf), \ - FN(btf_find_by_name_kind), \ - FN(sys_close), \ - FN(timer_init), \ - FN(timer_set_callback), \ - FN(timer_start), \ - FN(timer_cancel), \ - FN(get_func_ip), \ - FN(get_attach_cookie), \ - FN(task_pt_regs), \ - FN(get_branch_snapshot), \ - FN(trace_vprintk), \ - FN(skc_to_unix_sock), \ - FN(kallsyms_lookup_name), \ - FN(find_vma), \ - FN(loop), \ - FN(strncmp), \ - FN(get_func_arg), \ - FN(get_func_ret), \ - FN(get_func_arg_cnt), \ - FN(get_retval), \ - FN(set_retval), \ - FN(xdp_get_buff_len), \ - FN(xdp_load_bytes), \ - FN(xdp_store_bytes), \ - FN(copy_from_user_task), \ - FN(skb_set_tstamp), \ - FN(ima_file_hash), \ - FN(kptr_xchg), \ - FN(map_lookup_percpu_elem), \ - FN(skc_to_mptcp_sock), \ - FN(dynptr_from_mem), \ - FN(ringbuf_reserve_dynptr), \ - FN(ringbuf_submit_dynptr), \ - FN(ringbuf_discard_dynptr), \ - FN(dynptr_read), \ - FN(dynptr_write), \ - FN(dynptr_data), \ - FN(tcp_raw_gen_syncookie_ipv4), \ - FN(tcp_raw_gen_syncookie_ipv6), \ - FN(tcp_raw_check_syncookie_ipv4), \ - FN(tcp_raw_check_syncookie_ipv6), \ - FN(ktime_get_tai_ns), \ - FN(user_ringbuf_drain), \ +#define ___BPF_FUNC_MAPPER(FN, ctx...) \ + FN(unspec, 0, ##ctx) \ + FN(map_lookup_elem, 1, ##ctx) \ + FN(map_update_elem, 2, ##ctx) \ + FN(map_delete_elem, 3, ##ctx) \ + FN(probe_read, 4, ##ctx) \ + FN(ktime_get_ns, 5, ##ctx) \ + FN(trace_printk, 6, ##ctx) \ + FN(get_prandom_u32, 7, ##ctx) \ + FN(get_smp_processor_id, 8, ##ctx) \ + FN(skb_store_bytes, 9, ##ctx) \ + FN(l3_csum_replace, 10, ##ctx) \ + FN(l4_csum_replace, 11, ##ctx) \ + FN(tail_call, 12, ##ctx) \ + FN(clone_redirect, 13, ##ctx) \ + FN(get_current_pid_tgid, 14, ##ctx) \ + FN(get_current_uid_gid, 15, ##ctx) \ + FN(get_current_comm, 16, ##ctx) \ + FN(get_cgroup_classid, 17, ##ctx) \ + FN(skb_vlan_push, 18, ##ctx) \ + FN(skb_vlan_pop, 19, ##ctx) \ + FN(skb_get_tunnel_key, 20, ##ctx) \ + FN(skb_set_tunnel_key, 21, ##ctx) \ + FN(perf_event_read, 22, ##ctx) \ + FN(redirect, 23, ##ctx) \ + FN(get_route_realm, 24, ##ctx) \ + FN(perf_event_output, 25, ##ctx) \ + FN(skb_load_bytes, 26, ##ctx) \ + FN(get_stackid, 27, ##ctx) \ + FN(csum_diff, 28, ##ctx) \ + FN(skb_get_tunnel_opt, 29, ##ctx) \ + FN(skb_set_tunnel_opt, 30, ##ctx) \ + FN(skb_change_proto, 31, ##ctx) \ + FN(skb_change_type, 32, ##ctx) \ + FN(skb_under_cgroup, 33, ##ctx) \ + FN(get_hash_recalc, 34, ##ctx) \ + FN(get_current_task, 35, ##ctx) \ + FN(probe_write_user, 36, ##ctx) \ + FN(current_task_under_cgroup, 37, ##ctx) \ + FN(skb_change_tail, 38, ##ctx) \ + FN(skb_pull_data, 39, ##ctx) \ + FN(csum_update, 40, ##ctx) \ + FN(set_hash_invalid, 41, ##ctx) \ + FN(get_numa_node_id, 42, ##ctx) \ + FN(skb_change_head, 43, ##ctx) \ + FN(xdp_adjust_head, 44, ##ctx) \ + FN(probe_read_str, 45, ##ctx) \ + FN(get_socket_cookie, 46, ##ctx) \ + FN(get_socket_uid, 47, ##ctx) \ + FN(set_hash, 48, ##ctx) \ + FN(setsockopt, 49, ##ctx) \ + FN(skb_adjust_room, 50, ##ctx) \ + FN(redirect_map, 51, ##ctx) \ + FN(sk_redirect_map, 52, ##ctx) \ + FN(sock_map_update, 53, ##ctx) \ + FN(xdp_adjust_meta, 54, ##ctx) \ + FN(perf_event_read_value, 55, ##ctx) \ + FN(perf_prog_read_value, 56, ##ctx) \ + FN(getsockopt, 57, ##ctx) \ + FN(override_return, 58, ##ctx) \ + FN(sock_ops_cb_flags_set, 59, ##ctx) \ + FN(msg_redirect_map, 60, ##ctx) \ + FN(msg_apply_bytes, 61, ##ctx) \ + FN(msg_cork_bytes, 62, ##ctx) \ + FN(msg_pull_data, 63, ##ctx) \ + FN(bind, 64, ##ctx) \ + FN(xdp_adjust_tail, 65, ##ctx) \ + FN(skb_get_xfrm_state, 66, ##ctx) \ + FN(get_stack, 67, ##ctx) \ + FN(skb_load_bytes_relative, 68, ##ctx) \ + FN(fib_lookup, 69, ##ctx) \ + FN(sock_hash_update, 70, ##ctx) \ + FN(msg_redirect_hash, 71, ##ctx) \ + FN(sk_redirect_hash, 72, ##ctx) \ + FN(lwt_push_encap, 73, ##ctx) \ + FN(lwt_seg6_store_bytes, 74, ##ctx) \ + FN(lwt_seg6_adjust_srh, 75, ##ctx) \ + FN(lwt_seg6_action, 76, ##ctx) \ + FN(rc_repeat, 77, ##ctx) \ + FN(rc_keydown, 78, ##ctx) \ + FN(skb_cgroup_id, 79, ##ctx) \ + FN(get_current_cgroup_id, 80, ##ctx) \ + FN(get_local_storage, 81, ##ctx) \ + FN(sk_select_reuseport, 82, ##ctx) \ + FN(skb_ancestor_cgroup_id, 83, ##ctx) \ + FN(sk_lookup_tcp, 84, ##ctx) \ + FN(sk_lookup_udp, 85, ##ctx) \ + FN(sk_release, 86, ##ctx) \ + FN(map_push_elem, 87, ##ctx) \ + FN(map_pop_elem, 88, ##ctx) \ + FN(map_peek_elem, 89, ##ctx) \ + FN(msg_push_data, 90, ##ctx) \ + FN(msg_pop_data, 91, ##ctx) \ + FN(rc_pointer_rel, 92, ##ctx) \ + FN(spin_lock, 93, ##ctx) \ + FN(spin_unlock, 94, ##ctx) \ + FN(sk_fullsock, 95, ##ctx) \ + FN(tcp_sock, 96, ##ctx) \ + FN(skb_ecn_set_ce, 97, ##ctx) \ + FN(get_listener_sock, 98, ##ctx) \ + FN(skc_lookup_tcp, 99, ##ctx) \ + FN(tcp_check_syncookie, 100, ##ctx) \ + FN(sysctl_get_name, 101, ##ctx) \ + FN(sysctl_get_current_value, 102, ##ctx) \ + FN(sysctl_get_new_value, 103, ##ctx) \ + FN(sysctl_set_new_value, 104, ##ctx) \ + FN(strtol, 105, ##ctx) \ + FN(strtoul, 106, ##ctx) \ + FN(sk_storage_get, 107, ##ctx) \ + FN(sk_storage_delete, 108, ##ctx) \ + FN(send_signal, 109, ##ctx) \ + FN(tcp_gen_syncookie, 110, ##ctx) \ + FN(skb_output, 111, ##ctx) \ + FN(probe_read_user, 112, ##ctx) \ + FN(probe_read_kernel, 113, ##ctx) \ + FN(probe_read_user_str, 114, ##ctx) \ + FN(probe_read_kernel_str, 115, ##ctx) \ + FN(tcp_send_ack, 116, ##ctx) \ + FN(send_signal_thread, 117, ##ctx) \ + FN(jiffies64, 118, ##ctx) \ + FN(read_branch_records, 119, ##ctx) \ + FN(get_ns_current_pid_tgid, 120, ##ctx) \ + FN(xdp_output, 121, ##ctx) \ + FN(get_netns_cookie, 122, ##ctx) \ + FN(get_current_ancestor_cgroup_id, 123, ##ctx) \ + FN(sk_assign, 124, ##ctx) \ + FN(ktime_get_boot_ns, 125, ##ctx) \ + FN(seq_printf, 126, ##ctx) \ + FN(seq_write, 127, ##ctx) \ + FN(sk_cgroup_id, 128, ##ctx) \ + FN(sk_ancestor_cgroup_id, 129, ##ctx) \ + FN(ringbuf_output, 130, ##ctx) \ + FN(ringbuf_reserve, 131, ##ctx) \ + FN(ringbuf_submit, 132, ##ctx) \ + FN(ringbuf_discard, 133, ##ctx) \ + FN(ringbuf_query, 134, ##ctx) \ + FN(csum_level, 135, ##ctx) \ + FN(skc_to_tcp6_sock, 136, ##ctx) \ + FN(skc_to_tcp_sock, 137, ##ctx) \ + FN(skc_to_tcp_timewait_sock, 138, ##ctx) \ + FN(skc_to_tcp_request_sock, 139, ##ctx) \ + FN(skc_to_udp6_sock, 140, ##ctx) \ + FN(get_task_stack, 141, ##ctx) \ + FN(load_hdr_opt, 142, ##ctx) \ + FN(store_hdr_opt, 143, ##ctx) \ + FN(reserve_hdr_opt, 144, ##ctx) \ + FN(inode_storage_get, 145, ##ctx) \ + FN(inode_storage_delete, 146, ##ctx) \ + FN(d_path, 147, ##ctx) \ + FN(copy_from_user, 148, ##ctx) \ + FN(snprintf_btf, 149, ##ctx) \ + FN(seq_printf_btf, 150, ##ctx) \ + FN(skb_cgroup_classid, 151, ##ctx) \ + FN(redirect_neigh, 152, ##ctx) \ + FN(per_cpu_ptr, 153, ##ctx) \ + FN(this_cpu_ptr, 154, ##ctx) \ + FN(redirect_peer, 155, ##ctx) \ + FN(task_storage_get, 156, ##ctx) \ + FN(task_storage_delete, 157, ##ctx) \ + FN(get_current_task_btf, 158, ##ctx) \ + FN(bprm_opts_set, 159, ##ctx) \ + FN(ktime_get_coarse_ns, 160, ##ctx) \ + FN(ima_inode_hash, 161, ##ctx) \ + FN(sock_from_file, 162, ##ctx) \ + FN(check_mtu, 163, ##ctx) \ + FN(for_each_map_elem, 164, ##ctx) \ + FN(snprintf, 165, ##ctx) \ + FN(sys_bpf, 166, ##ctx) \ + FN(btf_find_by_name_kind, 167, ##ctx) \ + FN(sys_close, 168, ##ctx) \ + FN(timer_init, 169, ##ctx) \ + FN(timer_set_callback, 170, ##ctx) \ + FN(timer_start, 171, ##ctx) \ + FN(timer_cancel, 172, ##ctx) \ + FN(get_func_ip, 173, ##ctx) \ + FN(get_attach_cookie, 174, ##ctx) \ + FN(task_pt_regs, 175, ##ctx) \ + FN(get_branch_snapshot, 176, ##ctx) \ + FN(trace_vprintk, 177, ##ctx) \ + FN(skc_to_unix_sock, 178, ##ctx) \ + FN(kallsyms_lookup_name, 179, ##ctx) \ + FN(find_vma, 180, ##ctx) \ + FN(loop, 181, ##ctx) \ + FN(strncmp, 182, ##ctx) \ + FN(get_func_arg, 183, ##ctx) \ + FN(get_func_ret, 184, ##ctx) \ + FN(get_func_arg_cnt, 185, ##ctx) \ + FN(get_retval, 186, ##ctx) \ + FN(set_retval, 187, ##ctx) \ + FN(xdp_get_buff_len, 188, ##ctx) \ + FN(xdp_load_bytes, 189, ##ctx) \ + FN(xdp_store_bytes, 190, ##ctx) \ + FN(copy_from_user_task, 191, ##ctx) \ + FN(skb_set_tstamp, 192, ##ctx) \ + FN(ima_file_hash, 193, ##ctx) \ + FN(kptr_xchg, 194, ##ctx) \ + FN(map_lookup_percpu_elem, 195, ##ctx) \ + FN(skc_to_mptcp_sock, 196, ##ctx) \ + FN(dynptr_from_mem, 197, ##ctx) \ + FN(ringbuf_reserve_dynptr, 198, ##ctx) \ + FN(ringbuf_submit_dynptr, 199, ##ctx) \ + FN(ringbuf_discard_dynptr, 200, ##ctx) \ + FN(dynptr_read, 201, ##ctx) \ + FN(dynptr_write, 202, ##ctx) \ + FN(dynptr_data, 203, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv4, 204, ##ctx) \ + FN(tcp_raw_gen_syncookie_ipv6, 205, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv4, 206, ##ctx) \ + FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ + FN(ktime_get_tai_ns, 208, ##ctx) \ + FN(user_ringbuf_drain, 209, ##ctx) \ /* */ +/* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't + * know or care about integer value that is now passed as second argument + */ +#define __BPF_FUNC_MAPPER_APPLY(name, value, FN) FN(name), +#define __BPF_FUNC_MAPPER(FN) ___BPF_FUNC_MAPPER(__BPF_FUNC_MAPPER_APPLY, FN) + /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call */ -#define __BPF_ENUM_FN(x) BPF_FUNC_ ## x +#define __BPF_ENUM_FN(x, y) BPF_FUNC_ ## x = y, enum bpf_func_id { - __BPF_FUNC_MAPPER(__BPF_ENUM_FN) + ___BPF_FUNC_MAPPER(__BPF_ENUM_FN) __BPF_FUNC_MAX_ID, }; #undef __BPF_ENUM_FN -- cgit From 0ff57171d6d225558c81a69439d5323e35b40549 Mon Sep 17 00:00:00 2001 From: Vinayak Yadawad Date: Wed, 7 Sep 2022 18:14:48 +0530 Subject: cfg80211: Update Transition Disable policy during port authorization In case of 4way handshake offload, transition disable policy updated by the AP during EAPOL 3/4 is not updated to the upper layer. This results in mismatch between transition disable policy between the upper layer and the driver. This patch addresses this issue by updating transition disable policy as part of port authorization indication. Signed-off-by: Vinayak Yadawad Signed-off-by: Johannes Berg --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 2 +- include/net/cfg80211.h | 4 +++- include/uapi/linux/nl80211.h | 3 +++ net/wireless/core.h | 5 ++++- net/wireless/nl80211.c | 8 +++++++- net/wireless/nl80211.h | 3 ++- net/wireless/sme.c | 12 ++++++++---- net/wireless/util.c | 4 +++- 8 files changed, 31 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index bf184c0e64cb..3f2336062217 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -6268,7 +6268,7 @@ done: brcmf_dbg(CONN, "Report roaming result\n"); if (profile->use_fwsup == BRCMF_PROFILE_FWSUP_1X && profile->is_ft) { - cfg80211_port_authorized(ndev, profile->bssid, GFP_KERNEL); + cfg80211_port_authorized(ndev, profile->bssid, NULL, 0, GFP_KERNEL); brcmf_dbg(CONN, "Report port authorized\n"); } diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 659dd1bee70f..11a370e64143 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -7683,6 +7683,8 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, * * @dev: network device * @bssid: the BSSID of the AP + * @td_bitmap: transition disable policy + * @td_bitmap_len: Length of transition disable policy * @gfp: allocation flags * * This function should be called by a driver that supports 4 way handshake @@ -7693,7 +7695,7 @@ void cfg80211_roamed(struct net_device *dev, struct cfg80211_roam_info *info, * indicate the 802.11 association. */ void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, - gfp_t gfp); + const u8* td_bitmap, u8 td_bitmap_len, gfp_t gfp); /** * cfg80211_disconnected - notify cfg80211 that connection was dropped diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c32e7616a366..c14a91bbca7c 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -2749,6 +2749,8 @@ enum nl80211_commands { * When used with %NL80211_CMD_FRAME_TX_STATUS, indicates the ack RX * timestamp. When used with %NL80211_CMD_FRAME RX notification, indicates * the incoming frame RX timestamp. + * @NL80211_ATTR_TD_BITMAP: Transition Disable bitmap, for subsequent + * (re)associations. * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3276,6 +3278,7 @@ enum nl80211_attrs { NL80211_ATTR_TX_HW_TIMESTAMP, NL80211_ATTR_RX_HW_TIMESTAMP, + NL80211_ATTR_TD_BITMAP, /* add attributes here, update the policy in nl80211.c */ diff --git a/net/wireless/core.h b/net/wireless/core.h index 775e16cb99ed..af85d8909935 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -271,6 +271,8 @@ struct cfg80211_event { } ij; struct { u8 bssid[ETH_ALEN]; + const u8 *td_bitmap; + u8 td_bitmap_len; } pa; }; }; @@ -409,7 +411,8 @@ int cfg80211_disconnect(struct cfg80211_registered_device *rdev, bool wextev); void __cfg80211_roamed(struct wireless_dev *wdev, struct cfg80211_roam_info *info); -void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid); +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len); int cfg80211_mgd_wext_connect(struct cfg80211_registered_device *rdev, struct wireless_dev *wdev); void cfg80211_autodisconnect_wk(struct work_struct *work); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 1d0277758d0e..fe368af39554 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17942,7 +17942,8 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, } void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *bssid) + struct net_device *netdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len) { struct sk_buff *msg; void *hdr; @@ -17962,6 +17963,11 @@ void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid)) goto nla_put_failure; + if ((td_bitmap_len > 0) && td_bitmap) + if (nla_put(msg, NL80211_ATTR_TD_BITMAP, + td_bitmap_len, td_bitmap)) + goto nla_put_failure; + genlmsg_end(msg, hdr); genlmsg_multicast_netns(&nl80211_fam, wiphy_net(&rdev->wiphy), msg, 0, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 855d540ddfb9..ba9457e94c43 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -83,7 +83,8 @@ void nl80211_send_roamed(struct cfg80211_registered_device *rdev, struct net_device *netdev, struct cfg80211_roam_info *info, gfp_t gfp); void nl80211_send_port_authorized(struct cfg80211_registered_device *rdev, - struct net_device *netdev, const u8 *bssid); + struct net_device *netdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len); void nl80211_send_disconnected(struct cfg80211_registered_device *rdev, struct net_device *netdev, u16 reason, const u8 *ie, size_t ie_len, bool from_ap); diff --git a/net/wireless/sme.c b/net/wireless/sme.c index f94497e9db43..4b5b6ee0fe01 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1251,7 +1251,8 @@ out: } EXPORT_SYMBOL(cfg80211_roamed); -void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) +void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid, + const u8 *td_bitmap, u8 td_bitmap_len) { ASSERT_WDEV_LOCK(wdev); @@ -1264,11 +1265,11 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) return; nl80211_send_port_authorized(wiphy_to_rdev(wdev->wiphy), wdev->netdev, - bssid); + bssid, td_bitmap, td_bitmap_len); } void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, - gfp_t gfp) + const u8 *td_bitmap, u8 td_bitmap_len, gfp_t gfp) { struct wireless_dev *wdev = dev->ieee80211_ptr; struct cfg80211_registered_device *rdev = wiphy_to_rdev(wdev->wiphy); @@ -1278,12 +1279,15 @@ void cfg80211_port_authorized(struct net_device *dev, const u8 *bssid, if (WARN_ON(!bssid)) return; - ev = kzalloc(sizeof(*ev), gfp); + ev = kzalloc(sizeof(*ev) + td_bitmap_len, gfp); if (!ev) return; ev->type = EVENT_PORT_AUTHORIZED; memcpy(ev->pa.bssid, bssid, ETH_ALEN); + ev->pa.td_bitmap = ((u8 *)ev) + sizeof(*ev); + ev->pa.td_bitmap_len = td_bitmap_len; + memcpy((void *)ev->pa.td_bitmap, td_bitmap, td_bitmap_len); /* * Use the wdev event list so that if there are pending diff --git a/net/wireless/util.c b/net/wireless/util.c index 01493568a21d..f09d528e5199 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -988,7 +988,9 @@ void cfg80211_process_wdev_events(struct wireless_dev *wdev) __cfg80211_leave(wiphy_to_rdev(wdev->wiphy), wdev); break; case EVENT_PORT_AUTHORIZED: - __cfg80211_port_authorized(wdev, ev->pa.bssid); + __cfg80211_port_authorized(wdev, ev->pa.bssid, + ev->pa.td_bitmap, + ev->pa.td_bitmap_len); break; } wdev_unlock(wdev); -- cgit From dd2bc5cc9e25554546f16661f8de1dcb8033dde0 Mon Sep 17 00:00:00 2001 From: Quan Nguyen Date: Tue, 4 Oct 2022 16:31:04 +0700 Subject: ipmi: ssif_bmc: Add SSIF BMC driver The SMBus system interface (SSIF) IPMI BMC driver can be used to perform in-band IPMI communication with their host in management (BMC) side. Thanks Dan for the copy_from_user() fix in the link below. Link: https://lore.kernel.org/linux-arm-kernel/20220310114119.13736-4-quan@os.amperecomputing.com/ Signed-off-by: Quan Nguyen Message-Id: <20221004093106.1653317-2-quan@os.amperecomputing.com> Signed-off-by: Corey Minyard --- drivers/char/ipmi/Kconfig | 10 + drivers/char/ipmi/Makefile | 1 + drivers/char/ipmi/ssif_bmc.c | 873 +++++++++++++++++++++++++++++++++++++ include/uapi/linux/ipmi_ssif_bmc.h | 18 + 4 files changed, 902 insertions(+) create mode 100644 drivers/char/ipmi/ssif_bmc.c create mode 100644 include/uapi/linux/ipmi_ssif_bmc.h (limited to 'include/uapi/linux') diff --git a/drivers/char/ipmi/Kconfig b/drivers/char/ipmi/Kconfig index 39565cf74b2c..b6c0d35fc1a5 100644 --- a/drivers/char/ipmi/Kconfig +++ b/drivers/char/ipmi/Kconfig @@ -169,6 +169,16 @@ config ASPEED_BT_IPMI_BMC found on Aspeed SOCs (AST2400 and AST2500). The driver implements the BMC side of the BT interface. +config SSIF_IPMI_BMC + tristate "SSIF IPMI BMC driver" + depends on I2C && I2C_SLAVE + help + This enables the IPMI SMBus system interface (SSIF) at the + management (BMC) side. + + The driver implements the BMC side of the SMBus system + interface (SSIF). + config IPMB_DEVICE_INTERFACE tristate 'IPMB Interface handler' depends on I2C diff --git a/drivers/char/ipmi/Makefile b/drivers/char/ipmi/Makefile index 7ce790efad92..cb6138b8ded9 100644 --- a/drivers/char/ipmi/Makefile +++ b/drivers/char/ipmi/Makefile @@ -30,3 +30,4 @@ obj-$(CONFIG_ASPEED_BT_IPMI_BMC) += bt-bmc.o obj-$(CONFIG_ASPEED_KCS_IPMI_BMC) += kcs_bmc_aspeed.o obj-$(CONFIG_NPCM7XX_KCS_IPMI_BMC) += kcs_bmc_npcm7xx.o obj-$(CONFIG_IPMB_DEVICE_INTERFACE) += ipmb_dev_int.o +obj-$(CONFIG_SSIF_IPMI_BMC) += ssif_bmc.o diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c new file mode 100644 index 000000000000..a7bb4b99000e --- /dev/null +++ b/drivers/char/ipmi/ssif_bmc.c @@ -0,0 +1,873 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * The driver for BMC side of SSIF interface + * + * Copyright (c) 2022, Ampere Computing LLC + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#define DEVICE_NAME "ipmi-ssif-host" + +#define GET_8BIT_ADDR(addr_7bit) (((addr_7bit) << 1) & 0xff) + +/* A standard SMBus Transaction is limited to 32 data bytes */ +#define MAX_PAYLOAD_PER_TRANSACTION 32 +/* Transaction includes the address, the command, the length and the PEC byte */ +#define MAX_TRANSACTION (MAX_PAYLOAD_PER_TRANSACTION + 4) + +#define MAX_IPMI_DATA_PER_START_TRANSACTION 30 +#define MAX_IPMI_DATA_PER_MIDDLE_TRANSACTION 31 + +#define SSIF_IPMI_SINGLEPART_WRITE 0x2 +#define SSIF_IPMI_SINGLEPART_READ 0x3 +#define SSIF_IPMI_MULTIPART_WRITE_START 0x6 +#define SSIF_IPMI_MULTIPART_WRITE_MIDDLE 0x7 +#define SSIF_IPMI_MULTIPART_WRITE_END 0x8 +#define SSIF_IPMI_MULTIPART_READ_START 0x3 +#define SSIF_IPMI_MULTIPART_READ_MIDDLE 0x9 + +/* + * IPMI 2.0 Spec, section 12.7 SSIF Timing, + * Request-to-Response Time is T6max(250ms) - T1max(20ms) - 3ms = 227ms + * Recover ssif_bmc from busy state if it takes up to 500ms + */ +#define RESPONSE_TIMEOUT 500 /* ms */ + +struct ssif_part_buffer { + u8 address; + u8 smbus_cmd; + u8 length; + u8 payload[MAX_PAYLOAD_PER_TRANSACTION]; + u8 pec; + u8 index; +}; + +/* + * SSIF internal states: + * SSIF_READY 0x00 : Ready state + * SSIF_START 0x01 : Start smbus transaction + * SSIF_SMBUS_CMD 0x02 : Received SMBus command + * SSIF_REQ_RECVING 0x03 : Receiving request + * SSIF_RES_SENDING 0x04 : Sending response + * SSIF_ABORTING 0x05 : Aborting state + */ +enum ssif_state { + SSIF_READY, + SSIF_START, + SSIF_SMBUS_CMD, + SSIF_REQ_RECVING, + SSIF_RES_SENDING, + SSIF_ABORTING, + SSIF_STATE_MAX +}; + +struct ssif_bmc_ctx { + struct i2c_client *client; + struct miscdevice miscdev; + int msg_idx; + bool pec_support; + /* ssif bmc spinlock */ + spinlock_t lock; + wait_queue_head_t wait_queue; + u8 running; + enum ssif_state state; + /* Timeout waiting for response */ + struct timer_list response_timer; + bool response_timer_inited; + /* Flag to identify a Multi-part Read Transaction */ + bool is_singlepart_read; + u8 nbytes_processed; + u8 remain_len; + u8 recv_len; + /* Block Number of a Multi-part Read Transaction */ + u8 block_num; + bool request_available; + bool response_in_progress; + bool busy; + bool aborting; + /* Buffer for SSIF Transaction part*/ + struct ssif_part_buffer part_buf; + struct ipmi_ssif_msg response; + struct ipmi_ssif_msg request; +}; + +static inline struct ssif_bmc_ctx *to_ssif_bmc(struct file *file) +{ + return container_of(file->private_data, struct ssif_bmc_ctx, miscdev); +} + +static const char *state_to_string(enum ssif_state state) +{ + switch (state) { + case SSIF_READY: + return "SSIF_READY"; + case SSIF_START: + return "SSIF_START"; + case SSIF_SMBUS_CMD: + return "SSIF_SMBUS_CMD"; + case SSIF_REQ_RECVING: + return "SSIF_REQ_RECVING"; + case SSIF_RES_SENDING: + return "SSIF_RES_SENDING"; + case SSIF_ABORTING: + return "SSIF_ABORTING"; + default: + return "SSIF_STATE_UNKNOWN"; + } +} + +/* Handle SSIF message that will be sent to user */ +static ssize_t ssif_bmc_read(struct file *file, char __user *buf, size_t count, loff_t *ppos) +{ + struct ssif_bmc_ctx *ssif_bmc = to_ssif_bmc(file); + struct ipmi_ssif_msg msg; + unsigned long flags; + ssize_t ret; + + spin_lock_irqsave(&ssif_bmc->lock, flags); + while (!ssif_bmc->request_available) { + spin_unlock_irqrestore(&ssif_bmc->lock, flags); + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + ret = wait_event_interruptible(ssif_bmc->wait_queue, + ssif_bmc->request_available); + if (ret) + return ret; + spin_lock_irqsave(&ssif_bmc->lock, flags); + } + + if (count < min_t(ssize_t, + sizeof_field(struct ipmi_ssif_msg, len) + ssif_bmc->request.len, + sizeof(struct ipmi_ssif_msg))) { + spin_unlock_irqrestore(&ssif_bmc->lock, flags); + ret = -EINVAL; + } else { + count = min_t(ssize_t, + sizeof_field(struct ipmi_ssif_msg, len) + ssif_bmc->request.len, + sizeof(struct ipmi_ssif_msg)); + memcpy(&msg, &ssif_bmc->request, count); + ssif_bmc->request_available = false; + spin_unlock_irqrestore(&ssif_bmc->lock, flags); + + ret = copy_to_user(buf, &msg, count); + } + + return (ret < 0) ? ret : count; +} + +/* Handle SSIF message that is written by user */ +static ssize_t ssif_bmc_write(struct file *file, const char __user *buf, size_t count, + loff_t *ppos) +{ + struct ssif_bmc_ctx *ssif_bmc = to_ssif_bmc(file); + struct ipmi_ssif_msg msg; + unsigned long flags; + ssize_t ret; + + if (count > sizeof(struct ipmi_ssif_msg)) + return -EINVAL; + + if (copy_from_user(&msg, buf, count)) + return -EFAULT; + + if (!msg.len || count < sizeof_field(struct ipmi_ssif_msg, len) + msg.len) + return -EINVAL; + + spin_lock_irqsave(&ssif_bmc->lock, flags); + while (ssif_bmc->response_in_progress) { + spin_unlock_irqrestore(&ssif_bmc->lock, flags); + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + ret = wait_event_interruptible(ssif_bmc->wait_queue, + !ssif_bmc->response_in_progress); + if (ret) + return ret; + spin_lock_irqsave(&ssif_bmc->lock, flags); + } + + /* + * The write must complete before the response timeout fired, otherwise + * the response is aborted and wait for next request + * Return -EINVAL if the response is aborted + */ + ret = (ssif_bmc->response_timer_inited) ? 0 : -EINVAL; + if (ret) + goto exit; + + del_timer(&ssif_bmc->response_timer); + ssif_bmc->response_timer_inited = false; + + memcpy(&ssif_bmc->response, &msg, count); + ssif_bmc->is_singlepart_read = (msg.len <= MAX_PAYLOAD_PER_TRANSACTION); + + ssif_bmc->response_in_progress = true; + + /* ssif_bmc not busy */ + ssif_bmc->busy = false; + + /* Clean old request buffer */ + memset(&ssif_bmc->request, 0, sizeof(struct ipmi_ssif_msg)); +exit: + spin_unlock_irqrestore(&ssif_bmc->lock, flags); + + return (ret < 0) ? ret : count; +} + +static int ssif_bmc_open(struct inode *inode, struct file *file) +{ + struct ssif_bmc_ctx *ssif_bmc = to_ssif_bmc(file); + int ret = 0; + + spin_lock_irq(&ssif_bmc->lock); + if (!ssif_bmc->running) + ssif_bmc->running = 1; + else + ret = -EBUSY; + spin_unlock_irq(&ssif_bmc->lock); + + return ret; +} + +static __poll_t ssif_bmc_poll(struct file *file, poll_table *wait) +{ + struct ssif_bmc_ctx *ssif_bmc = to_ssif_bmc(file); + __poll_t mask = 0; + + poll_wait(file, &ssif_bmc->wait_queue, wait); + + spin_lock_irq(&ssif_bmc->lock); + /* The request is available, userspace application can get the request */ + if (ssif_bmc->request_available) + mask |= POLLIN; + + spin_unlock_irq(&ssif_bmc->lock); + + return mask; +} + +static int ssif_bmc_release(struct inode *inode, struct file *file) +{ + struct ssif_bmc_ctx *ssif_bmc = to_ssif_bmc(file); + + spin_lock_irq(&ssif_bmc->lock); + ssif_bmc->running = 0; + spin_unlock_irq(&ssif_bmc->lock); + + return 0; +} + +/* + * System calls to device interface for user apps + */ +static const struct file_operations ssif_bmc_fops = { + .owner = THIS_MODULE, + .open = ssif_bmc_open, + .read = ssif_bmc_read, + .write = ssif_bmc_write, + .release = ssif_bmc_release, + .poll = ssif_bmc_poll, +}; + +/* Called with ssif_bmc->lock held. */ +static void complete_response(struct ssif_bmc_ctx *ssif_bmc) +{ + /* Invalidate response in buffer to denote it having been sent. */ + ssif_bmc->response.len = 0; + ssif_bmc->response_in_progress = false; + ssif_bmc->nbytes_processed = 0; + ssif_bmc->remain_len = 0; + ssif_bmc->busy = false; + memset(&ssif_bmc->part_buf, 0, sizeof(struct ssif_part_buffer)); + wake_up_all(&ssif_bmc->wait_queue); +} + +static void response_timeout(struct timer_list *t) +{ + struct ssif_bmc_ctx *ssif_bmc = from_timer(ssif_bmc, t, response_timer); + unsigned long flags; + + spin_lock_irqsave(&ssif_bmc->lock, flags); + + /* Do nothing if the response is in progress */ + if (!ssif_bmc->response_in_progress) { + /* Recover ssif_bmc from busy */ + ssif_bmc->busy = false; + ssif_bmc->response_timer_inited = false; + /* Set aborting flag */ + ssif_bmc->aborting = true; + } + + spin_unlock_irqrestore(&ssif_bmc->lock, flags); +} + +/* Called with ssif_bmc->lock held. */ +static void handle_request(struct ssif_bmc_ctx *ssif_bmc) +{ + /* set ssif_bmc to busy waiting for response */ + ssif_bmc->busy = true; + /* Request message is available to process */ + ssif_bmc->request_available = true; + /* Clean old response buffer */ + memset(&ssif_bmc->response, 0, sizeof(struct ipmi_ssif_msg)); + /* This is the new READ request.*/ + wake_up_all(&ssif_bmc->wait_queue); + + /* Armed timer to recover slave from busy state in case of no response */ + if (!ssif_bmc->response_timer_inited) { + timer_setup(&ssif_bmc->response_timer, response_timeout, 0); + ssif_bmc->response_timer_inited = true; + } + mod_timer(&ssif_bmc->response_timer, jiffies + msecs_to_jiffies(RESPONSE_TIMEOUT)); +} + +static void calculate_response_part_pec(struct ssif_part_buffer *part) +{ + u8 addr = part->address; + + /* PEC - Start Read Address */ + part->pec = i2c_smbus_pec(0, &addr, 1); + /* PEC - SSIF Command */ + part->pec = i2c_smbus_pec(part->pec, &part->smbus_cmd, 1); + /* PEC - Restart Write Address */ + addr = addr | 0x01; + part->pec = i2c_smbus_pec(part->pec, &addr, 1); + part->pec = i2c_smbus_pec(part->pec, &part->length, 1); + if (part->length) + part->pec = i2c_smbus_pec(part->pec, part->payload, part->length); +} + +static void set_singlepart_response_buffer(struct ssif_bmc_ctx *ssif_bmc) +{ + struct ssif_part_buffer *part = &ssif_bmc->part_buf; + + part->address = GET_8BIT_ADDR(ssif_bmc->client->addr); + part->length = (u8)ssif_bmc->response.len; + + /* Clear the rest to 0 */ + memset(part->payload + part->length, 0, MAX_PAYLOAD_PER_TRANSACTION - part->length); + memcpy(&part->payload[0], &ssif_bmc->response.payload[0], part->length); +} + +static void set_multipart_response_buffer(struct ssif_bmc_ctx *ssif_bmc) +{ + struct ssif_part_buffer *part = &ssif_bmc->part_buf; + u8 part_len = 0; + + part->address = GET_8BIT_ADDR(ssif_bmc->client->addr); + switch (part->smbus_cmd) { + case SSIF_IPMI_MULTIPART_READ_START: + /* + * Read Start length is 32 bytes. + * Read Start transfer first 30 bytes of IPMI response + * and 2 special code 0x00, 0x01. + */ + ssif_bmc->nbytes_processed = 0; + ssif_bmc->block_num = 0; + part->length = MAX_PAYLOAD_PER_TRANSACTION; + part_len = MAX_IPMI_DATA_PER_START_TRANSACTION; + ssif_bmc->remain_len = ssif_bmc->response.len - part_len; + + part->payload[0] = 0x00; /* Start Flag */ + part->payload[1] = 0x01; /* Start Flag */ + + memcpy(&part->payload[2], &ssif_bmc->response.payload[0], part_len); + break; + + case SSIF_IPMI_MULTIPART_READ_MIDDLE: + /* + * IPMI READ Middle or READ End messages can carry up to 31 bytes + * IPMI data plus block number byte. + */ + if (ssif_bmc->remain_len <= MAX_IPMI_DATA_PER_MIDDLE_TRANSACTION) { + /* + * This is READ End message + * Return length is the remaining response data length + * plus block number + * Block number 0xFF is to indicate this is last message + * + */ + /* Clean the buffer */ + memset(&part->payload[0], 0, MAX_PAYLOAD_PER_TRANSACTION); + part->length = ssif_bmc->remain_len + 1; + part_len = ssif_bmc->remain_len; + ssif_bmc->block_num = 0xFF; + part->payload[0] = ssif_bmc->block_num; + } else { + /* + * This is READ Middle message + * Response length is the maximum SMBUS transfer length + * Block number byte is incremented + * Return length is maximum SMBUS transfer length + */ + part->length = MAX_PAYLOAD_PER_TRANSACTION; + part_len = MAX_IPMI_DATA_PER_MIDDLE_TRANSACTION; + part->payload[0] = ssif_bmc->block_num; + ssif_bmc->block_num++; + } + + ssif_bmc->remain_len -= part_len; + memcpy(&part->payload[1], ssif_bmc->response.payload + ssif_bmc->nbytes_processed, + part_len); + break; + + default: + /* Do not expect to go to this case */ + dev_err(&ssif_bmc->client->dev, "%s: Unexpected SMBus command 0x%x\n", + __func__, part->smbus_cmd); + break; + } + + ssif_bmc->nbytes_processed += part_len; +} + +static bool supported_read_cmd(u8 cmd) +{ + if (cmd == SSIF_IPMI_SINGLEPART_READ || + cmd == SSIF_IPMI_MULTIPART_READ_START || + cmd == SSIF_IPMI_MULTIPART_READ_MIDDLE) + return true; + + return false; +} + +static bool supported_write_cmd(u8 cmd) +{ + if (cmd == SSIF_IPMI_SINGLEPART_WRITE || + cmd == SSIF_IPMI_MULTIPART_WRITE_START || + cmd == SSIF_IPMI_MULTIPART_WRITE_MIDDLE || + cmd == SSIF_IPMI_MULTIPART_WRITE_END) + return true; + + return false; +} + +/* Process the IPMI response that will be read by master */ +static void handle_read_processed(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + struct ssif_part_buffer *part = &ssif_bmc->part_buf; + + /* msg_idx start from 0 */ + if (part->index < part->length) + *val = part->payload[part->index]; + else if (part->index == part->length && ssif_bmc->pec_support) + *val = part->pec; + else + *val = 0; + + part->index++; +} + +static void handle_write_received(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + /* + * The msg_idx must be 1 when first enter SSIF_REQ_RECVING state + * And it would never exceeded 36 bytes included the 32 bytes max payload + + * the address + the command + the len and the PEC. + */ + if (ssif_bmc->msg_idx < 1 || ssif_bmc->msg_idx > MAX_TRANSACTION) + return; + + if (ssif_bmc->msg_idx == 1) { + ssif_bmc->part_buf.length = *val; + ssif_bmc->part_buf.index = 0; + } else { + ssif_bmc->part_buf.payload[ssif_bmc->part_buf.index++] = *val; + } + + ssif_bmc->msg_idx++; +} + +static bool validate_request_part(struct ssif_bmc_ctx *ssif_bmc) +{ + struct ssif_part_buffer *part = &ssif_bmc->part_buf; + bool ret = true; + u8 cpec; + u8 addr; + + if (part->index == part->length) { + /* PEC is not included */ + ssif_bmc->pec_support = false; + ret = true; + goto exit; + } + + if (part->index != part->length + 1) { + ret = false; + goto exit; + } + + /* PEC is included */ + ssif_bmc->pec_support = true; + part->pec = part->payload[part->length]; + addr = GET_8BIT_ADDR(ssif_bmc->client->addr); + cpec = i2c_smbus_pec(0, &addr, 1); + cpec = i2c_smbus_pec(cpec, &part->smbus_cmd, 1); + cpec = i2c_smbus_pec(cpec, &part->length, 1); + /* + * As SMBus specification does not allow the length + * (byte count) in the Write-Block protocol to be zero. + * Therefore, it is illegal to have the last Middle + * transaction in the sequence carry 32-byte and have + * a length of ‘0’ in the End transaction. + * But some users may try to use this way and we should + * prevent ssif_bmc driver broken in this case. + */ + if (part->length) + cpec = i2c_smbus_pec(cpec, part->payload, part->length); + + if (cpec != part->pec) + ret = false; + +exit: + return ret; +} + +static void process_request_part(struct ssif_bmc_ctx *ssif_bmc) +{ + struct ssif_part_buffer *part = &ssif_bmc->part_buf; + unsigned int len; + + switch (part->smbus_cmd) { + case SSIF_IPMI_SINGLEPART_WRITE: + /* save the whole part to request*/ + ssif_bmc->request.len = part->length; + memcpy(ssif_bmc->request.payload, part->payload, part->length); + + break; + case SSIF_IPMI_MULTIPART_WRITE_START: + ssif_bmc->request.len = 0; + + fallthrough; + case SSIF_IPMI_MULTIPART_WRITE_MIDDLE: + case SSIF_IPMI_MULTIPART_WRITE_END: + len = ssif_bmc->request.len + part->length; + /* Do the bound check here, not allow the request len exceed 254 bytes */ + if (len > IPMI_SSIF_PAYLOAD_MAX) { + dev_warn(&ssif_bmc->client->dev, + "Warn: Request exceeded 254 bytes, aborting"); + /* Request too long, aborting */ + ssif_bmc->aborting = true; + } else { + memcpy(ssif_bmc->request.payload + ssif_bmc->request.len, + part->payload, part->length); + ssif_bmc->request.len += part->length; + } + break; + default: + /* Do not expect to go to this case */ + dev_err(&ssif_bmc->client->dev, "%s: Unexpected SMBus command 0x%x\n", + __func__, part->smbus_cmd); + break; + } +} + +static void process_smbus_cmd(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + /* SMBUS command can vary (single or multi-part) */ + ssif_bmc->part_buf.smbus_cmd = *val; + ssif_bmc->msg_idx = 1; + memset(&ssif_bmc->part_buf.payload[0], 0, MAX_PAYLOAD_PER_TRANSACTION); + + if (*val == SSIF_IPMI_SINGLEPART_WRITE || *val == SSIF_IPMI_MULTIPART_WRITE_START) { + /* + * The response maybe not come in-time, causing host SSIF driver + * to timeout and resend a new request. In such case check for + * pending response and clear it + */ + if (ssif_bmc->response_in_progress) + complete_response(ssif_bmc); + + /* This is new request, flip aborting flag if set */ + if (ssif_bmc->aborting) + ssif_bmc->aborting = false; + } +} + +static void on_read_requested_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + if (ssif_bmc->state == SSIF_READY || + ssif_bmc->state == SSIF_START || + ssif_bmc->state == SSIF_REQ_RECVING || + ssif_bmc->state == SSIF_RES_SENDING) { + dev_warn(&ssif_bmc->client->dev, + "Warn: %s unexpected READ REQUESTED in state=%s\n", + __func__, state_to_string(ssif_bmc->state)); + ssif_bmc->state = SSIF_ABORTING; + *val = 0; + return; + + } else if (ssif_bmc->state == SSIF_SMBUS_CMD) { + if (!supported_read_cmd(ssif_bmc->part_buf.smbus_cmd)) { + dev_warn(&ssif_bmc->client->dev, "Warn: Unknown SMBus read command=0x%x", + ssif_bmc->part_buf.smbus_cmd); + ssif_bmc->aborting = true; + } + + if (ssif_bmc->aborting) + ssif_bmc->state = SSIF_ABORTING; + else + ssif_bmc->state = SSIF_RES_SENDING; + } + + ssif_bmc->msg_idx = 0; + + /* Send 0 if there is nothing to send */ + if (!ssif_bmc->response_in_progress || ssif_bmc->state == SSIF_ABORTING) { + *val = 0; + return; + } + + if (ssif_bmc->is_singlepart_read) + set_singlepart_response_buffer(ssif_bmc); + else + set_multipart_response_buffer(ssif_bmc); + + calculate_response_part_pec(&ssif_bmc->part_buf); + ssif_bmc->part_buf.index = 0; + *val = ssif_bmc->part_buf.length; +} + +static void on_read_processed_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + if (ssif_bmc->state == SSIF_READY || + ssif_bmc->state == SSIF_START || + ssif_bmc->state == SSIF_REQ_RECVING || + ssif_bmc->state == SSIF_SMBUS_CMD) { + dev_warn(&ssif_bmc->client->dev, + "Warn: %s unexpected READ PROCESSED in state=%s\n", + __func__, state_to_string(ssif_bmc->state)); + ssif_bmc->state = SSIF_ABORTING; + *val = 0; + return; + } + + /* Send 0 if there is nothing to send */ + if (!ssif_bmc->response_in_progress || ssif_bmc->state == SSIF_ABORTING) { + *val = 0; + return; + } + + handle_read_processed(ssif_bmc, val); +} + +static void on_write_requested_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + if (ssif_bmc->state == SSIF_READY || ssif_bmc->state == SSIF_SMBUS_CMD) { + ssif_bmc->state = SSIF_START; + + } else if (ssif_bmc->state == SSIF_START || + ssif_bmc->state == SSIF_REQ_RECVING || + ssif_bmc->state == SSIF_RES_SENDING) { + dev_warn(&ssif_bmc->client->dev, + "Warn: %s unexpected WRITE REQUEST in state=%s\n", + __func__, state_to_string(ssif_bmc->state)); + ssif_bmc->state = SSIF_ABORTING; + return; + } + + ssif_bmc->msg_idx = 0; + ssif_bmc->part_buf.address = *val; +} + +static void on_write_received_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + if (ssif_bmc->state == SSIF_READY || + ssif_bmc->state == SSIF_RES_SENDING) { + dev_warn(&ssif_bmc->client->dev, + "Warn: %s unexpected WRITE RECEIVED in state=%s\n", + __func__, state_to_string(ssif_bmc->state)); + ssif_bmc->state = SSIF_ABORTING; + + } else if (ssif_bmc->state == SSIF_START) { + ssif_bmc->state = SSIF_SMBUS_CMD; + + } else if (ssif_bmc->state == SSIF_SMBUS_CMD) { + if (!supported_write_cmd(ssif_bmc->part_buf.smbus_cmd)) { + dev_warn(&ssif_bmc->client->dev, "Warn: Unknown SMBus write command=0x%x", + ssif_bmc->part_buf.smbus_cmd); + ssif_bmc->aborting = true; + } + + if (ssif_bmc->aborting) + ssif_bmc->state = SSIF_ABORTING; + else + ssif_bmc->state = SSIF_REQ_RECVING; + } + + /* This is response sending state */ + if (ssif_bmc->state == SSIF_REQ_RECVING) + handle_write_received(ssif_bmc, val); + else if (ssif_bmc->state == SSIF_SMBUS_CMD) + process_smbus_cmd(ssif_bmc, val); +} + +static void on_stop_event(struct ssif_bmc_ctx *ssif_bmc, u8 *val) +{ + if (ssif_bmc->state == SSIF_READY || + ssif_bmc->state == SSIF_START || + ssif_bmc->state == SSIF_SMBUS_CMD || + ssif_bmc->state == SSIF_ABORTING) { + dev_warn(&ssif_bmc->client->dev, + "Warn: %s unexpected SLAVE STOP in state=%s\n", + __func__, state_to_string(ssif_bmc->state)); + ssif_bmc->state = SSIF_READY; + + } else if (ssif_bmc->state == SSIF_REQ_RECVING) { + if (validate_request_part(ssif_bmc)) { + process_request_part(ssif_bmc); + if (ssif_bmc->part_buf.smbus_cmd == SSIF_IPMI_SINGLEPART_WRITE || + ssif_bmc->part_buf.smbus_cmd == SSIF_IPMI_MULTIPART_WRITE_END) + handle_request(ssif_bmc); + ssif_bmc->state = SSIF_READY; + } else { + /* + * A BMC that receives an invalid request drop the data for the write + * transaction and any further transactions (read or write) until + * the next valid read or write Start transaction is received + */ + dev_err(&ssif_bmc->client->dev, "Error: invalid pec\n"); + ssif_bmc->aborting = true; + } + } else if (ssif_bmc->state == SSIF_RES_SENDING) { + if (ssif_bmc->is_singlepart_read || ssif_bmc->block_num == 0xFF) + /* Invalidate response buffer to denote it is sent */ + complete_response(ssif_bmc); + ssif_bmc->state = SSIF_READY; + } + + /* Reset message index */ + ssif_bmc->msg_idx = 0; +} + +/* + * Callback function to handle I2C slave events + */ +static int ssif_bmc_cb(struct i2c_client *client, enum i2c_slave_event event, u8 *val) +{ + unsigned long flags; + struct ssif_bmc_ctx *ssif_bmc = i2c_get_clientdata(client); + int ret = 0; + + spin_lock_irqsave(&ssif_bmc->lock, flags); + + switch (event) { + case I2C_SLAVE_READ_REQUESTED: + on_read_requested_event(ssif_bmc, val); + break; + + case I2C_SLAVE_WRITE_REQUESTED: + on_write_requested_event(ssif_bmc, val); + break; + + case I2C_SLAVE_READ_PROCESSED: + on_read_processed_event(ssif_bmc, val); + break; + + case I2C_SLAVE_WRITE_RECEIVED: + on_write_received_event(ssif_bmc, val); + break; + + case I2C_SLAVE_STOP: + on_stop_event(ssif_bmc, val); + break; + + default: + dev_warn(&ssif_bmc->client->dev, "Warn: Unknown i2c slave event\n"); + break; + } + + if (!ssif_bmc->aborting && ssif_bmc->busy) + ret = -EBUSY; + + spin_unlock_irqrestore(&ssif_bmc->lock, flags); + + return ret; +} + +static int ssif_bmc_probe(struct i2c_client *client, const struct i2c_device_id *id) +{ + struct ssif_bmc_ctx *ssif_bmc; + int ret; + + ssif_bmc = devm_kzalloc(&client->dev, sizeof(*ssif_bmc), GFP_KERNEL); + if (!ssif_bmc) + return -ENOMEM; + + spin_lock_init(&ssif_bmc->lock); + + init_waitqueue_head(&ssif_bmc->wait_queue); + ssif_bmc->request_available = false; + ssif_bmc->response_in_progress = false; + ssif_bmc->busy = false; + ssif_bmc->response_timer_inited = false; + + /* Register misc device interface */ + ssif_bmc->miscdev.minor = MISC_DYNAMIC_MINOR; + ssif_bmc->miscdev.name = DEVICE_NAME; + ssif_bmc->miscdev.fops = &ssif_bmc_fops; + ssif_bmc->miscdev.parent = &client->dev; + ret = misc_register(&ssif_bmc->miscdev); + if (ret) + return ret; + + ssif_bmc->client = client; + ssif_bmc->client->flags |= I2C_CLIENT_SLAVE; + + /* Register I2C slave */ + i2c_set_clientdata(client, ssif_bmc); + ret = i2c_slave_register(client, ssif_bmc_cb); + if (ret) + misc_deregister(&ssif_bmc->miscdev); + + return ret; +} + +static void ssif_bmc_remove(struct i2c_client *client) +{ + struct ssif_bmc_ctx *ssif_bmc = i2c_get_clientdata(client); + + i2c_slave_unregister(client); + misc_deregister(&ssif_bmc->miscdev); +} + +static const struct of_device_id ssif_bmc_match[] = { + { .compatible = "ssif-bmc" }, + { }, +}; +MODULE_DEVICE_TABLE(of, ssif_bmc_match); + +static const struct i2c_device_id ssif_bmc_id[] = { + { DEVICE_NAME, 0 }, + { }, +}; +MODULE_DEVICE_TABLE(i2c, ssif_bmc_id); + +static struct i2c_driver ssif_bmc_driver = { + .driver = { + .name = DEVICE_NAME, + .of_match_table = ssif_bmc_match, + }, + .probe = ssif_bmc_probe, + .remove = ssif_bmc_remove, + .id_table = ssif_bmc_id, +}; + +module_i2c_driver(ssif_bmc_driver); + +MODULE_AUTHOR("Quan Nguyen "); +MODULE_AUTHOR("Chuong Tran "); +MODULE_DESCRIPTION("Linux device driver of the BMC IPMI SSIF interface."); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/ipmi_ssif_bmc.h b/include/uapi/linux/ipmi_ssif_bmc.h new file mode 100644 index 000000000000..1c6a753dad08 --- /dev/null +++ b/include/uapi/linux/ipmi_ssif_bmc.h @@ -0,0 +1,18 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note*/ +/* + * Copyright (c) 2022, Ampere Computing LLC. + */ + +#ifndef _UAPI_LINUX_IPMI_SSIF_BMC_H +#define _UAPI_LINUX_IPMI_SSIF_BMC_H + +#include + +/* Max length of ipmi ssif message included netfn and cmd field */ +#define IPMI_SSIF_PAYLOAD_MAX 254 +struct ipmi_ssif_msg { + unsigned int len; + __u8 payload[IPMI_SSIF_PAYLOAD_MAX]; +}; + +#endif /* _UAPI_LINUX_IPMI_SSIF_BMC_H */ -- cgit From b9f5ce27c8f8be409d6afca9797a2da01e5cebbb Mon Sep 17 00:00:00 2001 From: Günther Noack Date: Tue, 18 Oct 2022 20:22:09 +0200 Subject: landlock: Support file truncation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Introduce the LANDLOCK_ACCESS_FS_TRUNCATE flag for file truncation. This flag hooks into the path_truncate, file_truncate and file_alloc_security LSM hooks and covers file truncation using truncate(2), ftruncate(2), open(2) with O_TRUNC, as well as creat(). This change also increments the Landlock ABI version, updates corresponding selftests, and updates code documentation to document the flag. In security/security.c, allocate security blobs at pointer-aligned offsets. This fixes the problem where one LSM's security blob can shift another LSM's security blob to an unaligned address (reported by Nathan Chancellor). The following operations are restricted: open(2): requires the LANDLOCK_ACCESS_FS_TRUNCATE right if a file gets implicitly truncated as part of the open() (e.g. using O_TRUNC). Notable special cases: * open(..., O_RDONLY|O_TRUNC) can truncate files as well in Linux * open() with O_TRUNC does *not* need the TRUNCATE right when it creates a new file. truncate(2) (on a path): requires the LANDLOCK_ACCESS_FS_TRUNCATE right. ftruncate(2) (on a file): requires that the file had the TRUNCATE right when it was previously opened. File descriptors acquired by other means than open(2) (e.g. memfd_create(2)) continue to support truncation with ftruncate(2). Cc: Nathan Chancellor Signed-off-by: Günther Noack Acked-by: Paul Moore (LSM) Link: https://lore.kernel.org/r/20221018182216.301684-5-gnoack3000@gmail.com Signed-off-by: Mickaël Salaün --- include/uapi/linux/landlock.h | 21 ++++-- security/landlock/fs.c | 104 +++++++++++++++++++++++++-- security/landlock/fs.h | 24 +++++++ security/landlock/limits.h | 2 +- security/landlock/setup.c | 1 + security/landlock/syscalls.c | 2 +- security/security.c | 11 +-- tools/testing/selftests/landlock/base_test.c | 2 +- tools/testing/selftests/landlock/fs_test.c | 7 +- 9 files changed, 153 insertions(+), 21 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h index 9c4bcc37a455..f3223f964691 100644 --- a/include/uapi/linux/landlock.h +++ b/include/uapi/linux/landlock.h @@ -95,8 +95,19 @@ struct landlock_path_beneath_attr { * A file can only receive these access rights: * * - %LANDLOCK_ACCESS_FS_EXECUTE: Execute a file. - * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. + * - %LANDLOCK_ACCESS_FS_WRITE_FILE: Open a file with write access. Note that + * you might additionally need the %LANDLOCK_ACCESS_FS_TRUNCATE right in order + * to overwrite files with :manpage:`open(2)` using ``O_TRUNC`` or + * :manpage:`creat(2)`. * - %LANDLOCK_ACCESS_FS_READ_FILE: Open a file with read access. + * - %LANDLOCK_ACCESS_FS_TRUNCATE: Truncate a file with :manpage:`truncate(2)`, + * :manpage:`ftruncate(2)`, :manpage:`creat(2)`, or :manpage:`open(2)` with + * ``O_TRUNC``. Whether an opened file can be truncated with + * :manpage:`ftruncate(2)` is determined during :manpage:`open(2)`, in the + * same way as read and write permissions are checked during + * :manpage:`open(2)` using %LANDLOCK_ACCESS_FS_READ_FILE and + * %LANDLOCK_ACCESS_FS_WRITE_FILE. This access right is available since the + * third version of the Landlock ABI. * * A directory can receive access rights related to files or directories. The * following access right is applied to the directory itself, and the @@ -139,10 +150,9 @@ struct landlock_path_beneath_attr { * * It is currently not possible to restrict some file-related actions * accessible through these syscall families: :manpage:`chdir(2)`, - * :manpage:`truncate(2)`, :manpage:`stat(2)`, :manpage:`flock(2)`, - * :manpage:`chmod(2)`, :manpage:`chown(2)`, :manpage:`setxattr(2)`, - * :manpage:`utime(2)`, :manpage:`ioctl(2)`, :manpage:`fcntl(2)`, - * :manpage:`access(2)`. + * :manpage:`stat(2)`, :manpage:`flock(2)`, :manpage:`chmod(2)`, + * :manpage:`chown(2)`, :manpage:`setxattr(2)`, :manpage:`utime(2)`, + * :manpage:`ioctl(2)`, :manpage:`fcntl(2)`, :manpage:`access(2)`. * Future Landlock evolutions will enable to restrict them. */ /* clang-format off */ @@ -160,6 +170,7 @@ struct landlock_path_beneath_attr { #define LANDLOCK_ACCESS_FS_MAKE_BLOCK (1ULL << 11) #define LANDLOCK_ACCESS_FS_MAKE_SYM (1ULL << 12) #define LANDLOCK_ACCESS_FS_REFER (1ULL << 13) +#define LANDLOCK_ACCESS_FS_TRUNCATE (1ULL << 14) /* clang-format on */ #endif /* _UAPI_LINUX_LANDLOCK_H */ diff --git a/security/landlock/fs.c b/security/landlock/fs.c index 87fde50eb550..adcea0fe7e68 100644 --- a/security/landlock/fs.c +++ b/security/landlock/fs.c @@ -146,7 +146,8 @@ retry: #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ - LANDLOCK_ACCESS_FS_READ_FILE) + LANDLOCK_ACCESS_FS_READ_FILE | \ + LANDLOCK_ACCESS_FS_TRUNCATE) /* clang-format on */ /* @@ -1154,9 +1155,23 @@ static int hook_path_rmdir(const struct path *const dir, return current_check_access_path(dir, LANDLOCK_ACCESS_FS_REMOVE_DIR); } +static int hook_path_truncate(const struct path *const path) +{ + return current_check_access_path(path, LANDLOCK_ACCESS_FS_TRUNCATE); +} + /* File hooks */ -static inline access_mask_t get_file_access(const struct file *const file) +/** + * get_required_file_open_access - Get access needed to open a file + * + * @file: File being opened. + * + * Returns the access rights that are required for opening the given file, + * depending on the file type and open mode. + */ +static inline access_mask_t +get_required_file_open_access(const struct file *const file) { access_mask_t access = 0; @@ -1174,19 +1189,95 @@ static inline access_mask_t get_file_access(const struct file *const file) return access; } +static int hook_file_alloc_security(struct file *const file) +{ + /* + * Grants all access rights, even if most of them are not checked later + * on. It is more consistent. + * + * Notably, file descriptors for regular files can also be acquired + * without going through the file_open hook, for example when using + * memfd_create(2). + */ + landlock_file(file)->allowed_access = LANDLOCK_MASK_ACCESS_FS; + return 0; +} + static int hook_file_open(struct file *const file) { + layer_mask_t layer_masks[LANDLOCK_NUM_ACCESS_FS] = {}; + access_mask_t open_access_request, full_access_request, allowed_access; + const access_mask_t optional_access = LANDLOCK_ACCESS_FS_TRUNCATE; const struct landlock_ruleset *const dom = landlock_get_current_domain(); if (!dom) return 0; + /* - * Because a file may be opened with O_PATH, get_file_access() may - * return 0. This case will be handled with a future Landlock + * Because a file may be opened with O_PATH, get_required_file_open_access() + * may return 0. This case will be handled with a future Landlock * evolution. */ - return check_access_path(dom, &file->f_path, get_file_access(file)); + open_access_request = get_required_file_open_access(file); + + /* + * We look up more access than what we immediately need for open(), so + * that we can later authorize operations on opened files. + */ + full_access_request = open_access_request | optional_access; + + if (is_access_to_paths_allowed( + dom, &file->f_path, + init_layer_masks(dom, full_access_request, &layer_masks), + &layer_masks, NULL, 0, NULL, NULL)) { + allowed_access = full_access_request; + } else { + unsigned long access_bit; + const unsigned long access_req = full_access_request; + + /* + * Calculate the actual allowed access rights from layer_masks. + * Add each access right to allowed_access which has not been + * vetoed by any layer. + */ + allowed_access = 0; + for_each_set_bit(access_bit, &access_req, + ARRAY_SIZE(layer_masks)) { + if (!layer_masks[access_bit]) + allowed_access |= BIT_ULL(access_bit); + } + } + + /* + * For operations on already opened files (i.e. ftruncate()), it is the + * access rights at the time of open() which decide whether the + * operation is permitted. Therefore, we record the relevant subset of + * file access rights in the opened struct file. + */ + landlock_file(file)->allowed_access = allowed_access; + + if ((open_access_request & allowed_access) == open_access_request) + return 0; + + return -EACCES; +} + +static int hook_file_truncate(struct file *const file) +{ + /* + * Allows truncation if the truncate right was available at the time of + * opening the file, to get a consistent access check as for read, write + * and execute operations. + * + * Note: For checks done based on the file's Landlock allowed access, we + * enforce them independently of whether the current thread is in a + * Landlock domain, so that open files passed between independent + * processes retain their behaviour. + */ + if (landlock_file(file)->allowed_access & LANDLOCK_ACCESS_FS_TRUNCATE) + return 0; + return -EACCES; } static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = { @@ -1206,8 +1297,11 @@ static struct security_hook_list landlock_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(path_symlink, hook_path_symlink), LSM_HOOK_INIT(path_unlink, hook_path_unlink), LSM_HOOK_INIT(path_rmdir, hook_path_rmdir), + LSM_HOOK_INIT(path_truncate, hook_path_truncate), + LSM_HOOK_INIT(file_alloc_security, hook_file_alloc_security), LSM_HOOK_INIT(file_open, hook_file_open), + LSM_HOOK_INIT(file_truncate, hook_file_truncate), }; __init void landlock_add_fs_hooks(void) diff --git a/security/landlock/fs.h b/security/landlock/fs.h index 8db7acf9109b..488e4813680a 100644 --- a/security/landlock/fs.h +++ b/security/landlock/fs.h @@ -36,6 +36,24 @@ struct landlock_inode_security { struct landlock_object __rcu *object; }; +/** + * struct landlock_file_security - File security blob + * + * This information is populated when opening a file in hook_file_open, and + * tracks the relevant Landlock access rights that were available at the time + * of opening the file. Other LSM hooks use these rights in order to authorize + * operations on already opened files. + */ +struct landlock_file_security { + /** + * @allowed_access: Access rights that were available at the time of + * opening the file. This is not necessarily the full set of access + * rights available at that time, but it's the necessary subset as + * needed to authorize later operations on the open file. + */ + access_mask_t allowed_access; +}; + /** * struct landlock_superblock_security - Superblock security blob * @@ -50,6 +68,12 @@ struct landlock_superblock_security { atomic_long_t inode_refs; }; +static inline struct landlock_file_security * +landlock_file(const struct file *const file) +{ + return file->f_security + landlock_blob_sizes.lbs_file; +} + static inline struct landlock_inode_security * landlock_inode(const struct inode *const inode) { diff --git a/security/landlock/limits.h b/security/landlock/limits.h index b54184ab9439..82288f0e9e5e 100644 --- a/security/landlock/limits.h +++ b/security/landlock/limits.h @@ -18,7 +18,7 @@ #define LANDLOCK_MAX_NUM_LAYERS 16 #define LANDLOCK_MAX_NUM_RULES U32_MAX -#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_REFER +#define LANDLOCK_LAST_ACCESS_FS LANDLOCK_ACCESS_FS_TRUNCATE #define LANDLOCK_MASK_ACCESS_FS ((LANDLOCK_LAST_ACCESS_FS << 1) - 1) #define LANDLOCK_NUM_ACCESS_FS __const_hweight64(LANDLOCK_MASK_ACCESS_FS) diff --git a/security/landlock/setup.c b/security/landlock/setup.c index f8e8e980454c..3f196d2ce4f9 100644 --- a/security/landlock/setup.c +++ b/security/landlock/setup.c @@ -19,6 +19,7 @@ bool landlock_initialized __lsm_ro_after_init = false; struct lsm_blob_sizes landlock_blob_sizes __lsm_ro_after_init = { .lbs_cred = sizeof(struct landlock_cred_security), + .lbs_file = sizeof(struct landlock_file_security), .lbs_inode = sizeof(struct landlock_inode_security), .lbs_superblock = sizeof(struct landlock_superblock_security), }; diff --git a/security/landlock/syscalls.c b/security/landlock/syscalls.c index 2ca0ccbd905a..245cc650a4dc 100644 --- a/security/landlock/syscalls.c +++ b/security/landlock/syscalls.c @@ -129,7 +129,7 @@ static const struct file_operations ruleset_fops = { .write = fop_dummy_write, }; -#define LANDLOCK_ABI_VERSION 2 +#define LANDLOCK_ABI_VERSION 3 /** * sys_landlock_create_ruleset - Create a new ruleset diff --git a/security/security.c b/security/security.c index b55596958d0c..e0fe4ba39eb9 100644 --- a/security/security.c +++ b/security/security.c @@ -185,11 +185,12 @@ static void __init lsm_set_blob_size(int *need, int *lbs) { int offset; - if (*need > 0) { - offset = *lbs; - *lbs += *need; - *need = offset; - } + if (*need <= 0) + return; + + offset = ALIGN(*lbs, sizeof(void *)); + *lbs = offset + *need; + *need = offset; } static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed) diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c index da9290817866..72cdae277b02 100644 --- a/tools/testing/selftests/landlock/base_test.c +++ b/tools/testing/selftests/landlock/base_test.c @@ -75,7 +75,7 @@ TEST(abi_version) const struct landlock_ruleset_attr ruleset_attr = { .handled_access_fs = LANDLOCK_ACCESS_FS_READ_FILE, }; - ASSERT_EQ(2, landlock_create_ruleset(NULL, 0, + ASSERT_EQ(3, landlock_create_ruleset(NULL, 0, LANDLOCK_CREATE_RULESET_VERSION)); ASSERT_EQ(-1, landlock_create_ruleset(&ruleset_attr, 0, diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 45de42a027c5..87b28d14a1aa 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -406,9 +406,10 @@ TEST_F_FORK(layout1, inval) #define ACCESS_FILE ( \ LANDLOCK_ACCESS_FS_EXECUTE | \ LANDLOCK_ACCESS_FS_WRITE_FILE | \ - LANDLOCK_ACCESS_FS_READ_FILE) + LANDLOCK_ACCESS_FS_READ_FILE | \ + LANDLOCK_ACCESS_FS_TRUNCATE) -#define ACCESS_LAST LANDLOCK_ACCESS_FS_REFER +#define ACCESS_LAST LANDLOCK_ACCESS_FS_TRUNCATE #define ACCESS_ALL ( \ ACCESS_FILE | \ @@ -422,7 +423,7 @@ TEST_F_FORK(layout1, inval) LANDLOCK_ACCESS_FS_MAKE_FIFO | \ LANDLOCK_ACCESS_FS_MAKE_BLOCK | \ LANDLOCK_ACCESS_FS_MAKE_SYM | \ - ACCESS_LAST) + LANDLOCK_ACCESS_FS_REFER) /* clang-format on */ -- cgit From 0ec8ce07394442d722806fe61b901a5b2b17249d Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Fri, 14 Oct 2022 15:25:41 -0700 Subject: dmaengine: idxd: Do not enable user type Work Queue without Shared Virtual Addressing When the idxd_user_drv driver is bound to a Work Queue (WQ) device without IOMMU or with IOMMU Passthrough without Shared Virtual Addressing (SVA), the application gains direct access to physical memory via the device by programming physical address to a submitted descriptor. This allows direct userspace read and write access to arbitrary physical memory. This is inconsistent with the security goals of a good kernel API. Unlike vfio_pci driver, the IDXD char device driver does not provide any ways to pin user pages and translate the address from user VA to IOVA or PA without IOMMU SVA. Therefore the application has no way to instruct the device to perform DMA function. This makes the char device not usable for normal application usage. Since user type WQ without SVA cannot be used for normal application usage and presents the security issue, bind idxd_user_drv driver and enable user type WQ only when SVA is enabled (i.e. user PASID is enabled). Fixes: 448c3de8ac83 ("dmaengine: idxd: create user driver for wq 'device'") Cc: stable@vger.kernel.org Suggested-by: Arjan Van De Ven Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Reviewed-by: Jerry Snitselaar Link: https://lore.kernel.org/r/20221014222541.3912195-1-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- drivers/dma/idxd/cdev.c | 18 ++++++++++++++++++ include/uapi/linux/idxd.h | 1 + 2 files changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/dma/idxd/cdev.c b/drivers/dma/idxd/cdev.c index c2808fd081d6..a9b96b18772f 100644 --- a/drivers/dma/idxd/cdev.c +++ b/drivers/dma/idxd/cdev.c @@ -312,6 +312,24 @@ static int idxd_user_drv_probe(struct idxd_dev *idxd_dev) if (idxd->state != IDXD_DEV_ENABLED) return -ENXIO; + /* + * User type WQ is enabled only when SVA is enabled for two reasons: + * - If no IOMMU or IOMMU Passthrough without SVA, userspace + * can directly access physical address through the WQ. + * - The IDXD cdev driver does not provide any ways to pin + * user pages and translate the address from user VA to IOVA or + * PA without IOMMU SVA. Therefore the application has no way + * to instruct the device to perform DMA function. This makes + * the cdev not usable for normal application usage. + */ + if (!device_user_pasid_enabled(idxd)) { + idxd->cmd_status = IDXD_SCMD_WQ_USER_NO_IOMMU; + dev_dbg(&idxd->pdev->dev, + "User type WQ cannot be enabled without SVA.\n"); + + return -EOPNOTSUPP; + } + mutex_lock(&wq->wq_lock); wq->type = IDXD_WQT_USER; rc = drv_enable_wq(wq); diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 095299c75828..2b9e7feba3f3 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -29,6 +29,7 @@ enum idxd_scmd_stat { IDXD_SCMD_WQ_NO_SIZE = 0x800e0000, IDXD_SCMD_WQ_NO_PRIV = 0x800f0000, IDXD_SCMD_WQ_IRQ_ERR = 0x80100000, + IDXD_SCMD_WQ_USER_NO_IOMMU = 0x80110000, }; #define IDXD_SCMD_SOFTERR_MASK 0x80000000 -- cgit From d182bf156c4cb8b08ce4a75e82b3357b14a4382d Mon Sep 17 00:00:00 2001 From: Michael Grzeschik Date: Tue, 11 Oct 2022 09:53:48 +0200 Subject: usb: gadget: uvc: default the ctrl request interface offsets For the userspace it is needed to distinguish between requests for the control or streaming interface. The userspace would have to parse the configfs to know which interface index it has to compare the ctrl requests against. Since the interface numbers are not fixed, e.g. for composite gadgets, the interface offset depends on the setup. The kernel has this information when handing over the ctrl request to the userspace. This patch removes the offset from the interface numbers and expose the default interface defines in the uapi g_uvc.h. Signed-off-by: Michael Grzeschik Link: https://lore.kernel.org/r/20221011075348.1786897-1-m.grzeschik@pengutronix.de Signed-off-by: Greg Kroah-Hartman --- drivers/usb/gadget/function/f_uvc.c | 15 ++++++++++++--- include/uapi/linux/usb/g_uvc.h | 3 +++ 2 files changed, 15 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/usb/gadget/function/f_uvc.c b/drivers/usb/gadget/function/f_uvc.c index 6e196e06181e..6e131624011a 100644 --- a/drivers/usb/gadget/function/f_uvc.c +++ b/drivers/usb/gadget/function/f_uvc.c @@ -39,9 +39,6 @@ MODULE_PARM_DESC(trace, "Trace level bitmask"); /* string IDs are assigned dynamically */ -#define UVC_STRING_CONTROL_IDX 0 -#define UVC_STRING_STREAMING_IDX 1 - static struct usb_string uvc_en_us_strings[] = { /* [UVC_STRING_CONTROL_IDX].s = DYNAMIC, */ [UVC_STRING_STREAMING_IDX].s = "Video Streaming", @@ -228,6 +225,8 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) struct uvc_device *uvc = to_uvc(f); struct v4l2_event v4l2_event; struct uvc_event *uvc_event = (void *)&v4l2_event.u.data; + unsigned int interface = le16_to_cpu(ctrl->wIndex) & 0xff; + struct usb_ctrlrequest *mctrl; if ((ctrl->bRequestType & USB_TYPE_MASK) != USB_TYPE_CLASS) { uvcg_info(f, "invalid request type\n"); @@ -248,6 +247,16 @@ uvc_function_setup(struct usb_function *f, const struct usb_ctrlrequest *ctrl) memset(&v4l2_event, 0, sizeof(v4l2_event)); v4l2_event.type = UVC_EVENT_SETUP; memcpy(&uvc_event->req, ctrl, sizeof(uvc_event->req)); + + /* check for the interface number, fixup the interface number in + * the ctrl request so the userspace doesn't have to bother with + * offset and configfs parsing + */ + mctrl = &uvc_event->req; + mctrl->wIndex &= ~cpu_to_le16(0xff); + if (interface == uvc->streaming_intf) + mctrl->wIndex = cpu_to_le16(UVC_STRING_STREAMING_IDX); + v4l2_event_queue(&uvc->vdev, &v4l2_event); return 0; diff --git a/include/uapi/linux/usb/g_uvc.h b/include/uapi/linux/usb/g_uvc.h index 652f169a019e..8d7824dde1b2 100644 --- a/include/uapi/linux/usb/g_uvc.h +++ b/include/uapi/linux/usb/g_uvc.h @@ -21,6 +21,9 @@ #define UVC_EVENT_DATA (V4L2_EVENT_PRIVATE_START + 5) #define UVC_EVENT_LAST (V4L2_EVENT_PRIVATE_START + 5) +#define UVC_STRING_CONTROL_IDX 0 +#define UVC_STRING_STREAMING_IDX 1 + struct uvc_request_data { __s32 length; __u8 data[60]; -- cgit From 404c76783f322120266a4ef659abe418dc74f5c6 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 20 Oct 2022 17:20:03 +0200 Subject: ethtool: Add support for 800Gbps link modes Add support for 800Gbps speed, link modes of 100Gbps per lane. As mentioned in slide 21 in IEEE documentation [1], all adopted 802.3df copper and optical PMDs baselines using 100G/lane will be supported. Add the relevant PMDs which are mentioned in slide 5 in IEEE documentation [1] and were approved on 10-2022 [2]: BP - KR8 Cu Cable - CR8 MMF 50m - VR8 MMF 100m - SR8 SMF 500m - DR8 SMF 2km - DR8-2 [1]: https://www.ieee802.org/3/df/public/22_10/22_1004/shrikhande_3df_01a_221004.pdf [2]: https://ieee802.org/3/df/KeyMotions_3df_221005.pdf Signed-off-by: Amit Cohen Reviewed-by: Ido Schimmel Signed-off-by: Petr Machata Signed-off-by: David S. Miller --- drivers/net/phy/phy-core.c | 11 ++++++++++- include/uapi/linux/ethtool.h | 8 ++++++++ net/ethtool/common.c | 14 ++++++++++++++ 3 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c index 2c8bf438ea61..5d08c627a516 100644 --- a/drivers/net/phy/phy-core.c +++ b/drivers/net/phy/phy-core.c @@ -13,7 +13,7 @@ */ const char *phy_speed_to_str(int speed) { - BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 93, + BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 99, "Enum ethtool_link_mode_bit_indices and phylib are out of sync. " "If a speed or mode has been added please update phy_speed_to_str " "and the PHY settings array.\n"); @@ -49,6 +49,8 @@ const char *phy_speed_to_str(int speed) return "200Gbps"; case SPEED_400000: return "400Gbps"; + case SPEED_800000: + return "800Gbps"; case SPEED_UNKNOWN: return "Unknown"; default: @@ -157,6 +159,13 @@ EXPORT_SYMBOL_GPL(phy_interface_num_ports); .bit = ETHTOOL_LINK_MODE_ ## b ## _BIT} static const struct phy_setting settings[] = { + /* 800G */ + PHY_SETTING( 800000, FULL, 800000baseCR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseKR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseDR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseDR8_2_Full ), + PHY_SETTING( 800000, FULL, 800000baseSR8_Full ), + PHY_SETTING( 800000, FULL, 800000baseVR8_Full ), /* 400G */ PHY_SETTING( 400000, FULL, 400000baseCR8_Full ), PHY_SETTING( 400000, FULL, 400000baseKR8_Full ), diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index dc2aa3d75b39..f341de2ae612 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -1737,6 +1737,13 @@ enum ethtool_link_mode_bit_indices { ETHTOOL_LINK_MODE_100baseFX_Half_BIT = 90, ETHTOOL_LINK_MODE_100baseFX_Full_BIT = 91, ETHTOOL_LINK_MODE_10baseT1L_Full_BIT = 92, + ETHTOOL_LINK_MODE_800000baseCR8_Full_BIT = 93, + ETHTOOL_LINK_MODE_800000baseKR8_Full_BIT = 94, + ETHTOOL_LINK_MODE_800000baseDR8_Full_BIT = 95, + ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT = 96, + ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT = 97, + ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT = 98, + /* must be last entry */ __ETHTOOL_LINK_MODE_MASK_NBITS }; @@ -1848,6 +1855,7 @@ enum ethtool_link_mode_bit_indices { #define SPEED_100000 100000 #define SPEED_200000 200000 #define SPEED_400000 400000 +#define SPEED_800000 800000 #define SPEED_UNKNOWN -1 diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 566adf85e658..ee3e02da0013 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -202,6 +202,12 @@ const char link_mode_names[][ETH_GSTRING_LEN] = { __DEFINE_LINK_MODE_NAME(100, FX, Half), __DEFINE_LINK_MODE_NAME(100, FX, Full), __DEFINE_LINK_MODE_NAME(10, T1L, Full), + __DEFINE_LINK_MODE_NAME(800000, CR8, Full), + __DEFINE_LINK_MODE_NAME(800000, KR8, Full), + __DEFINE_LINK_MODE_NAME(800000, DR8, Full), + __DEFINE_LINK_MODE_NAME(800000, DR8_2, Full), + __DEFINE_LINK_MODE_NAME(800000, SR8, Full), + __DEFINE_LINK_MODE_NAME(800000, VR8, Full), }; static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); @@ -238,6 +244,8 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS); #define __LINK_MODE_LANES_X 1 #define __LINK_MODE_LANES_FX 1 #define __LINK_MODE_LANES_T1L 1 +#define __LINK_MODE_LANES_VR8 8 +#define __LINK_MODE_LANES_DR8_2 8 #define __DEFINE_LINK_MODE_PARAMS(_speed, _type, _duplex) \ [ETHTOOL_LINK_MODE(_speed, _type, _duplex)] = { \ @@ -352,6 +360,12 @@ const struct link_mode_info link_mode_params[] = { __DEFINE_LINK_MODE_PARAMS(100, FX, Half), __DEFINE_LINK_MODE_PARAMS(100, FX, Full), __DEFINE_LINK_MODE_PARAMS(10, T1L, Full), + __DEFINE_LINK_MODE_PARAMS(800000, CR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, KR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, DR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, DR8_2, Full), + __DEFINE_LINK_MODE_PARAMS(800000, SR8, Full), + __DEFINE_LINK_MODE_PARAMS(800000, VR8, Full), }; static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS); -- cgit From e77eb66342c73946f7ed9ea68a6329f13b4343eb Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Thu, 29 Sep 2022 11:11:22 +0200 Subject: videodev2.h: add p_s32 and p_s64 pointers Added p_s32 and p_s64 pointers to the union in struct v4l2_ext_control to simplify INTEGER and INTEGER64 control array support. Internally the control framework handles such arrays just fine, but userspace is missing corresponding pointers to access array elements of these types. The internal union v4l2_ctrl_ptr which the control framework uses already has these types, they just were never added to the public API. Signed-off-by: Hans Verkuil --- include/uapi/linux/videodev2.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 86cae23cc446..a6f5c008a5a8 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1779,6 +1779,8 @@ struct v4l2_ext_control { __u8 __user *p_u8; __u16 __user *p_u16; __u32 __user *p_u32; + __u32 __user *p_s32; + __u32 __user *p_s64; struct v4l2_area __user *p_area; struct v4l2_ctrl_h264_sps __user *p_h264_sps; struct v4l2_ctrl_h264_pps *p_h264_pps; -- cgit From 48f750e25ab72c36f2b043370175adf602d4a45e Mon Sep 17 00:00:00 2001 From: Benjamin Mugnier Date: Tue, 11 Oct 2022 14:16:01 +0200 Subject: media: v4l: Add 1X16 16-bit greyscale media bus code definition This extends the greyscale media bus family originally from MEDIA_BUS_FMT_Y8_1X8 up to MEDIA_BUS_FMT_Y14_1X14 by adding MEDIA_BUS_FMT_Y16_1X16, and behaves the same way with 16 bits. Add its documentation in subdev-formats.rst Signed-off-by: Benjamin Mugnier Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus --- .../userspace-api/media/v4l/subdev-formats.rst | 37 ++++++++++++++++++++++ include/uapi/linux/media-bus-format.h | 3 +- 2 files changed, 39 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/subdev-formats.rst b/Documentation/userspace-api/media/v4l/subdev-formats.rst index d21d532eee15..16ef3b41932e 100644 --- a/Documentation/userspace-api/media/v4l/subdev-formats.rst +++ b/Documentation/userspace-api/media/v4l/subdev-formats.rst @@ -6057,6 +6057,43 @@ the following codes. - y\ :sub:`2` - y\ :sub:`1` - y\ :sub:`0` + * .. _MEDIA-BUS-FMT-Y16-1X16: + + - MEDIA_BUS_FMT_Y16_1X16 + - 0x202e + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - + - y\ :sub:`15` + - y\ :sub:`14` + - y\ :sub:`13` + - y\ :sub:`12` + - y\ :sub:`11` + - y\ :sub:`10` + - y\ :sub:`9` + - y\ :sub:`8` + - y\ :sub:`7` + - y\ :sub:`6` + - y\ :sub:`5` + - y\ :sub:`4` + - y\ :sub:`3` + - y\ :sub:`2` + - y\ :sub:`1` + - y\ :sub:`0` * .. _MEDIA-BUS-FMT-UYVY8-1X16: - MEDIA_BUS_FMT_UYVY8_1X16 diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h index ec3323dbb927..ca9a24c874da 100644 --- a/include/uapi/linux/media-bus-format.h +++ b/include/uapi/linux/media-bus-format.h @@ -69,7 +69,7 @@ #define MEDIA_BUS_FMT_RGB121212_1X36 0x1019 #define MEDIA_BUS_FMT_RGB161616_1X48 0x101a -/* YUV (including grey) - next is 0x202e */ +/* YUV (including grey) - next is 0x202f */ #define MEDIA_BUS_FMT_Y8_1X8 0x2001 #define MEDIA_BUS_FMT_UV8_1X8 0x2015 #define MEDIA_BUS_FMT_UYVY8_1_5X8 0x2002 @@ -92,6 +92,7 @@ #define MEDIA_BUS_FMT_YUYV12_2X12 0x201e #define MEDIA_BUS_FMT_YVYU12_2X12 0x201f #define MEDIA_BUS_FMT_Y14_1X14 0x202d +#define MEDIA_BUS_FMT_Y16_1X16 0x202e #define MEDIA_BUS_FMT_UYVY8_1X16 0x200f #define MEDIA_BUS_FMT_VYUY8_1X16 0x2010 #define MEDIA_BUS_FMT_YUYV8_1X16 0x2011 -- cgit From 7673f3058bd2511474491d4f82c2ece09176412c Mon Sep 17 00:00:00 2001 From: Benjamin Mugnier Date: Tue, 11 Oct 2022 14:16:02 +0200 Subject: media: v4l: ctrls: Add a control for HDR mode Add V4L2_CID_HDR_MODE as a menu item control to set the HDR mode of the sensor, and its documentation. Menu items are not standardized as they differ for each sensors. Signed-off-by: Benjamin Mugnier Signed-off-by: Sakari Ailus --- Documentation/userspace-api/media/v4l/ext-ctrls-camera.rst | 8 ++++++++ drivers/media/v4l2-core/v4l2-ctrls-defs.c | 2 ++ include/uapi/linux/v4l2-controls.h | 2 ++ 3 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/ext-ctrls-camera.rst b/Documentation/userspace-api/media/v4l/ext-ctrls-camera.rst index 4c5061aa9cd4..daa4f40869f8 100644 --- a/Documentation/userspace-api/media/v4l/ext-ctrls-camera.rst +++ b/Documentation/userspace-api/media/v4l/ext-ctrls-camera.rst @@ -661,3 +661,11 @@ enum v4l2_scene_mode - .. [#f1] This control may be changed to a menu control in the future, if more options are required. + +``V4L2_CID_HDR_SENSOR_MODE (menu)`` + Change the sensor HDR mode. A HDR picture is obtained by merging two + captures of the same scene using two different exposure periods. HDR mode + describes the way these two captures are merged in the sensor. + + As modes differ for each sensor, menu items are not standardized by this + control and are left to the programmer. diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index e22921e7ea61..564fedee2c88 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -1043,6 +1043,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_UNIT_CELL_SIZE: return "Unit Cell Size"; case V4L2_CID_CAMERA_ORIENTATION: return "Camera Orientation"; case V4L2_CID_CAMERA_SENSOR_ROTATION: return "Camera Sensor Rotation"; + case V4L2_CID_HDR_SENSOR_MODE: return "HDR Sensor Mode"; /* FM Radio Modulator controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ @@ -1370,6 +1371,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type, case V4L2_CID_STATELESS_H264_START_CODE: case V4L2_CID_CAMERA_ORIENTATION: case V4L2_CID_MPEG_VIDEO_INTRA_REFRESH_PERIOD_TYPE: + case V4L2_CID_HDR_SENSOR_MODE: *type = V4L2_CTRL_TYPE_MENU; break; case V4L2_CID_LINK_FREQ: diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index b5e7d082b8ad..d27e255ed33b 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1019,6 +1019,8 @@ enum v4l2_auto_focus_range { #define V4L2_CID_CAMERA_SENSOR_ROTATION (V4L2_CID_CAMERA_CLASS_BASE+35) +#define V4L2_CID_HDR_SENSOR_MODE (V4L2_CID_CAMERA_CLASS_BASE+36) + /* FM Modulator class control IDs */ #define V4L2_CID_FM_TX_CLASS_BASE (V4L2_CTRL_CLASS_FM_TX | 0x900) -- cgit From 3a07327d10a09379315c844c63f27941f5081e0a Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 25 Oct 2022 13:48:15 +0200 Subject: netfilter: nft_inner: support for inner tunnel header matching This new expression allows you to match on the inner headers that are encapsulated by any of the existing tunneling protocols. This expression parses the inner packet to set the link, network and transport offsets, so the existing expressions (with a few updates) can be reused to match on the inner headers. The inner expression supports for different tunnel combinations such as: - ethernet frame over IPv4/IPv6 packet, eg. VxLAN. - IPv4/IPv6 packet over IPv4/IPv6 packet, eg. IPIP. - IPv4/IPv6 packet over IPv4/IPv6 + transport header, eg. GRE. - transport header (ESP or SCTP) over transport header (usually UDP) The following fields are used to describe the tunnel protocol: - flags, which describe how to parse the inner headers: NFT_PAYLOAD_CTX_INNER_TUN, the tunnel provides its own header. NFT_PAYLOAD_CTX_INNER_ETHER, the ethernet frame is available as inner header. NFT_PAYLOAD_CTX_INNER_NH, the network header is available as inner header. NFT_PAYLOAD_CTX_INNER_TH, the transport header is available as inner header. For example, VxLAN sets on all of these flags. While GRE only sets on NFT_PAYLOAD_CTX_INNER_NH and NFT_PAYLOAD_CTX_INNER_TH. Then, ESP over UDP only sets on NFT_PAYLOAD_CTX_INNER_TH. The tunnel description is composed of the following attributes: - header size: in case the tunnel comes with its own header, eg. VxLAN. - type: this provides a hint to userspace on how to delinearize the rule. This is useful for VxLAN and Geneve since they run over UDP, since transport does not provide a hint. This is also useful in case hardware offload is ever supported. The type is not currently interpreted by the kernel. - expression: currently only payload supported. Follow up patch adds also inner meta support which is required by autogenerated dependencies. The exthdr expression should be supported too at some point. There is a new inner_ops operation that needs to be set on to allow to use an existing expression from the inner expression. This patch adds a new NFT_PAYLOAD_TUN_HEADER base which allows to match on the tunnel header fields, eg. vxlan vni. The payload expression is embedded into nft_inner private area and this private data area is passed to the payload inner eval function via direct call. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 + include/net/netfilter/nf_tables_core.h | 24 +++ include/uapi/linux/netfilter/nf_tables.h | 26 +++ net/netfilter/Makefile | 2 +- net/netfilter/nf_tables_api.c | 37 ++++ net/netfilter/nf_tables_core.c | 1 + net/netfilter/nft_inner.c | 336 +++++++++++++++++++++++++++++++ net/netfilter/nft_payload.c | 89 +++++++- 8 files changed, 518 insertions(+), 2 deletions(-) create mode 100644 net/netfilter/nft_inner.c (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index f6db510689a8..2dbfe7524a7e 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -375,6 +375,10 @@ static inline void *nft_expr_priv(const struct nft_expr *expr) return (void *)expr->data; } +struct nft_expr_info; + +int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, + struct nft_expr_info *info); int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, @@ -864,6 +868,7 @@ struct nft_expr_type { const struct nlattr * const tb[]); void (*release_ops)(const struct nft_expr_ops *ops); const struct nft_expr_ops *ops; + const struct nft_expr_ops *inner_ops; struct list_head list; const char *name; struct module *owner; diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index 83d763631f81..be2b2b5d0a52 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -19,6 +19,7 @@ extern struct nft_expr_type nft_rt_type; extern struct nft_expr_type nft_exthdr_type; extern struct nft_expr_type nft_last_type; extern struct nft_expr_type nft_objref_type; +extern struct nft_expr_type nft_inner_type; #ifdef CONFIG_NETWORK_SECMARK extern struct nft_object_type nft_secmark_obj_type; @@ -139,4 +140,27 @@ void nft_rt_get_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); void nft_counter_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt); + +enum { + NFT_PAYLOAD_CTX_INNER_TUN = (1 << 0), + NFT_PAYLOAD_CTX_INNER_LL = (1 << 1), + NFT_PAYLOAD_CTX_INNER_NH = (1 << 2), + NFT_PAYLOAD_CTX_INNER_TH = (1 << 3), +}; + +struct nft_inner_tun_ctx { + u16 inner_tunoff; + u16 inner_lloff; + u16 inner_nhoff; + u16 inner_thoff; + __be16 llproto; + u8 l4proto; + u8 flags; +}; + +int nft_payload_inner_offset(const struct nft_pktinfo *pkt); +void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx); + #endif /* _NET_NF_TABLES_CORE_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 466fd3f4447c..05a15dce8271 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -760,6 +760,7 @@ enum nft_payload_bases { NFT_PAYLOAD_NETWORK_HEADER, NFT_PAYLOAD_TRANSPORT_HEADER, NFT_PAYLOAD_INNER_HEADER, + NFT_PAYLOAD_TUN_HEADER, }; /** @@ -779,6 +780,31 @@ enum nft_payload_csum_flags { NFT_PAYLOAD_L4CSUM_PSEUDOHDR = (1 << 0), }; +enum nft_inner_type { + NFT_INNER_UNSPEC = 0, + NFT_INNER_VXLAN, +}; + +enum nft_inner_flags { + NFT_INNER_HDRSIZE = (1 << 0), + NFT_INNER_LL = (1 << 1), + NFT_INNER_NH = (1 << 2), + NFT_INNER_TH = (1 << 3), +}; +#define NFT_INNER_MASK (NFT_INNER_HDRSIZE | NFT_INNER_LL | \ + NFT_INNER_NH | NFT_INNER_TH) + +enum nft_inner_attributes { + NFTA_INNER_UNSPEC, + NFTA_INNER_NUM, + NFTA_INNER_TYPE, + NFTA_INNER_FLAGS, + NFTA_INNER_HDRSIZE, + NFTA_INNER_EXPR, + __NFTA_INNER_MAX +}; +#define NFTA_INNER_MAX (__NFTA_INNER_MAX - 1) + /** * enum nft_payload_attributes - nf_tables payload expression netlink attributes * diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 7a6b518ba2b4..1d4db1943936 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -86,7 +86,7 @@ nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o nft_last.o \ - nft_counter.o nft_objref.o \ + nft_counter.o nft_objref.o nft_inner.o \ nft_chain_route.o nf_tables_offload.o \ nft_set_hash.o nft_set_bitmap.o nft_set_rbtree.o \ nft_set_pipapo.o diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 58d9cbc9ccdc..6b79f5e18f08 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2857,6 +2857,43 @@ err1: return err; } +int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, + struct nft_expr_info *info) +{ + struct nlattr *tb[NFTA_EXPR_MAX + 1]; + const struct nft_expr_type *type; + int err; + + err = nla_parse_nested_deprecated(tb, NFTA_EXPR_MAX, nla, + nft_expr_policy, NULL); + if (err < 0) + return err; + + if (!tb[NFTA_EXPR_DATA]) + return -EINVAL; + + type = __nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]); + if (IS_ERR(type)) + return PTR_ERR(type); + + if (!type->inner_ops) + return -EOPNOTSUPP; + + err = nla_parse_nested_deprecated(info->tb, type->maxattr, + tb[NFTA_EXPR_DATA], + type->policy, NULL); + if (err < 0) + goto err_nla_parse; + + info->attr = nla; + info->ops = type->inner_ops; + + return 0; + +err_nla_parse: + return err; +} + static int nf_tables_newexpr(const struct nft_ctx *ctx, const struct nft_expr_info *expr_info, struct nft_expr *expr) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 6dcead50208c..709a736c301c 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -341,6 +341,7 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_last_type, &nft_counter_type, &nft_objref_type, + &nft_inner_type, }; static struct nft_object_type *nft_basic_objects[] = { diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c new file mode 100644 index 000000000000..1e4079b5b431 --- /dev/null +++ b/net/netfilter/nft_inner.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2022 Pablo Neira Ayuso + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +/* Same layout as nft_expr but it embeds the private expression data area. */ +struct __nft_expr { + const struct nft_expr_ops *ops; + union { + struct nft_payload payload; + } __attribute__((aligned(__alignof__(u64)))); +}; + +enum { + NFT_INNER_EXPR_PAYLOAD, +}; + +struct nft_inner { + u8 flags; + u8 hdrsize; + u8 type; + u8 expr_type; + + struct __nft_expr expr; +}; + +static int nft_inner_parse_l2l3(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx, u32 off) +{ + __be16 llproto, outer_llproto; + u32 nhoff, thoff; + + if (priv->flags & NFT_INNER_LL) { + struct vlan_ethhdr *veth, _veth; + struct ethhdr *eth, _eth; + u32 hdrsize; + + eth = skb_header_pointer(pkt->skb, off, sizeof(_eth), &_eth); + if (!eth) + return -1; + + switch (eth->h_proto) { + case htons(ETH_P_IP): + case htons(ETH_P_IPV6): + llproto = eth->h_proto; + hdrsize = sizeof(_eth); + break; + case htons(ETH_P_8021Q): + veth = skb_header_pointer(pkt->skb, off, sizeof(_veth), &_veth); + if (!eth) + return -1; + + outer_llproto = veth->h_vlan_encapsulated_proto; + llproto = veth->h_vlan_proto; + hdrsize = sizeof(_veth); + break; + default: + return -1; + } + + ctx->inner_lloff = off; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_LL; + off += hdrsize; + } else { + struct iphdr *iph; + u32 _version; + + iph = skb_header_pointer(pkt->skb, off, sizeof(_version), &_version); + if (!iph) + return -1; + + switch (iph->version) { + case 4: + llproto = htons(ETH_P_IP); + break; + case 6: + llproto = htons(ETH_P_IPV6); + break; + default: + return -1; + } + } + + ctx->llproto = llproto; + if (llproto == htons(ETH_P_8021Q)) + llproto = outer_llproto; + + nhoff = off; + + switch (llproto) { + case htons(ETH_P_IP): { + struct iphdr *iph, _iph; + + iph = skb_header_pointer(pkt->skb, nhoff, sizeof(_iph), &_iph); + if (!iph) + return -1; + + if (iph->ihl < 5 || iph->version != 4) + return -1; + + ctx->inner_nhoff = nhoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_NH; + + thoff = nhoff + (iph->ihl * 4); + if ((ntohs(iph->frag_off) & IP_OFFSET) == 0) { + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; + ctx->inner_thoff = thoff; + ctx->l4proto = iph->protocol; + } + } + break; + case htons(ETH_P_IPV6): { + struct ipv6hdr *ip6h, _ip6h; + int fh_flags = IP6_FH_F_AUTH; + unsigned short fragoff; + int l4proto; + + ip6h = skb_header_pointer(pkt->skb, nhoff, sizeof(_ip6h), &_ip6h); + if (!ip6h) + return -1; + + if (ip6h->version != 6) + return -1; + + ctx->inner_nhoff = nhoff; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_NH; + + thoff = nhoff; + l4proto = ipv6_find_hdr(pkt->skb, &thoff, -1, &fragoff, &fh_flags); + if (l4proto < 0 || thoff > U16_MAX) + return -1; + + if (fragoff == 0) { + thoff = nhoff + sizeof(_ip6h); + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TH; + ctx->inner_thoff = thoff; + ctx->l4proto = l4proto; + } + } + break; + default: + return -1; + } + + return 0; +} + +static int nft_inner_parse_tunhdr(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *ctx, u32 *off) +{ + if (pkt->tprot != IPPROTO_UDP || + pkt->tprot != IPPROTO_GRE) + return -1; + + ctx->inner_tunoff = *off; + ctx->flags |= NFT_PAYLOAD_CTX_INNER_TUN; + *off += priv->hdrsize; + + return 0; +} + +static int nft_inner_parse(const struct nft_inner *priv, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + struct nft_inner_tun_ctx ctx = {}; + u32 off = pkt->inneroff; + + if (priv->flags & NFT_INNER_HDRSIZE && + nft_inner_parse_tunhdr(priv, pkt, &ctx, &off) < 0) + return -1; + + if (priv->flags & (NFT_INNER_LL | NFT_INNER_NH)) { + if (nft_inner_parse_l2l3(priv, pkt, &ctx, off) < 0) + return -1; + } else if (priv->flags & NFT_INNER_TH) { + ctx.inner_thoff = off; + ctx.flags |= NFT_PAYLOAD_CTX_INNER_TH; + } + + *tun_ctx = ctx; + + return 0; +} + +static void nft_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + const struct nft_inner *priv = nft_expr_priv(expr); + struct nft_inner_tun_ctx tun_ctx = {}; + + if (nft_payload_inner_offset(pkt) < 0) + goto err; + + if (nft_inner_parse(priv, pkt, &tun_ctx) < 0) + goto err; + + switch (priv->expr_type) { + case NFT_INNER_EXPR_PAYLOAD: + nft_payload_inner_eval((struct nft_expr *)&priv->expr, regs, pkt, &tun_ctx); + break; + default: + WARN_ON_ONCE(1); + goto err; + } + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static const struct nla_policy nft_inner_policy[NFTA_INNER_MAX + 1] = { + [NFTA_INNER_NUM] = { .type = NLA_U32 }, + [NFTA_INNER_FLAGS] = { .type = NLA_U32 }, + [NFTA_INNER_HDRSIZE] = { .type = NLA_U32 }, + [NFTA_INNER_TYPE] = { .type = NLA_U32 }, + [NFTA_INNER_EXPR] = { .type = NLA_NESTED }, +}; + +struct nft_expr_info { + const struct nft_expr_ops *ops; + const struct nlattr *attr; + struct nlattr *tb[NFT_EXPR_MAXATTR + 1]; +}; + +static int nft_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_inner *priv = nft_expr_priv(expr); + u32 flags, hdrsize, type, num; + struct nft_expr_info expr_info; + int err; + + if (!tb[NFTA_INNER_FLAGS] || + !tb[NFTA_INNER_HDRSIZE] || + !tb[NFTA_INNER_TYPE] || + !tb[NFTA_INNER_EXPR]) + return -EINVAL; + + flags = ntohl(nla_get_be32(tb[NFTA_INNER_FLAGS])); + if (flags & ~NFT_INNER_MASK) + return -EOPNOTSUPP; + + num = ntohl(nla_get_be32(tb[NFTA_INNER_NUM])); + if (num != 0) + return -EOPNOTSUPP; + + hdrsize = ntohl(nla_get_be32(tb[NFTA_INNER_HDRSIZE])); + type = ntohl(nla_get_be32(tb[NFTA_INNER_TYPE])); + + if (type > U8_MAX) + return -EINVAL; + + if (flags & NFT_INNER_HDRSIZE) { + if (hdrsize == 0 || hdrsize > 64) + return -EOPNOTSUPP; + } + + priv->flags = flags; + priv->hdrsize = hdrsize; + priv->type = type; + + err = nft_expr_inner_parse(ctx, tb[NFTA_INNER_EXPR], &expr_info); + if (err < 0) + return err; + + priv->expr.ops = expr_info.ops; + + if (!strcmp(expr_info.ops->type->name, "payload")) + priv->expr_type = NFT_INNER_EXPR_PAYLOAD; + else + return -EINVAL; + + err = expr_info.ops->init(ctx, (struct nft_expr *)&priv->expr, + (const struct nlattr * const*)expr_info.tb); + if (err < 0) + return err; + + return 0; +} + +static int nft_inner_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_inner *priv = nft_expr_priv(expr); + + if (nla_put_be32(skb, NFTA_INNER_NUM, htonl(0)) || + nla_put_be32(skb, NFTA_INNER_TYPE, htonl(priv->type)) || + nla_put_be32(skb, NFTA_INNER_FLAGS, htonl(priv->flags)) || + nla_put_be32(skb, NFTA_INNER_HDRSIZE, htonl(priv->hdrsize))) + goto nla_put_failure; + + if (nft_expr_dump(skb, NFTA_INNER_EXPR, + (struct nft_expr *)&priv->expr) < 0) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static const struct nft_expr_ops nft_inner_ops = { + .type = &nft_inner_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_inner)), + .eval = nft_inner_eval, + .init = nft_inner_init, + .dump = nft_inner_dump, +}; + +struct nft_expr_type nft_inner_type __read_mostly = { + .name = "inner", + .ops = &nft_inner_ops, + .policy = nft_inner_policy, + .maxattr = NFTA_INNER_MAX, + .owner = THIS_MODULE, +}; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 84b490d6cc75..9d2ac764a14c 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -144,7 +144,7 @@ static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) return 0; } -static int nft_payload_inner_offset(const struct nft_pktinfo *pkt) +int nft_payload_inner_offset(const struct nft_pktinfo *pkt) { if (!(pkt->flags & NFT_PKTINFO_INNER) && __nft_payload_inner_offset((struct nft_pktinfo *)pkt) < 0) @@ -587,6 +587,92 @@ const struct nft_expr_ops nft_payload_fast_ops = { .offload = nft_payload_offload, }; +void nft_payload_inner_eval(const struct nft_expr *expr, struct nft_regs *regs, + const struct nft_pktinfo *pkt, + struct nft_inner_tun_ctx *tun_ctx) +{ + const struct nft_payload *priv = nft_expr_priv(expr); + const struct sk_buff *skb = pkt->skb; + u32 *dest = ®s->data[priv->dreg]; + int offset; + + if (priv->len % NFT_REG32_SIZE) + dest[priv->len / NFT_REG32_SIZE] = 0; + + switch (priv->base) { + case NFT_PAYLOAD_TUN_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TUN)) + goto err; + + offset = tun_ctx->inner_tunoff; + break; + case NFT_PAYLOAD_LL_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_LL)) + goto err; + + offset = tun_ctx->inner_lloff; + break; + case NFT_PAYLOAD_NETWORK_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_NH)) + goto err; + + offset = tun_ctx->inner_nhoff; + break; + case NFT_PAYLOAD_TRANSPORT_HEADER: + if (!(tun_ctx->flags & NFT_PAYLOAD_CTX_INNER_TH)) + goto err; + + offset = tun_ctx->inner_thoff; + break; + default: + WARN_ON_ONCE(1); + goto err; + } + offset += priv->offset; + + if (skb_copy_bits(skb, offset, dest, priv->len) < 0) + goto err; + + return; +err: + regs->verdict.code = NFT_BREAK; +} + +static int nft_payload_inner_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_payload *priv = nft_expr_priv(expr); + u32 base; + + base = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_BASE])); + switch (base) { + case NFT_PAYLOAD_TUN_HEADER: + case NFT_PAYLOAD_LL_HEADER: + case NFT_PAYLOAD_NETWORK_HEADER: + case NFT_PAYLOAD_TRANSPORT_HEADER: + break; + default: + return -EOPNOTSUPP; + } + + priv->base = base; + priv->offset = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_OFFSET])); + priv->len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); + + return nft_parse_register_store(ctx, tb[NFTA_PAYLOAD_DREG], + &priv->dreg, NULL, NFT_DATA_VALUE, + priv->len); +} + +static const struct nft_expr_ops nft_payload_inner_ops = { + .type = &nft_payload_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_payload)), + .init = nft_payload_inner_init, + .dump = nft_payload_dump, + /* direct call to nft_payload_inner_eval(). */ +}; + static inline void nft_csum_replace(__sum16 *sum, __wsum fsum, __wsum tsum) { *sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), fsum), tsum)); @@ -930,6 +1016,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, struct nft_expr_type nft_payload_type __read_mostly = { .name = "payload", .select_ops = nft_payload_select_ops, + .inner_ops = &nft_payload_inner_ops, .policy = nft_payload_policy, .maxattr = NFTA_PAYLOAD_MAX, .owner = THIS_MODULE, -- cgit From 0db14b95660b63dceeb7e89f2e3ffa97d331fce0 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 17 Oct 2022 13:03:34 +0200 Subject: netfilter: nft_inner: add geneve support Geneve tunnel header may contain options, parse geneve header and update offset to point to the link layer header according to the opt_len field. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 1 + net/netfilter/nft_inner.c | 17 +++++++++++++++++ 2 files changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 05a15dce8271..e4b739d57480 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -783,6 +783,7 @@ enum nft_payload_csum_flags { enum nft_inner_type { NFT_INNER_UNSPEC = 0, NFT_INNER_VXLAN, + NFT_INNER_GENEVE, }; enum nft_inner_flags { diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index c43a2fe0ceb7..19fdc8c70cd1 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include #include @@ -181,6 +182,22 @@ static int nft_inner_parse_tunhdr(const struct nft_inner *priv, ctx->flags |= NFT_PAYLOAD_CTX_INNER_TUN; *off += priv->hdrsize; + switch (priv->type) { + case NFT_INNER_GENEVE: { + struct genevehdr *gnvh, _gnvh; + + gnvh = skb_header_pointer(pkt->skb, pkt->inneroff, + sizeof(_gnvh), &_gnvh); + if (!gnvh) + return -1; + + *off += gnvh->opt_len * 4; + } + break; + default: + break; + } + return 0; } -- cgit From 8da7f0976b9071b528c545008de9d10cc81883b1 Mon Sep 17 00:00:00 2001 From: Hans Verkuil Date: Wed, 12 Oct 2022 16:46:17 +0100 Subject: media: videodev2.h: V4L2_DV_BT_BLANKING_HEIGHT should check 'interlaced' If it is a progressive (non-interlaced) format, then ignore the interlaced timing values. Signed-off-by: Hans Verkuil Fixes: 7f68127fa11f ([media] videodev2.h: defines to calculate blanking and frame sizes) Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/videodev2.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 86cae23cc446..29da1f4b4578 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -1601,7 +1601,8 @@ struct v4l2_bt_timings { ((bt)->width + V4L2_DV_BT_BLANKING_WIDTH(bt)) #define V4L2_DV_BT_BLANKING_HEIGHT(bt) \ ((bt)->vfrontporch + (bt)->vsync + (bt)->vbackporch + \ - (bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) + ((bt)->interlaced ? \ + ((bt)->il_vfrontporch + (bt)->il_vsync + (bt)->il_vbackporch) : 0)) #define V4L2_DV_BT_FRAME_HEIGHT(bt) \ ((bt)->height + V4L2_DV_BT_BLANKING_HEIGHT(bt)) -- cgit From 23a7aea5faf6500051c52dfaba46845c41b3abd4 Mon Sep 17 00:00:00 2001 From: Rolf Eike Beer Date: Tue, 4 Oct 2022 12:25:40 +0200 Subject: ELF uapi: add spaces before '{' When searching for a struct definition I often enough end up simply doing git grep 'struct foobar {' Sadly some of the ELF structs did not follow the usual coding style so they were invisible. Signed-off-by: Rolf Eike Beer Signed-off-by: Kees Cook Link: https://lore.kernel.org/r/11563980.Ss37MnutNL@mobilepool36.emlix.com --- include/uapi/linux/elf.h | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index c7b056af9ef0..775a17b5b8ac 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -140,9 +140,9 @@ typedef __s64 Elf64_Sxword; #define ELF64_ST_BIND(x) ELF_ST_BIND(x) #define ELF64_ST_TYPE(x) ELF_ST_TYPE(x) -typedef struct dynamic{ +typedef struct dynamic { Elf32_Sword d_tag; - union{ + union { Elf32_Sword d_val; Elf32_Addr d_ptr; } d_un; @@ -173,7 +173,7 @@ typedef struct elf64_rel { Elf64_Xword r_info; /* index and type of relocation */ } Elf64_Rel; -typedef struct elf32_rela{ +typedef struct elf32_rela { Elf32_Addr r_offset; Elf32_Word r_info; Elf32_Sword r_addend; @@ -185,7 +185,7 @@ typedef struct elf64_rela { Elf64_Sxword r_addend; /* Constant addend used to compute value */ } Elf64_Rela; -typedef struct elf32_sym{ +typedef struct elf32_sym { Elf32_Word st_name; Elf32_Addr st_value; Elf32_Word st_size; @@ -206,7 +206,7 @@ typedef struct elf64_sym { #define EI_NIDENT 16 -typedef struct elf32_hdr{ +typedef struct elf32_hdr { unsigned char e_ident[EI_NIDENT]; Elf32_Half e_type; Elf32_Half e_machine; @@ -246,7 +246,7 @@ typedef struct elf64_hdr { #define PF_W 0x2 #define PF_X 0x1 -typedef struct elf32_phdr{ +typedef struct elf32_phdr { Elf32_Word p_type; Elf32_Off p_offset; Elf32_Addr p_vaddr; -- cgit From 8f6e3f9e5a0f58e458a348b7e36af11d0e9702af Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Oct 2022 00:14:20 -0700 Subject: binfmt: Fix whitespace issues Fix the annoying whitespace issues that have been following these files around for years. Cc: linux-fsdevel@vger.kernel.org Signed-off-by: Kees Cook Acked-by: Christian Brauner (Microsoft) Link: https://lore.kernel.org/r/20221018071350.never.230-kees@kernel.org --- fs/binfmt_elf.c | 14 +++++++------- fs/binfmt_elf_fdpic.c | 2 +- fs/exec.c | 2 +- include/uapi/linux/elf.h | 2 +- 4 files changed, 10 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 6a11025e5850..38a9496f83f3 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -248,7 +248,7 @@ create_elf_tables(struct linux_binprm *bprm, const struct elfhdr *exec, } while (0) #ifdef ARCH_DLINFO - /* + /* * ARCH_DLINFO must come first so PPC can do its special alignment of * AUXV. * update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT() in @@ -1020,7 +1020,7 @@ out_free_interp: executable_stack); if (retval < 0) goto out_free_dentry; - + elf_bss = 0; elf_brk = 0; @@ -1043,7 +1043,7 @@ out_free_interp: if (unlikely (elf_brk > elf_bss)) { unsigned long nbyte; - + /* There was a PT_LOAD segment with p_memsz > p_filesz before this one. Map anonymous pages, if needed, and clear the area. */ @@ -1521,7 +1521,7 @@ static void fill_elf_note_phdr(struct elf_phdr *phdr, int sz, loff_t offset) phdr->p_align = 0; } -static void fill_note(struct memelfnote *note, const char *name, int type, +static void fill_note(struct memelfnote *note, const char *name, int type, unsigned int sz, void *data) { note->name = name; @@ -2004,8 +2004,8 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) t->num_notes = 0; fill_prstatus(&t->prstatus.common, p, signr); - elf_core_copy_task_regs(p, &t->prstatus.pr_reg); - + elf_core_copy_task_regs(p, &t->prstatus.pr_reg); + fill_note(&t->notes[0], "CORE", NT_PRSTATUS, sizeof(t->prstatus), &(t->prstatus)); t->num_notes++; @@ -2295,7 +2295,7 @@ static int elf_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - /* write out the notes section */ + /* write out the notes section */ if (!write_note_info(&info, cprm)) goto end_coredump; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 08d0c8797828..e90c1192dec6 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -1603,7 +1603,7 @@ static int elf_fdpic_core_dump(struct coredump_params *cprm) if (!elf_core_write_extra_phdrs(cprm, offset)) goto end_coredump; - /* write out the notes section */ + /* write out the notes section */ if (!writenote(thread_list->notes, cprm)) goto end_coredump; if (!writenote(&psinfo_note, cprm)) diff --git a/fs/exec.c b/fs/exec.c index b3e87bd50962..1644bf10fb9d 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -172,7 +172,7 @@ SYSCALL_DEFINE1(uselib, const char __user *, library) exit: fput(file); out: - return error; + return error; } #endif /* #ifdef CONFIG_USELIB */ diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h index 775a17b5b8ac..4c6a8fa5e7ed 100644 --- a/include/uapi/linux/elf.h +++ b/include/uapi/linux/elf.h @@ -91,7 +91,7 @@ typedef __s64 Elf64_Sxword; #define DT_INIT 12 #define DT_FINI 13 #define DT_SONAME 14 -#define DT_RPATH 15 +#define DT_RPATH 15 #define DT_SYMBOLIC 16 #define DT_REL 17 #define DT_RELSZ 18 -- cgit From c4bcfb38a95edb1021a53f2d0356a78120ecfbe4 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 25 Oct 2022 21:28:50 -0700 Subject: bpf: Implement cgroup storage available to non-cgroup-attached bpf progs Similar to sk/inode/task storage, implement similar cgroup local storage. There already exists a local storage implementation for cgroup-attached bpf programs. See map type BPF_MAP_TYPE_CGROUP_STORAGE and helper bpf_get_local_storage(). But there are use cases such that non-cgroup attached bpf progs wants to access cgroup local storage data. For example, tc egress prog has access to sk and cgroup. It is possible to use sk local storage to emulate cgroup local storage by storing data in socket. But this is a waste as it could be lots of sockets belonging to a particular cgroup. Alternatively, a separate map can be created with cgroup id as the key. But this will introduce additional overhead to manipulate the new map. A cgroup local storage, similar to existing sk/inode/task storage, should help for this use case. The life-cycle of storage is managed with the life-cycle of the cgroup struct. i.e. the storage is destroyed along with the owning cgroup with a call to bpf_cgrp_storage_free() when cgroup itself is deleted. The userspace map operations can be done by using a cgroup fd as a key passed to the lookup, update and delete operations. Typically, the following code is used to get the current cgroup: struct task_struct *task = bpf_get_current_task_btf(); ... task->cgroups->dfl_cgrp ... and in structure task_struct definition: struct task_struct { .... struct css_set __rcu *cgroups; .... } With sleepable program, accessing task->cgroups is not protected by rcu_read_lock. So the current implementation only supports non-sleepable program and supporting sleepable program will be the next step together with adding rcu_read_lock protection for rcu tagged structures. Since map name BPF_MAP_TYPE_CGROUP_STORAGE has been used for old cgroup local storage support, the new map name BPF_MAP_TYPE_CGRP_STORAGE is used for cgroup storage available to non-cgroup-attached bpf programs. The old cgroup storage supports bpf_get_local_storage() helper to get the cgroup data. The new cgroup storage helper bpf_cgrp_storage_get() can provide similar functionality. While old cgroup storage pre-allocates storage memory, the new mechanism can also pre-allocate with a user space bpf_map_update_elem() call to avoid potential run-time memory allocation failure. Therefore, the new cgroup storage can provide all functionality w.r.t. the old one. So in uapi bpf.h, the old BPF_MAP_TYPE_CGROUP_STORAGE is alias to BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED to indicate the old cgroup storage can be deprecated since the new one can provide the same functionality. Acked-by: David Vernet Signed-off-by: Yonghong Song Link: https://lore.kernel.org/r/20221026042850.673791-1-yhs@fb.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 7 ++ include/linux/bpf_types.h | 1 + include/linux/cgroup-defs.h | 4 + include/uapi/linux/bpf.h | 50 ++++++++- kernel/bpf/Makefile | 2 +- kernel/bpf/bpf_cgrp_storage.c | 247 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/helpers.c | 6 + kernel/bpf/syscall.c | 3 +- kernel/bpf/verifier.c | 13 ++- kernel/cgroup/cgroup.c | 1 + kernel/trace/bpf_trace.c | 4 + scripts/bpf_doc.py | 2 + tools/include/uapi/linux/bpf.h | 50 ++++++++- 13 files changed, 385 insertions(+), 5 deletions(-) create mode 100644 kernel/bpf/bpf_cgrp_storage.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a5dbac8f5aba..9fd68b0b3e9c 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2041,6 +2041,7 @@ struct bpf_link *bpf_link_by_id(u32 id); const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id); void bpf_task_storage_free(struct task_struct *task); +void bpf_cgrp_storage_free(struct cgroup *cgroup); bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog); const struct btf_func_model * bpf_jit_find_kfunc_model(const struct bpf_prog *prog, @@ -2295,6 +2296,10 @@ static inline bool has_current_bpf_ctx(void) static inline void bpf_prog_inc_misses_counter(struct bpf_prog *prog) { } + +static inline void bpf_cgrp_storage_free(struct cgroup *cgroup) +{ +} #endif /* CONFIG_BPF_SYSCALL */ void __bpf_free_used_btfs(struct bpf_prog_aux *aux, @@ -2535,6 +2540,8 @@ extern const struct bpf_func_proto bpf_copy_from_user_task_proto; extern const struct bpf_func_proto bpf_set_retval_proto; extern const struct bpf_func_proto bpf_get_retval_proto; extern const struct bpf_func_proto bpf_user_ringbuf_drain_proto; +extern const struct bpf_func_proto bpf_cgrp_storage_get_proto; +extern const struct bpf_func_proto bpf_cgrp_storage_delete_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2c6a4f2562a7..d4ee3ccd3753 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -86,6 +86,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PROG_ARRAY, prog_array_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops) #ifdef CONFIG_CGROUPS BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_CGRP_STORAGE, cgrp_storage_map_ops) #endif #ifdef CONFIG_CGROUP_BPF BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops) diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 8f481d1b159a..c466fdc3a32a 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -504,6 +504,10 @@ struct cgroup { /* Used to store internal freezer state */ struct cgroup_freezer_state freezer; +#ifdef CONFIG_BPF_SYSCALL + struct bpf_local_storage __rcu *bpf_cgrp_storage; +#endif + /* All ancestors including self */ struct cgroup *ancestors[]; }; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 17f61338f8f8..94659f6b3395 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -922,7 +922,14 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, - BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, @@ -935,6 +942,7 @@ enum bpf_map_type { BPF_MAP_TYPE_TASK_STORAGE, BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, }; /* Note that tracing related programs such as @@ -5435,6 +5443,44 @@ union bpf_attr { * **-E2BIG** if user-space has tried to publish a sample which is * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + * Description + * Delete a bpf_local_storage from a *cgroup*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define ___BPF_FUNC_MAPPER(FN, ctx...) \ FN(unspec, 0, ##ctx) \ @@ -5647,6 +5693,8 @@ union bpf_attr { FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ FN(ktime_get_tai_ns, 208, ##ctx) \ FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ /* */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 341c94f208f4..3a12e6b400a2 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -25,7 +25,7 @@ ifeq ($(CONFIG_PERF_EVENTS),y) obj-$(CONFIG_BPF_SYSCALL) += stackmap.o endif ifeq ($(CONFIG_CGROUPS),y) -obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o +obj-$(CONFIG_BPF_SYSCALL) += cgroup_iter.o bpf_cgrp_storage.o endif obj-$(CONFIG_CGROUP_BPF) += cgroup.o ifeq ($(CONFIG_INET),y) diff --git a/kernel/bpf/bpf_cgrp_storage.c b/kernel/bpf/bpf_cgrp_storage.c new file mode 100644 index 000000000000..309403800f82 --- /dev/null +++ b/kernel/bpf/bpf_cgrp_storage.c @@ -0,0 +1,247 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2022 Meta Platforms, Inc. and affiliates. + */ + +#include +#include +#include +#include +#include + +DEFINE_BPF_STORAGE_CACHE(cgroup_cache); + +static DEFINE_PER_CPU(int, bpf_cgrp_storage_busy); + +static void bpf_cgrp_storage_lock(void) +{ + migrate_disable(); + this_cpu_inc(bpf_cgrp_storage_busy); +} + +static void bpf_cgrp_storage_unlock(void) +{ + this_cpu_dec(bpf_cgrp_storage_busy); + migrate_enable(); +} + +static bool bpf_cgrp_storage_trylock(void) +{ + migrate_disable(); + if (unlikely(this_cpu_inc_return(bpf_cgrp_storage_busy) != 1)) { + this_cpu_dec(bpf_cgrp_storage_busy); + migrate_enable(); + return false; + } + return true; +} + +static struct bpf_local_storage __rcu **cgroup_storage_ptr(void *owner) +{ + struct cgroup *cg = owner; + + return &cg->bpf_cgrp_storage; +} + +void bpf_cgrp_storage_free(struct cgroup *cgroup) +{ + struct bpf_local_storage *local_storage; + bool free_cgroup_storage = false; + unsigned long flags; + + rcu_read_lock(); + local_storage = rcu_dereference(cgroup->bpf_cgrp_storage); + if (!local_storage) { + rcu_read_unlock(); + return; + } + + bpf_cgrp_storage_lock(); + raw_spin_lock_irqsave(&local_storage->lock, flags); + free_cgroup_storage = bpf_local_storage_unlink_nolock(local_storage); + raw_spin_unlock_irqrestore(&local_storage->lock, flags); + bpf_cgrp_storage_unlock(); + rcu_read_unlock(); + + if (free_cgroup_storage) + kfree_rcu(local_storage, rcu); +} + +static struct bpf_local_storage_data * +cgroup_storage_lookup(struct cgroup *cgroup, struct bpf_map *map, bool cacheit_lockit) +{ + struct bpf_local_storage *cgroup_storage; + struct bpf_local_storage_map *smap; + + cgroup_storage = rcu_dereference_check(cgroup->bpf_cgrp_storage, + bpf_rcu_lock_held()); + if (!cgroup_storage) + return NULL; + + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(cgroup_storage, smap, cacheit_lockit); +} + +static void *bpf_cgrp_storage_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_local_storage_data *sdata; + struct cgroup *cgroup; + int fd; + + fd = *(int *)key; + cgroup = cgroup_get_from_fd(fd); + if (IS_ERR(cgroup)) + return ERR_CAST(cgroup); + + bpf_cgrp_storage_lock(); + sdata = cgroup_storage_lookup(cgroup, map, true); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return sdata ? sdata->data : NULL; +} + +static int bpf_cgrp_storage_update_elem(struct bpf_map *map, void *key, + void *value, u64 map_flags) +{ + struct bpf_local_storage_data *sdata; + struct cgroup *cgroup; + int fd; + + fd = *(int *)key; + cgroup = cgroup_get_from_fd(fd); + if (IS_ERR(cgroup)) + return PTR_ERR(cgroup); + + bpf_cgrp_storage_lock(); + sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, + value, map_flags, GFP_ATOMIC); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return PTR_ERR_OR_ZERO(sdata); +} + +static int cgroup_storage_delete(struct cgroup *cgroup, struct bpf_map *map) +{ + struct bpf_local_storage_data *sdata; + + sdata = cgroup_storage_lookup(cgroup, map, false); + if (!sdata) + return -ENOENT; + + bpf_selem_unlink(SELEM(sdata), true); + return 0; +} + +static int bpf_cgrp_storage_delete_elem(struct bpf_map *map, void *key) +{ + struct cgroup *cgroup; + int err, fd; + + fd = *(int *)key; + cgroup = cgroup_get_from_fd(fd); + if (IS_ERR(cgroup)) + return PTR_ERR(cgroup); + + bpf_cgrp_storage_lock(); + err = cgroup_storage_delete(cgroup, map); + bpf_cgrp_storage_unlock(); + cgroup_put(cgroup); + return err; +} + +static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + return -ENOTSUPP; +} + +static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) +{ + return bpf_local_storage_map_alloc(attr, &cgroup_cache); +} + +static void cgroup_storage_map_free(struct bpf_map *map) +{ + bpf_local_storage_map_free(map, &cgroup_cache, NULL); +} + +/* *gfp_flags* is a hidden argument provided by the verifier */ +BPF_CALL_5(bpf_cgrp_storage_get, struct bpf_map *, map, struct cgroup *, cgroup, + void *, value, u64, flags, gfp_t, gfp_flags) +{ + struct bpf_local_storage_data *sdata; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (flags & ~(BPF_LOCAL_STORAGE_GET_F_CREATE)) + return (unsigned long)NULL; + + if (!cgroup) + return (unsigned long)NULL; + + if (!bpf_cgrp_storage_trylock()) + return (unsigned long)NULL; + + sdata = cgroup_storage_lookup(cgroup, map, true); + if (sdata) + goto unlock; + + /* only allocate new storage, when the cgroup is refcounted */ + if (!percpu_ref_is_dying(&cgroup->self.refcnt) && + (flags & BPF_LOCAL_STORAGE_GET_F_CREATE)) + sdata = bpf_local_storage_update(cgroup, (struct bpf_local_storage_map *)map, + value, BPF_NOEXIST, gfp_flags); + +unlock: + bpf_cgrp_storage_unlock(); + return IS_ERR_OR_NULL(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; +} + +BPF_CALL_2(bpf_cgrp_storage_delete, struct bpf_map *, map, struct cgroup *, cgroup) +{ + int ret; + + WARN_ON_ONCE(!bpf_rcu_lock_held()); + if (!cgroup) + return -EINVAL; + + if (!bpf_cgrp_storage_trylock()) + return -EBUSY; + + ret = cgroup_storage_delete(cgroup, map); + bpf_cgrp_storage_unlock(); + return ret; +} + +BTF_ID_LIST_SINGLE(cgroup_storage_map_btf_ids, struct, bpf_local_storage_map) +const struct bpf_map_ops cgrp_storage_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = cgroup_storage_map_alloc, + .map_free = cgroup_storage_map_free, + .map_get_next_key = notsupp_get_next_key, + .map_lookup_elem = bpf_cgrp_storage_lookup_elem, + .map_update_elem = bpf_cgrp_storage_update_elem, + .map_delete_elem = bpf_cgrp_storage_delete_elem, + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_id = &cgroup_storage_map_btf_ids[0], + .map_owner_storage_ptr = cgroup_storage_ptr, +}; + +const struct bpf_func_proto bpf_cgrp_storage_get_proto = { + .func = bpf_cgrp_storage_get, + .gpl_only = false, + .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &bpf_cgroup_btf_id[0], + .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, + .arg4_type = ARG_ANYTHING, +}; + +const struct bpf_func_proto bpf_cgrp_storage_delete_proto = { + .func = bpf_cgrp_storage_delete, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_CONST_MAP_PTR, + .arg2_type = ARG_PTR_TO_BTF_ID, + .arg2_btf_id = &bpf_cgroup_btf_id[0], +}; diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a6b04faed282..124fd199ce5c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1663,6 +1663,12 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_dynptr_write_proto; case BPF_FUNC_dynptr_data: return &bpf_dynptr_data_proto; +#ifdef CONFIG_CGROUPS + case BPF_FUNC_cgrp_storage_get: + return &bpf_cgrp_storage_get_proto; + case BPF_FUNC_cgrp_storage_delete: + return &bpf_cgrp_storage_delete_proto; +#endif default: break; } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index a0b4266196a8..11df90962101 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1016,7 +1016,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE && map->map_type != BPF_MAP_TYPE_SK_STORAGE && map->map_type != BPF_MAP_TYPE_INODE_STORAGE && - map->map_type != BPF_MAP_TYPE_TASK_STORAGE) + map->map_type != BPF_MAP_TYPE_TASK_STORAGE && + map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) return -ENOTSUPP; if (map->spin_lock_off + sizeof(struct bpf_spin_lock) > map->value_size) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ddc1452cf023..8f849a763b79 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -6350,6 +6350,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, func_id != BPF_FUNC_task_storage_delete) goto error; break; + case BPF_MAP_TYPE_CGRP_STORAGE: + if (func_id != BPF_FUNC_cgrp_storage_get && + func_id != BPF_FUNC_cgrp_storage_delete) + goto error; + break; case BPF_MAP_TYPE_BLOOM_FILTER: if (func_id != BPF_FUNC_map_peek_elem && func_id != BPF_FUNC_map_push_elem) @@ -6462,6 +6467,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (map->map_type != BPF_MAP_TYPE_TASK_STORAGE) goto error; break; + case BPF_FUNC_cgrp_storage_get: + case BPF_FUNC_cgrp_storage_delete: + if (map->map_type != BPF_MAP_TYPE_CGRP_STORAGE) + goto error; + break; default: break; } @@ -14139,7 +14149,8 @@ static int do_misc_fixups(struct bpf_verifier_env *env) if (insn->imm == BPF_FUNC_task_storage_get || insn->imm == BPF_FUNC_sk_storage_get || - insn->imm == BPF_FUNC_inode_storage_get) { + insn->imm == BPF_FUNC_inode_storage_get || + insn->imm == BPF_FUNC_cgrp_storage_get) { if (env->prog->aux->sleepable) insn_buf[0] = BPF_MOV64_IMM(BPF_REG_5, (__force __s32)GFP_KERNEL); else diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 764bdd5fd8d1..12001928511b 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -5245,6 +5245,7 @@ static void css_free_rwork_fn(struct work_struct *work) atomic_dec(&cgrp->root->nr_cgrps); cgroup1_pidlist_destroy_all(cgrp); cancel_work_sync(&cgrp->release_agent_work); + bpf_cgrp_storage_free(cgrp); if (cgroup_parent(cgrp)) { /* diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index eed1bd952c3a..ce0228c72a93 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1455,6 +1455,10 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_current_cgroup_id_proto; case BPF_FUNC_get_current_ancestor_cgroup_id: return &bpf_get_current_ancestor_cgroup_id_proto; + case BPF_FUNC_cgrp_storage_get: + return &bpf_cgrp_storage_get_proto; + case BPF_FUNC_cgrp_storage_delete: + return &bpf_cgrp_storage_delete_proto; #endif case BPF_FUNC_send_signal: return &bpf_send_signal_proto; diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index c0e6690be82a..fdb0aff8cb5a 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -685,6 +685,7 @@ class PrinterHelpers(Printer): 'struct udp6_sock', 'struct unix_sock', 'struct task_struct', + 'struct cgroup', 'struct __sk_buff', 'struct sk_msg_md', @@ -742,6 +743,7 @@ class PrinterHelpers(Printer): 'struct udp6_sock', 'struct unix_sock', 'struct task_struct', + 'struct cgroup', 'struct path', 'struct btf_ptr', 'struct inode', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 17f61338f8f8..94659f6b3395 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -922,7 +922,14 @@ enum bpf_map_type { BPF_MAP_TYPE_CPUMAP, BPF_MAP_TYPE_XSKMAP, BPF_MAP_TYPE_SOCKHASH, - BPF_MAP_TYPE_CGROUP_STORAGE, + BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, + /* BPF_MAP_TYPE_CGROUP_STORAGE is available to bpf programs attaching + * to a cgroup. The newer BPF_MAP_TYPE_CGRP_STORAGE is available to + * both cgroup-attached and other progs and supports all functionality + * provided by BPF_MAP_TYPE_CGROUP_STORAGE. So mark + * BPF_MAP_TYPE_CGROUP_STORAGE deprecated. + */ + BPF_MAP_TYPE_CGROUP_STORAGE = BPF_MAP_TYPE_CGROUP_STORAGE_DEPRECATED, BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE, BPF_MAP_TYPE_QUEUE, @@ -935,6 +942,7 @@ enum bpf_map_type { BPF_MAP_TYPE_TASK_STORAGE, BPF_MAP_TYPE_BLOOM_FILTER, BPF_MAP_TYPE_USER_RINGBUF, + BPF_MAP_TYPE_CGRP_STORAGE, }; /* Note that tracing related programs such as @@ -5435,6 +5443,44 @@ union bpf_attr { * **-E2BIG** if user-space has tried to publish a sample which is * larger than the size of the ring buffer, or which cannot fit * within a struct bpf_dynptr. + * + * void *bpf_cgrp_storage_get(struct bpf_map *map, struct cgroup *cgroup, void *value, u64 flags) + * Description + * Get a bpf_local_storage from the *cgroup*. + * + * Logically, it could be thought of as getting the value from + * a *map* with *cgroup* as the **key**. From this + * perspective, the usage is not much different from + * **bpf_map_lookup_elem**\ (*map*, **&**\ *cgroup*) except this + * helper enforces the key must be a cgroup struct and the map must also + * be a **BPF_MAP_TYPE_CGRP_STORAGE**. + * + * In reality, the local-storage value is embedded directly inside of the + * *cgroup* object itself, rather than being located in the + * **BPF_MAP_TYPE_CGRP_STORAGE** map. When the local-storage value is + * queried for some *map* on a *cgroup* object, the kernel will perform an + * O(n) iteration over all of the live local-storage values for that + * *cgroup* object until the local-storage value for the *map* is found. + * + * An optional *flags* (**BPF_LOCAL_STORAGE_GET_F_CREATE**) can be + * used such that a new bpf_local_storage will be + * created if one does not exist. *value* can be used + * together with **BPF_LOCAL_STORAGE_GET_F_CREATE** to specify + * the initial value of a bpf_local_storage. If *value* is + * **NULL**, the new bpf_local_storage will be zero initialized. + * Return + * A bpf_local_storage pointer is returned on success. + * + * **NULL** if not found or there was an error in adding + * a new bpf_local_storage. + * + * long bpf_cgrp_storage_delete(struct bpf_map *map, struct cgroup *cgroup) + * Description + * Delete a bpf_local_storage from a *cgroup*. + * Return + * 0 on success. + * + * **-ENOENT** if the bpf_local_storage cannot be found. */ #define ___BPF_FUNC_MAPPER(FN, ctx...) \ FN(unspec, 0, ##ctx) \ @@ -5647,6 +5693,8 @@ union bpf_attr { FN(tcp_raw_check_syncookie_ipv6, 207, ##ctx) \ FN(ktime_get_tai_ns, 208, ##ctx) \ FN(user_ringbuf_drain, 209, ##ctx) \ + FN(cgrp_storage_get, 210, ##ctx) \ + FN(cgrp_storage_delete, 211, ##ctx) \ /* */ /* backwards-compatibility macros for users of __BPF_FUNC_MAPPER that don't -- cgit From cb6c18b5a41622c7a439508f7421f8766a91cb87 Mon Sep 17 00:00:00 2001 From: Ravi Bangoria Date: Sat, 1 Oct 2022 11:37:05 +0530 Subject: perf/mem: Rename PERF_MEM_LVLNUM_EXTN_MEM to PERF_MEM_LVLNUM_CXL PERF_MEM_LVLNUM_EXTN_MEM was introduced to cover CXL devices but it's bit ambiguous name and also not generic enough to cover cxl.cache and cxl.io devices. Rename it to PERF_MEM_LVLNUM_CXL to be more specific. Signed-off-by: Ravi Bangoria Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/f6268268-b4e9-9ed6-0453-65792644d953@amd.com --- arch/x86/events/amd/ibs.c | 2 +- include/uapi/linux/perf_event.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c index 3271735f0070..4cb710efbdd9 100644 --- a/arch/x86/events/amd/ibs.c +++ b/arch/x86/events/amd/ibs.c @@ -801,7 +801,7 @@ static void perf_ibs_get_mem_lvl(union ibs_op_data2 *op_data2, /* Extension Memory */ if (ibs_caps & IBS_CAPS_ZEN4 && ibs_data_src == IBS_DATA_SRC_EXT_EXT_MEM) { - data_src->mem_lvl_num = PERF_MEM_LVLNUM_EXTN_MEM; + data_src->mem_lvl_num = PERF_MEM_LVLNUM_CXL; if (op_data2->rmt_node) { data_src->mem_remote = PERF_MEM_REMOTE_REMOTE; /* IBS doesn't provide Remote socket detail */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 85be78e0e7f6..ccb7f5dad59b 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1337,7 +1337,7 @@ union perf_mem_data_src { #define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ #define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ /* 5-0x8 available */ -#define PERF_MEM_LVLNUM_EXTN_MEM 0x09 /* Extension memory */ +#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ #define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ #define PERF_MEM_LVLNUM_LFB 0x0c /* LFB */ -- cgit From e32e1e26c4098d8a866ce09fd26d8004da4ddf9e Mon Sep 17 00:00:00 2001 From: Vidya Sagar Date: Mon, 19 Sep 2022 20:03:39 +0530 Subject: PCI: Add PCI_PTM_CAP_RES macro Add macro defining Responder capable bit in Precision Time Measurement capability register. Link: https://lore.kernel.org/r/20220919143340.4527-2-vidyas@nvidia.com Signed-off-by: Vidya Sagar Signed-off-by: Lorenzo Pieralisi Reviewed-by: Jingoo Han --- include/uapi/linux/pci_regs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 57b8e2ffb1dd..1c3591c8e09e 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1058,6 +1058,7 @@ /* Precision Time Measurement */ #define PCI_PTM_CAP 0x04 /* PTM Capability */ #define PCI_PTM_CAP_REQ 0x00000001 /* Requester capable */ +#define PCI_PTM_CAP_RES 0x00000002 /* Responder capable */ #define PCI_PTM_CAP_ROOT 0x00000004 /* Root capable */ #define PCI_PTM_GRANULARITY_MASK 0x0000FF00 /* Clock granularity */ #define PCI_PTM_CTRL 0x08 /* PTM Control */ -- cgit From 7984ceb134bf31aa9a597f10ed52d831d5aede14 Mon Sep 17 00:00:00 2001 From: Frederick Lawler Date: Mon, 17 Oct 2022 14:25:00 -0500 Subject: crypto: af_alg - Support symmetric encryption via keyring keys We want to leverage keyring to store sensitive keys, and then use those keys for symmetric encryption via the crypto API. Among the key types we wish to support are: user, logon, encrypted, and trusted. User key types are already able to have their data copied to user space, but logon does not support this. Further, trusted and encrypted keys will return their encrypted data back to user space on read, which does not make them ideal for symmetric encryption. To support symmetric encryption for these key types, add a new ALG_SET_KEY_BY_KEY_SERIAL setsockopt() option to the crypto API. This allows users to pass a key_serial_t to the crypto API to perform symmetric encryption. The behavior is the same as ALG_SET_KEY, but the crypto key data is copied in kernel space from a keyring key, which allows for the support of logon, encrypted, and trusted key types. Keyring keys must have the KEY_(POS|USR|GRP|OTH)_SEARCH permission set to leverage this feature. This follows the asymmetric_key type where key lookup calls eventually lead to keyring_search_rcu() without the KEYRING_SEARCH_NO_CHECK_PERM flag set. Signed-off-by: Frederick Lawler Signed-off-by: Herbert Xu --- Documentation/crypto/userspace-if.rst | 15 +++- crypto/af_alg.c | 135 +++++++++++++++++++++++++++++++++- include/uapi/linux/if_alg.h | 1 + 3 files changed, 147 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/crypto/userspace-if.rst b/Documentation/crypto/userspace-if.rst index b45dabbf69d6..f80f243e227e 100644 --- a/Documentation/crypto/userspace-if.rst +++ b/Documentation/crypto/userspace-if.rst @@ -131,9 +131,9 @@ from the kernel crypto API. If the buffer is too small for the message digest, the flag MSG_TRUNC is set by the kernel. In order to set a message digest key, the calling application must use -the setsockopt() option of ALG_SET_KEY. If the key is not set the HMAC -operation is performed without the initial HMAC state change caused by -the key. +the setsockopt() option of ALG_SET_KEY or ALG_SET_KEY_BY_KEY_SERIAL. If the +key is not set the HMAC operation is performed without the initial HMAC state +change caused by the key. Symmetric Cipher API -------------------- @@ -382,6 +382,15 @@ mentioned optname: - the RNG cipher type to provide the seed +- ALG_SET_KEY_BY_KEY_SERIAL -- Setting the key via keyring key_serial_t. + This operation behaves the same as ALG_SET_KEY. The decrypted + data is copied from a keyring key, and uses that data as the + key for symmetric encryption. + + The passed in key_serial_t must have the KEY_(POS|USR|GRP|OTH)_SEARCH + permission set, otherwise -EPERM is returned. Supports key types: user, + logon, encrypted, and trusted. + - ALG_SET_AEAD_AUTHSIZE -- Setting the authentication tag size for AEAD ciphers. For a encryption operation, the authentication tag of the given size will be generated. For a decryption operation, the diff --git a/crypto/af_alg.c b/crypto/af_alg.c index e893c0f6c879..0a4fa2a429e2 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -12,6 +12,8 @@ #include #include #include +#include +#include #include #include #include @@ -19,6 +21,10 @@ #include #include #include +#include +#include +#include +#include struct alg_type_list { const struct af_alg_type *type; @@ -222,6 +228,129 @@ out: return err; } +#ifdef CONFIG_KEYS + +static const u8 *key_data_ptr_user(const struct key *key, + unsigned int *datalen) +{ + const struct user_key_payload *ukp; + + ukp = user_key_payload_locked(key); + if (IS_ERR_OR_NULL(ukp)) + return ERR_PTR(-EKEYREVOKED); + + *datalen = key->datalen; + + return ukp->data; +} + +static const u8 *key_data_ptr_encrypted(const struct key *key, + unsigned int *datalen) +{ + const struct encrypted_key_payload *ekp; + + ekp = dereference_key_locked(key); + if (IS_ERR_OR_NULL(ekp)) + return ERR_PTR(-EKEYREVOKED); + + *datalen = ekp->decrypted_datalen; + + return ekp->decrypted_data; +} + +static const u8 *key_data_ptr_trusted(const struct key *key, + unsigned int *datalen) +{ + const struct trusted_key_payload *tkp; + + tkp = dereference_key_locked(key); + if (IS_ERR_OR_NULL(tkp)) + return ERR_PTR(-EKEYREVOKED); + + *datalen = tkp->key_len; + + return tkp->key; +} + +static struct key *lookup_key(key_serial_t serial) +{ + key_ref_t key_ref; + + key_ref = lookup_user_key(serial, 0, KEY_NEED_SEARCH); + if (IS_ERR(key_ref)) + return ERR_CAST(key_ref); + + return key_ref_to_ptr(key_ref); +} + +static int alg_setkey_by_key_serial(struct alg_sock *ask, sockptr_t optval, + unsigned int optlen) +{ + const struct af_alg_type *type = ask->type; + u8 *key_data = NULL; + unsigned int key_datalen; + key_serial_t serial; + struct key *key; + const u8 *ret; + int err; + + if (optlen != sizeof(serial)) + return -EINVAL; + + if (copy_from_sockptr(&serial, optval, optlen)) + return -EFAULT; + + key = lookup_key(serial); + if (IS_ERR(key)) + return PTR_ERR(key); + + down_read(&key->sem); + + ret = ERR_PTR(-ENOPROTOOPT); + if (!strcmp(key->type->name, "user") || + !strcmp(key->type->name, "logon")) { + ret = key_data_ptr_user(key, &key_datalen); + } else if (IS_REACHABLE(CONFIG_ENCRYPTED_KEYS) && + !strcmp(key->type->name, "encrypted")) { + ret = key_data_ptr_encrypted(key, &key_datalen); + } else if (IS_REACHABLE(CONFIG_TRUSTED_KEYS) && + !strcmp(key->type->name, "trusted")) { + ret = key_data_ptr_trusted(key, &key_datalen); + } + + if (IS_ERR(ret)) { + up_read(&key->sem); + return PTR_ERR(ret); + } + + key_data = sock_kmalloc(&ask->sk, key_datalen, GFP_KERNEL); + if (!key_data) { + up_read(&key->sem); + return -ENOMEM; + } + + memcpy(key_data, ret, key_datalen); + + up_read(&key->sem); + + err = type->setkey(ask->private, key_data, key_datalen); + + sock_kzfree_s(&ask->sk, key_data, key_datalen); + + return err; +} + +#else + +static inline int alg_setkey_by_key_serial(struct alg_sock *ask, + sockptr_t optval, + unsigned int optlen) +{ + return -ENOPROTOOPT; +} + +#endif + static int alg_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { @@ -242,12 +371,16 @@ static int alg_setsockopt(struct socket *sock, int level, int optname, switch (optname) { case ALG_SET_KEY: + case ALG_SET_KEY_BY_KEY_SERIAL: if (sock->state == SS_CONNECTED) goto unlock; if (!type->setkey) goto unlock; - err = alg_setkey(sk, optval, optlen); + if (optname == ALG_SET_KEY_BY_KEY_SERIAL) + err = alg_setkey_by_key_serial(ask, optval, optlen); + else + err = alg_setkey(sk, optval, optlen); break; case ALG_SET_AEAD_AUTHSIZE: if (sock->state == SS_CONNECTED) diff --git a/include/uapi/linux/if_alg.h b/include/uapi/linux/if_alg.h index 578b18aab821..0824fbc026a1 100644 --- a/include/uapi/linux/if_alg.h +++ b/include/uapi/linux/if_alg.h @@ -52,6 +52,7 @@ struct af_alg_iv { #define ALG_SET_AEAD_ASSOCLEN 4 #define ALG_SET_AEAD_AUTHSIZE 5 #define ALG_SET_DRBG_ENTROPY 6 +#define ALG_SET_KEY_BY_KEY_SERIAL 7 /* Operations */ #define ALG_OP_DECRYPT 0 -- cgit From 29c1c44646aec5d5134f2365259a84becc1ee7d3 Mon Sep 17 00:00:00 2001 From: Mubashir Adnan Qureshi Date: Wed, 26 Oct 2022 13:51:14 +0000 Subject: tcp: add u32 counter in tcp_sock and an SNMP counter for PLB A u32 counter is added to tcp_sock for counting the number of PLB triggered rehashes for a TCP connection. An SNMP counter is also added to count overall PLB triggered rehash events for a host. These counters are hooked up to PLB implementation for DCTCP. TCP_NLA_REHASH is added to SCM_TIMESTAMPING_OPT_STATS that reports the rehash attempts triggered due to PLB or timeouts. This gives a historical view of sustained congestion or timeouts experienced by the TCP connection. Signed-off-by: Mubashir Adnan Qureshi Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/tcp.h | 1 + include/uapi/linux/snmp.h | 1 + include/uapi/linux/tcp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/tcp.c | 3 +++ net/ipv4/tcp_plb.c | 2 ++ 6 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 41b1da621a45..ca7f05a130d2 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -423,6 +423,7 @@ struct tcp_sock { u32 probe_seq_start; u32 probe_seq_end; } mtu_probe; + u32 plb_rehash; /* PLB-triggered rehash attempts */ u32 mtu_info; /* We received an ICMP_FRAG_NEEDED / ICMPV6_PKT_TOOBIG * while socket was owned by user. */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 4d7470036a8b..6600cb0164c2 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -292,6 +292,7 @@ enum LINUX_MIB_TCPDSACKIGNOREDDUBIOUS, /* TCPDSACKIgnoredDubious */ LINUX_MIB_TCPMIGRATEREQSUCCESS, /* TCPMigrateReqSuccess */ LINUX_MIB_TCPMIGRATEREQFAILURE, /* TCPMigrateReqFailure */ + LINUX_MIB_TCPPLBREHASH, /* TCPPLBRehash */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 8fc09e8638b3..c9abe86eda5f 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -315,6 +315,7 @@ enum { TCP_NLA_BYTES_NOTSENT, /* Bytes in write queue not yet sent */ TCP_NLA_EDT, /* Earliest departure time (CLOCK_MONOTONIC) */ TCP_NLA_TTL, /* TTL or hop limit of a packet received */ + TCP_NLA_REHASH, /* PLB and timeout triggered rehash attempts */ }; /* for TCP_MD5SIG socket option */ diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 5386f460bd20..f88daace9de3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -297,6 +297,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDSACKIgnoredDubious", LINUX_MIB_TCPDSACKIGNOREDDUBIOUS), SNMP_MIB_ITEM("TCPMigrateReqSuccess", LINUX_MIB_TCPMIGRATEREQSUCCESS), SNMP_MIB_ITEM("TCPMigrateReqFailure", LINUX_MIB_TCPMIGRATEREQFAILURE), + SNMP_MIB_ITEM("TCPPLBRehash", LINUX_MIB_TCPPLBREHASH), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ef14efa1fb70..1da7c53b6cb5 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3176,6 +3176,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->sacked_out = 0; tp->tlp_high_seq = 0; tp->last_oow_ack_time = 0; + tp->plb_rehash = 0; /* There's a bubble in the pipe until at least the first ACK. */ tp->app_limited = ~0U; tp->rack.mstamp = 0; @@ -3973,6 +3974,7 @@ static size_t tcp_opt_stats_get_size(void) nla_total_size(sizeof(u32)) + /* TCP_NLA_BYTES_NOTSENT */ nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_EDT */ nla_total_size(sizeof(u8)) + /* TCP_NLA_TTL */ + nla_total_size(sizeof(u32)) + /* TCP_NLA_REHASH */ 0; } @@ -4049,6 +4051,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk, nla_put_u8(stats, TCP_NLA_TTL, tcp_skb_ttl_or_hop_limit(ack_skb)); + nla_put_u32(stats, TCP_NLA_REHASH, tp->plb_rehash + tp->timeout_rehash); return stats; } diff --git a/net/ipv4/tcp_plb.c b/net/ipv4/tcp_plb.c index f4ced370acad..bb1a08fda113 100644 --- a/net/ipv4/tcp_plb.c +++ b/net/ipv4/tcp_plb.c @@ -79,6 +79,8 @@ void tcp_plb_check_rehash(struct sock *sk, struct tcp_plb_state *plb) sk_rethink_txhash(sk); plb->consec_cong_rounds = 0; + tcp_sk(sk)->plb_rehash++; + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPPLBREHASH); } EXPORT_SYMBOL_GPL(tcp_plb_check_rehash); -- cgit From 71fc704768f601ed3fa36310822a5e03f310f781 Mon Sep 17 00:00:00 2001 From: Mubashir Adnan Qureshi Date: Wed, 26 Oct 2022 13:51:15 +0000 Subject: tcp: add rcv_wnd and plb_rehash to TCP_INFO rcv_wnd can be useful to diagnose TCP performance where receiver window becomes the bottleneck. rehash reports the PLB and timeout triggered rehash attempts by the TCP connection. Signed-off-by: Mubashir Adnan Qureshi Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- include/uapi/linux/tcp.h | 5 +++++ net/ipv4/tcp.c | 2 ++ 2 files changed, 7 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index c9abe86eda5f..879eeb0a084b 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -284,6 +284,11 @@ struct tcp_info { __u32 tcpi_snd_wnd; /* peer's advertised receive window after * scaling (bytes) */ + __u32 tcpi_rcv_wnd; /* local advertised receive window after + * scaling (bytes) + */ + + __u32 tcpi_rehash; /* PLB or timeout triggered rehash attempts */ }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1da7c53b6cb5..de8f0cd7cb32 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3940,6 +3940,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_rcv_wnd = tp->rcv_wnd; + info->tcpi_rehash = tp->plb_rehash + tp->timeout_rehash; info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } -- cgit From 58ba426388d9fe56aa638f555b01d6e63cada88c Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 27 Oct 2022 17:10:14 -0400 Subject: net/packet: add PACKET_FANOUT_FLAG_IGNORE_OUTGOING Extend packet socket option PACKET_IGNORE_OUTGOING to fanout groups. The socket option sets ptype.ignore_outgoing, which makes dev_queue_xmit_nit skip the socket. When the socket joins a fanout group, the option is not reflected in the struct ptype of the group. dev_queue_xmit_nit only tests the fanout ptype, so the flag is ignored once a socket joins a fanout group. Inheriting the option from a socket would change established behavior. Different sockets in the group can set different flags, and can also change them at runtime. Testing in packet_rcv_fanout defeats the purpose of the original patch, which is to avoid skb_clone in dev_queue_xmit_nit (esp. for MSG_ZEROCOPY packets). Instead, introduce a new fanout group flag with the same behavior. Tested with https://github.com/wdebruij/kerneltools/blob/master/tests/test_psock_fanout_ignore_outgoing.c Signed-off-by: Willem de Bruijn Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20221027211014.3581513-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_packet.h | 1 + net/packet/af_packet.c | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_packet.h b/include/uapi/linux/if_packet.h index c07caf7b40db..a8516b3594a4 100644 --- a/include/uapi/linux/if_packet.h +++ b/include/uapi/linux/if_packet.h @@ -70,6 +70,7 @@ struct sockaddr_ll { #define PACKET_FANOUT_EBPF 7 #define PACKET_FANOUT_FLAG_ROLLOVER 0x1000 #define PACKET_FANOUT_FLAG_UNIQUEID 0x2000 +#define PACKET_FANOUT_FLAG_IGNORE_OUTGOING 0x4000 #define PACKET_FANOUT_FLAG_DEFRAG 0x8000 struct tpacket_stats { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 8c5b3da0c29f..44f20cf8a0c0 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1777,6 +1777,7 @@ static int fanout_add(struct sock *sk, struct fanout_args *args) match->prot_hook.af_packet_net = read_pnet(&match->net); match->prot_hook.id_match = match_fanout_group; match->max_num_members = args->max_num_members; + match->prot_hook.ignore_outgoing = type_flags & PACKET_FANOUT_FLAG_IGNORE_OUTGOING; list_add(&match->list, &fanout_list); } err = -EINVAL; -- cgit From 738136a0e3757a8534df3ad97d6ff6d7f429f6c1 Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 27 Oct 2022 14:25:53 -0700 Subject: netlink: split up copies in the ack construction Clean up the use of unsafe_memcpy() by adding a flexible array at the end of netlink message header and splitting up the header and data copies. Reviewed-by: Kees Cook Signed-off-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/net/netlink.h | 21 +++++++++++++++++++++ include/uapi/linux/netlink.h | 2 ++ net/netlink/af_netlink.c | 29 ++++++++++++++++++++--------- 3 files changed, 43 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netlink.h b/include/net/netlink.h index 4418b1981e31..784b4688fc6f 100644 --- a/include/net/netlink.h +++ b/include/net/netlink.h @@ -931,6 +931,27 @@ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 se return __nlmsg_put(skb, portid, seq, type, payload, flags); } +/** + * nlmsg_append - Add more data to a nlmsg in a skb + * @skb: socket buffer to store message in + * @size: length of message payload + * + * Append data to an existing nlmsg, used when constructing a message + * with multiple fixed-format headers (which is rare). + * Returns NULL if the tailroom of the skb is insufficient to store + * the extra payload. + */ +static inline void *nlmsg_append(struct sk_buff *skb, u32 size) +{ + if (unlikely(skb_tailroom(skb) < NLMSG_ALIGN(size))) + return NULL; + + if (NLMSG_ALIGN(size) - size) + memset(skb_tail_pointer(skb) + size, 0, + NLMSG_ALIGN(size) - size); + return __skb_put(skb, NLMSG_ALIGN(size)); +} + /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index e2ae82e3f9f7..5da0da59bf01 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -48,6 +48,7 @@ struct sockaddr_nl { * @nlmsg_flags: Additional flags * @nlmsg_seq: Sequence number * @nlmsg_pid: Sending process port ID + * @nlmsg_data: Message payload */ struct nlmsghdr { __u32 nlmsg_len; @@ -55,6 +56,7 @@ struct nlmsghdr { __u16 nlmsg_flags; __u32 nlmsg_seq; __u32 nlmsg_pid; + __u8 nlmsg_data[]; }; /* Flags values */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index f0c94d394ab1..b10d5e50b99d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2499,19 +2499,24 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, flags |= NLM_F_ACK_TLVS; skb = nlmsg_new(payload + tlvlen, GFP_KERNEL); - if (!skb) { - NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; - sk_error_report(NETLINK_CB(in_skb).sk); - return; - } + if (!skb) + goto err_bad_put; rep = nlmsg_put(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, - NLMSG_ERROR, payload, flags); + NLMSG_ERROR, sizeof(*errmsg), flags); + if (!rep) + goto err_bad_put; errmsg = nlmsg_data(rep); errmsg->error = err; - unsafe_memcpy(&errmsg->msg, nlh, payload > sizeof(*errmsg) - ? nlh->nlmsg_len : sizeof(*nlh), - /* Bounds checked by the skb layer. */); + errmsg->msg = *nlh; + + if (!(flags & NLM_F_CAPPED)) { + if (!nlmsg_append(skb, nlmsg_len(nlh))) + goto err_bad_put; + + memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data, + nlmsg_len(nlh)); + } if (tlvlen) netlink_ack_tlv_fill(in_skb, skb, nlh, err, extack); @@ -2519,6 +2524,12 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, nlmsg_end(skb, rep); nlmsg_unicast(in_skb->sk, skb, NETLINK_CB(in_skb).portid); + + return; + +err_bad_put: + NETLINK_CB(in_skb).sk->sk_err = ENOBUFS; + sk_error_report(NETLINK_CB(in_skb).sk); } EXPORT_SYMBOL(netlink_ack); -- cgit From 986d93f55bdeab1cac858d1e47b41fac10b2d7f6 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 31 Oct 2022 10:10:21 +0800 Subject: audit: fix undefined behavior in bit shift for AUDIT_BIT Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in kernel/auditfilter.c:179:23 left shift of 1 by 31 places cannot be represented in type 'int' Call Trace: dump_stack_lvl+0x7d/0xa5 dump_stack+0x15/0x1b ubsan_epilogue+0xe/0x4e __ubsan_handle_shift_out_of_bounds+0x1e7/0x20c audit_register_class+0x9d/0x137 audit_classes_init+0x4d/0xb8 do_one_initcall+0x76/0x430 kernel_init_freeable+0x3b3/0x422 kernel_init+0x24/0x1e0 ret_from_fork+0x1f/0x30 Signed-off-by: Gaosheng Cui [PM: remove bad 'Fixes' tag as issue predates git, added in v2.6.6-rc1] Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index 7c1dc818b1d5..d676ed2b246e 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -187,7 +187,7 @@ #define AUDIT_MAX_KEY_LEN 256 #define AUDIT_BITMASK_SIZE 64 #define AUDIT_WORD(nr) ((__u32)((nr)/32)) -#define AUDIT_BIT(nr) (1 << ((nr) - AUDIT_WORD(nr)*32)) +#define AUDIT_BIT(nr) (1U << ((nr) - AUDIT_WORD(nr)*32)) #define AUDIT_SYSCALL_CLASSES 16 #define AUDIT_CLASS_DIR_WRITE 0 -- cgit From 6dd07781b4cdd38103c81ddcc88fa4e8a31ebf71 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Wed, 19 Oct 2022 12:33:39 +0300 Subject: serial: Convert serial_rs485 to kernel doc MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Convert struct serial_rs485 comments to kernel doc format and include it into documentation. Suggested-by: Andy Shevchenko Reviewed-by: Andy Shevchenko Reviewed-by: Bagas Sanjaya Signed-off-by: Ilpo Järvinen Link: https://lore.kernel.org/r/20221019093343.9546-2-ilpo.jarvinen@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- Documentation/driver-api/serial/serial-rs485.rst | 13 +++--- include/uapi/linux/serial.h | 55 ++++++++++++++++-------- 2 files changed, 43 insertions(+), 25 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/driver-api/serial/serial-rs485.rst b/Documentation/driver-api/serial/serial-rs485.rst index 6ebad75c74ed..264e4b753713 100644 --- a/Documentation/driver-api/serial/serial-rs485.rst +++ b/Documentation/driver-api/serial/serial-rs485.rst @@ -29,11 +29,11 @@ RS485 Serial Communications 3. Data Structures Already Available in the Kernel ================================================== - The Linux kernel provides the serial_rs485 structure (see [1]) to handle - RS485 communications. This data structure is used to set and configure RS485 + The Linux kernel provides the serial_rs485 structure to handle RS485 + communications. This data structure is used to set and configure RS485 parameters in the platform data and in ioctls. - The device tree can also provide RS485 boot time parameters (see [2] + The device tree can also provide RS485 boot time parameters (see [1] for bindings). The driver is in charge of filling this data structure from the values given by the device tree. @@ -47,6 +47,9 @@ RS485 Serial Communications for the uart_port. TIOCGRS485 ioctl can be used to read back the serial_rs485 structure matching to the current configuration. +.. kernel-doc:: include/uapi/linux/serial.h + :identifiers: serial_rs485 + 4. Usage from user-level ======================== @@ -126,6 +129,4 @@ RS485 Serial Communications 6. References ============= - [1] include/uapi/linux/serial.h - - [2] Documentation/devicetree/bindings/serial/rs485.txt + [1] Documentation/devicetree/bindings/serial/rs485.txt diff --git a/include/uapi/linux/serial.h b/include/uapi/linux/serial.h index cea06924b295..53bc1af67a41 100644 --- a/include/uapi/linux/serial.h +++ b/include/uapi/linux/serial.h @@ -107,33 +107,50 @@ struct serial_icounter_struct { int reserved[9]; }; -/* +/** + * struct serial_rs485 - serial interface for controlling RS485 settings. + * @flags: RS485 feature flags. + * @delay_rts_before_send: Delay before send (milliseconds). + * @delay_rts_after_send: Delay after send (milliseconds). + * @addr_recv: Receive filter for RS485 addressing mode + * (used only when %SER_RS485_ADDR_RECV is set). + * @addr_dest: Destination address for RS485 addressing mode + * (used only when %SER_RS485_ADDR_DEST is set). + * @padding0: Padding (set to zero). + * @padding1: Padding (set to zero). + * @padding: Deprecated, use @padding0 and @padding1 instead. + * Do not use with @addr_recv and @addr_dest (due to + * overlap). + * * Serial interface for controlling RS485 settings on chips with suitable * support. Set with TIOCSRS485 and get with TIOCGRS485 if supported by your * platform. The set function returns the new state, with any unsupported bits * reverted appropriately. + * + * The flag bits are: + * + * * %SER_RS485_ENABLED - RS485 enabled. + * * %SER_RS485_RTS_ON_SEND - Logical level for RTS pin when sending. + * * %SER_RS485_RTS_AFTER_SEND - Logical level for RTS pin after sent. + * * %SER_RS485_RX_DURING_TX - Full-duplex RS485 line. + * * %SER_RS485_TERMINATE_BUS - Enable bus termination (if supported). + * * %SER_RS485_ADDRB - Enable RS485 addressing mode. + * * %SER_RS485_ADDR_RECV - Receive address filter (enables @addr_recv). Requires %SER_RS485_ADDRB. + * * %SER_RS485_ADDR_DEST - Destination address (enables @addr_dest). Requires %SER_RS485_ADDRB. */ - struct serial_rs485 { - __u32 flags; /* RS485 feature flags */ -#define SER_RS485_ENABLED (1 << 0) /* If enabled */ -#define SER_RS485_RTS_ON_SEND (1 << 1) /* Logical level for - RTS pin when - sending */ -#define SER_RS485_RTS_AFTER_SEND (1 << 2) /* Logical level for - RTS pin after sent*/ + __u32 flags; +#define SER_RS485_ENABLED (1 << 0) +#define SER_RS485_RTS_ON_SEND (1 << 1) +#define SER_RS485_RTS_AFTER_SEND (1 << 2) #define SER_RS485_RX_DURING_TX (1 << 4) -#define SER_RS485_TERMINATE_BUS (1 << 5) /* Enable bus - termination - (if supported) */ - -/* RS-485 addressing mode */ -#define SER_RS485_ADDRB (1 << 6) /* Enable addressing mode */ -#define SER_RS485_ADDR_RECV (1 << 7) /* Receive address filter */ -#define SER_RS485_ADDR_DEST (1 << 8) /* Destination address */ +#define SER_RS485_TERMINATE_BUS (1 << 5) +#define SER_RS485_ADDRB (1 << 6) +#define SER_RS485_ADDR_RECV (1 << 7) +#define SER_RS485_ADDR_DEST (1 << 8) - __u32 delay_rts_before_send; /* Delay before send (milliseconds) */ - __u32 delay_rts_after_send; /* Delay after send (milliseconds) */ + __u32 delay_rts_before_send; + __u32 delay_rts_after_send; /* The fields below are defined by flags */ union { -- cgit From aec1dc972d27c837d1406310dab5170189eb01e5 Mon Sep 17 00:00:00 2001 From: Andrii Nakryiko Date: Wed, 2 Nov 2022 11:25:16 -0700 Subject: net/ipv4: Fix linux/in.h header dependencies __DECLARE_FLEX_ARRAY is defined in include/uapi/linux/stddef.h but doesn't seem to be explicitly included from include/uapi/linux/in.h, which breaks BPF selftests builds (once we sync linux/stddef.h into tools/include directory in the next patch). Fix this by explicitly including linux/stddef.h. Given this affects BPF CI and bpf tree, targeting this for bpf tree. Fixes: 5854a09b4957 ("net/ipv4: Use __DECLARE_FLEX_ARRAY() helper") Signed-off-by: Andrii Nakryiko Signed-off-by: Daniel Borkmann Cc: Gustavo A. R. Silva Cc: Jakub Kicinski Link: https://lore.kernel.org/bpf/20221102182517.2675301-1-andrii@kernel.org --- include/uapi/linux/in.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/in.h b/include/uapi/linux/in.h index f243ce665f74..07a4cb149305 100644 --- a/include/uapi/linux/in.h +++ b/include/uapi/linux/in.h @@ -20,6 +20,7 @@ #define _UAPI_LINUX_IN_H #include +#include #include #include -- cgit From ec32c0c42d0a7208571c4c77f140bffaa4e5e304 Mon Sep 17 00:00:00 2001 From: Daniel Machon Date: Tue, 1 Nov 2022 10:48:29 +0100 Subject: net: dcb: add new pcp selector to app object Add new PCP selector for the 8021Qaz APP managed object. As the PCP selector is not part of the 8021Qaz standard, a new non-std extension attribute DCB_ATTR_DCB_APP has been introduced. Also two helper functions to translate between selector and app attribute type has been added. The new selector has been given a value of 255, to minimize the risk of future overlap of std- and non-std attributes. The new DCB_ATTR_DCB_APP is sent alongside the ieee std attribute in the app table. This means that the dcb_app struct can now both contain std- and non-std app attributes. Currently there is no overlap between the selector values of the two attributes. The purpose of adding the PCP selector, is to be able to offload PCP-based queue classification to the 8021Q Priority Code Point table, see 6.9.3 of IEEE Std 802.1Q-2018. PCP and DEI is encoded in the protocol field as 8*dei+pcp, so that a mapping of PCP 2 and DEI 1 to priority 3 is encoded as {255, 10, 3}. Signed-off-by: Daniel Machon Reviewed-by: Petr Machata Signed-off-by: Paolo Abeni --- include/uapi/linux/dcbnl.h | 6 +++++ net/dcb/dcbnl.c | 58 ++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 60 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index a791a94013a6..dc7ef96207ca 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -218,6 +218,9 @@ struct cee_pfc { #define IEEE_8021QAZ_APP_SEL_ANY 4 #define IEEE_8021QAZ_APP_SEL_DSCP 5 +/* Non-std selector values */ +#define DCB_APP_SEL_PCP 255 + /* This structure contains the IEEE 802.1Qaz APP managed object. This * object is also used for the CEE std as well. * @@ -247,6 +250,8 @@ struct dcb_app { __u16 protocol; }; +#define IEEE_8021QAZ_APP_SEL_MAX 255 + /** * struct dcb_peer_app_info - APP feature information sent by the peer * @@ -425,6 +430,7 @@ enum ieee_attrs { enum ieee_attrs_app { DCB_ATTR_IEEE_APP_UNSPEC, DCB_ATTR_IEEE_APP, + DCB_ATTR_DCB_APP, __DCB_ATTR_IEEE_APP_MAX }; #define DCB_ATTR_IEEE_APP_MAX (__DCB_ATTR_IEEE_APP_MAX - 1) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index dc4fb699b56c..0c17bb28ae60 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -179,6 +179,38 @@ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { static LIST_HEAD(dcb_app_list); static DEFINE_SPINLOCK(dcb_lock); +static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) +{ + switch (selector) { + case IEEE_8021QAZ_APP_SEL_ETHERTYPE: + case IEEE_8021QAZ_APP_SEL_STREAM: + case IEEE_8021QAZ_APP_SEL_DGRAM: + case IEEE_8021QAZ_APP_SEL_ANY: + case IEEE_8021QAZ_APP_SEL_DSCP: + return DCB_ATTR_IEEE_APP; + case DCB_APP_SEL_PCP: + return DCB_ATTR_DCB_APP; + default: + return DCB_ATTR_IEEE_APP_UNSPEC; + } +} + +static bool dcbnl_app_attr_type_validate(enum ieee_attrs_app type) +{ + switch (type) { + case DCB_ATTR_IEEE_APP: + case DCB_ATTR_DCB_APP: + return true; + default: + return false; + } +} + +static bool dcbnl_app_selector_validate(enum ieee_attrs_app type, u8 selector) +{ + return dcbnl_app_attr_type_get(selector) == type; +} + static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, u32 flags, struct nlmsghdr **nlhp) { @@ -1116,8 +1148,9 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { - err = nla_put(skb, DCB_ATTR_IEEE_APP, sizeof(itr->app), - &itr->app); + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(itr->app.selector); + err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); return -EMSGSIZE; @@ -1493,9 +1526,10 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, int rem; nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + enum ieee_attrs_app type = nla_type(attr); struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) + if (!dcbnl_app_attr_type_validate(type)) continue; if (nla_len(attr) < sizeof(struct dcb_app)) { @@ -1504,6 +1538,13 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, } app_data = nla_data(attr); + + if (!dcbnl_app_selector_validate(type, + app_data->selector)) { + err = -EINVAL; + goto err; + } + if (ops->ieee_setapp) err = ops->ieee_setapp(netdev, app_data); else @@ -1554,11 +1595,20 @@ static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, int rem; nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + enum ieee_attrs_app type = nla_type(attr); struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) + if (!dcbnl_app_attr_type_validate(type)) continue; + app_data = nla_data(attr); + + if (!dcbnl_app_selector_validate(type, + app_data->selector)) { + err = -EINVAL; + goto err; + } + if (ops->ieee_delapp) err = ops->ieee_delapp(netdev, app_data); else -- cgit From 6182d5875c330a5a611687caa05f47752455720c Mon Sep 17 00:00:00 2001 From: Daniel Machon Date: Tue, 1 Nov 2022 10:48:30 +0100 Subject: net: dcb: add new apptrust attribute Add new apptrust extension attributes to the 8021Qaz APP managed object. Two new attributes, DCB_ATTR_DCB_APP_TRUST_TABLE and DCB_ATTR_DCB_APP_TRUST, has been added. Trusted selectors are passed in the nested attribute DCB_ATTR_DCB_APP_TRUST, in order of precedence. The new attributes are meant to allow drivers, whose hw supports the notion of trust, to be able to set whether a particular app selector is trusted - and in which order. Signed-off-by: Daniel Machon Reviewed-by: Petr Machata Signed-off-by: Paolo Abeni --- include/net/dcbnl.h | 4 +++ include/uapi/linux/dcbnl.h | 2 ++ net/dcb/dcbnl.c | 76 ++++++++++++++++++++++++++++++++++++++++++++-- 3 files changed, 80 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h index 2b2d86fb3131..8841ab6c2de7 100644 --- a/include/net/dcbnl.h +++ b/include/net/dcbnl.h @@ -109,6 +109,10 @@ struct dcbnl_rtnl_ops { /* buffer settings */ int (*dcbnl_getbuffer)(struct net_device *, struct dcbnl_buffer *); int (*dcbnl_setbuffer)(struct net_device *, struct dcbnl_buffer *); + + /* apptrust */ + int (*dcbnl_setapptrust)(struct net_device *, u8 *, int); + int (*dcbnl_getapptrust)(struct net_device *, u8 *, int *); }; #endif /* __NET_DCBNL_H__ */ diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h index dc7ef96207ca..99047223ab26 100644 --- a/include/uapi/linux/dcbnl.h +++ b/include/uapi/linux/dcbnl.h @@ -410,6 +410,7 @@ enum dcbnl_attrs { * @DCB_ATTR_IEEE_PEER_ETS: peer ETS configuration - get only * @DCB_ATTR_IEEE_PEER_PFC: peer PFC configuration - get only * @DCB_ATTR_IEEE_PEER_APP: peer APP tlv - get only + * @DCB_ATTR_DCB_APP_TRUST_TABLE: selector trust table */ enum ieee_attrs { DCB_ATTR_IEEE_UNSPEC, @@ -423,6 +424,7 @@ enum ieee_attrs { DCB_ATTR_IEEE_QCN, DCB_ATTR_IEEE_QCN_STATS, DCB_ATTR_DCB_BUFFER, + DCB_ATTR_DCB_APP_TRUST_TABLE, __DCB_ATTR_IEEE_MAX }; #define DCB_ATTR_IEEE_MAX (__DCB_ATTR_IEEE_MAX - 1) diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 0c17bb28ae60..cec0632f96db 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -166,6 +166,7 @@ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, + [DCB_ATTR_DCB_APP_TRUST_TABLE] = {.type = NLA_NESTED}, }; /* DCB number of traffic classes nested attributes. */ @@ -1062,9 +1063,9 @@ nla_put_failure: /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { - struct nlattr *ieee, *app; - struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee, *app, *apptrust; + struct dcb_app_type *itr; int dcbx; int err; @@ -1166,6 +1167,30 @@ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); + if (ops->dcbnl_getapptrust) { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; + int nselectors, i; + + apptrust = nla_nest_start(skb, DCB_ATTR_DCB_APP_TRUST_TABLE); + if (!apptrust) + return -EMSGSIZE; + + err = ops->dcbnl_getapptrust(netdev, selectors, &nselectors); + if (!err) { + for (i = 0; i < nselectors; i++) { + enum ieee_attrs_app type = + dcbnl_app_attr_type_get(selectors[i]); + err = nla_put_u8(skb, type, selectors[i]); + if (err) { + nla_nest_cancel(skb, apptrust); + return err; + } + } + } + + nla_nest_end(skb, apptrust); + } + /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; @@ -1554,6 +1579,53 @@ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, } } + if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { + u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; + struct nlattr *attr; + int nselectors = 0; + int rem; + + if (!ops->dcbnl_setapptrust) { + err = -EOPNOTSUPP; + goto err; + } + + nla_for_each_nested(attr, ieee[DCB_ATTR_DCB_APP_TRUST_TABLE], + rem) { + enum ieee_attrs_app type = nla_type(attr); + u8 selector; + int i; + + if (!dcbnl_app_attr_type_validate(type) || + nla_len(attr) != 1 || + nselectors >= sizeof(selectors)) { + err = -EINVAL; + goto err; + } + + selector = nla_get_u8(attr); + + if (!dcbnl_app_selector_validate(type, selector)) { + err = -EINVAL; + goto err; + } + + /* Duplicate selector ? */ + for (i = 0; i < nselectors; i++) { + if (selectors[i] == selector) { + err = -EINVAL; + goto err; + } + } + + selectors[nselectors++] = selector; + } + + err = ops->dcbnl_setapptrust(netdev, selectors, nselectors); + if (err) + goto err; + } + err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); -- cgit From a35ec8e38cdd1766f29924ca391a01de20163931 Mon Sep 17 00:00:00 2001 From: "Hans J. Schultz" Date: Tue, 1 Nov 2022 21:39:21 +0200 Subject: bridge: Add MAC Authentication Bypass (MAB) support Hosts that support 802.1X authentication are able to authenticate themselves by exchanging EAPOL frames with an authenticator (Ethernet bridge, in this case) and an authentication server. Access to the network is only granted by the authenticator to successfully authenticated hosts. The above is implemented in the bridge using the "locked" bridge port option. When enabled, link-local frames (e.g., EAPOL) can be locally received by the bridge, but all other frames are dropped unless the host is authenticated. That is, unless the user space control plane installed an FDB entry according to which the source address of the frame is located behind the locked ingress port. The entry can be dynamic, in which case learning needs to be enabled so that the entry will be refreshed by incoming traffic. There are deployments in which not all the devices connected to the authenticator (the bridge) support 802.1X. Such devices can include printers and cameras. One option to support such deployments is to unlock the bridge ports connecting these devices, but a slightly more secure option is to use MAB. When MAB is enabled, the MAC address of the connected device is used as the user name and password for the authentication. For MAB to work, the user space control plane needs to be notified about MAC addresses that are trying to gain access so that they will be compared against an allow list. This can be implemented via the regular learning process with the sole difference that learned FDB entries are installed with a new "locked" flag indicating that the entry cannot be used to authenticate the device. The flag cannot be set by user space, but user space can clear the flag by replacing the entry, thereby authenticating the device. Locked FDB entries implement the following semantics with regards to roaming, aging and forwarding: 1. Roaming: Locked FDB entries can roam to unlocked (authorized) ports, in which case the "locked" flag is cleared. FDB entries cannot roam to locked ports regardless of MAB being enabled or not. Therefore, locked FDB entries are only created if an FDB entry with the given {MAC, VID} does not already exist. This behavior prevents unauthenticated devices from disrupting traffic destined to already authenticated devices. 2. Aging: Locked FDB entries age and refresh by incoming traffic like regular entries. 3. Forwarding: Locked FDB entries forward traffic like regular entries. If user space detects an unauthorized MAC behind a locked port and wishes to prevent traffic with this MAC DA from reaching the host, it can do so using tc or a different mechanism. Enable the above behavior using a new bridge port option called "mab". It can only be enabled on a bridge port that is both locked and has learning enabled. Locked FDB entries are flushed from the port once MAB is disabled. A new option is added because there are pure 802.1X deployments that are not interested in notifications about locked FDB entries. Signed-off-by: Hans J. Schultz Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Reviewed-by: Vladimir Oltean Signed-off-by: Jakub Kicinski --- include/linux/if_bridge.h | 1 + include/uapi/linux/if_link.h | 1 + include/uapi/linux/neighbour.h | 8 +++++++- net/bridge/br_fdb.c | 24 ++++++++++++++++++++++++ net/bridge/br_input.c | 21 +++++++++++++++++++-- net/bridge/br_netlink.c | 21 ++++++++++++++++++++- net/bridge/br_private.h | 3 ++- net/core/rtnetlink.c | 5 +++++ 8 files changed, 79 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index d62ef428e3aa..1668ac4d7adc 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -59,6 +59,7 @@ struct br_ip_list { #define BR_MRP_LOST_IN_CONT BIT(19) #define BR_TX_FWD_OFFLOAD BIT(20) #define BR_PORT_LOCKED BIT(21) +#define BR_PORT_MAB BIT(22) #define BR_DEFAULT_AGEING_TIME (300 * HZ) diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 5e7a1041df3a..d92b3f79eba3 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -561,6 +561,7 @@ enum { IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT, IFLA_BRPORT_MCAST_EHT_HOSTS_CNT, IFLA_BRPORT_LOCKED, + IFLA_BRPORT_MAB, __IFLA_BRPORT_MAX }; #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1) diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index a998bf761635..5e67a7eaf4a7 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -52,7 +52,8 @@ enum { #define NTF_STICKY (1 << 6) #define NTF_ROUTER (1 << 7) /* Extended flags under NDA_FLAGS_EXT: */ -#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_MANAGED (1 << 0) +#define NTF_EXT_LOCKED (1 << 1) /* * Neighbor Cache Entry States. @@ -86,6 +87,11 @@ enum { * NTF_EXT_MANAGED flagged neigbor entries are managed by the kernel on behalf * of a user space control plane, and automatically refreshed so that (if * possible) they remain in NUD_REACHABLE state. + * + * NTF_EXT_LOCKED flagged bridge FDB entries are entries generated by the + * bridge in response to a host trying to communicate via a locked bridge port + * with MAB enabled. Their purpose is to notify user space that a host requires + * authentication. */ struct nda_cacheinfo { diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index e7f4fccb6adb..3b83af4458b8 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -105,6 +105,7 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, struct nda_cacheinfo ci; struct nlmsghdr *nlh; struct ndmsg *ndm; + u32 ext_flags = 0; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags); if (nlh == NULL) @@ -125,11 +126,16 @@ static int fdb_fill_info(struct sk_buff *skb, const struct net_bridge *br, ndm->ndm_flags |= NTF_EXT_LEARNED; if (test_bit(BR_FDB_STICKY, &fdb->flags)) ndm->ndm_flags |= NTF_STICKY; + if (test_bit(BR_FDB_LOCKED, &fdb->flags)) + ext_flags |= NTF_EXT_LOCKED; if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->key.addr)) goto nla_put_failure; if (nla_put_u32(skb, NDA_MASTER, br->dev->ifindex)) goto nla_put_failure; + if (nla_put_u32(skb, NDA_FLAGS_EXT, ext_flags)) + goto nla_put_failure; + ci.ndm_used = jiffies_to_clock_t(now - fdb->used); ci.ndm_confirmed = 0; ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated); @@ -171,6 +177,7 @@ static inline size_t fdb_nlmsg_size(void) return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(ETH_ALEN) /* NDA_LLADDR */ + nla_total_size(sizeof(u32)) /* NDA_MASTER */ + + nla_total_size(sizeof(u32)) /* NDA_FLAGS_EXT */ + nla_total_size(sizeof(u16)) /* NDA_VLAN */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(0) /* NDA_FDB_EXT_ATTRS */ @@ -879,6 +886,11 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, &fdb->flags))) clear_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags); + /* Clear locked flag when roaming to an + * unlocked port. + */ + if (unlikely(test_bit(BR_FDB_LOCKED, &fdb->flags))) + clear_bit(BR_FDB_LOCKED, &fdb->flags); } if (unlikely(test_bit(BR_FDB_ADDED_BY_USER, &flags))) @@ -1082,6 +1094,9 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, modified = true; } + if (test_and_clear_bit(BR_FDB_LOCKED, &fdb->flags)) + modified = true; + if (fdb_handle_notify(fdb, notify)) modified = true; @@ -1150,6 +1165,7 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_bridge_port *p = NULL; struct net_bridge_vlan *v; struct net_bridge *br = NULL; + u32 ext_flags = 0; int err = 0; trace_br_fdb_add(ndm, dev, addr, vid, nlh_flags); @@ -1178,6 +1194,14 @@ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], vg = nbp_vlan_group(p); } + if (tb[NDA_FLAGS_EXT]) + ext_flags = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext_flags & NTF_EXT_LOCKED) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add FDB entry with \"locked\" flag set"); + return -EINVAL; + } + if (tb[NDA_FDB_EXT_ATTRS]) { attr = tb[NDA_FDB_EXT_ATTRS]; err = nla_parse_nested(nfea_tb, NFEA_MAX, attr, diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 68b3e850bcb9..d04d2205ad4e 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -109,9 +109,26 @@ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb struct net_bridge_fdb_entry *fdb_src = br_fdb_find_rcu(br, eth_hdr(skb)->h_source, vid); - if (!fdb_src || READ_ONCE(fdb_src->dst) != p || - test_bit(BR_FDB_LOCAL, &fdb_src->flags)) + if (!fdb_src) { + /* FDB miss. Create locked FDB entry if MAB is enabled + * and drop the packet. + */ + if (p->flags & BR_PORT_MAB) + br_fdb_update(br, p, eth_hdr(skb)->h_source, + vid, BIT(BR_FDB_LOCKED)); goto drop; + } else if (READ_ONCE(fdb_src->dst) != p || + test_bit(BR_FDB_LOCAL, &fdb_src->flags)) { + /* FDB mismatch. Drop the packet without roaming. */ + goto drop; + } else if test_bit(BR_FDB_LOCKED, &fdb_src->flags) { + /* FDB match, but entry is locked. Refresh it and drop + * the packet. + */ + br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, + BIT(BR_FDB_LOCKED)); + goto drop; + } } nbp_switchdev_frame_mark(p, skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index d087fd4c784a..4316cc82ae17 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -188,6 +188,7 @@ static inline size_t br_port_info_size(void) + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(1) /* IFLA_BRPORT_LOCKED */ + + nla_total_size(1) /* IFLA_BRPORT_MAB */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ @@ -274,7 +275,8 @@ static int br_port_fill_attrs(struct sk_buff *skb, nla_put_u8(skb, IFLA_BRPORT_MRP_IN_OPEN, !!(p->flags & BR_MRP_LOST_IN_CONT)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED)) || - nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED))) + nla_put_u8(skb, IFLA_BRPORT_LOCKED, !!(p->flags & BR_PORT_LOCKED)) || + nla_put_u8(skb, IFLA_BRPORT_MAB, !!(p->flags & BR_PORT_MAB))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); @@ -876,6 +878,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_LOCKED] = { .type = NLA_U8 }, + [IFLA_BRPORT_MAB] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, [IFLA_BRPORT_MCAST_EHT_HOSTS_LIMIT] = { .type = NLA_U32 }, }; @@ -943,6 +946,22 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[], br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); br_set_port_flag(p, tb, IFLA_BRPORT_LOCKED, BR_PORT_LOCKED); + br_set_port_flag(p, tb, IFLA_BRPORT_MAB, BR_PORT_MAB); + + if ((p->flags & BR_PORT_MAB) && + (!(p->flags & BR_PORT_LOCKED) || !(p->flags & BR_LEARNING))) { + NL_SET_ERR_MSG(extack, "Bridge port must be locked and have learning enabled when MAB is enabled"); + p->flags = old_flags; + return -EINVAL; + } else if (!(p->flags & BR_PORT_MAB) && (old_flags & BR_PORT_MAB)) { + struct net_bridge_fdb_flush_desc desc = { + .flags = BIT(BR_FDB_LOCKED), + .flags_mask = BIT(BR_FDB_LOCKED), + .port_ifindex = p->dev->ifindex, + }; + + br_fdb_flush(p->br, &desc); + } changed_mask = old_flags ^ p->flags; diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 06e5f6faa431..4ce8b8e5ae0b 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -251,7 +251,8 @@ enum { BR_FDB_ADDED_BY_EXT_LEARN, BR_FDB_OFFLOADED, BR_FDB_NOTIFY, - BR_FDB_NOTIFY_INACTIVE + BR_FDB_NOTIFY_INACTIVE, + BR_FDB_LOCKED, }; struct net_bridge_fdb_key { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d2f27548fc0b..b64fffeb3844 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4051,6 +4051,11 @@ int ndo_dflt_fdb_add(struct ndmsg *ndm, return err; } + if (tb[NDA_FLAGS_EXT]) { + netdev_info(dev, "invalid flags given to default FDB implementation\n"); + return err; + } + if (vid) { netdev_info(dev, "vlans aren't supported yet for dev_uc|mc_add()\n"); return err; -- cgit From dca56c3038c34a3e5acfe0aadb1f2bc9d724ae79 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Wed, 2 Nov 2022 17:02:11 +0100 Subject: net: expose devlink port over rtnetlink Expose devlink port handle related to netdev over rtnetlink. Introduce a new nested IFLA attribute to carry the info. Call into devlink code to fill-up the nest with existing devlink attributes that are used over devlink netlink. Signed-off-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 14 ++++++++++++++ include/uapi/linux/if_link.h | 2 ++ net/core/devlink.c | 18 ++++++++++++++++++ net/core/rtnetlink.c | 39 +++++++++++++++++++++++++++++++++++++++ 4 files changed, 73 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7befad57afd4..fa6e936af1a5 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1873,6 +1873,9 @@ int devlink_compat_phys_port_name_get(struct net_device *dev, int devlink_compat_switch_id_get(struct net_device *dev, struct netdev_phys_item_id *ppid); +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port); +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port); + #else static inline struct devlink *devlink_try_get(struct devlink *devlink) @@ -1909,6 +1912,17 @@ devlink_compat_switch_id_get(struct net_device *dev, return -EOPNOTSUPP; } +static inline int +devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + return 0; +} + +static inline size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + return 0; +} + #endif #endif /* _NET_DEVLINK_H_ */ diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index d92b3f79eba3..1021a7e47a86 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -372,6 +372,8 @@ enum { IFLA_TSO_MAX_SEGS, IFLA_ALLMULTI, /* Allmulti count: > 0 means acts ALLMULTI */ + IFLA_DEVLINK_PORT, + __IFLA_MAX }; diff --git a/net/core/devlink.c b/net/core/devlink.c index 3a454d0045e5..2dcf2bcc3527 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -880,6 +880,24 @@ nla_put_failure: return -EMSGSIZE; } +int devlink_nl_port_handle_fill(struct sk_buff *msg, struct devlink_port *devlink_port) +{ + if (devlink_nl_put_handle(msg, devlink_port->devlink)) + return -EMSGSIZE; + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) + return -EMSGSIZE; + return 0; +} + +size_t devlink_nl_port_handle_size(struct devlink_port *devlink_port) +{ + struct devlink *devlink = devlink_port->devlink; + + return nla_total_size(strlen(devlink->dev->bus->name) + 1) /* DEVLINK_ATTR_BUS_NAME */ + + nla_total_size(strlen(dev_name(devlink->dev)) + 1) /* DEVLINK_ATTR_DEV_NAME */ + + nla_total_size(4); /* DEVLINK_ATTR_PORT_INDEX */ +} + struct devlink_reload_combination { enum devlink_reload_action action; enum devlink_reload_limit limit; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index b64fffeb3844..64289bc98887 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -53,6 +53,7 @@ #include #include #include +#include #include "dev.h" @@ -1038,6 +1039,16 @@ static size_t rtnl_proto_down_size(const struct net_device *dev) return size; } +static size_t rtnl_devlink_port_size(const struct net_device *dev) +{ + size_t size = nla_total_size(0); /* nest IFLA_DEVLINK_PORT */ + + if (dev->devlink_port) + size += devlink_nl_port_handle_size(dev->devlink_port); + + return size; +} + static noinline size_t if_nlmsg_size(const struct net_device *dev, u32 ext_filter_mask) { @@ -1091,6 +1102,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev, + nla_total_size(4) /* IFLA_MAX_MTU */ + rtnl_prop_list_size(dev) + nla_total_size(MAX_ADDR_LEN) /* IFLA_PERM_ADDRESS */ + + rtnl_devlink_port_size(dev) + 0; } @@ -1728,6 +1740,30 @@ nla_put_failure: return -EMSGSIZE; } +static int rtnl_fill_devlink_port(struct sk_buff *skb, + const struct net_device *dev) +{ + struct nlattr *devlink_port_nest; + int ret; + + devlink_port_nest = nla_nest_start(skb, IFLA_DEVLINK_PORT); + if (!devlink_port_nest) + return -EMSGSIZE; + + if (dev->devlink_port) { + ret = devlink_nl_port_handle_fill(skb, dev->devlink_port); + if (ret < 0) + goto nest_cancel; + } + + nla_nest_end(skb, devlink_port_nest); + return 0; + +nest_cancel: + nla_nest_cancel(skb, devlink_port_nest); + return ret; +} + static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct net *src_net, int type, u32 pid, u32 seq, u32 change, @@ -1865,6 +1901,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, dev->dev.parent->bus->name)) goto nla_put_failure; + if (rtnl_fill_devlink_port(skb, dev)) + goto nla_put_failure; + nlmsg_end(skb, nlh); return 0; -- cgit From 7a4b3770d635d05f1d8a4a17ae4acab5b3d2bad1 Mon Sep 17 00:00:00 2001 From: Jammy Huang Date: Fri, 28 Oct 2022 10:35:50 +0800 Subject: media: v4l: Add definition for the Aspeed JPEG format This introduces support for the Aspeed JPEG format, where the new frame can refer to previous frame to reduce the amount of compressed data. The concept is similar to I/P frame of video compression. It will compare the new frame with previous one to decide which macroblock's data is changed, and only the changed macroblocks will be compressed. This Aspeed JPEG format is used by the video engine on Aspeed platforms, which is generally adapted for remote KVM. Signed-off-by: Jammy Huang Signed-off-by: Hans Verkuil --- .../userspace-api/media/v4l/pixfmt-reserved.rst | 17 +++++++++++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 19 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index 0ff68cd8cf62..73cd99828010 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -258,6 +258,23 @@ please make a proposal on the linux-media mailing list. and it is used by various multimedia hardware blocks like GPU, display controllers, ISP and video accelerators. It contains four planes for progressive video. + * .. _V4L2-PIX-FMT-AJPG: + + - ``V4L2_PIX_FMT_AJPG`` + - 'AJPG' + - ASPEED JPEG format used by the aspeed-video driver on Aspeed platforms, + which is generally adapted for remote KVM. + On each frame compression, I will compare the new frame with previous + one to decide which macroblock's data is changed, and only the changed + macroblocks will be compressed. + + The implementation is based on AST2600 A3 datasheet, revision 0.9, which + is not publicly available. Or you can reference Video stream data format + – ASPEED mode compression of SDK_User_Guide which available on + AspeedTech-BMC/openbmc/releases. + + Decoder's implementation can be found here, + `aspeed_codec `__ .. raw:: latex \normalsize diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index fddba75d9074..8cb4b976064e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1497,6 +1497,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_MT21C: descr = "Mediatek Compressed Format"; break; case V4L2_PIX_FMT_QC08C: descr = "QCOM Compressed 8-bit Format"; break; case V4L2_PIX_FMT_QC10C: descr = "QCOM Compressed 10-bit Format"; break; + case V4L2_PIX_FMT_AJPG: descr = "Aspeed JPEG"; break; default: if (fmt->description[0]) return; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 29da1f4b4578..f91260e79ddc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -775,6 +775,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ #define V4L2_PIX_FMT_QC08C v4l2_fourcc('Q', '0', '8', 'C') /* Qualcomm 8-bit compressed */ #define V4L2_PIX_FMT_QC10C v4l2_fourcc('Q', '1', '0', 'C') /* Qualcomm 10-bit compressed */ +#define V4L2_PIX_FMT_AJPG v4l2_fourcc('A', 'J', 'P', 'G') /* Aspeed JPEG */ /* 10bit raw packed, 32 bytes for every 25 pixels, last LSB 6 bits unused */ #define V4L2_PIX_FMT_IPU3_SBGGR10 v4l2_fourcc('i', 'p', '3', 'b') /* IPU3 packed 10-bit BGGR bayer */ -- cgit From 867d3b275c385e80eaf7c46ab08674ae0af47bf3 Mon Sep 17 00:00:00 2001 From: Jammy Huang Date: Fri, 28 Oct 2022 10:35:51 +0800 Subject: media: v4l2-ctrls: Reserve controls for ASPEED Reserve controls for ASPEED video family. Aspeed video engine contains a few features which improve video quality, reduce amount of compressed data, and etc. Hence, 16 controls are reserved for these aspeed proprietary features. Signed-off-by: Jammy Huang Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-controls.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index b5e7d082b8ad..5c09451779cb 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -231,6 +231,12 @@ enum v4l2_colorfx { */ #define V4L2_CID_USER_DW100_BASE (V4L2_CID_USER_BASE + 0x1190) +/* + * The base for Aspeed driver controls. + * We reserve 16 controls for this driver. + */ +#define V4L2_CID_USER_ASPEED_BASE (V4L2_CID_USER_BASE + 0x11a0) + /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls * and the 'MPEG' part of the define is historical */ -- cgit From d4b9fd006fae58d2fdc68a1d1000e0498d8fbe33 Mon Sep 17 00:00:00 2001 From: Jammy Huang Date: Fri, 28 Oct 2022 10:35:53 +0800 Subject: media: aspeed: Support aspeed mode to reduce compressed data aspeed supports differential jpeg format which only compress the parts which are changed. In this way, it reduces both the amount of data to be transferred by network and those to be decoded on the client side. 2 new ctrls are added: * Aspeed HQ Mode: to control aspeed's high quality(2-pass) compression mode This only works with yuv444 subsampling. * Aspeed HQ Quality: to control the quality of aspeed's HQ mode only useful if Aspeed HQ mode is enabled Aspeed JPEG Format requires an additional buffer, called bcd, to store the information about which macro block in the new frame is different from the previous one. To have bcd correctly working, we need to swap the buffers for src0/1 to make src1 refer to previous frame and src0 to the coming new frame. Signed-off-by: Jammy Huang Reported-by: kernel test robot Signed-off-by: Hans Verkuil [hverkuil: fix logging dma_addr_t, use %pad for that] --- drivers/media/platform/aspeed/aspeed-video.c | 278 ++++++++++++++++++++++----- include/uapi/linux/aspeed-video.h | 14 ++ 2 files changed, 241 insertions(+), 51 deletions(-) create mode 100644 include/uapi/linux/aspeed-video.h (limited to 'include/uapi/linux') diff --git a/drivers/media/platform/aspeed/aspeed-video.c b/drivers/media/platform/aspeed/aspeed-video.c index 20f795ccc11b..482fa897b3a3 100644 --- a/drivers/media/platform/aspeed/aspeed-video.c +++ b/drivers/media/platform/aspeed/aspeed-video.c @@ -33,6 +33,7 @@ #include #include #include +#include #define ASPEED_VIDEO_V4L2_MIN_BUF_REQ 3 @@ -59,6 +60,7 @@ #define VE_MAX_SRC_BUFFER_SIZE 0x8ca000 /* 1920 * 1200, 32bpp */ #define VE_JPEG_HEADER_SIZE 0x006000 /* 512 * 12 * 4 */ +#define VE_BCD_BUFF_SIZE 0x9000 /* (1920/8) * (1200/8) */ #define VE_PROTECTION_KEY 0x000 #define VE_PROTECTION_KEY_UNLOCK 0x1a038aa8 @@ -107,6 +109,13 @@ #define VE_SCALING_FILTER2 0x020 #define VE_SCALING_FILTER3 0x024 +#define VE_BCD_CTRL 0x02C +#define VE_BCD_CTRL_EN_BCD BIT(0) +#define VE_BCD_CTRL_EN_ABCD BIT(1) +#define VE_BCD_CTRL_EN_CB BIT(2) +#define VE_BCD_CTRL_THR GENMASK(23, 16) +#define VE_BCD_CTRL_ABCD_THR GENMASK(31, 24) + #define VE_CAP_WINDOW 0x030 #define VE_COMP_WINDOW 0x034 #define VE_COMP_PROC_OFFSET 0x038 @@ -115,6 +124,7 @@ #define VE_SRC0_ADDR 0x044 #define VE_SRC_SCANLINE_OFFSET 0x048 #define VE_SRC1_ADDR 0x04c +#define VE_BCD_ADDR 0x050 #define VE_COMP_ADDR 0x054 #define VE_STREAM_BUF_SIZE 0x058 @@ -135,6 +145,8 @@ #define VE_COMP_CTRL_HQ_DCT_CHR GENMASK(26, 22) #define VE_COMP_CTRL_HQ_DCT_LUM GENMASK(31, 27) +#define VE_CB_ADDR 0x06C + #define AST2400_VE_COMP_SIZE_READ_BACK 0x078 #define AST2600_VE_COMP_SIZE_READ_BACK 0x084 @@ -211,6 +223,12 @@ enum { VIDEO_CLOCKS_ON, }; +enum aspeed_video_format { + VIDEO_FMT_STANDARD = 0, + VIDEO_FMT_ASPEED, + VIDEO_FMT_MAX = VIDEO_FMT_ASPEED +}; + // for VE_CTRL_CAPTURE_FMT enum aspeed_video_capture_format { VIDEO_CAP_FMT_YUV_STUDIO_SWING = 0, @@ -245,16 +263,20 @@ struct aspeed_video_perf { /* * struct aspeed_video - driver data * - * res_work: holds the delayed_work for res-detection if unlock - * buffers: holds the list of buffer queued from user + * res_work: holds the delayed_work for res-detection if unlock + * buffers: holds the list of buffer queued from user * flags: holds the state of video * sequence: holds the last number of frame completed * max_compressed_size: holds max compressed stream's size * srcs: holds the buffer information for srcs * jpeg: holds the buffer information for jpeg header + * bcd: holds the buffer information for bcd work * yuv420: a flag raised if JPEG subsampling is 420 + * format: holds the video format + * hq_mode: a flag raised if HQ is enabled. Only for VIDEO_FMT_ASPEED * frame_rate: holds the frame_rate * jpeg_quality: holds jpeq's quality (0~11) + * jpeg_hq_quality: holds hq's quality (1~12) only if hq_mode enabled * frame_bottom: end position of video data in vertical direction * frame_left: start position of video data in horizontal direction * frame_right: end position of video data in horizontal direction @@ -290,10 +312,14 @@ struct aspeed_video { unsigned int max_compressed_size; struct aspeed_video_addr srcs[2]; struct aspeed_video_addr jpeg; + struct aspeed_video_addr bcd; bool yuv420; + enum aspeed_video_format format; + bool hq_mode; unsigned int frame_rate; unsigned int jpeg_quality; + unsigned int jpeg_hq_quality; unsigned int frame_bottom; unsigned int frame_left; @@ -458,8 +484,18 @@ static const struct v4l2_dv_timings_cap aspeed_video_timings_cap = { }, }; +static const char * const format_str[] = {"Standard JPEG", + "Aspeed JPEG"}; + static unsigned int debug; +static bool aspeed_video_alloc_buf(struct aspeed_video *video, + struct aspeed_video_addr *addr, + unsigned int size); + +static void aspeed_video_free_buf(struct aspeed_video *video, + struct aspeed_video_addr *addr); + static void aspeed_video_init_jpeg_table(u32 *table, bool yuv420) { int i; @@ -547,6 +583,7 @@ static int aspeed_video_start_frame(struct aspeed_video *video) unsigned long flags; struct aspeed_video_buffer *buf; u32 seq_ctrl = aspeed_video_read(video, VE_SEQ_CTRL); + bool bcd_buf_need = (video->format != VIDEO_FMT_STANDARD); if (video->v4l2_input_status) { v4l2_warn(&video->v4l2_dev, "No signal; don't start frame\n"); @@ -559,6 +596,20 @@ static int aspeed_video_start_frame(struct aspeed_video *video) return -EBUSY; } + if (bcd_buf_need && !video->bcd.size) { + if (!aspeed_video_alloc_buf(video, &video->bcd, + VE_BCD_BUFF_SIZE)) { + dev_err(video->dev, "Failed to allocate BCD buffer\n"); + dev_err(video->dev, "don't start frame\n"); + return -ENOMEM; + } + aspeed_video_write(video, VE_BCD_ADDR, video->bcd.dma); + v4l2_dbg(1, debug, &video->v4l2_dev, "bcd addr(%pad) size(%d)\n", + &video->bcd.dma, video->bcd.size); + } else if (!bcd_buf_need && video->bcd.size) { + aspeed_video_free_buf(video, &video->bcd); + } + spin_lock_irqsave(&video->lock, flags); buf = list_first_entry_or_null(&video->buffers, struct aspeed_video_buffer, link); @@ -657,6 +708,24 @@ static void aspeed_video_irq_res_change(struct aspeed_video *video, ulong delay) schedule_delayed_work(&video->res_work, delay); } +static void aspeed_video_swap_src_buf(struct aspeed_video *v) +{ + if (v->format == VIDEO_FMT_STANDARD) + return; + + /* Reset bcd buffer to have a full frame update every 8 frames. */ + if (IS_ALIGNED(v->sequence, 8)) + memset((u8 *)v->bcd.virt, 0x00, VE_BCD_BUFF_SIZE); + + if (v->sequence & 0x01) { + aspeed_video_write(v, VE_SRC0_ADDR, v->srcs[1].dma); + aspeed_video_write(v, VE_SRC1_ADDR, v->srcs[0].dma); + } else { + aspeed_video_write(v, VE_SRC0_ADDR, v->srcs[0].dma); + aspeed_video_write(v, VE_SRC1_ADDR, v->srcs[1].dma); + } +} + static irqreturn_t aspeed_video_irq(int irq, void *arg) { struct aspeed_video *video = arg; @@ -705,6 +774,7 @@ static irqreturn_t aspeed_video_irq(int irq, void *arg) if (sts & VE_INTERRUPT_COMP_COMPLETE) { struct aspeed_video_buffer *buf; + bool empty = true; u32 frame_size = aspeed_video_read(video, video->comp_size_read); @@ -718,13 +788,23 @@ static irqreturn_t aspeed_video_irq(int irq, void *arg) if (buf) { vb2_set_plane_payload(&buf->vb.vb2_buf, 0, frame_size); - if (!list_is_last(&buf->link, &video->buffers)) { + /* + * aspeed_jpeg requires continuous update. + * On the contrary, standard jpeg can keep last buffer + * to always have the latest result. + */ + if (video->format == VIDEO_FMT_STANDARD && + list_is_last(&buf->link, &video->buffers)) { + empty = false; + v4l2_warn(&video->v4l2_dev, "skip to keep last frame updated\n"); + } else { buf->vb.vb2_buf.timestamp = ktime_get_ns(); buf->vb.sequence = video->sequence++; buf->vb.field = V4L2_FIELD_NONE; vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_DONE); list_del(&buf->link); + empty = list_empty(&video->buffers); } } spin_unlock(&video->lock); @@ -738,7 +818,10 @@ static irqreturn_t aspeed_video_irq(int irq, void *arg) aspeed_video_write(video, VE_INTERRUPT_STATUS, VE_INTERRUPT_COMP_COMPLETE); sts &= ~VE_INTERRUPT_COMP_COMPLETE; - if (test_bit(VIDEO_STREAMING, &video->flags) && buf) + + aspeed_video_swap_src_buf(video); + + if (test_bit(VIDEO_STREAMING, &video->flags) && !empty) aspeed_video_start_frame(video); } @@ -1085,10 +1168,14 @@ static void aspeed_video_set_resolution(struct aspeed_video *video) FIELD_PREP(VE_TGS_FIRST, video->frame_top) | FIELD_PREP(VE_TGS_LAST, video->frame_bottom + 1)); - aspeed_video_update(video, VE_CTRL, 0, VE_CTRL_INT_DE); + aspeed_video_update(video, VE_CTRL, + VE_CTRL_INT_DE | VE_CTRL_DIRECT_FETCH, + VE_CTRL_INT_DE); } else { v4l2_dbg(1, debug, &video->v4l2_dev, "Capture: Direct Mode\n"); - aspeed_video_update(video, VE_CTRL, 0, VE_CTRL_DIRECT_FETCH); + aspeed_video_update(video, VE_CTRL, + VE_CTRL_INT_DE | VE_CTRL_DIRECT_FETCH, + VE_CTRL_DIRECT_FETCH); } size *= 4; @@ -1121,21 +1208,65 @@ err_mem: aspeed_video_free_buf(video, &video->srcs[0]); } -static void aspeed_video_init_regs(struct aspeed_video *video) +static void aspeed_video_update_regs(struct aspeed_video *video) { - u32 comp_ctrl = VE_COMP_CTRL_RSVD | - FIELD_PREP(VE_COMP_CTRL_DCT_LUM, video->jpeg_quality) | - FIELD_PREP(VE_COMP_CTRL_DCT_CHR, video->jpeg_quality | 0x10); - u32 ctrl = VE_CTRL_AUTO_OR_CURSOR | - FIELD_PREP(VE_CTRL_CAPTURE_FMT, VIDEO_CAP_FMT_YUV_FULL_SWING); - u32 seq_ctrl = video->jpeg_mode; + u8 jpeg_hq_quality = clamp((int)video->jpeg_hq_quality - 1, 0, + ASPEED_VIDEO_JPEG_NUM_QUALITIES - 1); + u32 comp_ctrl = FIELD_PREP(VE_COMP_CTRL_DCT_LUM, video->jpeg_quality) | + FIELD_PREP(VE_COMP_CTRL_DCT_CHR, video->jpeg_quality | 0x10) | + FIELD_PREP(VE_COMP_CTRL_EN_HQ, video->hq_mode) | + FIELD_PREP(VE_COMP_CTRL_HQ_DCT_LUM, jpeg_hq_quality) | + FIELD_PREP(VE_COMP_CTRL_HQ_DCT_CHR, jpeg_hq_quality | 0x10); + u32 ctrl = 0; + u32 seq_ctrl = 0; + + v4l2_dbg(1, debug, &video->v4l2_dev, "framerate(%d)\n", + video->frame_rate); + v4l2_dbg(1, debug, &video->v4l2_dev, "jpeg format(%s) subsample(%s)\n", + format_str[video->format], + video->yuv420 ? "420" : "444"); + v4l2_dbg(1, debug, &video->v4l2_dev, "compression quality(%d)\n", + video->jpeg_quality); + v4l2_dbg(1, debug, &video->v4l2_dev, "hq_mode(%s) hq_quality(%d)\n", + video->hq_mode ? "on" : "off", video->jpeg_hq_quality); + + if (video->format == VIDEO_FMT_ASPEED) + aspeed_video_update(video, VE_BCD_CTRL, 0, VE_BCD_CTRL_EN_BCD); + else + aspeed_video_update(video, VE_BCD_CTRL, VE_BCD_CTRL_EN_BCD, 0); if (video->frame_rate) ctrl |= FIELD_PREP(VE_CTRL_FRC, video->frame_rate); + if (video->format == VIDEO_FMT_STANDARD) { + comp_ctrl &= ~FIELD_PREP(VE_COMP_CTRL_EN_HQ, video->hq_mode); + seq_ctrl |= video->jpeg_mode; + } + if (video->yuv420) seq_ctrl |= VE_SEQ_CTRL_YUV420; + if (video->jpeg.virt) + aspeed_video_update_jpeg_table(video->jpeg.virt, video->yuv420); + + /* Set control registers */ + aspeed_video_update(video, VE_SEQ_CTRL, + video->jpeg_mode | VE_SEQ_CTRL_YUV420, + seq_ctrl); + aspeed_video_update(video, VE_CTRL, VE_CTRL_FRC, ctrl); + aspeed_video_update(video, VE_COMP_CTRL, + VE_COMP_CTRL_DCT_LUM | VE_COMP_CTRL_DCT_CHR | + VE_COMP_CTRL_EN_HQ | VE_COMP_CTRL_HQ_DCT_LUM | + VE_COMP_CTRL_HQ_DCT_CHR | VE_COMP_CTRL_VQ_4COLOR | + VE_COMP_CTRL_VQ_DCT_ONLY, + comp_ctrl); +} + +static void aspeed_video_init_regs(struct aspeed_video *video) +{ + u32 ctrl = VE_CTRL_AUTO_OR_CURSOR | + FIELD_PREP(VE_CTRL_CAPTURE_FMT, VIDEO_CAP_FMT_YUV_FULL_SWING); + /* Unlock VE registers */ aspeed_video_write(video, VE_PROTECTION_KEY, VE_PROTECTION_KEY_UNLOCK); @@ -1150,9 +1281,8 @@ static void aspeed_video_init_regs(struct aspeed_video *video) aspeed_video_write(video, VE_JPEG_ADDR, video->jpeg.dma); /* Set control registers */ - aspeed_video_write(video, VE_SEQ_CTRL, seq_ctrl); aspeed_video_write(video, VE_CTRL, ctrl); - aspeed_video_write(video, VE_COMP_CTRL, comp_ctrl); + aspeed_video_write(video, VE_COMP_CTRL, VE_COMP_CTRL_RSVD); /* Don't downscale */ aspeed_video_write(video, VE_SCALING_FACTOR, 0x10001000); @@ -1168,6 +1298,8 @@ static void aspeed_video_init_regs(struct aspeed_video *video) FIELD_PREP(VE_MODE_DT_HOR_STABLE, 6) | FIELD_PREP(VE_MODE_DT_VER_STABLE, 6) | FIELD_PREP(VE_MODE_DT_EDG_THROD, 0x65)); + + aspeed_video_write(video, VE_BCD_CTRL, 0); } static void aspeed_video_start(struct aspeed_video *video) @@ -1201,6 +1333,9 @@ static void aspeed_video_stop(struct aspeed_video *video) if (video->srcs[1].size) aspeed_video_free_buf(video, &video->srcs[1]); + if (video->bcd.size) + aspeed_video_free_buf(video, &video->bcd); + video->v4l2_input_status = V4L2_IN_ST_NO_SIGNAL; video->flags = 0; } @@ -1219,10 +1354,12 @@ static int aspeed_video_querycap(struct file *file, void *fh, static int aspeed_video_enum_format(struct file *file, void *fh, struct v4l2_fmtdesc *f) { + struct aspeed_video *video = video_drvdata(file); + if (f->index) return -EINVAL; - f->pixelformat = V4L2_PIX_FMT_JPEG; + f->pixelformat = video->pix_fmt.pixelformat; return 0; } @@ -1237,6 +1374,29 @@ static int aspeed_video_get_format(struct file *file, void *fh, return 0; } +static int aspeed_video_set_format(struct file *file, void *fh, + struct v4l2_format *f) +{ + struct aspeed_video *video = video_drvdata(file); + + if (vb2_is_busy(&video->queue)) + return -EBUSY; + + switch (f->fmt.pix.pixelformat) { + case V4L2_PIX_FMT_JPEG: + video->format = VIDEO_FMT_STANDARD; + break; + case V4L2_PIX_FMT_AJPG: + video->format = VIDEO_FMT_ASPEED; + break; + default: + return -EINVAL; + } + video->pix_fmt.pixelformat = f->fmt.pix.pixelformat; + + return 0; +} + static int aspeed_video_enum_input(struct file *file, void *fh, struct v4l2_input *inp) { @@ -1454,7 +1614,7 @@ static const struct v4l2_ioctl_ops aspeed_video_ioctl_ops = { .vidioc_enum_fmt_vid_cap = aspeed_video_enum_format, .vidioc_g_fmt_vid_cap = aspeed_video_get_format, - .vidioc_s_fmt_vid_cap = aspeed_video_get_format, + .vidioc_s_fmt_vid_cap = aspeed_video_set_format, .vidioc_try_fmt_vid_cap = aspeed_video_get_format, .vidioc_reqbufs = vb2_ioctl_reqbufs, @@ -1486,27 +1646,6 @@ static const struct v4l2_ioctl_ops aspeed_video_ioctl_ops = { .vidioc_unsubscribe_event = v4l2_event_unsubscribe, }; -static void aspeed_video_update_jpeg_quality(struct aspeed_video *video) -{ - u32 comp_ctrl = FIELD_PREP(VE_COMP_CTRL_DCT_LUM, video->jpeg_quality) | - FIELD_PREP(VE_COMP_CTRL_DCT_CHR, video->jpeg_quality | 0x10); - - aspeed_video_update(video, VE_COMP_CTRL, - VE_COMP_CTRL_DCT_LUM | VE_COMP_CTRL_DCT_CHR, - comp_ctrl); -} - -static void aspeed_video_update_subsampling(struct aspeed_video *video) -{ - if (video->jpeg.virt) - aspeed_video_update_jpeg_table(video->jpeg.virt, video->yuv420); - - if (video->yuv420) - aspeed_video_update(video, VE_SEQ_CTRL, 0, VE_SEQ_CTRL_YUV420); - else - aspeed_video_update(video, VE_SEQ_CTRL, VE_SEQ_CTRL_YUV420, 0); -} - static int aspeed_video_set_ctrl(struct v4l2_ctrl *ctrl) { struct aspeed_video *video = container_of(ctrl->handler, @@ -1516,16 +1655,23 @@ static int aspeed_video_set_ctrl(struct v4l2_ctrl *ctrl) switch (ctrl->id) { case V4L2_CID_JPEG_COMPRESSION_QUALITY: video->jpeg_quality = ctrl->val; - aspeed_video_update_jpeg_quality(video); + if (test_bit(VIDEO_STREAMING, &video->flags)) + aspeed_video_update_regs(video); break; case V4L2_CID_JPEG_CHROMA_SUBSAMPLING: - if (ctrl->val == V4L2_JPEG_CHROMA_SUBSAMPLING_420) { - video->yuv420 = true; - aspeed_video_update_subsampling(video); - } else { - video->yuv420 = false; - aspeed_video_update_subsampling(video); - } + video->yuv420 = (ctrl->val == V4L2_JPEG_CHROMA_SUBSAMPLING_420); + if (test_bit(VIDEO_STREAMING, &video->flags)) + aspeed_video_update_regs(video); + break; + case V4L2_CID_ASPEED_HQ_MODE: + video->hq_mode = ctrl->val; + if (test_bit(VIDEO_STREAMING, &video->flags)) + aspeed_video_update_regs(video); + break; + case V4L2_CID_ASPEED_HQ_JPEG_QUALITY: + video->jpeg_hq_quality = ctrl->val; + if (test_bit(VIDEO_STREAMING, &video->flags)) + aspeed_video_update_regs(video); break; default: return -EINVAL; @@ -1538,6 +1684,28 @@ static const struct v4l2_ctrl_ops aspeed_video_ctrl_ops = { .s_ctrl = aspeed_video_set_ctrl, }; +static const struct v4l2_ctrl_config aspeed_ctrl_HQ_mode = { + .ops = &aspeed_video_ctrl_ops, + .id = V4L2_CID_ASPEED_HQ_MODE, + .name = "Aspeed HQ Mode", + .type = V4L2_CTRL_TYPE_BOOLEAN, + .min = false, + .max = true, + .step = 1, + .def = false, +}; + +static const struct v4l2_ctrl_config aspeed_ctrl_HQ_jpeg_quality = { + .ops = &aspeed_video_ctrl_ops, + .id = V4L2_CID_ASPEED_HQ_JPEG_QUALITY, + .name = "Aspeed HQ Quality", + .type = V4L2_CTRL_TYPE_INTEGER, + .min = 1, + .max = ASPEED_VIDEO_JPEG_NUM_QUALITIES, + .step = 1, + .def = 1, +}; + static void aspeed_video_resolution_work(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); @@ -1552,6 +1720,8 @@ static void aspeed_video_resolution_work(struct work_struct *work) aspeed_video_init_regs(video); + aspeed_video_update_regs(video); + aspeed_video_get_resolution(video); if (video->detected_timings.width != video->active_timings.width || @@ -1662,6 +1832,8 @@ static int aspeed_video_start_streaming(struct vb2_queue *q, video->perf.duration_max = 0; video->perf.duration_min = 0xffffffff; + aspeed_video_update_regs(video); + rc = aspeed_video_start_frame(video); if (rc) { aspeed_video_bufs_done(video, VB2_BUF_STATE_QUEUED); @@ -1800,6 +1972,7 @@ static int aspeed_video_setup_video(struct aspeed_video *video) struct v4l2_device *v4l2_dev = &video->v4l2_dev; struct vb2_queue *vbq = &video->queue; struct video_device *vdev = &video->vdev; + struct v4l2_ctrl_handler *hdl = &video->ctrl_handler; int rc; video->pix_fmt.pixelformat = V4L2_PIX_FMT_JPEG; @@ -1814,16 +1987,18 @@ static int aspeed_video_setup_video(struct aspeed_video *video) return rc; } - v4l2_ctrl_handler_init(&video->ctrl_handler, 2); - v4l2_ctrl_new_std(&video->ctrl_handler, &aspeed_video_ctrl_ops, + v4l2_ctrl_handler_init(hdl, 4); + v4l2_ctrl_new_std(hdl, &aspeed_video_ctrl_ops, V4L2_CID_JPEG_COMPRESSION_QUALITY, 0, ASPEED_VIDEO_JPEG_NUM_QUALITIES - 1, 1, 0); - v4l2_ctrl_new_std_menu(&video->ctrl_handler, &aspeed_video_ctrl_ops, + v4l2_ctrl_new_std_menu(hdl, &aspeed_video_ctrl_ops, V4L2_CID_JPEG_CHROMA_SUBSAMPLING, V4L2_JPEG_CHROMA_SUBSAMPLING_420, mask, V4L2_JPEG_CHROMA_SUBSAMPLING_444); + v4l2_ctrl_new_custom(hdl, &aspeed_ctrl_HQ_mode, NULL); + v4l2_ctrl_new_custom(hdl, &aspeed_ctrl_HQ_jpeg_quality, NULL); - rc = video->ctrl_handler.error; + rc = hdl->error; if (rc) { v4l2_ctrl_handler_free(&video->ctrl_handler); v4l2_device_unregister(v4l2_dev); @@ -1832,7 +2007,7 @@ static int aspeed_video_setup_video(struct aspeed_video *video) return rc; } - v4l2_dev->ctrl_handler = &video->ctrl_handler; + v4l2_dev->ctrl_handler = hdl; vbq->type = V4L2_BUF_TYPE_VIDEO_CAPTURE; vbq->io_modes = VB2_MMAP | VB2_READ | VB2_DMABUF; @@ -1980,6 +2155,7 @@ static int aspeed_video_probe(struct platform_device *pdev) video->comp_size_read = config->comp_size_read; video->frame_rate = 30; + video->jpeg_hq_quality = 1; video->dev = &pdev->dev; spin_lock_init(&video->lock); mutex_init(&video->video_lock); diff --git a/include/uapi/linux/aspeed-video.h b/include/uapi/linux/aspeed-video.h new file mode 100644 index 000000000000..6586a65548c4 --- /dev/null +++ b/include/uapi/linux/aspeed-video.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (C) 2021 ASPEED Technology Inc. + */ + +#ifndef _UAPI_LINUX_ASPEED_VIDEO_H +#define _UAPI_LINUX_ASPEED_VIDEO_H + +#include + +#define V4L2_CID_ASPEED_HQ_MODE (V4L2_CID_USER_ASPEED_BASE + 1) +#define V4L2_CID_ASPEED_HQ_JPEG_QUALITY (V4L2_CID_USER_ASPEED_BASE + 2) + +#endif /* _UAPI_LINUX_ASPEED_VIDEO_H */ -- cgit From 46653972e3ea64f79e7f8ae3aa41a4d3fdb70a13 Mon Sep 17 00:00:00 2001 From: Gaosheng Cui Date: Mon, 31 Oct 2022 19:25:36 +0800 Subject: capabilities: fix undefined behavior in bit shift for CAP_TO_MASK Shifting signed 32-bit value by 31 bits is undefined, so changing significant bit to unsigned. The UBSAN warning calltrace like below: UBSAN: shift-out-of-bounds in security/commoncap.c:1252:2 left shift of 1 by 31 places cannot be represented in type 'int' Call Trace: dump_stack_lvl+0x7d/0xa5 dump_stack+0x15/0x1b ubsan_epilogue+0xe/0x4e __ubsan_handle_shift_out_of_bounds+0x1e7/0x20c cap_task_prctl+0x561/0x6f0 security_task_prctl+0x5a/0xb0 __x64_sys_prctl+0x61/0x8f0 do_syscall_64+0x58/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd Fixes: e338d263a76a ("Add 64-bit capability support to the kernel") Signed-off-by: Gaosheng Cui Acked-by: Andrew G. Morgan Reviewed-by: Serge Hallyn Signed-off-by: Paul Moore --- include/uapi/linux/capability.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 463d1ba2232a..3d61a0ae055d 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -426,7 +426,7 @@ struct vfs_ns_cap_data { */ #define CAP_TO_INDEX(x) ((x) >> 5) /* 1 << 5 == bits in __u32 */ -#define CAP_TO_MASK(x) (1 << ((x) & 31)) /* mask for indexed __u32 */ +#define CAP_TO_MASK(x) (1U << ((x) & 31)) /* mask for indexed __u32 */ #endif /* _UAPI_LINUX_CAPABILITY_H */ -- cgit From 6dcabcd398946e2b0b776a8310291aeebe1ca0e6 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 6 Nov 2022 13:17:27 -0700 Subject: io_uring: fix typo in io_uring.h comment Just a basic s/thig/this swap, fixing up a typo introduced by a commit added in the 6.1 release. Fixes: 9cda70f622cd ("io_uring: introduce fixed buffer support for io_uring_cmd") Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index ab7458033ee3..2df3225b562f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -222,7 +222,7 @@ enum io_uring_op { /* * sqe->uring_cmd_flags - * IORING_URING_CMD_FIXED use registered buffer; pass thig flag + * IORING_URING_CMD_FIXED use registered buffer; pass this flag * along with setting sqe->buf_index. */ #define IORING_URING_CMD_FIXED (1U << 0) -- cgit From 9a0f830f80265bd1ef816e1541ac24bee80e9a3c Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Fri, 4 Nov 2022 12:01:25 -0700 Subject: ethtool: linkstate: add a statistic for PHY down events The previous attempt to augment carrier_down (see Link) was not met with much enthusiasm so let's do the simple thing of exposing what some devices already maintain. Add a common ethtool statistic for link going down. Currently users have to maintain per-driver mapping to extract the right stat from the vendor-specific ethtool -S stats. carrier_down does not fit the bill because it counts a lot of software related false positives. Add the statistic to the extended link state API to steer vendors towards implementing all of it. Implement for bnxt and all Linux-controlled PHYs. mlx5 and (possibly) enic also have a counter for this but I leave the implementation to their maintainers. Link: https://lore.kernel.org/r/20220520004500.2250674-1-kuba@kernel.org Reviewed-by: Florian Fainelli Reviewed-by: Michael Chan Reviewed-by: Andrew Lunn Signed-off-by: Jakub Kicinski Link: https://lore.kernel.org/r/20221104190125.684910-1-kuba@kernel.org Signed-off-by: Paolo Abeni --- Documentation/networking/ethtool-netlink.rst | 1 + drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 15 ++++++++++++++ drivers/net/phy/phy.c | 1 + include/linux/ethtool.h | 17 ++++++++++++++++ include/linux/phy.h | 3 +++ include/uapi/linux/ethtool_netlink.h | 1 + net/ethtool/linkstate.c | 24 ++++++++++++++++++++++- 7 files changed, 61 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d578b8bcd8a4..bede24ef44fd 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -491,6 +491,7 @@ Kernel response contents: ``ETHTOOL_A_LINKSTATE_SQI_MAX`` u32 Max support SQI value ``ETHTOOL_A_LINKSTATE_EXT_STATE`` u8 link extended state ``ETHTOOL_A_LINKSTATE_EXT_SUBSTATE`` u8 link extended substate + ``ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT`` u32 count of link down events ==================================== ====== ============================ For most NIC drivers, the value of ``ETHTOOL_A_LINKSTATE_LINK`` returns diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index cc89e5eabcb9..d8f0351df954 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -4112,6 +4112,20 @@ static void bnxt_get_rmon_stats(struct net_device *dev, *ranges = bnxt_rmon_ranges; } +static void bnxt_get_link_ext_stats(struct net_device *dev, + struct ethtool_link_ext_stats *stats) +{ + struct bnxt *bp = netdev_priv(dev); + u64 *rx; + + if (BNXT_VF(bp) || !(bp->flags & BNXT_FLAG_PORT_STATS_EXT)) + return; + + rx = bp->rx_port_stats_ext.sw_stats; + stats->link_down_events = + *(rx + BNXT_RX_STATS_EXT_OFFSET(link_down_events)); +} + void bnxt_ethtool_free(struct bnxt *bp) { kfree(bp->test_info); @@ -4161,6 +4175,7 @@ const struct ethtool_ops bnxt_ethtool_ops = { .get_eeprom = bnxt_get_eeprom, .set_eeprom = bnxt_set_eeprom, .get_link = bnxt_get_link, + .get_link_ext_stats = bnxt_get_link_ext_stats, .get_eee = bnxt_get_eee, .set_eee = bnxt_set_eee, .get_module_info = bnxt_get_module_info, diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index e741d8aebffe..e5b6cb1a77f9 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -67,6 +67,7 @@ static void phy_link_down(struct phy_device *phydev) { phydev->phy_link_change(phydev, false); phy_led_trigger_change_speed(phydev); + WRITE_ONCE(phydev->link_down_events, phydev->link_down_events + 1); } static const char *phy_pause_str(struct phy_device *phydev) diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 99dc7bfbcd3c..5c51c7fda32a 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -125,6 +125,20 @@ struct ethtool_link_ext_state_info { }; }; +struct ethtool_link_ext_stats { + /* Custom Linux statistic for PHY level link down events. + * In a simpler world it should be equal to netdev->carrier_down_count + * unfortunately netdev also counts local reconfigurations which don't + * actually take the physical link down, not to mention NC-SI which, + * if present, keeps the link up regardless of host state. + * This statistic counts when PHY _actually_ went down, or lost link. + * + * Note that we need u64 for ethtool_stats_init() and comparisons + * to ETHTOOL_STAT_NOT_SET, but only u32 is exposed to the user. + */ + u64 link_down_events; +}; + /** * ethtool_rxfh_indir_default - get default value for RX flow hash indirection * @index: Index in RX flow hash indirection table @@ -481,6 +495,7 @@ struct ethtool_module_power_mode_params { * do not attach ext_substate attribute to netlink message). If link_ext_state * and link_ext_substate are unknown, return -ENODATA. If not implemented, * link_ext_state and link_ext_substate will not be sent to userspace. + * @get_link_ext_stats: Read extra link-related counters. * @get_eeprom_len: Read range of EEPROM addresses for validation of * @get_eeprom and @set_eeprom requests. * Returns 0 if device does not support EEPROM access. @@ -652,6 +667,8 @@ struct ethtool_ops { u32 (*get_link)(struct net_device *); int (*get_link_ext_state)(struct net_device *, struct ethtool_link_ext_state_info *); + void (*get_link_ext_stats)(struct net_device *dev, + struct ethtool_link_ext_stats *stats); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); diff --git a/include/linux/phy.h b/include/linux/phy.h index ddf66198f751..9a3752c0c444 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -600,6 +600,7 @@ struct macsec_ops; * @psec: Pointer to Power Sourcing Equipment control struct * @lock: Mutex for serialization access to PHY * @state_queue: Work queue for state machine + * @link_down_events: Number of times link was lost * @shared: Pointer to private data shared by phys in one package * @priv: Pointer to driver private data * @@ -723,6 +724,8 @@ struct phy_device { int pma_extable; + unsigned int link_down_events; + void (*phy_link_change)(struct phy_device *phydev, bool up); void (*adjust_link)(struct net_device *dev); diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index bb57084ac524..aaf7c6963d61 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -262,6 +262,7 @@ enum { ETHTOOL_A_LINKSTATE_SQI_MAX, /* u32 */ ETHTOOL_A_LINKSTATE_EXT_STATE, /* u8 */ ETHTOOL_A_LINKSTATE_EXT_SUBSTATE, /* u8 */ + ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, /* u32 */ /* add new constants above here */ __ETHTOOL_A_LINKSTATE_CNT, diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c index fb676f349455..2158c17a0b32 100644 --- a/net/ethtool/linkstate.c +++ b/net/ethtool/linkstate.c @@ -13,6 +13,7 @@ struct linkstate_reply_data { int link; int sqi; int sqi_max; + struct ethtool_link_ext_stats link_stats; bool link_ext_state_provided; struct ethtool_link_ext_state_info ethtool_link_ext_state_info; }; @@ -22,7 +23,7 @@ struct linkstate_reply_data { const struct nla_policy ethnl_linkstate_get_policy[] = { [ETHTOOL_A_LINKSTATE_HEADER] = - NLA_POLICY_NESTED(ethnl_header_policy), + NLA_POLICY_NESTED(ethnl_header_policy_stats), }; static int linkstate_get_sqi(struct net_device *dev) @@ -107,6 +108,19 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base, goto out; } + ethtool_stats_init((u64 *)&data->link_stats, + sizeof(data->link_stats) / 8); + + if (req_base->flags & ETHTOOL_FLAG_STATS) { + if (dev->phydev) + data->link_stats.link_down_events = + READ_ONCE(dev->phydev->link_down_events); + + if (dev->ethtool_ops->get_link_ext_stats) + dev->ethtool_ops->get_link_ext_stats(dev, + &data->link_stats); + } + ret = 0; out: ethnl_ops_complete(dev); @@ -134,6 +148,9 @@ static int linkstate_reply_size(const struct ethnl_req_info *req_base, if (data->ethtool_link_ext_state_info.__link_ext_substate) len += nla_total_size(sizeof(u8)); /* LINKSTATE_EXT_SUBSTATE */ + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + len += nla_total_size(sizeof(u32)); + return len; } @@ -166,6 +183,11 @@ static int linkstate_fill_reply(struct sk_buff *skb, return -EMSGSIZE; } + if (data->link_stats.link_down_events != ETHTOOL_STAT_NOT_SET) + if (nla_put_u32(skb, ETHTOOL_A_LINKSTATE_EXT_DOWN_CNT, + data->link_stats.link_down_events)) + return -EMSGSIZE; + return 0; } -- cgit From a21b06e7319129994f339ed47f512bbe57b77f5b Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 6 Nov 2022 15:34:17 -0500 Subject: net: sched: add helper support in act_ct This patch is to add helper support in act_ct for OVS actions=ct(alg=xxx) offloading, which is corresponding to Commit cae3a2627520 ("openvswitch: Allow attaching helpers to ct action") in OVS kernel part. The difference is when adding TC actions family and proto cannot be got from the filter/match, other than helper name in tb[TCA_CT_HELPER_NAME], we also need to send the family in tb[TCA_CT_HELPER_FAMILY] and the proto in tb[TCA_CT_HELPER_PROTO] to kernel. Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Signed-off-by: Paolo Abeni --- include/net/tc_act/tc_ct.h | 1 + include/uapi/linux/tc_act/tc_ct.h | 3 ++ net/sched/act_ct.c | 89 +++++++++++++++++++++++++++++++++++---- 3 files changed, 85 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/tc_act/tc_ct.h b/include/net/tc_act/tc_ct.h index 8250d6f0a462..b24ea2d9400b 100644 --- a/include/net/tc_act/tc_ct.h +++ b/include/net/tc_act/tc_ct.h @@ -10,6 +10,7 @@ #include struct tcf_ct_params { + struct nf_conntrack_helper *helper; struct nf_conn *tmpl; u16 zone; diff --git a/include/uapi/linux/tc_act/tc_ct.h b/include/uapi/linux/tc_act/tc_ct.h index 5fb1d7ac1027..6c5200f0ed38 100644 --- a/include/uapi/linux/tc_act/tc_ct.h +++ b/include/uapi/linux/tc_act/tc_ct.h @@ -22,6 +22,9 @@ enum { TCA_CT_NAT_PORT_MIN, /* be16 */ TCA_CT_NAT_PORT_MAX, /* be16 */ TCA_CT_PAD, + TCA_CT_HELPER_NAME, /* string */ + TCA_CT_HELPER_FAMILY, /* u8 */ + TCA_CT_HELPER_PROTO, /* u8 */ __TCA_CT_MAX }; diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c index 193a460a9d7f..da0b7f665277 100644 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@ -33,6 +33,7 @@ #include #include #include +#include #include static struct workqueue_struct *act_ct_wq; @@ -655,7 +656,7 @@ struct tc_ct_action_net { /* Determine whether skb->_nfct is equal to the result of conntrack lookup. */ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, - u16 zone_id, bool force) + struct tcf_ct_params *p) { enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -665,11 +666,19 @@ static bool tcf_ct_skb_nfct_cached(struct net *net, struct sk_buff *skb, return false; if (!net_eq(net, read_pnet(&ct->ct_net))) goto drop_ct; - if (nf_ct_zone(ct)->id != zone_id) + if (nf_ct_zone(ct)->id != p->zone) goto drop_ct; + if (p->helper) { + struct nf_conn_help *help; + + help = nf_ct_ext_find(ct, NF_CT_EXT_HELPER); + if (help && rcu_access_pointer(help->helper) != p->helper) + goto drop_ct; + } /* Force conntrack entry direction. */ - if (force && CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { + if ((p->ct_action & TCA_CT_ACT_FORCE) && + CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) { if (nf_ct_is_confirmed(ct)) nf_ct_kill(ct); @@ -832,6 +841,13 @@ out_free: static void tcf_ct_params_free(struct tcf_ct_params *params) { + if (params->helper) { +#if IS_ENABLED(CONFIG_NF_NAT) + if (params->ct_action & TCA_CT_ACT_NAT) + nf_nat_helper_put(params->helper); +#endif + nf_conntrack_helper_put(params->helper); + } if (params->ct_ft) tcf_ct_flow_table_put(params->ct_ft); if (params->tmpl) @@ -1026,13 +1042,14 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct net *net = dev_net(skb->dev); - bool cached, commit, clear, force; enum ip_conntrack_info ctinfo; struct tcf_ct *c = to_ct(a); struct nf_conn *tmpl = NULL; struct nf_hook_state state; + bool cached, commit, clear; int nh_ofs, err, retval; struct tcf_ct_params *p; + bool add_helper = false; bool skip_add = false; bool defrag = false; struct nf_conn *ct; @@ -1043,7 +1060,6 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, retval = READ_ONCE(c->tcf_action); commit = p->ct_action & TCA_CT_ACT_COMMIT; clear = p->ct_action & TCA_CT_ACT_CLEAR; - force = p->ct_action & TCA_CT_ACT_FORCE; tmpl = p->tmpl; tcf_lastuse_update(&c->tcf_tm); @@ -1086,7 +1102,7 @@ static int tcf_ct_act(struct sk_buff *skb, const struct tc_action *a, * actually run the packet through conntrack twice unless it's for a * different zone. */ - cached = tcf_ct_skb_nfct_cached(net, skb, p->zone, force); + cached = tcf_ct_skb_nfct_cached(net, skb, p); if (!cached) { if (tcf_ct_flow_table_lookup(p, skb, family)) { skip_add = true; @@ -1119,6 +1135,22 @@ do_nat: if (err != NF_ACCEPT) goto drop; + if (!nf_ct_is_confirmed(ct) && commit && p->helper && !nfct_help(ct)) { + err = __nf_ct_try_assign_helper(ct, p->tmpl, GFP_ATOMIC); + if (err) + goto drop; + add_helper = true; + if (p->ct_action & TCA_CT_ACT_NAT && !nfct_seqadj(ct)) { + if (!nfct_seqadj_ext_add(ct)) + goto drop; + } + } + + if (nf_ct_is_confirmed(ct) ? ((!cached && !skip_add) || add_helper) : commit) { + if (nf_ct_helper(skb, ct, ctinfo, family) != NF_ACCEPT) + goto drop; + } + if (commit) { tcf_ct_act_set_mark(ct, p->mark, p->mark_mask); tcf_ct_act_set_labels(ct, p->labels, p->labels_mask); @@ -1167,6 +1199,9 @@ static const struct nla_policy ct_policy[TCA_CT_MAX + 1] = { [TCA_CT_NAT_IPV6_MAX] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [TCA_CT_NAT_PORT_MIN] = { .type = NLA_U16 }, [TCA_CT_NAT_PORT_MAX] = { .type = NLA_U16 }, + [TCA_CT_HELPER_NAME] = { .type = NLA_STRING, .len = NF_CT_HELPER_NAME_LEN }, + [TCA_CT_HELPER_FAMILY] = { .type = NLA_U8 }, + [TCA_CT_HELPER_PROTO] = { .type = NLA_U8 }, }; static int tcf_ct_fill_params_nat(struct tcf_ct_params *p, @@ -1256,8 +1291,9 @@ static int tcf_ct_fill_params(struct net *net, { struct tc_ct_action_net *tn = net_generic(net, act_ct_ops.net_id); struct nf_conntrack_zone zone; + int err, family, proto, len; struct nf_conn *tmpl; - int err; + char *name; p->zone = NF_CT_DEFAULT_ZONE_ID; @@ -1318,10 +1354,31 @@ static int tcf_ct_fill_params(struct net *net, NL_SET_ERR_MSG_MOD(extack, "Failed to allocate conntrack template"); return -ENOMEM; } - __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); p->tmpl = tmpl; + if (tb[TCA_CT_HELPER_NAME]) { + name = nla_data(tb[TCA_CT_HELPER_NAME]); + len = nla_len(tb[TCA_CT_HELPER_NAME]); + if (len > 16 || name[len - 1] != '\0') { + NL_SET_ERR_MSG_MOD(extack, "Failed to parse helper name."); + err = -EINVAL; + goto err; + } + family = tb[TCA_CT_HELPER_FAMILY] ? nla_get_u8(tb[TCA_CT_HELPER_FAMILY]) : AF_INET; + proto = tb[TCA_CT_HELPER_PROTO] ? nla_get_u8(tb[TCA_CT_HELPER_PROTO]) : IPPROTO_TCP; + err = nf_ct_add_helper(tmpl, name, family, proto, + p->ct_action & TCA_CT_ACT_NAT, &p->helper); + if (err) { + NL_SET_ERR_MSG_MOD(extack, "Failed to add helper"); + goto err; + } + } + __set_bit(IPS_CONFIRMED_BIT, &tmpl->status); return 0; +err: + nf_ct_put(p->tmpl); + p->tmpl = NULL; + return err; } static int tcf_ct_init(struct net *net, struct nlattr *nla, @@ -1490,6 +1547,19 @@ static int tcf_ct_dump_nat(struct sk_buff *skb, struct tcf_ct_params *p) return 0; } +static int tcf_ct_dump_helper(struct sk_buff *skb, struct nf_conntrack_helper *helper) +{ + if (!helper) + return 0; + + if (nla_put_string(skb, TCA_CT_HELPER_NAME, helper->name) || + nla_put_u8(skb, TCA_CT_HELPER_FAMILY, helper->tuple.src.l3num) || + nla_put_u8(skb, TCA_CT_HELPER_PROTO, helper->tuple.dst.protonum)) + return -1; + + return 0; +} + static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { @@ -1542,6 +1612,9 @@ static inline int tcf_ct_dump(struct sk_buff *skb, struct tc_action *a, if (tcf_ct_dump_nat(skb, p)) goto nla_put_failure; + if (tcf_ct_dump_helper(skb, p->helper)) + goto nla_put_failure; + skip_dump: if (nla_put(skb, TCA_CT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; -- cgit From defbab270d45e32b068e7e73c3567232d745c60f Mon Sep 17 00:00:00 2001 From: Matt Redfearn Date: Tue, 27 Sep 2022 14:52:56 -0700 Subject: include/uapi/linux/swab: Fix potentially missing __always_inline MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit bc27fb68aaad ("include/uapi/linux/byteorder, swab: force inlining of some byteswap operations") added __always_inline to swab functions and commit 283d75737837 ("uapi/linux/stddef.h: Provide __always_inline to userspace headers") added a definition of __always_inline for use in exported headers when the kernel's compiler.h is not available. However, since swab.h does not include stddef.h, if the header soup does not indirectly include it, the definition of __always_inline is missing, resulting in a compilation failure, which was observed compiling the perf tool using exported headers containing this commit: In file included from /usr/include/linux/byteorder/little_endian.h:12:0, from /usr/include/asm/byteorder.h:14, from tools/include/uapi/linux/perf_event.h:20, from perf.h:8, from builtin-bench.c:18: /usr/include/linux/swab.h:160:8: error: unknown type name `__always_inline' static __always_inline __u16 __swab16p(const __u16 *p) Fix this by replacing the inclusion of linux/compiler.h with linux/stddef.h to ensure that we pick up that definition if required, without relying on it's indirect inclusion. compiler.h is then included indirectly, via stddef.h. Fixes: 283d75737837 ("uapi/linux/stddef.h: Provide __always_inline to userspace headers") Signed-off-by: Matt Redfearn Signed-off-by: Florian Fainelli Signed-off-by: Arnd Bergmann Tested-by: Nathan Chancellor Reviewed-by: Petr Vaněk Signed-off-by: Arnd Bergmann --- include/uapi/linux/swab.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/swab.h b/include/uapi/linux/swab.h index 0723a9cce747..01717181339e 100644 --- a/include/uapi/linux/swab.h +++ b/include/uapi/linux/swab.h @@ -3,7 +3,7 @@ #define _UAPI_LINUX_SWAB_H #include -#include +#include #include #include -- cgit From db205f7e1edc8d8f0880f0218d3a03b13fe94af3 Mon Sep 17 00:00:00 2001 From: Aaron Lewis Date: Wed, 21 Sep 2022 15:15:22 +0000 Subject: KVM: x86: Add a VALID_MASK for the MSR exit reason flags Add the mask KVM_MSR_EXIT_REASON_VALID_MASK for the MSR exit reason flags. This simplifies checks that validate these flags, and makes it easier to introduce new flags in the future. No functional change intended. Signed-off-by: Aaron Lewis Message-Id: <20220921151525.904162-3-aaronlewis@google.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/x86.c | 4 +--- include/uapi/linux/kvm.h | 3 +++ 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cbec2e675c18..9ba8c1b73db4 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -6230,9 +6230,7 @@ split_irqchip_unlock: break; case KVM_CAP_X86_USER_SPACE_MSR: r = -EINVAL; - if (cap->args[0] & ~(KVM_MSR_EXIT_REASON_INVAL | - KVM_MSR_EXIT_REASON_UNKNOWN | - KVM_MSR_EXIT_REASON_FILTER)) + if (cap->args[0] & ~KVM_MSR_EXIT_REASON_VALID_MASK) break; kvm->arch.user_space_msr_mask = cap->args[0]; r = 0; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0d5d4419139a..7fea12369245 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -485,6 +485,9 @@ struct kvm_run { #define KVM_MSR_EXIT_REASON_INVAL (1 << 0) #define KVM_MSR_EXIT_REASON_UNKNOWN (1 << 1) #define KVM_MSR_EXIT_REASON_FILTER (1 << 2) +#define KVM_MSR_EXIT_REASON_VALID_MASK (KVM_MSR_EXIT_REASON_INVAL | \ + KVM_MSR_EXIT_REASON_UNKNOWN | \ + KVM_MSR_EXIT_REASON_FILTER) __u32 reason; /* kernel -> user */ __u32 index; /* kernel -> user */ __u64 data; /* kernel <-> user */ -- cgit From 86bdf3ebcfe1ded055282536fecce13001874740 Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Thu, 10 Nov 2022 18:49:10 +0800 Subject: KVM: Support dirty ring in conjunction with bitmap ARM64 needs to dirty memory outside of a VCPU context when VGIC/ITS is enabled. It's conflicting with that ring-based dirty page tracking always requires a running VCPU context. Introduce a new flavor of dirty ring that requires the use of both VCPU dirty rings and a dirty bitmap. The expectation is that for non-VCPU sources of dirty memory (such as the VGIC/ITS on arm64), KVM writes to the dirty bitmap. Userspace should scan the dirty bitmap before migrating the VM to the target. Use an additional capability to advertise this behavior. The newly added capability (KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP) can't be enabled before KVM_CAP_DIRTY_LOG_RING_ACQ_REL on ARM64. In this way, the newly added capability is treated as an extension of KVM_CAP_DIRTY_LOG_RING_ACQ_REL. Suggested-by: Marc Zyngier Suggested-by: Peter Xu Co-developed-by: Oliver Upton Signed-off-by: Oliver Upton Signed-off-by: Gavin Shan Acked-by: Peter Xu Signed-off-by: Marc Zyngier Link: https://lore.kernel.org/r/20221110104914.31280-4-gshan@redhat.com --- Documentation/virt/kvm/api.rst | 34 +++++++++++--- Documentation/virt/kvm/devices/arm-vgic-its.rst | 5 +- include/linux/kvm_dirty_ring.h | 7 +++ include/linux/kvm_host.h | 1 + include/uapi/linux/kvm.h | 1 + virt/kvm/Kconfig | 6 +++ virt/kvm/dirty_ring.c | 14 ++++++ virt/kvm/kvm_main.c | 61 +++++++++++++++++++++---- 8 files changed, 112 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index eee9f857a986..1f1b09aa6db4 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -8003,13 +8003,6 @@ flushing is done by the KVM_GET_DIRTY_LOG ioctl). To achieve that, one needs to kick the vcpu out of KVM_RUN using a signal. The resulting vmexit ensures that all dirty GFNs are flushed to the dirty rings. -NOTE: the capability KVM_CAP_DIRTY_LOG_RING and the corresponding -ioctl KVM_RESET_DIRTY_RINGS are mutual exclusive to the existing ioctls -KVM_GET_DIRTY_LOG and KVM_CLEAR_DIRTY_LOG. After enabling -KVM_CAP_DIRTY_LOG_RING with an acceptable dirty ring size, the virtual -machine will switch to ring-buffer dirty page tracking and further -KVM_GET_DIRTY_LOG or KVM_CLEAR_DIRTY_LOG ioctls will fail. - NOTE: KVM_CAP_DIRTY_LOG_RING_ACQ_REL is the only capability that should be exposed by weakly ordered architecture, in order to indicate the additional memory ordering requirements imposed on userspace when @@ -8018,6 +8011,33 @@ Architecture with TSO-like ordering (such as x86) are allowed to expose both KVM_CAP_DIRTY_LOG_RING and KVM_CAP_DIRTY_LOG_RING_ACQ_REL to userspace. +After enabling the dirty rings, the userspace needs to detect the +capability of KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP to see whether the +ring structures can be backed by per-slot bitmaps. With this capability +advertised, it means the architecture can dirty guest pages without +vcpu/ring context, so that some of the dirty information will still be +maintained in the bitmap structure. KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP +can't be enabled if the capability of KVM_CAP_DIRTY_LOG_RING_ACQ_REL +hasn't been enabled, or any memslot has been existing. + +Note that the bitmap here is only a backup of the ring structure. The +use of the ring and bitmap combination is only beneficial if there is +only a very small amount of memory that is dirtied out of vcpu/ring +context. Otherwise, the stand-alone per-slot bitmap mechanism needs to +be considered. + +To collect dirty bits in the backup bitmap, userspace can use the same +KVM_GET_DIRTY_LOG ioctl. KVM_CLEAR_DIRTY_LOG isn't needed as long as all +the generation of the dirty bits is done in a single pass. Collecting +the dirty bitmap should be the very last thing that the VMM does before +considering the state as complete. VMM needs to ensure that the dirty +state is final and avoid missing dirty pages from another ioctl ordered +after the bitmap collection. + +NOTE: One example of using the backup bitmap is saving arm64 vgic/its +tables through KVM_DEV_ARM_{VGIC_GRP_CTRL, ITS_SAVE_TABLES} command on +KVM device "kvm-arm-vgic-its" when dirty ring is enabled. + 8.30 KVM_CAP_XEN_HVM -------------------- diff --git a/Documentation/virt/kvm/devices/arm-vgic-its.rst b/Documentation/virt/kvm/devices/arm-vgic-its.rst index d257eddbae29..e053124f77c4 100644 --- a/Documentation/virt/kvm/devices/arm-vgic-its.rst +++ b/Documentation/virt/kvm/devices/arm-vgic-its.rst @@ -52,7 +52,10 @@ KVM_DEV_ARM_VGIC_GRP_CTRL KVM_DEV_ARM_ITS_SAVE_TABLES save the ITS table data into guest RAM, at the location provisioned - by the guest in corresponding registers/table entries. + by the guest in corresponding registers/table entries. Should userspace + require a form of dirty tracking to identify which pages are modified + by the saving process, it should use a bitmap even if using another + mechanism to track the memory dirtied by the vCPUs. The layout of the tables in guest memory defines an ABI. The entries are laid out in little endian format as described in the last paragraph. diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h index 199ead37b104..4862c98d80d3 100644 --- a/include/linux/kvm_dirty_ring.h +++ b/include/linux/kvm_dirty_ring.h @@ -37,6 +37,11 @@ static inline u32 kvm_dirty_ring_get_rsvd_entries(void) return 0; } +static inline bool kvm_use_dirty_bitmap(struct kvm *kvm) +{ + return true; +} + static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size) { @@ -67,6 +72,8 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring) #else /* CONFIG_HAVE_KVM_DIRTY_RING */ int kvm_cpu_dirty_log_size(void); +bool kvm_use_dirty_bitmap(struct kvm *kvm); +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm); u32 kvm_dirty_ring_get_rsvd_entries(void); int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 648d663f32c4..db83f63f4e61 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -779,6 +779,7 @@ struct kvm { pid_t userspace_pid; unsigned int max_halt_poll_ns; u32 dirty_ring_size; + bool dirty_ring_with_bitmap; bool vm_bugged; bool vm_dead; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0d5d4419139a..c87b5882d7ae 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1178,6 +1178,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_ZPCI_OP 221 #define KVM_CAP_S390_CPU_TOPOLOGY 222 #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 +#define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 224 #ifdef KVM_CAP_IRQ_ROUTING diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 800f9470e36b..9fb1ff6f19e5 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -33,6 +33,12 @@ config HAVE_KVM_DIRTY_RING_ACQ_REL bool select HAVE_KVM_DIRTY_RING +# Allow enabling both the dirty bitmap and dirty ring. Only architectures +# that need to dirty memory outside of a vCPU context should select this. +config NEED_KVM_DIRTY_RING_WITH_BITMAP + bool + depends on HAVE_KVM_DIRTY_RING + config HAVE_KVM_EVENTFD bool select EVENTFD diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c index fecbb7d75ad2..c1cd7dfe4a90 100644 --- a/virt/kvm/dirty_ring.c +++ b/virt/kvm/dirty_ring.c @@ -21,6 +21,20 @@ u32 kvm_dirty_ring_get_rsvd_entries(void) return KVM_DIRTY_RING_RSVD_ENTRIES + kvm_cpu_dirty_log_size(); } +bool kvm_use_dirty_bitmap(struct kvm *kvm) +{ + lockdep_assert_held(&kvm->slots_lock); + + return !kvm->dirty_ring_size || kvm->dirty_ring_with_bitmap; +} + +#ifndef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP +bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm) +{ + return false; +} +#endif + static u32 kvm_dirty_ring_used(struct kvm_dirty_ring *ring) { return READ_ONCE(ring->dirty_index) - READ_ONCE(ring->reset_index); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 04b22d2f99d8..be40d1ce6e91 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1617,7 +1617,7 @@ static int kvm_prepare_memory_region(struct kvm *kvm, new->dirty_bitmap = NULL; else if (old && old->dirty_bitmap) new->dirty_bitmap = old->dirty_bitmap; - else if (!kvm->dirty_ring_size) { + else if (kvm_use_dirty_bitmap(kvm)) { r = kvm_alloc_dirty_bitmap(new); if (r) return r; @@ -2060,8 +2060,8 @@ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, unsigned long n; unsigned long any = 0; - /* Dirty ring tracking is exclusive to dirty log tracking */ - if (kvm->dirty_ring_size) + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; *memslot = NULL; @@ -2125,8 +2125,8 @@ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) unsigned long *dirty_bitmap_buffer; bool flush; - /* Dirty ring tracking is exclusive to dirty log tracking */ - if (kvm->dirty_ring_size) + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; @@ -2237,8 +2237,8 @@ static int kvm_clear_dirty_log_protect(struct kvm *kvm, unsigned long *dirty_bitmap_buffer; bool flush; - /* Dirty ring tracking is exclusive to dirty log tracking */ - if (kvm->dirty_ring_size) + /* Dirty ring tracking may be exclusive to dirty log tracking */ + if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; @@ -3305,7 +3305,10 @@ void mark_page_dirty_in_slot(struct kvm *kvm, struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); #ifdef CONFIG_HAVE_KVM_DIRTY_RING - if (WARN_ON_ONCE(!vcpu) || WARN_ON_ONCE(vcpu->kvm != kvm)) + if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm)) + return; + + if (WARN_ON_ONCE(!kvm_arch_allow_write_without_running_vcpu(kvm) && !vcpu)) return; #endif @@ -3313,7 +3316,7 @@ void mark_page_dirty_in_slot(struct kvm *kvm, unsigned long rel_gfn = gfn - memslot->base_gfn; u32 slot = (memslot->as_id << 16) | memslot->id; - if (kvm->dirty_ring_size) + if (kvm->dirty_ring_size && vcpu) kvm_dirty_ring_push(vcpu, slot, rel_gfn); else set_bit_le(rel_gfn, memslot->dirty_bitmap); @@ -4482,6 +4485,9 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; +#endif +#ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP + case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: #endif case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: @@ -4558,6 +4564,20 @@ int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, return -EINVAL; } +static bool kvm_are_all_memslots_empty(struct kvm *kvm) +{ + int i; + + lockdep_assert_held(&kvm->slots_lock); + + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) + return false; + } + + return true; +} + static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) { @@ -4588,6 +4608,29 @@ static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, return -EINVAL; return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); + case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: { + int r = -EINVAL; + + if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) || + !kvm->dirty_ring_size || cap->flags) + return r; + + mutex_lock(&kvm->slots_lock); + + /* + * For simplicity, allow enabling ring+bitmap if and only if + * there are no memslots, e.g. to ensure all memslots allocate + * a bitmap after the capability is enabled. + */ + if (kvm_are_all_memslots_empty(kvm)) { + kvm->dirty_ring_with_bitmap = true; + r = 0; + } + + mutex_unlock(&kvm->slots_lock); + + return r; + } default: return kvm_vm_ioctl_enable_cap(kvm, cap); } -- cgit From 9bb053490f1a5a0914eb9f7b4116a0e4a95d4f8e Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 7 Nov 2022 15:04:18 -0800 Subject: bpf: Add hwtstamp field for the sockops prog The bpf-tc prog has already been able to access the skb_hwtstamps(skb)->hwtstamp. This patch extends the same hwtstamp access to the sockops prog. In sockops, the skb is also available to the bpf prog during the BPF_SOCK_OPS_PARSE_HDR_OPT_CB event. There is a use case that the hwtstamp will be useful to the sockops prog to better measure the one-way-delay when the sender has put the tx timestamp in the tcp header option. Signed-off-by: Martin KaFai Lau Signed-off-by: Andrii Nakryiko Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20221107230420.4192307-2-martin.lau@linux.dev --- include/uapi/linux/bpf.h | 1 + net/core/filter.c | 39 +++++++++++++++++++++++++++++++-------- tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 33 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 94659f6b3395..fb4c911d2a03 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6445,6 +6445,7 @@ struct bpf_sock_ops { * the outgoing header has not * been written yet. */ + __u64 skb_hwtstamp; }; /* Definitions for bpf_sock_ops_cb_flags */ diff --git a/net/core/filter.c b/net/core/filter.c index cb3b635e35be..cd667cdbdb26 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -8925,6 +8925,10 @@ static bool sock_ops_is_valid_access(int off, int size, bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); + case offsetof(struct bpf_sock_ops, skb_hwtstamp): + if (size != sizeof(__u64)) + return false; + break; default: if (size != size_default) return false; @@ -9108,21 +9112,21 @@ static struct bpf_insn *bpf_convert_tstamp_type_read(const struct bpf_insn *si, return insn; } -static struct bpf_insn *bpf_convert_shinfo_access(const struct bpf_insn *si, +static struct bpf_insn *bpf_convert_shinfo_access(__u8 dst_reg, __u8 skb_reg, struct bpf_insn *insn) { /* si->dst_reg = skb_shinfo(SKB); */ #ifdef NET_SKBUFF_DATA_USES_OFFSET *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - BPF_REG_AX, si->src_reg, + BPF_REG_AX, skb_reg, offsetof(struct sk_buff, end)); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), - si->dst_reg, si->src_reg, + dst_reg, skb_reg, offsetof(struct sk_buff, head)); - *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); + *insn++ = BPF_ALU64_REG(BPF_ADD, dst_reg, BPF_REG_AX); #else *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), - si->dst_reg, si->src_reg, + dst_reg, skb_reg, offsetof(struct sk_buff, end)); #endif @@ -9515,7 +9519,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct __sk_buff, gso_segs): - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -9523,7 +9527,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; case offsetof(struct __sk_buff, gso_size): - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_size), si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -9550,7 +9554,7 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); - insn = bpf_convert_shinfo_access(si, insn); + insn = bpf_convert_shinfo_access(si->dst_reg, si->src_reg, insn); *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, bpf_target_off(struct skb_shared_info, @@ -10400,6 +10404,25 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, tcp_flags), si->dst_reg, si->dst_reg, off); break; + case offsetof(struct bpf_sock_ops, skb_hwtstamp): { + struct bpf_insn *jmp_on_null_skb; + + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + /* Reserve one insn to test skb == NULL */ + jmp_on_null_skb = insn++; + insn = bpf_convert_shinfo_access(si->dst_reg, si->dst_reg, insn); + *insn++ = BPF_LDX_MEM(BPF_DW, si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + hwtstamps, 8, + target_size)); + *jmp_on_null_skb = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, + insn - jmp_on_null_skb - 1); + break; + } } return insn - insn_buf; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 94659f6b3395..fb4c911d2a03 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6445,6 +6445,7 @@ struct bpf_sock_ops { * the outgoing header has not * been written yet. */ + __u64 skb_hwtstamp; }; /* Definitions for bpf_sock_ops_cb_flags */ -- cgit From dc901d98b1fe6e52ab81cd3e0879379168e06daa Mon Sep 17 00:00:00 2001 From: Fenghua Yu Date: Thu, 10 Nov 2022 17:27:15 -0800 Subject: dmaengine: idxd: Fix crc_val field for completion record The crc_val in the completion record should be 64 bits and not 32 bits. Fixes: 4ac823e9cd85 ("dmaengine: idxd: fix delta_rec and crc size field for completion record") Reported-by: Nirav N Shah Signed-off-by: Fenghua Yu Reviewed-by: Dave Jiang Link: https://lore.kernel.org/r/20221111012715.2031481-1-fenghua.yu@intel.com Signed-off-by: Vinod Koul --- include/uapi/linux/idxd.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/idxd.h b/include/uapi/linux/idxd.h index 2b9e7feba3f3..1d553bedbdb5 100644 --- a/include/uapi/linux/idxd.h +++ b/include/uapi/linux/idxd.h @@ -295,7 +295,7 @@ struct dsa_completion_record { }; uint32_t delta_rec_size; - uint32_t crc_val; + uint64_t crc_val; /* DIF check & strip */ struct { -- cgit From 487d828d751d90cf9ca594f45b02dd0e0d712b64 Mon Sep 17 00:00:00 2001 From: Ira Weiny Date: Mon, 26 Sep 2022 14:57:11 -0700 Subject: cxl/doe: Request exclusive DOE access The PCIE Data Object Exchange (DOE) mailbox is a protocol run over configuration cycles. It assumes one initiator at a time. While the kernel has control of the mailbox user space writes could interfere with the kernel access. Mark DOE mailbox config space exclusive when iterated by the CXL driver. Signed-off-by: Ira Weiny Reviewed-by: Jonathan Cameron Link: https://lore.kernel.org/r/20220926215711.2893286-3-ira.weiny@intel.com Signed-off-by: Dan Williams --- drivers/cxl/pci.c | 5 +++++ include/uapi/linux/pci_regs.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/pci.c b/drivers/cxl/pci.c index faeb5d9d7a7a..621a0522b554 100644 --- a/drivers/cxl/pci.c +++ b/drivers/cxl/pci.c @@ -418,6 +418,11 @@ static void devm_cxl_pci_create_doe(struct cxl_dev_state *cxlds) continue; } + if (!pci_request_config_region_exclusive(pdev, off, + PCI_DOE_CAP_SIZEOF, + dev_name(dev))) + pci_err(pdev, "Failed to exclude DOE registers\n"); + if (xa_insert(&cxlds->doe_mbs, off, doe_mb, GFP_KERNEL)) { dev_err(dev, "xa_insert failed to insert MB @ %x\n", off); diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 57b8e2ffb1dd..82a03ea954af 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -1119,6 +1119,7 @@ #define PCI_DOE_STATUS_DATA_OBJECT_READY 0x80000000 /* Data Object Ready */ #define PCI_DOE_WRITE 0x10 /* DOE Write Data Mailbox Register */ #define PCI_DOE_READ 0x14 /* DOE Read Data Mailbox Register */ +#define PCI_DOE_CAP_SIZEOF 0x18 /* Size of DOE register block */ /* DOE Data Object - note not actually registers */ #define PCI_DOE_DATA_OBJECT_HEADER_1_VID 0x0000ffff -- cgit From 4e016f969529f2aec0545e90119e7eb3cb124c46 Mon Sep 17 00:00:00 2001 From: Yishai Hadas Date: Sun, 6 Nov 2022 19:46:18 +0200 Subject: vfio: Add an option to get migration data size Add an option to get migration data size by introducing a new migration feature named VFIO_DEVICE_FEATURE_MIG_DATA_SIZE. Upon VFIO_DEVICE_FEATURE_GET the estimated data length that will be required to complete STOP_COPY is returned. This option may better enable user space to consider before moving to STOP_COPY whether it can meet the downtime SLA based on the returned data. The patch also includes the implementation for mlx5 and hisi for this new option to make it feature complete for the existing drivers in this area. Signed-off-by: Yishai Hadas Reviewed-by: Jason Gunthorpe Reviewed-by: Longfang Liu Link: https://lore.kernel.org/r/20221106174630.25909-2-yishaih@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c | 9 ++++++++ drivers/vfio/pci/mlx5/main.c | 18 +++++++++++++++ drivers/vfio/pci/vfio_pci_core.c | 3 ++- drivers/vfio/vfio_main.c | 32 ++++++++++++++++++++++++++ include/linux/vfio.h | 5 ++++ include/uapi/linux/vfio.h | 13 +++++++++++ 6 files changed, 79 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c index 39eeca18a0f7..0c0c0c7f0521 100644 --- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c +++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c @@ -957,6 +957,14 @@ hisi_acc_vfio_pci_set_device_state(struct vfio_device *vdev, return res; } +static int +hisi_acc_vfio_pci_get_data_size(struct vfio_device *vdev, + unsigned long *stop_copy_length) +{ + *stop_copy_length = sizeof(struct acc_vf_data); + return 0; +} + static int hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev, enum vfio_device_mig_state *curr_state) @@ -1213,6 +1221,7 @@ static void hisi_acc_vfio_pci_close_device(struct vfio_device *core_vdev) static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = { .migration_set_state = hisi_acc_vfio_pci_set_device_state, .migration_get_state = hisi_acc_vfio_pci_get_device_state, + .migration_get_data_size = hisi_acc_vfio_pci_get_data_size, }; static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev) diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c index 457138b92f13..6e9cf2aacc52 100644 --- a/drivers/vfio/pci/mlx5/main.c +++ b/drivers/vfio/pci/mlx5/main.c @@ -512,6 +512,23 @@ mlx5vf_pci_set_device_state(struct vfio_device *vdev, return res; } +static int mlx5vf_pci_get_data_size(struct vfio_device *vdev, + unsigned long *stop_copy_length) +{ + struct mlx5vf_pci_core_device *mvdev = container_of( + vdev, struct mlx5vf_pci_core_device, core_device.vdev); + size_t state_size; + int ret; + + mutex_lock(&mvdev->state_mutex); + ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, + &state_size); + if (!ret) + *stop_copy_length = state_size; + mlx5vf_state_mutex_unlock(mvdev); + return ret; +} + static int mlx5vf_pci_get_device_state(struct vfio_device *vdev, enum vfio_device_mig_state *curr_state) { @@ -577,6 +594,7 @@ static void mlx5vf_pci_close_device(struct vfio_device *core_vdev) static const struct vfio_migration_ops mlx5vf_pci_mig_ops = { .migration_set_state = mlx5vf_pci_set_device_state, .migration_get_state = mlx5vf_pci_get_device_state, + .migration_get_data_size = mlx5vf_pci_get_data_size, }; static const struct vfio_log_ops mlx5vf_pci_log_ops = { diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 9be2d5be5d95..189d4930c276 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -2127,7 +2127,8 @@ int vfio_pci_core_register_device(struct vfio_pci_core_device *vdev) if (vdev->vdev.mig_ops) { if (!(vdev->vdev.mig_ops->migration_get_state && - vdev->vdev.mig_ops->migration_set_state) || + vdev->vdev.mig_ops->migration_set_state && + vdev->vdev.mig_ops->migration_get_data_size) || !(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY)) return -EINVAL; } diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 9835757e2bee..662e267a3e13 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1242,6 +1242,34 @@ out_copy: return 0; } +static int +vfio_ioctl_device_feature_migration_data_size(struct vfio_device *device, + u32 flags, void __user *arg, + size_t argsz) +{ + struct vfio_device_feature_mig_data_size data_size = {}; + unsigned long stop_copy_length; + int ret; + + if (!device->mig_ops) + return -ENOTTY; + + ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET, + sizeof(data_size)); + if (ret != 1) + return ret; + + ret = device->mig_ops->migration_get_data_size(device, &stop_copy_length); + if (ret) + return ret; + + data_size.stop_copy_length = stop_copy_length; + if (copy_to_user(arg, &data_size, sizeof(data_size))) + return -EFAULT; + + return 0; +} + static int vfio_ioctl_device_feature_migration(struct vfio_device *device, u32 flags, void __user *arg, size_t argsz) @@ -1469,6 +1497,10 @@ static int vfio_ioctl_device_feature(struct vfio_device *device, return vfio_ioctl_device_feature_logging_report( device, feature.flags, arg->data, feature.argsz - minsz); + case VFIO_DEVICE_FEATURE_MIG_DATA_SIZE: + return vfio_ioctl_device_feature_migration_data_size( + device, feature.flags, arg->data, + feature.argsz - minsz); default: if (unlikely(!device->ops->device_feature)) return -EINVAL; diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e7480154825e..43b67e46a2cb 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -107,6 +107,9 @@ struct vfio_device_ops { * @migration_get_state: Optional callback to get the migration state for * devices that support migration. It's mandatory for * VFIO_DEVICE_FEATURE_MIGRATION migration support. + * @migration_get_data_size: Optional callback to get the estimated data + * length that will be required to complete stop copy. It's mandatory for + * VFIO_DEVICE_FEATURE_MIGRATION migration support. */ struct vfio_migration_ops { struct file *(*migration_set_state)( @@ -114,6 +117,8 @@ struct vfio_migration_ops { enum vfio_device_mig_state new_state); int (*migration_get_state)(struct vfio_device *device, enum vfio_device_mig_state *curr_state); + int (*migration_get_data_size)(struct vfio_device *device, + unsigned long *stop_copy_length); }; /** diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index d7d8e0922376..3e45dbaf190e 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -1128,6 +1128,19 @@ struct vfio_device_feature_dma_logging_report { #define VFIO_DEVICE_FEATURE_DMA_LOGGING_REPORT 8 +/* + * Upon VFIO_DEVICE_FEATURE_GET read back the estimated data length that will + * be required to complete stop copy. + * + * Note: Can be called on each device state. + */ + +struct vfio_device_feature_mig_data_size { + __aligned_u64 stop_copy_length; +}; + +#define VFIO_DEVICE_FEATURE_MIG_DATA_SIZE 9 + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit From f0c5941ff5b255413d31425bb327c2aec3625673 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Tue, 15 Nov 2022 00:45:25 +0530 Subject: bpf: Support bpf_list_head in map values Add the support on the map side to parse, recognize, verify, and build metadata table for a new special field of the type struct bpf_list_head. To parameterize the bpf_list_head for a certain value type and the list_node member it will accept in that value type, we use BTF declaration tags. The definition of bpf_list_head in a map value will be done as follows: struct foo { struct bpf_list_node node; int data; }; struct map_value { struct bpf_list_head head __contains(foo, node); }; Then, the bpf_list_head only allows adding to the list 'head' using the bpf_list_node 'node' for the type struct foo. The 'contains' annotation is a BTF declaration tag composed of four parts, "contains:name:node" where the name is then used to look up the type in the map BTF, with its kind hardcoded to BTF_KIND_STRUCT during the lookup. The node defines name of the member in this type that has the type struct bpf_list_node, which is actually used for linking into the linked list. For now, 'kind' part is hardcoded as struct. This allows building intrusive linked lists in BPF, using container_of to obtain pointer to entry, while being completely type safe from the perspective of the verifier. The verifier knows exactly the type of the nodes, and knows that list helpers return that type at some fixed offset where the bpf_list_node member used for this list exists. The verifier also uses this information to disallow adding types that are not accepted by a certain list. For now, no elements can be added to such lists. Support for that is coming in future patches, hence draining and freeing items is done with a TODO that will be resolved in a future patch. Note that the bpf_list_head_free function moves the list out to a local variable under the lock and releases it, doing the actual draining of the list items outside the lock. While this helps with not holding the lock for too long pessimizing other concurrent list operations, it is also necessary for deadlock prevention: unless every function called in the critical section would be notrace, a fentry/fexit program could attach and call bpf_map_update_elem again on the map, leading to the same lock being acquired if the key matches and lead to a deadlock. While this requires some special effort on part of the BPF programmer to trigger and is highly unlikely to occur in practice, it is always better if we can avoid such a condition. While notrace would prevent this, doing the draining outside the lock has advantages of its own, hence it is used to also fix the deadlock related problem. Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221114191547.1694267-5-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 17 +++++ include/uapi/linux/bpf.h | 10 +++ kernel/bpf/btf.c | 145 ++++++++++++++++++++++++++++++++++++++++- kernel/bpf/helpers.c | 32 +++++++++ kernel/bpf/syscall.c | 22 ++++++- kernel/bpf/verifier.c | 7 ++ tools/include/uapi/linux/bpf.h | 10 +++ 7 files changed, 239 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index f08eb2d27de0..05f98e9e5c48 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -175,6 +175,7 @@ enum btf_field_type { BPF_KPTR_UNREF = (1 << 2), BPF_KPTR_REF = (1 << 3), BPF_KPTR = BPF_KPTR_UNREF | BPF_KPTR_REF, + BPF_LIST_HEAD = (1 << 4), }; struct btf_field_kptr { @@ -184,11 +185,18 @@ struct btf_field_kptr { u32 btf_id; }; +struct btf_field_list_head { + struct btf *btf; + u32 value_btf_id; + u32 node_offset; +}; + struct btf_field { u32 offset; enum btf_field_type type; union { struct btf_field_kptr kptr; + struct btf_field_list_head list_head; }; }; @@ -266,6 +274,8 @@ 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_LIST_HEAD: + return "bpf_list_head"; default: WARN_ON_ONCE(1); return "unknown"; @@ -282,6 +292,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return sizeof(u64); + case BPF_LIST_HEAD: + return sizeof(struct bpf_list_head); default: WARN_ON_ONCE(1); return 0; @@ -298,6 +310,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type) case BPF_KPTR_UNREF: case BPF_KPTR_REF: return __alignof__(u64); + case BPF_LIST_HEAD: + return __alignof__(struct bpf_list_head); default: WARN_ON_ONCE(1); return 0; @@ -403,6 +417,9 @@ static inline void zero_map_value(struct bpf_map *map, void *dst) void copy_map_value_locked(struct bpf_map *map, void *dst, void *src, bool lock_src); void bpf_timer_cancel_and_free(void *timer); +void bpf_list_head_free(const struct btf_field *field, void *list_head, + struct bpf_spin_lock *spin_lock); + int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size); struct bpf_offload_dev; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index fb4c911d2a03..6580448e9f77 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -6888,6 +6888,16 @@ struct bpf_dynptr { __u64 :64; } __attribute__((aligned(8))); +struct bpf_list_head { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 12361d7b2498..c0d73d71c539 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -3205,9 +3205,15 @@ enum { struct btf_field_info { enum btf_field_type type; u32 off; - struct { - u32 type_id; - } kptr; + union { + struct { + u32 type_id; + } kptr; + struct { + const char *node_name; + u32 value_btf_id; + } list_head; + }; }; static int btf_find_struct(const struct btf *btf, const struct btf_type *t, @@ -3261,6 +3267,63 @@ static int btf_find_kptr(const struct btf *btf, const struct btf_type *t, return BTF_FIELD_FOUND; } +static const char *btf_find_decl_tag_value(const struct btf *btf, + const struct btf_type *pt, + int comp_idx, const char *tag_key) +{ + int i; + + for (i = 1; i < btf_nr_types(btf); i++) { + const struct btf_type *t = btf_type_by_id(btf, i); + int len = strlen(tag_key); + + if (!btf_type_is_decl_tag(t)) + continue; + if (pt != btf_type_by_id(btf, t->type) || + btf_type_decl_tag(t)->component_idx != comp_idx) + continue; + if (strncmp(__btf_name_by_offset(btf, t->name_off), tag_key, len)) + continue; + return __btf_name_by_offset(btf, t->name_off) + len; + } + return NULL; +} + +static int btf_find_list_head(const struct btf *btf, const struct btf_type *pt, + const struct btf_type *t, int comp_idx, + u32 off, int sz, struct btf_field_info *info) +{ + const char *value_type; + const char *list_node; + s32 id; + + if (!__btf_type_is_struct(t)) + return BTF_FIELD_IGNORE; + if (t->size != sz) + return BTF_FIELD_IGNORE; + value_type = btf_find_decl_tag_value(btf, pt, comp_idx, "contains:"); + if (!value_type) + return -EINVAL; + list_node = strstr(value_type, ":"); + if (!list_node) + return -EINVAL; + value_type = kstrndup(value_type, list_node - value_type, GFP_KERNEL | __GFP_NOWARN); + if (!value_type) + return -ENOMEM; + id = btf_find_by_name_kind(btf, value_type, BTF_KIND_STRUCT); + kfree(value_type); + if (id < 0) + return id; + list_node++; + if (str_is_empty(list_node)) + return -EINVAL; + info->type = BPF_LIST_HEAD; + info->off = off; + info->list_head.value_btf_id = id; + info->list_head.node_name = list_node; + return BTF_FIELD_FOUND; +} + static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, int *align, int *sz) { @@ -3284,6 +3347,12 @@ static int btf_get_field_type(const char *name, u32 field_mask, u32 *seen_mask, goto end; } } + if (field_mask & BPF_LIST_HEAD) { + if (!strcmp(name, "bpf_list_head")) { + type = BPF_LIST_HEAD; + goto end; + } + } /* Only return BPF_KPTR when all other types with matchable names fail */ if (field_mask & BPF_KPTR) { type = BPF_KPTR_REF; @@ -3339,6 +3408,12 @@ static int btf_find_struct_field(const struct btf *btf, if (ret < 0) return ret; break; + case BPF_LIST_HEAD: + ret = btf_find_list_head(btf, t, member_type, i, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; default: return -EFAULT; } @@ -3393,6 +3468,12 @@ static int btf_find_datasec_var(const struct btf *btf, const struct btf_type *t, if (ret < 0) return ret; break; + case BPF_LIST_HEAD: + ret = btf_find_list_head(btf, var, var_type, -1, off, sz, + idx < info_cnt ? &info[idx] : &tmp); + if (ret < 0) + return ret; + break; default: return -EFAULT; } @@ -3491,11 +3572,52 @@ end_btf: return ret; } +static int btf_parse_list_head(const struct btf *btf, struct btf_field *field, + struct btf_field_info *info) +{ + const struct btf_type *t, *n = NULL; + const struct btf_member *member; + u32 offset; + int i; + + t = btf_type_by_id(btf, info->list_head.value_btf_id); + /* We've already checked that value_btf_id is a struct type. We + * just need to figure out the offset of the list_node, and + * verify its type. + */ + for_each_member(i, t, member) { + if (strcmp(info->list_head.node_name, __btf_name_by_offset(btf, member->name_off))) + continue; + /* Invalid BTF, two members with same name */ + if (n) + return -EINVAL; + n = btf_type_by_id(btf, member->type); + if (!__btf_type_is_struct(n)) + return -EINVAL; + if (strcmp("bpf_list_node", __btf_name_by_offset(btf, n->name_off))) + return -EINVAL; + offset = __btf_member_bit_offset(n, member); + if (offset % 8) + return -EINVAL; + offset /= 8; + if (offset % __alignof__(struct bpf_list_node)) + return -EINVAL; + + field->list_head.btf = (struct btf *)btf; + field->list_head.value_btf_id = info->list_head.value_btf_id; + field->list_head.node_offset = offset; + } + if (!n) + return -ENOENT; + return 0; +} + struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t, u32 field_mask, u32 value_size) { struct btf_field_info info_arr[BTF_FIELDS_MAX]; struct btf_record *rec; + u32 next_off = 0; int ret, i, cnt; ret = btf_find_field(btf, t, field_mask, info_arr, ARRAY_SIZE(info_arr)); @@ -3517,6 +3639,11 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type ret = -EFAULT; goto end; } + if (info_arr[i].off < next_off) { + ret = -EEXIST; + goto end; + } + next_off = info_arr[i].off + btf_field_type_size(info_arr[i].type); rec->field_mask |= info_arr[i].type; rec->fields[i].offset = info_arr[i].off; @@ -3539,12 +3666,24 @@ struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type if (ret < 0) goto end; break; + case BPF_LIST_HEAD: + ret = btf_parse_list_head(btf, &rec->fields[i], &info_arr[i]); + if (ret < 0) + goto end; + break; default: ret = -EFAULT; goto end; } rec->cnt++; } + + /* bpf_list_head requires bpf_spin_lock */ + if (btf_record_has_field(rec, BPF_LIST_HEAD) && rec->spin_lock_off < 0) { + ret = -EINVAL; + goto end; + } + return rec; end: btf_record_free(rec); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 283f55bbeb70..7bc71995f17c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1706,6 +1706,38 @@ bpf_base_func_proto(enum bpf_func_id func_id) } } +void bpf_list_head_free(const struct btf_field *field, void *list_head, + struct bpf_spin_lock *spin_lock) +{ + struct list_head *head = list_head, *orig_head = list_head; + + BUILD_BUG_ON(sizeof(struct list_head) > sizeof(struct bpf_list_head)); + BUILD_BUG_ON(__alignof__(struct list_head) > __alignof__(struct bpf_list_head)); + + /* Do the actual list draining outside the lock to not hold the lock for + * too long, and also prevent deadlocks if tracing programs end up + * executing on entry/exit of functions called inside the critical + * section, and end up doing map ops that call bpf_list_head_free for + * the same map value again. + */ + __bpf_spin_lock_irqsave(spin_lock); + if (!head->next || list_empty(head)) + goto unlock; + head = head->next; +unlock: + INIT_LIST_HEAD(orig_head); + __bpf_spin_unlock_irqrestore(spin_lock); + + while (head != orig_head) { + void *obj = head; + + obj -= field->list_head.node_offset; + head = head->next; + /* TODO: Rework later */ + kfree(obj); + } +} + BTF_SET8_START(tracing_btf_ids) #ifdef CONFIG_KEXEC_CORE BTF_ID_FLAGS(func, crash_kexec, KF_DESTRUCTIVE) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 85532d301124..fdbae52f463f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -536,6 +536,9 @@ void btf_record_free(struct btf_record *rec) module_put(rec->fields[i].kptr.module); btf_put(rec->fields[i].kptr.btf); break; + case BPF_LIST_HEAD: + /* Nothing to release for bpf_list_head */ + break; default: WARN_ON_ONCE(1); continue; @@ -578,6 +581,9 @@ struct btf_record *btf_record_dup(const struct btf_record *rec) goto free; } break; + case BPF_LIST_HEAD: + /* Nothing to acquire for bpf_list_head */ + break; default: ret = -EFAULT; WARN_ON_ONCE(1); @@ -637,6 +643,11 @@ void bpf_obj_free_fields(const struct btf_record *rec, void *obj) case BPF_KPTR_REF: field->kptr.dtor((void *)xchg((unsigned long *)field_ptr, 0)); break; + case BPF_LIST_HEAD: + if (WARN_ON_ONCE(rec->spin_lock_off < 0)) + continue; + bpf_list_head_free(field, field_ptr, obj + rec->spin_lock_off); + break; default: WARN_ON_ONCE(1); continue; @@ -965,7 +976,8 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, if (!value_type || value_size != map->value_size) return -EINVAL; - map->record = btf_parse_fields(btf, value_type, BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR, + map->record = btf_parse_fields(btf, value_type, + BPF_SPIN_LOCK | BPF_TIMER | BPF_KPTR | BPF_LIST_HEAD, map->value_size); if (!IS_ERR_OR_NULL(map->record)) { int i; @@ -1012,6 +1024,14 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, goto free_map_tab; } break; + case BPF_LIST_HEAD: + if (map->map_type != BPF_MAP_TYPE_HASH && + map->map_type != BPF_MAP_TYPE_LRU_HASH && + map->map_type != BPF_MAP_TYPE_ARRAY) { + ret = -EOPNOTSUPP; + goto free_map_tab; + } + break; default: /* Fail if map_type checks are missing for a field type */ ret = -EOPNOTSUPP; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 07c0259dfc1a..a50018e2d4a0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -12814,6 +12814,13 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, { enum bpf_prog_type prog_type = resolve_prog_type(prog); + if (btf_record_has_field(map->record, BPF_LIST_HEAD)) { + if (is_tracing_prog_type(prog_type)) { + verbose(env, "tracing progs cannot use bpf_list_head yet\n"); + return -EINVAL; + } + } + if (btf_record_has_field(map->record, BPF_SPIN_LOCK)) { if (prog_type == BPF_PROG_TYPE_SOCKET_FILTER) { verbose(env, "socket filter progs cannot use bpf_spin_lock yet\n"); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index fb4c911d2a03..6580448e9f77 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -6888,6 +6888,16 @@ struct bpf_dynptr { __u64 :64; } __attribute__((aligned(8))); +struct bpf_list_head { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + +struct bpf_list_node { + __u64 :64; + __u64 :64; +} __attribute__((aligned(8))); + struct bpf_sysctl { __u32 write; /* Sysctl is being read (= 0) or written (= 1). * Allows 1,2,4-byte read, but no write. -- cgit From 8daa8fde3fc3f069ff0b5c87079a5c1df7743113 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Fri, 14 Oct 2022 23:45:59 +0200 Subject: netfilter: nf_tables: Introduce NFT_MSG_GETRULE_RESET Analogous to NFT_MSG_GETOBJ_RESET, but for rules: Reset stateful expressions like counters or quotas. The latter two are the only consumers, adjust their 'dump' callbacks to respect the parameter introduced earlier. Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nf_tables_api.c | 49 +++++++++++++++++++++----------- net/netfilter/nft_counter.c | 2 +- net/netfilter/nft_dynset.c | 4 +-- net/netfilter/nft_inner.c | 2 +- net/netfilter/nft_quota.c | 2 +- 7 files changed, 41 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index c557a57fb0f1..e69ce23566ea 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -383,7 +383,7 @@ int nft_expr_inner_parse(const struct nft_ctx *ctx, const struct nlattr *nla, int nft_expr_clone(struct nft_expr *dst, struct nft_expr *src); void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr); int nft_expr_dump(struct sk_buff *skb, unsigned int attr, - const struct nft_expr *expr); + const struct nft_expr *expr, bool reset); bool nft_expr_reduce_bitwise(struct nft_regs_track *track, const struct nft_expr *expr); diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e4b739d57480..cfa844da1ce6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -97,6 +97,7 @@ enum nft_verdicts { * @NFT_MSG_NEWFLOWTABLE: add new flow table (enum nft_flowtable_attributes) * @NFT_MSG_GETFLOWTABLE: get flow table (enum nft_flowtable_attributes) * @NFT_MSG_DELFLOWTABLE: delete flow table (enum nft_flowtable_attributes) + * @NFT_MSG_GETRULE_RESET: get rules and reset stateful expressions (enum nft_obj_attributes) */ enum nf_tables_msg_types { NFT_MSG_NEWTABLE, @@ -124,6 +125,7 @@ enum nf_tables_msg_types { NFT_MSG_NEWFLOWTABLE, NFT_MSG_GETFLOWTABLE, NFT_MSG_DELFLOWTABLE, + NFT_MSG_GETRULE_RESET, NFT_MSG_MAX, }; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 741a0e386406..80e613405f6f 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2759,7 +2759,7 @@ static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = { }; static int nf_tables_fill_expr_info(struct sk_buff *skb, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { if (nla_put_string(skb, NFTA_EXPR_NAME, expr->ops->type->name)) goto nla_put_failure; @@ -2769,7 +2769,7 @@ static int nf_tables_fill_expr_info(struct sk_buff *skb, NFTA_EXPR_DATA); if (data == NULL) goto nla_put_failure; - if (expr->ops->dump(skb, expr, false) < 0) + if (expr->ops->dump(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, data); } @@ -2781,14 +2781,14 @@ nla_put_failure: }; int nft_expr_dump(struct sk_buff *skb, unsigned int attr, - const struct nft_expr *expr) + const struct nft_expr *expr, bool reset) { struct nlattr *nest; nest = nla_nest_start_noflag(skb, attr); if (!nest) goto nla_put_failure; - if (nf_tables_fill_expr_info(skb, expr) < 0) + if (nf_tables_fill_expr_info(skb, expr, reset) < 0) goto nla_put_failure; nla_nest_end(skb, nest); return 0; @@ -3034,7 +3034,8 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, u32 flags, int family, const struct nft_table *table, const struct nft_chain *chain, - const struct nft_rule *rule, u64 handle) + const struct nft_rule *rule, u64 handle, + bool reset) { struct nlmsghdr *nlh; const struct nft_expr *expr, *next; @@ -3067,7 +3068,7 @@ static int nf_tables_fill_rule_info(struct sk_buff *skb, struct net *net, if (list == NULL) goto nla_put_failure; nft_rule_for_each_expr(expr, next, rule) { - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, reset) < 0) goto nla_put_failure; } nla_nest_end(skb, list); @@ -3118,7 +3119,7 @@ static void nf_tables_rule_notify(const struct nft_ctx *ctx, err = nf_tables_fill_rule_info(skb, ctx->net, ctx->portid, ctx->seq, event, flags, ctx->family, ctx->table, - ctx->chain, rule, handle); + ctx->chain, rule, handle, false); if (err < 0) { kfree_skb(skb); goto err; @@ -3139,7 +3140,8 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, unsigned int *idx, struct netlink_callback *cb, const struct nft_table *table, - const struct nft_chain *chain) + const struct nft_chain *chain, + bool reset) { struct net *net = sock_net(skb->sk); const struct nft_rule *rule, *prule; @@ -3166,7 +3168,7 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NFT_MSG_NEWRULE, NLM_F_MULTI | NLM_F_APPEND, table->family, - table, chain, rule, handle) < 0) + table, chain, rule, handle, reset) < 0) return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); @@ -3189,6 +3191,10 @@ static int nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); int family = nfmsg->nfgen_family; struct nftables_pernet *nft_net; + bool reset = false; + + if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) + reset = true; rcu_read_lock(); nft_net = nft_pernet(net); @@ -3213,14 +3219,15 @@ static int nf_tables_dump_rules(struct sk_buff *skb, if (!nft_is_active(net, chain)) continue; __nf_tables_dump_rules(skb, &idx, - cb, table, chain); + cb, table, chain, reset); break; } goto done; } list_for_each_entry_rcu(chain, &table->chains, list) { - if (__nf_tables_dump_rules(skb, &idx, cb, table, chain)) + if (__nf_tables_dump_rules(skb, &idx, + cb, table, chain, reset)) goto done; } @@ -3291,6 +3298,7 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, struct net *net = info->net; struct nft_table *table; struct sk_buff *skb2; + bool reset = false; int err; if (info->nlh->nlmsg_flags & NLM_F_DUMP) { @@ -3327,9 +3335,12 @@ static int nf_tables_getrule(struct sk_buff *skb, const struct nfnl_info *info, if (!skb2) return -ENOMEM; + if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETRULE_RESET) + reset = true; + err = nf_tables_fill_rule_info(skb2, net, NETLINK_CB(skb).portid, info->nlh->nlmsg_seq, NFT_MSG_NEWRULE, 0, - family, table, chain, rule, 0); + family, table, chain, rule, 0, reset); if (err < 0) goto err_fill_rule_info; @@ -4104,7 +4115,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (set->num_exprs == 1) { nest = nla_nest_start_noflag(skb, NFTA_SET_EXPR); - if (nf_tables_fill_expr_info(skb, set->exprs[0]) < 0) + if (nf_tables_fill_expr_info(skb, set->exprs[0], false) < 0) goto nla_put_failure; nla_nest_end(skb, nest); @@ -4115,7 +4126,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, for (i = 0; i < set->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, - set->exprs[i]) < 0) + set->exprs[i], false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -4946,7 +4957,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, if (num_exprs == 1) { expr = nft_setelem_expr_at(elem_expr, 0); - if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr) < 0) + if (nft_expr_dump(skb, NFTA_SET_ELEM_EXPR, expr, false) < 0) return -1; return 0; @@ -4957,7 +4968,7 @@ static int nft_set_elem_expr_dump(struct sk_buff *skb, nft_setelem_expr_foreach(expr, elem_expr, size) { expr = nft_setelem_expr_at(elem_expr, size); - if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr) < 0) + if (nft_expr_dump(skb, NFTA_LIST_ELEM, expr, false) < 0) goto nla_put_failure; } nla_nest_end(skb, nest); @@ -8311,6 +8322,12 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = { .attr_count = NFTA_RULE_MAX, .policy = nft_rule_policy, }, + [NFT_MSG_GETRULE_RESET] = { + .call = nf_tables_getrule, + .type = NFNL_CB_RCU, + .attr_count = NFTA_RULE_MAX, + .policy = nft_rule_policy, + }, [NFT_MSG_DELRULE] = { .call = nf_tables_delrule, .type = NFNL_CB_BATCH, diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index 06482fb9c145..dccc68a5135a 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -206,7 +206,7 @@ static int nft_counter_dump(struct sk_buff *skb, { struct nft_counter_percpu_priv *priv = nft_expr_priv(expr); - return nft_counter_do_dump(skb, priv, false); + return nft_counter_do_dump(skb, priv, reset); } static int nft_counter_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 01c61e090639..274579b1696e 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -380,7 +380,7 @@ static int nft_dynset_dump(struct sk_buff *skb, if (priv->set->num_exprs == 0) { if (priv->num_exprs == 1) { if (nft_expr_dump(skb, NFTA_DYNSET_EXPR, - priv->expr_array[0])) + priv->expr_array[0], reset)) goto nla_put_failure; } else if (priv->num_exprs > 1) { struct nlattr *nest; @@ -391,7 +391,7 @@ static int nft_dynset_dump(struct sk_buff *skb, for (i = 0; i < priv->num_exprs; i++) { if (nft_expr_dump(skb, NFTA_LIST_ELEM, - priv->expr_array[i])) + priv->expr_array[i], reset)) goto nla_put_failure; } nla_nest_end(skb, nest); diff --git a/net/netfilter/nft_inner.c b/net/netfilter/nft_inner.c index 6d96b826db4e..28e2873ba24e 100644 --- a/net/netfilter/nft_inner.c +++ b/net/netfilter/nft_inner.c @@ -359,7 +359,7 @@ static int nft_inner_dump(struct sk_buff *skb, goto nla_put_failure; if (nft_expr_dump(skb, NFTA_INNER_EXPR, - (struct nft_expr *)&priv->expr) < 0) + (struct nft_expr *)&priv->expr, reset) < 0) goto nla_put_failure; return 0; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index b1a1217bca4c..123578e28917 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -222,7 +222,7 @@ static int nft_quota_dump(struct sk_buff *skb, { struct nft_quota *priv = nft_expr_priv(expr); - return nft_quota_do_dump(skb, priv, false); + return nft_quota_do_dump(skb, priv, reset); } static void nft_quota_destroy(const struct nft_ctx *ctx, -- cgit From 32637e33003f36e75e9147788cc0e2f21706ef99 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 8 Nov 2022 15:06:00 +0100 Subject: bpf: Expand map key argument of bpf_redirect_map to u64 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit For queueing packets in XDP we want to add a new redirect map type with support for 64-bit indexes. To prepare fore this, expand the width of the 'key' argument to the bpf_redirect_map() helper. Since BPF registers are always 64-bit, this should be safe to do after the fact. Acked-by: Song Liu Reviewed-by: Stanislav Fomichev Signed-off-by: Toke Høiland-Jørgensen Link: https://lore.kernel.org/r/20221108140601.149971-3-toke@redhat.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 2 +- include/linux/filter.h | 12 ++++++------ include/uapi/linux/bpf.h | 2 +- kernel/bpf/cpumap.c | 4 ++-- kernel/bpf/devmap.c | 4 ++-- kernel/bpf/verifier.c | 2 +- net/core/filter.c | 4 ++-- net/xdp/xskmap.c | 4 ++-- 8 files changed, 17 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 49f9d2bec401..54462dd28824 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -135,7 +135,7 @@ struct bpf_map_ops { struct bpf_local_storage __rcu ** (*map_owner_storage_ptr)(void *owner); /* Misc helpers.*/ - int (*map_redirect)(struct bpf_map *map, u32 ifindex, u64 flags); + int (*map_redirect)(struct bpf_map *map, u64 key, u64 flags); /* map_meta_equal must be implemented for maps that can be * used as an inner map. It is a runtime check to ensure diff --git a/include/linux/filter.h b/include/linux/filter.h index 787d35dbf5b0..bf701976056e 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -643,13 +643,13 @@ struct bpf_nh_params { }; struct bpf_redirect_info { - u32 flags; - u32 tgt_index; + u64 tgt_index; void *tgt_value; struct bpf_map *map; + u32 flags; + u32 kern_flags; u32 map_id; enum bpf_map_type map_type; - u32 kern_flags; struct bpf_nh_params nh; }; @@ -1504,7 +1504,7 @@ static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, } #endif /* IS_ENABLED(CONFIG_IPV6) */ -static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifindex, +static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { @@ -1515,7 +1515,7 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; - ri->tgt_value = lookup_elem(map, ifindex); + ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program @@ -1527,7 +1527,7 @@ static __always_inline int __bpf_xdp_redirect_map(struct bpf_map *map, u32 ifind return flags & action_mask; } - ri->tgt_index = ifindex; + ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6580448e9f77..ab86145df760 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2647,7 +2647,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 6b6a78c04b90..e0b2d016f0bf 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -667,9 +667,9 @@ static int cpu_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -static int cpu_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int cpu_map_redirect(struct bpf_map *map, u64 index, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + return __bpf_xdp_redirect_map(map, index, flags, 0, __cpu_map_lookup_elem); } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index f9a87dcc5535..d01e4c55b376 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -992,14 +992,14 @@ static int dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, map, key, value, map_flags); } -static int dev_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, __dev_map_lookup_elem); } -static int dev_hash_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) { return __bpf_xdp_redirect_map(map, ifindex, flags, BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5e74f460dfd0..be24774961ab 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14384,7 +14384,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env) BUILD_BUG_ON(!__same_type(ops->map_peek_elem, (int (*)(struct bpf_map *map, void *value))NULL)); BUILD_BUG_ON(!__same_type(ops->map_redirect, - (int (*)(struct bpf_map *map, u32 ifindex, u64 flags))NULL)); + (int (*)(struct bpf_map *map, u64 index, u64 flags))NULL)); BUILD_BUG_ON(!__same_type(ops->map_for_each_callback, (int (*)(struct bpf_map *map, bpf_callback_t callback_fn, diff --git a/net/core/filter.c b/net/core/filter.c index 37fad5a9b752..754dd01354d8 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4414,10 +4414,10 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = { .arg2_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, +BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u64, key, u64, flags) { - return map->ops->map_redirect(map, ifindex, flags); + return map->ops->map_redirect(map, key, flags); } static const struct bpf_func_proto bpf_xdp_redirect_map_proto = { diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index acc8e52a4f5f..771d0fa90ef5 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -231,9 +231,9 @@ static int xsk_map_delete_elem(struct bpf_map *map, void *key) return 0; } -static int xsk_map_redirect(struct bpf_map *map, u32 ifindex, u64 flags) +static int xsk_map_redirect(struct bpf_map *map, u64 index, u64 flags) { - return __bpf_xdp_redirect_map(map, ifindex, flags, 0, + return __bpf_xdp_redirect_map(map, index, flags, 0, __xsk_map_lookup_elem); } -- cgit From 58e0be1ef6118c5352b56a4d06e974c5599993a5 Mon Sep 17 00:00:00 2001 From: Hangbin Liu Date: Tue, 15 Nov 2022 22:24:00 +0800 Subject: net: use struct_group to copy ip/ipv6 header addresses MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit kernel test robot reported warnings when build bonding module with make W=1 O=build_dir ARCH=x86_64 SHELL=/bin/bash drivers/net/bonding/: from ../drivers/net/bonding/bond_main.c:35: In function ‘fortify_memcpy_chk’, inlined from ‘iph_to_flow_copy_v4addrs’ at ../include/net/ip.h:566:2, inlined from ‘bond_flow_ip’ at ../drivers/net/bonding/bond_main.c:3984:3: ../include/linux/fortify-string.h:413:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of f ield (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 413 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In function ‘fortify_memcpy_chk’, inlined from ‘iph_to_flow_copy_v6addrs’ at ../include/net/ipv6.h:900:2, inlined from ‘bond_flow_ip’ at ../drivers/net/bonding/bond_main.c:3994:3: ../include/linux/fortify-string.h:413:25: warning: call to ‘__read_overflow2_field’ declared with attribute warning: detected read beyond size of f ield (2nd parameter); maybe use struct_group()? [-Wattribute-warning] 413 | __read_overflow2_field(q_size_field, size); | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ This is because we try to copy the whole ip/ip6 address to the flow_key, while we only point the to ip/ip6 saddr. Note that since these are UAPI headers, __struct_group() is used to avoid the compiler warnings. Reported-by: kernel test robot Fixes: c3f8324188fa ("net: Add full IPv6 addresses to flow_keys") Signed-off-by: Hangbin Liu Link: https://lore.kernel.org/r/20221115142400.1204786-1-liuhangbin@gmail.com Signed-off-by: Paolo Abeni --- include/net/ip.h | 2 +- include/net/ipv6.h | 2 +- include/uapi/linux/ip.h | 6 ++++-- include/uapi/linux/ipv6.h | 6 ++++-- 4 files changed, 10 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/ip.h b/include/net/ip.h index 038097c2a152..144bdfbb25af 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -563,7 +563,7 @@ static inline void iph_to_flow_copy_v4addrs(struct flow_keys *flow, BUILD_BUG_ON(offsetof(typeof(flow->addrs), v4addrs.dst) != offsetof(typeof(flow->addrs), v4addrs.src) + sizeof(flow->addrs.v4addrs.src)); - memcpy(&flow->addrs.v4addrs, &iph->saddr, sizeof(flow->addrs.v4addrs)); + memcpy(&flow->addrs.v4addrs, &iph->addrs, sizeof(flow->addrs.v4addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; } diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 37943ba3a73c..d383c895592a 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -897,7 +897,7 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); - memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs)); + memcpy(&flow->addrs.v6addrs, &iph->addrs, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index 961ec16a26b8..874a92349bf5 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -100,8 +100,10 @@ struct iphdr { __u8 ttl; __u8 protocol; __sum16 check; - __be32 saddr; - __be32 daddr; + __struct_group(/* no tag */, addrs, /* no attrs */, + __be32 saddr; + __be32 daddr; + ); /*The options start here. */ }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index 03cdbe798fe3..81f4243bebb1 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -130,8 +130,10 @@ struct ipv6hdr { __u8 nexthdr; __u8 hop_limit; - struct in6_addr saddr; - struct in6_addr daddr; + __struct_group(/* no tag */, addrs, /* no attrs */, + struct in6_addr saddr; + struct in6_addr daddr; + ); }; -- cgit From 6c8c1406a6d6a3f2e61ac590f5c0994231bc6be7 Mon Sep 17 00:00:00 2001 From: Kuppuswamy Sathyanarayanan Date: Wed, 16 Nov 2022 14:38:19 -0800 Subject: virt: Add TDX guest driver TDX guest driver exposes IOCTL interfaces to service TDX guest user-specific requests. Currently, it is only used to allow the user to get the TDREPORT to support TDX attestation. Details about the TDX attestation process are documented in Documentation/x86/tdx.rst, and the IOCTL details are documented in Documentation/virt/coco/tdx-guest.rst. Operations like getting TDREPORT involves sending a blob of data as input and getting another blob of data as output. It was considered to use a sysfs interface for this, but it doesn't fit well into the standard sysfs model for configuring values. It would be possible to do read/write on files, but it would need multiple file descriptors, which would be somewhat messy. IOCTLs seem to be the best fitting and simplest model for this use case. The AMD sev-guest driver also uses the IOCTL interface to support attestation. [Bagas Sanjaya: Ack is for documentation portion] Signed-off-by: Kuppuswamy Sathyanarayanan Signed-off-by: Dave Hansen Reviewed-by: Bagas Sanjaya Reviewed-by: Tony Luck Reviewed-by: Mika Westerberg Acked-by: Kai Huang Acked-by: Kirill A. Shutemov Acked-by: Wander Lairson Costa Link: https://lore.kernel.org/all/20221116223820.819090-3-sathyanarayanan.kuppuswamy%40linux.intel.com --- Documentation/virt/coco/tdx-guest.rst | 52 ++++++++++++++++ Documentation/virt/index.rst | 1 + Documentation/x86/tdx.rst | 43 ++++++++++++++ drivers/virt/Kconfig | 2 + drivers/virt/Makefile | 1 + drivers/virt/coco/tdx-guest/Kconfig | 10 ++++ drivers/virt/coco/tdx-guest/Makefile | 2 + drivers/virt/coco/tdx-guest/tdx-guest.c | 102 ++++++++++++++++++++++++++++++++ include/uapi/linux/tdx-guest.h | 42 +++++++++++++ 9 files changed, 255 insertions(+) create mode 100644 Documentation/virt/coco/tdx-guest.rst create mode 100644 drivers/virt/coco/tdx-guest/Kconfig create mode 100644 drivers/virt/coco/tdx-guest/Makefile create mode 100644 drivers/virt/coco/tdx-guest/tdx-guest.c create mode 100644 include/uapi/linux/tdx-guest.h (limited to 'include/uapi/linux') diff --git a/Documentation/virt/coco/tdx-guest.rst b/Documentation/virt/coco/tdx-guest.rst new file mode 100644 index 000000000000..46e316db6bb4 --- /dev/null +++ b/Documentation/virt/coco/tdx-guest.rst @@ -0,0 +1,52 @@ +.. SPDX-License-Identifier: GPL-2.0 + +=================================================================== +TDX Guest API Documentation +=================================================================== + +1. General description +====================== + +The TDX guest driver exposes IOCTL interfaces via the /dev/tdx-guest misc +device to allow userspace to get certain TDX guest-specific details. + +2. API description +================== + +In this section, for each supported IOCTL, the following information is +provided along with a generic description. + +:Input parameters: Parameters passed to the IOCTL and related details. +:Output: Details about output data and return value (with details about + the non common error values). + +2.1 TDX_CMD_GET_REPORT0 +----------------------- + +:Input parameters: struct tdx_report_req +:Output: Upon successful execution, TDREPORT data is copied to + tdx_report_req.tdreport and return 0. Return -EINVAL for invalid + operands, -EIO on TDCALL failure or standard error number on other + common failures. + +The TDX_CMD_GET_REPORT0 IOCTL can be used by the attestation software to get +the TDREPORT0 (a.k.a. TDREPORT subtype 0) from the TDX module using +TDCALL[TDG.MR.REPORT]. + +A subtype index is added at the end of this IOCTL CMD to uniquely identify the +subtype-specific TDREPORT request. Although the subtype option is mentioned in +the TDX Module v1.0 specification, section titled "TDG.MR.REPORT", it is not +currently used, and it expects this value to be 0. So to keep the IOCTL +implementation simple, the subtype option was not included as part of the input +ABI. However, in the future, if the TDX Module supports more than one subtype, +a new IOCTL CMD will be created to handle it. To keep the IOCTL naming +consistent, a subtype index is added as part of the IOCTL CMD. + +Reference +--------- + +TDX reference material is collected here: + +https://www.intel.com/content/www/us/en/developer/articles/technical/intel-trust-domain-extensions.html + +The driver is based on TDX module specification v1.0 and TDX GHCI specification v1.0. diff --git a/Documentation/virt/index.rst b/Documentation/virt/index.rst index 2f1cffa87b1b..56e003ff28ff 100644 --- a/Documentation/virt/index.rst +++ b/Documentation/virt/index.rst @@ -14,6 +14,7 @@ Linux Virtualization Support ne_overview acrn/index coco/sev-guest + coco/tdx-guest hyperv/index .. only:: html and subproject diff --git a/Documentation/x86/tdx.rst b/Documentation/x86/tdx.rst index b8fa4329e1a5..dc8d9fd2c3f7 100644 --- a/Documentation/x86/tdx.rst +++ b/Documentation/x86/tdx.rst @@ -210,6 +210,49 @@ converted to shared on boot. For coherent DMA allocation, the DMA buffer gets converted on the allocation. Check force_dma_unencrypted() for details. +Attestation +=========== + +Attestation is used to verify the TDX guest trustworthiness to other +entities before provisioning secrets to the guest. For example, a key +server may want to use attestation to verify that the guest is the +desired one before releasing the encryption keys to mount the encrypted +rootfs or a secondary drive. + +The TDX module records the state of the TDX guest in various stages of +the guest boot process using the build time measurement register (MRTD) +and runtime measurement registers (RTMR). Measurements related to the +guest initial configuration and firmware image are recorded in the MRTD +register. Measurements related to initial state, kernel image, firmware +image, command line options, initrd, ACPI tables, etc are recorded in +RTMR registers. For more details, as an example, please refer to TDX +Virtual Firmware design specification, section titled "TD Measurement". +At TDX guest runtime, the attestation process is used to attest to these +measurements. + +The attestation process consists of two steps: TDREPORT generation and +Quote generation. + +TDX guest uses TDCALL[TDG.MR.REPORT] to get the TDREPORT (TDREPORT_STRUCT) +from the TDX module. TDREPORT is a fixed-size data structure generated by +the TDX module which contains guest-specific information (such as build +and boot measurements), platform security version, and the MAC to protect +the integrity of the TDREPORT. A user-provided 64-Byte REPORTDATA is used +as input and included in the TDREPORT. Typically it can be some nonce +provided by attestation service so the TDREPORT can be verified uniquely. +More details about the TDREPORT can be found in Intel TDX Module +specification, section titled "TDG.MR.REPORT Leaf". + +After getting the TDREPORT, the second step of the attestation process +is to send it to the Quoting Enclave (QE) to generate the Quote. TDREPORT +by design can only be verified on the local platform as the MAC key is +bound to the platform. To support remote verification of the TDREPORT, +TDX leverages Intel SGX Quoting Enclave to verify the TDREPORT locally +and convert it to a remotely verifiable Quote. Method of sending TDREPORT +to QE is implementation specific. Attestation software can choose +whatever communication channel available (i.e. vsock or TCP/IP) to +send the TDREPORT to QE and receive the Quote. + References ========== diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig index 87ef258cec64..f79ab13a5c28 100644 --- a/drivers/virt/Kconfig +++ b/drivers/virt/Kconfig @@ -52,4 +52,6 @@ source "drivers/virt/coco/efi_secret/Kconfig" source "drivers/virt/coco/sev-guest/Kconfig" +source "drivers/virt/coco/tdx-guest/Kconfig" + endif diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile index 093674e05c40..e9aa6fc96fab 100644 --- a/drivers/virt/Makefile +++ b/drivers/virt/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_NITRO_ENCLAVES) += nitro_enclaves/ obj-$(CONFIG_ACRN_HSM) += acrn/ obj-$(CONFIG_EFI_SECRET) += coco/efi_secret/ obj-$(CONFIG_SEV_GUEST) += coco/sev-guest/ +obj-$(CONFIG_INTEL_TDX_GUEST) += coco/tdx-guest/ diff --git a/drivers/virt/coco/tdx-guest/Kconfig b/drivers/virt/coco/tdx-guest/Kconfig new file mode 100644 index 000000000000..14246fc2fb02 --- /dev/null +++ b/drivers/virt/coco/tdx-guest/Kconfig @@ -0,0 +1,10 @@ +config TDX_GUEST_DRIVER + tristate "TDX Guest driver" + depends on INTEL_TDX_GUEST + help + The driver provides userspace interface to communicate with + the TDX module to request the TDX guest details like attestation + report. + + To compile this driver as module, choose M here. The module will + be called tdx-guest. diff --git a/drivers/virt/coco/tdx-guest/Makefile b/drivers/virt/coco/tdx-guest/Makefile new file mode 100644 index 000000000000..775cb463f9c8 --- /dev/null +++ b/drivers/virt/coco/tdx-guest/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_TDX_GUEST_DRIVER) += tdx-guest.o diff --git a/drivers/virt/coco/tdx-guest/tdx-guest.c b/drivers/virt/coco/tdx-guest/tdx-guest.c new file mode 100644 index 000000000000..5e44a0fa69bd --- /dev/null +++ b/drivers/virt/coco/tdx-guest/tdx-guest.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * TDX guest user interface driver + * + * Copyright (C) 2022 Intel Corporation + */ + +#include +#include +#include +#include +#include +#include +#include + +#include + +#include +#include + +static long tdx_get_report0(struct tdx_report_req __user *req) +{ + u8 *reportdata, *tdreport; + long ret; + + reportdata = kmalloc(TDX_REPORTDATA_LEN, GFP_KERNEL); + if (!reportdata) + return -ENOMEM; + + tdreport = kzalloc(TDX_REPORT_LEN, GFP_KERNEL); + if (!tdreport) { + ret = -ENOMEM; + goto out; + } + + if (copy_from_user(reportdata, req->reportdata, TDX_REPORTDATA_LEN)) { + ret = -EFAULT; + goto out; + } + + /* Generate TDREPORT0 using "TDG.MR.REPORT" TDCALL */ + ret = tdx_mcall_get_report0(reportdata, tdreport); + if (ret) + goto out; + + if (copy_to_user(req->tdreport, tdreport, TDX_REPORT_LEN)) + ret = -EFAULT; + +out: + kfree(reportdata); + kfree(tdreport); + + return ret; +} + +static long tdx_guest_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + switch (cmd) { + case TDX_CMD_GET_REPORT0: + return tdx_get_report0((struct tdx_report_req __user *)arg); + default: + return -ENOTTY; + } +} + +static const struct file_operations tdx_guest_fops = { + .owner = THIS_MODULE, + .unlocked_ioctl = tdx_guest_ioctl, + .llseek = no_llseek, +}; + +static struct miscdevice tdx_misc_dev = { + .name = KBUILD_MODNAME, + .minor = MISC_DYNAMIC_MINOR, + .fops = &tdx_guest_fops, +}; + +static const struct x86_cpu_id tdx_guest_ids[] = { + X86_MATCH_FEATURE(X86_FEATURE_TDX_GUEST, NULL), + {} +}; +MODULE_DEVICE_TABLE(x86cpu, tdx_guest_ids); + +static int __init tdx_guest_init(void) +{ + if (!x86_match_cpu(tdx_guest_ids)) + return -ENODEV; + + return misc_register(&tdx_misc_dev); +} +module_init(tdx_guest_init); + +static void __exit tdx_guest_exit(void) +{ + misc_deregister(&tdx_misc_dev); +} +module_exit(tdx_guest_exit); + +MODULE_AUTHOR("Kuppuswamy Sathyanarayanan "); +MODULE_DESCRIPTION("TDX Guest Driver"); +MODULE_LICENSE("GPL"); diff --git a/include/uapi/linux/tdx-guest.h b/include/uapi/linux/tdx-guest.h new file mode 100644 index 000000000000..a6a2098c08ff --- /dev/null +++ b/include/uapi/linux/tdx-guest.h @@ -0,0 +1,42 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Userspace interface for TDX guest driver + * + * Copyright (C) 2022 Intel Corporation + */ + +#ifndef _UAPI_LINUX_TDX_GUEST_H_ +#define _UAPI_LINUX_TDX_GUEST_H_ + +#include +#include + +/* Length of the REPORTDATA used in TDG.MR.REPORT TDCALL */ +#define TDX_REPORTDATA_LEN 64 + +/* Length of TDREPORT used in TDG.MR.REPORT TDCALL */ +#define TDX_REPORT_LEN 1024 + +/** + * struct tdx_report_req - Request struct for TDX_CMD_GET_REPORT0 IOCTL. + * + * @reportdata: User buffer with REPORTDATA to be included into TDREPORT. + * Typically it can be some nonce provided by attestation + * service, so the generated TDREPORT can be uniquely verified. + * @tdreport: User buffer to store TDREPORT output from TDCALL[TDG.MR.REPORT]. + */ +struct tdx_report_req { + __u8 reportdata[TDX_REPORTDATA_LEN]; + __u8 tdreport[TDX_REPORT_LEN]; +}; + +/* + * TDX_CMD_GET_REPORT0 - Get TDREPORT0 (a.k.a. TDREPORT subtype 0) using + * TDCALL[TDG.MR.REPORT] + * + * Return 0 on success, -EIO on TDCALL execution failure, and + * standard errno on other general error cases. + */ +#define TDX_CMD_GET_REPORT0 _IOWR('T', 1, struct tdx_report_req) + +#endif /* _UAPI_LINUX_TDX_GUEST_H_ */ -- cgit From 8acbca3a92b859e3dfe0538254acd5bd5b4632b1 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 11 Sep 2022 13:56:59 +0200 Subject: headers: Remove some left-over license text in include/uapi/linux/hsi/ Remove some left-over from commit e2be04c7f995 ("License cleanup: add SPDX license identifier to uapi header files with a license") When the SPDX-License-Identifier tag has been added, the corresponding license text has not been removed. Signed-off-by: Christophe JAILLET Acked-by: Kai Vehmanen Acked-by: Peter Ujfalusi Signed-off-by: Sebastian Reichel --- include/uapi/linux/hsi/cs-protocol.h | 14 -------------- include/uapi/linux/hsi/hsi_char.h | 14 -------------- 2 files changed, 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/hsi/cs-protocol.h b/include/uapi/linux/hsi/cs-protocol.h index c7f6e7672cb5..07c3bfb67463 100644 --- a/include/uapi/linux/hsi/cs-protocol.h +++ b/include/uapi/linux/hsi/cs-protocol.h @@ -6,20 +6,6 @@ * * Contact: Kai Vehmanen * Original author: Peter Ujfalusi - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA */ #ifndef _CS_PROTOCOL_H diff --git a/include/uapi/linux/hsi/hsi_char.h b/include/uapi/linux/hsi/hsi_char.h index 91623b0398b1..5ef72f0daf94 100644 --- a/include/uapi/linux/hsi/hsi_char.h +++ b/include/uapi/linux/hsi/hsi_char.h @@ -5,20 +5,6 @@ * Copyright (C) 2010 Nokia Corporation. All rights reserved. * * Contact: Andras Domokos - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA - * 02110-1301 USA */ #ifndef __HSI_CHAR_H -- cgit From f20a0a0519f35a3a34236ed2d38b067c5cb22b9f Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Thu, 17 Nov 2022 02:18:28 +0900 Subject: ethtool: doc: clarify what drivers can implement in their get_drvinfo() Many of the drivers which implement ethtool_ops::get_drvinfo() will prints the .driver, .version or .bus_info of struct ethtool_drvinfo. To have a glance of current state, do: $ git grep -W "get_drvinfo(struct" Printing in those three fields is useless because: - since [1], the driver version should be the kernel version (at least for upstream drivers). Arguably, out of tree drivers might still want to set a custom version, but out of tree is not our focus. - since [2], the core is able to provide default values for .driver and .bus_info. In summary, drivers may provide .fw_version and .erom_version, the rest is expected to be done by the core. In struct ethtool_ops doc from linux/ethtool: rephrase field get_drvinfo() doc to discourage developers from implementing this callback. In struct ethtool_drvinfo doc from uapi/linux/ethtool.h: remove the paragraph mentioning what drivers should do. Rationale: no need to repeat what is already written in struct ethtool_ops doc. But add a note that .fw_version and .erom_version are driver defined. Also update the dummy driver and simply remove the callback in order not to confuse the newcomers: most of the drivers will not need this callback function any more. [1] commit 6a7e25c7fb48 ("net/core: Replace driver version to be kernel version") Link: https://git.kernel.org/torvalds/linux/c/6a7e25c7fb48 [2] commit edaf5df22cb8 ("ethtool: ethtool_get_drvinfo: populate drvinfo fields even if callback exits") Link: https://git.kernel.org/netdev/net-next/c/edaf5df22cb8 Reviewed-by: Leon Romanovsky Signed-off-by: Vincent Mailhol Link: https://lore.kernel.org/r/20221116171828.4093-1-mailhol.vincent@wanadoo.fr Signed-off-by: Jakub Kicinski --- drivers/net/dummy.c | 7 ------- include/linux/ethtool.h | 8 ++++---- include/uapi/linux/ethtool.h | 10 ++++------ 3 files changed, 8 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c index aa0fc00faecb..c4b1b0aa438a 100644 --- a/drivers/net/dummy.c +++ b/drivers/net/dummy.c @@ -99,14 +99,7 @@ static const struct net_device_ops dummy_netdev_ops = { .ndo_change_carrier = dummy_change_carrier, }; -static void dummy_get_drvinfo(struct net_device *dev, - struct ethtool_drvinfo *info) -{ - strscpy(info->driver, DRV_NAME, sizeof(info->driver)); -} - static const struct ethtool_ops dummy_ethtool_ops = { - .get_drvinfo = dummy_get_drvinfo, .get_ts_info = ethtool_op_get_ts_info, }; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 5c51c7fda32a..9e0a76fc7de9 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -473,10 +473,10 @@ struct ethtool_module_power_mode_params { * parameter. * @supported_coalesce_params: supported types of interrupt coalescing. * @supported_ring_params: supported ring params. - * @get_drvinfo: Report driver/device information. Should only set the - * @driver, @version, @fw_version and @bus_info fields. If not - * implemented, the @driver and @bus_info fields will be filled in - * according to the netdev's parent device. + * @get_drvinfo: Report driver/device information. Modern drivers no + * longer have to implement this callback. Most fields are + * correctly filled in by the core using system information, or + * populated using other driver operations. * @get_regs_len: Get buffer length required for @get_regs * @get_regs: Get device registers * @get_wol: Report whether Wake-on-Lan is enabled diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index f341de2ae612..58e587ba0450 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -159,8 +159,10 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) * in its bus driver structure (e.g. pci_driver::name). Must * not be an empty string. * @version: Driver version string; may be an empty string - * @fw_version: Firmware version string; may be an empty string - * @erom_version: Expansion ROM version string; may be an empty string + * @fw_version: Firmware version string; driver defined; may be an + * empty string + * @erom_version: Expansion ROM version string; driver defined; may be + * an empty string * @bus_info: Device bus address. This should match the dev_name() * string for the underlying bus device, if there is one. May be * an empty string. @@ -179,10 +181,6 @@ static inline __u32 ethtool_cmd_speed(const struct ethtool_cmd *ep) * * Users can use the %ETHTOOL_GSSET_INFO command to get the number of * strings in any string set (from Linux 2.6.34). - * - * Drivers should set at most @driver, @version, @fw_version and - * @bus_info in their get_drvinfo() implementation. The ethtool - * core fills in the other fields using other driver operations. */ struct ethtool_drvinfo { __u32 cmd; -- cgit From cd502236835b678738810ecd501c85a3a7a11150 Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Tue, 15 Nov 2022 11:48:15 +0100 Subject: devlink: Introduce new attribute 'tx_priority' to devlink-rate To fully utilize offload capabilities of Intel 100G card QoS capabilities new attribute 'tx_priority' needs to be introduced. This attribute allows for usage of strict priority arbiter among siblings. This arbitration scheme attempts to schedule nodes based on their priority as long as the nodes remain within their bandwidth limit. Introduce new attribute in devlink-rate that will allow for configuration of strict priority. New attribute is optional. Signed-off-by: Michal Wilczynski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 6 ++++++ include/uapi/linux/devlink.h | 1 + net/core/devlink.c | 31 +++++++++++++++++++++++++++++++ 3 files changed, 38 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index 611a23a3deb2..90d59d673cb1 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -114,6 +114,8 @@ struct devlink_rate { refcount_t refcnt; }; }; + + u32 tx_priority; }; struct devlink_port { @@ -1511,10 +1513,14 @@ struct devlink_ops { u64 tx_share, struct netlink_ext_ack *extack); int (*rate_leaf_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_leaf_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_max, struct netlink_ext_ack *extack); + int (*rate_node_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_priority, struct netlink_ext_ack *extack); int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, struct netlink_ext_ack *extack); int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 2f24b53a87a5..1a9214d35ef5 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -607,6 +607,7 @@ enum devlink_attr { DEVLINK_ATTR_SELFTESTS, /* nested */ + DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */ /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 7f789bbcbbd7..bf6d3a3c28bb 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1203,6 +1203,9 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, devlink_rate->tx_max, DEVLINK_ATTR_PAD)) goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY, + devlink_rate->tx_priority)) + goto nla_put_failure; if (devlink_rate->parent) if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, devlink_rate->parent->name)) @@ -1936,6 +1939,7 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, { struct nlattr *nla_parent, **attrs = info->attrs; int err = -EOPNOTSUPP; + u32 priority; u64 rate; if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { @@ -1964,6 +1968,20 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, devlink_rate->tx_max = rate; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]) { + priority = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_PRIORITY]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_priority_set(devlink_rate, devlink_rate->priv, + priority, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_priority_set(devlink_rate, devlink_rate->priv, + priority, info->extack); + + if (err) + return err; + devlink_rate->tx_priority = priority; + } + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; if (nla_parent) { err = devlink_nl_rate_parent_node_set(devlink_rate, info, @@ -1995,6 +2013,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_leaf_tx_priority_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_PRIORITY], + "TX priority set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); @@ -2009,6 +2033,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, NL_SET_ERR_MSG_MOD(info->extack, "Parent set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_PRIORITY] && !ops->rate_node_tx_priority_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_PRIORITY], + "TX priority set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false; @@ -9187,6 +9217,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_LINECARD_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { -- cgit From 6e2d7e84fcfee62d70e62aa9e469d10b8b6a7dc7 Mon Sep 17 00:00:00 2001 From: Michal Wilczynski Date: Tue, 15 Nov 2022 11:48:16 +0100 Subject: devlink: Introduce new attribute 'tx_weight' to devlink-rate To fully utilize offload capabilities of Intel 100G card QoS capabilities new attribute 'tx_weight' needs to be introduced. This attribute allows for usage of Weighted Fair Queuing arbitration scheme among siblings. This arbitration scheme can be used simultaneously with the strict priority. Introduce new attribute in devlink-rate that will allow for configuration of Weighted Fair Queueing. New attribute is optional. Signed-off-by: Michal Wilczynski Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- include/net/devlink.h | 5 +++++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 33 +++++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/devlink.h b/include/net/devlink.h index 90d59d673cb1..366b23d3f973 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -116,6 +116,7 @@ struct devlink_rate { }; u32 tx_priority; + u32 tx_weight; }; struct devlink_port { @@ -1515,12 +1516,16 @@ struct devlink_ops { u64 tx_max, struct netlink_ext_ack *extack); int (*rate_leaf_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_priority, struct netlink_ext_ack *extack); + int (*rate_leaf_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_weight, struct netlink_ext_ack *extack); int (*rate_node_tx_share_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_share, struct netlink_ext_ack *extack); int (*rate_node_tx_max_set)(struct devlink_rate *devlink_rate, void *priv, u64 tx_max, struct netlink_ext_ack *extack); int (*rate_node_tx_priority_set)(struct devlink_rate *devlink_rate, void *priv, u32 tx_priority, struct netlink_ext_ack *extack); + int (*rate_node_tx_weight_set)(struct devlink_rate *devlink_rate, void *priv, + u32 tx_weight, struct netlink_ext_ack *extack); int (*rate_node_new)(struct devlink_rate *rate_node, void **priv, struct netlink_ext_ack *extack); int (*rate_node_del)(struct devlink_rate *rate_node, void *priv, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 1a9214d35ef5..498d0d5d0957 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -608,6 +608,8 @@ enum devlink_attr { DEVLINK_ATTR_SELFTESTS, /* nested */ DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */ + DEVLINK_ATTR_RATE_TX_WEIGHT, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index bf6d3a3c28bb..525bdf426163 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -1206,6 +1206,11 @@ static int devlink_nl_rate_fill(struct sk_buff *msg, if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_PRIORITY, devlink_rate->tx_priority)) goto nla_put_failure; + + if (nla_put_u32(msg, DEVLINK_ATTR_RATE_TX_WEIGHT, + devlink_rate->tx_weight)) + goto nla_put_failure; + if (devlink_rate->parent) if (nla_put_string(msg, DEVLINK_ATTR_RATE_PARENT_NODE_NAME, devlink_rate->parent->name)) @@ -1940,6 +1945,7 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, struct nlattr *nla_parent, **attrs = info->attrs; int err = -EOPNOTSUPP; u32 priority; + u32 weight; u64 rate; if (attrs[DEVLINK_ATTR_RATE_TX_SHARE]) { @@ -1982,6 +1988,20 @@ static int devlink_nl_rate_set(struct devlink_rate *devlink_rate, devlink_rate->tx_priority = priority; } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]) { + weight = nla_get_u32(attrs[DEVLINK_ATTR_RATE_TX_WEIGHT]); + if (devlink_rate_is_leaf(devlink_rate)) + err = ops->rate_leaf_tx_weight_set(devlink_rate, devlink_rate->priv, + weight, info->extack); + else if (devlink_rate_is_node(devlink_rate)) + err = ops->rate_node_tx_weight_set(devlink_rate, devlink_rate->priv, + weight, info->extack); + + if (err) + return err; + devlink_rate->tx_weight = weight; + } + nla_parent = attrs[DEVLINK_ATTR_RATE_PARENT_NODE_NAME]; if (nla_parent) { err = devlink_nl_rate_parent_node_set(devlink_rate, info, @@ -2019,6 +2039,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX priority set isn't supported for the leafs"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_leaf_tx_weight_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_WEIGHT], + "TX weight set isn't supported for the leafs"); + return false; + } } else if (type == DEVLINK_RATE_TYPE_NODE) { if (attrs[DEVLINK_ATTR_RATE_TX_SHARE] && !ops->rate_node_tx_share_set) { NL_SET_ERR_MSG_MOD(info->extack, "TX share set isn't supported for the nodes"); @@ -2039,6 +2065,12 @@ static bool devlink_rate_set_ops_supported(const struct devlink_ops *ops, "TX priority set isn't supported for the nodes"); return false; } + if (attrs[DEVLINK_ATTR_RATE_TX_WEIGHT] && !ops->rate_node_tx_weight_set) { + NL_SET_ERR_MSG_ATTR(info->extack, + attrs[DEVLINK_ATTR_RATE_TX_WEIGHT], + "TX weight set isn't supported for the nodes"); + return false; + } } else { WARN(1, "Unknown type of rate object"); return false; @@ -9218,6 +9250,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_LINECARD_TYPE] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, + [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, }; static const struct genl_small_ops devlink_nl_ops[] = { -- cgit From c73a72f4cbb47672c8cc7f7d7aba52f1cb15baca Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Thu, 17 Nov 2022 19:39:03 -0800 Subject: netlink: remove the flex array from struct nlmsghdr I've added a flex array to struct nlmsghdr in commit 738136a0e375 ("netlink: split up copies in the ack construction") to allow accessing the data easily. It leads to warnings with clang, if user space wraps this structure into another struct and the flex array is not at the end of the container. Reviewed-by: Kees Cook Reviewed-by: David Ahern Link: https://lore.kernel.org/all/20221114023927.GA685@u2004-local/ Link: https://lore.kernel.org/r/20221118033903.1651026-1-kuba@kernel.org Signed-off-by: Jakub Kicinski --- include/uapi/linux/netlink.h | 2 -- net/netlink/af_netlink.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h index 5da0da59bf01..e2ae82e3f9f7 100644 --- a/include/uapi/linux/netlink.h +++ b/include/uapi/linux/netlink.h @@ -48,7 +48,6 @@ struct sockaddr_nl { * @nlmsg_flags: Additional flags * @nlmsg_seq: Sequence number * @nlmsg_pid: Sending process port ID - * @nlmsg_data: Message payload */ struct nlmsghdr { __u32 nlmsg_len; @@ -56,7 +55,6 @@ struct nlmsghdr { __u16 nlmsg_flags; __u32 nlmsg_seq; __u32 nlmsg_pid; - __u8 nlmsg_data[]; }; /* Flags values */ diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9ebdf3262015..d73091f6bb0f 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2514,7 +2514,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, if (!nlmsg_append(skb, nlmsg_len(nlh))) goto err_bad_put; - memcpy(errmsg->msg.nlmsg_data, nlh->nlmsg_data, + memcpy(nlmsg_data(&errmsg->msg), nlmsg_data(nlh), nlmsg_len(nlh)); } -- cgit From e307e6698165ca6508ed42c69cb1be76c8eb6a3c Mon Sep 17 00:00:00 2001 From: Stefan Metzmacher Date: Thu, 27 Oct 2022 20:34:45 +0200 Subject: io_uring/net: introduce IORING_SEND_ZC_REPORT_USAGE flag It might be useful for applications to detect if a zero copy transfer with SEND[MSG]_ZC was actually possible or not. The application can fallback to plain SEND[MSG] in order to avoid the overhead of two cqes per request. Or it can generate a log message that could indicate to an administrator that no zero copy was possible and could explain degraded performance. Cc: stable@vger.kernel.org # 6.1 Link: https://lore.kernel.org/io-uring/fb6a7599-8a9b-15e5-9b64-6cd9d01c6ff4@gmail.com/T/#m2b0d9df94ce43b0e69e6c089bdff0ce6babbdfaa Signed-off-by: Stefan Metzmacher Reviewed-by: Pavel Begunkov Link: https://lore.kernel.org/r/8945b01756d902f5d5b0667f20b957ad3f742e5e.1666895626.git.metze@samba.org Signed-off-by: Jens Axboe --- include/uapi/linux/io_uring.h | 18 ++++++++++++++++++ io_uring/net.c | 6 +++++- io_uring/notif.c | 12 ++++++++++++ io_uring/notif.h | 3 +++ 4 files changed, 38 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 2df3225b562f..9d4c4078e8d0 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -296,10 +296,28 @@ enum io_uring_op { * * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in * the buf_index field. + * + * IORING_SEND_ZC_REPORT_USAGE + * If set, SEND[MSG]_ZC should report + * the zerocopy usage in cqe.res + * for the IORING_CQE_F_NOTIF cqe. + * 0 is reported if zerocopy was actually possible. + * IORING_NOTIF_USAGE_ZC_COPIED if data was copied + * (at least partially). */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) +#define IORING_SEND_ZC_REPORT_USAGE (1U << 3) + +/* + * cqe.res for IORING_CQE_F_NOTIF if + * IORING_SEND_ZC_REPORT_USAGE was requested + * + * It should be treated as a flag, all other + * bits of cqe.res should be treated as reserved! + */ +#define IORING_NOTIF_USAGE_ZC_COPIED (1U << 31) /* * accept flags stored in sqe->ioprio diff --git a/io_uring/net.c b/io_uring/net.c index ab83da7e80f0..03825b043afe 100644 --- a/io_uring/net.c +++ b/io_uring/net.c @@ -937,7 +937,8 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) zc->flags = READ_ONCE(sqe->ioprio); if (zc->flags & ~(IORING_RECVSEND_POLL_FIRST | - IORING_RECVSEND_FIXED_BUF)) + IORING_RECVSEND_FIXED_BUF | + IORING_SEND_ZC_REPORT_USAGE)) return -EINVAL; notif = zc->notif = io_alloc_notif(ctx); if (!notif) @@ -955,6 +956,9 @@ int io_send_zc_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe) req->imu = READ_ONCE(ctx->user_bufs[idx]); io_req_set_rsrc_node(notif, ctx, 0); } + if (zc->flags & IORING_SEND_ZC_REPORT_USAGE) { + io_notif_to_data(notif)->zc_report = true; + } if (req->opcode == IORING_OP_SEND_ZC) { if (READ_ONCE(sqe->__pad3[0])) diff --git a/io_uring/notif.c b/io_uring/notif.c index e37c6569d82e..4bfef10161fa 100644 --- a/io_uring/notif.c +++ b/io_uring/notif.c @@ -18,6 +18,10 @@ static void __io_notif_complete_tw(struct io_kiocb *notif, bool *locked) __io_unaccount_mem(ctx->user, nd->account_pages); nd->account_pages = 0; } + + if (nd->zc_report && (nd->zc_copied || !nd->zc_used)) + notif->cqe.res |= IORING_NOTIF_USAGE_ZC_COPIED; + io_req_task_complete(notif, locked); } @@ -28,6 +32,13 @@ static void io_uring_tx_zerocopy_callback(struct sk_buff *skb, struct io_notif_data *nd = container_of(uarg, struct io_notif_data, uarg); struct io_kiocb *notif = cmd_to_io_kiocb(nd); + if (nd->zc_report) { + if (success && !nd->zc_used && skb) + WRITE_ONCE(nd->zc_used, true); + else if (!success && !nd->zc_copied) + WRITE_ONCE(nd->zc_copied, true); + } + if (refcount_dec_and_test(&uarg->refcnt)) { notif->io_task_work.func = __io_notif_complete_tw; io_req_task_work_add(notif); @@ -55,6 +66,7 @@ struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx) nd->account_pages = 0; nd->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; nd->uarg.callback = io_uring_tx_zerocopy_callback; + nd->zc_report = nd->zc_used = nd->zc_copied = false; refcount_set(&nd->uarg.refcnt, 1); return notif; } diff --git a/io_uring/notif.h b/io_uring/notif.h index 5b4d710c8ca5..4ae696273c78 100644 --- a/io_uring/notif.h +++ b/io_uring/notif.h @@ -13,6 +13,9 @@ struct io_notif_data { struct file *file; struct ubuf_info uarg; unsigned long account_pages; + bool zc_report; + bool zc_used; + bool zc_copied; }; void io_notif_flush(struct io_kiocb *notif); -- cgit From caf1aeaffc3b09649a56769e559333ae2c4f1802 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sun, 20 Nov 2022 10:10:53 -0700 Subject: eventpoll: add EPOLL_URING_WAKE poll wakeup flag We can have dependencies between epoll and io_uring. Consider an epoll context, identified by the epfd file descriptor, and an io_uring file descriptor identified by iofd. If we add iofd to the epfd context, and arm a multishot poll request for epfd with iofd, then the multishot poll request will repeatedly trigger and generate events until terminated by CQ ring overflow. This isn't a desired behavior. Add EPOLL_URING so that io_uring can pass it in as part of the poll wakeup key, and io_uring can check for that to detect a potential recursive invocation. Cc: stable@vger.kernel.org # 6.0 Signed-off-by: Jens Axboe --- fs/eventpoll.c | 18 ++++++++++-------- include/uapi/linux/eventpoll.h | 6 ++++++ 2 files changed, 16 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 52954d4637b5..64659b110973 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -491,7 +491,8 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC -static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) +static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, + unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; @@ -522,16 +523,17 @@ static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; - wake_up_locked_poll(&ep->poll_wait, EPOLLIN); + wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else -static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi) +static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, + unsigned pollflags) { - wake_up_poll(&ep->poll_wait, EPOLLIN); + wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif @@ -742,7 +744,7 @@ static void ep_free(struct eventpoll *ep) /* We need to release all tasks waiting for these file */ if (waitqueue_active(&ep->poll_wait)) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); /* * We need to lock this because we could be hit by @@ -1208,7 +1210,7 @@ out_unlock: /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, epi); + ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; @@ -1553,7 +1555,7 @@ static int ep_insert(struct eventpoll *ep, const struct epoll_event *event, /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); return 0; } @@ -1629,7 +1631,7 @@ static int ep_modify(struct eventpoll *ep, struct epitem *epi, /* We have to call this outside the lock */ if (pwake) - ep_poll_safewake(ep, NULL); + ep_poll_safewake(ep, NULL, 0); return 0; } diff --git a/include/uapi/linux/eventpoll.h b/include/uapi/linux/eventpoll.h index 8a3432d0f0dc..e687658843b1 100644 --- a/include/uapi/linux/eventpoll.h +++ b/include/uapi/linux/eventpoll.h @@ -41,6 +41,12 @@ #define EPOLLMSG (__force __poll_t)0x00000400 #define EPOLLRDHUP (__force __poll_t)0x00002000 +/* + * Internal flag - wakeup generated by io_uring, used to detect recursion back + * into the io_uring poll handler. + */ +#define EPOLL_URING_WAKE ((__force __poll_t)(1U << 27)) + /* Set exclusive wakeup mode for the target file descriptor */ #define EPOLLEXCLUSIVE ((__force __poll_t)(1U << 28)) -- cgit From 9f4211bf7f811b653aa6acfb9aea38222436a458 Mon Sep 17 00:00:00 2001 From: Eray Orçunus Date: Tue, 22 Nov 2022 17:46:55 -0800 Subject: HID: add mapping for camera access keys MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit HUTRR72 added 3 new usage codes for keys that are supposed to enable, disable and toggle camera access. These are useful, considering many laptops today have key(s) for toggling access to camera. This patch adds new key definitions for KEY_CAMERA_ACCESS_ENABLE, KEY_CAMERA_ACCESS_DISABLE and KEY_CAMERA_ACCESS_TOGGLE. Additionally hid-debug is adjusted to recognize this new usage codes as well. Signed-off-by: Eray Orçunus Acked-by: Jiri Kosina Link: https://lore.kernel.org/r/20221029120311.11152-3-erayorcunus@gmail.com Signed-off-by: Dmitry Torokhov --- drivers/hid/hid-debug.c | 3 +++ drivers/hid/hid-input.c | 3 +++ include/uapi/linux/input-event-codes.h | 3 +++ 3 files changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c index 2ca6ab600bc9..e213bdde543a 100644 --- a/drivers/hid/hid-debug.c +++ b/drivers/hid/hid-debug.c @@ -971,6 +971,9 @@ static const char *keys[KEY_MAX + 1] = { [KEY_ASSISTANT] = "Assistant", [KEY_KBD_LAYOUT_NEXT] = "KbdLayoutNext", [KEY_EMOJI_PICKER] = "EmojiPicker", + [KEY_CAMERA_ACCESS_ENABLE] = "CameraAccessEnable", + [KEY_CAMERA_ACCESS_DISABLE] = "CameraAccessDisable", + [KEY_CAMERA_ACCESS_TOGGLE] = "CameraAccessToggle", [KEY_DICTATE] = "Dictate", [KEY_BRIGHTNESS_MIN] = "BrightnessMin", [KEY_BRIGHTNESS_MAX] = "BrightnessMax", diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c index 859aeb07542e..c6259d9e5ff6 100644 --- a/drivers/hid/hid-input.c +++ b/drivers/hid/hid-input.c @@ -1086,6 +1086,9 @@ static void hidinput_configure_usage(struct hid_input *hidinput, struct hid_fiel case 0x0cd: map_key_clear(KEY_PLAYPAUSE); break; case 0x0cf: map_key_clear(KEY_VOICECOMMAND); break; + case 0x0d5: map_key_clear(KEY_CAMERA_ACCESS_ENABLE); break; + case 0x0d6: map_key_clear(KEY_CAMERA_ACCESS_DISABLE); break; + case 0x0d7: map_key_clear(KEY_CAMERA_ACCESS_TOGGLE); break; case 0x0d8: map_key_clear(KEY_DICTATE); break; case 0x0d9: map_key_clear(KEY_EMOJI_PICKER); break; diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 7ad931a32970..022a520e31fc 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -614,6 +614,9 @@ #define KEY_KBD_LAYOUT_NEXT 0x248 /* AC Next Keyboard Layout Select */ #define KEY_EMOJI_PICKER 0x249 /* Show/hide emoji picker (HUTRR101) */ #define KEY_DICTATE 0x24a /* Start or Stop Voice Dictation Session (HUTRR99) */ +#define KEY_CAMERA_ACCESS_ENABLE 0x24b /* Enables programmatic access to camera devices. (HUTRR72) */ +#define KEY_CAMERA_ACCESS_DISABLE 0x24c /* Disables programmatic access to camera devices. (HUTRR72) */ +#define KEY_CAMERA_ACCESS_TOGGLE 0x24d /* Toggles the current state of the camera access control. (HUTRR72) */ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ -- cgit From 4f8d37020e1fd0bf6ee9381ba918135ef3712efd Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 28 Oct 2022 14:25:21 +0200 Subject: fuse: add "expire only" mode to FUSE_NOTIFY_INVAL_ENTRY Add a flag to entry expiration that lets the filesystem expire a dentry without kicking it out from the cache immediately. This makes a difference for overmounted dentries, where plain invalidation would detach all submounts before dropping the dentry from the cache. If only expiry is set on the dentry, then any overmounts are left alone and until ->d_revalidate() is called. Note: ->d_revalidate() is not called for the case of following a submount, so invalidation will only be triggered for the non-overmounted case. The dentry could also be mounted in a different mount instance, in which case any submounts will still be detached. Suggested-by: Jakob Blomer Signed-off-by: Miklos Szeredi --- fs/fuse/dev.c | 4 ++-- fs/fuse/dir.c | 6 ++++-- fs/fuse/fuse_i.h | 2 +- include/uapi/linux/fuse.h | 13 +++++++++++-- 4 files changed, 18 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index b4a6e0a1b945..0a845fac3ba8 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -1498,7 +1498,7 @@ static int fuse_notify_inval_entry(struct fuse_conn *fc, unsigned int size, buf[outarg.namelen] = 0; down_read(&fc->killsb); - err = fuse_reverse_inval_entry(fc, outarg.parent, 0, &name); + err = fuse_reverse_inval_entry(fc, outarg.parent, 0, &name, outarg.flags); up_read(&fc->killsb); kfree(buf); return err; @@ -1546,7 +1546,7 @@ static int fuse_notify_delete(struct fuse_conn *fc, unsigned int size, buf[outarg.namelen] = 0; down_read(&fc->killsb); - err = fuse_reverse_inval_entry(fc, outarg.parent, outarg.child, &name); + err = fuse_reverse_inval_entry(fc, outarg.parent, outarg.child, &name, 0); up_read(&fc->killsb); kfree(buf); return err; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index bb97a384dc5d..d092c7d75929 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1170,7 +1170,7 @@ int fuse_update_attributes(struct inode *inode, struct file *file, u32 mask) } int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, - u64 child_nodeid, struct qstr *name) + u64 child_nodeid, struct qstr *name, u32 flags) { int err = -ENOTDIR; struct inode *parent; @@ -1197,7 +1197,9 @@ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, goto unlock; fuse_dir_changed(parent); - fuse_invalidate_entry(entry); + if (!(flags & FUSE_EXPIRE_ONLY)) + d_invalidate(entry); + fuse_invalidate_entry_cache(entry); if (child_nodeid != 0 && d_really_is_positive(entry)) { inode_lock(d_inode(entry)); diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 98a9cf531873..8789d94eda21 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -1220,7 +1220,7 @@ int fuse_reverse_inval_inode(struct fuse_conn *fc, u64 nodeid, * then the dentry is unhashed (d_delete()). */ int fuse_reverse_inval_entry(struct fuse_conn *fc, u64 parent_nodeid, - u64 child_nodeid, struct qstr *name); + u64 child_nodeid, struct qstr *name, u32 flags); int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file, bool isdir); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 76ee8f9e024a..39cfb343faa8 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -197,6 +197,9 @@ * * 7.37 * - add FUSE_TMPFILE + * + * 7.38 + * - add FUSE_EXPIRE_ONLY flag to fuse_notify_inval_entry */ #ifndef _LINUX_FUSE_H @@ -232,7 +235,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 37 +#define FUSE_KERNEL_MINOR_VERSION 38 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -491,6 +494,12 @@ struct fuse_file_lock { */ #define FUSE_SETXATTR_ACL_KILL_SGID (1 << 0) +/** + * notify_inval_entry flags + * FUSE_EXPIRE_ONLY + */ +#define FUSE_EXPIRE_ONLY (1 << 0) + enum fuse_opcode { FUSE_LOOKUP = 1, FUSE_FORGET = 2, /* no reply */ @@ -919,7 +928,7 @@ struct fuse_notify_inval_inode_out { struct fuse_notify_inval_entry_out { uint64_t parent; uint32_t namelen; - uint32_t padding; + uint32_t flags; }; struct fuse_notify_delete_out { -- cgit From 153524053bbb0d27bb2e0be36d1b46862e9ce74c Mon Sep 17 00:00:00 2001 From: Dharmendra Singh Date: Fri, 17 Jun 2022 12:40:27 +0530 Subject: fuse: allow non-extending parallel direct writes on the same file In general, as of now, in FUSE, direct writes on the same file are serialized over inode lock i.e we hold inode lock for the full duration of the write request. I could not find in fuse code and git history a comment which clearly explains why this exclusive lock is taken for direct writes. Following might be the reasons for acquiring an exclusive lock but not be limited to 1) Our guess is some USER space fuse implementations might be relying on this lock for serialization. 2) The lock protects against file read/write size races. 3) Ruling out any issues arising from partial write failures. This patch relaxes the exclusive lock for direct non-extending writes only. File size extending writes might not need the lock either, but we are not entirely sure if there is a risk to introduce any kind of regression. Furthermore, benchmarking with fio does not show a difference between patch versions that take on file size extension a) an exclusive lock and b) a shared lock. A possible example of an issue with i_size extending writes are write error cases. Some writes might succeed and others might fail for file system internal reasons - for example ENOSPACE. With parallel file size extending writes it _might_ be difficult to revert the action of the failing write, especially to restore the right i_size. With these changes, we allow non-extending parallel direct writes on the same file with the help of a flag called FOPEN_PARALLEL_DIRECT_WRITES. If this flag is set on the file (flag is passed from libfuse to fuse kernel as part of file open/create), we do not take exclusive lock anymore, but instead use a shared lock that allows non-extending writes to run in parallel. FUSE implementations which rely on this inode lock for serialization can continue to do so and serialized direct writes are still the default. Implementations that do not do write serialization need to be updated and need to set the FOPEN_PARALLEL_DIRECT_WRITES flag in their file open/create reply. On patch review there were concerns that network file systems (or vfs multiple mounts of the same file system) might have issues with parallel writes. We believe this is not the case, as this is just a local lock, which network file systems could not rely on anyway. I.e. this lock is just for local consistency. Signed-off-by: Dharmendra Singh Signed-off-by: Bernd Schubert Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 43 ++++++++++++++++++++++++++++++++++++++++--- include/uapi/linux/fuse.h | 3 +++ 2 files changed, 43 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 89f4741728ba..d360d38ab616 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1563,14 +1563,47 @@ static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to) return res; } +static bool fuse_direct_write_extending_i_size(struct kiocb *iocb, + struct iov_iter *iter) +{ + struct inode *inode = file_inode(iocb->ki_filp); + + return iocb->ki_pos + iov_iter_count(iter) > i_size_read(inode); +} + static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct inode *inode = file_inode(iocb->ki_filp); + struct file *file = iocb->ki_filp; + struct fuse_file *ff = file->private_data; struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb); ssize_t res; + bool exclusive_lock = + !(ff->open_flags & FOPEN_PARALLEL_DIRECT_WRITES) || + iocb->ki_flags & IOCB_APPEND || + fuse_direct_write_extending_i_size(iocb, from); + + /* + * Take exclusive lock if + * - Parallel direct writes are disabled - a user space decision + * - Parallel direct writes are enabled and i_size is being extended. + * This might not be needed at all, but needs further investigation. + */ + if (exclusive_lock) + inode_lock(inode); + else { + inode_lock_shared(inode); + + /* A race with truncate might have come up as the decision for + * the lock type was done without holding the lock, check again. + */ + if (fuse_direct_write_extending_i_size(iocb, from)) { + inode_unlock_shared(inode); + inode_lock(inode); + exclusive_lock = true; + } + } - /* Don't allow parallel writes to the same file */ - inode_lock(inode); res = generic_write_checks(iocb, from); if (res > 0) { if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) { @@ -1581,7 +1614,10 @@ static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from) fuse_write_update_attr(inode, iocb->ki_pos, res); } } - inode_unlock(inode); + if (exclusive_lock) + inode_unlock(inode); + else + inode_unlock_shared(inode); return res; } @@ -2931,6 +2967,7 @@ fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter) if (iov_iter_rw(iter) == WRITE) { fuse_write_update_attr(inode, pos, ret); + /* For extending writes we already hold exclusive lock */ if (ret < 0 && offset + count > i_size) fuse_do_truncate(file); } diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 39cfb343faa8..e3c54109bae9 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -200,6 +200,7 @@ * * 7.38 * - add FUSE_EXPIRE_ONLY flag to fuse_notify_inval_entry + * - add FOPEN_PARALLEL_DIRECT_WRITES */ #ifndef _LINUX_FUSE_H @@ -307,6 +308,7 @@ struct fuse_file_lock { * FOPEN_CACHE_DIR: allow caching this directory * FOPEN_STREAM: the file is stream-like (no file position at all) * FOPEN_NOFLUSH: don't flush data cache on close (unless FUSE_WRITEBACK_CACHE) + * FOPEN_PARALLEL_DIRECT_WRITES: Allow concurrent direct writes on the same inode */ #define FOPEN_DIRECT_IO (1 << 0) #define FOPEN_KEEP_CACHE (1 << 1) @@ -314,6 +316,7 @@ struct fuse_file_lock { #define FOPEN_CACHE_DIR (1 << 3) #define FOPEN_STREAM (1 << 4) #define FOPEN_NOFLUSH (1 << 5) +#define FOPEN_PARALLEL_DIRECT_WRITES (1 << 6) /** * INIT request/reply flags -- cgit From fb491d5500a7ca551e49bc32d9b19d226023f68d Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Fri, 11 Nov 2022 18:06:27 +0100 Subject: KVM: s390: pv: asynchronous destroy for reboot Until now, destroying a protected guest was an entirely synchronous operation that could potentially take a very long time, depending on the size of the guest, due to the time needed to clean up the address space from protected pages. This patch implements an asynchronous destroy mechanism, that allows a protected guest to reboot significantly faster than previously. This is achieved by clearing the pages of the old guest in background. In case of reboot, the new guest will be able to run in the same address space almost immediately. The old protected guest is then only destroyed when all of its memory has been destroyed or otherwise made non protected. Two new PV commands are added for the KVM_S390_PV_COMMAND ioctl: KVM_PV_ASYNC_CLEANUP_PREPARE: set aside the current protected VM for later asynchronous teardown. The current KVM VM will then continue immediately as non-protected. If a protected VM had already been set aside for asynchronous teardown, but without starting the teardown process, this call will fail. There can be at most one VM set aside at any time. Once it is set aside, the protected VM only exists in the context of the Ultravisor, it is not associated with the KVM VM anymore. Its protected CPUs have already been destroyed, but not its memory. This command can be issued again immediately after starting KVM_PV_ASYNC_CLEANUP_PERFORM, without having to wait for completion. KVM_PV_ASYNC_CLEANUP_PERFORM: tears down the protected VM previously set aside using KVM_PV_ASYNC_CLEANUP_PREPARE. Ideally the KVM_PV_ASYNC_CLEANUP_PERFORM PV command should be issued by userspace from a separate thread. If a fatal signal is received (or if the process terminates naturally), the command will terminate immediately without completing. All protected VMs whose teardown was interrupted will be put in the need_cleanup list. The rest of the normal KVM teardown process will take care of properly cleaning up all remaining protected VMs, including the ones on the need_cleanup list. Signed-off-by: Claudio Imbrenda Reviewed-by: Nico Boehr Reviewed-by: Janosch Frank Reviewed-by: Steffen Eiden Link: https://lore.kernel.org/r/20221111170632.77622-2-imbrenda@linux.ibm.com Message-Id: <20221111170632.77622-2-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/include/asm/kvm_host.h | 2 + arch/s390/kvm/kvm-s390.c | 49 +++++-- arch/s390/kvm/kvm-s390.h | 3 + arch/s390/kvm/pv.c | 295 +++++++++++++++++++++++++++++++++++++-- include/uapi/linux/kvm.h | 2 + 5 files changed, 333 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h index 21f1339a4197..d67ce719d16a 100644 --- a/arch/s390/include/asm/kvm_host.h +++ b/arch/s390/include/asm/kvm_host.h @@ -942,6 +942,8 @@ struct kvm_s390_pv { unsigned long stor_base; void *stor_var; bool dumping; + void *set_aside; + struct list_head need_cleanup; struct mmu_notifier mmu_notifier; }; diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index bd6e0201bfe5..f0abaaf7eea4 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -209,6 +209,8 @@ unsigned int diag9c_forwarding_hz; module_param(diag9c_forwarding_hz, uint, 0644); MODULE_PARM_DESC(diag9c_forwarding_hz, "Maximum diag9c forwarding per second, 0 to turn off"); +static int async_destroy; + /* * For now we handle at most 16 double words as this is what the s390 base * kernel handles and stores in the prefix page. If we ever need to go beyond @@ -2504,9 +2506,13 @@ static int kvm_s390_pv_dmp(struct kvm *kvm, struct kvm_pv_cmd *cmd, static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) { + const bool need_lock = (cmd->cmd != KVM_PV_ASYNC_CLEANUP_PERFORM); + void __user *argp = (void __user *)cmd->data; int r = 0; u16 dummy; - void __user *argp = (void __user *)cmd->data; + + if (need_lock) + mutex_lock(&kvm->lock); switch (cmd->cmd) { case KVM_PV_ENABLE: { @@ -2540,6 +2546,31 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); break; } + case KVM_PV_ASYNC_CLEANUP_PREPARE: + r = -EINVAL; + if (!kvm_s390_pv_is_protected(kvm) || !async_destroy) + break; + + r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc); + /* + * If a CPU could not be destroyed, destroy VM will also fail. + * There is no point in trying to destroy it. Instead return + * the rc and rrc from the first CPU that failed destroying. + */ + if (r) + break; + r = kvm_s390_pv_set_aside(kvm, &cmd->rc, &cmd->rrc); + + /* no need to block service interrupts any more */ + clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); + break; + case KVM_PV_ASYNC_CLEANUP_PERFORM: + r = -EINVAL; + if (!async_destroy) + break; + /* kvm->lock must not be held; this is asserted inside the function. */ + r = kvm_s390_pv_deinit_aside_vm(kvm, &cmd->rc, &cmd->rrc); + break; case KVM_PV_DISABLE: { r = -EINVAL; if (!kvm_s390_pv_is_protected(kvm)) @@ -2553,7 +2584,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) */ if (r) break; - r = kvm_s390_pv_deinit_vm(kvm, &cmd->rc, &cmd->rrc); + r = kvm_s390_pv_deinit_cleanup_all(kvm, &cmd->rc, &cmd->rrc); /* no need to block service interrupts any more */ clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs); @@ -2703,6 +2734,9 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd) default: r = -ENOTTY; } + if (need_lock) + mutex_unlock(&kvm->lock); + return r; } @@ -2907,9 +2941,8 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EINVAL; break; } - mutex_lock(&kvm->lock); + /* must be called without kvm->lock */ r = kvm_s390_handle_pv(kvm, &args); - mutex_unlock(&kvm->lock); if (copy_to_user(argp, &args, sizeof(args))) { r = -EFAULT; break; @@ -3228,6 +3261,8 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type) kvm_s390_vsie_init(kvm); if (use_gisa) kvm_s390_gisa_init(kvm); + INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup); + kvm->arch.pv.set_aside = NULL; KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid); return 0; @@ -3272,11 +3307,9 @@ void kvm_arch_destroy_vm(struct kvm *kvm) /* * We are already at the end of life and kvm->lock is not taken. * This is ok as the file descriptor is closed by now and nobody - * can mess with the pv state. To avoid lockdep_assert_held from - * complaining we do not use kvm_s390_pv_is_protected. + * can mess with the pv state. */ - if (kvm_s390_pv_get_handle(kvm)) - kvm_s390_pv_deinit_vm(kvm, &rc, &rrc); + kvm_s390_pv_deinit_cleanup_all(kvm, &rc, &rrc); /* * Remove the mmu notifier only when the whole KVM VM is torn down, * and only if one was registered to begin with. If the VM is diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h index a60d1e5c44cd..826754937ae4 100644 --- a/arch/s390/kvm/kvm-s390.h +++ b/arch/s390/kvm/kvm-s390.h @@ -244,6 +244,9 @@ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm) /* implemented in pv.c */ int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc); +int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_deinit_aside_vm(struct kvm *kvm, u16 *rc, u16 *rrc); +int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc); int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc); int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc); int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc, diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c index 48c4f57d5d76..5f958fcf6283 100644 --- a/arch/s390/kvm/pv.c +++ b/arch/s390/kvm/pv.c @@ -18,6 +18,29 @@ #include #include "kvm-s390.h" +/** + * struct pv_vm_to_be_destroyed - Represents a protected VM that needs to + * be destroyed + * + * @list: list head for the list of leftover VMs + * @old_gmap_table: the gmap table of the leftover protected VM + * @handle: the handle of the leftover protected VM + * @stor_var: pointer to the variable storage of the leftover protected VM + * @stor_base: address of the base storage of the leftover protected VM + * + * Represents a protected VM that is still registered with the Ultravisor, + * but which does not correspond any longer to an active KVM VM. It should + * be destroyed at some point later, either asynchronously or when the + * process terminates. + */ +struct pv_vm_to_be_destroyed { + struct list_head list; + unsigned long old_gmap_table; + u64 handle; + void *stor_var; + unsigned long stor_base; +}; + static void kvm_s390_clear_pv_state(struct kvm *kvm) { kvm->arch.pv.handle = 0; @@ -161,23 +184,150 @@ out_err: return -ENOMEM; } -/* this should not fail, but if it does, we must not free the donated memory */ -int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +/** + * kvm_s390_pv_dispose_one_leftover - Clean up one leftover protected VM. + * @kvm: the KVM that was associated with this leftover protected VM + * @leftover: details about the leftover protected VM that needs a clean up + * @rc: the RC code of the Destroy Secure Configuration UVC + * @rrc: the RRC code of the Destroy Secure Configuration UVC + * + * Destroy one leftover protected VM. + * On success, kvm->mm->context.protected_count will be decremented atomically + * and all other resources used by the VM will be freed. + * + * Return: 0 in case of success, otherwise 1 + */ +static int kvm_s390_pv_dispose_one_leftover(struct kvm *kvm, + struct pv_vm_to_be_destroyed *leftover, + u16 *rc, u16 *rrc) { int cc; - cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), - UVC_CMD_DESTROY_SEC_CONF, rc, rrc); - WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); + cc = uv_cmd_nodata(leftover->handle, UVC_CMD_DESTROY_SEC_CONF, rc, rrc); + KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY LEFTOVER VM: rc %x rrc %x", *rc, *rrc); + WARN_ONCE(cc, "protvirt destroy leftover vm failed rc %x rrc %x", *rc, *rrc); + if (cc) + return cc; /* - * if the mm still has a mapping, make all its pages accessible - * before destroying the guest + * Intentionally leak unusable memory. If the UVC fails, the memory + * used for the VM and its metadata is permanently unusable. + * This can only happen in case of a serious KVM or hardware bug; it + * is not expected to happen in normal operation. */ - if (mmget_not_zero(kvm->mm)) { - s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE); - mmput(kvm->mm); + free_pages(leftover->stor_base, get_order(uv_info.guest_base_stor_len)); + free_pages(leftover->old_gmap_table, CRST_ALLOC_ORDER); + vfree(leftover->stor_var); + atomic_dec(&kvm->mm->context.protected_count); + return 0; +} + +/** + * kvm_s390_destroy_lower_2g - Destroy the first 2GB of protected guest memory. + * @kvm: the VM whose memory is to be cleared. + * + * Destroy the first 2GB of guest memory, to avoid prefix issues after reboot. + * The CPUs of the protected VM need to be destroyed beforehand. + */ +static void kvm_s390_destroy_lower_2g(struct kvm *kvm) +{ + const unsigned long pages_2g = SZ_2G / PAGE_SIZE; + struct kvm_memory_slot *slot; + unsigned long len; + int srcu_idx; + + srcu_idx = srcu_read_lock(&kvm->srcu); + + /* Take the memslot containing guest absolute address 0 */ + slot = gfn_to_memslot(kvm, 0); + /* Clear all slots or parts thereof that are below 2GB */ + while (slot && slot->base_gfn < pages_2g) { + len = min_t(u64, slot->npages, pages_2g - slot->base_gfn) * PAGE_SIZE; + s390_uv_destroy_range(kvm->mm, slot->userspace_addr, slot->userspace_addr + len); + /* Take the next memslot */ + slot = gfn_to_memslot(kvm, slot->base_gfn + slot->npages); + } + + srcu_read_unlock(&kvm->srcu, srcu_idx); +} + +/** + * kvm_s390_pv_set_aside - Set aside a protected VM for later teardown. + * @kvm: the VM + * @rc: return value for the RC field of the UVCB + * @rrc: return value for the RRC field of the UVCB + * + * Set aside the protected VM for a subsequent teardown. The VM will be able + * to continue immediately as a non-secure VM, and the information needed to + * properly tear down the protected VM is set aside. If another protected VM + * was already set aside without starting its teardown, this function will + * fail. + * The CPUs of the protected VM need to be destroyed beforehand. + * + * Context: kvm->lock needs to be held + * + * Return: 0 in case of success, -EINVAL if another protected VM was already set + * aside, -ENOMEM if the system ran out of memory. + */ +int kvm_s390_pv_set_aside(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct pv_vm_to_be_destroyed *priv; + + lockdep_assert_held(&kvm->lock); + /* + * If another protected VM was already prepared for teardown, refuse. + * A normal deinitialization has to be performed instead. + */ + if (kvm->arch.pv.set_aside) + return -EINVAL; + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->stor_var = kvm->arch.pv.stor_var; + priv->stor_base = kvm->arch.pv.stor_base; + priv->handle = kvm_s390_pv_get_handle(kvm); + priv->old_gmap_table = (unsigned long)kvm->arch.gmap->table; + WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); + if (s390_replace_asce(kvm->arch.gmap)) { + kfree(priv); + return -ENOMEM; } + kvm_s390_destroy_lower_2g(kvm); + kvm_s390_clear_pv_state(kvm); + kvm->arch.pv.set_aside = priv; + + *rc = UVC_RC_EXECUTED; + *rrc = 42; + return 0; +} + +/** + * kvm_s390_pv_deinit_vm - Deinitialize the current protected VM + * @kvm: the KVM whose protected VM needs to be deinitialized + * @rc: the RC code of the UVC + * @rrc: the RRC code of the UVC + * + * Deinitialize the current protected VM. This function will destroy and + * cleanup the current protected VM, but it will not cleanup the guest + * memory. This function should only be called when the protected VM has + * just been created and therefore does not have any guest memory, or when + * the caller cleans up the guest memory separately. + * + * This function should not fail, but if it does, the donated memory must + * not be freed. + * + * Context: kvm->lock needs to be held + * + * Return: 0 in case of success, otherwise -EIO + */ +int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + int cc; + + cc = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm), + UVC_CMD_DESTROY_SEC_CONF, rc, rrc); + WRITE_ONCE(kvm->arch.gmap->guest_handle, 0); if (!cc) { atomic_dec(&kvm->mm->context.protected_count); kvm_s390_pv_dealloc_vm(kvm); @@ -191,6 +341,131 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc) return cc ? -EIO : 0; } +/** + * kvm_s390_pv_deinit_cleanup_all - Clean up all protected VMs associated + * with a specific KVM. + * @kvm: the KVM to be cleaned up + * @rc: the RC code of the first failing UVC + * @rrc: the RRC code of the first failing UVC + * + * This function will clean up all protected VMs associated with a KVM. + * This includes the active one, the one prepared for deinitialization with + * kvm_s390_pv_set_aside, and any still pending in the need_cleanup list. + * + * Context: kvm->lock needs to be held unless being called from + * kvm_arch_destroy_vm. + * + * Return: 0 if all VMs are successfully cleaned up, otherwise -EIO + */ +int kvm_s390_pv_deinit_cleanup_all(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct pv_vm_to_be_destroyed *cur; + bool need_zap = false; + u16 _rc, _rrc; + int cc = 0; + + /* Make sure the counter does not reach 0 before calling s390_uv_destroy_range */ + atomic_inc(&kvm->mm->context.protected_count); + + *rc = 1; + /* If the current VM is protected, destroy it */ + if (kvm_s390_pv_get_handle(kvm)) { + cc = kvm_s390_pv_deinit_vm(kvm, rc, rrc); + need_zap = true; + } + + /* If a previous protected VM was set aside, put it in the need_cleanup list */ + if (kvm->arch.pv.set_aside) { + list_add(kvm->arch.pv.set_aside, &kvm->arch.pv.need_cleanup); + kvm->arch.pv.set_aside = NULL; + } + + /* Cleanup all protected VMs in the need_cleanup list */ + while (!list_empty(&kvm->arch.pv.need_cleanup)) { + cur = list_first_entry(&kvm->arch.pv.need_cleanup, typeof(*cur), list); + need_zap = true; + if (kvm_s390_pv_dispose_one_leftover(kvm, cur, &_rc, &_rrc)) { + cc = 1; + /* + * Only return the first error rc and rrc, so make + * sure it is not overwritten. All destroys will + * additionally be reported via KVM_UV_EVENT(). + */ + if (*rc == UVC_RC_EXECUTED) { + *rc = _rc; + *rrc = _rrc; + } + } + list_del(&cur->list); + kfree(cur); + } + + /* + * If the mm still has a mapping, try to mark all its pages as + * accessible. The counter should not reach zero before this + * cleanup has been performed. + */ + if (need_zap && mmget_not_zero(kvm->mm)) { + s390_uv_destroy_range(kvm->mm, 0, TASK_SIZE); + mmput(kvm->mm); + } + + /* Now the counter can safely reach 0 */ + atomic_dec(&kvm->mm->context.protected_count); + return cc ? -EIO : 0; +} + +/** + * kvm_s390_pv_deinit_aside_vm - Teardown a previously set aside protected VM. + * @kvm: the VM previously associated with the protected VM + * @rc: return value for the RC field of the UVCB + * @rrc: return value for the RRC field of the UVCB + * + * Tear down the protected VM that had been previously prepared for teardown + * using kvm_s390_pv_set_aside_vm. Ideally this should be called by + * userspace asynchronously from a separate thread. + * + * Context: kvm->lock must not be held. + * + * Return: 0 in case of success, -EINVAL if no protected VM had been + * prepared for asynchronous teardowm, -EIO in case of other errors. + */ +int kvm_s390_pv_deinit_aside_vm(struct kvm *kvm, u16 *rc, u16 *rrc) +{ + struct pv_vm_to_be_destroyed *p; + int ret = 0; + + lockdep_assert_not_held(&kvm->lock); + mutex_lock(&kvm->lock); + p = kvm->arch.pv.set_aside; + kvm->arch.pv.set_aside = NULL; + mutex_unlock(&kvm->lock); + if (!p) + return -EINVAL; + + /* When a fatal signal is received, stop immediately */ + if (s390_uv_destroy_range_interruptible(kvm->mm, 0, TASK_SIZE_MAX)) + goto done; + if (kvm_s390_pv_dispose_one_leftover(kvm, p, rc, rrc)) + ret = -EIO; + kfree(p); + p = NULL; +done: + /* + * p is not NULL if we aborted because of a fatal signal, in which + * case queue the leftover for later cleanup. + */ + if (p) { + mutex_lock(&kvm->lock); + list_add(&p->list, &kvm->arch.pv.need_cleanup); + mutex_unlock(&kvm->lock); + /* Did not finish, but pretend things went well */ + *rc = UVC_RC_EXECUTED; + *rrc = 42; + } + return ret; +} + static void kvm_s390_pv_mmu_notifier_release(struct mmu_notifier *subscription, struct mm_struct *mm) { diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0d5d4419139a..b3701b23ca18 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1740,6 +1740,8 @@ enum pv_cmd_id { KVM_PV_UNSHARE_ALL, KVM_PV_INFO, KVM_PV_DUMP, + KVM_PV_ASYNC_CLEANUP_PREPARE, + KVM_PV_ASYNC_CLEANUP_PERFORM, }; struct kvm_pv_cmd { -- cgit From 8c516b25d6e9c70e6d76627932b14b0ef03a82c4 Mon Sep 17 00:00:00 2001 From: Claudio Imbrenda Date: Fri, 11 Nov 2022 18:06:29 +0100 Subject: KVM: s390: pv: add KVM_CAP_S390_PROTECTED_ASYNC_DISABLE Add KVM_CAP_S390_PROTECTED_ASYNC_DISABLE to signal that the KVM_PV_ASYNC_DISABLE and KVM_PV_ASYNC_DISABLE_PREPARE commands for the KVM_S390_PV_COMMAND ioctl are available. Signed-off-by: Claudio Imbrenda Reviewed-by: Nico Boehr Reviewed-by: Steffen Eiden Reviewed-by: Janosch Frank Link: https://lore.kernel.org/r/20221111170632.77622-4-imbrenda@linux.ibm.com Message-Id: <20221111170632.77622-4-imbrenda@linux.ibm.com> Signed-off-by: Janosch Frank --- arch/s390/kvm/kvm-s390.c | 3 +++ include/uapi/linux/kvm.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c index f0abaaf7eea4..b6cc7d2935c0 100644 --- a/arch/s390/kvm/kvm-s390.c +++ b/arch/s390/kvm/kvm-s390.c @@ -618,6 +618,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) case KVM_CAP_S390_BPB: r = test_facility(82); break; + case KVM_CAP_S390_PROTECTED_ASYNC_DISABLE: + r = async_destroy && is_prot_virt_host(); + break; case KVM_CAP_S390_PROTECTED: r = is_prot_virt_host(); break; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index b3701b23ca18..d3f86a280858 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1178,6 +1178,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_S390_ZPCI_OP 221 #define KVM_CAP_S390_CPU_TOPOLOGY 222 #define KVM_CAP_DIRTY_LOG_RING_ACQ_REL 223 +#define KVM_CAP_S390_PROTECTED_ASYNC_DISABLE 224 #ifdef KVM_CAP_IRQ_ROUTING -- cgit From 1dbb4f0235a450f22e518124cbf9b922802ce38f Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Wed, 16 Nov 2022 18:29:56 +0200 Subject: virt: acrn: Mark the uuid field as unused After the commits for userspace (see Link tags below) the uuid field is not being used in the ACRN code. Update kernel to reflect these changes, i.e. do the following: - adding a comment explaining that it's not used anymore - replacing the specific type by a raw buffer - updating the example code accordingly The advertised field confused users and actually never been used. So the wrong part here is that kernel puts something which userspace never used and hence this may confuse a reader of this code. Note, that there is only a single tool that had been prepared a year ago for these forthcoming changes in the kernel. Link: https://github.com/projectacrn/acrn-hypervisor/commit/da0d24326ed6 Link: https://github.com/projectacrn/acrn-hypervisor/commit/bb0327e70097 Signed-off-by: Andy Shevchenko Acked-by: Rafael J. Wysocki Link: https://lore.kernel.org/r/20221116162956.72658-1-andriy.shevchenko@linux.intel.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/acrn.h | 5 ++--- samples/acrn/vm-sample.c | 3 --- 2 files changed, 2 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index ccf47ed92500..7b714c1902eb 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -12,7 +12,6 @@ #define _UAPI_ACRN_H #include -#include #define ACRN_IO_REQUEST_MAX 16 @@ -186,7 +185,7 @@ struct acrn_ioreq_notify { * @reserved0: Reserved and must be 0 * @vcpu_num: Number of vCPU in the VM. Return from hypervisor. * @reserved1: Reserved and must be 0 - * @uuid: UUID of the VM. Pass to hypervisor directly. + * @uuid: Empty space never to be used again (used to be UUID of the VM) * @vm_flag: Flag of the VM creating. Pass to hypervisor directly. * @ioreq_buf: Service VM GPA of I/O request buffer. Pass to * hypervisor directly. @@ -198,7 +197,7 @@ struct acrn_vm_creation { __u16 reserved0; __u16 vcpu_num; __u16 reserved1; - guid_t uuid; + __u8 uuid[16]; __u64 vm_flag; __u64 ioreq_buf; __u64 cpu_affinity; diff --git a/samples/acrn/vm-sample.c b/samples/acrn/vm-sample.c index b2dad47a77a0..7abd68b20153 100644 --- a/samples/acrn/vm-sample.c +++ b/samples/acrn/vm-sample.c @@ -29,8 +29,6 @@ static struct acrn_io_request *io_req_buf = (struct acrn_io_request *)io_request __u16 vcpu_num; __u16 vmid; -/* POST_STANDARD_VM_UUID1, refer to https://github.com/projectacrn/acrn-hypervisor/blob/master/hypervisor/include/common/vm_uuids.h */ -guid_t vm_uuid = GUID_INIT(0x385479d2, 0xd625, 0xe811, 0x86, 0x4e, 0xcb, 0x7a, 0x18, 0xb3, 0x46, 0x43); int hsm_fd; int is_running = 1; @@ -63,7 +61,6 @@ int main(int argc, char **argv) } hsm_fd = open("/dev/acrn_hsm", O_RDWR|O_CLOEXEC); - memcpy(&create_vm.uuid, &vm_uuid, 16); create_vm.ioreq_buf = (__u64)io_req_buf; ret = ioctl(hsm_fd, ACRN_IOCTL_CREATE_VM, &create_vm); printf("Created VM! [%d]\n", ret); -- cgit From 72b43bde38de4aa05e6a7fa12d7965f48180deb6 Mon Sep 17 00:00:00 2001 From: Ji Rongfeng Date: Fri, 18 Nov 2022 16:18:18 +0800 Subject: bpf: Update bpf_{g,s}etsockopt() documentation * append missing optnames to the end * simplify bpf_getsockopt()'s doc Signed-off-by: Ji Rongfeng Link: https://lore.kernel.org/r/DU0P192MB15479B86200B1216EC90E162D6099@DU0P192MB1547.EURP192.PROD.OUTLOOK.COM Signed-off-by: Martin KaFai Lau --- include/uapi/linux/bpf.h | 21 ++++++++++++--------- tools/include/uapi/linux/bpf.h | 23 +++++++++++++---------- 2 files changed, 25 insertions(+), 19 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index ab86145df760..f89de51a45db 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -2584,14 +2584,19 @@ union bpf_attr { * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. * Return * 0 on success, or a negative error in case of failure. * @@ -2808,12 +2813,10 @@ union bpf_attr { * and **BPF_CGROUP_INET6_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. - * It supports the following *level*\ s: - * - * * **IPPROTO_TCP**, which supports *optname* - * **TCP_CONGESTION**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. * Return * 0 on success, or a negative error in case of failure. * diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6580448e9f77..f89de51a45db 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -2584,14 +2584,19 @@ union bpf_attr { * * **SOL_SOCKET**, which supports the following *optname*\ s: * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**, - * **SO_BINDTODEVICE**, **SO_KEEPALIVE**. + * **SO_BINDTODEVICE**, **SO_KEEPALIVE**, **SO_REUSEADDR**, + * **SO_REUSEPORT**, **SO_BINDTOIFINDEX**, **SO_TXREHASH**. * * **IPPROTO_TCP**, which supports the following *optname*\ s: * **TCP_CONGESTION**, **TCP_BPF_IW**, * **TCP_BPF_SNDCWND_CLAMP**, **TCP_SAVE_SYN**, * **TCP_KEEPIDLE**, **TCP_KEEPINTVL**, **TCP_KEEPCNT**, - * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**. + * **TCP_SYNCNT**, **TCP_USER_TIMEOUT**, **TCP_NOTSENT_LOWAT**, + * **TCP_NODELAY**, **TCP_MAXSEG**, **TCP_WINDOW_CLAMP**, + * **TCP_THIN_LINEAR_TIMEOUTS**, **TCP_BPF_DELACK_MAX**, + * **TCP_BPF_RTO_MIN**. * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * * **IPPROTO_IPV6**, which supports the following *optname*\ s: + * **IPV6_TCLASS**, **IPV6_AUTOFLOWLABEL**. * Return * 0 on success, or a negative error in case of failure. * @@ -2647,7 +2652,7 @@ union bpf_attr { * Return * 0 on success, or a negative error in case of failure. * - * long bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * long bpf_redirect_map(struct bpf_map *map, u64 key, u64 flags) * Description * Redirect the packet to the endpoint referenced by *map* at * index *key*. Depending on its type, this *map* can contain @@ -2808,12 +2813,10 @@ union bpf_attr { * and **BPF_CGROUP_INET6_CONNECT**. * * This helper actually implements a subset of **getsockopt()**. - * It supports the following *level*\ s: - * - * * **IPPROTO_TCP**, which supports *optname* - * **TCP_CONGESTION**. - * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. - * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * It supports the same set of *optname*\ s that is supported by + * the **bpf_setsockopt**\ () helper. The exceptions are + * **TCP_BPF_*** is **bpf_setsockopt**\ () only and + * **TCP_SAVED_SYN** is **bpf_getsockopt**\ () only. * Return * 0 on success, or a negative error in case of failure. * -- cgit From 6508a50fe84f9858e8b59b53dce3847aaeeab744 Mon Sep 17 00:00:00 2001 From: Robert Schlabbach Date: Fri, 14 Jan 2022 07:43:48 +0000 Subject: media: dvb: add DVB-C2 and DVB-S2X parameter values Extend the DVB frontend parameter enums with additional values specified by the DVB-C2 (ETSI EN 302 769) and DVB-S2X (ETSI EN 302 307-2) standards to be ready for frontend drivers for such receivers. While most parameters will be "read-only" due to being autodetected by the receiver and only being reported back for informational purposes, the addition of SYS_DVBC2 to the delivery systems enum is required, because there are DVB-C2 capable receivers which are not capable of DVB-C/C2 autodetection and thus need this enum value to be explicitly instructed to search for a DVB-C2 signal. As for DVB-S2X, as that is an extension to DVB-S2, the same delivery system enum as for DVB-S2 can be used. Add the additional enum values and comments to the documentation. Link: https://lore.kernel.org/linux-media/trinity-1b7c5a66-85d4-4595-a690-0fde965d49b3-1642146228587@3c-app-gmx-bap69 Signed-off-by: Robert Schlabbach Signed-off-by: Mauro Carvalho Chehab --- .../media/dvb/fe_property_parameters.rst | 25 +++++---- include/uapi/linux/dvb/frontend.h | 59 +++++++++++++++++++++- 2 files changed, 74 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/dvb/fe_property_parameters.rst b/Documentation/userspace-api/media/dvb/fe_property_parameters.rst index ecd84a8790a2..1717a0565fe8 100644 --- a/Documentation/userspace-api/media/dvb/fe_property_parameters.rst +++ b/Documentation/userspace-api/media/dvb/fe_property_parameters.rst @@ -89,16 +89,21 @@ ATSC (version 1) 8-VSB and 16-VSB. DMTB 4-QAM, 16-QAM, 32-QAM, 64-QAM and 4-QAM-NR. DVB-C Annex A/C 16-QAM, 32-QAM, 64-QAM and 256-QAM. DVB-C Annex B 64-QAM. +DVB-C2 QPSK, 16-QAM, 64-QAM, 256-QAM, 1024-QAM and 4096-QAM. DVB-T QPSK, 16-QAM and 64-QAM. DVB-T2 QPSK, 16-QAM, 64-QAM and 256-QAM. DVB-S No need to set. It supports only QPSK. DVB-S2 QPSK, 8-PSK, 16-APSK and 32-APSK. +DVB-S2X 8-APSK-L, 16-APSK-L, 32-APSK-L, 64-APSK and 64-APSK-L. ISDB-T QPSK, DQPSK, 16-QAM and 64-QAM. ISDB-S 8-PSK, QPSK and BPSK. ======================= ======================================================= .. note:: + As DVB-S2X specifies extensions to the DVB-S2 standard, the same + delivery system enum value is used (SYS_DVBS2). + Please notice that some of the above modulation types may not be defined currently at the Kernel. The reason is simple: no driver needed such definition yet. @@ -854,9 +859,10 @@ The acceptable values are defined by :c:type:`fe_guard_interval`. #. If ``DTV_GUARD_INTERVAL`` is set the ``GUARD_INTERVAL_AUTO`` the hardware will try to find the correct guard interval (if capable) and will use TMCC to fill in the missing parameters. - #. Intervals ``GUARD_INTERVAL_1_128``, ``GUARD_INTERVAL_19_128`` - and ``GUARD_INTERVAL_19_256`` are used only for DVB-T2 at - present. + #. Interval ``GUARD_INTERVAL_1_64`` is used only for DVB-C2. + #. Interval ``GUARD_INTERVAL_1_128`` is used for both DVB-C2 and DVB_T2. + #. Intervals ``GUARD_INTERVAL_19_128`` and ``GUARD_INTERVAL_19_256`` are + used only for DVB-T2. #. Intervals ``GUARD_INTERVAL_PN420``, ``GUARD_INTERVAL_PN595`` and ``GUARD_INTERVAL_PN945`` are used only for DMTB at the present. On such standard, only those intervals and ``GUARD_INTERVAL_AUTO`` @@ -916,14 +922,15 @@ The acceptable values are defined by :c:type:`fe_hierarchy`. DTV_STREAM_ID ============= -Used on DVB-S2, DVB-T2 and ISDB-S. +Used on DVB-C2, DVB-S2, DVB-T2 and ISDB-S. -DVB-S2, DVB-T2 and ISDB-S support the transmission of several streams on -a single transport stream. This property enables the digital TV driver to -handle substream filtering, when supported by the hardware. By default, -substream filtering is disabled. +DVB-C2, DVB-S2, DVB-T2 and ISDB-S support the transmission of several +streams on a single transport stream. This property enables the digital +TV driver to handle substream filtering, when supported by the hardware. +By default, substream filtering is disabled. -For DVB-S2 and DVB-T2, the valid substream id range is from 0 to 255. +For DVB-C2, DVB-S2 and DVB-T2, the valid substream id range is from 0 to +255. For ISDB, the valid substream id range is from 1 to 65535. diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 4f9b4551c534..4fed9e316147 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -296,6 +296,22 @@ enum fe_spectral_inversion { * @FEC_3_5: Forward Error Correction Code 3/5 * @FEC_9_10: Forward Error Correction Code 9/10 * @FEC_2_5: Forward Error Correction Code 2/5 + * @FEC_1_3: Forward Error Correction Code 1/3 + * @FEC_1_4: Forward Error Correction Code 1/4 + * @FEC_5_9: Forward Error Correction Code 5/9 + * @FEC_7_9: Forward Error Correction Code 7/9 + * @FEC_8_15: Forward Error Correction Code 8/15 + * @FEC_11_15: Forward Error Correction Code 11/15 + * @FEC_13_18: Forward Error Correction Code 13/18 + * @FEC_9_20: Forward Error Correction Code 9/20 + * @FEC_11_20: Forward Error Correction Code 11/20 + * @FEC_23_36: Forward Error Correction Code 23/36 + * @FEC_25_36: Forward Error Correction Code 25/36 + * @FEC_13_45: Forward Error Correction Code 13/45 + * @FEC_26_45: Forward Error Correction Code 26/45 + * @FEC_28_45: Forward Error Correction Code 28/45 + * @FEC_32_45: Forward Error Correction Code 32/45 + * @FEC_77_90: Forward Error Correction Code 77/90 * * Please note that not all FEC types are supported by a given standard. */ @@ -313,6 +329,22 @@ enum fe_code_rate { FEC_3_5, FEC_9_10, FEC_2_5, + FEC_1_3, + FEC_1_4, + FEC_5_9, + FEC_7_9, + FEC_8_15, + FEC_11_15, + FEC_13_18, + FEC_9_20, + FEC_11_20, + FEC_23_36, + FEC_25_36, + FEC_13_45, + FEC_26_45, + FEC_28_45, + FEC_32_45, + FEC_77_90, }; /** @@ -331,6 +363,13 @@ enum fe_code_rate { * @APSK_32: 32-APSK modulation * @DQPSK: DQPSK modulation * @QAM_4_NR: 4-QAM-NR modulation + * @QAM-1024: 1024-QAM modulation + * @QAM-4096: 4096-QAM modulation + * @APSK_8_L: 8APSK-L modulation + * @APSK_16_L: 16APSK-L modulation + * @APSK_32_L: 32APSK-L modulation + * @APSK_64: 64APSK modulation + * @APSK_64_L: 64APSK-L modulation * * Please note that not all modulations are supported by a given standard. * @@ -350,6 +389,13 @@ enum fe_modulation { APSK_32, DQPSK, QAM_4_NR, + QAM_1024, + QAM_4096, + APSK_8_L, + APSK_16_L, + APSK_32_L, + APSK_64, + APSK_64_L, }; /** @@ -404,6 +450,7 @@ enum fe_transmit_mode { * @GUARD_INTERVAL_PN420: PN length 420 (1/4) * @GUARD_INTERVAL_PN595: PN length 595 (1/6) * @GUARD_INTERVAL_PN945: PN length 945 (1/9) + * @GUARD_INTERVAL_1_64: Guard interval 1/64 * * Please note that not all guard intervals are supported by a given standard. */ @@ -419,6 +466,7 @@ enum fe_guard_interval { GUARD_INTERVAL_PN420, GUARD_INTERVAL_PN595, GUARD_INTERVAL_PN945, + GUARD_INTERVAL_1_64, }; /** @@ -571,6 +619,9 @@ enum fe_pilot { * @ROLLOFF_20: Roloff factor: α=20% * @ROLLOFF_25: Roloff factor: α=25% * @ROLLOFF_AUTO: Auto-detect the roloff factor. + * @ROLLOFF_15: Rolloff factor: α=15% + * @ROLLOFF_10: Rolloff factor: α=10% + * @ROLLOFF_5: Rolloff factor: α=5% * * .. note: * @@ -581,6 +632,9 @@ enum fe_rolloff { ROLLOFF_20, ROLLOFF_25, ROLLOFF_AUTO, + ROLLOFF_15, + ROLLOFF_10, + ROLLOFF_5, }; /** @@ -594,6 +648,8 @@ enum fe_rolloff { * Cable TV: DVB-C following ITU-T J.83 Annex B spec (ClearQAM) * @SYS_DVBC_ANNEX_C: * Cable TV: DVB-C following ITU-T J.83 Annex C spec + * @SYS_DVBC2: + * Cable TV: DVB-C2 * @SYS_ISDBC: * Cable TV: ISDB-C (no drivers yet) * @SYS_DVBT: @@ -611,7 +667,7 @@ enum fe_rolloff { * @SYS_DVBS: * Satellite TV: DVB-S * @SYS_DVBS2: - * Satellite TV: DVB-S2 + * Satellite TV: DVB-S2 and DVB-S2X * @SYS_TURBO: * Satellite TV: DVB-S Turbo * @SYS_ISDBS: @@ -645,6 +701,7 @@ enum fe_delivery_system { SYS_DVBT2, SYS_TURBO, SYS_DVBC_ANNEX_C, + SYS_DVBC2, }; /* backward compatibility definitions for delivery systems */ -- cgit From 5b8bb216e91a2f4f4d5b82739c0101b3922064e5 Mon Sep 17 00:00:00 2001 From: Ming Qian Date: Thu, 25 Aug 2022 02:38:29 +0100 Subject: media: add nv12_8l128 and nv12_10be_8l128 video format. add contiguous nv12 tiled format nv12_8l128 and nv12_10be_8l128 Signed-off-by: Ming Qian Reviewed-by: Nicolas Dufresne Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst | 8 ++++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 2 ++ include/uapi/linux/videodev2.h | 2 ++ 3 files changed, 12 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 10b1feeb0b57..f1d5bb7b806d 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -273,7 +273,9 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12-16L16: .. _V4L2-PIX-FMT-NV12-32L32: .. _V4L2-PIX-FMT-NV12M-8L128: +.. _V4L2-PIX-FMT-NV12-8L128: .. _V4L2-PIX-FMT-NV12M-10BE-8L128: +.. _V4L2-PIX-FMT-NV12-10BE-8L128: .. _V4L2-PIX-FMT-MM21: Tiled NV12 @@ -319,6 +321,9 @@ pixels in 2D 8x128 tiles, and stores tiles linearly in memory. The image height must be aligned to a multiple of 128. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_8L128`` is similar to ``V4L2_PIX_FMT_NV12M_8L128`` but stores +two planes in one memory. + ``V4L2_PIX_FMT_NV12M_10BE_8L128`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores 10 bits pixels in 2D 8x128 tiles, and stores tiles linearly in memory. the data is arranged in big endian order. @@ -334,6 +339,9 @@ byte 2: Y1(bits 3-0) Y2(bits 9-6) byte 3: Y2(bits 5-0) Y3(bits 9-8) byte 4: Y3(bits 7-0) +``V4L2_PIX_FMT_NV12_10BE_8L128`` is similar to ``V4L2_PIX_FMT_NV12M_10BE_8L128`` but stores +two planes in one memory. + ``V4L2_PIX_FMT_MM21`` store luma pixel in 16x32 tiles, and chroma pixels in 16x16 tiles. The line stride must be aligned to a multiple of 16 and the image height must be aligned to a multiple of 32. The number of luma and chroma diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 9010b9f68e8f..8e0a0ff62a70 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1438,7 +1438,9 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_META_FMT_VIVID: descr = "Vivid Metadata"; break; case V4L2_META_FMT_RK_ISP1_PARAMS: descr = "Rockchip ISP1 3A Parameters"; break; case V4L2_META_FMT_RK_ISP1_STAT_3A: descr = "Rockchip ISP1 3A Statistics"; break; + case V4L2_PIX_FMT_NV12_8L128: descr = "NV12 (8x128 Linear)"; break; case V4L2_PIX_FMT_NV12M_8L128: descr = "NV12M (8x128 Linear)"; break; + case V4L2_PIX_FMT_NV12_10BE_8L128: descr = "10-bit NV12 (8x128 Linear, BE)"; break; case V4L2_PIX_FMT_NV12M_10BE_8L128: descr = "10-bit NV12M (8x128 Linear, BE)"; break; default: diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index e8c621ad8439..1befd181a4cc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -654,6 +654,8 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV12_16L16 v4l2_fourcc('H', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ #define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ #define V4L2_PIX_FMT_P010_4L4 v4l2_fourcc('T', '0', '1', '0') /* 12 Y/CbCr 4:2:0 10-bit 4x4 macroblocks */ +#define V4L2_PIX_FMT_NV12_8L128 v4l2_fourcc('A', 'T', '1', '2') /* Y/CbCr 4:2:0 8x128 tiles */ +#define V4L2_PIX_FMT_NV12_10BE_8L128 v4l2_fourcc_be('A', 'X', '1', '2') /* Y/CbCr 4:2:0 10-bit 8x128 tiles */ /* Tiled YUV formats, non contiguous planes */ #define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 tiles */ -- cgit From 41e8f85a75fc60e1543e4903428a1b481b672a17 Mon Sep 17 00:00:00 2001 From: Daeho Jeong Date: Fri, 11 Nov 2022 09:04:06 -0800 Subject: f2fs: introduce F2FS_IOC_START_ATOMIC_REPLACE introduce a new ioctl to replace the whole content of a file atomically, which means it induces truncate and content update at the same time. We can start it with F2FS_IOC_START_ATOMIC_REPLACE and complete it with F2FS_IOC_COMMIT_ATOMIC_WRITE. Or abort it with F2FS_IOC_ABORT_ATOMIC_WRITE. Signed-off-by: Daeho Jeong Reviewed-by: Chao Yu Signed-off-by: Jaegeuk Kim --- fs/f2fs/data.c | 3 +++ fs/f2fs/f2fs.h | 1 + fs/f2fs/file.c | 21 +++++++++++++++------ fs/f2fs/segment.c | 13 ++++++++++++- include/uapi/linux/f2fs.h | 1 + 5 files changed, 32 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 9b47ded653d1..560fa80590e9 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -3466,6 +3466,9 @@ static int prepare_atomic_write_begin(struct f2fs_sb_info *sbi, else if (*blk_addr != NULL_ADDR) return 0; + if (is_inode_flag_set(inode, FI_ATOMIC_REPLACE)) + goto reserve_block; + /* Look for the block in the original inode */ err = __find_data_block(inode, index, &ori_blk_addr); if (err) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 6a8cbf5bb187..b89b5d755ce0 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -769,6 +769,7 @@ enum { FI_ALIGNED_WRITE, /* enable aligned write */ FI_COW_FILE, /* indicate COW file */ FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */ + FI_ATOMIC_REPLACE, /* indicate atomic replace */ FI_MAX, /* max flag, never be used */ }; diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c index 28f586e77999..ab0a0d3730f6 100644 --- a/fs/f2fs/file.c +++ b/fs/f2fs/file.c @@ -2034,7 +2034,7 @@ static int f2fs_ioc_getversion(struct file *filp, unsigned long arg) return put_user(inode->i_generation, (int __user *)arg); } -static int f2fs_ioc_start_atomic_write(struct file *filp) +static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate) { struct inode *inode = file_inode(filp); struct user_namespace *mnt_userns = file_mnt_user_ns(filp); @@ -2103,15 +2103,22 @@ static int f2fs_ioc_start_atomic_write(struct file *filp) f2fs_write_inode(inode, NULL); - isize = i_size_read(inode); - fi->original_i_size = isize; - f2fs_i_size_write(fi->cow_inode, isize); - stat_inc_atomic_inode(inode); set_inode_flag(inode, FI_ATOMIC_FILE); set_inode_flag(fi->cow_inode, FI_COW_FILE); clear_inode_flag(fi->cow_inode, FI_INLINE_DATA); + + isize = i_size_read(inode); + fi->original_i_size = isize; + if (truncate) { + set_inode_flag(inode, FI_ATOMIC_REPLACE); + truncate_inode_pages_final(inode->i_mapping); + f2fs_i_size_write(inode, 0); + isize = 0; + } + f2fs_i_size_write(fi->cow_inode, isize); + f2fs_up_write(&fi->i_gc_rwsem[WRITE]); f2fs_update_time(sbi, REQ_TIME); @@ -4139,7 +4146,9 @@ static long __f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) case FS_IOC_GETVERSION: return f2fs_ioc_getversion(filp, arg); case F2FS_IOC_START_ATOMIC_WRITE: - return f2fs_ioc_start_atomic_write(filp); + return f2fs_ioc_start_atomic_write(filp, false); + case F2FS_IOC_START_ATOMIC_REPLACE: + return f2fs_ioc_start_atomic_write(filp, true); case F2FS_IOC_COMMIT_ATOMIC_WRITE: return f2fs_ioc_commit_atomic_write(filp); case F2FS_IOC_ABORT_ATOMIC_WRITE: diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c index 8aa81238c770..5ac026a57228 100644 --- a/fs/f2fs/segment.c +++ b/fs/f2fs/segment.c @@ -197,6 +197,7 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean) fi->cow_inode = NULL; release_atomic_write_cnt(inode); clear_inode_flag(inode, FI_ATOMIC_COMMITTED); + clear_inode_flag(inode, FI_ATOMIC_REPLACE); clear_inode_flag(inode, FI_ATOMIC_FILE); stat_dec_atomic_inode(inode); @@ -261,14 +262,24 @@ static void __complete_revoke_list(struct inode *inode, struct list_head *head, bool revoke) { struct revoke_entry *cur, *tmp; + pgoff_t start_index = 0; + bool truncate = is_inode_flag_set(inode, FI_ATOMIC_REPLACE); list_for_each_entry_safe(cur, tmp, head, list) { - if (revoke) + if (revoke) { __replace_atomic_write_block(inode, cur->index, cur->old_addr, NULL, true); + } else if (truncate) { + f2fs_truncate_hole(inode, start_index, cur->index); + start_index = cur->index + 1; + } + list_del(&cur->list); kmem_cache_free(revoke_entry_slab, cur); } + + if (!revoke && truncate) + f2fs_do_truncate_blocks(inode, start_index * PAGE_SIZE, false); } static int __f2fs_commit_atomic_write(struct inode *inode) diff --git a/include/uapi/linux/f2fs.h b/include/uapi/linux/f2fs.h index 3121d127d5aa..955d440be104 100644 --- a/include/uapi/linux/f2fs.h +++ b/include/uapi/linux/f2fs.h @@ -42,6 +42,7 @@ struct f2fs_comp_option) #define F2FS_IOC_DECOMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 23) #define F2FS_IOC_COMPRESS_FILE _IO(F2FS_IOCTL_MAGIC, 24) +#define F2FS_IOC_START_ATOMIC_REPLACE _IO(F2FS_IOCTL_MAGIC, 25) /* * should be same as XFS_IOC_GOINGDOWN. -- cgit From d8ba8ba4c801b794f47852a6f1821ea48f83b5d1 Mon Sep 17 00:00:00 2001 From: David Woodhouse Date: Sun, 27 Nov 2022 12:22:10 +0000 Subject: KVM: x86/xen: Allow XEN_RUNSTATE_UPDATE flag behaviour to be configured Closer inspection of the Xen code shows that we aren't supposed to be using the XEN_RUNSTATE_UPDATE flag unconditionally. It should be explicitly enabled by guests through the HYPERVISOR_vm_assist hypercall. If we randomly set the top bit of ->state_entry_time for a guest that hasn't asked for it and doesn't expect it, that could make the runtimes fail to add up and confuse the guest. Without the flag it's perfectly safe for a vCPU to read its own vcpu_runstate_info; just not for one vCPU to read *another's*. I briefly pondered adding a word for the whole set of VMASST_TYPE_* flags but the only one we care about for HVM guests is this, so it seemed a bit pointless. Signed-off-by: David Woodhouse Message-Id: <20221127122210.248427-3-dwmw2@infradead.org> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 34 ++++++++++--- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/x86.c | 3 +- arch/x86/kvm/xen.c | 57 +++++++++++++++++----- include/uapi/linux/kvm.h | 4 ++ .../testing/selftests/kvm/x86_64/xen_shinfo_test.c | 14 ++++++ 6 files changed, 93 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 9175d41e8081..5617bc4f899f 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -5339,6 +5339,7 @@ KVM_PV_ASYNC_CLEANUP_PERFORM union { __u8 long_mode; __u8 vector; + __u8 runstate_update_flag; struct { __u64 gfn; } shared_info; @@ -5416,6 +5417,14 @@ KVM_XEN_ATTR_TYPE_XEN_VERSION event channel delivery, so responding within the kernel without exiting to userspace is beneficial. +KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG + This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates + support for KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG. It enables the + XEN_RUNSTATE_UPDATE flag which allows guest vCPUs to safely read + other vCPUs' vcpu_runstate_info. Xen guests enable this feature via + the VM_ASST_TYPE_runstate_update_flag of the HYPERVISOR_vm_assist + hypercall. + 4.127 KVM_XEN_HVM_GET_ATTR -------------------------- @@ -8059,12 +8068,13 @@ to userspace. This capability indicates the features that Xen supports for hosting Xen PVHVM guests. Valid flags are:: - #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) - #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) - #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) - #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) - #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) - #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) + #define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0) + #define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1) + #define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2) + #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) + #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) + #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) + #define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG ioctl is available, for the guest to set its hypercall page. @@ -8096,6 +8106,18 @@ KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_VECTOR vCPU attributes. related to event channel delivery, timers, and the XENVER_version interception. +The KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG flag indicates that KVM supports +the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute in the KVM_XEN_SET_ATTR +and KVM_XEN_GET_ATTR ioctls. This controls whether KVM will set the +XEN_RUNSTATE_UPDATE flag in guest memory mapped vcpu_runstate_info during +updates of the runstate information. Note that versions of KVM which support +the RUNSTATE feature above, but not thie RUNSTATE_UPDATE_FLAG feature, will +always set the XEN_RUNSTATE_UPDATE flag when updating the guest structure, +which is perhaps counterintuitive. When this flag is advertised, KVM will +behave more correctly, not using the XEN_RUNSTATE_UPDATE flag until/unless +specifically enabled (by the guest making the hypercall, causing the VMM +to enable the KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG attribute). + 8.31 KVM_CAP_PPC_MULTITCE ------------------------- diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 70af7240a1d5..283cbb83d6ae 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1113,6 +1113,7 @@ struct msr_bitmap_range { struct kvm_xen { u32 xen_version; bool long_mode; + bool runstate_update_flag; u8 upcall_vector; struct gfn_to_pfn_cache shinfo_cache; struct idr evtchn_ports; diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 72ac6bf05c8b..59fd55badd73 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4431,7 +4431,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL | KVM_XEN_HVM_CONFIG_EVTCHN_SEND; if (sched_info_on()) - r |= KVM_XEN_HVM_CONFIG_RUNSTATE; + r |= KVM_XEN_HVM_CONFIG_RUNSTATE | + KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG; break; #endif case KVM_CAP_SYNC_REGS: diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c index cfc1c07bc78f..7acac5dfe2f8 100644 --- a/arch/x86/kvm/xen.c +++ b/arch/x86/kvm/xen.c @@ -179,7 +179,8 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) struct vcpu_runstate_info rs; unsigned long flags; size_t times_ofs; - uint8_t *update_bit; + uint8_t *update_bit = NULL; + uint64_t entry_time; uint64_t *rs_times; int *rs_state; @@ -297,7 +298,8 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) */ rs_state = gpc1->khva; rs_times = gpc1->khva + times_ofs; - update_bit = ((void *)(&rs_times[1])) - 1; + if (v->kvm->arch.xen.runstate_update_flag) + update_bit = ((void *)(&rs_times[1])) - 1; } else { /* * The guest's runstate_info is split across two pages and we @@ -351,12 +353,14 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * The update_bit is still directly in the guest memory, * via one GPC or the other. */ - if (user_len1 >= times_ofs + sizeof(uint64_t)) - update_bit = gpc1->khva + times_ofs + - sizeof(uint64_t) - 1; - else - update_bit = gpc2->khva + times_ofs + - sizeof(uint64_t) - 1 - user_len1; + if (v->kvm->arch.xen.runstate_update_flag) { + if (user_len1 >= times_ofs + sizeof(uint64_t)) + update_bit = gpc1->khva + times_ofs + + sizeof(uint64_t) - 1; + else + update_bit = gpc2->khva + times_ofs + + sizeof(uint64_t) - 1 - user_len1; + } #ifdef CONFIG_X86_64 /* @@ -376,8 +380,12 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * different cache line to the rest of the 64-bit word, due to * the (lack of) alignment constraints. */ - *update_bit = (vx->runstate_entry_time | XEN_RUNSTATE_UPDATE) >> 56; - smp_wmb(); + entry_time = vx->runstate_entry_time; + if (update_bit) { + entry_time |= XEN_RUNSTATE_UPDATE; + *update_bit = (vx->runstate_entry_time | XEN_RUNSTATE_UPDATE) >> 56; + smp_wmb(); + } /* * Now assemble the actual structure, either on our kernel stack @@ -385,7 +393,7 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) * rs_times pointers were set up above. */ *rs_state = vx->current_runstate; - rs_times[0] = vx->runstate_entry_time | XEN_RUNSTATE_UPDATE; + rs_times[0] = entry_time; memcpy(rs_times + 1, vx->runstate_times, sizeof(vx->runstate_times)); /* For the split case, we have to then copy it to the guest. */ @@ -396,8 +404,11 @@ static void kvm_xen_update_runstate_guest(struct kvm_vcpu *v, bool atomic) smp_wmb(); /* Finally, clear the XEN_RUNSTATE_UPDATE bit. */ - *update_bit = vx->runstate_entry_time >> 56; - smp_wmb(); + if (update_bit) { + entry_time &= ~XEN_RUNSTATE_UPDATE; + *update_bit = entry_time >> 56; + smp_wmb(); + } if (user_len2) read_unlock(&gpc2->lock); @@ -619,6 +630,17 @@ int kvm_xen_hvm_set_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = 0; break; + case KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + mutex_lock(&kvm->lock); + kvm->arch.xen.runstate_update_flag = !!data->u.runstate_update_flag; + mutex_unlock(&kvm->lock); + r = 0; + break; + default: break; } @@ -656,6 +678,15 @@ int kvm_xen_hvm_get_attr(struct kvm *kvm, struct kvm_xen_hvm_attr *data) r = 0; break; + case KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG: + if (!sched_info_on()) { + r = -EOPNOTSUPP; + break; + } + data->u.runstate_update_flag = kvm->arch.xen.runstate_update_flag; + r = 0; + break; + default: break; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 88448397642c..64dfe9c07c87 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1271,6 +1271,7 @@ struct kvm_x86_mce { #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3) #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4) #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5) +#define KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG (1 << 6) struct kvm_xen_hvm_config { __u32 flags; @@ -1776,6 +1777,7 @@ struct kvm_xen_hvm_attr { union { __u8 long_mode; __u8 vector; + __u8 runstate_update_flag; struct { __u64 gfn; } shared_info; @@ -1816,6 +1818,8 @@ struct kvm_xen_hvm_attr { /* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND */ #define KVM_XEN_ATTR_TYPE_EVTCHN 0x3 #define KVM_XEN_ATTR_TYPE_XEN_VERSION 0x4 +/* Available with KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG */ +#define KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG 0x5 /* Per-vCPU Xen attributes */ #define KVM_XEN_VCPU_GET_ATTR _IOWR(KVMIO, 0xca, struct kvm_xen_vcpu_attr) diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c index 7f39815f1772..c9b0110d73f3 100644 --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c @@ -440,6 +440,7 @@ int main(int argc, char *argv[]) TEST_REQUIRE(xen_caps & KVM_XEN_HVM_CONFIG_SHARED_INFO); bool do_runstate_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE); + bool do_runstate_flag = !!(xen_caps & KVM_XEN_HVM_CONFIG_RUNSTATE_UPDATE_FLAG); bool do_eventfd_tests = !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL); bool do_evtchn_tests = do_eventfd_tests && !!(xen_caps & KVM_XEN_HVM_CONFIG_EVTCHN_SEND); @@ -475,6 +476,19 @@ int main(int argc, char *argv[]) }; vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &lm); + if (do_runstate_flag) { + struct kvm_xen_hvm_attr ruf = { + .type = KVM_XEN_ATTR_TYPE_RUNSTATE_UPDATE_FLAG, + .u.runstate_update_flag = 1, + }; + vm_ioctl(vm, KVM_XEN_HVM_SET_ATTR, &ruf); + + ruf.u.runstate_update_flag = 0; + vm_ioctl(vm, KVM_XEN_HVM_GET_ATTR, &ruf); + TEST_ASSERT(ruf.u.runstate_update_flag == 1, + "Failed to read back RUNSTATE_UPDATE_FLAG attr"); + } + struct kvm_xen_hvm_attr ha = { .type = KVM_XEN_ATTR_TYPE_SHARED_INFO, .u.shared_info.gfn = SHINFO_REGION_GPA / PAGE_SIZE, -- cgit From bff3d0534804452e19c097ae6b4eb4b4d846d67f Mon Sep 17 00:00:00 2001 From: Sriram Yagnaraman Date: Fri, 4 Nov 2022 18:18:35 +0100 Subject: netfilter: conntrack: add sctp DATA_SENT state SCTP conntrack currently assumes that the SCTP endpoints will probe secondary paths using HEARTBEAT before sending traffic. But, according to RFC 9260, SCTP endpoints can send any traffic on any of the confirmed paths after SCTP association is up. SCTP endpoints that sends INIT will confirm all peer addresses that upper layer configures, and the SCTP endpoint that receives COOKIE_ECHO will only confirm the address it sent the INIT_ACK to. So, we can have a situation where the INIT sender can start to use secondary paths without the need to send HEARTBEAT. This patch allows DATA/SACK packets to create new connection tracking entry. A new state has been added to indicate that a DATA/SACK chunk has been seen in the original direction - SCTP_CONNTRACK_DATA_SENT. State transitions mostly follows the HEARTBEAT_SENT, except on receiving HEARTBEAT/HEARTBEAT_ACK/DATA/SACK in the reply direction. State transitions in original direction: - DATA_SENT behaves similar to HEARTBEAT_SENT for all chunks, except that it remains in DATA_SENT on receving HEARTBEAT, HEARTBEAT_ACK/DATA/SACK chunks State transitions in reply direction: - DATA_SENT behaves similar to HEARTBEAT_SENT for all chunks, except that it moves to HEARTBEAT_ACKED on receiving HEARTBEAT/HEARTBEAT_ACK/DATA/SACK chunks Note: This patch still doesn't solve the problem when the SCTP endpoint decides to use primary paths for association establishment but uses a secondary path for association shutdown. We still have to depend on timeout for connections to expire in such a case. Signed-off-by: Sriram Yagnaraman Reviewed-by: Marcelo Ricardo Leitner Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_conntrack_sctp.h | 1 + include/uapi/linux/netfilter/nfnetlink_cttimeout.h | 1 + net/netfilter/nf_conntrack_proto_sctp.c | 104 ++++++++++++--------- net/netfilter/nf_conntrack_standalone.c | 8 ++ 4 files changed, 71 insertions(+), 43 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_conntrack_sctp.h b/include/uapi/linux/netfilter/nf_conntrack_sctp.h index edc6ddab0de6..c742469afe21 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_sctp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_sctp.h @@ -16,6 +16,7 @@ enum sctp_conntrack { SCTP_CONNTRACK_SHUTDOWN_ACK_SENT, SCTP_CONNTRACK_HEARTBEAT_SENT, SCTP_CONNTRACK_HEARTBEAT_ACKED, + SCTP_CONNTRACK_DATA_SENT, SCTP_CONNTRACK_MAX }; diff --git a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h index 6b20fb22717b..94e74034706d 100644 --- a/include/uapi/linux/netfilter/nfnetlink_cttimeout.h +++ b/include/uapi/linux/netfilter/nfnetlink_cttimeout.h @@ -95,6 +95,7 @@ enum ctattr_timeout_sctp { CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_SENT, CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED, + CTA_TIMEOUT_SCTP_DATA_SENT, __CTA_TIMEOUT_SCTP_MAX }; #define CTA_TIMEOUT_SCTP_MAX (__CTA_TIMEOUT_SCTP_MAX - 1) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 5a936334b517..d88b92a8ffca 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -60,6 +60,7 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { [SCTP_CONNTRACK_SHUTDOWN_ACK_SENT] = 3 SECS, [SCTP_CONNTRACK_HEARTBEAT_SENT] = 30 SECS, [SCTP_CONNTRACK_HEARTBEAT_ACKED] = 210 SECS, + [SCTP_CONNTRACK_DATA_SENT] = 30 SECS, }; #define SCTP_FLAG_HEARTBEAT_VTAG_FAILED 1 @@ -74,6 +75,7 @@ static const unsigned int sctp_timeouts[SCTP_CONNTRACK_MAX] = { #define sSA SCTP_CONNTRACK_SHUTDOWN_ACK_SENT #define sHS SCTP_CONNTRACK_HEARTBEAT_SENT #define sHA SCTP_CONNTRACK_HEARTBEAT_ACKED +#define sDS SCTP_CONNTRACK_DATA_SENT #define sIV SCTP_CONNTRACK_MAX /* @@ -90,15 +92,16 @@ COOKIE WAIT - We have seen an INIT chunk in the original direction, or als COOKIE ECHOED - We have seen a COOKIE_ECHO chunk in the original direction. ESTABLISHED - We have seen a COOKIE_ACK in the reply direction. SHUTDOWN_SENT - We have seen a SHUTDOWN chunk in the original direction. -SHUTDOWN_RECD - We have seen a SHUTDOWN chunk in the reply directoin. +SHUTDOWN_RECD - We have seen a SHUTDOWN chunk in the reply direction. SHUTDOWN_ACK_SENT - We have seen a SHUTDOWN_ACK chunk in the direction opposite to that of the SHUTDOWN chunk. CLOSED - We have seen a SHUTDOWN_COMPLETE chunk in the direction of the SHUTDOWN chunk. Connection is closed. HEARTBEAT_SENT - We have seen a HEARTBEAT in a new flow. -HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK in the direction opposite to - that of the HEARTBEAT chunk. Secondary connection is - established. +HEARTBEAT_ACKED - We have seen a HEARTBEAT-ACK/DATA/SACK in the direction + opposite to that of the HEARTBEAT/DATA chunk. Secondary connection + is established. +DATA_SENT - We have seen a DATA/SACK in a new flow. */ /* TODO @@ -112,36 +115,38 @@ cookie echoed to closed. */ /* SCTP conntrack state transitions */ -static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { +static const u8 sctp_conntracks[2][12][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, -/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, -/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, -/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, -/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA}, -/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't have Stale cookie*/ -/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* 5.2.4 - Big TODO */ -/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA},/* Can't come in orig dir */ -/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA}, -/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA, sCW}, +/* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL}, +/* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, +/* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS, sCL}, +/* shutdown_ack */ {sSA, sCL, sCW, sCE, sES, sSA, sSA, sSA, sSA, sHA, sSA}, +/* error */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't have Stale cookie*/ +/* cookie_echo */ {sCL, sCL, sCE, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* 5.2.4 - Big TODO */ +/* cookie_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA, sCL},/* Can't come in orig dir */ +/* shutdown_comp*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sCL, sCL, sHA, sCL}, +/* heartbeat */ {sHS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, +/* heartbeat_ack*/ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS}, +/* data/sack */ {sDS, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS} }, { /* REPLY */ -/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, -/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, -/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, -/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, -/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA}, -/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* Can't come in reply dir */ -/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA}, -/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA}, -/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA}, -/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA} +/* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sDS */ +/* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* INIT in sCL Big TODO */ +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV}, +/* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL, sIV}, +/* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR, sIV}, +/* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA, sIV}, +/* error */ {sIV, sCL, sCW, sCL, sES, sSS, sSR, sSA, sIV, sHA, sIV}, +/* cookie_echo */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA, sIV},/* Can't come in reply dir */ +/* cookie_ack */ {sIV, sCL, sCW, sES, sES, sSS, sSR, sSA, sIV, sHA, sIV}, +/* shutdown_comp*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sCL, sIV, sHA, sIV}, +/* heartbeat */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA, sHA}, +/* heartbeat_ack*/ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, +/* data/sack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHA, sHA, sHA}, } }; @@ -253,6 +258,11 @@ static int sctp_new_state(enum ip_conntrack_dir dir, pr_debug("SCTP_CID_HEARTBEAT_ACK"); i = 10; break; + case SCTP_CID_DATA: + case SCTP_CID_SACK: + pr_debug("SCTP_CID_DATA/SACK"); + i = 11; + break; default: /* Other chunks like DATA or SACK do not change the state */ pr_debug("Unknown chunk type, Will stay in %s\n", @@ -306,7 +316,9 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ih->init_tag); ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = ih->init_tag; - } else if (sch->type == SCTP_CID_HEARTBEAT) { + } else if (sch->type == SCTP_CID_HEARTBEAT || + sch->type == SCTP_CID_DATA || + sch->type == SCTP_CID_SACK) { pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; @@ -392,19 +404,19 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, if (!sctp_new(ct, skb, sh, dataoff)) return -NF_ACCEPT; - } - - /* Check the verification tag (Sec 8.5) */ - if (!test_bit(SCTP_CID_INIT, map) && - !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && - !test_bit(SCTP_CID_COOKIE_ECHO, map) && - !test_bit(SCTP_CID_ABORT, map) && - !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && - !test_bit(SCTP_CID_HEARTBEAT, map) && - !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && - sh->vtag != ct->proto.sctp.vtag[dir]) { - pr_debug("Verification tag check failed\n"); - goto out; + } else { + /* Check the verification tag (Sec 8.5) */ + if (!test_bit(SCTP_CID_INIT, map) && + !test_bit(SCTP_CID_SHUTDOWN_COMPLETE, map) && + !test_bit(SCTP_CID_COOKIE_ECHO, map) && + !test_bit(SCTP_CID_ABORT, map) && + !test_bit(SCTP_CID_SHUTDOWN_ACK, map) && + !test_bit(SCTP_CID_HEARTBEAT, map) && + !test_bit(SCTP_CID_HEARTBEAT_ACK, map) && + sh->vtag != ct->proto.sctp.vtag[dir]) { + pr_debug("Verification tag check failed\n"); + goto out; + } } old_state = new_state = SCTP_CONNTRACK_NONE; @@ -464,6 +476,11 @@ int nf_conntrack_sctp_packet(struct nf_conn *ct, } else if (ct->proto.sctp.flags & SCTP_FLAG_HEARTBEAT_VTAG_FAILED) { ct->proto.sctp.flags &= ~SCTP_FLAG_HEARTBEAT_VTAG_FAILED; } + } else if (sch->type == SCTP_CID_DATA || sch->type == SCTP_CID_SACK) { + if (ct->proto.sctp.vtag[dir] == 0) { + pr_debug("Setting vtag %x for dir %d\n", sh->vtag, dir); + ct->proto.sctp.vtag[dir] = sh->vtag; + } } old_state = ct->proto.sctp.state; @@ -684,6 +701,7 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { [CTA_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_SENT] = { .type = NLA_U32 }, [CTA_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { .type = NLA_U32 }, + [CTA_TIMEOUT_SCTP_DATA_SENT] = { .type = NLA_U32 }, }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 4ffe84c5a82c..a884c06abf09 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -602,6 +602,7 @@ enum nf_ct_sysctl_index { NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, @@ -892,6 +893,12 @@ static struct ctl_table nf_ct_sysctl_table[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_DATA_SENT] = { + .procname = "nf_conntrack_sctp_timeout_data_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, #endif #ifdef CONFIG_NF_CT_PROTO_DCCP [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { @@ -1036,6 +1043,7 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, XASSIGN(SHUTDOWN_ACK_SENT, sn); XASSIGN(HEARTBEAT_SENT, sn); XASSIGN(HEARTBEAT_ACKED, sn); + XASSIGN(DATA_SENT, sn); #undef XASSIGN #endif } -- cgit From e9374524950512a1769f610a868fcdf89ea59b8e Mon Sep 17 00:00:00 2001 From: Vishwanath Pai Date: Tue, 22 Nov 2022 20:30:57 +0100 Subject: netfilter: ipset: Add support for new bitmask parameter Add a new parameter to complement the existing 'netmask' option. The main difference between netmask and bitmask is that bitmask takes any arbitrary ip address as input, it does not have to be a valid netmask. The name of the new parameter is 'bitmask'. This lets us mask out arbitrary bits in the ip address, for example: ipset create set1 hash:ip bitmask 255.128.255.0 ipset create set2 hash:ip,port family inet6 bitmask ffff::ff80 Signed-off-by: Vishwanath Pai Signed-off-by: Joshua Hunt Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set.h | 10 ++++ include/uapi/linux/netfilter/ipset/ip_set.h | 2 + net/netfilter/ipset/ip_set_hash_gen.h | 71 +++++++++++++++++++++++++---- net/netfilter/ipset/ip_set_hash_ip.c | 19 ++++---- net/netfilter/ipset/ip_set_hash_ipport.c | 24 +++++++++- net/netfilter/ipset/ip_set_hash_netnet.c | 26 +++++++++-- 6 files changed, 126 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h index ada1296c87d5..ab934ad951a8 100644 --- a/include/linux/netfilter/ipset/ip_set.h +++ b/include/linux/netfilter/ipset/ip_set.h @@ -515,6 +515,16 @@ ip_set_init_skbinfo(struct ip_set_skbinfo *skbinfo, *skbinfo = ext->skbinfo; } +static inline void +nf_inet_addr_mask_inplace(union nf_inet_addr *a1, + const union nf_inet_addr *mask) +{ + a1->all[0] &= mask->all[0]; + a1->all[1] &= mask->all[1]; + a1->all[2] &= mask->all[2]; + a1->all[3] &= mask->all[3]; +} + #define IP_SET_INIT_KEXT(skb, opt, set) \ { .bytes = (skb)->len, .packets = 1, .target = true,\ .timeout = ip_set_adt_opt_timeout(opt, set) } diff --git a/include/uapi/linux/netfilter/ipset/ip_set.h b/include/uapi/linux/netfilter/ipset/ip_set.h index 79e5d68b87af..333807efd32b 100644 --- a/include/uapi/linux/netfilter/ipset/ip_set.h +++ b/include/uapi/linux/netfilter/ipset/ip_set.h @@ -85,6 +85,7 @@ enum { IPSET_ATTR_CADT_LINENO = IPSET_ATTR_LINENO, /* 9 */ IPSET_ATTR_MARK, /* 10 */ IPSET_ATTR_MARKMASK, /* 11 */ + IPSET_ATTR_BITMASK, /* 12 */ /* Reserve empty slots */ IPSET_ATTR_CADT_MAX = 16, /* Create-only specific attributes */ @@ -153,6 +154,7 @@ enum ipset_errno { IPSET_ERR_COMMENT, IPSET_ERR_INVALID_MARKMASK, IPSET_ERR_SKBINFO, + IPSET_ERR_BITMASK_NETMASK_EXCL, /* Type specific error codes */ IPSET_ERR_TYPE_SPECIFIC = 4352, diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 3adc291d9ce1..fdb5225a3e5c 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -159,6 +159,17 @@ htable_size(u8 hbits) (SET_WITH_TIMEOUT(set) && \ ip_set_timeout_expired(ext_timeout(d, set))) +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) +static const union nf_inet_addr onesmask = { + .all[0] = 0xffffffff, + .all[1] = 0xffffffff, + .all[2] = 0xffffffff, + .all[3] = 0xffffffff +}; + +static const union nf_inet_addr zeromask = {}; +#endif + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -283,8 +294,9 @@ struct htype { u32 markmask; /* markmask value for mark mask to store */ #endif u8 bucketsize; /* max elements in an array block */ -#ifdef IP_SET_HASH_WITH_NETMASK +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) u8 netmask; /* netmask value for subnets to store */ + union nf_inet_addr bitmask; /* stores bitmask */ #endif struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ @@ -459,8 +471,8 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) /* Resizing changes htable_bits, so we ignore it */ return x->maxelem == y->maxelem && a->timeout == b->timeout && -#ifdef IP_SET_HASH_WITH_NETMASK - x->netmask == y->netmask && +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) + nf_inet_addr_cmp(&x->bitmask, &y->bitmask) && #endif #ifdef IP_SET_HASH_WITH_MARKMASK x->markmask == y->markmask && @@ -1264,9 +1276,21 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) htonl(jhash_size(htable_bits))) || nla_put_net32(skb, IPSET_ATTR_MAXELEM, htonl(h->maxelem))) goto nla_put_failure; +#ifdef IP_SET_HASH_WITH_BITMASK + /* if netmask is set to anything other than HOST_MASK we know that the user supplied netmask + * and not bitmask. These two are mutually exclusive. */ + if (h->netmask == HOST_MASK && !nf_inet_addr_cmp(&onesmask, &h->bitmask)) { + if (set->family == NFPROTO_IPV4) { + if (nla_put_ipaddr4(skb, IPSET_ATTR_BITMASK, h->bitmask.ip)) + goto nla_put_failure; + } else if (set->family == NFPROTO_IPV6) { + if (nla_put_ipaddr6(skb, IPSET_ATTR_BITMASK, &h->bitmask.in6)) + goto nla_put_failure; + } + } +#endif #ifdef IP_SET_HASH_WITH_NETMASK - if (h->netmask != HOST_MASK && - nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) + if (h->netmask != HOST_MASK && nla_put_u8(skb, IPSET_ATTR_NETMASK, h->netmask)) goto nla_put_failure; #endif #ifdef IP_SET_HASH_WITH_MARKMASK @@ -1429,8 +1453,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, u32 markmask; #endif u8 hbits; -#ifdef IP_SET_HASH_WITH_NETMASK - u8 netmask; +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) + int ret __attribute__((unused)) = 0; + u8 netmask = set->family == NFPROTO_IPV4 ? 32 : 128; + union nf_inet_addr bitmask = onesmask; #endif size_t hsize; struct htype *h; @@ -1468,7 +1494,6 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #endif #ifdef IP_SET_HASH_WITH_NETMASK - netmask = set->family == NFPROTO_IPV4 ? 32 : 128; if (tb[IPSET_ATTR_NETMASK]) { netmask = nla_get_u8(tb[IPSET_ATTR_NETMASK]); @@ -1476,6 +1501,33 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, (set->family == NFPROTO_IPV6 && netmask > 128) || netmask == 0) return -IPSET_ERR_INVALID_NETMASK; + + /* we convert netmask to bitmask and store it */ + if (set->family == NFPROTO_IPV4) + bitmask.ip = ip_set_netmask(netmask); + else + ip6_netmask(&bitmask, netmask); + } +#endif + +#ifdef IP_SET_HASH_WITH_BITMASK + if (tb[IPSET_ATTR_BITMASK]) { + /* bitmask and netmask do the same thing, allow only one of these options */ + if (tb[IPSET_ATTR_NETMASK]) + return -IPSET_ERR_BITMASK_NETMASK_EXCL; + + if (set->family == NFPROTO_IPV4) { + ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_BITMASK], &bitmask.ip); + if (ret || !bitmask.ip) + return -IPSET_ERR_INVALID_NETMASK; + } else if (set->family == NFPROTO_IPV6) { + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_BITMASK], &bitmask); + if (ret || ipv6_addr_any(&bitmask.in6)) + return -IPSET_ERR_INVALID_NETMASK; + } + + if (nf_inet_addr_cmp(&bitmask, &zeromask)) + return -IPSET_ERR_INVALID_NETMASK; } #endif @@ -1518,7 +1570,8 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, for (i = 0; i < ahash_numof_locks(hbits); i++) spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; -#ifdef IP_SET_HASH_WITH_NETMASK +#if defined(IP_SET_HASH_WITH_NETMASK) || defined(IP_SET_HASH_WITH_BITMASK) + h->bitmask = bitmask; h->netmask = netmask; #endif #ifdef IP_SET_HASH_WITH_MARKMASK diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index dd30c03d5a23..556f74268a28 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -24,7 +24,8 @@ /* 2 Comments support */ /* 3 Forceadd support */ /* 4 skbinfo support */ -#define IPSET_TYPE_REV_MAX 5 /* bucketsize, initval support */ +/* 5 bucketsize, initval support */ +#define IPSET_TYPE_REV_MAX 6 /* bitmask support */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -34,6 +35,7 @@ MODULE_ALIAS("ip_set_hash:ip"); /* Type specific function prefix */ #define HTYPE hash_ip #define IP_SET_HASH_WITH_NETMASK +#define IP_SET_HASH_WITH_BITMASK /* IPv4 variant */ @@ -86,7 +88,7 @@ hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb, __be32 ip; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip); - ip &= ip_set_netmask(h->netmask); + ip &= h->bitmask.ip; if (ip == 0) return -EINVAL; @@ -119,7 +121,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - ip &= ip_set_hostmask(h->netmask); + ip &= ntohl(h->bitmask.ip); e.ip = htonl(ip); if (e.ip == 0) return -IPSET_ERR_HASH_ELEM; @@ -187,12 +189,6 @@ hash_ip6_data_equal(const struct hash_ip6_elem *ip1, return ipv6_addr_equal(&ip1->ip.in6, &ip2->ip.in6); } -static void -hash_ip6_netmask(union nf_inet_addr *ip, u8 prefix) -{ - ip6_netmask(ip, prefix); -} - static bool hash_ip6_data_list(struct sk_buff *skb, const struct hash_ip6_elem *e) { @@ -229,7 +225,7 @@ hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb, struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); - hash_ip6_netmask(&e.ip, h->netmask); + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); if (ipv6_addr_any(&e.ip.in6)) return -EINVAL; @@ -268,7 +264,7 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; - hash_ip6_netmask(&e.ip, h->netmask); + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); if (ipv6_addr_any(&e.ip.in6)) return -IPSET_ERR_HASH_ELEM; @@ -295,6 +291,7 @@ static struct ip_set_type hash_ip_type __read_mostly = { [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, }, .adt_policy = { diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 7303138e46be..2ffbd0b78a8c 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -26,7 +26,8 @@ /* 3 Comments support added */ /* 4 Forceadd support added */ /* 5 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 6 /* bucketsize, initval support added */ +/* 6 bucketsize, initval support added */ +#define IPSET_TYPE_REV_MAX 7 /* bitmask support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Jozsef Kadlecsik "); @@ -35,6 +36,8 @@ MODULE_ALIAS("ip_set_hash:ip,port"); /* Type specific function prefix */ #define HTYPE hash_ipport +#define IP_SET_HASH_WITH_NETMASK +#define IP_SET_HASH_WITH_BITMASK /* IPv4 variant */ @@ -92,12 +95,16 @@ hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem e = { .ip = 0 }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + const struct MTYPE *h = set->data; if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip); + e.ip &= h->bitmask.ip; + if (e.ip == 0) + return -EINVAL; return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -129,6 +136,10 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; + e.ip &= h->bitmask.ip; + if (e.ip == 0) + return -EINVAL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { @@ -253,12 +264,17 @@ hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb, ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem e = { .ip = { .all = { 0 } } }; struct ip_set_ext ext = IP_SET_INIT_KEXT(skb, opt, set); + const struct MTYPE *h = set->data; if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.port, &e.proto)) return -EINVAL; ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip.in6); + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); + if (ipv6_addr_any(&e.ip.in6)) + return -EINVAL; + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -298,6 +314,10 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (ret) return ret; + nf_inet_addr_mask_inplace(&e.ip, &h->bitmask); + if (ipv6_addr_any(&e.ip.in6)) + return -EINVAL; + e.port = nla_get_be16(tb[IPSET_ATTR_PORT]); if (tb[IPSET_ATTR_PROTO]) { @@ -356,6 +376,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = { [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 3d09eefe998a..cdfb78c6e0d3 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -23,7 +23,8 @@ #define IPSET_TYPE_REV_MIN 0 /* 1 Forceadd support added */ /* 2 skbinfo support added */ -#define IPSET_TYPE_REV_MAX 3 /* bucketsize, initval support added */ +/* 3 bucketsize, initval support added */ +#define IPSET_TYPE_REV_MAX 4 /* bitmask support added */ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Oliver Smith "); @@ -33,6 +34,8 @@ MODULE_ALIAS("ip_set_hash:net,net"); /* Type specific function prefix */ #define HTYPE hash_netnet #define IP_SET_HASH_WITH_NETS +#define IP_SET_HASH_WITH_NETMASK +#define IP_SET_HASH_WITH_BITMASK #define IPSET_NET_COUNT 2 /* IPv4 variants */ @@ -153,8 +156,8 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb, ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &e.ip[0]); ip4addrptr(skb, opt->flags & IPSET_DIM_TWO_SRC, &e.ip[1]); - e.ip[0] &= ip_set_netmask(e.cidr[0]); - e.ip[1] &= ip_set_netmask(e.cidr[1]); + e.ip[0] &= (ip_set_netmask(e.cidr[0]) & h->bitmask.ip); + e.ip[1] &= (ip_set_netmask(e.cidr[1]) & h->bitmask.ip); return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -213,8 +216,8 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_IP2_TO])) { - e.ip[0] = htonl(ip & ip_set_hostmask(e.cidr[0])); - e.ip[1] = htonl(ip2_from & ip_set_hostmask(e.cidr[1])); + e.ip[0] = htonl(ip & ntohl(h->bitmask.ip) & ip_set_hostmask(e.cidr[0])); + e.ip[1] = htonl(ip2_from & ntohl(h->bitmask.ip) & ip_set_hostmask(e.cidr[1])); ret = adtfn(set, &e, &ext, &ext, flags); return ip_set_enomatch(ret, flags, adt, set) ? -ret : ip_set_eexist(ret, flags) ? 0 : ret; @@ -404,6 +407,11 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb, ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); + nf_inet_addr_mask_inplace(&e.ip[0], &h->bitmask); + nf_inet_addr_mask_inplace(&e.ip[1], &h->bitmask); + if (e.cidr[0] == HOST_MASK && ipv6_addr_any(&e.ip[0].in6)) + return -EINVAL; + return adtfn(set, &e, &ext, &opt->ext, opt->cmdflags); } @@ -414,6 +422,7 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netnet6_elem e = { }; struct ip_set_ext ext = IP_SET_INIT_UEXT(set); + const struct hash_netnet6 *h = set->data; int ret; if (tb[IPSET_ATTR_LINENO]) @@ -453,6 +462,11 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[], ip6_netmask(&e.ip[0], e.cidr[0]); ip6_netmask(&e.ip[1], e.cidr[1]); + nf_inet_addr_mask_inplace(&e.ip[0], &h->bitmask); + nf_inet_addr_mask_inplace(&e.ip[1], &h->bitmask); + if (e.cidr[0] == HOST_MASK && ipv6_addr_any(&e.ip[0].in6)) + return -IPSET_ERR_HASH_ELEM; + if (tb[IPSET_ATTR_CADT_FLAGS]) { u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); @@ -484,6 +498,8 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + [IPSET_ATTR_NETMASK] = { .type = NLA_U8 }, + [IPSET_ATTR_BITMASK] = { .type = NLA_NESTED }, }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, -- cgit From 2ff4bed7fee72ba1abfcff5f11ae8f8e570353f2 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 29 Nov 2022 16:29:29 -0400 Subject: iommufd: File descriptor, context, kconfig and makefiles This is the basic infrastructure of a new miscdevice to hold the iommufd IOCTL API. It provides: - A miscdevice to create file descriptors to run the IOCTL interface over - A table based ioctl dispatch and centralized extendable pre-validation step - An xarray mapping userspace ID's to kernel objects. The design has multiple inter-related objects held within in a single IOMMUFD fd - A simple usage count to build a graph of object relations and protect against hostile userspace racing ioctls The only IOCTL provided in this patch is the generic 'destroy any object by handle' operation. Link: https://lore.kernel.org/r/6-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Reviewed-by: Lu Baolu Reviewed-by: Kevin Tian Reviewed-by: Eric Auger Tested-by: Nicolin Chen Tested-by: Yi Liu Tested-by: Lixiao Yang Tested-by: Matthew Rosato Signed-off-by: Yi Liu Signed-off-by: Jason Gunthorpe --- Documentation/userspace-api/ioctl/ioctl-number.rst | 1 + MAINTAINERS | 12 + drivers/iommu/Kconfig | 1 + drivers/iommu/Makefile | 2 +- drivers/iommu/iommufd/Kconfig | 12 + drivers/iommu/iommufd/Makefile | 5 + drivers/iommu/iommufd/iommufd_private.h | 109 +++++++ drivers/iommu/iommufd/main.c | 344 +++++++++++++++++++++ include/linux/iommufd.h | 31 ++ include/uapi/linux/iommufd.h | 55 ++++ 10 files changed, 571 insertions(+), 1 deletion(-) create mode 100644 drivers/iommu/iommufd/Kconfig create mode 100644 drivers/iommu/iommufd/Makefile create mode 100644 drivers/iommu/iommufd/iommufd_private.h create mode 100644 drivers/iommu/iommufd/main.c create mode 100644 include/linux/iommufd.h create mode 100644 include/uapi/linux/iommufd.h (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst index 5f81e2a24a5c..eb045fc495a4 100644 --- a/Documentation/userspace-api/ioctl/ioctl-number.rst +++ b/Documentation/userspace-api/ioctl/ioctl-number.rst @@ -105,6 +105,7 @@ Code Seq# Include File Comments '8' all SNP8023 advanced NIC card ';' 64-7F linux/vfio.h +';' 80-FF linux/iommufd.h '=' 00-3f uapi/linux/ptp_clock.h '@' 00-0F linux/radeonfb.h conflict! '@' 00-0F drivers/video/aty/aty128fb.c conflict! diff --git a/MAINTAINERS b/MAINTAINERS index 379945f82a64..c0a93779731d 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -10717,6 +10717,18 @@ F: drivers/iommu/dma-iommu.h F: drivers/iommu/iova.c F: include/linux/iova.h +IOMMUFD +M: Jason Gunthorpe +M: Kevin Tian +L: iommu@lists.linux.dev +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd.git +F: Documentation/userspace-api/iommufd.rst +F: drivers/iommu/iommufd/ +F: include/linux/iommufd.h +F: include/uapi/linux/iommufd.h +F: tools/testing/selftests/iommu/ + IOMMU SUBSYSTEM M: Joerg Roedel M: Will Deacon diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index dc5f7a156ff5..319966cde5cf 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -188,6 +188,7 @@ config MSM_IOMMU source "drivers/iommu/amd/Kconfig" source "drivers/iommu/intel/Kconfig" +source "drivers/iommu/iommufd/Kconfig" config IRQ_REMAP bool "Support for Interrupt Remapping" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 7fbf6a337662..f461d0651385 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -obj-y += amd/ intel/ arm/ +obj-y += amd/ intel/ arm/ iommufd/ obj-$(CONFIG_IOMMU_API) += iommu.o obj-$(CONFIG_IOMMU_API) += iommu-traces.o obj-$(CONFIG_IOMMU_API) += iommu-sysfs.o diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig new file mode 100644 index 000000000000..164812084a67 --- /dev/null +++ b/drivers/iommu/iommufd/Kconfig @@ -0,0 +1,12 @@ +# SPDX-License-Identifier: GPL-2.0-only +config IOMMUFD + tristate "IOMMU Userspace API" + select INTERVAL_TREE + select INTERVAL_TREE_SPAN_ITER + select IOMMU_API + default n + help + Provides /dev/iommu, the user API to control the IOMMU subsystem as + it relates to managing IO page tables that point at user space memory. + + If you don't know what to do here, say N. diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile new file mode 100644 index 000000000000..a07a8cffe937 --- /dev/null +++ b/drivers/iommu/iommufd/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0-only +iommufd-y := \ + main.o + +obj-$(CONFIG_IOMMUFD) += iommufd.o diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h new file mode 100644 index 000000000000..bb720bc11317 --- /dev/null +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#ifndef __IOMMUFD_PRIVATE_H +#define __IOMMUFD_PRIVATE_H + +#include +#include +#include +#include + +struct iommufd_ctx { + struct file *file; + struct xarray objects; +}; + +struct iommufd_ucmd { + struct iommufd_ctx *ictx; + void __user *ubuffer; + u32 user_size; + void *cmd; +}; + +/* Copy the response in ucmd->cmd back to userspace. */ +static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, + size_t cmd_len) +{ + if (copy_to_user(ucmd->ubuffer, ucmd->cmd, + min_t(size_t, ucmd->user_size, cmd_len))) + return -EFAULT; + return 0; +} + +enum iommufd_object_type { + IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, +}; + +/* Base struct for all objects with a userspace ID handle. */ +struct iommufd_object { + struct rw_semaphore destroy_rwsem; + refcount_t users; + enum iommufd_object_type type; + unsigned int id; +}; + +static inline bool iommufd_lock_obj(struct iommufd_object *obj) +{ + if (!down_read_trylock(&obj->destroy_rwsem)) + return false; + if (!refcount_inc_not_zero(&obj->users)) { + up_read(&obj->destroy_rwsem); + return false; + } + return true; +} + +struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id, + enum iommufd_object_type type); +static inline void iommufd_put_object(struct iommufd_object *obj) +{ + refcount_dec(&obj->users); + up_read(&obj->destroy_rwsem); +} + +/** + * iommufd_ref_to_users() - Switch from destroy_rwsem to users refcount + * protection + * @obj - Object to release + * + * Objects have two refcount protections (destroy_rwsem and the refcount_t + * users). Holding either of these will prevent the object from being destroyed. + * + * Depending on the use case, one protection or the other is appropriate. In + * most cases references are being protected by the destroy_rwsem. This allows + * orderly destruction of the object because iommufd_object_destroy_user() will + * wait for it to become unlocked. However, as a rwsem, it cannot be held across + * a system call return. So cases that have longer term needs must switch + * to the weaker users refcount_t. + * + * With users protection iommufd_object_destroy_user() will return false, + * refusing to destroy the object, causing -EBUSY to userspace. + */ +static inline void iommufd_ref_to_users(struct iommufd_object *obj) +{ + up_read(&obj->destroy_rwsem); + /* iommufd_lock_obj() obtains users as well */ +} +void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj); +void iommufd_object_abort_and_destroy(struct iommufd_ctx *ictx, + struct iommufd_object *obj); +void iommufd_object_finalize(struct iommufd_ctx *ictx, + struct iommufd_object *obj); +bool iommufd_object_destroy_user(struct iommufd_ctx *ictx, + struct iommufd_object *obj); +struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, + size_t size, + enum iommufd_object_type type); + +#define iommufd_object_alloc(ictx, ptr, type) \ + container_of(_iommufd_object_alloc( \ + ictx, \ + sizeof(*(ptr)) + BUILD_BUG_ON_ZERO( \ + offsetof(typeof(*(ptr)), \ + obj) != 0), \ + type), \ + typeof(*(ptr)), obj) + +#endif diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c new file mode 100644 index 000000000000..dfbc68b97506 --- /dev/null +++ b/drivers/iommu/iommufd/main.c @@ -0,0 +1,344 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2021 Intel Corporation + * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + * + * iommufd provides control over the IOMMU HW objects created by IOMMU kernel + * drivers. IOMMU HW objects revolve around IO page tables that map incoming DMA + * addresses (IOVA) to CPU addresses. + */ +#define pr_fmt(fmt) "iommufd: " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "iommufd_private.h" + +struct iommufd_object_ops { + void (*destroy)(struct iommufd_object *obj); +}; +static const struct iommufd_object_ops iommufd_object_ops[]; + +struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, + size_t size, + enum iommufd_object_type type) +{ + struct iommufd_object *obj; + int rc; + + obj = kzalloc(size, GFP_KERNEL_ACCOUNT); + if (!obj) + return ERR_PTR(-ENOMEM); + obj->type = type; + init_rwsem(&obj->destroy_rwsem); + refcount_set(&obj->users, 1); + + /* + * Reserve an ID in the xarray but do not publish the pointer yet since + * the caller hasn't initialized it yet. Once the pointer is published + * in the xarray and visible to other threads we can't reliably destroy + * it anymore, so the caller must complete all errorable operations + * before calling iommufd_object_finalize(). + */ + rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY, + xa_limit_32b, GFP_KERNEL_ACCOUNT); + if (rc) + goto out_free; + return obj; +out_free: + kfree(obj); + return ERR_PTR(rc); +} + +/* + * Allow concurrent access to the object. + * + * Once another thread can see the object pointer it can prevent object + * destruction. Expect for special kernel-only objects there is no in-kernel way + * to reliably destroy a single object. Thus all APIs that are creating objects + * must use iommufd_object_abort() to handle their errors and only call + * iommufd_object_finalize() once object creation cannot fail. + */ +void iommufd_object_finalize(struct iommufd_ctx *ictx, + struct iommufd_object *obj) +{ + void *old; + + old = xa_store(&ictx->objects, obj->id, obj, GFP_KERNEL); + /* obj->id was returned from xa_alloc() so the xa_store() cannot fail */ + WARN_ON(old); +} + +/* Undo _iommufd_object_alloc() if iommufd_object_finalize() was not called */ +void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj) +{ + void *old; + + old = xa_erase(&ictx->objects, obj->id); + WARN_ON(old); + kfree(obj); +} + +/* + * Abort an object that has been fully initialized and needs destroy, but has + * not been finalized. + */ +void iommufd_object_abort_and_destroy(struct iommufd_ctx *ictx, + struct iommufd_object *obj) +{ + iommufd_object_ops[obj->type].destroy(obj); + iommufd_object_abort(ictx, obj); +} + +struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id, + enum iommufd_object_type type) +{ + struct iommufd_object *obj; + + xa_lock(&ictx->objects); + obj = xa_load(&ictx->objects, id); + if (!obj || (type != IOMMUFD_OBJ_ANY && obj->type != type) || + !iommufd_lock_obj(obj)) + obj = ERR_PTR(-ENOENT); + xa_unlock(&ictx->objects); + return obj; +} + +/* + * The caller holds a users refcount and wants to destroy the object. Returns + * true if the object was destroyed. In all cases the caller no longer has a + * reference on obj. + */ +bool iommufd_object_destroy_user(struct iommufd_ctx *ictx, + struct iommufd_object *obj) +{ + /* + * The purpose of the destroy_rwsem is to ensure deterministic + * destruction of objects used by external drivers and destroyed by this + * function. Any temporary increment of the refcount must hold the read + * side of this, such as during ioctl execution. + */ + down_write(&obj->destroy_rwsem); + xa_lock(&ictx->objects); + refcount_dec(&obj->users); + if (!refcount_dec_if_one(&obj->users)) { + xa_unlock(&ictx->objects); + up_write(&obj->destroy_rwsem); + return false; + } + __xa_erase(&ictx->objects, obj->id); + xa_unlock(&ictx->objects); + up_write(&obj->destroy_rwsem); + + iommufd_object_ops[obj->type].destroy(obj); + kfree(obj); + return true; +} + +static int iommufd_destroy(struct iommufd_ucmd *ucmd) +{ + struct iommu_destroy *cmd = ucmd->cmd; + struct iommufd_object *obj; + + obj = iommufd_get_object(ucmd->ictx, cmd->id, IOMMUFD_OBJ_ANY); + if (IS_ERR(obj)) + return PTR_ERR(obj); + iommufd_ref_to_users(obj); + /* See iommufd_ref_to_users() */ + if (!iommufd_object_destroy_user(ucmd->ictx, obj)) + return -EBUSY; + return 0; +} + +static int iommufd_fops_open(struct inode *inode, struct file *filp) +{ + struct iommufd_ctx *ictx; + + ictx = kzalloc(sizeof(*ictx), GFP_KERNEL_ACCOUNT); + if (!ictx) + return -ENOMEM; + + xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT); + ictx->file = filp; + filp->private_data = ictx; + return 0; +} + +static int iommufd_fops_release(struct inode *inode, struct file *filp) +{ + struct iommufd_ctx *ictx = filp->private_data; + struct iommufd_object *obj; + + /* + * The objects in the xarray form a graph of "users" counts, and we have + * to destroy them in a depth first manner. Leaf objects will reduce the + * users count of interior objects when they are destroyed. + * + * Repeatedly destroying all the "1 users" leaf objects will progress + * until the entire list is destroyed. If this can't progress then there + * is some bug related to object refcounting. + */ + while (!xa_empty(&ictx->objects)) { + unsigned int destroyed = 0; + unsigned long index; + + xa_for_each(&ictx->objects, index, obj) { + if (!refcount_dec_if_one(&obj->users)) + continue; + destroyed++; + xa_erase(&ictx->objects, index); + iommufd_object_ops[obj->type].destroy(obj); + kfree(obj); + } + /* Bug related to users refcount */ + if (WARN_ON(!destroyed)) + break; + } + kfree(ictx); + return 0; +} + +union ucmd_buffer { + struct iommu_destroy destroy; +}; + +struct iommufd_ioctl_op { + unsigned int size; + unsigned int min_size; + unsigned int ioctl_num; + int (*execute)(struct iommufd_ucmd *ucmd); +}; + +#define IOCTL_OP(_ioctl, _fn, _struct, _last) \ + [_IOC_NR(_ioctl) - IOMMUFD_CMD_BASE] = { \ + .size = sizeof(_struct) + \ + BUILD_BUG_ON_ZERO(sizeof(union ucmd_buffer) < \ + sizeof(_struct)), \ + .min_size = offsetofend(_struct, _last), \ + .ioctl_num = _ioctl, \ + .execute = _fn, \ + } +static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { + IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id), +}; + +static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + const struct iommufd_ioctl_op *op; + struct iommufd_ucmd ucmd = {}; + union ucmd_buffer buf; + unsigned int nr; + int ret; + + ucmd.ictx = filp->private_data; + ucmd.ubuffer = (void __user *)arg; + ret = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); + if (ret) + return ret; + + nr = _IOC_NR(cmd); + if (nr < IOMMUFD_CMD_BASE || + (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) + return -ENOIOCTLCMD; + op = &iommufd_ioctl_ops[nr - IOMMUFD_CMD_BASE]; + if (op->ioctl_num != cmd) + return -ENOIOCTLCMD; + if (ucmd.user_size < op->min_size) + return -EINVAL; + + ucmd.cmd = &buf; + ret = copy_struct_from_user(ucmd.cmd, op->size, ucmd.ubuffer, + ucmd.user_size); + if (ret) + return ret; + ret = op->execute(&ucmd); + return ret; +} + +static const struct file_operations iommufd_fops = { + .owner = THIS_MODULE, + .open = iommufd_fops_open, + .release = iommufd_fops_release, + .unlocked_ioctl = iommufd_fops_ioctl, +}; + +/** + * iommufd_ctx_get - Get a context reference + * @ictx: Context to get + * + * The caller must already hold a valid reference to ictx. + */ +void iommufd_ctx_get(struct iommufd_ctx *ictx) +{ + get_file(ictx->file); +} +EXPORT_SYMBOL_NS_GPL(iommufd_ctx_get, IOMMUFD); + +/** + * iommufd_ctx_from_file - Acquires a reference to the iommufd context + * @file: File to obtain the reference from + * + * Returns a pointer to the iommufd_ctx, otherwise ERR_PTR. The struct file + * remains owned by the caller and the caller must still do fput. On success + * the caller is responsible to call iommufd_ctx_put(). + */ +struct iommufd_ctx *iommufd_ctx_from_file(struct file *file) +{ + struct iommufd_ctx *ictx; + + if (file->f_op != &iommufd_fops) + return ERR_PTR(-EBADFD); + ictx = file->private_data; + iommufd_ctx_get(ictx); + return ictx; +} +EXPORT_SYMBOL_NS_GPL(iommufd_ctx_from_file, IOMMUFD); + +/** + * iommufd_ctx_put - Put back a reference + * @ictx: Context to put back + */ +void iommufd_ctx_put(struct iommufd_ctx *ictx) +{ + fput(ictx->file); +} +EXPORT_SYMBOL_NS_GPL(iommufd_ctx_put, IOMMUFD); + +static const struct iommufd_object_ops iommufd_object_ops[] = { +}; + +static struct miscdevice iommu_misc_dev = { + .minor = MISC_DYNAMIC_MINOR, + .name = "iommu", + .fops = &iommufd_fops, + .nodename = "iommu", + .mode = 0660, +}; + +static int __init iommufd_init(void) +{ + int ret; + + ret = misc_register(&iommu_misc_dev); + if (ret) + return ret; + return 0; +} + +static void __exit iommufd_exit(void) +{ + misc_deregister(&iommu_misc_dev); +} + +module_init(iommufd_init); +module_exit(iommufd_exit); + +MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices"); +MODULE_LICENSE("GPL"); diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h new file mode 100644 index 000000000000..d1817472c273 --- /dev/null +++ b/include/linux/iommufd.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 2021 Intel Corporation + * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#ifndef __LINUX_IOMMUFD_H +#define __LINUX_IOMMUFD_H + +#include +#include +#include + +struct iommufd_ctx; +struct file; + +void iommufd_ctx_get(struct iommufd_ctx *ictx); + +#if IS_ENABLED(CONFIG_IOMMUFD) +struct iommufd_ctx *iommufd_ctx_from_file(struct file *file); +void iommufd_ctx_put(struct iommufd_ctx *ictx); +#else /* !CONFIG_IOMMUFD */ +static inline struct iommufd_ctx *iommufd_ctx_from_file(struct file *file) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline void iommufd_ctx_put(struct iommufd_ctx *ictx) +{ +} +#endif /* CONFIG_IOMMUFD */ +#endif diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h new file mode 100644 index 000000000000..37de92f0534b --- /dev/null +++ b/include/uapi/linux/iommufd.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + */ +#ifndef _UAPI_IOMMUFD_H +#define _UAPI_IOMMUFD_H + +#include +#include + +#define IOMMUFD_TYPE (';') + +/** + * DOC: General ioctl format + * + * The ioctl interface follows a general format to allow for extensibility. Each + * ioctl is passed in a structure pointer as the argument providing the size of + * the structure in the first u32. The kernel checks that any structure space + * beyond what it understands is 0. This allows userspace to use the backward + * compatible portion while consistently using the newer, larger, structures. + * + * ioctls use a standard meaning for common errnos: + * + * - ENOTTY: The IOCTL number itself is not supported at all + * - E2BIG: The IOCTL number is supported, but the provided structure has + * non-zero in a part the kernel does not understand. + * - EOPNOTSUPP: The IOCTL number is supported, and the structure is + * understood, however a known field has a value the kernel does not + * understand or support. + * - EINVAL: Everything about the IOCTL was understood, but a field is not + * correct. + * - ENOENT: An ID or IOVA provided does not exist. + * - ENOMEM: Out of memory. + * - EOVERFLOW: Mathematics overflowed. + * + * As well as additional errnos, within specific ioctls. + */ +enum { + IOMMUFD_CMD_BASE = 0x80, + IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, +}; + +/** + * struct iommu_destroy - ioctl(IOMMU_DESTROY) + * @size: sizeof(struct iommu_destroy) + * @id: iommufd object ID to destroy. Can by any destroyable object type. + * + * Destroy any object held within iommufd. + */ +struct iommu_destroy { + __u32 size; + __u32 id; +}; +#define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY) + +#endif -- cgit From aad37e71d5c4dc1d3c25734f0bcd51c324f94b5e Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 29 Nov 2022 16:29:34 -0400 Subject: iommufd: IOCTLs for the io_pagetable Connect the IOAS to its IOCTL interface. This exposes most of the functionality in the io_pagetable to userspace. This is intended to be the core of the generic interface that IOMMUFD will provide. Every IOMMU driver should be able to implement an iommu_domain that is compatible with this generic mechanism. It is also designed to be easy to use for simple non virtual machine monitor users, like DPDK: - Universal simple support for all IOMMUs (no PPC special path) - An IOVA allocator that considers the aperture and the allowed/reserved ranges - io_pagetable allows any number of iommu_domains to be connected to the IOAS - Automatic allocation and re-use of iommu_domains Along with room in the design to add non-generic features to cater to specific HW functionality. Link: https://lore.kernel.org/r/11-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Tested-by: Nicolin Chen Tested-by: Yi Liu Tested-by: Lixiao Yang Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Eric Auger Signed-off-by: Nicolin Chen Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/ioas.c | 392 ++++++++++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 33 +++ drivers/iommu/iommufd/main.c | 48 ++++ include/uapi/linux/iommufd.h | 258 ++++++++++++++++++++- 5 files changed, 731 insertions(+), 1 deletion(-) create mode 100644 drivers/iommu/iommufd/ioas.c (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index b66a8c47ff55..2b4f36f1b72f 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ io_pagetable.o \ + ioas.o \ main.o \ pages.o diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c new file mode 100644 index 000000000000..6ff97dafc891 --- /dev/null +++ b/drivers/iommu/iommufd/ioas.c @@ -0,0 +1,392 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#include +#include +#include +#include + +#include "io_pagetable.h" + +void iommufd_ioas_destroy(struct iommufd_object *obj) +{ + struct iommufd_ioas *ioas = container_of(obj, struct iommufd_ioas, obj); + int rc; + + rc = iopt_unmap_all(&ioas->iopt, NULL); + WARN_ON(rc && rc != -ENOENT); + iopt_destroy_table(&ioas->iopt); +} + +struct iommufd_ioas *iommufd_ioas_alloc(struct iommufd_ctx *ictx) +{ + struct iommufd_ioas *ioas; + + ioas = iommufd_object_alloc(ictx, ioas, IOMMUFD_OBJ_IOAS); + if (IS_ERR(ioas)) + return ioas; + + iopt_init_table(&ioas->iopt); + return ioas; +} + +int iommufd_ioas_alloc_ioctl(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_alloc *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + int rc; + + if (cmd->flags) + return -EOPNOTSUPP; + + ioas = iommufd_ioas_alloc(ucmd->ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + cmd->out_ioas_id = ioas->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_table; + iommufd_object_finalize(ucmd->ictx, &ioas->obj); + return 0; + +out_table: + iommufd_object_abort_and_destroy(ucmd->ictx, &ioas->obj); + return rc; +} + +int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd) +{ + struct iommu_iova_range __user *ranges; + struct iommu_ioas_iova_ranges *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + struct interval_tree_span_iter span; + u32 max_iovas; + int rc; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + down_read(&ioas->iopt.iova_rwsem); + max_iovas = cmd->num_iovas; + ranges = u64_to_user_ptr(cmd->allowed_iovas); + cmd->num_iovas = 0; + cmd->out_iova_alignment = ioas->iopt.iova_alignment; + interval_tree_for_each_span(&span, &ioas->iopt.reserved_itree, 0, + ULONG_MAX) { + if (!span.is_hole) + continue; + if (cmd->num_iovas < max_iovas) { + struct iommu_iova_range elm = { + .start = span.start_hole, + .last = span.last_hole, + }; + + if (copy_to_user(&ranges[cmd->num_iovas], &elm, + sizeof(elm))) { + rc = -EFAULT; + goto out_put; + } + } + cmd->num_iovas++; + } + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_put; + if (cmd->num_iovas > max_iovas) + rc = -EMSGSIZE; +out_put: + up_read(&ioas->iopt.iova_rwsem); + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_ioas_load_iovas(struct rb_root_cached *itree, + struct iommu_iova_range __user *ranges, + u32 num) +{ + u32 i; + + for (i = 0; i != num; i++) { + struct iommu_iova_range range; + struct iopt_allowed *allowed; + + if (copy_from_user(&range, ranges + i, sizeof(range))) + return -EFAULT; + + if (range.start >= range.last) + return -EINVAL; + + if (interval_tree_iter_first(itree, range.start, range.last)) + return -EINVAL; + + allowed = kzalloc(sizeof(*allowed), GFP_KERNEL_ACCOUNT); + if (!allowed) + return -ENOMEM; + allowed->node.start = range.start; + allowed->node.last = range.last; + + interval_tree_insert(&allowed->node, itree); + } + return 0; +} + +int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_allow_iovas *cmd = ucmd->cmd; + struct rb_root_cached allowed_iova = RB_ROOT_CACHED; + struct interval_tree_node *node; + struct iommufd_ioas *ioas; + struct io_pagetable *iopt; + int rc = 0; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + iopt = &ioas->iopt; + + rc = iommufd_ioas_load_iovas(&allowed_iova, + u64_to_user_ptr(cmd->allowed_iovas), + cmd->num_iovas); + if (rc) + goto out_free; + + /* + * We want the allowed tree update to be atomic, so we have to keep the + * original nodes around, and keep track of the new nodes as we allocate + * memory for them. The simplest solution is to have a new/old tree and + * then swap new for old. On success we free the old tree, on failure we + * free the new tree. + */ + rc = iopt_set_allow_iova(iopt, &allowed_iova); +out_free: + while ((node = interval_tree_iter_first(&allowed_iova, 0, ULONG_MAX))) { + interval_tree_remove(node, &allowed_iova); + kfree(container_of(node, struct iopt_allowed, node)); + } + iommufd_put_object(&ioas->obj); + return rc; +} + +static int conv_iommu_prot(u32 map_flags) +{ + /* + * We provide no manual cache coherency ioctls to userspace and most + * architectures make the CPU ops for cache flushing privileged. + * Therefore we require the underlying IOMMU to support CPU coherent + * operation. Support for IOMMU_CACHE is enforced by the + * IOMMU_CAP_CACHE_COHERENCY test during bind. + */ + int iommu_prot = IOMMU_CACHE; + + if (map_flags & IOMMU_IOAS_MAP_WRITEABLE) + iommu_prot |= IOMMU_WRITE; + if (map_flags & IOMMU_IOAS_MAP_READABLE) + iommu_prot |= IOMMU_READ; + return iommu_prot; +} + +int iommufd_ioas_map(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_map *cmd = ucmd->cmd; + unsigned long iova = cmd->iova; + struct iommufd_ioas *ioas; + unsigned int flags = 0; + int rc; + + if ((cmd->flags & + ~(IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE)) || + cmd->__reserved) + return -EOPNOTSUPP; + if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX) + return -EOVERFLOW; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA)) + flags = IOPT_ALLOC_IOVA; + rc = iopt_map_user_pages(ucmd->ictx, &ioas->iopt, &iova, + u64_to_user_ptr(cmd->user_va), cmd->length, + conv_iommu_prot(cmd->flags), flags); + if (rc) + goto out_put; + + cmd->iova = iova; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); +out_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_ioas_copy(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_copy *cmd = ucmd->cmd; + struct iommufd_ioas *src_ioas; + struct iommufd_ioas *dst_ioas; + unsigned int flags = 0; + LIST_HEAD(pages_list); + unsigned long iova; + int rc; + + if ((cmd->flags & + ~(IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE))) + return -EOPNOTSUPP; + if (cmd->length >= ULONG_MAX || cmd->src_iova >= ULONG_MAX || + cmd->dst_iova >= ULONG_MAX) + return -EOVERFLOW; + + src_ioas = iommufd_get_ioas(ucmd, cmd->src_ioas_id); + if (IS_ERR(src_ioas)) + return PTR_ERR(src_ioas); + rc = iopt_get_pages(&src_ioas->iopt, cmd->src_iova, cmd->length, + &pages_list); + iommufd_put_object(&src_ioas->obj); + if (rc) + return rc; + + dst_ioas = iommufd_get_ioas(ucmd, cmd->dst_ioas_id); + if (IS_ERR(dst_ioas)) { + rc = PTR_ERR(dst_ioas); + goto out_pages; + } + + if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA)) + flags = IOPT_ALLOC_IOVA; + iova = cmd->dst_iova; + rc = iopt_map_pages(&dst_ioas->iopt, &pages_list, cmd->length, &iova, + conv_iommu_prot(cmd->flags), flags); + if (rc) + goto out_put_dst; + + cmd->dst_iova = iova; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); +out_put_dst: + iommufd_put_object(&dst_ioas->obj); +out_pages: + iopt_free_pages_list(&pages_list); + return rc; +} + +int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_unmap *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + unsigned long unmapped = 0; + int rc; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (cmd->iova == 0 && cmd->length == U64_MAX) { + rc = iopt_unmap_all(&ioas->iopt, &unmapped); + if (rc) + goto out_put; + } else { + if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX) { + rc = -EOVERFLOW; + goto out_put; + } + rc = iopt_unmap_iova(&ioas->iopt, cmd->iova, cmd->length, + &unmapped); + if (rc) + goto out_put; + } + + cmd->length = unmapped; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + +out_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_option_rlimit_mode(struct iommu_option *cmd, + struct iommufd_ctx *ictx) +{ + if (cmd->object_id) + return -EOPNOTSUPP; + + if (cmd->op == IOMMU_OPTION_OP_GET) { + cmd->val64 = ictx->account_mode == IOPT_PAGES_ACCOUNT_MM; + return 0; + } + if (cmd->op == IOMMU_OPTION_OP_SET) { + int rc = 0; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + xa_lock(&ictx->objects); + if (!xa_empty(&ictx->objects)) { + rc = -EBUSY; + } else { + if (cmd->val64 == 0) + ictx->account_mode = IOPT_PAGES_ACCOUNT_USER; + else if (cmd->val64 == 1) + ictx->account_mode = IOPT_PAGES_ACCOUNT_MM; + else + rc = -EINVAL; + } + xa_unlock(&ictx->objects); + + return rc; + } + return -EOPNOTSUPP; +} + +static int iommufd_ioas_option_huge_pages(struct iommu_option *cmd, + struct iommufd_ioas *ioas) +{ + if (cmd->op == IOMMU_OPTION_OP_GET) { + cmd->val64 = !ioas->iopt.disable_large_pages; + return 0; + } + if (cmd->op == IOMMU_OPTION_OP_SET) { + if (cmd->val64 == 0) + return iopt_disable_large_pages(&ioas->iopt); + if (cmd->val64 == 1) { + iopt_enable_large_pages(&ioas->iopt); + return 0; + } + return -EINVAL; + } + return -EOPNOTSUPP; +} + +int iommufd_ioas_option(struct iommufd_ucmd *ucmd) +{ + struct iommu_option *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + int rc = 0; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + ioas = iommufd_get_ioas(ucmd, cmd->object_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + switch (cmd->option_id) { + case IOMMU_OPTION_HUGE_PAGES: + rc = iommufd_ioas_option_huge_pages(cmd, ioas); + break; + default: + rc = -EOPNOTSUPP; + } + + iommufd_put_object(&ioas->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index f7ab6c6edafd..1a13c54a8def 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -11,6 +11,7 @@ struct iommu_domain; struct iommu_group; +struct iommu_option; struct iommufd_ctx { struct file *file; @@ -102,6 +103,7 @@ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, enum iommufd_object_type { IOMMUFD_OBJ_NONE, IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_IOAS, }; /* Base struct for all objects with a userspace ID handle. */ @@ -174,6 +176,37 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, type), \ typeof(*(ptr)), obj) +/* + * The IO Address Space (IOAS) pagetable is a virtual page table backed by the + * io_pagetable object. It is a user controlled mapping of IOVA -> PFNs. The + * mapping is copied into all of the associated domains and made available to + * in-kernel users. + */ +struct iommufd_ioas { + struct iommufd_object obj; + struct io_pagetable iopt; +}; + +static inline struct iommufd_ioas *iommufd_get_ioas(struct iommufd_ucmd *ucmd, + u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_IOAS), + struct iommufd_ioas, obj); +} + +struct iommufd_ioas *iommufd_ioas_alloc(struct iommufd_ctx *ictx); +int iommufd_ioas_alloc_ioctl(struct iommufd_ucmd *ucmd); +void iommufd_ioas_destroy(struct iommufd_object *obj); +int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd); +int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd); +int iommufd_ioas_map(struct iommufd_ucmd *ucmd); +int iommufd_ioas_copy(struct iommufd_ucmd *ucmd); +int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd); +int iommufd_ioas_option(struct iommufd_ucmd *ucmd); +int iommufd_option_rlimit_mode(struct iommu_option *cmd, + struct iommufd_ctx *ictx); + struct iommufd_access { unsigned long iova_alignment; u32 iopt_access_list_id; diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index dfbc68b97506..1c0a1f499378 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -204,8 +204,39 @@ static int iommufd_fops_release(struct inode *inode, struct file *filp) return 0; } +static int iommufd_option(struct iommufd_ucmd *ucmd) +{ + struct iommu_option *cmd = ucmd->cmd; + int rc; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + switch (cmd->option_id) { + case IOMMU_OPTION_RLIMIT_MODE: + rc = iommufd_option_rlimit_mode(cmd, ucmd->ictx); + break; + case IOMMU_OPTION_HUGE_PAGES: + rc = iommufd_ioas_option(ucmd); + break; + default: + return -EOPNOTSUPP; + } + if (rc) + return rc; + if (copy_to_user(&((struct iommu_option __user *)ucmd->ubuffer)->val64, + &cmd->val64, sizeof(cmd->val64))) + return -EFAULT; + return 0; +} + union ucmd_buffer { struct iommu_destroy destroy; + struct iommu_ioas_alloc alloc; + struct iommu_ioas_allow_iovas allow_iovas; + struct iommu_ioas_iova_ranges iova_ranges; + struct iommu_ioas_map map; + struct iommu_ioas_unmap unmap; }; struct iommufd_ioctl_op { @@ -226,6 +257,20 @@ struct iommufd_ioctl_op { } static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id), + IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, + struct iommu_ioas_alloc, out_ioas_id), + IOCTL_OP(IOMMU_IOAS_ALLOW_IOVAS, iommufd_ioas_allow_iovas, + struct iommu_ioas_allow_iovas, allowed_iovas), + IOCTL_OP(IOMMU_IOAS_COPY, iommufd_ioas_copy, struct iommu_ioas_copy, + src_iova), + IOCTL_OP(IOMMU_IOAS_IOVA_RANGES, iommufd_ioas_iova_ranges, + struct iommu_ioas_iova_ranges, out_iova_alignment), + IOCTL_OP(IOMMU_IOAS_MAP, iommufd_ioas_map, struct iommu_ioas_map, + iova), + IOCTL_OP(IOMMU_IOAS_UNMAP, iommufd_ioas_unmap, struct iommu_ioas_unmap, + length), + IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, + val64), }; static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, @@ -312,6 +357,9 @@ void iommufd_ctx_put(struct iommufd_ctx *ictx) EXPORT_SYMBOL_NS_GPL(iommufd_ctx_put, IOMMUFD); static const struct iommufd_object_ops iommufd_object_ops[] = { + [IOMMUFD_OBJ_IOAS] = { + .destroy = iommufd_ioas_destroy, + }, }; static struct miscdevice iommu_misc_dev = { diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 37de92f0534b..30cc5c5e2b34 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -37,12 +37,19 @@ enum { IOMMUFD_CMD_BASE = 0x80, IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, + IOMMUFD_CMD_IOAS_ALLOC, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS, + IOMMUFD_CMD_IOAS_COPY, + IOMMUFD_CMD_IOAS_IOVA_RANGES, + IOMMUFD_CMD_IOAS_MAP, + IOMMUFD_CMD_IOAS_UNMAP, + IOMMUFD_CMD_OPTION, }; /** * struct iommu_destroy - ioctl(IOMMU_DESTROY) * @size: sizeof(struct iommu_destroy) - * @id: iommufd object ID to destroy. Can by any destroyable object type. + * @id: iommufd object ID to destroy. Can be any destroyable object type. * * Destroy any object held within iommufd. */ @@ -52,4 +59,253 @@ struct iommu_destroy { }; #define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY) +/** + * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC) + * @size: sizeof(struct iommu_ioas_alloc) + * @flags: Must be 0 + * @out_ioas_id: Output IOAS ID for the allocated object + * + * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (IOVA) + * to memory mapping. + */ +struct iommu_ioas_alloc { + __u32 size; + __u32 flags; + __u32 out_ioas_id; +}; +#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC) + +/** + * struct iommu_iova_range - ioctl(IOMMU_IOVA_RANGE) + * @start: First IOVA + * @last: Inclusive last IOVA + * + * An interval in IOVA space. + */ +struct iommu_iova_range { + __aligned_u64 start; + __aligned_u64 last; +}; + +/** + * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES) + * @size: sizeof(struct iommu_ioas_iova_ranges) + * @ioas_id: IOAS ID to read ranges from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to the output array of struct iommu_iova_range + * @out_iova_alignment: Minimum alignment required for mapping IOVA + * + * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these ranges + * is not allowed. num_iovas will be set to the total number of iovas and + * the allowed_iovas[] will be filled in as space permits. + * + * The allowed ranges are dependent on the HW path the DMA operation takes, and + * can change during the lifetime of the IOAS. A fresh empty IOAS will have a + * full range, and each attached device will narrow the ranges based on that + * device's HW restrictions. Detaching a device can widen the ranges. Userspace + * should query ranges after every attach/detach to know what IOVAs are valid + * for mapping. + * + * On input num_iovas is the length of the allowed_iovas array. On output it is + * the total number of iovas filled in. The ioctl will return -EMSGSIZE and set + * num_iovas to the required value if num_iovas is too small. In this case the + * caller should allocate a larger output array and re-issue the ioctl. + * + * out_iova_alignment returns the minimum IOVA alignment that can be given + * to IOMMU_IOAS_MAP/COPY. IOVA's must satisfy:: + * + * starting_iova % out_iova_alignment == 0 + * (starting_iova + length) % out_iova_alignment == 0 + * + * out_iova_alignment can be 1 indicating any IOVA is allowed. It cannot + * be higher than the system PAGE_SIZE. + */ +struct iommu_ioas_iova_ranges { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; + __aligned_u64 out_iova_alignment; +}; +#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RANGES) + +/** + * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS) + * @size: sizeof(struct iommu_ioas_allow_iovas) + * @ioas_id: IOAS ID to allow IOVAs from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to array of struct iommu_iova_range + * + * Ensure a range of IOVAs are always available for allocation. If this call + * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA ranges + * that are narrower than the ranges provided here. This call will fail if + * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges. + * + * When an IOAS is first created the IOVA_RANGES will be maximally sized, and as + * devices are attached the IOVA will narrow based on the device restrictions. + * When an allowed range is specified any narrowing will be refused, ie device + * attachment can fail if the device requires limiting within the allowed range. + * + * Automatic IOVA allocation is also impacted by this call. MAP will only + * allocate within the allowed IOVAs if they are present. + * + * This call replaces the entire allowed list with the given list. + */ +struct iommu_ioas_allow_iovas { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; +}; +#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IOVAS) + +/** + * enum iommufd_ioas_map_flags - Flags for map and copy + * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropriate + * IOVA to place the mapping at + * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping + * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping + */ +enum iommufd_ioas_map_flags { + IOMMU_IOAS_MAP_FIXED_IOVA = 1 << 0, + IOMMU_IOAS_MAP_WRITEABLE = 1 << 1, + IOMMU_IOAS_MAP_READABLE = 1 << 2, +}; + +/** + * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP) + * @size: sizeof(struct iommu_ioas_map) + * @flags: Combination of enum iommufd_ioas_map_flags + * @ioas_id: IOAS ID to change the mapping of + * @__reserved: Must be 0 + * @user_va: Userspace pointer to start mapping from + * @length: Number of bytes to map + * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is set + * then this must be provided as input. + * + * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified then the + * mapping will be established at iova, otherwise a suitable location based on + * the reserved and allowed lists will be automatically selected and returned in + * iova. + * + * If IOMMU_IOAS_MAP_FIXED_IOVA is specified then the iova range must currently + * be unused, existing IOVA cannot be replaced. + */ +struct iommu_ioas_map { + __u32 size; + __u32 flags; + __u32 ioas_id; + __u32 __reserved; + __aligned_u64 user_va; + __aligned_u64 length; + __aligned_u64 iova; +}; +#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP) + +/** + * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY) + * @size: sizeof(struct iommu_ioas_copy) + * @flags: Combination of enum iommufd_ioas_map_flags + * @dst_ioas_id: IOAS ID to change the mapping of + * @src_ioas_id: IOAS ID to copy from + * @length: Number of bytes to copy and map + * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is + * set then this must be provided as input. + * @src_iova: IOVA to start the copy + * + * Copy an already existing mapping from src_ioas_id and establish it in + * dst_ioas_id. The src iova/length must exactly match a range used with + * IOMMU_IOAS_MAP. + * + * This may be used to efficiently clone a subset of an IOAS to another, or as a + * kind of 'cache' to speed up mapping. Copy has an efficiency advantage over + * establishing equivalent new mappings, as internal resources are shared, and + * the kernel will pin the user memory only once. + */ +struct iommu_ioas_copy { + __u32 size; + __u32 flags; + __u32 dst_ioas_id; + __u32 src_ioas_id; + __aligned_u64 length; + __aligned_u64 dst_iova; + __aligned_u64 src_iova; +}; +#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY) + +/** + * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP) + * @size: sizeof(struct iommu_ioas_unmap) + * @ioas_id: IOAS ID to change the mapping of + * @iova: IOVA to start the unmapping at + * @length: Number of bytes to unmap, and return back the bytes unmapped + * + * Unmap an IOVA range. The iova/length must be a superset of a previously + * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or + * truncating ranges is not allowed. The values 0 to U64_MAX will unmap + * everything. + */ +struct iommu_ioas_unmap { + __u32 size; + __u32 ioas_id; + __aligned_u64 iova; + __aligned_u64 length; +}; +#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP) + +/** + * enum iommufd_option - ioctl(IOMMU_OPTION_RLIMIT_MODE) and + * ioctl(IOMMU_OPTION_HUGE_PAGES) + * @IOMMU_OPTION_RLIMIT_MODE: + * Change how RLIMIT_MEMLOCK accounting works. The caller must have privilege + * to invoke this. Value 0 (default) is user based accouting, 1 uses process + * based accounting. Global option, object_id must be 0 + * @IOMMU_OPTION_HUGE_PAGES: + * Value 1 (default) allows contiguous pages to be combined when generating + * iommu mappings. Value 0 disables combining, everything is mapped to + * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS + * option, the object_id must be the IOAS ID. + */ +enum iommufd_option { + IOMMU_OPTION_RLIMIT_MODE = 0, + IOMMU_OPTION_HUGE_PAGES = 1, +}; + +/** + * enum iommufd_option_ops - ioctl(IOMMU_OPTION_OP_SET) and + * ioctl(IOMMU_OPTION_OP_GET) + * @IOMMU_OPTION_OP_SET: Set the option's value + * @IOMMU_OPTION_OP_GET: Get the option's value + */ +enum iommufd_option_ops { + IOMMU_OPTION_OP_SET = 0, + IOMMU_OPTION_OP_GET = 1, +}; + +/** + * struct iommu_option - iommu option multiplexer + * @size: sizeof(struct iommu_option) + * @option_id: One of enum iommufd_option + * @op: One of enum iommufd_option_ops + * @__reserved: Must be 0 + * @object_id: ID of the object if required + * @val64: Option value to set or value returned on get + * + * Change a simple option value. This multiplexor allows controlling options + * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP_GET + * will return the current value. + */ +struct iommu_option { + __u32 size; + __u32 option_id; + __u16 op; + __u16 __reserved; + __u32 object_id; + __aligned_u64 val64; +}; +#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) #endif -- cgit From d624d6652a65ad4f47a58b8651a1ec1163bb81d3 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 29 Nov 2022 16:29:38 -0400 Subject: iommufd: vfio container FD ioctl compatibility iommufd can directly implement the /dev/vfio/vfio container IOCTLs by mapping them into io_pagetable operations. A userspace application can test against iommufd and confirm compatibility then simply make a small change to open /dev/iommu instead of /dev/vfio/vfio. For testing purposes /dev/vfio/vfio can be symlinked to /dev/iommu and then all applications will use the compatibility path with no code changes. A later series allows /dev/vfio/vfio to be directly provided by iommufd, which allows the rlimit mode to work the same as well. This series just provides the iommufd side of compatibility. Actually linking this to VFIO_SET_CONTAINER is a followup series, with a link in the cover letter. Internally the compatibility API uses a normal IOAS object that, like vfio, is automatically allocated when the first device is attached. Userspace can also query or set this IOAS object directly using the IOMMU_VFIO_IOAS ioctl. This allows mixing and matching new iommufd only features while still using the VFIO style map/unmap ioctls. While this is enough to operate qemu, it has a few differences: - Resource limits rely on memory cgroups to bound what userspace can do instead of the module parameter dma_entry_limit. - VFIO P2P is not implemented. The DMABUF patches for vfio are a start at a solution where iommufd would import a special DMABUF. This is to avoid further propogating the follow_pfn() security problem. - A full audit for pedantic compatibility details (eg errnos, etc) has not yet been done - powerpc SPAPR is left out, as it is not connected to the iommu_domain framework. It seems interest in SPAPR is minimal as it is currently non-working in v6.1-rc1. They will have to convert to the iommu subsystem framework to enjoy iommfd. The following are not going to be implemented and we expect to remove them from VFIO type1: - SW access 'dirty tracking'. As discussed in the cover letter this will be done in VFIO. - VFIO_TYPE1_NESTING_IOMMU https://lore.kernel.org/all/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/ - VFIO_DMA_MAP_FLAG_VADDR https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ Link: https://lore.kernel.org/r/15-v6-a196d26f289e+11787-iommufd_jgg@nvidia.com Tested-by: Nicolin Chen Tested-by: Yi Liu Tested-by: Lixiao Yang Tested-by: Matthew Rosato Reviewed-by: Kevin Tian Reviewed-by: Eric Auger Signed-off-by: Nicolin Chen Signed-off-by: Jason Gunthorpe --- drivers/iommu/iommufd/Makefile | 3 +- drivers/iommu/iommufd/iommufd_private.h | 6 + drivers/iommu/iommufd/main.c | 16 +- drivers/iommu/iommufd/vfio_compat.c | 472 ++++++++++++++++++++++++++++++++ include/linux/iommufd.h | 7 + include/uapi/linux/iommufd.h | 36 +++ 6 files changed, 534 insertions(+), 6 deletions(-) create mode 100644 drivers/iommu/iommufd/vfio_compat.c (limited to 'include/uapi/linux') diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index ca28a135b967..2fdff04000b3 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -5,6 +5,7 @@ iommufd-y := \ io_pagetable.o \ ioas.o \ main.o \ - pages.o + pages.o \ + vfio_compat.o obj-$(CONFIG_IOMMUFD) += iommufd.o diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 40302cc0da36..8fe5f162ccbc 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -18,6 +18,7 @@ struct iommufd_ctx { struct xarray objects; u8 account_mode; + struct iommufd_ioas *vfio_ioas; }; /* @@ -92,6 +93,9 @@ struct iommufd_ucmd { void *cmd; }; +int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, + unsigned long arg); + /* Copy the response in ucmd->cmd back to userspace. */ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, size_t cmd_len) @@ -222,6 +226,8 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd); int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx); +int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd); + /* * A HW pagetable is called an iommu_domain inside the kernel. This user object * allows directly creating and inspecting the domains. Domains that have kernel diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 4153f6a20255..5cf69c4d591d 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -133,6 +133,8 @@ bool iommufd_object_destroy_user(struct iommufd_ctx *ictx, return false; } __xa_erase(&ictx->objects, obj->id); + if (ictx->vfio_ioas && &ictx->vfio_ioas->obj == obj) + ictx->vfio_ioas = NULL; xa_unlock(&ictx->objects); up_write(&obj->destroy_rwsem); @@ -271,27 +273,31 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { length), IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, val64), + IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas, + __reserved), }; static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + struct iommufd_ctx *ictx = filp->private_data; const struct iommufd_ioctl_op *op; struct iommufd_ucmd ucmd = {}; union ucmd_buffer buf; unsigned int nr; int ret; - ucmd.ictx = filp->private_data; + nr = _IOC_NR(cmd); + if (nr < IOMMUFD_CMD_BASE || + (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) + return iommufd_vfio_ioctl(ictx, cmd, arg); + + ucmd.ictx = ictx; ucmd.ubuffer = (void __user *)arg; ret = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); if (ret) return ret; - nr = _IOC_NR(cmd); - if (nr < IOMMUFD_CMD_BASE || - (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) - return -ENOIOCTLCMD; op = &iommufd_ioctl_ops[nr - IOMMUFD_CMD_BASE]; if (op->ioctl_num != cmd) return -ENOIOCTLCMD; diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c new file mode 100644 index 000000000000..3ceca0e8311c --- /dev/null +++ b/drivers/iommu/iommufd/vfio_compat.c @@ -0,0 +1,472 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#include +#include +#include +#include +#include +#include +#include +#include + +#include "iommufd_private.h" + +static struct iommufd_ioas *get_compat_ioas(struct iommufd_ctx *ictx) +{ + struct iommufd_ioas *ioas = ERR_PTR(-ENODEV); + + xa_lock(&ictx->objects); + if (!ictx->vfio_ioas || !iommufd_lock_obj(&ictx->vfio_ioas->obj)) + goto out_unlock; + ioas = ictx->vfio_ioas; +out_unlock: + xa_unlock(&ictx->objects); + return ioas; +} + +/** + * iommufd_vfio_compat_ioas_id - Return the IOAS ID that vfio should use + * @ictx: Context to operate on + * @out_ioas_id: The ioas_id the caller should use + * + * The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate + * on since they do not have an IOAS ID input in their ABI. Only attaching a + * group should cause a default creation of the internal ioas, this returns the + * existing ioas if it has already been assigned somehow. + */ +int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) +{ + struct iommufd_ioas *ioas = NULL; + struct iommufd_ioas *out_ioas; + + ioas = iommufd_ioas_alloc(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + xa_lock(&ictx->objects); + if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) + out_ioas = ictx->vfio_ioas; + else { + out_ioas = ioas; + ictx->vfio_ioas = ioas; + } + xa_unlock(&ictx->objects); + + *out_ioas_id = out_ioas->obj.id; + if (out_ioas != ioas) { + iommufd_put_object(&out_ioas->obj); + iommufd_object_abort(ictx, &ioas->obj); + return 0; + } + /* + * An automatically created compat IOAS is treated as a userspace + * created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET, + * and if not manually destroyed it will be destroyed automatically + * at iommufd release. + */ + iommufd_object_finalize(ictx, &ioas->obj); + return 0; +} +EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_id, IOMMUFD_VFIO); + +int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd) +{ + struct iommu_vfio_ioas *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + + if (cmd->__reserved) + return -EOPNOTSUPP; + switch (cmd->op) { + case IOMMU_VFIO_IOAS_GET: + ioas = get_compat_ioas(ucmd->ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + cmd->ioas_id = ioas->obj.id; + iommufd_put_object(&ioas->obj); + return iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + + case IOMMU_VFIO_IOAS_SET: + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + xa_lock(&ucmd->ictx->objects); + ucmd->ictx->vfio_ioas = ioas; + xa_unlock(&ucmd->ictx->objects); + iommufd_put_object(&ioas->obj); + return 0; + + case IOMMU_VFIO_IOAS_CLEAR: + xa_lock(&ucmd->ictx->objects); + ucmd->ictx->vfio_ioas = NULL; + xa_unlock(&ucmd->ictx->objects); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd, + void __user *arg) +{ + u32 supported_flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE; + size_t minsz = offsetofend(struct vfio_iommu_type1_dma_map, size); + struct vfio_iommu_type1_dma_map map; + int iommu_prot = IOMMU_CACHE; + struct iommufd_ioas *ioas; + unsigned long iova; + int rc; + + if (copy_from_user(&map, arg, minsz)) + return -EFAULT; + + if (map.argsz < minsz || map.flags & ~supported_flags) + return -EINVAL; + + if (map.flags & VFIO_DMA_MAP_FLAG_READ) + iommu_prot |= IOMMU_READ; + if (map.flags & VFIO_DMA_MAP_FLAG_WRITE) + iommu_prot |= IOMMU_WRITE; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + /* + * Maps created through the legacy interface always use VFIO compatible + * rlimit accounting. If the user wishes to use the faster user based + * rlimit accounting then they must use the new interface. + */ + iova = map.iova; + rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr), + map.size, iommu_prot, 0); + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd, + void __user *arg) +{ + size_t minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); + /* + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is obsoleted by the new + * dirty tracking direction: + * https://lore.kernel.org/kvm/20220731125503.142683-1-yishaih@nvidia.com/ + * https://lore.kernel.org/kvm/20220428210933.3583-1-joao.m.martins@oracle.com/ + */ + u32 supported_flags = VFIO_DMA_UNMAP_FLAG_ALL; + struct vfio_iommu_type1_dma_unmap unmap; + unsigned long unmapped = 0; + struct iommufd_ioas *ioas; + int rc; + + if (copy_from_user(&unmap, arg, minsz)) + return -EFAULT; + + if (unmap.argsz < minsz || unmap.flags & ~supported_flags) + return -EINVAL; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (unmap.flags & VFIO_DMA_UNMAP_FLAG_ALL) { + if (unmap.iova != 0 || unmap.size != 0) { + rc = -EINVAL; + goto err_put; + } + rc = iopt_unmap_all(&ioas->iopt, &unmapped); + } else { + if (READ_ONCE(ioas->iopt.disable_large_pages)) { + /* + * Create cuts at the start and last of the requested + * range. If the start IOVA is 0 then it doesn't need to + * be cut. + */ + unsigned long iovas[] = { unmap.iova + unmap.size - 1, + unmap.iova - 1 }; + + rc = iopt_cut_iova(&ioas->iopt, iovas, + unmap.iova ? 2 : 1); + if (rc) + goto err_put; + } + rc = iopt_unmap_iova(&ioas->iopt, unmap.iova, unmap.size, + &unmapped); + } + unmap.size = unmapped; + if (copy_to_user(arg, &unmap, minsz)) + rc = -EFAULT; + +err_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx) +{ + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = 1; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + mutex_lock(&ioas->mutex); + list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) { + if (!hwpt->enforce_cache_coherency) { + rc = 0; + break; + } + } + mutex_unlock(&ioas->mutex); + + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, + unsigned long type) +{ + switch (type) { + case VFIO_TYPE1_IOMMU: + case VFIO_TYPE1v2_IOMMU: + case VFIO_UNMAP_ALL: + return 1; + + case VFIO_DMA_CC_IOMMU: + return iommufd_vfio_cc_iommu(ictx); + + /* + * This is obsolete, and to be removed from VFIO. It was an incomplete + * idea that got merged. + * https://lore.kernel.org/kvm/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/ + */ + case VFIO_TYPE1_NESTING_IOMMU: + return 0; + + /* + * VFIO_DMA_MAP_FLAG_VADDR + * https://lore.kernel.org/kvm/1611939252-7240-1-git-send-email-steven.sistare@oracle.com/ + * https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ + * + * It is hard to see how this could be implemented safely. + */ + case VFIO_UPDATE_VADDR: + default: + return 0; + } +} + +static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type) +{ + struct iommufd_ioas *ioas = NULL; + int rc = 0; + + if (type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) + return -EINVAL; + + /* VFIO fails the set_iommu if there is no group */ + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + /* + * The difference between TYPE1 and TYPE1v2 is the ability to unmap in + * the middle of mapped ranges. This is complicated by huge page support + * which creates single large IOPTEs that cannot be split by the iommu + * driver. TYPE1 is very old at this point and likely nothing uses it, + * however it is simple enough to emulate by simply disabling the + * problematic large IOPTEs. Then we can safely unmap within any range. + */ + if (type == VFIO_TYPE1_IOMMU) + rc = iopt_disable_large_pages(&ioas->iopt); + iommufd_put_object(&ioas->obj); + return rc; +} + +static unsigned long iommufd_get_pagesizes(struct iommufd_ioas *ioas) +{ + struct io_pagetable *iopt = &ioas->iopt; + unsigned long pgsize_bitmap = ULONG_MAX; + struct iommu_domain *domain; + unsigned long index; + + down_read(&iopt->domains_rwsem); + xa_for_each(&iopt->domains, index, domain) + pgsize_bitmap &= domain->pgsize_bitmap; + + /* See vfio_update_pgsize_bitmap() */ + if (pgsize_bitmap & ~PAGE_MASK) { + pgsize_bitmap &= PAGE_MASK; + pgsize_bitmap |= PAGE_SIZE; + } + pgsize_bitmap = max(pgsize_bitmap, ioas->iopt.iova_alignment); + up_read(&iopt->domains_rwsem); + return pgsize_bitmap; +} + +static int iommufd_fill_cap_iova(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail) +{ + struct vfio_iommu_type1_info_cap_iova_range __user *ucap_iovas = + container_of(cur, + struct vfio_iommu_type1_info_cap_iova_range __user, + header); + struct vfio_iommu_type1_info_cap_iova_range cap_iovas = { + .header = { + .id = VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE, + .version = 1, + }, + }; + struct interval_tree_span_iter span; + + interval_tree_for_each_span(&span, &ioas->iopt.reserved_itree, 0, + ULONG_MAX) { + struct vfio_iova_range range; + + if (!span.is_hole) + continue; + range.start = span.start_hole; + range.end = span.last_hole; + if (avail >= struct_size(&cap_iovas, iova_ranges, + cap_iovas.nr_iovas + 1) && + copy_to_user(&ucap_iovas->iova_ranges[cap_iovas.nr_iovas], + &range, sizeof(range))) + return -EFAULT; + cap_iovas.nr_iovas++; + } + if (avail >= struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas) && + copy_to_user(ucap_iovas, &cap_iovas, sizeof(cap_iovas))) + return -EFAULT; + return struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas); +} + +static int iommufd_fill_cap_dma_avail(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail) +{ + struct vfio_iommu_type1_info_dma_avail cap_dma = { + .header = { + .id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL, + .version = 1, + }, + /* + * iommufd's limit is based on the cgroup's memory limit. + * Normally vfio would return U16_MAX here, and provide a module + * parameter to adjust it. Since S390 qemu userspace actually + * pays attention and needs a value bigger than U16_MAX return + * U32_MAX. + */ + .avail = U32_MAX, + }; + + if (avail >= sizeof(cap_dma) && + copy_to_user(cur, &cap_dma, sizeof(cap_dma))) + return -EFAULT; + return sizeof(cap_dma); +} + +static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx, + void __user *arg) +{ + typedef int (*fill_cap_fn)(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail); + static const fill_cap_fn fill_fns[] = { + iommufd_fill_cap_dma_avail, + iommufd_fill_cap_iova, + }; + size_t minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes); + struct vfio_info_cap_header __user *last_cap = NULL; + struct vfio_iommu_type1_info info; + struct iommufd_ioas *ioas; + size_t total_cap_size; + int rc; + int i; + + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + minsz = min_t(size_t, info.argsz, sizeof(info)); + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + info.flags = VFIO_IOMMU_INFO_PGSIZES; + info.iova_pgsizes = iommufd_get_pagesizes(ioas); + info.cap_offset = 0; + + down_read(&ioas->iopt.iova_rwsem); + total_cap_size = sizeof(info); + for (i = 0; i != ARRAY_SIZE(fill_fns); i++) { + int cap_size; + + if (info.argsz > total_cap_size) + cap_size = fill_fns[i](ioas, arg + total_cap_size, + info.argsz - total_cap_size); + else + cap_size = fill_fns[i](ioas, NULL, 0); + if (cap_size < 0) { + rc = cap_size; + goto out_put; + } + if (last_cap && info.argsz >= total_cap_size && + put_user(total_cap_size, &last_cap->next)) { + rc = -EFAULT; + goto out_put; + } + last_cap = arg + total_cap_size; + total_cap_size += cap_size; + } + + /* + * If the user did not provide enough space then only some caps are + * returned and the argsz will be updated to the correct amount to get + * all caps. + */ + if (info.argsz >= total_cap_size) + info.cap_offset = sizeof(info); + info.argsz = total_cap_size; + info.flags |= VFIO_IOMMU_INFO_CAPS; + if (copy_to_user(arg, &info, minsz)) { + rc = -EFAULT; + goto out_put; + } + rc = 0; + +out_put: + up_read(&ioas->iopt.iova_rwsem); + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, + unsigned long arg) +{ + void __user *uarg = (void __user *)arg; + + switch (cmd) { + case VFIO_GET_API_VERSION: + return VFIO_API_VERSION; + case VFIO_SET_IOMMU: + return iommufd_vfio_set_iommu(ictx, arg); + case VFIO_CHECK_EXTENSION: + return iommufd_vfio_check_extension(ictx, arg); + case VFIO_IOMMU_GET_INFO: + return iommufd_vfio_iommu_get_info(ictx, uarg); + case VFIO_IOMMU_MAP_DMA: + return iommufd_vfio_map_dma(ictx, cmd, uarg); + case VFIO_IOMMU_UNMAP_DMA: + return iommufd_vfio_unmap_dma(ictx, cmd, uarg); + case VFIO_IOMMU_DIRTY_PAGES: + default: + return -ENOIOCTLCMD; + } + return -ENOIOCTLCMD; +} diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 46c481a26d79..84af9a239769 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -54,6 +54,7 @@ void iommufd_access_unpin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length); int iommufd_access_rw(struct iommufd_access *access, unsigned long iova, void *data, size_t len, unsigned int flags); +int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id); #else /* !CONFIG_IOMMUFD */ static inline struct iommufd_ctx *iommufd_ctx_from_file(struct file *file) { @@ -84,5 +85,11 @@ static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long { return -EOPNOTSUPP; } + +static inline int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, + u32 *out_ioas_id) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_IOMMUFD */ #endif diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 30cc5c5e2b34..98ebba80cfa1 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -44,6 +44,7 @@ enum { IOMMUFD_CMD_IOAS_MAP, IOMMUFD_CMD_IOAS_UNMAP, IOMMUFD_CMD_OPTION, + IOMMUFD_CMD_VFIO_IOAS, }; /** @@ -308,4 +309,39 @@ struct iommu_option { __aligned_u64 val64; }; #define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) + +/** + * enum iommufd_vfio_ioas_op - IOMMU_VFIO_IOAS_* ioctls + * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS + * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS + * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility + */ +enum iommufd_vfio_ioas_op { + IOMMU_VFIO_IOAS_GET = 0, + IOMMU_VFIO_IOAS_SET = 1, + IOMMU_VFIO_IOAS_CLEAR = 2, +}; + +/** + * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS) + * @size: sizeof(struct iommu_vfio_ioas) + * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set + * For IOMMU_VFIO_IOAS_GET will output the IOAS ID + * @op: One of enum iommufd_vfio_ioas_op + * @__reserved: Must be 0 + * + * The VFIO compatibility support uses a single ioas because VFIO APIs do not + * support the ID field. Set or Get the IOAS that VFIO compatibility will use. + * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the + * compatibility ioas, either by taking what is already set, or auto creating + * one. From then on VFIO will continue to use that ioas and is not effected by + * this ioctl. SET or CLEAR does not destroy any auto-created IOAS. + */ +struct iommu_vfio_ioas { + __u32 size; + __u32 ioas_id; + __u16 op; + __u16 __reserved; +}; +#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) #endif -- cgit From 328281155539b44539e12d62803e09310d86d11f Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 12:21:36 -0700 Subject: cxl/pmem: Introduce nvdimm_security_ops with ->get_flags() operation Add nvdimm_security_ops support for CXL memory device with the introduction of the ->get_flags() callback function. This is part of the "Persistent Memory Data-at-rest Security" command set for CXL memory device support. The ->get_flags() function provides the security state of the persistent memory device defined by the CXL 3.0 spec section 8.2.9.8.6.1. Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166983609611.2734609.13231854299523325319.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- drivers/cxl/Makefile | 2 +- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 8 +++++++ drivers/cxl/pmem.c | 6 +++-- drivers/cxl/security.c | 56 ++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/cxl_mem.h | 1 + tools/testing/cxl/Kbuild | 1 + 7 files changed, 72 insertions(+), 3 deletions(-) create mode 100644 drivers/cxl/security.c (limited to 'include/uapi/linux') diff --git a/drivers/cxl/Makefile b/drivers/cxl/Makefile index a78270794150..db321f48ba52 100644 --- a/drivers/cxl/Makefile +++ b/drivers/cxl/Makefile @@ -9,5 +9,5 @@ obj-$(CONFIG_CXL_PORT) += cxl_port.o cxl_mem-y := mem.o cxl_pci-y := pci.o cxl_acpi-y := acpi.o -cxl_pmem-y := pmem.o +cxl_pmem-y := pmem.o security.o cxl_port-y := port.o diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 0c90f13870a4..6907ee1f43e0 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -65,6 +65,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), CXL_CMD(GET_SCAN_MEDIA, 0, CXL_VARIABLE_PAYLOAD, 0), + CXL_CMD(GET_SECURITY_STATE, 0, 0x4, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 88e3a8e54b6a..25d1d8fa7d1e 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -273,6 +273,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_SCAN_MEDIA_CAPS = 0x4303, CXL_MBOX_OP_SCAN_MEDIA = 0x4304, CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, + CXL_MBOX_OP_GET_SECURITY_STATE = 0x4500, CXL_MBOX_OP_MAX = 0x10000 }; @@ -372,6 +373,13 @@ struct cxl_mem_command { #define CXL_CMD_FLAG_FORCE_ENABLE BIT(0) }; +#define CXL_PMEM_SEC_STATE_USER_PASS_SET 0x01 +#define CXL_PMEM_SEC_STATE_MASTER_PASS_SET 0x02 +#define CXL_PMEM_SEC_STATE_LOCKED 0x04 +#define CXL_PMEM_SEC_STATE_FROZEN 0x08 +#define CXL_PMEM_SEC_STATE_USER_PLIMIT 0x10 +#define CXL_PMEM_SEC_STATE_MASTER_PLIMIT 0x20 + int cxl_mbox_send_cmd(struct cxl_dev_state *cxlds, u16 opcode, void *in, size_t in_size, void *out, size_t out_size); int cxl_dev_state_identify(struct cxl_dev_state *cxlds); diff --git a/drivers/cxl/pmem.c b/drivers/cxl/pmem.c index 4c627d67281a..efffc731c2ec 100644 --- a/drivers/cxl/pmem.c +++ b/drivers/cxl/pmem.c @@ -11,6 +11,8 @@ #include "cxlmem.h" #include "cxl.h" +extern const struct nvdimm_security_ops *cxl_security_ops; + /* * Ordered workqueue for cxl nvdimm device arrival and departure * to coordinate bus rescans when a bridge arrives and trigger remove @@ -78,8 +80,8 @@ static int cxl_nvdimm_probe(struct device *dev) set_bit(ND_CMD_GET_CONFIG_SIZE, &cmd_mask); set_bit(ND_CMD_GET_CONFIG_DATA, &cmd_mask); set_bit(ND_CMD_SET_CONFIG_DATA, &cmd_mask); - nvdimm = nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, - cmd_mask, 0, NULL); + nvdimm = __nvdimm_create(cxl_nvb->nvdimm_bus, cxl_nvd, NULL, flags, + cmd_mask, 0, NULL, NULL, cxl_security_ops, NULL); if (!nvdimm) { rc = -ENOMEM; goto out; diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c new file mode 100644 index 000000000000..806173084216 --- /dev/null +++ b/drivers/cxl/security.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2022 Intel Corporation. All rights reserved. */ +#include +#include +#include +#include +#include +#include "cxlmem.h" +#include "cxl.h" + +static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + unsigned long security_flags = 0; + u32 sec_out; + int rc; + + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_GET_SECURITY_STATE, NULL, 0, + &sec_out, sizeof(sec_out)); + if (rc < 0) + return 0; + + if (ptype == NVDIMM_MASTER) { + if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PASS_SET) + set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags); + else + set_bit(NVDIMM_SECURITY_DISABLED, &security_flags); + if (sec_out & CXL_PMEM_SEC_STATE_MASTER_PLIMIT) + set_bit(NVDIMM_SECURITY_FROZEN, &security_flags); + return security_flags; + } + + if (sec_out & CXL_PMEM_SEC_STATE_USER_PASS_SET) { + if (sec_out & CXL_PMEM_SEC_STATE_FROZEN || + sec_out & CXL_PMEM_SEC_STATE_USER_PLIMIT) + set_bit(NVDIMM_SECURITY_FROZEN, &security_flags); + + if (sec_out & CXL_PMEM_SEC_STATE_LOCKED) + set_bit(NVDIMM_SECURITY_LOCKED, &security_flags); + else + set_bit(NVDIMM_SECURITY_UNLOCKED, &security_flags); + } else { + set_bit(NVDIMM_SECURITY_DISABLED, &security_flags); + } + + return security_flags; +} + +static const struct nvdimm_security_ops __cxl_security_ops = { + .get_flags = cxl_pmem_get_security_flags, +}; + +const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index c71021a2a9ed..cdc6049683ce 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -41,6 +41,7 @@ ___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"), \ ___C(SCAN_MEDIA, "Scan Media"), \ ___C(GET_SCAN_MEDIA, "Get Scan Media Results"), \ + ___C(GET_SECURITY_STATE, "Get Security State"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a diff --git a/tools/testing/cxl/Kbuild b/tools/testing/cxl/Kbuild index 500be85729cc..e4048a05b6ab 100644 --- a/tools/testing/cxl/Kbuild +++ b/tools/testing/cxl/Kbuild @@ -26,6 +26,7 @@ cxl_acpi-y += config_check.o obj-m += cxl_pmem.o cxl_pmem-y := $(CXL_SRC)/pmem.o +cxl_pmem-y += $(CXL_SRC)/security.o cxl_pmem-y += config_check.o obj-m += cxl_port.o -- cgit From 255c4f4a6d5b60cfcd218d8fdae517b886ff155a Mon Sep 17 00:00:00 2001 From: Mike Christie Date: Mon, 21 Nov 2022 21:26:00 -0600 Subject: block: Add error codes for common PR failures If a PR operation fails we can return a device-specific error which is impossible to handle in some cases because we could have a mix of devices when DM is used, or future users like LIO only knows it's interacting with a block device so it doesn't know the type. This patch adds a new pr_status enum so drivers can convert errors to a common type which can be handled by the caller. Signed-off-by: Mike Christie Link: https://lore.kernel.org/r/20221122032603.32766-2-michael.christie@oracle.com Reviewed-by: Christoph Hellwig Reviewed-by: Chaitanya Kulkarni Signed-off-by: Martin K. Petersen --- include/uapi/linux/pr.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pr.h b/include/uapi/linux/pr.h index ccc78cbf1221..d8126415966f 100644 --- a/include/uapi/linux/pr.h +++ b/include/uapi/linux/pr.h @@ -4,6 +4,23 @@ #include +enum pr_status { + PR_STS_SUCCESS = 0x0, + /* + * The following error codes are based on SCSI, because the interface + * was originally created for it and has existing users. + */ + /* Generic device failure. */ + PR_STS_IOERR = 0x2, + PR_STS_RESERVATION_CONFLICT = 0x18, + /* Temporary path failure that can be retried. */ + PR_STS_RETRY_PATH_FAILURE = 0xe0000, + /* The request was failed due to a fast failure timer. */ + PR_STS_PATH_FAST_FAILED = 0xf0000, + /* The path cannot be reached and has been marked as failed. */ + PR_STS_PATH_FAILED = 0x10000, +}; + enum pr_type { PR_WRITE_EXCLUSIVE = 1, PR_EXCLUSIVE_ACCESS = 2, -- cgit From af6397c9ee2b42988c912dcad2fca1f43d5c1c99 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Mon, 28 Nov 2022 12:36:44 -0800 Subject: devlink: support directly reading from region memory To read from a region, user space must currently request a new snapshot of the region and then read from that snapshot. This can sometimes be overkill if user space only reads a tiny portion. They first create the snapshot, then request a read, then destroy the snapshot. For regions which have a single underlying "contents", it makes sense to allow supporting direct reading of the region data. Extend the DEVLINK_CMD_REGION_READ to allow direct reading from a region if requested via the new DEVLINK_ATTR_REGION_DIRECT. If this attribute is set, then perform a direct read instead of using a snapshot. Direct read is mutually exclusive with DEVLINK_ATTR_REGION_SNAPSHOT_ID, and care is taken to ensure that we reject commands which provide incorrect attributes. Regions must enable support for direct read by implementing the .read() callback function. If a region does not support such direct reads, a suitable extended error message is reported. Signed-off-by: Jacob Keller Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- .../networking/devlink/devlink-region.rst | 13 ++++ include/net/devlink.h | 16 +++++ include/uapi/linux/devlink.h | 2 + net/core/devlink.c | 80 +++++++++++++++++----- 4 files changed, 94 insertions(+), 17 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index f06dca9a1eb6..9232cd7da301 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -31,6 +31,15 @@ in its ``devlink_region_ops`` structure. If snapshot id is not set in the ``DEVLINK_CMD_REGION_NEW`` request kernel will allocate one and send the snapshot information to user space. +Regions may optionally allow directly reading from their contents without a +snapshot. Direct read requests are not atomic. In particular a read request +of size 256 bytes or larger will be split into multiple chunks. If atomic +access is required, use a snapshot. A driver wishing to enable this for a +region should implement the ``.read`` callback in the ``devlink_region_ops`` +structure. User space can request a direct read by using the +``DEVLINK_ATTR_REGION_DIRECT`` attribute instead of specifying a snapshot +id. + example usage ------------- @@ -65,6 +74,10 @@ example usage $ devlink region read pci/0000:00:05.0/fw-health snapshot 1 address 0 length 16 0000000000000000 0014 95dc 0014 9514 0035 1670 0034 db30 + # Read from the region without a snapshot + $ devlink region read pci/0000:00:05.0/fw-health address 16 length 16 + 0000000000000010 0000 0000 ffff ff04 0029 8c00 0028 8cc8 + As regions are likely very device or driver specific, no generic regions are defined. See the driver-specific documentation files for information on the specific regions a driver supports. diff --git a/include/net/devlink.h b/include/net/devlink.h index 074a79b8933f..02528f736f65 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -650,6 +650,10 @@ struct devlink_info_req; * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @read: callback to directly read a portion of the region. On success, + * the data pointer will be updated with the contents of the + * requested portion of the region. The function will be called + * while the devlink instance lock is held. * @priv: Pointer to driver private data for the region operation */ struct devlink_region_ops { @@ -659,6 +663,10 @@ struct devlink_region_ops { const struct devlink_region_ops *ops, struct netlink_ext_ack *extack, u8 **data); + int (*read)(struct devlink *devlink, + const struct devlink_region_ops *ops, + struct netlink_ext_ack *extack, + u64 offset, u32 size, u8 *data); void *priv; }; @@ -670,6 +678,10 @@ struct devlink_region_ops { * the data variable must be updated to point to the snapshot data. * The function will be called while the devlink instance lock is * held. + * @read: callback to directly read a portion of the region. On success, + * the data pointer will be updated with the contents of the + * requested portion of the region. The function will be called + * while the devlink instance lock is held. * @priv: Pointer to driver private data for the region operation */ struct devlink_port_region_ops { @@ -679,6 +691,10 @@ struct devlink_port_region_ops { const struct devlink_port_region_ops *ops, struct netlink_ext_ack *extack, u8 **data); + int (*read)(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + struct netlink_ext_ack *extack, + u64 offset, u32 size, u8 *data); void *priv; }; diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 498d0d5d0957..70191d96af89 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -610,6 +610,8 @@ enum devlink_attr { DEVLINK_ATTR_RATE_TX_PRIORITY, /* u32 */ DEVLINK_ATTR_RATE_TX_WEIGHT, /* u32 */ + DEVLINK_ATTR_REGION_DIRECT, /* flag */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 6c05cfaa571d..298041a44aa8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -6515,6 +6515,26 @@ devlink_region_snapshot_fill(void *cb_priv, u8 *chunk, u32 chunk_size, return 0; } +static int +devlink_region_port_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, + u64 curr_offset, struct netlink_ext_ack *extack) +{ + struct devlink_region *region = cb_priv; + + return region->port_ops->read(region->port, region->port_ops, extack, + curr_offset, chunk_size, chunk); +} + +static int +devlink_region_direct_fill(void *cb_priv, u8 *chunk, u32 chunk_size, + u64 curr_offset, struct netlink_ext_ack *extack) +{ + struct devlink_region *region = cb_priv; + + return region->ops->read(region->devlink, region->ops, extack, + curr_offset, chunk_size, chunk); +} + static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { @@ -6523,12 +6543,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->attrs; struct devlink_port *port = NULL; - struct devlink_snapshot *snapshot; + devlink_chunk_fill_t *region_cb; struct devlink_region *region; const char *region_name; struct devlink *devlink; unsigned int index; - u32 snapshot_id; + void *region_cb_priv; void *hdr; int err; @@ -6546,12 +6566,6 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } - if (!attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) { - NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); - err = -EINVAL; - goto out_unlock; - } - if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); @@ -6577,12 +6591,43 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, } snapshot_attr = attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]; - snapshot_id = nla_get_u32(snapshot_attr); - snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); - if (!snapshot) { - NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); - err = -EINVAL; - goto out_unlock; + if (!snapshot_attr) { + if (!nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { + NL_SET_ERR_MSG(cb->extack, "No snapshot id provided"); + err = -EINVAL; + goto out_unlock; + } + + if (!region->ops->read) { + NL_SET_ERR_MSG(cb->extack, "Requested region does not support direct read"); + err = -EOPNOTSUPP; + goto out_unlock; + } + + if (port) + region_cb = &devlink_region_port_direct_fill; + else + region_cb = &devlink_region_direct_fill; + region_cb_priv = region; + } else { + struct devlink_snapshot *snapshot; + u32 snapshot_id; + + if (nla_get_flag(attrs[DEVLINK_ATTR_REGION_DIRECT])) { + NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Direct region read does not use snapshot"); + err = -EINVAL; + goto out_unlock; + } + + snapshot_id = nla_get_u32(snapshot_attr); + snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id); + if (!snapshot) { + NL_SET_ERR_MSG_ATTR(cb->extack, snapshot_attr, "Requested snapshot does not exist"); + err = -EINVAL; + goto out_unlock; + } + region_cb = &devlink_region_snapshot_fill; + region_cb_priv = snapshot; } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && @@ -6633,9 +6678,9 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; } - err = devlink_nl_region_read_fill(skb, &devlink_region_snapshot_fill, - snapshot, start_offset, end_offset, - &ret_offset, cb->extack); + err = devlink_nl_region_read_fill(skb, region_cb, region_cb_priv, + start_offset, end_offset, &ret_offset, + cb->extack); if (err && err != -EMSGSIZE) goto nla_put_failure; @@ -9280,6 +9325,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_SELFTESTS] = { .type = NLA_NESTED }, [DEVLINK_ATTR_RATE_TX_PRIORITY] = { .type = NLA_U32 }, [DEVLINK_ATTR_RATE_TX_WEIGHT] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_DIRECT] = { .type = NLA_FLAG }, }; static const struct genl_small_ops devlink_nl_ops[] = { -- cgit From e0cefada1383c5ceb5a35f08369d0d40a6629c18 Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 1 Dec 2022 20:58:19 +0800 Subject: fscrypt: Add SM4 XTS/CTS symmetric algorithm support Add support for XTS and CTS mode variant of SM4 algorithm. The former is used to encrypt file contents, while the latter (SM4-CTS-CBC) is used to encrypt filenames. SM4 is a symmetric algorithm widely used in China, and is even mandatory algorithm in some special scenarios. We need to provide these users with the ability to encrypt files or disks using SM4-XTS. Signed-off-by: Tianjia Zhang Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20221201125819.36932-3-tianjia.zhang@linux.alibaba.com --- Documentation/filesystems/fscrypt.rst | 1 + fs/crypto/keysetup.c | 15 +++++++++++++++ fs/crypto/policy.c | 5 +++++ include/uapi/linux/fscrypt.h | 2 ++ 4 files changed, 23 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/filesystems/fscrypt.rst b/Documentation/filesystems/fscrypt.rst index 5ba5817c17c2..c0784ec05553 100644 --- a/Documentation/filesystems/fscrypt.rst +++ b/Documentation/filesystems/fscrypt.rst @@ -338,6 +338,7 @@ Currently, the following pairs of encryption modes are supported: - AES-128-CBC for contents and AES-128-CTS-CBC for filenames - Adiantum for both contents and filenames - AES-256-XTS for contents and AES-256-HCTR2 for filenames (v2 policies only) +- SM4-XTS for contents and SM4-CTS-CBC for filenames (v2 policies only) If unsure, you should use the (AES-256-XTS, AES-256-CTS-CBC) pair. diff --git a/fs/crypto/keysetup.c b/fs/crypto/keysetup.c index 9e44dc078a81..94757ccd3056 100644 --- a/fs/crypto/keysetup.c +++ b/fs/crypto/keysetup.c @@ -44,6 +44,21 @@ struct fscrypt_mode fscrypt_modes[] = { .security_strength = 16, .ivsize = 16, }, + [FSCRYPT_MODE_SM4_XTS] = { + .friendly_name = "SM4-XTS", + .cipher_str = "xts(sm4)", + .keysize = 32, + .security_strength = 16, + .ivsize = 16, + .blk_crypto_mode = BLK_ENCRYPTION_MODE_SM4_XTS, + }, + [FSCRYPT_MODE_SM4_CTS] = { + .friendly_name = "SM4-CTS-CBC", + .cipher_str = "cts(cbc(sm4))", + .keysize = 16, + .security_strength = 16, + .ivsize = 16, + }, [FSCRYPT_MODE_ADIANTUM] = { .friendly_name = "Adiantum", .cipher_str = "adiantum(xchacha12,aes)", diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c index 84fa51604b15..893661b52376 100644 --- a/fs/crypto/policy.c +++ b/fs/crypto/policy.c @@ -90,6 +90,11 @@ static bool fscrypt_valid_enc_modes_v2(u32 contents_mode, u32 filenames_mode) if (contents_mode == FSCRYPT_MODE_AES_256_XTS && filenames_mode == FSCRYPT_MODE_AES_256_HCTR2) return true; + + if (contents_mode == FSCRYPT_MODE_SM4_XTS && + filenames_mode == FSCRYPT_MODE_SM4_CTS) + return true; + return fscrypt_valid_enc_modes_v1(contents_mode, filenames_mode); } diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index a756b29afcc2..47dbd1994bfe 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -26,6 +26,8 @@ #define FSCRYPT_MODE_AES_256_CTS 4 #define FSCRYPT_MODE_AES_128_CBC 5 #define FSCRYPT_MODE_AES_128_CTS 6 +#define FSCRYPT_MODE_SM4_XTS 7 +#define FSCRYPT_MODE_SM4_CTS 8 #define FSCRYPT_MODE_ADIANTUM 9 #define FSCRYPT_MODE_AES_256_HCTR2 10 /* If adding a mode number > 10, update FSCRYPT_MODE_MAX in fscrypt_private.h */ -- cgit From 997469407f266250040f20ec73aecc77ad277145 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 12:21:47 -0700 Subject: cxl/pmem: Add "Set Passphrase" security command support Create callback function to support the nvdimm_security_ops ->change_key() callback. Translate the operation to send "Set Passphrase" security command for CXL memory device. The operation supports setting a passphrase for the CXL persistent memory device. It also supports the changing of the currently set passphrase. The operation allows manipulation of a user passphrase or a master passphrase. See CXL rev3.0 spec section 8.2.9.8.6.2 for reference. However, the spec leaves a gap WRT master passphrase usages. The spec does not define any ways to retrieve the status of if the support of master passphrase is available for the device, nor does the commands that utilize master passphrase will return a specific error that indicates master passphrase is not supported. If using a device does not support master passphrase and a command is issued with a master passphrase, the error message returned by the device will be ambiguous. Reviewed-by: Davidlohr Bueso Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166983610751.2734609.4445075071552032091.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 15 +++++++++++++++ drivers/cxl/security.c | 22 ++++++++++++++++++++++ include/uapi/linux/cxl_mem.h | 1 + 4 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 6907ee1f43e0..2fdafa697e6a 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -66,6 +66,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), CXL_CMD(GET_SCAN_MEDIA, 0, CXL_VARIABLE_PAYLOAD, 0), CXL_CMD(GET_SECURITY_STATE, 0, 0x4, 0), + CXL_CMD(SET_PASSPHRASE, 0x60, 0, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 25d1d8fa7d1e..725b08148524 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -274,6 +274,7 @@ enum cxl_opcode { CXL_MBOX_OP_SCAN_MEDIA = 0x4304, CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, CXL_MBOX_OP_GET_SECURITY_STATE = 0x4500, + CXL_MBOX_OP_SET_PASSPHRASE = 0x4501, CXL_MBOX_OP_MAX = 0x10000 }; @@ -380,6 +381,20 @@ struct cxl_mem_command { #define CXL_PMEM_SEC_STATE_USER_PLIMIT 0x10 #define CXL_PMEM_SEC_STATE_MASTER_PLIMIT 0x20 +/* set passphrase input payload */ +struct cxl_set_pass { + u8 type; + u8 reserved[31]; + /* CXL field using NVDIMM define, same length */ + u8 old_pass[NVDIMM_PASSPHRASE_LEN]; + u8 new_pass[NVDIMM_PASSPHRASE_LEN]; +} __packed; + +enum { + CXL_PMEM_SEC_PASS_MASTER = 0, + CXL_PMEM_SEC_PASS_USER, +}; + int cxl_mbox_send_cmd(struct cxl_dev_state *cxlds, u16 opcode, void *in, size_t in_size, void *out, size_t out_size); int cxl_dev_state_identify(struct cxl_dev_state *cxlds); diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 806173084216..5365646230c3 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -49,8 +49,30 @@ static unsigned long cxl_pmem_get_security_flags(struct nvdimm *nvdimm, return security_flags; } +static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, + const struct nvdimm_key_data *old_data, + const struct nvdimm_key_data *new_data, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_set_pass set_pass; + int rc; + + set_pass.type = ptype == NVDIMM_MASTER ? + CXL_PMEM_SEC_PASS_MASTER : CXL_PMEM_SEC_PASS_USER; + memcpy(set_pass.old_pass, old_data->data, NVDIMM_PASSPHRASE_LEN); + memcpy(set_pass.new_pass, new_data->data, NVDIMM_PASSPHRASE_LEN); + + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_SET_PASSPHRASE, + &set_pass, sizeof(set_pass), NULL, 0); + return rc; +} + static const struct nvdimm_security_ops __cxl_security_ops = { .get_flags = cxl_pmem_get_security_flags, + .change_key = cxl_pmem_security_change_key, }; const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index cdc6049683ce..9da047e9b038 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -42,6 +42,7 @@ ___C(SCAN_MEDIA, "Scan Media"), \ ___C(GET_SCAN_MEDIA, "Get Scan Media Results"), \ ___C(GET_SECURITY_STATE, "Get Security State"), \ + ___C(SET_PASSPHRASE, "Set Passphrase"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From c4ef680d0b72815003a76074ca1cd872a2fecfc3 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 12:21:58 -0700 Subject: cxl/pmem: Add Disable Passphrase security command support Create callback function to support the nvdimm_security_ops ->disable() callback. Translate the operation to send "Disable Passphrase" security command for CXL memory device. The operation supports disabling a passphrase for the CXL persistent memory device. In the original implementation of nvdimm_security_ops, this operation only supports disabling of the user passphrase. This is due to the NFIT version of disable passphrase only supported disabling of user passphrase. The CXL spec allows disabling of the master passphrase as well which nvidmm_security_ops does not support yet. In this commit, the callback function will only support user passphrase. See CXL rev3.0 spec section 8.2.9.8.6.3 for reference. Reviewed-by: Davidlohr Bueso Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166983611878.2734609.10602135274526390127.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 8 ++++++++ drivers/cxl/security.c | 18 ++++++++++++++++++ include/uapi/linux/cxl_mem.h | 1 + 4 files changed, 28 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 2fdafa697e6a..890db291c6bf 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -67,6 +67,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SCAN_MEDIA, 0, CXL_VARIABLE_PAYLOAD, 0), CXL_CMD(GET_SECURITY_STATE, 0, 0x4, 0), CXL_CMD(SET_PASSPHRASE, 0x60, 0, 0), + CXL_CMD(DISABLE_PASSPHRASE, 0x40, 0, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 725b08148524..9ad92f975b78 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -275,6 +275,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_SCAN_MEDIA = 0x4305, CXL_MBOX_OP_GET_SECURITY_STATE = 0x4500, CXL_MBOX_OP_SET_PASSPHRASE = 0x4501, + CXL_MBOX_OP_DISABLE_PASSPHRASE = 0x4502, CXL_MBOX_OP_MAX = 0x10000 }; @@ -390,6 +391,13 @@ struct cxl_set_pass { u8 new_pass[NVDIMM_PASSPHRASE_LEN]; } __packed; +/* disable passphrase input payload */ +struct cxl_disable_pass { + u8 type; + u8 reserved[31]; + u8 pass[NVDIMM_PASSPHRASE_LEN]; +} __packed; + enum { CXL_PMEM_SEC_PASS_MASTER = 0, CXL_PMEM_SEC_PASS_USER, diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 5365646230c3..5a8e852ecadb 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -70,9 +70,27 @@ static int cxl_pmem_security_change_key(struct nvdimm *nvdimm, return rc; } +static int cxl_pmem_security_disable(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key_data) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_disable_pass dis_pass; + int rc; + + dis_pass.type = CXL_PMEM_SEC_PASS_USER; + memcpy(dis_pass.pass, key_data->data, NVDIMM_PASSPHRASE_LEN); + + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_DISABLE_PASSPHRASE, + &dis_pass, sizeof(dis_pass), NULL, 0); + return rc; +} + static const struct nvdimm_security_ops __cxl_security_ops = { .get_flags = cxl_pmem_get_security_flags, .change_key = cxl_pmem_security_change_key, + .disable = cxl_pmem_security_disable, }; const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 9da047e9b038..f6d383a80f22 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -43,6 +43,7 @@ ___C(GET_SCAN_MEDIA, "Get Scan Media Results"), \ ___C(GET_SECURITY_STATE, "Get Security State"), \ ___C(SET_PASSPHRASE, "Set Passphrase"), \ + ___C(DISABLE_PASSPHRASE, "Disable Passphrase"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From a072f7b7972fd85bdefefa1d6febec483438d420 Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 12:22:10 -0700 Subject: cxl/pmem: Add "Freeze Security State" security command support Create callback function to support the nvdimm_security_ops() ->freeze() callback. Translate the operation to send "Freeze Security State" security command for CXL memory device. See CXL rev3.0 spec section 8.2.9.8.6.5 for reference. Reviewed-by: Davidlohr Bueso Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166983613019.2734609.10645754779802492122.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 1 + drivers/cxl/security.c | 10 ++++++++++ include/uapi/linux/cxl_mem.h | 1 + 4 files changed, 13 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 890db291c6bf..20bceb9e78bc 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -68,6 +68,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SECURITY_STATE, 0, 0x4, 0), CXL_CMD(SET_PASSPHRASE, 0x60, 0, 0), CXL_CMD(DISABLE_PASSPHRASE, 0x40, 0, 0), + CXL_CMD(FREEZE_SECURITY, 0, 0, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 9ad92f975b78..9007158969fe 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -276,6 +276,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_SECURITY_STATE = 0x4500, CXL_MBOX_OP_SET_PASSPHRASE = 0x4501, CXL_MBOX_OP_DISABLE_PASSPHRASE = 0x4502, + CXL_MBOX_OP_FREEZE_SECURITY = 0x4504, CXL_MBOX_OP_MAX = 0x10000 }; diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 5a8e852ecadb..f323a1593cfc 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -87,10 +87,20 @@ static int cxl_pmem_security_disable(struct nvdimm *nvdimm, return rc; } +static int cxl_pmem_security_freeze(struct nvdimm *nvdimm) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + + return cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_FREEZE_SECURITY, NULL, 0, NULL, 0); +} + static const struct nvdimm_security_ops __cxl_security_ops = { .get_flags = cxl_pmem_get_security_flags, .change_key = cxl_pmem_security_change_key, .disable = cxl_pmem_security_disable, + .freeze = cxl_pmem_security_freeze, }; const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index f6d383a80f22..7c0adcd68f4c 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -44,6 +44,7 @@ ___C(GET_SECURITY_STATE, "Get Security State"), \ ___C(SET_PASSPHRASE, "Set Passphrase"), \ ___C(DISABLE_PASSPHRASE, "Disable Passphrase"), \ + ___C(FREEZE_SECURITY, "Freeze Security"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From 2bb692f7a6cd0a7b2c29d8d5029c4469c4ec02dd Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 12:22:21 -0700 Subject: cxl/pmem: Add "Unlock" security command support Create callback function to support the nvdimm_security_ops() ->unlock() callback. Translate the operation to send "Unlock" security command for CXL mem device. When the mem device is unlocked, cpu_cache_invalidate_memregion() is called in order to invalidate all CPU caches before attempting to access the mem device. See CXL rev3.0 spec section 8.2.9.8.6.4 for reference. Reviewed-by: Davidlohr Bueso Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166983614167.2734609.15124543712487741176.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 1 + drivers/cxl/security.c | 27 +++++++++++++++++++++++++++ include/uapi/linux/cxl_mem.h | 1 + 4 files changed, 30 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 20bceb9e78bc..4f84d3962fb1 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -69,6 +69,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(SET_PASSPHRASE, 0x60, 0, 0), CXL_CMD(DISABLE_PASSPHRASE, 0x40, 0, 0), CXL_CMD(FREEZE_SECURITY, 0, 0, 0), + CXL_CMD(UNLOCK, 0x20, 0, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 9007158969fe..4e6897e8eb7d 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -276,6 +276,7 @@ enum cxl_opcode { CXL_MBOX_OP_GET_SECURITY_STATE = 0x4500, CXL_MBOX_OP_SET_PASSPHRASE = 0x4501, CXL_MBOX_OP_DISABLE_PASSPHRASE = 0x4502, + CXL_MBOX_OP_UNLOCK = 0x4503, CXL_MBOX_OP_FREEZE_SECURITY = 0x4504, CXL_MBOX_OP_MAX = 0x10000 }; diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index f323a1593cfc..32b9e279e74b 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -5,6 +5,7 @@ #include #include #include +#include #include "cxlmem.h" #include "cxl.h" @@ -96,11 +97,37 @@ static int cxl_pmem_security_freeze(struct nvdimm *nvdimm) return cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_FREEZE_SECURITY, NULL, 0, NULL, 0); } +static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key_data) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + u8 pass[NVDIMM_PASSPHRASE_LEN]; + int rc; + + if (!cpu_cache_has_invalidate_memregion()) + return -EINVAL; + + memcpy(pass, key_data->data, NVDIMM_PASSPHRASE_LEN); + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_UNLOCK, + pass, NVDIMM_PASSPHRASE_LEN, NULL, 0); + if (rc < 0) + return rc; + + /* DIMM unlocked, invalidate all CPU caches before we read it */ + cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY); + return 0; +} + static const struct nvdimm_security_ops __cxl_security_ops = { .get_flags = cxl_pmem_get_security_flags, .change_key = cxl_pmem_security_change_key, .disable = cxl_pmem_security_disable, .freeze = cxl_pmem_security_freeze, + .unlock = cxl_pmem_security_unlock, }; const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; + +MODULE_IMPORT_NS(DEVMEM); diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 7c0adcd68f4c..95dca8d4584f 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -45,6 +45,7 @@ ___C(SET_PASSPHRASE, "Set Passphrase"), \ ___C(DISABLE_PASSPHRASE, "Disable Passphrase"), \ ___C(FREEZE_SECURITY, "Freeze Security"), \ + ___C(UNLOCK, "Unlock"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From 3b502e886d01c2f96b2774176be4c7bceef2516b Mon Sep 17 00:00:00 2001 From: Dave Jiang Date: Wed, 30 Nov 2022 12:22:32 -0700 Subject: cxl/pmem: Add "Passphrase Secure Erase" security command support Create callback function to support the nvdimm_security_ops() ->erase() callback. Translate the operation to send "Passphrase Secure Erase" security command for CXL memory device. When the mem device is secure erased, cpu_cache_invalidate_memregion() is called in order to invalidate all CPU caches before attempting to access the mem device again. See CXL 3.0 spec section 8.2.9.8.6.6 for reference. Reviewed-by: Jonathan Cameron Signed-off-by: Dave Jiang Link: https://lore.kernel.org/r/166983615293.2734609.10358657600295932156.stgit@djiang5-desk3.ch.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 1 + drivers/cxl/cxlmem.h | 8 ++++++++ drivers/cxl/security.c | 29 +++++++++++++++++++++++++++++ include/uapi/linux/cxl_mem.h | 1 + 4 files changed, 39 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index 4f84d3962fb1..8747db329087 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -70,6 +70,7 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(DISABLE_PASSPHRASE, 0x40, 0, 0), CXL_CMD(FREEZE_SECURITY, 0, 0, 0), CXL_CMD(UNLOCK, 0x20, 0, 0), + CXL_CMD(PASSPHRASE_SECURE_ERASE, 0x40, 0, 0), }; /* diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h index 4e6897e8eb7d..75baeb0bbe57 100644 --- a/drivers/cxl/cxlmem.h +++ b/drivers/cxl/cxlmem.h @@ -278,6 +278,7 @@ enum cxl_opcode { CXL_MBOX_OP_DISABLE_PASSPHRASE = 0x4502, CXL_MBOX_OP_UNLOCK = 0x4503, CXL_MBOX_OP_FREEZE_SECURITY = 0x4504, + CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE = 0x4505, CXL_MBOX_OP_MAX = 0x10000 }; @@ -400,6 +401,13 @@ struct cxl_disable_pass { u8 pass[NVDIMM_PASSPHRASE_LEN]; } __packed; +/* passphrase secure erase payload */ +struct cxl_pass_erase { + u8 type; + u8 reserved[31]; + u8 pass[NVDIMM_PASSPHRASE_LEN]; +} __packed; + enum { CXL_PMEM_SEC_PASS_MASTER = 0, CXL_PMEM_SEC_PASS_USER, diff --git a/drivers/cxl/security.c b/drivers/cxl/security.c index 32b9e279e74b..4a8132559a96 100644 --- a/drivers/cxl/security.c +++ b/drivers/cxl/security.c @@ -120,12 +120,41 @@ static int cxl_pmem_security_unlock(struct nvdimm *nvdimm, return 0; } +static int cxl_pmem_security_passphrase_erase(struct nvdimm *nvdimm, + const struct nvdimm_key_data *key, + enum nvdimm_passphrase_type ptype) +{ + struct cxl_nvdimm *cxl_nvd = nvdimm_provider_data(nvdimm); + struct cxl_memdev *cxlmd = cxl_nvd->cxlmd; + struct cxl_dev_state *cxlds = cxlmd->cxlds; + struct cxl_pass_erase erase; + int rc; + + if (!cpu_cache_has_invalidate_memregion()) + return -EINVAL; + + erase.type = ptype == NVDIMM_MASTER ? + CXL_PMEM_SEC_PASS_MASTER : CXL_PMEM_SEC_PASS_USER; + memcpy(erase.pass, key->data, NVDIMM_PASSPHRASE_LEN); + /* Flush all cache before we erase mem device */ + cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY); + rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_PASSPHRASE_SECURE_ERASE, + &erase, sizeof(erase), NULL, 0); + if (rc < 0) + return rc; + + /* mem device erased, invalidate all CPU caches before data is read */ + cpu_cache_invalidate_memregion(IORES_DESC_PERSISTENT_MEMORY); + return 0; +} + static const struct nvdimm_security_ops __cxl_security_ops = { .get_flags = cxl_pmem_get_security_flags, .change_key = cxl_pmem_security_change_key, .disable = cxl_pmem_security_disable, .freeze = cxl_pmem_security_freeze, .unlock = cxl_pmem_security_unlock, + .erase = cxl_pmem_security_passphrase_erase, }; const struct nvdimm_security_ops *cxl_security_ops = &__cxl_security_ops; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 95dca8d4584f..82bdad4ce5de 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -46,6 +46,7 @@ ___C(DISABLE_PASSPHRASE, "Disable Passphrase"), \ ___C(FREEZE_SECURITY, "Freeze Security"), \ ___C(UNLOCK, "Unlock"), \ + ___C(PASSPHRASE_SECURE_ERASE, "Passphrase Secure Erase"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From f8b435f93b7630afea2df958e0331c566496214b Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Thu, 1 Dec 2022 19:55:29 -0800 Subject: fscrypt: remove unused Speck definitions These old unused definitions were originally left around to prevent the same mode numbers from being reused. However, we've now decided to reuse the mode numbers anyway. So let's completely remove these old unused definitions to avoid confusion. There is no reason for any code to be using these constants in any way; and indeed, Debian Code Search shows no uses of them (other than in copies or translations of the header). So this should be perfectly safe. Signed-off-by: Eric Biggers Link: https://lore.kernel.org/r/20221202035529.55992-1-ebiggers@kernel.org --- include/uapi/linux/fscrypt.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 47dbd1994bfe..fd1fb0d5389d 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -187,8 +187,6 @@ struct fscrypt_get_key_status_arg { #define FS_ENCRYPTION_MODE_AES_256_CTS FSCRYPT_MODE_AES_256_CTS #define FS_ENCRYPTION_MODE_AES_128_CBC FSCRYPT_MODE_AES_128_CBC #define FS_ENCRYPTION_MODE_AES_128_CTS FSCRYPT_MODE_AES_128_CTS -#define FS_ENCRYPTION_MODE_SPECK128_256_XTS 7 /* removed */ -#define FS_ENCRYPTION_MODE_SPECK128_256_CTS 8 /* removed */ #define FS_ENCRYPTION_MODE_ADIANTUM FSCRYPT_MODE_ADIANTUM #define FS_KEY_DESC_PREFIX FSCRYPT_KEY_DESC_PREFIX #define FS_KEY_DESC_PREFIX_SIZE FSCRYPT_KEY_DESC_PREFIX_SIZE -- cgit From f8c9dfbd875b17fee59c7f1aa35a4944d4e6d810 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Wed, 30 Nov 2022 15:06:28 +0100 Subject: mptcp: add pm listener events This patch adds two new MPTCP netlink event types for PM listening socket create and close, named MPTCP_EVENT_LISTENER_CREATED and MPTCP_EVENT_LISTENER_CLOSED. Add a new function mptcp_event_pm_listener() to push the new events with family, port and addr to userspace. Invoke mptcp_event_pm_listener() with MPTCP_EVENT_LISTENER_CREATED in mptcp_listen() and mptcp_pm_nl_create_listen_socket(), invoke it with MPTCP_EVENT_LISTENER_CLOSED in __mptcp_close_ssk(). Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 9 ++++++++ net/mptcp/pm_netlink.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++ net/mptcp/protocol.c | 3 +++ net/mptcp/protocol.h | 2 ++ 4 files changed, 71 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index dfe19bf13f4c..32af2d278cb4 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -160,6 +160,12 @@ struct mptcp_info { * daddr4 | daddr6, sport, dport, backup, if_idx * [, error] * The priority of a subflow has changed. 'error' should not be set. + * + * MPTCP_EVENT_LISTENER_CREATED: family, sport, saddr4 | saddr6 + * A new PM listener is created. + * + * MPTCP_EVENT_LISTENER_CLOSED: family, sport, saddr4 | saddr6 + * A PM listener is closed. */ enum mptcp_event_type { MPTCP_EVENT_UNSPEC = 0, @@ -174,6 +180,9 @@ enum mptcp_event_type { MPTCP_EVENT_SUB_CLOSED = 11, MPTCP_EVENT_SUB_PRIORITY = 13, + + MPTCP_EVENT_LISTENER_CREATED = 15, + MPTCP_EVENT_LISTENER_CLOSED = 16, }; enum mptcp_event_attr { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index d66fbd558263..eef69d0e44ec 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1029,6 +1029,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, if (err) return err; + mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); + return 0; } @@ -2152,6 +2154,58 @@ nla_put_failure: kfree_skb(skb); } +void mptcp_event_pm_listener(const struct sock *ssk, + enum mptcp_event_type event) +{ + const struct inet_sock *issk = inet_sk(ssk); + struct net *net = sock_net(ssk); + struct nlmsghdr *nlh; + struct sk_buff *skb; + + if (!genl_has_listeners(&mptcp_genl_family, net, MPTCP_PM_EV_GRP_OFFSET)) + return; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return; + + nlh = genlmsg_put(skb, 0, 0, &mptcp_genl_family, 0, event); + if (!nlh) + goto nla_put_failure; + + if (nla_put_u16(skb, MPTCP_ATTR_FAMILY, ssk->sk_family)) + goto nla_put_failure; + + if (nla_put_be16(skb, MPTCP_ATTR_SPORT, issk->inet_sport)) + goto nla_put_failure; + + switch (ssk->sk_family) { + case AF_INET: + if (nla_put_in_addr(skb, MPTCP_ATTR_SADDR4, issk->inet_saddr)) + goto nla_put_failure; + break; +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + case AF_INET6: { + const struct ipv6_pinfo *np = inet6_sk(ssk); + + if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) + goto nla_put_failure; + break; + } +#endif + default: + WARN_ON_ONCE(1); + goto nla_put_failure; + } + + genlmsg_end(skb, nlh); + mptcp_nl_mcast_send(net, skb, GFP_KERNEL); + return; + +nla_put_failure: + kfree_skb(skb); +} + void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp) { @@ -2197,6 +2251,9 @@ void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, if (mptcp_event_sub_closed(skb, msk, ssk) < 0) goto nla_put_failure; break; + case MPTCP_EVENT_LISTENER_CREATED: + case MPTCP_EVENT_LISTENER_CLOSED: + break; } genlmsg_end(skb, nlh); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b0d387be500a..f6f93957275b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2355,6 +2355,7 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(ssk); inet_csk_listen_stop(ssk); + mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); } __tcp_close(ssk, 0); @@ -3647,6 +3648,8 @@ static int mptcp_listen(struct socket *sock, int backlog) if (!err) mptcp_copy_inaddrs(sock->sk, ssock->sk); + mptcp_event_pm_listener(ssock->sk, MPTCP_EVENT_LISTENER_CREATED); + unlock: release_sock(sock->sk); return err; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8b4379a2cd85..955fb3d88eb3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -839,6 +839,8 @@ void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk, const struct sock *ssk, gfp_t gfp); void mptcp_event_addr_announced(const struct sock *ssk, const struct mptcp_addr_info *info); void mptcp_event_addr_removed(const struct mptcp_sock *msk, u8 id); +void mptcp_event_pm_listener(const struct sock *ssk, + enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, -- cgit From 61e15f871241ee86f217320909005cd022dd844f Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Fri, 2 Dec 2022 11:50:08 +0100 Subject: KVM: Delete all references to removed KVM_SET_MEMORY_REGION ioctl The documentation says that the ioctl has been deprecated, but it has been actually removed and the remaining references are just left overs. Suggested-by: Sean Christopherson Signed-off-by: Javier Martinez Canillas Message-Id: <20221202105011.185147-2-javierm@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 16 ---------------- include/uapi/linux/kvm.h | 12 ------------ tools/include/uapi/linux/kvm.h | 12 ------------ 3 files changed, 40 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 5617bc4f899f..850e187c0a38 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -272,18 +272,6 @@ the VCPU file descriptor can be mmap-ed, including: KVM_CAP_DIRTY_LOG_RING, see section 8.3. -4.6 KVM_SET_MEMORY_REGION -------------------------- - -:Capability: basic -:Architectures: all -:Type: vm ioctl -:Parameters: struct kvm_memory_region (in) -:Returns: 0 on success, -1 on error - -This ioctl is obsolete and has been removed. - - 4.7 KVM_CREATE_VCPU ------------------- @@ -1377,10 +1365,6 @@ the memory region are automatically reflected into the guest. For example, an mmap() that affects the region will be made visible immediately. Another example is madvise(MADV_DROP). -It is recommended to use this API instead of the KVM_SET_MEMORY_REGION ioctl. -The KVM_SET_MEMORY_REGION does not allow fine grained control over memory -allocation and is deprecated. - 4.36 KVM_SET_TSS_ADDR --------------------- diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 64dfe9c07c87..c338ca2c972d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -86,14 +86,6 @@ struct kvm_debug_guest { /* *** End of deprecated interfaces *** */ -/* for KVM_CREATE_MEMORY_REGION */ -struct kvm_memory_region { - __u32 slot; - __u32 flags; - __u64 guest_phys_addr; - __u64 memory_size; /* bytes */ -}; - /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -1442,10 +1434,6 @@ struct kvm_vfio_spapr_tce { __s32 tablefd; }; -/* - * ioctls for VM fds - */ -#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 0d5d4419139a..8899201d5964 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -86,14 +86,6 @@ struct kvm_debug_guest { /* *** End of deprecated interfaces *** */ -/* for KVM_CREATE_MEMORY_REGION */ -struct kvm_memory_region { - __u32 slot; - __u32 flags; - __u64 guest_phys_addr; - __u64 memory_size; /* bytes */ -}; - /* for KVM_SET_USER_MEMORY_REGION */ struct kvm_userspace_memory_region { __u32 slot; @@ -1437,10 +1429,6 @@ struct kvm_vfio_spapr_tce { __s32 tablefd; }; -/* - * ioctls for VM fds - */ -#define KVM_SET_MEMORY_REGION _IOW(KVMIO, 0x40, struct kvm_memory_region) /* * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns * a vcpu fd. -- cgit From 66a9221d73e71199a120ca12ea5bfaac2aa670a3 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Fri, 2 Dec 2022 11:50:09 +0100 Subject: KVM: Delete all references to removed KVM_SET_MEMORY_ALIAS ioctl The documentation says that the ioctl has been deprecated, but it has been actually removed and the remaining references are just left overs. Suggested-by: Sean Christopherson Signed-off-by: Javier Martinez Canillas Message-Id: <20221202105011.185147-3-javierm@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 11 ----------- arch/x86/include/uapi/asm/kvm.h | 8 -------- include/uapi/linux/kvm.h | 2 -- tools/arch/x86/include/uapi/asm/kvm.h | 8 -------- tools/include/uapi/linux/kvm.h | 2 -- 5 files changed, 31 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 850e187c0a38..07e8a42d839a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -356,17 +356,6 @@ see the description of the capability. Note that the Xen shared info page, if configured, shall always be assumed to be dirty. KVM will not explicitly mark it such. -4.9 KVM_SET_MEMORY_ALIAS ------------------------- - -:Capability: basic -:Architectures: x86 -:Type: vm ioctl -:Parameters: struct kvm_memory_alias (in) -:Returns: 0 (success), -1 (error) - -This ioctl is obsolete and has been removed. - 4.10 KVM_RUN ------------ diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index c6df6b16a088..e48deab8901d 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -53,14 +53,6 @@ /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 -struct kvm_memory_alias { - __u32 slot; /* this has a different namespace than memory slots */ - __u32 flags; - __u64 guest_phys_addr; - __u64 memory_size; - __u64 target_phys_addr; -}; - /* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ struct kvm_pic_state { __u8 last_irr; /* edge detection */ diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index c338ca2c972d..ce9183765616 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1440,8 +1440,6 @@ struct kvm_vfio_spapr_tce { */ #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) -/* KVM_SET_MEMORY_ALIAS is obsolete: */ -#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) #define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h index 46de10a809ec..649e50a8f9dd 100644 --- a/tools/arch/x86/include/uapi/asm/kvm.h +++ b/tools/arch/x86/include/uapi/asm/kvm.h @@ -53,14 +53,6 @@ /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 -struct kvm_memory_alias { - __u32 slot; /* this has a different namespace than memory slots */ - __u32 flags; - __u64 guest_phys_addr; - __u64 memory_size; - __u64 target_phys_addr; -}; - /* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */ struct kvm_pic_state { __u8 last_irr; /* edge detection */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 8899201d5964..6ba2928f8f18 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1435,8 +1435,6 @@ struct kvm_vfio_spapr_tce { */ #define KVM_CREATE_VCPU _IO(KVMIO, 0x41) #define KVM_GET_DIRTY_LOG _IOW(KVMIO, 0x42, struct kvm_dirty_log) -/* KVM_SET_MEMORY_ALIAS is obsolete: */ -#define KVM_SET_MEMORY_ALIAS _IOW(KVMIO, 0x43, struct kvm_memory_alias) #define KVM_SET_NR_MMU_PAGES _IO(KVMIO, 0x44) #define KVM_GET_NR_MMU_PAGES _IO(KVMIO, 0x45) #define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46, \ -- cgit From 30ee198ce42d60101620d33f8bc70c3234798365 Mon Sep 17 00:00:00 2001 From: Javier Martinez Canillas Date: Fri, 2 Dec 2022 11:50:10 +0100 Subject: KVM: Reference to kvm_userspace_memory_region in doc and comments There are still references to the removed kvm_memory_region data structure but the doc and comments should mention struct kvm_userspace_memory_region instead, since that is what's used by the ioctl that replaced the old one and this data structure support the same set of flags. Signed-off-by: Javier Martinez Canillas Message-Id: <20221202105011.185147-4-javierm@redhat.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 2 +- include/linux/kvm_host.h | 4 ++-- include/uapi/linux/kvm.h | 6 +++--- tools/include/uapi/linux/kvm.h | 6 +++--- 4 files changed, 9 insertions(+), 9 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 07e8a42d839a..92e14823619a 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1309,7 +1309,7 @@ yet and must be cleared on entry. __u64 userspace_addr; /* start of the userspace allocated memory */ }; - /* for kvm_memory_region::flags */ + /* for kvm_userspace_memory_region::flags */ #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) #define KVM_MEM_READONLY (1UL << 1) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 8f874a964313..a5a82b536774 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -50,8 +50,8 @@ #endif /* - * The bit 16 ~ bit 31 of kvm_memory_region::flags are internally used - * in kvm, other bits are visible for userspace which are defined in + * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally + * used in kvm, other bits are visible for userspace which are defined in * include/linux/kvm_h. */ #define KVM_MEMSLOT_INVALID (1UL << 16) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index ce9183765616..03708ce10bda 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -96,9 +96,9 @@ struct kvm_userspace_memory_region { }; /* - * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace, - * other bits are reserved for kvm internal use which are defined in - * include/linux/kvm_host.h. + * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for + * userspace, other bits are reserved for kvm internal use which are defined + * in include/linux/kvm_host.h. */ #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) #define KVM_MEM_READONLY (1UL << 1) diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 6ba2928f8f18..21d6d29502e4 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -96,9 +96,9 @@ struct kvm_userspace_memory_region { }; /* - * The bit 0 ~ bit 15 of kvm_memory_region::flags are visible for userspace, - * other bits are reserved for kvm internal use which are defined in - * include/linux/kvm_host.h. + * The bit 0 ~ bit 15 of kvm_userspace_memory_region::flags are visible for + * userspace, other bits are reserved for kvm internal use which are defined + *in include/linux/kvm_host.h. */ #define KVM_MEM_LOG_DIRTY_PAGES (1UL << 0) #define KVM_MEM_READONLY (1UL << 1) -- cgit From f40eb99897af665f11858dd7b56edcb62c3f3c67 Mon Sep 17 00:00:00 2001 From: Greg Kroah-Hartman Date: Fri, 2 Dec 2022 19:27:58 +0100 Subject: pktcdvd: remove driver. Way back in 2016 in commit 5a8b187c61e9 ("pktcdvd: mark as unmaintained and deprecated") this driver was marked as "will be removed soon". 5 years seems long enough to have it stick around after that, so finally remove the thing now. Reported-by: Christoph Hellwig Cc: Jens Axboe Cc: Thomas Maier Cc: Peter Osterlund Cc: linux-block@vger.kernel.org Signed-off-by: Greg Kroah-Hartman Link: https://lore.kernel.org/r/20221202182758.1339039-1-gregkh@linuxfoundation.org Signed-off-by: Jens Axboe --- Documentation/ABI/testing/debugfs-pktcdvd | 18 - Documentation/ABI/testing/sysfs-class-pktcdvd | 97 - MAINTAINERS | 7 - drivers/block/Kconfig | 43 - drivers/block/Makefile | 1 - drivers/block/pktcdvd.c | 2944 ------------------------- include/linux/pktcdvd.h | 197 -- include/uapi/linux/pktcdvd.h | 112 - 8 files changed, 3419 deletions(-) delete mode 100644 Documentation/ABI/testing/debugfs-pktcdvd delete mode 100644 Documentation/ABI/testing/sysfs-class-pktcdvd delete mode 100644 drivers/block/pktcdvd.c delete mode 100644 include/linux/pktcdvd.h delete mode 100644 include/uapi/linux/pktcdvd.h (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd deleted file mode 100644 index f6f65a4faea0..000000000000 --- a/Documentation/ABI/testing/debugfs-pktcdvd +++ /dev/null @@ -1,18 +0,0 @@ -What: /sys/kernel/debug/pktcdvd/pktcdvd[0-7] -Date: Oct. 2006 -KernelVersion: 2.6.20 -Contact: Thomas Maier -Description: - -The pktcdvd module (packet writing driver) creates -these files in debugfs: - -/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/ - - ==== ====== ==================================== - info 0444 Lots of driver statistics and infos. - ==== ====== ==================================== - -Example:: - - cat /sys/kernel/debug/pktcdvd/pktcdvd0/info diff --git a/Documentation/ABI/testing/sysfs-class-pktcdvd b/Documentation/ABI/testing/sysfs-class-pktcdvd deleted file mode 100644 index ba1ce626591d..000000000000 --- a/Documentation/ABI/testing/sysfs-class-pktcdvd +++ /dev/null @@ -1,97 +0,0 @@ -sysfs interface ---------------- -The pktcdvd module (packet writing driver) creates the following files in the -sysfs: ( is in the format major:minor) - -What: /sys/class/pktcdvd/add -What: /sys/class/pktcdvd/remove -What: /sys/class/pktcdvd/device_map -Date: Oct. 2006 -KernelVersion: 2.6.20 -Contact: Thomas Maier -Description: - - ========== ============================================== - add (WO) Write a block device id (major:minor) to - create a new pktcdvd device and map it to the - block device. - - remove (WO) Write the pktcdvd device id (major:minor) - to remove the pktcdvd device. - - device_map (RO) Shows the device mapping in format: - pktcdvd[0-7] - ========== ============================================== - - -What: /sys/class/pktcdvd/pktcdvd[0-7]/dev -What: /sys/class/pktcdvd/pktcdvd[0-7]/uevent -Date: Oct. 2006 -KernelVersion: 2.6.20 -Contact: Thomas Maier -Description: - dev: (RO) Device id - - uevent: (WO) To send a uevent - - -What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started -What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished -What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written -What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read -What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather -What: /sys/class/pktcdvd/pktcdvd[0-7]/stat/reset -Date: Oct. 2006 -KernelVersion: 2.6.20 -Contact: Thomas Maier -Description: - packets_started: (RO) Number of started packets. - - packets_finished: (RO) Number of finished packets. - - kb_written: (RO) kBytes written. - - kb_read: (RO) kBytes read. - - kb_read_gather: (RO) kBytes read to fill write packets. - - reset: (WO) Write any value to it to reset - pktcdvd device statistic values, like - bytes read/written. - - -What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size -What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off -What: /sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on -Date: Oct. 2006 -KernelVersion: 2.6.20 -Contact: Thomas Maier -Description: - ============== ================================================ - size (RO) Contains the size of the bio write queue. - - congestion_off (RW) If bio write queue size is below this mark, - accept new bio requests from the block layer. - - congestion_on (RW) If bio write queue size is higher as this - mark, do no longer accept bio write requests - from the block layer and wait till the pktcdvd - device has processed enough bio's so that bio - write queue size is below congestion off mark. - A value of <= 0 disables congestion control. - ============== ================================================ - - -Example: --------- -To use the pktcdvd sysfs interface directly, you can do:: - - # create a new pktcdvd device mapped to /dev/hdc - echo "22:0" >/sys/class/pktcdvd/add - cat /sys/class/pktcdvd/device_map - # assuming device pktcdvd0 was created, look at stat's - cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written - # print the device id of the mapped block device - fgrep pktcdvd0 /sys/class/pktcdvd/device_map - # remove device, using pktcdvd0 device id 253:0 - echo "253:0" >/sys/class/pktcdvd/remove diff --git a/MAINTAINERS b/MAINTAINERS index e04d944005ba..595d59eec7ea 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -16367,13 +16367,6 @@ S: Supported F: Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml F: drivers/input/keyboard/pinephone-keyboard.c -PKTCDVD DRIVER -M: linux-block@vger.kernel.org -S: Orphan -F: drivers/block/pktcdvd.c -F: include/linux/pktcdvd.h -F: include/uapi/linux/pktcdvd.h - PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER M: Tomasz Duszynski S: Maintained diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index db1b4b202646..91de9fc29bbe 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -285,49 +285,6 @@ config BLK_DEV_RAM_SIZE The default value is 4096 kilobytes. Only change this if you know what you are doing. -config CDROM_PKTCDVD - tristate "Packet writing on CD/DVD media (DEPRECATED)" - depends on !UML - depends on SCSI - select CDROM - help - Note: This driver is deprecated and will be removed from the - kernel in the near future! - - If you have a CDROM/DVD drive that supports packet writing, say - Y to include support. It should work with any MMC/Mt Fuji - compliant ATAPI or SCSI drive, which is just about any newer - DVD/CD writer. - - Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs - is possible. - DVD-RW disks must be in restricted overwrite mode. - - See the file - for further information on the use of this driver. - - To compile this driver as a module, choose M here: the - module will be called pktcdvd. - -config CDROM_PKTCDVD_BUFFERS - int "Free buffers for data gathering" - depends on CDROM_PKTCDVD - default "8" - help - This controls the maximum number of active concurrent packets. More - concurrent packets can increase write performance, but also require - more memory. Each concurrent packet will require approximately 64Kb - of non-swappable kernel memory, memory which will be allocated when - a disc is opened for writing. - -config CDROM_PKTCDVD_WCACHE - bool "Enable write caching" - depends on CDROM_PKTCDVD - help - If enabled, write caching will be set for the CD-R/W device. For now - this option is dangerous unless the CD-RW media is known good, as we - don't do deferred write error handling yet. - config ATA_OVER_ETH tristate "ATA over Ethernet support" depends on NET diff --git a/drivers/block/Makefile b/drivers/block/Makefile index 101612cba303..962ee65d8ca3 100644 --- a/drivers/block/Makefile +++ b/drivers/block/Makefile @@ -20,7 +20,6 @@ obj-$(CONFIG_AMIGA_Z2RAM) += z2ram.o obj-$(CONFIG_N64CART) += n64cart.o obj-$(CONFIG_BLK_DEV_RAM) += brd.o obj-$(CONFIG_BLK_DEV_LOOP) += loop.o -obj-$(CONFIG_CDROM_PKTCDVD) += pktcdvd.o obj-$(CONFIG_SUNVDC) += sunvdc.o obj-$(CONFIG_BLK_DEV_NBD) += nbd.o diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c deleted file mode 100644 index 4cea3b08087e..000000000000 --- a/drivers/block/pktcdvd.c +++ /dev/null @@ -1,2944 +0,0 @@ -/* - * Copyright (C) 2000 Jens Axboe - * Copyright (C) 2001-2004 Peter Osterlund - * Copyright (C) 2006 Thomas Maier - * - * May be copied or modified under the terms of the GNU General Public - * License. See linux/COPYING for more information. - * - * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and - * DVD-RAM devices. - * - * Theory of operation: - * - * At the lowest level, there is the standard driver for the CD/DVD device, - * such as drivers/scsi/sr.c. This driver can handle read and write requests, - * but it doesn't know anything about the special restrictions that apply to - * packet writing. One restriction is that write requests must be aligned to - * packet boundaries on the physical media, and the size of a write request - * must be equal to the packet size. Another restriction is that a - * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read - * command, if the previous command was a write. - * - * The purpose of the packet writing driver is to hide these restrictions from - * higher layers, such as file systems, and present a block device that can be - * randomly read and written using 2kB-sized blocks. - * - * The lowest layer in the packet writing driver is the packet I/O scheduler. - * Its data is defined by the struct packet_iosched and includes two bio - * queues with pending read and write requests. These queues are processed - * by the pkt_iosched_process_queue() function. The write requests in this - * queue are already properly aligned and sized. This layer is responsible for - * issuing the flush cache commands and scheduling the I/O in a good order. - * - * The next layer transforms unaligned write requests to aligned writes. This - * transformation requires reading missing pieces of data from the underlying - * block device, assembling the pieces to full packets and queuing them to the - * packet I/O scheduler. - * - * At the top layer there is a custom ->submit_bio function that forwards - * read requests directly to the iosched queue and puts write requests in the - * unaligned write queue. A kernel thread performs the necessary read - * gathering to convert the unaligned writes to aligned writes and then feeds - * them to the packet I/O scheduler. - * - *************************************************************************/ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#define DRIVER_NAME "pktcdvd" - -#define pkt_err(pd, fmt, ...) \ - pr_err("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_notice(pd, fmt, ...) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__) -#define pkt_info(pd, fmt, ...) \ - pr_info("%s: " fmt, pd->name, ##__VA_ARGS__) - -#define pkt_dbg(level, pd, fmt, ...) \ -do { \ - if (level == 2 && PACKET_DEBUG >= 2) \ - pr_notice("%s: %s():" fmt, \ - pd->name, __func__, ##__VA_ARGS__); \ - else if (level == 1 && PACKET_DEBUG >= 1) \ - pr_notice("%s: " fmt, pd->name, ##__VA_ARGS__); \ -} while (0) - -#define MAX_SPEED 0xffff - -static DEFINE_MUTEX(pktcdvd_mutex); -static struct pktcdvd_device *pkt_devs[MAX_WRITERS]; -static struct proc_dir_entry *pkt_proc; -static int pktdev_major; -static int write_congestion_on = PKT_WRITE_CONGESTION_ON; -static int write_congestion_off = PKT_WRITE_CONGESTION_OFF; -static struct mutex ctl_mutex; /* Serialize open/close/setup/teardown */ -static mempool_t psd_pool; -static struct bio_set pkt_bio_set; - -static struct class *class_pktcdvd = NULL; /* /sys/class/pktcdvd */ -static struct dentry *pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */ - -/* forward declaration */ -static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev); -static int pkt_remove_dev(dev_t pkt_dev); -static int pkt_seq_show(struct seq_file *m, void *p); - -static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd) -{ - return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1); -} - -/********************************************************** - * sysfs interface for pktcdvd - * by (C) 2006 Thomas Maier - - /sys/class/pktcdvd/pktcdvd[0-7]/ - stat/reset - stat/packets_started - stat/packets_finished - stat/kb_written - stat/kb_read - stat/kb_read_gather - write_queue/size - write_queue/congestion_off - write_queue/congestion_on - **********************************************************/ - -static ssize_t packets_started_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started); -} -static DEVICE_ATTR_RO(packets_started); - -static ssize_t packets_finished_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended); -} -static DEVICE_ATTR_RO(packets_finished); - -static ssize_t kb_written_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1); -} -static DEVICE_ATTR_RO(kb_written); - -static ssize_t kb_read_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1); -} -static DEVICE_ATTR_RO(kb_read); - -static ssize_t kb_read_gather_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - - return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1); -} -static DEVICE_ATTR_RO(kb_read_gather); - -static ssize_t reset_store(struct device *dev, struct device_attribute *attr, - const char *buf, size_t len) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - - if (len > 0) { - pd->stats.pkt_started = 0; - pd->stats.pkt_ended = 0; - pd->stats.secs_w = 0; - pd->stats.secs_rg = 0; - pd->stats.secs_r = 0; - } - return len; -} -static DEVICE_ATTR_WO(reset); - -static struct attribute *pkt_stat_attrs[] = { - &dev_attr_packets_finished.attr, - &dev_attr_packets_started.attr, - &dev_attr_kb_read.attr, - &dev_attr_kb_written.attr, - &dev_attr_kb_read_gather.attr, - &dev_attr_reset.attr, - NULL, -}; - -static const struct attribute_group pkt_stat_group = { - .name = "stat", - .attrs = pkt_stat_attrs, -}; - -static ssize_t size_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - int n; - - spin_lock(&pd->lock); - n = sysfs_emit(buf, "%d\n", pd->bio_queue_size); - spin_unlock(&pd->lock); - return n; -} -static DEVICE_ATTR_RO(size); - -static void init_write_congestion_marks(int* lo, int* hi) -{ - if (*hi > 0) { - *hi = max(*hi, 500); - *hi = min(*hi, 1000000); - if (*lo <= 0) - *lo = *hi - 100; - else { - *lo = min(*lo, *hi - 100); - *lo = max(*lo, 100); - } - } else { - *hi = -1; - *lo = -1; - } -} - -static ssize_t congestion_off_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - int n; - - spin_lock(&pd->lock); - n = sysfs_emit(buf, "%d\n", pd->write_congestion_off); - spin_unlock(&pd->lock); - return n; -} - -static ssize_t congestion_off_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - int val; - - if (sscanf(buf, "%d", &val) == 1) { - spin_lock(&pd->lock); - pd->write_congestion_off = val; - init_write_congestion_marks(&pd->write_congestion_off, - &pd->write_congestion_on); - spin_unlock(&pd->lock); - } - return len; -} -static DEVICE_ATTR_RW(congestion_off); - -static ssize_t congestion_on_show(struct device *dev, - struct device_attribute *attr, char *buf) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - int n; - - spin_lock(&pd->lock); - n = sysfs_emit(buf, "%d\n", pd->write_congestion_on); - spin_unlock(&pd->lock); - return n; -} - -static ssize_t congestion_on_store(struct device *dev, - struct device_attribute *attr, - const char *buf, size_t len) -{ - struct pktcdvd_device *pd = dev_get_drvdata(dev); - int val; - - if (sscanf(buf, "%d", &val) == 1) { - spin_lock(&pd->lock); - pd->write_congestion_on = val; - init_write_congestion_marks(&pd->write_congestion_off, - &pd->write_congestion_on); - spin_unlock(&pd->lock); - } - return len; -} -static DEVICE_ATTR_RW(congestion_on); - -static struct attribute *pkt_wq_attrs[] = { - &dev_attr_congestion_on.attr, - &dev_attr_congestion_off.attr, - &dev_attr_size.attr, - NULL, -}; - -static const struct attribute_group pkt_wq_group = { - .name = "write_queue", - .attrs = pkt_wq_attrs, -}; - -static const struct attribute_group *pkt_groups[] = { - &pkt_stat_group, - &pkt_wq_group, - NULL, -}; - -static void pkt_sysfs_dev_new(struct pktcdvd_device *pd) -{ - if (class_pktcdvd) { - pd->dev = device_create_with_groups(class_pktcdvd, NULL, - MKDEV(0, 0), pd, pkt_groups, - "%s", pd->name); - if (IS_ERR(pd->dev)) - pd->dev = NULL; - } -} - -static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd) -{ - if (class_pktcdvd) - device_unregister(pd->dev); -} - - -/******************************************************************** - /sys/class/pktcdvd/ - add map block device - remove unmap packet dev - device_map show mappings - *******************************************************************/ - -static void class_pktcdvd_release(struct class *cls) -{ - kfree(cls); -} - -static ssize_t device_map_show(struct class *c, struct class_attribute *attr, - char *data) -{ - int n = 0; - int idx; - mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); - for (idx = 0; idx < MAX_WRITERS; idx++) { - struct pktcdvd_device *pd = pkt_devs[idx]; - if (!pd) - continue; - n += sprintf(data+n, "%s %u:%u %u:%u\n", - pd->name, - MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev), - MAJOR(pd->bdev->bd_dev), - MINOR(pd->bdev->bd_dev)); - } - mutex_unlock(&ctl_mutex); - return n; -} -static CLASS_ATTR_RO(device_map); - -static ssize_t add_store(struct class *c, struct class_attribute *attr, - const char *buf, size_t count) -{ - unsigned int major, minor; - - if (sscanf(buf, "%u:%u", &major, &minor) == 2) { - /* pkt_setup_dev() expects caller to hold reference to self */ - if (!try_module_get(THIS_MODULE)) - return -ENODEV; - - pkt_setup_dev(MKDEV(major, minor), NULL); - - module_put(THIS_MODULE); - - return count; - } - - return -EINVAL; -} -static CLASS_ATTR_WO(add); - -static ssize_t remove_store(struct class *c, struct class_attribute *attr, - const char *buf, size_t count) -{ - unsigned int major, minor; - if (sscanf(buf, "%u:%u", &major, &minor) == 2) { - pkt_remove_dev(MKDEV(major, minor)); - return count; - } - return -EINVAL; -} -static CLASS_ATTR_WO(remove); - -static struct attribute *class_pktcdvd_attrs[] = { - &class_attr_add.attr, - &class_attr_remove.attr, - &class_attr_device_map.attr, - NULL, -}; -ATTRIBUTE_GROUPS(class_pktcdvd); - -static int pkt_sysfs_init(void) -{ - int ret = 0; - - /* - * create control files in sysfs - * /sys/class/pktcdvd/... - */ - class_pktcdvd = kzalloc(sizeof(*class_pktcdvd), GFP_KERNEL); - if (!class_pktcdvd) - return -ENOMEM; - class_pktcdvd->name = DRIVER_NAME; - class_pktcdvd->owner = THIS_MODULE; - class_pktcdvd->class_release = class_pktcdvd_release; - class_pktcdvd->class_groups = class_pktcdvd_groups; - ret = class_register(class_pktcdvd); - if (ret) { - kfree(class_pktcdvd); - class_pktcdvd = NULL; - pr_err("failed to create class pktcdvd\n"); - return ret; - } - return 0; -} - -static void pkt_sysfs_cleanup(void) -{ - if (class_pktcdvd) - class_destroy(class_pktcdvd); - class_pktcdvd = NULL; -} - -/******************************************************************** - entries in debugfs - - /sys/kernel/debug/pktcdvd[0-7]/ - info - - *******************************************************************/ - -static int pkt_debugfs_seq_show(struct seq_file *m, void *p) -{ - return pkt_seq_show(m, p); -} - -static int pkt_debugfs_fops_open(struct inode *inode, struct file *file) -{ - return single_open(file, pkt_debugfs_seq_show, inode->i_private); -} - -static const struct file_operations debug_fops = { - .open = pkt_debugfs_fops_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - -static void pkt_debugfs_dev_new(struct pktcdvd_device *pd) -{ - if (!pkt_debugfs_root) - return; - pd->dfs_d_root = debugfs_create_dir(pd->name, pkt_debugfs_root); - if (!pd->dfs_d_root) - return; - - pd->dfs_f_info = debugfs_create_file("info", 0444, - pd->dfs_d_root, pd, &debug_fops); -} - -static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd) -{ - if (!pkt_debugfs_root) - return; - debugfs_remove(pd->dfs_f_info); - debugfs_remove(pd->dfs_d_root); - pd->dfs_f_info = NULL; - pd->dfs_d_root = NULL; -} - -static void pkt_debugfs_init(void) -{ - pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL); -} - -static void pkt_debugfs_cleanup(void) -{ - debugfs_remove(pkt_debugfs_root); - pkt_debugfs_root = NULL; -} - -/* ----------------------------------------------------------*/ - - -static void pkt_bio_finished(struct pktcdvd_device *pd) -{ - BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0); - if (atomic_dec_and_test(&pd->cdrw.pending_bios)) { - pkt_dbg(2, pd, "queue empty\n"); - atomic_set(&pd->iosched.attention, 1); - wake_up(&pd->wqueue); - } -} - -/* - * Allocate a packet_data struct - */ -static struct packet_data *pkt_alloc_packet_data(int frames) -{ - int i; - struct packet_data *pkt; - - pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL); - if (!pkt) - goto no_pkt; - - pkt->frames = frames; - pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL); - if (!pkt->w_bio) - goto no_bio; - - for (i = 0; i < frames / FRAMES_PER_PAGE; i++) { - pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO); - if (!pkt->pages[i]) - goto no_page; - } - - spin_lock_init(&pkt->lock); - bio_list_init(&pkt->orig_bios); - - for (i = 0; i < frames; i++) { - pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL); - if (!pkt->r_bios[i]) - goto no_rd_bio; - } - - return pkt; - -no_rd_bio: - for (i = 0; i < frames; i++) - kfree(pkt->r_bios[i]); -no_page: - for (i = 0; i < frames / FRAMES_PER_PAGE; i++) - if (pkt->pages[i]) - __free_page(pkt->pages[i]); - kfree(pkt->w_bio); -no_bio: - kfree(pkt); -no_pkt: - return NULL; -} - -/* - * Free a packet_data struct - */ -static void pkt_free_packet_data(struct packet_data *pkt) -{ - int i; - - for (i = 0; i < pkt->frames; i++) - kfree(pkt->r_bios[i]); - for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++) - __free_page(pkt->pages[i]); - kfree(pkt->w_bio); - kfree(pkt); -} - -static void pkt_shrink_pktlist(struct pktcdvd_device *pd) -{ - struct packet_data *pkt, *next; - - BUG_ON(!list_empty(&pd->cdrw.pkt_active_list)); - - list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) { - pkt_free_packet_data(pkt); - } - INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); -} - -static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets) -{ - struct packet_data *pkt; - - BUG_ON(!list_empty(&pd->cdrw.pkt_free_list)); - - while (nr_packets > 0) { - pkt = pkt_alloc_packet_data(pd->settings.size >> 2); - if (!pkt) { - pkt_shrink_pktlist(pd); - return 0; - } - pkt->id = nr_packets; - pkt->pd = pd; - list_add(&pkt->list, &pd->cdrw.pkt_free_list); - nr_packets--; - } - return 1; -} - -static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node) -{ - struct rb_node *n = rb_next(&node->rb_node); - if (!n) - return NULL; - return rb_entry(n, struct pkt_rb_node, rb_node); -} - -static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node) -{ - rb_erase(&node->rb_node, &pd->bio_queue); - mempool_free(node, &pd->rb_pool); - pd->bio_queue_size--; - BUG_ON(pd->bio_queue_size < 0); -} - -/* - * Find the first node in the pd->bio_queue rb tree with a starting sector >= s. - */ -static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s) -{ - struct rb_node *n = pd->bio_queue.rb_node; - struct rb_node *next; - struct pkt_rb_node *tmp; - - if (!n) { - BUG_ON(pd->bio_queue_size > 0); - return NULL; - } - - for (;;) { - tmp = rb_entry(n, struct pkt_rb_node, rb_node); - if (s <= tmp->bio->bi_iter.bi_sector) - next = n->rb_left; - else - next = n->rb_right; - if (!next) - break; - n = next; - } - - if (s > tmp->bio->bi_iter.bi_sector) { - tmp = pkt_rbtree_next(tmp); - if (!tmp) - return NULL; - } - BUG_ON(s > tmp->bio->bi_iter.bi_sector); - return tmp; -} - -/* - * Insert a node into the pd->bio_queue rb tree. - */ -static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node) -{ - struct rb_node **p = &pd->bio_queue.rb_node; - struct rb_node *parent = NULL; - sector_t s = node->bio->bi_iter.bi_sector; - struct pkt_rb_node *tmp; - - while (*p) { - parent = *p; - tmp = rb_entry(parent, struct pkt_rb_node, rb_node); - if (s < tmp->bio->bi_iter.bi_sector) - p = &(*p)->rb_left; - else - p = &(*p)->rb_right; - } - rb_link_node(&node->rb_node, parent, p); - rb_insert_color(&node->rb_node, &pd->bio_queue); - pd->bio_queue_size++; -} - -/* - * Send a packet_command to the underlying block device and - * wait for completion. - */ -static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc) -{ - struct request_queue *q = bdev_get_queue(pd->bdev); - struct scsi_cmnd *scmd; - struct request *rq; - int ret = 0; - - rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ? - REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0); - if (IS_ERR(rq)) - return PTR_ERR(rq); - scmd = blk_mq_rq_to_pdu(rq); - - if (cgc->buflen) { - ret = blk_rq_map_kern(q, rq, cgc->buffer, cgc->buflen, - GFP_NOIO); - if (ret) - goto out; - } - - scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]); - memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE); - - rq->timeout = 60*HZ; - if (cgc->quiet) - rq->rq_flags |= RQF_QUIET; - - blk_execute_rq(rq, false); - if (scmd->result) - ret = -EIO; -out: - blk_mq_free_request(rq); - return ret; -} - -static const char *sense_key_string(__u8 index) -{ - static const char * const info[] = { - "No sense", "Recovered error", "Not ready", - "Medium error", "Hardware error", "Illegal request", - "Unit attention", "Data protect", "Blank check", - }; - - return index < ARRAY_SIZE(info) ? info[index] : "INVALID"; -} - -/* - * A generic sense dump / resolve mechanism should be implemented across - * all ATAPI + SCSI devices. - */ -static void pkt_dump_sense(struct pktcdvd_device *pd, - struct packet_command *cgc) -{ - struct scsi_sense_hdr *sshdr = cgc->sshdr; - - if (sshdr) - pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n", - CDROM_PACKET_SIZE, cgc->cmd, - sshdr->sense_key, sshdr->asc, sshdr->ascq, - sense_key_string(sshdr->sense_key)); - else - pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd); -} - -/* - * flush the drive cache to media - */ -static int pkt_flush_cache(struct pktcdvd_device *pd) -{ - struct packet_command cgc; - - init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); - cgc.cmd[0] = GPCMD_FLUSH_CACHE; - cgc.quiet = 1; - - /* - * the IMMED bit -- we default to not setting it, although that - * would allow a much faster close, this is safer - */ -#if 0 - cgc.cmd[1] = 1 << 1; -#endif - return pkt_generic_packet(pd, &cgc); -} - -/* - * speed is given as the normal factor, e.g. 4 for 4x - */ -static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd, - unsigned write_speed, unsigned read_speed) -{ - struct packet_command cgc; - struct scsi_sense_hdr sshdr; - int ret; - - init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); - cgc.sshdr = &sshdr; - cgc.cmd[0] = GPCMD_SET_SPEED; - cgc.cmd[2] = (read_speed >> 8) & 0xff; - cgc.cmd[3] = read_speed & 0xff; - cgc.cmd[4] = (write_speed >> 8) & 0xff; - cgc.cmd[5] = write_speed & 0xff; - - ret = pkt_generic_packet(pd, &cgc); - if (ret) - pkt_dump_sense(pd, &cgc); - - return ret; -} - -/* - * Queue a bio for processing by the low-level CD device. Must be called - * from process context. - */ -static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio) -{ - spin_lock(&pd->iosched.lock); - if (bio_data_dir(bio) == READ) - bio_list_add(&pd->iosched.read_queue, bio); - else - bio_list_add(&pd->iosched.write_queue, bio); - spin_unlock(&pd->iosched.lock); - - atomic_set(&pd->iosched.attention, 1); - wake_up(&pd->wqueue); -} - -/* - * Process the queued read/write requests. This function handles special - * requirements for CDRW drives: - * - A cache flush command must be inserted before a read request if the - * previous request was a write. - * - Switching between reading and writing is slow, so don't do it more often - * than necessary. - * - Optimize for throughput at the expense of latency. This means that streaming - * writes will never be interrupted by a read, but if the drive has to seek - * before the next write, switch to reading instead if there are any pending - * read requests. - * - Set the read speed according to current usage pattern. When only reading - * from the device, it's best to use the highest possible read speed, but - * when switching often between reading and writing, it's better to have the - * same read and write speeds. - */ -static void pkt_iosched_process_queue(struct pktcdvd_device *pd) -{ - - if (atomic_read(&pd->iosched.attention) == 0) - return; - atomic_set(&pd->iosched.attention, 0); - - for (;;) { - struct bio *bio; - int reads_queued, writes_queued; - - spin_lock(&pd->iosched.lock); - reads_queued = !bio_list_empty(&pd->iosched.read_queue); - writes_queued = !bio_list_empty(&pd->iosched.write_queue); - spin_unlock(&pd->iosched.lock); - - if (!reads_queued && !writes_queued) - break; - - if (pd->iosched.writing) { - int need_write_seek = 1; - spin_lock(&pd->iosched.lock); - bio = bio_list_peek(&pd->iosched.write_queue); - spin_unlock(&pd->iosched.lock); - if (bio && (bio->bi_iter.bi_sector == - pd->iosched.last_write)) - need_write_seek = 0; - if (need_write_seek && reads_queued) { - if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "write, waiting\n"); - break; - } - pkt_flush_cache(pd); - pd->iosched.writing = 0; - } - } else { - if (!reads_queued && writes_queued) { - if (atomic_read(&pd->cdrw.pending_bios) > 0) { - pkt_dbg(2, pd, "read, waiting\n"); - break; - } - pd->iosched.writing = 1; - } - } - - spin_lock(&pd->iosched.lock); - if (pd->iosched.writing) - bio = bio_list_pop(&pd->iosched.write_queue); - else - bio = bio_list_pop(&pd->iosched.read_queue); - spin_unlock(&pd->iosched.lock); - - if (!bio) - continue; - - if (bio_data_dir(bio) == READ) - pd->iosched.successive_reads += - bio->bi_iter.bi_size >> 10; - else { - pd->iosched.successive_reads = 0; - pd->iosched.last_write = bio_end_sector(bio); - } - if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) { - if (pd->read_speed == pd->write_speed) { - pd->read_speed = MAX_SPEED; - pkt_set_speed(pd, pd->write_speed, pd->read_speed); - } - } else { - if (pd->read_speed != pd->write_speed) { - pd->read_speed = pd->write_speed; - pkt_set_speed(pd, pd->write_speed, pd->read_speed); - } - } - - atomic_inc(&pd->cdrw.pending_bios); - submit_bio_noacct(bio); - } -} - -/* - * Special care is needed if the underlying block device has a small - * max_phys_segments value. - */ -static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q) -{ - if ((pd->settings.size << 9) / CD_FRAMESIZE - <= queue_max_segments(q)) { - /* - * The cdrom device can handle one segment/frame - */ - clear_bit(PACKET_MERGE_SEGS, &pd->flags); - return 0; - } else if ((pd->settings.size << 9) / PAGE_SIZE - <= queue_max_segments(q)) { - /* - * We can handle this case at the expense of some extra memory - * copies during write operations - */ - set_bit(PACKET_MERGE_SEGS, &pd->flags); - return 0; - } else { - pkt_err(pd, "cdrom max_phys_segments too small\n"); - return -EIO; - } -} - -static void pkt_end_io_read(struct bio *bio) -{ - struct packet_data *pkt = bio->bi_private; - struct pktcdvd_device *pd = pkt->pd; - BUG_ON(!pd); - - pkt_dbg(2, pd, "bio=%p sec0=%llx sec=%llx err=%d\n", - bio, (unsigned long long)pkt->sector, - (unsigned long long)bio->bi_iter.bi_sector, bio->bi_status); - - if (bio->bi_status) - atomic_inc(&pkt->io_errors); - bio_uninit(bio); - if (atomic_dec_and_test(&pkt->io_wait)) { - atomic_inc(&pkt->run_sm); - wake_up(&pd->wqueue); - } - pkt_bio_finished(pd); -} - -static void pkt_end_io_packet_write(struct bio *bio) -{ - struct packet_data *pkt = bio->bi_private; - struct pktcdvd_device *pd = pkt->pd; - BUG_ON(!pd); - - pkt_dbg(2, pd, "id=%d, err=%d\n", pkt->id, bio->bi_status); - - pd->stats.pkt_ended++; - - bio_uninit(bio); - pkt_bio_finished(pd); - atomic_dec(&pkt->io_wait); - atomic_inc(&pkt->run_sm); - wake_up(&pd->wqueue); -} - -/* - * Schedule reads for the holes in a packet - */ -static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt) -{ - int frames_read = 0; - struct bio *bio; - int f; - char written[PACKET_MAX_SIZE]; - - BUG_ON(bio_list_empty(&pkt->orig_bios)); - - atomic_set(&pkt->io_wait, 0); - atomic_set(&pkt->io_errors, 0); - - /* - * Figure out which frames we need to read before we can write. - */ - memset(written, 0, sizeof(written)); - spin_lock(&pkt->lock); - bio_list_for_each(bio, &pkt->orig_bios) { - int first_frame = (bio->bi_iter.bi_sector - pkt->sector) / - (CD_FRAMESIZE >> 9); - int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE; - pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9); - BUG_ON(first_frame < 0); - BUG_ON(first_frame + num_frames > pkt->frames); - for (f = first_frame; f < first_frame + num_frames; f++) - written[f] = 1; - } - spin_unlock(&pkt->lock); - - if (pkt->cache_valid) { - pkt_dbg(2, pd, "zone %llx cached\n", - (unsigned long long)pkt->sector); - goto out_account; - } - - /* - * Schedule reads for missing parts of the packet. - */ - for (f = 0; f < pkt->frames; f++) { - int p, offset; - - if (written[f]) - continue; - - bio = pkt->r_bios[f]; - bio_init(bio, pd->bdev, bio->bi_inline_vecs, 1, REQ_OP_READ); - bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9); - bio->bi_end_io = pkt_end_io_read; - bio->bi_private = pkt; - - p = (f * CD_FRAMESIZE) / PAGE_SIZE; - offset = (f * CD_FRAMESIZE) % PAGE_SIZE; - pkt_dbg(2, pd, "Adding frame %d, page:%p offs:%d\n", - f, pkt->pages[p], offset); - if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset)) - BUG(); - - atomic_inc(&pkt->io_wait); - pkt_queue_bio(pd, bio); - frames_read++; - } - -out_account: - pkt_dbg(2, pd, "need %d frames for zone %llx\n", - frames_read, (unsigned long long)pkt->sector); - pd->stats.pkt_started++; - pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9); -} - -/* - * Find a packet matching zone, or the least recently used packet if - * there is no match. - */ -static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone) -{ - struct packet_data *pkt; - - list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) { - if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) { - list_del_init(&pkt->list); - if (pkt->sector != zone) - pkt->cache_valid = 0; - return pkt; - } - } - BUG(); - return NULL; -} - -static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt) -{ - if (pkt->cache_valid) { - list_add(&pkt->list, &pd->cdrw.pkt_free_list); - } else { - list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list); - } -} - -static inline void pkt_set_state(struct packet_data *pkt, enum packet_data_state state) -{ -#if PACKET_DEBUG > 1 - static const char *state_name[] = { - "IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED" - }; - enum packet_data_state old_state = pkt->state; - pkt_dbg(2, pd, "pkt %2d : s=%6llx %s -> %s\n", - pkt->id, (unsigned long long)pkt->sector, - state_name[old_state], state_name[state]); -#endif - pkt->state = state; -} - -/* - * Scan the work queue to see if we can start a new packet. - * returns non-zero if any work was done. - */ -static int pkt_handle_queue(struct pktcdvd_device *pd) -{ - struct packet_data *pkt, *p; - struct bio *bio = NULL; - sector_t zone = 0; /* Suppress gcc warning */ - struct pkt_rb_node *node, *first_node; - struct rb_node *n; - - atomic_set(&pd->scan_queue, 0); - - if (list_empty(&pd->cdrw.pkt_free_list)) { - pkt_dbg(2, pd, "no pkt\n"); - return 0; - } - - /* - * Try to find a zone we are not already working on. - */ - spin_lock(&pd->lock); - first_node = pkt_rbtree_find(pd, pd->current_sector); - if (!first_node) { - n = rb_first(&pd->bio_queue); - if (n) - first_node = rb_entry(n, struct pkt_rb_node, rb_node); - } - node = first_node; - while (node) { - bio = node->bio; - zone = get_zone(bio->bi_iter.bi_sector, pd); - list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) { - if (p->sector == zone) { - bio = NULL; - goto try_next_bio; - } - } - break; -try_next_bio: - node = pkt_rbtree_next(node); - if (!node) { - n = rb_first(&pd->bio_queue); - if (n) - node = rb_entry(n, struct pkt_rb_node, rb_node); - } - if (node == first_node) - node = NULL; - } - spin_unlock(&pd->lock); - if (!bio) { - pkt_dbg(2, pd, "no bio\n"); - return 0; - } - - pkt = pkt_get_packet_data(pd, zone); - - pd->current_sector = zone + pd->settings.size; - pkt->sector = zone; - BUG_ON(pkt->frames != pd->settings.size >> 2); - pkt->write_size = 0; - - /* - * Scan work queue for bios in the same zone and link them - * to this packet. - */ - spin_lock(&pd->lock); - pkt_dbg(2, pd, "looking for zone %llx\n", (unsigned long long)zone); - while ((node = pkt_rbtree_find(pd, zone)) != NULL) { - bio = node->bio; - pkt_dbg(2, pd, "found zone=%llx\n", (unsigned long long) - get_zone(bio->bi_iter.bi_sector, pd)); - if (get_zone(bio->bi_iter.bi_sector, pd) != zone) - break; - pkt_rbtree_erase(pd, node); - spin_lock(&pkt->lock); - bio_list_add(&pkt->orig_bios, bio); - pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE; - spin_unlock(&pkt->lock); - } - /* check write congestion marks, and if bio_queue_size is - * below, wake up any waiters - */ - if (pd->congested && - pd->bio_queue_size <= pd->write_congestion_off) { - pd->congested = false; - wake_up_var(&pd->congested); - } - spin_unlock(&pd->lock); - - pkt->sleep_time = max(PACKET_WAIT_TIME, 1); - pkt_set_state(pkt, PACKET_WAITING_STATE); - atomic_set(&pkt->run_sm, 1); - - spin_lock(&pd->cdrw.active_list_lock); - list_add(&pkt->list, &pd->cdrw.pkt_active_list); - spin_unlock(&pd->cdrw.active_list_lock); - - return 1; -} - -/** - * bio_list_copy_data - copy contents of data buffers from one chain of bios to - * another - * @src: source bio list - * @dst: destination bio list - * - * Stops when it reaches the end of either the @src list or @dst list - that is, - * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of - * bios). - */ -static void bio_list_copy_data(struct bio *dst, struct bio *src) -{ - struct bvec_iter src_iter = src->bi_iter; - struct bvec_iter dst_iter = dst->bi_iter; - - while (1) { - if (!src_iter.bi_size) { - src = src->bi_next; - if (!src) - break; - - src_iter = src->bi_iter; - } - - if (!dst_iter.bi_size) { - dst = dst->bi_next; - if (!dst) - break; - - dst_iter = dst->bi_iter; - } - - bio_copy_data_iter(dst, &dst_iter, src, &src_iter); - } -} - -/* - * Assemble a bio to write one packet and queue the bio for processing - * by the underlying block device. - */ -static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt) -{ - int f; - - bio_init(pkt->w_bio, pd->bdev, pkt->w_bio->bi_inline_vecs, pkt->frames, - REQ_OP_WRITE); - pkt->w_bio->bi_iter.bi_sector = pkt->sector; - pkt->w_bio->bi_end_io = pkt_end_io_packet_write; - pkt->w_bio->bi_private = pkt; - - /* XXX: locking? */ - for (f = 0; f < pkt->frames; f++) { - struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE]; - unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE; - - if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset)) - BUG(); - } - pkt_dbg(2, pd, "vcnt=%d\n", pkt->w_bio->bi_vcnt); - - /* - * Fill-in bvec with data from orig_bios. - */ - spin_lock(&pkt->lock); - bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head); - - pkt_set_state(pkt, PACKET_WRITE_WAIT_STATE); - spin_unlock(&pkt->lock); - - pkt_dbg(2, pd, "Writing %d frames for zone %llx\n", - pkt->write_size, (unsigned long long)pkt->sector); - - if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames)) - pkt->cache_valid = 1; - else - pkt->cache_valid = 0; - - /* Start the write request */ - atomic_set(&pkt->io_wait, 1); - pkt_queue_bio(pd, pkt->w_bio); -} - -static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status) -{ - struct bio *bio; - - if (status) - pkt->cache_valid = 0; - - /* Finish all bios corresponding to this packet */ - while ((bio = bio_list_pop(&pkt->orig_bios))) { - bio->bi_status = status; - bio_endio(bio); - } -} - -static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt) -{ - pkt_dbg(2, pd, "pkt %d\n", pkt->id); - - for (;;) { - switch (pkt->state) { - case PACKET_WAITING_STATE: - if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0)) - return; - - pkt->sleep_time = 0; - pkt_gather_data(pd, pkt); - pkt_set_state(pkt, PACKET_READ_WAIT_STATE); - break; - - case PACKET_READ_WAIT_STATE: - if (atomic_read(&pkt->io_wait) > 0) - return; - - if (atomic_read(&pkt->io_errors) > 0) { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); - } else { - pkt_start_write(pd, pkt); - } - break; - - case PACKET_WRITE_WAIT_STATE: - if (atomic_read(&pkt->io_wait) > 0) - return; - - if (!pkt->w_bio->bi_status) { - pkt_set_state(pkt, PACKET_FINISHED_STATE); - } else { - pkt_set_state(pkt, PACKET_RECOVERY_STATE); - } - break; - - case PACKET_RECOVERY_STATE: - pkt_dbg(2, pd, "No recovery possible\n"); - pkt_set_state(pkt, PACKET_FINISHED_STATE); - break; - - case PACKET_FINISHED_STATE: - pkt_finish_packet(pkt, pkt->w_bio->bi_status); - return; - - default: - BUG(); - break; - } - } -} - -static void pkt_handle_packets(struct pktcdvd_device *pd) -{ - struct packet_data *pkt, *next; - - /* - * Run state machine for active packets - */ - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - if (atomic_read(&pkt->run_sm) > 0) { - atomic_set(&pkt->run_sm, 0); - pkt_run_state_machine(pd, pkt); - } - } - - /* - * Move no longer active packets to the free list - */ - spin_lock(&pd->cdrw.active_list_lock); - list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) { - if (pkt->state == PACKET_FINISHED_STATE) { - list_del(&pkt->list); - pkt_put_packet_data(pd, pkt); - pkt_set_state(pkt, PACKET_IDLE_STATE); - atomic_set(&pd->scan_queue, 1); - } - } - spin_unlock(&pd->cdrw.active_list_lock); -} - -static void pkt_count_states(struct pktcdvd_device *pd, int *states) -{ - struct packet_data *pkt; - int i; - - for (i = 0; i < PACKET_NUM_STATES; i++) - states[i] = 0; - - spin_lock(&pd->cdrw.active_list_lock); - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - states[pkt->state]++; - } - spin_unlock(&pd->cdrw.active_list_lock); -} - -/* - * kcdrwd is woken up when writes have been queued for one of our - * registered devices - */ -static int kcdrwd(void *foobar) -{ - struct pktcdvd_device *pd = foobar; - struct packet_data *pkt; - long min_sleep_time, residue; - - set_user_nice(current, MIN_NICE); - set_freezable(); - - for (;;) { - DECLARE_WAITQUEUE(wait, current); - - /* - * Wait until there is something to do - */ - add_wait_queue(&pd->wqueue, &wait); - for (;;) { - set_current_state(TASK_INTERRUPTIBLE); - - /* Check if we need to run pkt_handle_queue */ - if (atomic_read(&pd->scan_queue) > 0) - goto work_to_do; - - /* Check if we need to run the state machine for some packet */ - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - if (atomic_read(&pkt->run_sm) > 0) - goto work_to_do; - } - - /* Check if we need to process the iosched queues */ - if (atomic_read(&pd->iosched.attention) != 0) - goto work_to_do; - - /* Otherwise, go to sleep */ - if (PACKET_DEBUG > 1) { - int states[PACKET_NUM_STATES]; - pkt_count_states(pd, states); - pkt_dbg(2, pd, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], - states[3], states[4], states[5]); - } - - min_sleep_time = MAX_SCHEDULE_TIMEOUT; - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - if (pkt->sleep_time && pkt->sleep_time < min_sleep_time) - min_sleep_time = pkt->sleep_time; - } - - pkt_dbg(2, pd, "sleeping\n"); - residue = schedule_timeout(min_sleep_time); - pkt_dbg(2, pd, "wake up\n"); - - /* make swsusp happy with our thread */ - try_to_freeze(); - - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - if (!pkt->sleep_time) - continue; - pkt->sleep_time -= min_sleep_time - residue; - if (pkt->sleep_time <= 0) { - pkt->sleep_time = 0; - atomic_inc(&pkt->run_sm); - } - } - - if (kthread_should_stop()) - break; - } -work_to_do: - set_current_state(TASK_RUNNING); - remove_wait_queue(&pd->wqueue, &wait); - - if (kthread_should_stop()) - break; - - /* - * if pkt_handle_queue returns true, we can queue - * another request. - */ - while (pkt_handle_queue(pd)) - ; - - /* - * Handle packet state machine - */ - pkt_handle_packets(pd); - - /* - * Handle iosched queues - */ - pkt_iosched_process_queue(pd); - } - - return 0; -} - -static void pkt_print_settings(struct pktcdvd_device *pd) -{ - pkt_info(pd, "%s packets, %u blocks, Mode-%c disc\n", - pd->settings.fp ? "Fixed" : "Variable", - pd->settings.size >> 2, - pd->settings.block_mode == 8 ? '1' : '2'); -} - -static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control) -{ - memset(cgc->cmd, 0, sizeof(cgc->cmd)); - - cgc->cmd[0] = GPCMD_MODE_SENSE_10; - cgc->cmd[2] = page_code | (page_control << 6); - cgc->cmd[7] = cgc->buflen >> 8; - cgc->cmd[8] = cgc->buflen & 0xff; - cgc->data_direction = CGC_DATA_READ; - return pkt_generic_packet(pd, cgc); -} - -static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc) -{ - memset(cgc->cmd, 0, sizeof(cgc->cmd)); - memset(cgc->buffer, 0, 2); - cgc->cmd[0] = GPCMD_MODE_SELECT_10; - cgc->cmd[1] = 0x10; /* PF */ - cgc->cmd[7] = cgc->buflen >> 8; - cgc->cmd[8] = cgc->buflen & 0xff; - cgc->data_direction = CGC_DATA_WRITE; - return pkt_generic_packet(pd, cgc); -} - -static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di) -{ - struct packet_command cgc; - int ret; - - /* set up command and get the disc info */ - init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ); - cgc.cmd[0] = GPCMD_READ_DISC_INFO; - cgc.cmd[8] = cgc.buflen = 2; - cgc.quiet = 1; - - ret = pkt_generic_packet(pd, &cgc); - if (ret) - return ret; - - /* not all drives have the same disc_info length, so requeue - * packet with the length the drive tells us it can supply - */ - cgc.buflen = be16_to_cpu(di->disc_information_length) + - sizeof(di->disc_information_length); - - if (cgc.buflen > sizeof(disc_information)) - cgc.buflen = sizeof(disc_information); - - cgc.cmd[8] = cgc.buflen; - return pkt_generic_packet(pd, &cgc); -} - -static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti) -{ - struct packet_command cgc; - int ret; - - init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ); - cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO; - cgc.cmd[1] = type & 3; - cgc.cmd[4] = (track & 0xff00) >> 8; - cgc.cmd[5] = track & 0xff; - cgc.cmd[8] = 8; - cgc.quiet = 1; - - ret = pkt_generic_packet(pd, &cgc); - if (ret) - return ret; - - cgc.buflen = be16_to_cpu(ti->track_information_length) + - sizeof(ti->track_information_length); - - if (cgc.buflen > sizeof(track_information)) - cgc.buflen = sizeof(track_information); - - cgc.cmd[8] = cgc.buflen; - return pkt_generic_packet(pd, &cgc); -} - -static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd, - long *last_written) -{ - disc_information di; - track_information ti; - __u32 last_track; - int ret; - - ret = pkt_get_disc_info(pd, &di); - if (ret) - return ret; - - last_track = (di.last_track_msb << 8) | di.last_track_lsb; - ret = pkt_get_track_info(pd, last_track, 1, &ti); - if (ret) - return ret; - - /* if this track is blank, try the previous. */ - if (ti.blank) { - last_track--; - ret = pkt_get_track_info(pd, last_track, 1, &ti); - if (ret) - return ret; - } - - /* if last recorded field is valid, return it. */ - if (ti.lra_v) { - *last_written = be32_to_cpu(ti.last_rec_address); - } else { - /* make it up instead */ - *last_written = be32_to_cpu(ti.track_start) + - be32_to_cpu(ti.track_size); - if (ti.free_blocks) - *last_written -= (be32_to_cpu(ti.free_blocks) + 7); - } - return 0; -} - -/* - * write mode select package based on pd->settings - */ -static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd) -{ - struct packet_command cgc; - struct scsi_sense_hdr sshdr; - write_param_page *wp; - char buffer[128]; - int ret, size; - - /* doesn't apply to DVD+RW or DVD-RAM */ - if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12)) - return 0; - - memset(buffer, 0, sizeof(buffer)); - init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ); - cgc.sshdr = &sshdr; - ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0); - if (ret) { - pkt_dump_sense(pd, &cgc); - return ret; - } - - size = 2 + ((buffer[0] << 8) | (buffer[1] & 0xff)); - pd->mode_offset = (buffer[6] << 8) | (buffer[7] & 0xff); - if (size > sizeof(buffer)) - size = sizeof(buffer); - - /* - * now get it all - */ - init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ); - cgc.sshdr = &sshdr; - ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0); - if (ret) { - pkt_dump_sense(pd, &cgc); - return ret; - } - - /* - * write page is offset header + block descriptor length - */ - wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset]; - - wp->fp = pd->settings.fp; - wp->track_mode = pd->settings.track_mode; - wp->write_type = pd->settings.write_type; - wp->data_block_type = pd->settings.block_mode; - - wp->multi_session = 0; - -#ifdef PACKET_USE_LS - wp->link_size = 7; - wp->ls_v = 1; -#endif - - if (wp->data_block_type == PACKET_BLOCK_MODE1) { - wp->session_format = 0; - wp->subhdr2 = 0x20; - } else if (wp->data_block_type == PACKET_BLOCK_MODE2) { - wp->session_format = 0x20; - wp->subhdr2 = 8; -#if 0 - wp->mcn[0] = 0x80; - memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1); -#endif - } else { - /* - * paranoia - */ - pkt_err(pd, "write mode wrong %d\n", wp->data_block_type); - return 1; - } - wp->packet_size = cpu_to_be32(pd->settings.size >> 2); - - cgc.buflen = cgc.cmd[8] = size; - ret = pkt_mode_select(pd, &cgc); - if (ret) { - pkt_dump_sense(pd, &cgc); - return ret; - } - - pkt_print_settings(pd); - return 0; -} - -/* - * 1 -- we can write to this track, 0 -- we can't - */ -static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti) -{ - switch (pd->mmc3_profile) { - case 0x1a: /* DVD+RW */ - case 0x12: /* DVD-RAM */ - /* The track is always writable on DVD+RW/DVD-RAM */ - return 1; - default: - break; - } - - if (!ti->packet || !ti->fp) - return 0; - - /* - * "good" settings as per Mt Fuji. - */ - if (ti->rt == 0 && ti->blank == 0) - return 1; - - if (ti->rt == 0 && ti->blank == 1) - return 1; - - if (ti->rt == 1 && ti->blank == 0) - return 1; - - pkt_err(pd, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet); - return 0; -} - -/* - * 1 -- we can write to this disc, 0 -- we can't - */ -static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di) -{ - switch (pd->mmc3_profile) { - case 0x0a: /* CD-RW */ - case 0xffff: /* MMC3 not supported */ - break; - case 0x1a: /* DVD+RW */ - case 0x13: /* DVD-RW */ - case 0x12: /* DVD-RAM */ - return 1; - default: - pkt_dbg(2, pd, "Wrong disc profile (%x)\n", - pd->mmc3_profile); - return 0; - } - - /* - * for disc type 0xff we should probably reserve a new track. - * but i'm not sure, should we leave this to user apps? probably. - */ - if (di->disc_type == 0xff) { - pkt_notice(pd, "unknown disc - no track?\n"); - return 0; - } - - if (di->disc_type != 0x20 && di->disc_type != 0) { - pkt_err(pd, "wrong disc type (%x)\n", di->disc_type); - return 0; - } - - if (di->erasable == 0) { - pkt_notice(pd, "disc not erasable\n"); - return 0; - } - - if (di->border_status == PACKET_SESSION_RESERVED) { - pkt_err(pd, "can't write to last track (reserved)\n"); - return 0; - } - - return 1; -} - -static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd) -{ - struct packet_command cgc; - unsigned char buf[12]; - disc_information di; - track_information ti; - int ret, track; - - init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ); - cgc.cmd[0] = GPCMD_GET_CONFIGURATION; - cgc.cmd[8] = 8; - ret = pkt_generic_packet(pd, &cgc); - pd->mmc3_profile = ret ? 0xffff : buf[6] << 8 | buf[7]; - - memset(&di, 0, sizeof(disc_information)); - memset(&ti, 0, sizeof(track_information)); - - ret = pkt_get_disc_info(pd, &di); - if (ret) { - pkt_err(pd, "failed get_disc\n"); - return ret; - } - - if (!pkt_writable_disc(pd, &di)) - return -EROFS; - - pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR; - - track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */ - ret = pkt_get_track_info(pd, track, 1, &ti); - if (ret) { - pkt_err(pd, "failed get_track\n"); - return ret; - } - - if (!pkt_writable_track(pd, &ti)) { - pkt_err(pd, "can't write to this track\n"); - return -EROFS; - } - - /* - * we keep packet size in 512 byte units, makes it easier to - * deal with request calculations. - */ - pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2; - if (pd->settings.size == 0) { - pkt_notice(pd, "detected zero packet size!\n"); - return -ENXIO; - } - if (pd->settings.size > PACKET_MAX_SECTORS) { - pkt_err(pd, "packet size is too big\n"); - return -EROFS; - } - pd->settings.fp = ti.fp; - pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1); - - if (ti.nwa_v) { - pd->nwa = be32_to_cpu(ti.next_writable); - set_bit(PACKET_NWA_VALID, &pd->flags); - } - - /* - * in theory we could use lra on -RW media as well and just zero - * blocks that haven't been written yet, but in practice that - * is just a no-go. we'll use that for -R, naturally. - */ - if (ti.lra_v) { - pd->lra = be32_to_cpu(ti.last_rec_address); - set_bit(PACKET_LRA_VALID, &pd->flags); - } else { - pd->lra = 0xffffffff; - set_bit(PACKET_LRA_VALID, &pd->flags); - } - - /* - * fine for now - */ - pd->settings.link_loss = 7; - pd->settings.write_type = 0; /* packet */ - pd->settings.track_mode = ti.track_mode; - - /* - * mode1 or mode2 disc - */ - switch (ti.data_mode) { - case PACKET_MODE1: - pd->settings.block_mode = PACKET_BLOCK_MODE1; - break; - case PACKET_MODE2: - pd->settings.block_mode = PACKET_BLOCK_MODE2; - break; - default: - pkt_err(pd, "unknown data mode\n"); - return -EROFS; - } - return 0; -} - -/* - * enable/disable write caching on drive - */ -static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd, - int set) -{ - struct packet_command cgc; - struct scsi_sense_hdr sshdr; - unsigned char buf[64]; - int ret; - - init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ); - cgc.sshdr = &sshdr; - cgc.buflen = pd->mode_offset + 12; - - /* - * caching mode page might not be there, so quiet this command - */ - cgc.quiet = 1; - - ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0); - if (ret) - return ret; - - buf[pd->mode_offset + 10] |= (!!set << 2); - - cgc.buflen = cgc.cmd[8] = 2 + ((buf[0] << 8) | (buf[1] & 0xff)); - ret = pkt_mode_select(pd, &cgc); - if (ret) { - pkt_err(pd, "write caching control failed\n"); - pkt_dump_sense(pd, &cgc); - } else if (!ret && set) - pkt_notice(pd, "enabled write caching\n"); - return ret; -} - -static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag) -{ - struct packet_command cgc; - - init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); - cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL; - cgc.cmd[4] = lockflag ? 1 : 0; - return pkt_generic_packet(pd, &cgc); -} - -/* - * Returns drive maximum write speed - */ -static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd, - unsigned *write_speed) -{ - struct packet_command cgc; - struct scsi_sense_hdr sshdr; - unsigned char buf[256+18]; - unsigned char *cap_buf; - int ret, offset; - - cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset]; - init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN); - cgc.sshdr = &sshdr; - - ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0); - if (ret) { - cgc.buflen = pd->mode_offset + cap_buf[1] + 2 + - sizeof(struct mode_page_header); - ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0); - if (ret) { - pkt_dump_sense(pd, &cgc); - return ret; - } - } - - offset = 20; /* Obsoleted field, used by older drives */ - if (cap_buf[1] >= 28) - offset = 28; /* Current write speed selected */ - if (cap_buf[1] >= 30) { - /* If the drive reports at least one "Logical Unit Write - * Speed Performance Descriptor Block", use the information - * in the first block. (contains the highest speed) - */ - int num_spdb = (cap_buf[30] << 8) + cap_buf[31]; - if (num_spdb > 0) - offset = 34; - } - - *write_speed = (cap_buf[offset] << 8) | cap_buf[offset + 1]; - return 0; -} - -/* These tables from cdrecord - I don't have orange book */ -/* standard speed CD-RW (1-4x) */ -static char clv_to_speed[16] = { - /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */ - 0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 -}; -/* high speed CD-RW (-10x) */ -static char hs_clv_to_speed[16] = { - /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */ - 0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 -}; -/* ultra high speed CD-RW */ -static char us_clv_to_speed[16] = { - /* 0 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 */ - 0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0 -}; - -/* - * reads the maximum media speed from ATIP - */ -static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd, - unsigned *speed) -{ - struct packet_command cgc; - struct scsi_sense_hdr sshdr; - unsigned char buf[64]; - unsigned int size, st, sp; - int ret; - - init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ); - cgc.sshdr = &sshdr; - cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP; - cgc.cmd[1] = 2; - cgc.cmd[2] = 4; /* READ ATIP */ - cgc.cmd[8] = 2; - ret = pkt_generic_packet(pd, &cgc); - if (ret) { - pkt_dump_sense(pd, &cgc); - return ret; - } - size = ((unsigned int) buf[0]<<8) + buf[1] + 2; - if (size > sizeof(buf)) - size = sizeof(buf); - - init_cdrom_command(&cgc, buf, size, CGC_DATA_READ); - cgc.sshdr = &sshdr; - cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP; - cgc.cmd[1] = 2; - cgc.cmd[2] = 4; - cgc.cmd[8] = size; - ret = pkt_generic_packet(pd, &cgc); - if (ret) { - pkt_dump_sense(pd, &cgc); - return ret; - } - - if (!(buf[6] & 0x40)) { - pkt_notice(pd, "disc type is not CD-RW\n"); - return 1; - } - if (!(buf[6] & 0x4)) { - pkt_notice(pd, "A1 values on media are not valid, maybe not CDRW?\n"); - return 1; - } - - st = (buf[6] >> 3) & 0x7; /* disc sub-type */ - - sp = buf[16] & 0xf; /* max speed from ATIP A1 field */ - - /* Info from cdrecord */ - switch (st) { - case 0: /* standard speed */ - *speed = clv_to_speed[sp]; - break; - case 1: /* high speed */ - *speed = hs_clv_to_speed[sp]; - break; - case 2: /* ultra high speed */ - *speed = us_clv_to_speed[sp]; - break; - default: - pkt_notice(pd, "unknown disc sub-type %d\n", st); - return 1; - } - if (*speed) { - pkt_info(pd, "maximum media speed: %d\n", *speed); - return 0; - } else { - pkt_notice(pd, "unknown speed %d for sub-type %d\n", sp, st); - return 1; - } -} - -static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd) -{ - struct packet_command cgc; - struct scsi_sense_hdr sshdr; - int ret; - - pkt_dbg(2, pd, "Performing OPC\n"); - - init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE); - cgc.sshdr = &sshdr; - cgc.timeout = 60*HZ; - cgc.cmd[0] = GPCMD_SEND_OPC; - cgc.cmd[1] = 1; - ret = pkt_generic_packet(pd, &cgc); - if (ret) - pkt_dump_sense(pd, &cgc); - return ret; -} - -static int pkt_open_write(struct pktcdvd_device *pd) -{ - int ret; - unsigned int write_speed, media_write_speed, read_speed; - - ret = pkt_probe_settings(pd); - if (ret) { - pkt_dbg(2, pd, "failed probe\n"); - return ret; - } - - ret = pkt_set_write_settings(pd); - if (ret) { - pkt_dbg(1, pd, "failed saving write settings\n"); - return -EIO; - } - - pkt_write_caching(pd, USE_WCACHING); - - ret = pkt_get_max_speed(pd, &write_speed); - if (ret) - write_speed = 16 * 177; - switch (pd->mmc3_profile) { - case 0x13: /* DVD-RW */ - case 0x1a: /* DVD+RW */ - case 0x12: /* DVD-RAM */ - pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed); - break; - default: - ret = pkt_media_speed(pd, &media_write_speed); - if (ret) - media_write_speed = 16; - write_speed = min(write_speed, media_write_speed * 177); - pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176); - break; - } - read_speed = write_speed; - - ret = pkt_set_speed(pd, write_speed, read_speed); - if (ret) { - pkt_dbg(1, pd, "couldn't set write speed\n"); - return -EIO; - } - pd->write_speed = write_speed; - pd->read_speed = read_speed; - - ret = pkt_perform_opc(pd); - if (ret) { - pkt_dbg(1, pd, "Optimum Power Calibration failed\n"); - } - - return 0; -} - -/* - * called at open time. - */ -static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) -{ - int ret; - long lba; - struct request_queue *q; - struct block_device *bdev; - - /* - * We need to re-open the cdrom device without O_NONBLOCK to be able - * to read/write from/to it. It is already opened in O_NONBLOCK mode - * so open should not fail. - */ - bdev = blkdev_get_by_dev(pd->bdev->bd_dev, FMODE_READ | FMODE_EXCL, pd); - if (IS_ERR(bdev)) { - ret = PTR_ERR(bdev); - goto out; - } - - ret = pkt_get_last_written(pd, &lba); - if (ret) { - pkt_err(pd, "pkt_get_last_written failed\n"); - goto out_putdev; - } - - set_capacity(pd->disk, lba << 2); - set_capacity_and_notify(pd->bdev->bd_disk, lba << 2); - - q = bdev_get_queue(pd->bdev); - if (write) { - ret = pkt_open_write(pd); - if (ret) - goto out_putdev; - /* - * Some CDRW drives can not handle writes larger than one packet, - * even if the size is a multiple of the packet size. - */ - blk_queue_max_hw_sectors(q, pd->settings.size); - set_bit(PACKET_WRITABLE, &pd->flags); - } else { - pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); - clear_bit(PACKET_WRITABLE, &pd->flags); - } - - ret = pkt_set_segment_merging(pd, q); - if (ret) - goto out_putdev; - - if (write) { - if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) { - pkt_err(pd, "not enough memory for buffers\n"); - ret = -ENOMEM; - goto out_putdev; - } - pkt_info(pd, "%lukB available on disc\n", lba << 1); - } - - return 0; - -out_putdev: - blkdev_put(bdev, FMODE_READ | FMODE_EXCL); -out: - return ret; -} - -/* - * called when the device is closed. makes sure that the device flushes - * the internal cache before we close. - */ -static void pkt_release_dev(struct pktcdvd_device *pd, int flush) -{ - if (flush && pkt_flush_cache(pd)) - pkt_dbg(1, pd, "not flushing cache\n"); - - pkt_lock_door(pd, 0); - - pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); - blkdev_put(pd->bdev, FMODE_READ | FMODE_EXCL); - - pkt_shrink_pktlist(pd); -} - -static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor) -{ - if (dev_minor >= MAX_WRITERS) - return NULL; - - dev_minor = array_index_nospec(dev_minor, MAX_WRITERS); - return pkt_devs[dev_minor]; -} - -static int pkt_open(struct block_device *bdev, fmode_t mode) -{ - struct pktcdvd_device *pd = NULL; - int ret; - - mutex_lock(&pktcdvd_mutex); - mutex_lock(&ctl_mutex); - pd = pkt_find_dev_from_minor(MINOR(bdev->bd_dev)); - if (!pd) { - ret = -ENODEV; - goto out; - } - BUG_ON(pd->refcnt < 0); - - pd->refcnt++; - if (pd->refcnt > 1) { - if ((mode & FMODE_WRITE) && - !test_bit(PACKET_WRITABLE, &pd->flags)) { - ret = -EBUSY; - goto out_dec; - } - } else { - ret = pkt_open_dev(pd, mode & FMODE_WRITE); - if (ret) - goto out_dec; - /* - * needed here as well, since ext2 (among others) may change - * the blocksize at mount time - */ - set_blocksize(bdev, CD_FRAMESIZE); - } - - mutex_unlock(&ctl_mutex); - mutex_unlock(&pktcdvd_mutex); - return 0; - -out_dec: - pd->refcnt--; -out: - mutex_unlock(&ctl_mutex); - mutex_unlock(&pktcdvd_mutex); - return ret; -} - -static void pkt_close(struct gendisk *disk, fmode_t mode) -{ - struct pktcdvd_device *pd = disk->private_data; - - mutex_lock(&pktcdvd_mutex); - mutex_lock(&ctl_mutex); - pd->refcnt--; - BUG_ON(pd->refcnt < 0); - if (pd->refcnt == 0) { - int flush = test_bit(PACKET_WRITABLE, &pd->flags); - pkt_release_dev(pd, flush); - } - mutex_unlock(&ctl_mutex); - mutex_unlock(&pktcdvd_mutex); -} - - -static void pkt_end_io_read_cloned(struct bio *bio) -{ - struct packet_stacked_data *psd = bio->bi_private; - struct pktcdvd_device *pd = psd->pd; - - psd->bio->bi_status = bio->bi_status; - bio_put(bio); - bio_endio(psd->bio); - mempool_free(psd, &psd_pool); - pkt_bio_finished(pd); -} - -static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio) -{ - struct bio *cloned_bio = - bio_alloc_clone(pd->bdev, bio, GFP_NOIO, &pkt_bio_set); - struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO); - - psd->pd = pd; - psd->bio = bio; - cloned_bio->bi_private = psd; - cloned_bio->bi_end_io = pkt_end_io_read_cloned; - pd->stats.secs_r += bio_sectors(bio); - pkt_queue_bio(pd, cloned_bio); -} - -static void pkt_make_request_write(struct request_queue *q, struct bio *bio) -{ - struct pktcdvd_device *pd = q->queuedata; - sector_t zone; - struct packet_data *pkt; - int was_empty, blocked_bio; - struct pkt_rb_node *node; - - zone = get_zone(bio->bi_iter.bi_sector, pd); - - /* - * If we find a matching packet in state WAITING or READ_WAIT, we can - * just append this bio to that packet. - */ - spin_lock(&pd->cdrw.active_list_lock); - blocked_bio = 0; - list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) { - if (pkt->sector == zone) { - spin_lock(&pkt->lock); - if ((pkt->state == PACKET_WAITING_STATE) || - (pkt->state == PACKET_READ_WAIT_STATE)) { - bio_list_add(&pkt->orig_bios, bio); - pkt->write_size += - bio->bi_iter.bi_size / CD_FRAMESIZE; - if ((pkt->write_size >= pkt->frames) && - (pkt->state == PACKET_WAITING_STATE)) { - atomic_inc(&pkt->run_sm); - wake_up(&pd->wqueue); - } - spin_unlock(&pkt->lock); - spin_unlock(&pd->cdrw.active_list_lock); - return; - } else { - blocked_bio = 1; - } - spin_unlock(&pkt->lock); - } - } - spin_unlock(&pd->cdrw.active_list_lock); - - /* - * Test if there is enough room left in the bio work queue - * (queue size >= congestion on mark). - * If not, wait till the work queue size is below the congestion off mark. - */ - spin_lock(&pd->lock); - if (pd->write_congestion_on > 0 - && pd->bio_queue_size >= pd->write_congestion_on) { - struct wait_bit_queue_entry wqe; - - init_wait_var_entry(&wqe, &pd->congested, 0); - for (;;) { - prepare_to_wait_event(__var_waitqueue(&pd->congested), - &wqe.wq_entry, - TASK_UNINTERRUPTIBLE); - if (pd->bio_queue_size <= pd->write_congestion_off) - break; - pd->congested = true; - spin_unlock(&pd->lock); - schedule(); - spin_lock(&pd->lock); - } - } - spin_unlock(&pd->lock); - - /* - * No matching packet found. Store the bio in the work queue. - */ - node = mempool_alloc(&pd->rb_pool, GFP_NOIO); - node->bio = bio; - spin_lock(&pd->lock); - BUG_ON(pd->bio_queue_size < 0); - was_empty = (pd->bio_queue_size == 0); - pkt_rbtree_insert(pd, node); - spin_unlock(&pd->lock); - - /* - * Wake up the worker thread. - */ - atomic_set(&pd->scan_queue, 1); - if (was_empty) { - /* This wake_up is required for correct operation */ - wake_up(&pd->wqueue); - } else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) { - /* - * This wake up is not required for correct operation, - * but improves performance in some cases. - */ - wake_up(&pd->wqueue); - } -} - -static void pkt_submit_bio(struct bio *bio) -{ - struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->queue->queuedata; - struct bio *split; - - bio = bio_split_to_limits(bio); - - pkt_dbg(2, pd, "start = %6llx stop = %6llx\n", - (unsigned long long)bio->bi_iter.bi_sector, - (unsigned long long)bio_end_sector(bio)); - - /* - * Clone READ bios so we can have our own bi_end_io callback. - */ - if (bio_data_dir(bio) == READ) { - pkt_make_request_read(pd, bio); - return; - } - - if (!test_bit(PACKET_WRITABLE, &pd->flags)) { - pkt_notice(pd, "WRITE for ro device (%llu)\n", - (unsigned long long)bio->bi_iter.bi_sector); - goto end_io; - } - - if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) { - pkt_err(pd, "wrong bio size\n"); - goto end_io; - } - - do { - sector_t zone = get_zone(bio->bi_iter.bi_sector, pd); - sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd); - - if (last_zone != zone) { - BUG_ON(last_zone != zone + pd->settings.size); - - split = bio_split(bio, last_zone - - bio->bi_iter.bi_sector, - GFP_NOIO, &pkt_bio_set); - bio_chain(split, bio); - } else { - split = bio; - } - - pkt_make_request_write(bio->bi_bdev->bd_disk->queue, split); - } while (split != bio); - - return; -end_io: - bio_io_error(bio); -} - -static void pkt_init_queue(struct pktcdvd_device *pd) -{ - struct request_queue *q = pd->disk->queue; - - blk_queue_logical_block_size(q, CD_FRAMESIZE); - blk_queue_max_hw_sectors(q, PACKET_MAX_SECTORS); - q->queuedata = pd; -} - -static int pkt_seq_show(struct seq_file *m, void *p) -{ - struct pktcdvd_device *pd = m->private; - char *msg; - int states[PACKET_NUM_STATES]; - - seq_printf(m, "Writer %s mapped to %pg:\n", pd->name, pd->bdev); - - seq_printf(m, "\nSettings:\n"); - seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2); - - if (pd->settings.write_type == 0) - msg = "Packet"; - else - msg = "Unknown"; - seq_printf(m, "\twrite type:\t\t%s\n", msg); - - seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable"); - seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss); - - seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode); - - if (pd->settings.block_mode == PACKET_BLOCK_MODE1) - msg = "Mode 1"; - else if (pd->settings.block_mode == PACKET_BLOCK_MODE2) - msg = "Mode 2"; - else - msg = "Unknown"; - seq_printf(m, "\tblock mode:\t\t%s\n", msg); - - seq_printf(m, "\nStatistics:\n"); - seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started); - seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended); - seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1); - seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1); - seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1); - - seq_printf(m, "\nMisc:\n"); - seq_printf(m, "\treference count:\t%d\n", pd->refcnt); - seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags); - seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed); - seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed); - seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset); - seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset); - - seq_printf(m, "\nQueue state:\n"); - seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size); - seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios)); - seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", (unsigned long long)pd->current_sector); - - pkt_count_states(pd, states); - seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n", - states[0], states[1], states[2], states[3], states[4], states[5]); - - seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n", - pd->write_congestion_off, - pd->write_congestion_on); - return 0; -} - -static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev) -{ - int i; - struct block_device *bdev; - struct scsi_device *sdev; - - if (pd->pkt_dev == dev) { - pkt_err(pd, "recursive setup not allowed\n"); - return -EBUSY; - } - for (i = 0; i < MAX_WRITERS; i++) { - struct pktcdvd_device *pd2 = pkt_devs[i]; - if (!pd2) - continue; - if (pd2->bdev->bd_dev == dev) { - pkt_err(pd, "%pg already setup\n", pd2->bdev); - return -EBUSY; - } - if (pd2->pkt_dev == dev) { - pkt_err(pd, "can't chain pktcdvd devices\n"); - return -EBUSY; - } - } - - bdev = blkdev_get_by_dev(dev, FMODE_READ | FMODE_NDELAY, NULL); - if (IS_ERR(bdev)) - return PTR_ERR(bdev); - sdev = scsi_device_from_queue(bdev->bd_disk->queue); - if (!sdev) { - blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); - return -EINVAL; - } - put_device(&sdev->sdev_gendev); - - /* This is safe, since we have a reference from open(). */ - __module_get(THIS_MODULE); - - pd->bdev = bdev; - set_blocksize(bdev, CD_FRAMESIZE); - - pkt_init_queue(pd); - - atomic_set(&pd->cdrw.pending_bios, 0); - pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->name); - if (IS_ERR(pd->cdrw.thread)) { - pkt_err(pd, "can't start kernel thread\n"); - goto out_mem; - } - - proc_create_single_data(pd->name, 0, pkt_proc, pkt_seq_show, pd); - pkt_dbg(1, pd, "writer mapped to %pg\n", bdev); - return 0; - -out_mem: - blkdev_put(bdev, FMODE_READ | FMODE_NDELAY); - /* This is safe: open() is still holding a reference. */ - module_put(THIS_MODULE); - return -ENOMEM; -} - -static int pkt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) -{ - struct pktcdvd_device *pd = bdev->bd_disk->private_data; - int ret; - - pkt_dbg(2, pd, "cmd %x, dev %d:%d\n", - cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev)); - - mutex_lock(&pktcdvd_mutex); - switch (cmd) { - case CDROMEJECT: - /* - * The door gets locked when the device is opened, so we - * have to unlock it or else the eject command fails. - */ - if (pd->refcnt == 1) - pkt_lock_door(pd, 0); - fallthrough; - /* - * forward selected CDROM ioctls to CD-ROM, for UDF - */ - case CDROMMULTISESSION: - case CDROMREADTOCENTRY: - case CDROM_LAST_WRITTEN: - case CDROM_SEND_PACKET: - case SCSI_IOCTL_SEND_COMMAND: - if (!bdev->bd_disk->fops->ioctl) - ret = -ENOTTY; - else - ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg); - break; - default: - pkt_dbg(2, pd, "Unknown ioctl (%x)\n", cmd); - ret = -ENOTTY; - } - mutex_unlock(&pktcdvd_mutex); - - return ret; -} - -static unsigned int pkt_check_events(struct gendisk *disk, - unsigned int clearing) -{ - struct pktcdvd_device *pd = disk->private_data; - struct gendisk *attached_disk; - - if (!pd) - return 0; - if (!pd->bdev) - return 0; - attached_disk = pd->bdev->bd_disk; - if (!attached_disk || !attached_disk->fops->check_events) - return 0; - return attached_disk->fops->check_events(attached_disk, clearing); -} - -static char *pkt_devnode(struct gendisk *disk, umode_t *mode) -{ - return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name); -} - -static const struct block_device_operations pktcdvd_ops = { - .owner = THIS_MODULE, - .submit_bio = pkt_submit_bio, - .open = pkt_open, - .release = pkt_close, - .ioctl = pkt_ioctl, - .compat_ioctl = blkdev_compat_ptr_ioctl, - .check_events = pkt_check_events, - .devnode = pkt_devnode, -}; - -/* - * Set up mapping from pktcdvd device to CD-ROM device. - */ -static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev) -{ - int idx; - int ret = -ENOMEM; - struct pktcdvd_device *pd; - struct gendisk *disk; - - mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); - - for (idx = 0; idx < MAX_WRITERS; idx++) - if (!pkt_devs[idx]) - break; - if (idx == MAX_WRITERS) { - pr_err("max %d writers supported\n", MAX_WRITERS); - ret = -EBUSY; - goto out_mutex; - } - - pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL); - if (!pd) - goto out_mutex; - - ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE, - sizeof(struct pkt_rb_node)); - if (ret) - goto out_mem; - - INIT_LIST_HEAD(&pd->cdrw.pkt_free_list); - INIT_LIST_HEAD(&pd->cdrw.pkt_active_list); - spin_lock_init(&pd->cdrw.active_list_lock); - - spin_lock_init(&pd->lock); - spin_lock_init(&pd->iosched.lock); - bio_list_init(&pd->iosched.read_queue); - bio_list_init(&pd->iosched.write_queue); - sprintf(pd->name, DRIVER_NAME"%d", idx); - init_waitqueue_head(&pd->wqueue); - pd->bio_queue = RB_ROOT; - - pd->write_congestion_on = write_congestion_on; - pd->write_congestion_off = write_congestion_off; - - ret = -ENOMEM; - disk = blk_alloc_disk(NUMA_NO_NODE); - if (!disk) - goto out_mem; - pd->disk = disk; - disk->major = pktdev_major; - disk->first_minor = idx; - disk->minors = 1; - disk->fops = &pktcdvd_ops; - disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART; - strcpy(disk->disk_name, pd->name); - disk->private_data = pd; - - pd->pkt_dev = MKDEV(pktdev_major, idx); - ret = pkt_new_dev(pd, dev); - if (ret) - goto out_mem2; - - /* inherit events of the host device */ - disk->events = pd->bdev->bd_disk->events; - - ret = add_disk(disk); - if (ret) - goto out_mem2; - - pkt_sysfs_dev_new(pd); - pkt_debugfs_dev_new(pd); - - pkt_devs[idx] = pd; - if (pkt_dev) - *pkt_dev = pd->pkt_dev; - - mutex_unlock(&ctl_mutex); - return 0; - -out_mem2: - put_disk(disk); -out_mem: - mempool_exit(&pd->rb_pool); - kfree(pd); -out_mutex: - mutex_unlock(&ctl_mutex); - pr_err("setup of pktcdvd device failed\n"); - return ret; -} - -/* - * Tear down mapping from pktcdvd device to CD-ROM device. - */ -static int pkt_remove_dev(dev_t pkt_dev) -{ - struct pktcdvd_device *pd; - int idx; - int ret = 0; - - mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); - - for (idx = 0; idx < MAX_WRITERS; idx++) { - pd = pkt_devs[idx]; - if (pd && (pd->pkt_dev == pkt_dev)) - break; - } - if (idx == MAX_WRITERS) { - pr_debug("dev not setup\n"); - ret = -ENXIO; - goto out; - } - - if (pd->refcnt > 0) { - ret = -EBUSY; - goto out; - } - if (!IS_ERR(pd->cdrw.thread)) - kthread_stop(pd->cdrw.thread); - - pkt_devs[idx] = NULL; - - pkt_debugfs_dev_remove(pd); - pkt_sysfs_dev_remove(pd); - - blkdev_put(pd->bdev, FMODE_READ | FMODE_NDELAY); - - remove_proc_entry(pd->name, pkt_proc); - pkt_dbg(1, pd, "writer unmapped\n"); - - del_gendisk(pd->disk); - put_disk(pd->disk); - - mempool_exit(&pd->rb_pool); - kfree(pd); - - /* This is safe: open() is still holding a reference. */ - module_put(THIS_MODULE); - -out: - mutex_unlock(&ctl_mutex); - return ret; -} - -static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd) -{ - struct pktcdvd_device *pd; - - mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING); - - pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index); - if (pd) { - ctrl_cmd->dev = new_encode_dev(pd->bdev->bd_dev); - ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev); - } else { - ctrl_cmd->dev = 0; - ctrl_cmd->pkt_dev = 0; - } - ctrl_cmd->num_devices = MAX_WRITERS; - - mutex_unlock(&ctl_mutex); -} - -static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - void __user *argp = (void __user *)arg; - struct pkt_ctrl_command ctrl_cmd; - int ret = 0; - dev_t pkt_dev = 0; - - if (cmd != PACKET_CTRL_CMD) - return -ENOTTY; - - if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command))) - return -EFAULT; - - switch (ctrl_cmd.command) { - case PKT_CTRL_CMD_SETUP: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev); - ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev); - break; - case PKT_CTRL_CMD_TEARDOWN: - if (!capable(CAP_SYS_ADMIN)) - return -EPERM; - ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev)); - break; - case PKT_CTRL_CMD_STATUS: - pkt_get_status(&ctrl_cmd); - break; - default: - return -ENOTTY; - } - - if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command))) - return -EFAULT; - return ret; -} - -#ifdef CONFIG_COMPAT -static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg) -{ - return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); -} -#endif - -static const struct file_operations pkt_ctl_fops = { - .open = nonseekable_open, - .unlocked_ioctl = pkt_ctl_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = pkt_ctl_compat_ioctl, -#endif - .owner = THIS_MODULE, - .llseek = no_llseek, -}; - -static struct miscdevice pkt_misc = { - .minor = MISC_DYNAMIC_MINOR, - .name = DRIVER_NAME, - .nodename = "pktcdvd/control", - .fops = &pkt_ctl_fops -}; - -static int __init pkt_init(void) -{ - int ret; - - mutex_init(&ctl_mutex); - - ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE, - sizeof(struct packet_stacked_data)); - if (ret) - return ret; - ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0); - if (ret) { - mempool_exit(&psd_pool); - return ret; - } - - ret = register_blkdev(pktdev_major, DRIVER_NAME); - if (ret < 0) { - pr_err("unable to register block device\n"); - goto out2; - } - if (!pktdev_major) - pktdev_major = ret; - - ret = pkt_sysfs_init(); - if (ret) - goto out; - - pkt_debugfs_init(); - - ret = misc_register(&pkt_misc); - if (ret) { - pr_err("unable to register misc device\n"); - goto out_misc; - } - - pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL); - - return 0; - -out_misc: - pkt_debugfs_cleanup(); - pkt_sysfs_cleanup(); -out: - unregister_blkdev(pktdev_major, DRIVER_NAME); -out2: - mempool_exit(&psd_pool); - bioset_exit(&pkt_bio_set); - return ret; -} - -static void __exit pkt_exit(void) -{ - remove_proc_entry("driver/"DRIVER_NAME, NULL); - misc_deregister(&pkt_misc); - - pkt_debugfs_cleanup(); - pkt_sysfs_cleanup(); - - unregister_blkdev(pktdev_major, DRIVER_NAME); - mempool_exit(&psd_pool); - bioset_exit(&pkt_bio_set); -} - -MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives"); -MODULE_AUTHOR("Jens Axboe "); -MODULE_LICENSE("GPL"); - -module_init(pkt_init); -module_exit(pkt_exit); diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h deleted file mode 100644 index f9c5ac80d59b..000000000000 --- a/include/linux/pktcdvd.h +++ /dev/null @@ -1,197 +0,0 @@ -/* - * Copyright (C) 2000 Jens Axboe - * Copyright (C) 2001-2004 Peter Osterlund - * - * May be copied or modified under the terms of the GNU General Public - * License. See linux/COPYING for more information. - * - * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and - * DVD-RW devices. - * - */ -#ifndef __PKTCDVD_H -#define __PKTCDVD_H - -#include -#include -#include -#include -#include -#include -#include - -/* default bio write queue congestion marks */ -#define PKT_WRITE_CONGESTION_ON 10000 -#define PKT_WRITE_CONGESTION_OFF 9000 - - -struct packet_settings -{ - __u32 size; /* packet size in (512 byte) sectors */ - __u8 fp; /* fixed packets */ - __u8 link_loss; /* the rest is specified - * as per Mt Fuji */ - __u8 write_type; - __u8 track_mode; - __u8 block_mode; -}; - -/* - * Very crude stats for now - */ -struct packet_stats -{ - unsigned long pkt_started; - unsigned long pkt_ended; - unsigned long secs_w; - unsigned long secs_rg; - unsigned long secs_r; -}; - -struct packet_cdrw -{ - struct list_head pkt_free_list; - struct list_head pkt_active_list; - spinlock_t active_list_lock; /* Serialize access to pkt_active_list */ - struct task_struct *thread; - atomic_t pending_bios; -}; - -/* - * Switch to high speed reading after reading this many kilobytes - * with no interspersed writes. - */ -#define HI_SPEED_SWITCH 512 - -struct packet_iosched -{ - atomic_t attention; /* Set to non-zero when queue processing is needed */ - int writing; /* Non-zero when writing, zero when reading */ - spinlock_t lock; /* Protecting read/write queue manipulations */ - struct bio_list read_queue; - struct bio_list write_queue; - sector_t last_write; /* The sector where the last write ended */ - int successive_reads; -}; - -/* - * 32 buffers of 2048 bytes - */ -#if (PAGE_SIZE % CD_FRAMESIZE) != 0 -#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE" -#endif -#define PACKET_MAX_SIZE 128 -#define FRAMES_PER_PAGE (PAGE_SIZE / CD_FRAMESIZE) -#define PACKET_MAX_SECTORS (PACKET_MAX_SIZE * CD_FRAMESIZE >> 9) - -enum packet_data_state { - PACKET_IDLE_STATE, /* Not used at the moment */ - PACKET_WAITING_STATE, /* Waiting for more bios to arrive, so */ - /* we don't have to do as much */ - /* data gathering */ - PACKET_READ_WAIT_STATE, /* Waiting for reads to fill in holes */ - PACKET_WRITE_WAIT_STATE, /* Waiting for the write to complete */ - PACKET_RECOVERY_STATE, /* Recover after read/write errors */ - PACKET_FINISHED_STATE, /* After write has finished */ - - PACKET_NUM_STATES /* Number of possible states */ -}; - -/* - * Information needed for writing a single packet - */ -struct pktcdvd_device; - -struct packet_data -{ - struct list_head list; - - spinlock_t lock; /* Lock protecting state transitions and */ - /* orig_bios list */ - - struct bio_list orig_bios; /* Original bios passed to pkt_make_request */ - /* that will be handled by this packet */ - int write_size; /* Total size of all bios in the orig_bios */ - /* list, measured in number of frames */ - - struct bio *w_bio; /* The bio we will send to the real CD */ - /* device once we have all data for the */ - /* packet we are going to write */ - sector_t sector; /* First sector in this packet */ - int frames; /* Number of frames in this packet */ - - enum packet_data_state state; /* Current state */ - atomic_t run_sm; /* Incremented whenever the state */ - /* machine needs to be run */ - long sleep_time; /* Set this to non-zero to make the state */ - /* machine run after this many jiffies. */ - - atomic_t io_wait; /* Number of pending IO operations */ - atomic_t io_errors; /* Number of read/write errors during IO */ - - struct bio *r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */ - struct page *pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE]; - - int cache_valid; /* If non-zero, the data for the zone defined */ - /* by the sector variable is completely cached */ - /* in the pages[] vector. */ - - int id; /* ID number for debugging */ - struct pktcdvd_device *pd; -}; - -struct pkt_rb_node { - struct rb_node rb_node; - struct bio *bio; -}; - -struct packet_stacked_data -{ - struct bio *bio; /* Original read request bio */ - struct pktcdvd_device *pd; -}; -#define PSD_POOL_SIZE 64 - -struct pktcdvd_device -{ - struct block_device *bdev; /* dev attached */ - dev_t pkt_dev; /* our dev */ - char name[20]; - struct packet_settings settings; - struct packet_stats stats; - int refcnt; /* Open count */ - int write_speed; /* current write speed, kB/s */ - int read_speed; /* current read speed, kB/s */ - unsigned long offset; /* start offset */ - __u8 mode_offset; /* 0 / 8 */ - __u8 type; - unsigned long flags; - __u16 mmc3_profile; - __u32 nwa; /* next writable address */ - __u32 lra; /* last recorded address */ - struct packet_cdrw cdrw; - wait_queue_head_t wqueue; - - spinlock_t lock; /* Serialize access to bio_queue */ - struct rb_root bio_queue; /* Work queue of bios we need to handle */ - int bio_queue_size; /* Number of nodes in bio_queue */ - bool congested; /* Someone is waiting for bio_queue_size - * to drop. */ - sector_t current_sector; /* Keep track of where the elevator is */ - atomic_t scan_queue; /* Set to non-zero when pkt_handle_queue */ - /* needs to be run. */ - mempool_t rb_pool; /* mempool for pkt_rb_node allocations */ - - struct packet_iosched iosched; - struct gendisk *disk; - - int write_congestion_off; - int write_congestion_on; - - struct device *dev; /* sysfs pktcdvd[0-7] dev */ - - struct dentry *dfs_d_root; /* debugfs: devname directory */ - struct dentry *dfs_f_info; /* debugfs: info file */ -}; - -#endif /* __PKTCDVD_H */ diff --git a/include/uapi/linux/pktcdvd.h b/include/uapi/linux/pktcdvd.h deleted file mode 100644 index 9cbb55d21c94..000000000000 --- a/include/uapi/linux/pktcdvd.h +++ /dev/null @@ -1,112 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * Copyright (C) 2000 Jens Axboe - * Copyright (C) 2001-2004 Peter Osterlund - * - * May be copied or modified under the terms of the GNU General Public - * License. See linux/COPYING for more information. - * - * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and - * DVD-RW devices. - * - */ -#ifndef _UAPI__PKTCDVD_H -#define _UAPI__PKTCDVD_H - -#include - -/* - * 1 for normal debug messages, 2 is very verbose. 0 to turn it off. - */ -#define PACKET_DEBUG 1 - -#define MAX_WRITERS 8 - -#define PKT_RB_POOL_SIZE 512 - -/* - * How long we should hold a non-full packet before starting data gathering. - */ -#define PACKET_WAIT_TIME (HZ * 5 / 1000) - -/* - * use drive write caching -- we need deferred error handling to be - * able to successfully recover with this option (drive will return good - * status as soon as the cdb is validated). - */ -#if defined(CONFIG_CDROM_PKTCDVD_WCACHE) -#define USE_WCACHING 1 -#else -#define USE_WCACHING 0 -#endif - -/* - * No user-servicable parts beyond this point -> - */ - -/* - * device types - */ -#define PACKET_CDR 1 -#define PACKET_CDRW 2 -#define PACKET_DVDR 3 -#define PACKET_DVDRW 4 - -/* - * flags - */ -#define PACKET_WRITABLE 1 /* pd is writable */ -#define PACKET_NWA_VALID 2 /* next writable address valid */ -#define PACKET_LRA_VALID 3 /* last recorded address valid */ -#define PACKET_MERGE_SEGS 4 /* perform segment merging to keep */ - /* underlying cdrom device happy */ - -/* - * Disc status -- from READ_DISC_INFO - */ -#define PACKET_DISC_EMPTY 0 -#define PACKET_DISC_INCOMPLETE 1 -#define PACKET_DISC_COMPLETE 2 -#define PACKET_DISC_OTHER 3 - -/* - * write type, and corresponding data block type - */ -#define PACKET_MODE1 1 -#define PACKET_MODE2 2 -#define PACKET_BLOCK_MODE1 8 -#define PACKET_BLOCK_MODE2 10 - -/* - * Last session/border status - */ -#define PACKET_SESSION_EMPTY 0 -#define PACKET_SESSION_INCOMPLETE 1 -#define PACKET_SESSION_RESERVED 2 -#define PACKET_SESSION_COMPLETE 3 - -#define PACKET_MCN "4a656e734178626f65323030300000" - -#undef PACKET_USE_LS - -#define PKT_CTRL_CMD_SETUP 0 -#define PKT_CTRL_CMD_TEARDOWN 1 -#define PKT_CTRL_CMD_STATUS 2 - -struct pkt_ctrl_command { - __u32 command; /* in: Setup, teardown, status */ - __u32 dev_index; /* in/out: Device index */ - __u32 dev; /* in/out: Device nr for cdrw device */ - __u32 pkt_dev; /* in/out: Device nr for packet device */ - __u32 num_devices; /* out: Largest device index + 1 */ - __u32 padding; /* Not used */ -}; - -/* - * packet ioctls - */ -#define PACKET_IOCTL_MAGIC ('X') -#define PACKET_CTRL_CMD _IOWR(PACKET_IOCTL_MAGIC, 1, struct pkt_ctrl_command) - - -#endif /* _UAPI__PKTCDVD_H */ -- cgit From d14f28b8c1de668bab863bf5892a49c824cb110d Mon Sep 17 00:00:00 2001 From: Leon Romanovsky Date: Fri, 2 Dec 2022 20:41:27 +0200 Subject: xfrm: add new packet offload flag In the next patches, the xfrm core code will be extended to support new type of offload - packet offload. In that mode, both policy and state should be specially configured in order to perform whole offloaded data path. Full offload takes care of encryption, decryption, encapsulation and other operations with headers. As this mode is new for XFRM policy flow, we can "start fresh" with flag bits and release first and second bit for future use. Reviewed-by: Raed Salem Signed-off-by: Leon Romanovsky Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 7 +++++++ include/uapi/linux/xfrm.h | 6 ++++++ net/xfrm/xfrm_device.c | 3 +++ net/xfrm/xfrm_user.c | 2 ++ 4 files changed, 18 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index e0cc6791c001..b39d24fa2ef0 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -131,12 +131,19 @@ enum { XFRM_DEV_OFFLOAD_OUT, }; +enum { + XFRM_DEV_OFFLOAD_UNSPECIFIED, + XFRM_DEV_OFFLOAD_CRYPTO, + XFRM_DEV_OFFLOAD_PACKET, +}; + struct xfrm_dev_offload { struct net_device *dev; netdevice_tracker dev_tracker; struct net_device *real_dev; unsigned long offload_handle; u8 dir : 2; + u8 type : 2; }; struct xfrm_mode { diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 4f84ea7ee14c..23543c33fee8 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -519,6 +519,12 @@ struct xfrm_user_offload { */ #define XFRM_OFFLOAD_IPV6 1 #define XFRM_OFFLOAD_INBOUND 2 +/* Two bits above are relevant for state path only, while + * offload is used for both policy and state flows. + * + * In policy offload mode, they are free and can be safely reused. + */ +#define XFRM_OFFLOAD_PACKET 4 struct xfrm_userpolicy_default { #define XFRM_USERPOLICY_UNSPEC 0 diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 21269e8f2db4..3b0c1ca8d4bb 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -291,12 +291,15 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x, else xso->dir = XFRM_DEV_OFFLOAD_OUT; + xso->type = XFRM_DEV_OFFLOAD_CRYPTO; + err = dev->xfrmdev_ops->xdo_dev_state_add(x); if (err) { xso->dev = NULL; xso->dir = 0; xso->real_dev = NULL; netdev_put(dev, &xso->dev_tracker); + xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; if (err != -EOPNOTSUPP) { NL_SET_ERR_MSG(extack, "Device failed to offload this state"); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 0eb4696661c8..c3b8c1532718 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -956,6 +956,8 @@ static int copy_user_offload(struct xfrm_dev_offload *xso, struct sk_buff *skb) xuo->ifindex = xso->dev->ifindex; if (xso->dir == XFRM_DEV_OFFLOAD_IN) xuo->flags = XFRM_OFFLOAD_INBOUND; + if (xso->type == XFRM_DEV_OFFLOAD_PACKET) + xuo->flags |= XFRM_OFFLOAD_PACKET; return 0; } -- cgit From 4300c58f809079951c87d84e5f11a2d265e3c9e7 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 14 Sep 2022 11:06:28 -0400 Subject: btrfs: move btrfs on-disk definitions out of ctree.h The bulk of our on-disk definitions exist in btrfs_tree.h, which user space can use. Keep things consistent and move the rest of the on disk definitions out of ctree.h into btrfs_tree.h. Note I did have to update all u8's to __u8, but otherwise this is a strict copy and paste. Most of the definitions are mainly for internal use and are not guaranteed stable public API and may change as we need. Compilation failures by user applications can happen. Reviewed-by: Qu Wenruo Signed-off-by: Josef Bacik Reviewed-by: David Sterba [ reformat comments, style fixups ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 215 +--------------------------------------- include/uapi/linux/btrfs_tree.h | 215 ++++++++++++++++++++++++++++++++++++++++ 2 files changed, 216 insertions(+), 214 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7760cc07288e..7a80f9380146 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -55,8 +55,6 @@ struct btrfs_balance_control; struct btrfs_delayed_root; struct reloc_control; -#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */ - /* * Maximum number of mirrors that can be available for all profiles counting * the target device of dev-replace as one. During an active device replace @@ -68,8 +66,6 @@ struct reloc_control; */ #define BTRFS_MAX_MIRRORS (4 + 1) -#define BTRFS_MAX_LEVEL 8 - #define BTRFS_OLDEST_GENERATION 0ULL /* @@ -138,81 +134,9 @@ enum { BTRFS_FS_STATE_COUNT }; -#define BTRFS_BACKREF_REV_MAX 256 -#define BTRFS_BACKREF_REV_SHIFT 56 -#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \ - BTRFS_BACKREF_REV_SHIFT) - -#define BTRFS_OLD_BACKREF_REV 0 -#define BTRFS_MIXED_BACKREF_REV 1 - -/* - * every tree block (leaf or node) starts with this header. - */ -struct btrfs_header { - /* these first four must match the super block */ - u8 csum[BTRFS_CSUM_SIZE]; - u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */ - __le64 bytenr; /* which block this node is supposed to live in */ - __le64 flags; - - /* allowed to be different from the super from here on down */ - u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; - __le64 generation; - __le64 owner; - __le32 nritems; - u8 level; -} __attribute__ ((__packed__)); - -/* - * this is a very generous portion of the super block, giving us - * room to translate 14 chunks with 3 stripes each. - */ -#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048 - -/* - * just in case we somehow lose the roots and are not able to mount, - * we store an array of the roots from previous transactions - * in the super. - */ -#define BTRFS_NUM_BACKUP_ROOTS 4 -struct btrfs_root_backup { - __le64 tree_root; - __le64 tree_root_gen; - - __le64 chunk_root; - __le64 chunk_root_gen; - - __le64 extent_root; - __le64 extent_root_gen; - - __le64 fs_root; - __le64 fs_root_gen; - - __le64 dev_root; - __le64 dev_root_gen; - - __le64 csum_root; - __le64 csum_root_gen; - - __le64 total_bytes; - __le64 bytes_used; - __le64 num_devices; - /* future */ - __le64 unused_64[4]; - - u8 tree_root_level; - u8 chunk_root_level; - u8 extent_root_level; - u8 fs_root_level; - u8 dev_root_level; - u8 csum_root_level; - /* future and to align */ - u8 unused_8[10]; -} __attribute__ ((__packed__)); - #define BTRFS_SUPER_INFO_OFFSET SZ_64K #define BTRFS_SUPER_INFO_SIZE 4096 +static_assert(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE); /* * The reserved space at the beginning of each device. @@ -221,69 +145,6 @@ struct btrfs_root_backup { */ #define BTRFS_DEVICE_RANGE_RESERVED (SZ_1M) -/* - * the super block basically lists the main trees of the FS - * it currently lacks any block count etc etc - */ -struct btrfs_super_block { - /* the first 4 fields must match struct btrfs_header */ - u8 csum[BTRFS_CSUM_SIZE]; - /* FS specific UUID, visible to user */ - u8 fsid[BTRFS_FSID_SIZE]; - __le64 bytenr; /* this block number */ - __le64 flags; - - /* allowed to be different from the btrfs_header from here own down */ - __le64 magic; - __le64 generation; - __le64 root; - __le64 chunk_root; - __le64 log_root; - - /* - * This member has never been utilized since the very beginning, thus - * it's always 0 regardless of kernel version. We always use - * generation + 1 to read log tree root. So here we mark it deprecated. - */ - __le64 __unused_log_root_transid; - __le64 total_bytes; - __le64 bytes_used; - __le64 root_dir_objectid; - __le64 num_devices; - __le32 sectorsize; - __le32 nodesize; - __le32 __unused_leafsize; - __le32 stripesize; - __le32 sys_chunk_array_size; - __le64 chunk_root_generation; - __le64 compat_flags; - __le64 compat_ro_flags; - __le64 incompat_flags; - __le16 csum_type; - u8 root_level; - u8 chunk_root_level; - u8 log_root_level; - struct btrfs_dev_item dev_item; - - char label[BTRFS_LABEL_SIZE]; - - __le64 cache_generation; - __le64 uuid_tree_generation; - - /* the UUID written into btree blocks */ - u8 metadata_uuid[BTRFS_FSID_SIZE]; - - /* future expansion */ - u8 reserved8[8]; - __le64 reserved[27]; - u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; - struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; - - /* Padded to 4096 bytes */ - u8 padding[565]; -} __attribute__ ((__packed__)); -static_assert(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE); - /* * Compat flags that we support. If any incompat flags are set other than the * ones specified below then we will fail to mount @@ -341,43 +202,6 @@ static_assert(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE); (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) #define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL -/* - * A leaf is full of items. offset and size tell us where to find - * the item in the leaf (relative to the start of the data area) - */ -struct btrfs_item { - struct btrfs_disk_key key; - __le32 offset; - __le32 size; -} __attribute__ ((__packed__)); - -/* - * leaves have an item area and a data area: - * [item0, item1....itemN] [free space] [dataN...data1, data0] - * - * The data is separate from the items to get the keys closer together - * during searches. - */ -struct btrfs_leaf { - struct btrfs_header header; - struct btrfs_item items[]; -} __attribute__ ((__packed__)); - -/* - * all non-leaf blocks are nodes, they hold only keys and pointers to - * other blocks - */ -struct btrfs_key_ptr { - struct btrfs_disk_key key; - __le64 blockptr; - __le64 generation; -} __attribute__ ((__packed__)); - -struct btrfs_node { - struct btrfs_header header; - struct btrfs_key_ptr ptrs[]; -} __attribute__ ((__packed__)); - /* Read ahead values for struct btrfs_path.reada */ enum { READA_NONE, @@ -1650,43 +1474,6 @@ do { \ #define btrfs_clear_pending(info, opt) \ clear_bit(BTRFS_PENDING_##opt, &(info)->pending_changes) -/* - * Inode flags - */ -#define BTRFS_INODE_NODATASUM (1U << 0) -#define BTRFS_INODE_NODATACOW (1U << 1) -#define BTRFS_INODE_READONLY (1U << 2) -#define BTRFS_INODE_NOCOMPRESS (1U << 3) -#define BTRFS_INODE_PREALLOC (1U << 4) -#define BTRFS_INODE_SYNC (1U << 5) -#define BTRFS_INODE_IMMUTABLE (1U << 6) -#define BTRFS_INODE_APPEND (1U << 7) -#define BTRFS_INODE_NODUMP (1U << 8) -#define BTRFS_INODE_NOATIME (1U << 9) -#define BTRFS_INODE_DIRSYNC (1U << 10) -#define BTRFS_INODE_COMPRESS (1U << 11) - -#define BTRFS_INODE_ROOT_ITEM_INIT (1U << 31) - -#define BTRFS_INODE_FLAG_MASK \ - (BTRFS_INODE_NODATASUM | \ - BTRFS_INODE_NODATACOW | \ - BTRFS_INODE_READONLY | \ - BTRFS_INODE_NOCOMPRESS | \ - BTRFS_INODE_PREALLOC | \ - BTRFS_INODE_SYNC | \ - BTRFS_INODE_IMMUTABLE | \ - BTRFS_INODE_APPEND | \ - BTRFS_INODE_NODUMP | \ - BTRFS_INODE_NOATIME | \ - BTRFS_INODE_DIRSYNC | \ - BTRFS_INODE_COMPRESS | \ - BTRFS_INODE_ROOT_ITEM_INIT) - -#define BTRFS_INODE_RO_VERITY (1U << 0) - -#define BTRFS_INODE_RO_FLAG_MASK (BTRFS_INODE_RO_VERITY) - struct btrfs_map_token { struct extent_buffer *eb; char *kaddr; diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 1f7a38ec6ac3..d43f67f676c2 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -10,6 +10,11 @@ #include #endif +/* ASCII for _BHRfS_M, no terminating nul */ +#define BTRFS_MAGIC 0x4D5F53665248425FULL + +#define BTRFS_MAX_LEVEL 8 + /* * This header contains the structure definitions and constants used * by file system objects that can be retrieved using @@ -360,6 +365,43 @@ enum btrfs_csum_type { #define BTRFS_FT_XATTR 8 #define BTRFS_FT_MAX 9 +/* + * Inode flags + */ +#define BTRFS_INODE_NODATASUM (1U << 0) +#define BTRFS_INODE_NODATACOW (1U << 1) +#define BTRFS_INODE_READONLY (1U << 2) +#define BTRFS_INODE_NOCOMPRESS (1U << 3) +#define BTRFS_INODE_PREALLOC (1U << 4) +#define BTRFS_INODE_SYNC (1U << 5) +#define BTRFS_INODE_IMMUTABLE (1U << 6) +#define BTRFS_INODE_APPEND (1U << 7) +#define BTRFS_INODE_NODUMP (1U << 8) +#define BTRFS_INODE_NOATIME (1U << 9) +#define BTRFS_INODE_DIRSYNC (1U << 10) +#define BTRFS_INODE_COMPRESS (1U << 11) + +#define BTRFS_INODE_ROOT_ITEM_INIT (1U << 31) + +#define BTRFS_INODE_FLAG_MASK \ + (BTRFS_INODE_NODATASUM | \ + BTRFS_INODE_NODATACOW | \ + BTRFS_INODE_READONLY | \ + BTRFS_INODE_NOCOMPRESS | \ + BTRFS_INODE_PREALLOC | \ + BTRFS_INODE_SYNC | \ + BTRFS_INODE_IMMUTABLE | \ + BTRFS_INODE_APPEND | \ + BTRFS_INODE_NODUMP | \ + BTRFS_INODE_NOATIME | \ + BTRFS_INODE_DIRSYNC | \ + BTRFS_INODE_COMPRESS | \ + BTRFS_INODE_ROOT_ITEM_INIT) + +#define BTRFS_INODE_RO_VERITY (1U << 0) + +#define BTRFS_INODE_RO_FLAG_MASK (BTRFS_INODE_RO_VERITY) + /* * The key defines the order in the tree, and so it also defines (optimal) * block layout. @@ -389,6 +431,109 @@ struct btrfs_key { __u64 offset; } __attribute__ ((__packed__)); +/* + * Every tree block (leaf or node) starts with this header. + */ +struct btrfs_header { + /* These first four must match the super block */ + __u8 csum[BTRFS_CSUM_SIZE]; + /* FS specific uuid */ + __u8 fsid[BTRFS_FSID_SIZE]; + /* Which block this node is supposed to live in */ + __le64 bytenr; + __le64 flags; + + /* Allowed to be different from the super from here on down */ + __u8 chunk_tree_uuid[BTRFS_UUID_SIZE]; + __le64 generation; + __le64 owner; + __le32 nritems; + __u8 level; +} __attribute__ ((__packed__)); + +/* + * This is a very generous portion of the super block, giving us room to + * translate 14 chunks with 3 stripes each. + */ +#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048 + +/* + * Just in case we somehow lose the roots and are not able to mount, we store + * an array of the roots from previous transactions in the super. + */ +#define BTRFS_NUM_BACKUP_ROOTS 4 +struct btrfs_root_backup { + __le64 tree_root; + __le64 tree_root_gen; + + __le64 chunk_root; + __le64 chunk_root_gen; + + __le64 extent_root; + __le64 extent_root_gen; + + __le64 fs_root; + __le64 fs_root_gen; + + __le64 dev_root; + __le64 dev_root_gen; + + __le64 csum_root; + __le64 csum_root_gen; + + __le64 total_bytes; + __le64 bytes_used; + __le64 num_devices; + /* future */ + __le64 unused_64[4]; + + __u8 tree_root_level; + __u8 chunk_root_level; + __u8 extent_root_level; + __u8 fs_root_level; + __u8 dev_root_level; + __u8 csum_root_level; + /* future and to align */ + __u8 unused_8[10]; +} __attribute__ ((__packed__)); + +/* + * A leaf is full of items. offset and size tell us where to find the item in + * the leaf (relative to the start of the data area) + */ +struct btrfs_item { + struct btrfs_disk_key key; + __le32 offset; + __le32 size; +} __attribute__ ((__packed__)); + +/* + * Leaves have an item area and a data area: + * [item0, item1....itemN] [free space] [dataN...data1, data0] + * + * The data is separate from the items to get the keys closer together during + * searches. + */ +struct btrfs_leaf { + struct btrfs_header header; + struct btrfs_item items[]; +} __attribute__ ((__packed__)); + +/* + * All non-leaf blocks are nodes, they hold only keys and pointers to other + * blocks. + */ +struct btrfs_key_ptr { + struct btrfs_disk_key key; + __le64 blockptr; + __le64 generation; +} __attribute__ ((__packed__)); + +struct btrfs_node { + struct btrfs_header header; + struct btrfs_key_ptr ptrs[]; +} __attribute__ ((__packed__)); + struct btrfs_dev_item { /* the internal btrfs device id */ __le64 devid; @@ -472,6 +617,68 @@ struct btrfs_chunk { /* additional stripes go here */ } __attribute__ ((__packed__)); +/* + * The super block basically lists the main trees of the FS. + */ +struct btrfs_super_block { + /* The first 4 fields must match struct btrfs_header */ + __u8 csum[BTRFS_CSUM_SIZE]; + /* FS specific UUID, visible to user */ + __u8 fsid[BTRFS_FSID_SIZE]; + /* This block number */ + __le64 bytenr; + __le64 flags; + + /* Allowed to be different from the btrfs_header from here own down */ + __le64 magic; + __le64 generation; + __le64 root; + __le64 chunk_root; + __le64 log_root; + + /* + * This member has never been utilized since the very beginning, thus + * it's always 0 regardless of kernel version. We always use + * generation + 1 to read log tree root. So here we mark it deprecated. + */ + __le64 __unused_log_root_transid; + __le64 total_bytes; + __le64 bytes_used; + __le64 root_dir_objectid; + __le64 num_devices; + __le32 sectorsize; + __le32 nodesize; + __le32 __unused_leafsize; + __le32 stripesize; + __le32 sys_chunk_array_size; + __le64 chunk_root_generation; + __le64 compat_flags; + __le64 compat_ro_flags; + __le64 incompat_flags; + __le16 csum_type; + __u8 root_level; + __u8 chunk_root_level; + __u8 log_root_level; + struct btrfs_dev_item dev_item; + + char label[BTRFS_LABEL_SIZE]; + + __le64 cache_generation; + __le64 uuid_tree_generation; + + /* The UUID written into btree blocks */ + __u8 metadata_uuid[BTRFS_FSID_SIZE]; + + /* Future expansion */ + __u8 reserved8[8]; + __le64 reserved[27]; + __u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; + struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; + + /* Padded to 4096 bytes */ + __u8 padding[565]; +} __attribute__ ((__packed__)); + #define BTRFS_FREE_SPACE_EXTENT 1 #define BTRFS_FREE_SPACE_BITMAP 2 @@ -526,6 +733,14 @@ struct btrfs_extent_item_v0 { /* use full backrefs for extent pointers in the block */ #define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8) +#define BTRFS_BACKREF_REV_MAX 256 +#define BTRFS_BACKREF_REV_SHIFT 56 +#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \ + BTRFS_BACKREF_REV_SHIFT) + +#define BTRFS_OLD_BACKREF_REV 0 +#define BTRFS_MIXED_BACKREF_REV 1 + /* * this flag is only used internally by scrub and may be changed at any time * it is only declared here to avoid collisions -- cgit From ad4b63caf56d0dc08e03966172d685ff9ebad996 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 14 Sep 2022 11:06:30 -0400 Subject: btrfs: move maximum limits to btrfs_tree.h We have maximum link and name length limits, move these to btrfs_tree.h as they're on disk limitations. Reviewed-by: Qu Wenruo Reviewed-by: Johannes Thumshirn Signed-off-by: Josef Bacik Reviewed-by: David Sterba [ reformat comments ] Signed-off-by: David Sterba --- fs/btrfs/ctree.h | 13 ------------- include/uapi/linux/btrfs_tree.h | 12 ++++++++++++ 2 files changed, 12 insertions(+), 13 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 7a80f9380146..6a37df0fa0eb 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -68,19 +68,6 @@ struct reloc_control; #define BTRFS_OLDEST_GENERATION 0ULL -/* - * we can actually store much bigger names, but lets not confuse the rest - * of linux - */ -#define BTRFS_NAME_LEN 255 - -/* - * Theoretical limit is larger, but we keep this down to a sane - * value. That should limit greatly the possibility of collisions on - * inode ref items. - */ -#define BTRFS_LINK_MAX 65535U - #define BTRFS_EMPTY_DIR_SIZE 0 #define BTRFS_DIRTY_METADATA_THRESH SZ_32M diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index d43f67f676c2..4809272f5063 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -15,6 +15,18 @@ #define BTRFS_MAX_LEVEL 8 +/* + * We can actually store much bigger names, but lets not confuse the rest of + * linux. + */ +#define BTRFS_NAME_LEN 255 + +/* + * Theoretical limit is larger, but we keep this down to a sane value. That + * should limit greatly the possibility of collisions on inode ref items. + */ +#define BTRFS_LINK_MAX 65535U + /* * This header contains the structure definitions and constants used * by file system objects that can be retrieved using -- cgit From 94a48aef49f235cc1efc74dc18e7708ca3b8d698 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Thu, 20 Oct 2022 12:58:28 -0400 Subject: btrfs: extend btrfs_dir_item type to store encryption status For directories with encrypted files/filenames, we need to store a flag indicating this fact. There's no room in other fields, so we'll need to borrow a bit from dir_type. Since it's now a combination of type and flags, we rename it to dir_flags to reflect its new usage. The new flag, FT_ENCRYPTED, indicates a directory containing encrypted data, which is orthogonal to file type; therefore, add the new flag, and make conversion from directory type to file type strip the flag. As the file types almost never change we can afford to use the bits. Actual usage will be guarded behind an incompat bit, this patch only adds the support for later use by fscrypt. Signed-off-by: Omar Sandoval Signed-off-by: Sweet Tea Dorminy Reviewed-by: David Sterba Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 15 +++++++++++++-- fs/btrfs/delayed-inode.c | 6 +++--- fs/btrfs/delayed-inode.h | 2 +- fs/btrfs/dir-item.c | 7 +++++-- fs/btrfs/inode.c | 13 +++++++------ fs/btrfs/print-tree.c | 4 ++-- fs/btrfs/send.c | 2 +- fs/btrfs/tree-checker.c | 2 +- fs/btrfs/tree-log.c | 20 ++++++++++---------- include/uapi/linux/btrfs_tree.h | 7 +++++++ 10 files changed, 50 insertions(+), 28 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index e8bbd4d80161..cb59b69d2af1 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -484,14 +484,25 @@ BTRFS_SETGET_FUNCS(root_ref_name_len, struct btrfs_root_ref, name_len, 16); /* struct btrfs_dir_item */ BTRFS_SETGET_FUNCS(dir_data_len, struct btrfs_dir_item, data_len, 16); -BTRFS_SETGET_FUNCS(dir_type, struct btrfs_dir_item, type, 8); +BTRFS_SETGET_FUNCS(dir_flags, struct btrfs_dir_item, type, 8); BTRFS_SETGET_FUNCS(dir_name_len, struct btrfs_dir_item, name_len, 16); BTRFS_SETGET_FUNCS(dir_transid, struct btrfs_dir_item, transid, 64); -BTRFS_SETGET_STACK_FUNCS(stack_dir_type, struct btrfs_dir_item, type, 8); +BTRFS_SETGET_STACK_FUNCS(stack_dir_flags, struct btrfs_dir_item, type, 8); BTRFS_SETGET_STACK_FUNCS(stack_dir_data_len, struct btrfs_dir_item, data_len, 16); BTRFS_SETGET_STACK_FUNCS(stack_dir_name_len, struct btrfs_dir_item, name_len, 16); BTRFS_SETGET_STACK_FUNCS(stack_dir_transid, struct btrfs_dir_item, transid, 64); +static inline u8 btrfs_dir_ftype(const struct extent_buffer *eb, + const struct btrfs_dir_item *item) +{ + return btrfs_dir_flags_to_ftype(btrfs_dir_flags(eb, item)); +} + +static inline u8 btrfs_stack_dir_ftype(const struct btrfs_dir_item *item) +{ + return btrfs_dir_flags_to_ftype(btrfs_stack_dir_flags(item)); +} + static inline void btrfs_dir_item_key(const struct extent_buffer *eb, const struct btrfs_dir_item *item, struct btrfs_disk_key *key) diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c index 012c96de4701..f93d2695e423 100644 --- a/fs/btrfs/delayed-inode.c +++ b/fs/btrfs/delayed-inode.c @@ -1416,7 +1416,7 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info) int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, const char *name, int name_len, struct btrfs_inode *dir, - struct btrfs_disk_key *disk_key, u8 type, + struct btrfs_disk_key *disk_key, u8 flags, u64 index) { struct btrfs_fs_info *fs_info = trans->fs_info; @@ -1447,7 +1447,7 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, btrfs_set_stack_dir_transid(dir_item, trans->transid); btrfs_set_stack_dir_data_len(dir_item, 0); btrfs_set_stack_dir_name_len(dir_item, name_len); - btrfs_set_stack_dir_type(dir_item, type); + btrfs_set_stack_dir_flags(dir_item, flags); memcpy((char *)(dir_item + 1), name, name_len); data_len = delayed_item->data_len + sizeof(struct btrfs_item); @@ -1757,7 +1757,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx, name = (char *)(di + 1); name_len = btrfs_stack_dir_name_len(di); - d_type = fs_ftype_to_dtype(di->type); + d_type = fs_ftype_to_dtype(btrfs_dir_flags_to_ftype(di->type)); btrfs_disk_key_to_cpu(&location, &di->location); over = !dir_emit(ctx, name, name_len, diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h index 0163ca637a96..4f21daa3dbc7 100644 --- a/fs/btrfs/delayed-inode.h +++ b/fs/btrfs/delayed-inode.h @@ -113,7 +113,7 @@ static inline void btrfs_init_delayed_root( int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans, const char *name, int name_len, struct btrfs_inode *dir, - struct btrfs_disk_key *disk_key, u8 type, + struct btrfs_disk_key *disk_key, u8 flags, u64 index); int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c index 23777021b331..ca69fb35a2cc 100644 --- a/fs/btrfs/dir-item.c +++ b/fs/btrfs/dir-item.c @@ -83,7 +83,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans, leaf = path->nodes[0]; btrfs_cpu_key_to_disk(&disk_key, &location); btrfs_set_dir_item_key(leaf, dir_item, &disk_key); - btrfs_set_dir_type(leaf, dir_item, BTRFS_FT_XATTR); + btrfs_set_dir_flags(leaf, dir_item, BTRFS_FT_XATTR); btrfs_set_dir_name_len(leaf, dir_item, name_len); btrfs_set_dir_transid(leaf, dir_item, trans->transid); btrfs_set_dir_data_len(leaf, dir_item, data_len); @@ -140,9 +140,12 @@ int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, goto out_free; } + if (IS_ENCRYPTED(&dir->vfs_inode)) + type |= BTRFS_FT_ENCRYPTED; + leaf = path->nodes[0]; btrfs_set_dir_item_key(leaf, dir_item, &disk_key); - btrfs_set_dir_type(leaf, dir_item, type); + btrfs_set_dir_flags(leaf, dir_item, type); btrfs_set_dir_data_len(leaf, dir_item, 0); btrfs_set_dir_name_len(leaf, dir_item, name->len); btrfs_set_dir_transid(leaf, dir_item, trans->transid); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 7e76d5e91786..78867a084428 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5597,7 +5597,7 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry, location->objectid, location->type, location->offset); } if (!ret) - *type = btrfs_dir_type(path->nodes[0], di); + *type = btrfs_dir_ftype(path->nodes[0], di); out: fscrypt_free_filename(&fname); btrfs_free_path(path); @@ -6046,6 +6046,7 @@ again: btrfs_for_each_slot(root, &key, &found_key, path, ret) { struct dir_entry *entry; struct extent_buffer *leaf = path->nodes[0]; + u8 ftype; if (found_key.objectid != key.objectid) break; @@ -6069,13 +6070,13 @@ again: goto again; } + ftype = btrfs_dir_flags_to_ftype(btrfs_dir_flags(leaf, di)); entry = addr; - put_unaligned(name_len, &entry->name_len); name_ptr = (char *)(entry + 1); - read_extent_buffer(leaf, name_ptr, (unsigned long)(di + 1), - name_len); - put_unaligned(fs_ftype_to_dtype(btrfs_dir_type(leaf, di)), - &entry->type); + read_extent_buffer(leaf, name_ptr, + (unsigned long)(di + 1), name_len); + put_unaligned(name_len, &entry->name_len); + put_unaligned(fs_ftype_to_dtype(ftype), &entry->type); btrfs_dir_item_key_to_cpu(leaf, di, &location); put_unaligned(location.objectid, &entry->ino); put_unaligned(found_key.offset, &entry->offset); diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c index aab7d30eed55..1a2350fd68be 100644 --- a/fs/btrfs/print-tree.c +++ b/fs/btrfs/print-tree.c @@ -242,9 +242,9 @@ void btrfs_print_leaf(struct extent_buffer *l) case BTRFS_DIR_ITEM_KEY: di = btrfs_item_ptr(l, i, struct btrfs_dir_item); btrfs_dir_item_key_to_cpu(l, di, &found_key); - pr_info("\t\tdir oid %llu type %u\n", + pr_info("\t\tdir oid %llu flags %u\n", found_key.objectid, - btrfs_dir_type(l, di)); + btrfs_dir_flags(l, di)); break; case BTRFS_ROOT_ITEM_KEY: ri = btrfs_item_ptr(l, i, struct btrfs_root_item); diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index 0ebca9dba5ab..2ece3a030a66 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -1094,7 +1094,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path, data_len = btrfs_dir_data_len(eb, di); btrfs_dir_item_key_to_cpu(eb, di, &di_key); - if (btrfs_dir_type(eb, di) == BTRFS_FT_XATTR) { + if (btrfs_dir_ftype(eb, di) == BTRFS_FT_XATTR) { if (name_len > XATTR_NAME_MAX) { ret = -ENAMETOOLONG; goto out; diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c index 11cafc520b47..1c2d418dda6a 100644 --- a/fs/btrfs/tree-checker.c +++ b/fs/btrfs/tree-checker.c @@ -531,7 +531,7 @@ static int check_dir_item(struct extent_buffer *leaf, } /* dir type check */ - dir_type = btrfs_dir_type(leaf, di); + dir_type = btrfs_dir_ftype(leaf, di); if (unlikely(dir_type >= BTRFS_FT_MAX)) { dir_item_err(leaf, slot, "invalid dir item type, have %u expect [0, %u)", diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index 7002cc3315da..a5e56a678af2 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -1799,7 +1799,7 @@ static int delete_conflicting_dir_entry(struct btrfs_trans_handle *trans, struct btrfs_path *path, struct btrfs_dir_item *dst_di, const struct btrfs_key *log_key, - u8 log_type, + u8 log_flags, bool exists) { struct btrfs_key found_key; @@ -1809,7 +1809,7 @@ static int delete_conflicting_dir_entry(struct btrfs_trans_handle *trans, if (found_key.objectid == log_key->objectid && found_key.type == log_key->type && found_key.offset == log_key->offset && - btrfs_dir_type(path->nodes[0], dst_di) == log_type) + btrfs_dir_flags(path->nodes[0], dst_di) == log_flags) return 1; /* @@ -1853,7 +1853,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, struct btrfs_key log_key; struct btrfs_key search_key; struct inode *dir; - u8 log_type; + u8 log_flags; bool exists; int ret; bool update_size = true; @@ -1867,7 +1867,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, if (ret) goto out; - log_type = btrfs_dir_type(eb, di); + log_flags = btrfs_dir_flags(eb, di); btrfs_dir_item_key_to_cpu(eb, di, &log_key); ret = btrfs_lookup_inode(trans, root, path, &log_key, 0); btrfs_release_path(path); @@ -1883,8 +1883,8 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, goto out; } else if (dir_dst_di) { ret = delete_conflicting_dir_entry(trans, BTRFS_I(dir), path, - dir_dst_di, &log_key, log_type, - exists); + dir_dst_di, &log_key, + log_flags, exists); if (ret < 0) goto out; dir_dst_matches = (ret == 1); @@ -1901,7 +1901,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans, } else if (index_dst_di) { ret = delete_conflicting_dir_entry(trans, BTRFS_I(dir), path, index_dst_di, &log_key, - log_type, exists); + log_flags, exists); if (ret < 0) goto out; index_dst_matches = (ret == 1); @@ -2010,7 +2010,7 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans, * to ever delete the parent directory has it would result in stale * dentries that can never be deleted. */ - if (ret == 1 && btrfs_dir_type(eb, di) != BTRFS_FT_DIR) { + if (ret == 1 && btrfs_dir_ftype(eb, di) != BTRFS_FT_DIR) { struct btrfs_path *fixup_path; struct btrfs_key di_key; @@ -5452,7 +5452,7 @@ again: } di = btrfs_item_ptr(leaf, i, struct btrfs_dir_item); - type = btrfs_dir_type(leaf, di); + type = btrfs_dir_ftype(leaf, di); if (btrfs_dir_transid(leaf, di) < trans->transid) continue; btrfs_dir_item_key_to_cpu(leaf, di, &di_key); @@ -6292,7 +6292,7 @@ static int log_new_delayed_dentries(struct btrfs_trans_handle *trans, continue; } - if (btrfs_stack_dir_type(dir_item) == BTRFS_FT_DIR) + if (btrfs_stack_dir_ftype(dir_item) == BTRFS_FT_DIR) log_mode = LOG_INODE_ALL; ctx->log_new_dentries = false; diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 4809272f5063..29895ffa470d 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -376,6 +376,13 @@ enum btrfs_csum_type { #define BTRFS_FT_SYMLINK 7 #define BTRFS_FT_XATTR 8 #define BTRFS_FT_MAX 9 +/* Directory contains encrypted data */ +#define BTRFS_FT_ENCRYPTED 0x80 + +static inline __u8 btrfs_dir_flags_to_ftype(__u8 flags) +{ + return flags & ~BTRFS_FT_ENCRYPTED; +} /* * Inode flags -- cgit From 0c7030038e6106711c5d0b237c980905dd3244ec Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 15 Nov 2022 11:16:19 -0500 Subject: btrfs: add nr_global_roots to the super block definition We already have this defined in btrfs-progs, add it to the kernel to make it easier to sync these files into btrfs-progs. Signed-off-by: Josef Bacik Signed-off-by: David Sterba --- fs/btrfs/accessors.h | 2 ++ include/uapi/linux/btrfs_tree.h | 3 ++- 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/accessors.h b/fs/btrfs/accessors.h index e6228ff73c81..75c181b579eb 100644 --- a/fs/btrfs/accessors.h +++ b/fs/btrfs/accessors.h @@ -889,6 +889,8 @@ BTRFS_SETGET_STACK_FUNCS(super_cache_generation, struct btrfs_super_block, BTRFS_SETGET_STACK_FUNCS(super_magic, struct btrfs_super_block, magic, 64); BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block, uuid_tree_generation, 64); +BTRFS_SETGET_STACK_FUNCS(super_nr_global_roots, struct btrfs_super_block, + nr_global_roots, 64); /* struct btrfs_file_extent_item */ BTRFS_SETGET_STACK_FUNCS(stack_file_extent_type, struct btrfs_file_extent_item, diff --git a/include/uapi/linux/btrfs_tree.h b/include/uapi/linux/btrfs_tree.h index 29895ffa470d..ab38d0f411fa 100644 --- a/include/uapi/linux/btrfs_tree.h +++ b/include/uapi/linux/btrfs_tree.h @@ -688,8 +688,9 @@ struct btrfs_super_block { /* The UUID written into btree blocks */ __u8 metadata_uuid[BTRFS_FSID_SIZE]; + __u64 nr_global_roots; + /* Future expansion */ - __u8 reserved8[8]; __le64 reserved[27]; __u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE]; struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS]; -- cgit From a28135303a669917002f569aecebd5758263e4aa Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 28 Nov 2022 14:26:38 -0500 Subject: btrfs: sync some cleanups from progs into uapi/btrfs.h When syncing this code into btrfs-progs Dave noticed there's some things we were losing in the sync that are needed. This syncs those changes into the kernel, which include a few comments that weren't in the kernel, some whitespace changes, an attribute, and the cplusplus bit. Signed-off-by: Josef Bacik Reviewed-by: David Sterba Signed-off-by: David Sterba --- include/uapi/linux/btrfs.h | 36 ++++++++++++++++++++++++++++++------ 1 file changed, 30 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index 5655e89b962b..b4f0f9531119 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -19,8 +19,14 @@ #ifndef _UAPI_LINUX_BTRFS_H #define _UAPI_LINUX_BTRFS_H + +#ifdef __cplusplus +extern "C" { +#endif + #include #include +#include #define BTRFS_IOCTL_MAGIC 0x94 #define BTRFS_VOL_NAME_MAX 255 @@ -333,6 +339,12 @@ struct btrfs_ioctl_feature_flags { */ struct btrfs_balance_args { __u64 profiles; + + /* + * usage filter + * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N' + * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max + */ union { __u64 usage; struct { @@ -549,7 +561,7 @@ struct btrfs_ioctl_search_header { __u64 offset; __u32 type; __u32 len; -}; +} __attribute__ ((__may_alias__)); #define BTRFS_SEARCH_ARGS_BUFSIZE (4096 - sizeof(struct btrfs_ioctl_search_key)) /* @@ -562,6 +574,10 @@ struct btrfs_ioctl_search_args { char buf[BTRFS_SEARCH_ARGS_BUFSIZE]; }; +/* + * Extended version of TREE_SEARCH ioctl that can return more than 4k of bytes. + * The allocated size of the buffer is set in buf_size. + */ struct btrfs_ioctl_search_args_v2 { struct btrfs_ioctl_search_key key; /* in/out - search parameters */ __u64 buf_size; /* in - size of buffer @@ -570,10 +586,11 @@ struct btrfs_ioctl_search_args_v2 { __u64 buf[]; /* out - found items */ }; +/* With a @src_length of zero, the range from @src_offset->EOF is cloned! */ struct btrfs_ioctl_clone_range_args { - __s64 src_fd; - __u64 src_offset, src_length; - __u64 dest_offset; + __s64 src_fd; + __u64 src_offset, src_length; + __u64 dest_offset; }; /* @@ -677,8 +694,11 @@ struct btrfs_ioctl_logical_ino_args { /* struct btrfs_data_container *inodes; out */ __u64 inodes; }; -/* Return every ref to the extent, not just those containing logical block. - * Requires logical == extent bytenr. */ + +/* + * Return every ref to the extent, not just those containing logical block. + * Requires logical == extent bytenr. + */ #define BTRFS_LOGICAL_INO_ARGS_IGNORE_OFFSET (1ULL << 0) enum btrfs_dev_stat_values { @@ -1144,4 +1164,8 @@ enum btrfs_err_code { #define BTRFS_IOC_ENCODED_WRITE _IOW(BTRFS_IOCTL_MAGIC, 64, \ struct btrfs_ioctl_encoded_io_args) +#ifdef __cplusplus +} +#endif + #endif /* _UAPI_LINUX_BTRFS_H */ -- cgit From 7112a04664bfc10ae4709b2079fe3991cbd1fe18 Mon Sep 17 00:00:00 2001 From: Sudheer Mogilappagari Date: Thu, 1 Dec 2022 16:25:55 -0800 Subject: ethtool: add netlink based get rss support Add netlink based support for "ethtool -x [context x]" command by implementing ETHTOOL_MSG_RSS_GET netlink message. This is equivalent to functionality provided via ETHTOOL_GRSSH in ioctl path. It sends RSS table, hash key and hash function of an interface to user space. This patch implements existing functionality available in ioctl path and enables addition of new RSS context based parameters in future. Signed-off-by: Sudheer Mogilappagari Link: https://lore.kernel.org/r/20221202002555.241580-1-sudheer.mogilappagari@intel.com Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 31 +++++- include/uapi/linux/ethtool_netlink.h | 14 +++ net/ethtool/Makefile | 2 +- net/ethtool/netlink.c | 7 ++ net/ethtool/netlink.h | 2 + net/ethtool/rss.c | 153 +++++++++++++++++++++++++++ 6 files changed, 207 insertions(+), 2 deletions(-) create mode 100644 net/ethtool/rss.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index bede24ef44fd..f10f8eb44255 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -222,6 +222,7 @@ Userspace to kernel: ``ETHTOOL_MSG_MODULE_GET`` get transceiver module parameters ``ETHTOOL_MSG_PSE_SET`` set PSE parameters ``ETHTOOL_MSG_PSE_GET`` get PSE parameters + ``ETHTOOL_MSG_RSS_GET`` get RSS settings ===================================== ================================= Kernel to userspace: @@ -263,6 +264,7 @@ Kernel to userspace: ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info ``ETHTOOL_MSG_MODULE_GET_REPLY`` transceiver module parameters ``ETHTOOL_MSG_PSE_GET_REPLY`` PSE parameters + ``ETHTOOL_MSG_RSS_GET_REPLY`` RSS settings ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1687,6 +1689,33 @@ to control PoDL PSE Admin functions. This option is implementing ``IEEE 802.3-2018`` 30.15.1.2.1 acPoDLPSEAdminControl. See ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` for supported values. +RSS_GET +======= + +Get indirection table, hash key and hash function info associated with a +RSS context of an interface similar to ``ETHTOOL_GRSSH`` ioctl request. + +Request contents: + +===================================== ====== ========================== + ``ETHTOOL_A_RSS_HEADER`` nested request header + ``ETHTOOL_A_RSS_CONTEXT`` u32 context number +===================================== ====== ========================== + +Kernel response contents: + +===================================== ====== ========================== + ``ETHTOOL_A_RSS_HEADER`` nested reply header + ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func + ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes + ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes +===================================== ====== ========================== + +ETHTOOL_A_RSS_HFUNC attribute is bitmap indicating the hash function +being used. Current supported options are toeplitz, xor or crc32. +ETHTOOL_A_RSS_INDIR attribute returns RSS indrection table where each byte +indicates queue number. + Request translation =================== @@ -1768,7 +1797,7 @@ are netlink only. ``ETHTOOL_GMODULEEEPROM`` ``ETHTOOL_MSG_MODULE_EEPROM_GET`` ``ETHTOOL_GEEE`` ``ETHTOOL_MSG_EEE_GET`` ``ETHTOOL_SEEE`` ``ETHTOOL_MSG_EEE_SET`` - ``ETHTOOL_GRSSH`` n/a + ``ETHTOOL_GRSSH`` ``ETHTOOL_MSG_RSS_GET`` ``ETHTOOL_SRSSH`` n/a ``ETHTOOL_GTUNABLE`` n/a ``ETHTOOL_STUNABLE`` n/a diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index aaf7c6963d61..5799a9db034e 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -51,6 +51,7 @@ enum { ETHTOOL_MSG_MODULE_SET, ETHTOOL_MSG_PSE_GET, ETHTOOL_MSG_PSE_SET, + ETHTOOL_MSG_RSS_GET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -97,6 +98,7 @@ enum { ETHTOOL_MSG_MODULE_GET_REPLY, ETHTOOL_MSG_MODULE_NTF, ETHTOOL_MSG_PSE_GET_REPLY, + ETHTOOL_MSG_RSS_GET_REPLY, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -880,6 +882,18 @@ enum { ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1) }; +enum { + ETHTOOL_A_RSS_UNSPEC, + ETHTOOL_A_RSS_HEADER, + ETHTOOL_A_RSS_CONTEXT, /* u32 */ + ETHTOOL_A_RSS_HFUNC, /* u32 */ + ETHTOOL_A_RSS_INDIR, /* binary */ + ETHTOOL_A_RSS_HKEY, /* binary */ + + __ETHTOOL_A_RSS_CNT, + ETHTOOL_A_RSS_MAX = (__ETHTOOL_A_RSS_CNT - 1), +}; + /* generic netlink info */ #define ETHTOOL_GENL_NAME "ethtool" #define ETHTOOL_GENL_VERSION 1 diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile index 72ab0944262a..228f13df2e18 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -4,7 +4,7 @@ obj-y += ioctl.o common.o obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o -ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o \ +ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.o rss.o \ linkstate.o debug.o wol.o features.o privflags.o rings.o \ channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \ tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o \ diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1a4c11356c96..aee98be6237f 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -287,6 +287,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, [ETHTOOL_MSG_PSE_GET] = ðnl_pse_request_ops, + [ETHTOOL_MSG_RSS_GET] = ðnl_rss_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -1040,6 +1041,12 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_pse_set_policy, .maxattr = ARRAY_SIZE(ethnl_pse_set_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_RSS_GET, + .doit = ethnl_default_doit, + .policy = ethnl_rss_get_policy, + .maxattr = ARRAY_SIZE(ethnl_rss_get_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index 1bfd374f9718..3753787ba233 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -346,6 +346,7 @@ extern const struct ethnl_request_ops ethnl_stats_request_ops; extern const struct ethnl_request_ops ethnl_phc_vclocks_request_ops; extern const struct ethnl_request_ops ethnl_module_request_ops; extern const struct ethnl_request_ops ethnl_pse_request_ops; +extern const struct ethnl_request_ops ethnl_rss_request_ops; extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -386,6 +387,7 @@ extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1]; extern const struct nla_policy ethnl_pse_get_policy[ETHTOOL_A_PSE_HEADER + 1]; extern const struct nla_policy ethnl_pse_set_policy[ETHTOOL_A_PSE_MAX + 1]; +extern const struct nla_policy ethnl_rss_get_policy[ETHTOOL_A_RSS_CONTEXT + 1]; int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info); int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info); diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c new file mode 100644 index 000000000000..ebe6145aed3f --- /dev/null +++ b/net/ethtool/rss.c @@ -0,0 +1,153 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "netlink.h" +#include "common.h" + +struct rss_req_info { + struct ethnl_req_info base; + u32 rss_context; +}; + +struct rss_reply_data { + struct ethnl_reply_data base; + u32 indir_size; + u32 hkey_size; + u32 hfunc; + u32 *indir_table; + u8 *hkey; +}; + +#define RSS_REQINFO(__req_base) \ + container_of(__req_base, struct rss_req_info, base) + +#define RSS_REPDATA(__reply_base) \ + container_of(__reply_base, struct rss_reply_data, base) + +const struct nla_policy ethnl_rss_get_policy[] = { + [ETHTOOL_A_RSS_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_RSS_CONTEXT] = { .type = NLA_U32 }, +}; + +static int +rss_parse_request(struct ethnl_req_info *req_info, struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rss_req_info *request = RSS_REQINFO(req_info); + + if (tb[ETHTOOL_A_RSS_CONTEXT]) + request->rss_context = nla_get_u32(tb[ETHTOOL_A_RSS_CONTEXT]); + + return 0; +} + +static int +rss_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, struct genl_info *info) +{ + struct rss_reply_data *data = RSS_REPDATA(reply_base); + struct rss_req_info *request = RSS_REQINFO(req_base); + struct net_device *dev = reply_base->dev; + const struct ethtool_ops *ops; + u32 total_size, indir_bytes; + u8 dev_hfunc = 0; + u8 *rss_config; + int ret; + + ops = dev->ethtool_ops; + if (!ops->get_rxfh) + return -EOPNOTSUPP; + + /* Some drivers don't handle rss_context */ + if (request->rss_context && !ops->get_rxfh_context) + return -EOPNOTSUPP; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + data->indir_size = 0; + data->hkey_size = 0; + if (ops->get_rxfh_indir_size) + data->indir_size = ops->get_rxfh_indir_size(dev); + if (ops->get_rxfh_key_size) + data->hkey_size = ops->get_rxfh_key_size(dev); + + indir_bytes = data->indir_size * sizeof(u32); + total_size = indir_bytes + data->hkey_size; + rss_config = kzalloc(total_size, GFP_KERNEL); + if (!rss_config) { + ret = -ENOMEM; + goto out_ops; + } + + if (data->indir_size) + data->indir_table = (u32 *)rss_config; + + if (data->hkey_size) + data->hkey = rss_config + indir_bytes; + + if (request->rss_context) + ret = ops->get_rxfh_context(dev, data->indir_table, data->hkey, + &dev_hfunc, request->rss_context); + else + ret = ops->get_rxfh(dev, data->indir_table, data->hkey, + &dev_hfunc); + + if (ret) + goto out_ops; + + data->hfunc = dev_hfunc; +out_ops: + ethnl_ops_complete(dev); + return ret; +} + +static int +rss_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct rss_reply_data *data = RSS_REPDATA(reply_base); + int len; + + len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */ + nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */ + nla_total_size(data->hkey_size); /* _RSS_HKEY */ + + return len; +} + +static int +rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct rss_reply_data *data = RSS_REPDATA(reply_base); + + if (nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc) || + nla_put(skb, ETHTOOL_A_RSS_INDIR, + sizeof(u32) * data->indir_size, data->indir_table) || + nla_put(skb, ETHTOOL_A_RSS_HKEY, data->hkey_size, data->hkey)) + return -EMSGSIZE; + + return 0; +} + +static void rss_cleanup_data(struct ethnl_reply_data *reply_base) +{ + const struct rss_reply_data *data = RSS_REPDATA(reply_base); + + kfree(data->indir_table); +} + +const struct ethnl_request_ops ethnl_rss_request_ops = { + .request_cmd = ETHTOOL_MSG_RSS_GET, + .reply_cmd = ETHTOOL_MSG_RSS_GET_REPLY, + .hdr_attr = ETHTOOL_A_RSS_HEADER, + .req_info_size = sizeof(struct rss_req_info), + .reply_data_size = sizeof(struct rss_reply_data), + + .parse_request = rss_parse_request, + .prepare_data = rss_prepare_data, + .reply_size = rss_reply_size, + .fill_reply = rss_fill_reply, + .cleanup_data = rss_cleanup_data, +}; -- cgit From d50fd948d3d086e2608430eb17a01948c3c0d0d2 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 28 Nov 2022 05:43:03 +0000 Subject: media: dvb/frontend.h: fix kernel-doc warnings scripts/kernel-doc spouts multiple warnings, so fix them: include/uapi/linux/dvb/frontend.h:399: warning: Enum value 'QAM_1024' not described in enum 'fe_modulation' include/uapi/linux/dvb/frontend.h:399: warning: Enum value 'QAM_4096' not described in enum 'fe_modulation' frontend.h:286: warning: contents before sections frontend.h:780: warning: missing initial short description on line: * enum atscmh_rs_code_mode Fixes: 8220ead805b6 ("media: dvb/frontend.h: document the uAPI file") Fixes: 6508a50fe84f ("media: dvb: add DVB-C2 and DVB-S2X parameter values") Signed-off-by: Randy Dunlap Reviewed-by: Robert Schlabbach Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- include/uapi/linux/dvb/frontend.h | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 4fed9e316147..022a787815e0 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -282,7 +282,6 @@ enum fe_spectral_inversion { /** * enum fe_code_rate - Type of Forward Error Correction (FEC) * - * * @FEC_NONE: No Forward Error Correction Code * @FEC_1_2: Forward Error Correction Code 1/2 * @FEC_2_3: Forward Error Correction Code 2/3 @@ -363,8 +362,8 @@ enum fe_code_rate { * @APSK_32: 32-APSK modulation * @DQPSK: DQPSK modulation * @QAM_4_NR: 4-QAM-NR modulation - * @QAM-1024: 1024-QAM modulation - * @QAM-4096: 4096-QAM modulation + * @QAM_1024: 1024-QAM modulation + * @QAM_4096: 4096-QAM modulation * @APSK_8_L: 8APSK-L modulation * @APSK_16_L: 16APSK-L modulation * @APSK_32_L: 32APSK-L modulation @@ -777,7 +776,7 @@ enum atscmh_rs_frame_mode { }; /** - * enum atscmh_rs_code_mode + * enum atscmh_rs_code_mode - ATSC-M/H Reed Solomon modes * @ATSCMH_RSCODE_211_187: Reed Solomon code (211,187). * @ATSCMH_RSCODE_223_187: Reed Solomon code (223,187). * @ATSCMH_RSCODE_235_187: Reed Solomon code (235,187). -- cgit From 4db52602a6074e9cc523500b8304600ff63e7b85 Mon Sep 17 00:00:00 2001 From: Jason Gunthorpe Date: Tue, 6 Dec 2022 10:34:26 +0200 Subject: vfio: Extend the device migration protocol with PRE_COPY The optional PRE_COPY states open the saving data transfer FD before reaching STOP_COPY and allows the device to dirty track internal state changes with the general idea to reduce the volume of data transferred in the STOP_COPY stage. While in PRE_COPY the device remains RUNNING, but the saving FD is open. Only if the device also supports RUNNING_P2P can it support PRE_COPY_P2P, which halts P2P transfers while continuing the saving FD. PRE_COPY, with P2P support, requires the driver to implement 7 new arcs and exists as an optional FSM branch between RUNNING and STOP_COPY: RUNNING -> PRE_COPY -> PRE_COPY_P2P -> STOP_COPY A new ioctl VFIO_MIG_GET_PRECOPY_INFO is provided to allow userspace to query the progress of the precopy operation in the driver with the idea it will judge to move to STOP_COPY at least once the initial data set is transferred, and possibly after the dirty size has shrunk appropriately. This ioctl is valid only in PRE_COPY states and kernel driver should return -EINVAL from any other migration state. Compared to the v1 clarification, STOP_COPY -> PRE_COPY is blocked and to be defined in future. We also split the pending_bytes report into the initial and sustaining values, e.g.: initial_bytes and dirty_bytes. initial_bytes: Amount of initial precopy data. dirty_bytes: Device state changes relative to data previously retrieved. These fields are not required to have any bearing to STOP_COPY phase. It is recommended to leave PRE_COPY for STOP_COPY only after the initial_bytes field reaches zero. Leaving PRE_COPY earlier might make things slower. Signed-off-by: Jason Gunthorpe Signed-off-by: Shay Drory Reviewed-by: Kevin Tian Reviewed-by: Shameer Kolothum Signed-off-by: Yishai Hadas Link: https://lore.kernel.org/r/20221206083438.37807-3-yishaih@nvidia.com Signed-off-by: Alex Williamson --- drivers/vfio/vfio_main.c | 74 +++++++++++++++++++++++++++- include/uapi/linux/vfio.h | 123 ++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 191 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 7f88569c3eba..03dbcd3d96f0 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -1042,7 +1042,7 @@ int vfio_mig_get_next_state(struct vfio_device *device, enum vfio_device_mig_state new_fsm, enum vfio_device_mig_state *next_fsm) { - enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RUNNING_P2P + 1 }; + enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_PRE_COPY_P2P + 1 }; /* * The coding in this table requires the driver to implement the * following FSM arcs: @@ -1057,30 +1057,65 @@ int vfio_mig_get_next_state(struct vfio_device *device, * RUNNING_P2P -> RUNNING * RUNNING_P2P -> STOP * STOP -> RUNNING_P2P - * Without P2P the driver must implement: + * + * If precopy is supported then the driver must support these additional + * FSM arcs: + * RUNNING -> PRE_COPY + * PRE_COPY -> RUNNING + * PRE_COPY -> STOP_COPY + * However, if precopy and P2P are supported together then the driver + * must support these additional arcs beyond the P2P arcs above: + * PRE_COPY -> RUNNING + * PRE_COPY -> PRE_COPY_P2P + * PRE_COPY_P2P -> PRE_COPY + * PRE_COPY_P2P -> RUNNING_P2P + * PRE_COPY_P2P -> STOP_COPY + * RUNNING -> PRE_COPY + * RUNNING_P2P -> PRE_COPY_P2P + * + * Without P2P and precopy the driver must implement: * RUNNING -> STOP * STOP -> RUNNING * * The coding will step through multiple states for some combination * transitions; if all optional features are supported, this means the * following ones: + * PRE_COPY -> PRE_COPY_P2P -> STOP_COPY + * PRE_COPY -> RUNNING -> RUNNING_P2P + * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP + * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP -> RESUMING + * PRE_COPY_P2P -> RUNNING_P2P -> RUNNING + * PRE_COPY_P2P -> RUNNING_P2P -> STOP + * PRE_COPY_P2P -> RUNNING_P2P -> STOP -> RESUMING * RESUMING -> STOP -> RUNNING_P2P + * RESUMING -> STOP -> RUNNING_P2P -> PRE_COPY_P2P * RESUMING -> STOP -> RUNNING_P2P -> RUNNING + * RESUMING -> STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY * RESUMING -> STOP -> STOP_COPY + * RUNNING -> RUNNING_P2P -> PRE_COPY_P2P * RUNNING -> RUNNING_P2P -> STOP * RUNNING -> RUNNING_P2P -> STOP -> RESUMING * RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY + * RUNNING_P2P -> RUNNING -> PRE_COPY * RUNNING_P2P -> STOP -> RESUMING * RUNNING_P2P -> STOP -> STOP_COPY + * STOP -> RUNNING_P2P -> PRE_COPY_P2P * STOP -> RUNNING_P2P -> RUNNING + * STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY * STOP_COPY -> STOP -> RESUMING * STOP_COPY -> STOP -> RUNNING_P2P * STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING + * + * The following transitions are blocked: + * STOP_COPY -> PRE_COPY + * STOP_COPY -> PRE_COPY_P2P */ static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = { [VFIO_DEVICE_STATE_STOP] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, @@ -1089,14 +1124,38 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_RUNNING] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, }, + [VFIO_DEVICE_STATE_PRE_COPY] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_PRE_COPY_P2P, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = { + [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P, + [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, + [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, + [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR, + }, [VFIO_DEVICE_STATE_STOP_COPY] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP, @@ -1105,6 +1164,8 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_RESUMING] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_STOP, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP, @@ -1113,6 +1174,8 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_RUNNING_P2P] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P, @@ -1121,6 +1184,8 @@ int vfio_mig_get_next_state(struct vfio_device *device, [VFIO_DEVICE_STATE_ERROR] = { [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR, [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR, @@ -1131,6 +1196,11 @@ int vfio_mig_get_next_state(struct vfio_device *device, static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = { [VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY, + [VFIO_DEVICE_STATE_PRE_COPY] = + VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY, + [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_MIGRATION_STOP_COPY | + VFIO_MIGRATION_P2P | + VFIO_MIGRATION_PRE_COPY, [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY, [VFIO_DEVICE_STATE_RUNNING_P2P] = diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 3e45dbaf190e..23105eb036fa 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -819,12 +819,20 @@ struct vfio_device_feature { * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P means that RUNNING_P2P * is supported in addition to the STOP_COPY states. * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY means that + * PRE_COPY is supported in addition to the STOP_COPY states. + * + * VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY + * means that RUNNING_P2P, PRE_COPY and PRE_COPY_P2P are supported + * in addition to the STOP_COPY states. + * * Other combinations of flags have behavior to be defined in the future. */ struct vfio_device_feature_migration { __aligned_u64 flags; #define VFIO_MIGRATION_STOP_COPY (1 << 0) #define VFIO_MIGRATION_P2P (1 << 1) +#define VFIO_MIGRATION_PRE_COPY (1 << 2) }; #define VFIO_DEVICE_FEATURE_MIGRATION 1 @@ -875,8 +883,13 @@ struct vfio_device_feature_mig_state { * RESUMING - The device is stopped and is loading a new internal state * ERROR - The device has failed and must be reset * - * And 1 optional state to support VFIO_MIGRATION_P2P: + * And optional states to support VFIO_MIGRATION_P2P: * RUNNING_P2P - RUNNING, except the device cannot do peer to peer DMA + * And VFIO_MIGRATION_PRE_COPY: + * PRE_COPY - The device is running normally but tracking internal state + * changes + * And VFIO_MIGRATION_P2P | VFIO_MIGRATION_PRE_COPY: + * PRE_COPY_P2P - PRE_COPY, except the device cannot do peer to peer DMA * * The FSM takes actions on the arcs between FSM states. The driver implements * the following behavior for the FSM arcs: @@ -908,20 +921,48 @@ struct vfio_device_feature_mig_state { * * To abort a RESUMING session the device must be reset. * + * PRE_COPY -> RUNNING * RUNNING_P2P -> RUNNING * While in RUNNING the device is fully operational, the device may generate * interrupts, DMA, respond to MMIO, all vfio device regions are functional, * and the device may advance its internal state. * + * The PRE_COPY arc will terminate a data transfer session. + * + * PRE_COPY_P2P -> RUNNING_P2P * RUNNING -> RUNNING_P2P * STOP -> RUNNING_P2P * While in RUNNING_P2P the device is partially running in the P2P quiescent * state defined below. * + * The PRE_COPY_P2P arc will terminate a data transfer session. + * + * RUNNING -> PRE_COPY + * RUNNING_P2P -> PRE_COPY_P2P * STOP -> STOP_COPY - * This arc begin the process of saving the device state and will return a - * new data_fd. + * PRE_COPY, PRE_COPY_P2P and STOP_COPY form the "saving group" of states + * which share a data transfer session. Moving between these states alters + * what is streamed in session, but does not terminate or otherwise affect + * the associated fd. + * + * These arcs begin the process of saving the device state and will return a + * new data_fd. The migration driver may perform actions such as enabling + * dirty logging of device state when entering PRE_COPY or PER_COPY_P2P. * + * Each arc does not change the device operation, the device remains + * RUNNING, P2P quiesced or in STOP. The STOP_COPY state is described below + * in PRE_COPY_P2P -> STOP_COPY. + * + * PRE_COPY -> PRE_COPY_P2P + * Entering PRE_COPY_P2P continues all the behaviors of PRE_COPY above. + * However, while in the PRE_COPY_P2P state, the device is partially running + * in the P2P quiescent state defined below, like RUNNING_P2P. + * + * PRE_COPY_P2P -> PRE_COPY + * This arc allows returning the device to a full RUNNING behavior while + * continuing all the behaviors of PRE_COPY. + * + * PRE_COPY_P2P -> STOP_COPY * While in the STOP_COPY state the device has the same behavior as STOP * with the addition that the data transfers session continues to stream the * migration state. End of stream on the FD indicates the entire device @@ -939,6 +980,13 @@ struct vfio_device_feature_mig_state { * device state for this arc if required to prepare the device to receive the * migration data. * + * STOP_COPY -> PRE_COPY + * STOP_COPY -> PRE_COPY_P2P + * These arcs are not permitted and return error if requested. Future + * revisions of this API may define behaviors for these arcs, in this case + * support will be discoverable by a new flag in + * VFIO_DEVICE_FEATURE_MIGRATION. + * * any -> ERROR * ERROR cannot be specified as a device state, however any transition request * can be failed with an errno return and may then move the device_state into @@ -950,7 +998,7 @@ struct vfio_device_feature_mig_state { * The optional peer to peer (P2P) quiescent state is intended to be a quiescent * state for the device for the purposes of managing multiple devices within a * user context where peer-to-peer DMA between devices may be active. The - * RUNNING_P2P states must prevent the device from initiating + * RUNNING_P2P and PRE_COPY_P2P states must prevent the device from initiating * any new P2P DMA transactions. If the device can identify P2P transactions * then it can stop only P2P DMA, otherwise it must stop all DMA. The migration * driver must complete any such outstanding operations prior to completing the @@ -963,6 +1011,8 @@ struct vfio_device_feature_mig_state { * above FSM arcs. As there are multiple paths through the FSM arcs the path * should be selected based on the following rules: * - Select the shortest path. + * - The path cannot have saving group states as interior arcs, only + * starting/end states. * Refer to vfio_mig_get_next_state() for the result of the algorithm. * * The automatic transit through the FSM arcs that make up the combination @@ -976,6 +1026,9 @@ struct vfio_device_feature_mig_state { * support them. The user can discover if these states are supported by using * VFIO_DEVICE_FEATURE_MIGRATION. By using combination transitions the user can * avoid knowing about these optional states if the kernel driver supports them. + * + * Arcs touching PRE_COPY and PRE_COPY_P2P are removed if support for PRE_COPY + * is not present. */ enum vfio_device_mig_state { VFIO_DEVICE_STATE_ERROR = 0, @@ -984,8 +1037,70 @@ enum vfio_device_mig_state { VFIO_DEVICE_STATE_STOP_COPY = 3, VFIO_DEVICE_STATE_RESUMING = 4, VFIO_DEVICE_STATE_RUNNING_P2P = 5, + VFIO_DEVICE_STATE_PRE_COPY = 6, + VFIO_DEVICE_STATE_PRE_COPY_P2P = 7, +}; + +/** + * VFIO_MIG_GET_PRECOPY_INFO - _IO(VFIO_TYPE, VFIO_BASE + 21) + * + * This ioctl is used on the migration data FD in the precopy phase of the + * migration data transfer. It returns an estimate of the current data sizes + * remaining to be transferred. It allows the user to judge when it is + * appropriate to leave PRE_COPY for STOP_COPY. + * + * This ioctl is valid only in PRE_COPY states and kernel driver should + * return -EINVAL from any other migration state. + * + * The vfio_precopy_info data structure returned by this ioctl provides + * estimates of data available from the device during the PRE_COPY states. + * This estimate is split into two categories, initial_bytes and + * dirty_bytes. + * + * The initial_bytes field indicates the amount of initial precopy + * data available from the device. This field should have a non-zero initial + * value and decrease as migration data is read from the device. + * It is recommended to leave PRE_COPY for STOP_COPY only after this field + * reaches zero. Leaving PRE_COPY earlier might make things slower. + * + * The dirty_bytes field tracks device state changes relative to data + * previously retrieved. This field starts at zero and may increase as + * the internal device state is modified or decrease as that modified + * state is read from the device. + * + * Userspace may use the combination of these fields to estimate the + * potential data size available during the PRE_COPY phases, as well as + * trends relative to the rate the device is dirtying its internal + * state, but these fields are not required to have any bearing relative + * to the data size available during the STOP_COPY phase. + * + * Drivers have a lot of flexibility in when and what they transfer during the + * PRE_COPY phase, and how they report this from VFIO_MIG_GET_PRECOPY_INFO. + * + * During pre-copy the migration data FD has a temporary "end of stream" that is + * reached when both initial_bytes and dirty_byte are zero. For instance, this + * may indicate that the device is idle and not currently dirtying any internal + * state. When read() is done on this temporary end of stream the kernel driver + * should return ENOMSG from read(). Userspace can wait for more data (which may + * never come) by using poll. + * + * Once in STOP_COPY the migration data FD has a permanent end of stream + * signaled in the usual way by read() always returning 0 and poll always + * returning readable. ENOMSG may not be returned in STOP_COPY. + * Support for this ioctl is mandatory if a driver claims to support + * VFIO_MIGRATION_PRE_COPY. + * + * Return: 0 on success, -1 and errno set on failure. + */ +struct vfio_precopy_info { + __u32 argsz; + __u32 flags; + __aligned_u64 initial_bytes; + __aligned_u64 dirty_bytes; }; +#define VFIO_MIG_GET_PRECOPY_INFO _IO(VFIO_TYPE, VFIO_BASE + 21) + /* * Upon VFIO_DEVICE_FEATURE_SET, allow the device to be moved into a low power * state with the platform-based power management. Device use of lower power -- cgit From 7fe898041fb0c8e630504ecc2cb8805651ac85c1 Mon Sep 17 00:00:00 2001 From: Dan Williams Date: Mon, 5 Dec 2022 20:22:44 -0800 Subject: cxl/security: Drop security command ioctl uapi CXL PMEM security operations are routed through the NVDIMM sysfs interface. For this reason the corresponding commands are marked "exclusive" to preclude collisions between the ioctl ABI and the sysfs ABI. However, a better way to preclude that collision is to simply remove the ioctl ABI (command-id definitions) for those operations. Now that cxl_internal_send_cmd() (formerly cxl_mbox_send_cmd()) no longer needs to talk the cxl_mem_commands array, all of the uapi definitions for the security commands can be dropped. These never appeared in a released kernel, so no regression risk. Reviewed-by: Dave Jiang Reviewed-by: Ira Weiny Link: https://lore.kernel.org/r/167030056464.4044561.11486507095384253833.stgit@dwillia2-xfh.jf.intel.com Signed-off-by: Dan Williams --- drivers/cxl/core/mbox.c | 17 ----------------- include/uapi/linux/cxl_mem.h | 6 ------ 2 files changed, 23 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c index c36a3589377a..b03fba212799 100644 --- a/drivers/cxl/core/mbox.c +++ b/drivers/cxl/core/mbox.c @@ -65,12 +65,6 @@ static struct cxl_mem_command cxl_mem_commands[CXL_MEM_COMMAND_ID_MAX] = { CXL_CMD(GET_SCAN_MEDIA_CAPS, 0x10, 0x4, 0), CXL_CMD(SCAN_MEDIA, 0x11, 0, 0), CXL_CMD(GET_SCAN_MEDIA, 0, CXL_VARIABLE_PAYLOAD, 0), - CXL_CMD(GET_SECURITY_STATE, 0, 0x4, 0), - CXL_CMD(SET_PASSPHRASE, 0x60, 0, 0), - CXL_CMD(DISABLE_PASSPHRASE, 0x40, 0, 0), - CXL_CMD(FREEZE_SECURITY, 0, 0, 0), - CXL_CMD(UNLOCK, 0x20, 0, 0), - CXL_CMD(PASSPHRASE_SECURE_ERASE, 0x40, 0, 0), }; /* @@ -717,17 +711,6 @@ int cxl_enumerate_cmds(struct cxl_dev_state *cxlds) /* Found the required CEL */ rc = 0; } - - /* - * Setup permanently kernel exclusive commands, i.e. the - * mechanism is driven through sysfs, keyctl, etc... - */ - set_bit(CXL_MEM_COMMAND_ID_SET_PASSPHRASE, cxlds->exclusive_cmds); - set_bit(CXL_MEM_COMMAND_ID_DISABLE_PASSPHRASE, cxlds->exclusive_cmds); - set_bit(CXL_MEM_COMMAND_ID_UNLOCK, cxlds->exclusive_cmds); - set_bit(CXL_MEM_COMMAND_ID_PASSPHRASE_SECURE_ERASE, - cxlds->exclusive_cmds); - out: kvfree(gsl); return rc; diff --git a/include/uapi/linux/cxl_mem.h b/include/uapi/linux/cxl_mem.h index 82bdad4ce5de..c71021a2a9ed 100644 --- a/include/uapi/linux/cxl_mem.h +++ b/include/uapi/linux/cxl_mem.h @@ -41,12 +41,6 @@ ___C(GET_SCAN_MEDIA_CAPS, "Get Scan Media Capabilities"), \ ___C(SCAN_MEDIA, "Scan Media"), \ ___C(GET_SCAN_MEDIA, "Get Scan Media Results"), \ - ___C(GET_SECURITY_STATE, "Get Security State"), \ - ___C(SET_PASSPHRASE, "Set Passphrase"), \ - ___C(DISABLE_PASSPHRASE, "Disable Passphrase"), \ - ___C(FREEZE_SECURITY, "Freeze Security"), \ - ___C(UNLOCK, "Unlock"), \ - ___C(PASSPHRASE_SECURE_ERASE, "Passphrase Secure Erase"), \ ___C(MAX, "invalid / last command") #define ___C(a, b) CXL_MEM_COMMAND_ID_##a -- cgit From 8478afa837c48f10dddb2e06714ffc667843781d Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 11 Sep 2022 14:10:59 +0200 Subject: headers: Remove some left-over license text in include/uapi/linux/dvb/ Remove some left-over from commit e2be04c7f995 ("License cleanup: add SPDX license identifier to uapi header files with a license") When the SPDX-License-Identifier tag has been added, the corresponding license text has not been removed. Remove it now. Signed-off-by: Christophe JAILLET Signed-off-by: Hans Verkuil --- include/uapi/linux/dvb/audio.h | 15 --------------- include/uapi/linux/dvb/ca.h | 15 --------------- include/uapi/linux/dvb/dmx.h | 15 --------------- include/uapi/linux/dvb/frontend.h | 15 --------------- include/uapi/linux/dvb/net.h | 15 --------------- include/uapi/linux/dvb/osd.h | 15 --------------- include/uapi/linux/dvb/version.h | 15 --------------- include/uapi/linux/dvb/video.h | 15 --------------- 8 files changed, 120 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/dvb/audio.h b/include/uapi/linux/dvb/audio.h index 2f869da69171..77fb866890b4 100644 --- a/include/uapi/linux/dvb/audio.h +++ b/include/uapi/linux/dvb/audio.h @@ -7,21 +7,6 @@ * Copyright (C) 2000 Ralph Metzler * & Marcus Metzler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Lesser Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _DVBAUDIO_H_ diff --git a/include/uapi/linux/dvb/ca.h b/include/uapi/linux/dvb/ca.h index dffa59e95ebb..4244b187cc4d 100644 --- a/include/uapi/linux/dvb/ca.h +++ b/include/uapi/linux/dvb/ca.h @@ -5,21 +5,6 @@ * Copyright (C) 2000 Ralph Metzler * & Marcus Metzler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Lesser Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _DVBCA_H_ diff --git a/include/uapi/linux/dvb/dmx.h b/include/uapi/linux/dvb/dmx.h index b4112f0b6dd3..7b16375f94e2 100644 --- a/include/uapi/linux/dvb/dmx.h +++ b/include/uapi/linux/dvb/dmx.h @@ -5,21 +5,6 @@ * Copyright (C) 2000 Marcus Metzler * & Ralph Metzler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _UAPI_DVBDMX_H_ diff --git a/include/uapi/linux/dvb/frontend.h b/include/uapi/linux/dvb/frontend.h index 4fed9e316147..53f4fb8043e3 100644 --- a/include/uapi/linux/dvb/frontend.h +++ b/include/uapi/linux/dvb/frontend.h @@ -7,21 +7,6 @@ * Holger Waechtler * Andre Draszik * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _DVBFRONTEND_H_ diff --git a/include/uapi/linux/dvb/net.h b/include/uapi/linux/dvb/net.h index 0c550ef93f2c..7cbb47ac38ef 100644 --- a/include/uapi/linux/dvb/net.h +++ b/include/uapi/linux/dvb/net.h @@ -5,21 +5,6 @@ * Copyright (C) 2000 Marcus Metzler * & Ralph Metzler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _DVBNET_H_ diff --git a/include/uapi/linux/dvb/osd.h b/include/uapi/linux/dvb/osd.h index 858997c74043..6003b108ba45 100644 --- a/include/uapi/linux/dvb/osd.h +++ b/include/uapi/linux/dvb/osd.h @@ -7,21 +7,6 @@ * Copyright (C) 2001 Ralph Metzler * & Marcus Metzler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Lesser Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _DVBOSD_H_ diff --git a/include/uapi/linux/dvb/version.h b/include/uapi/linux/dvb/version.h index 2c5cffe6d2a0..1a8cd038aa0b 100644 --- a/include/uapi/linux/dvb/version.h +++ b/include/uapi/linux/dvb/version.h @@ -4,21 +4,6 @@ * * Copyright (C) 2000 Holger Waechtler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _DVBVERSION_H_ diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h index 179f1ec60af6..9910b73737e0 100644 --- a/include/uapi/linux/dvb/video.h +++ b/include/uapi/linux/dvb/video.h @@ -7,21 +7,6 @@ * Copyright (C) 2000 Marcus Metzler * & Ralph Metzler * for convergence integrated media GmbH - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public License - * as published by the Free Software Foundation; either version 2.1 - * of the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. - * */ #ifndef _UAPI_DVBVIDEO_H_ -- cgit From 96c1212a61e089fcd10abe88f6a8f069f2ac1354 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 11 Sep 2022 17:13:14 +0200 Subject: headers: Remove some left-over license text in include/uapi/linux/v4l2-* Remove some left-over from commit e2be04c7f995 ("License cleanup: add SPDX license identifier to uapi header files with a license") When the SPDX-License-Identifier tag has been added, the corresponding license text has not been removed. Remove it now. Signed-off-by: Christophe JAILLET Signed-off-by: Hans Verkuil --- include/uapi/linux/v4l2-common.h | 39 ------------------------------------ include/uapi/linux/v4l2-controls.h | 38 ----------------------------------- include/uapi/linux/v4l2-dv-timings.h | 9 --------- include/uapi/linux/v4l2-mediabus.h | 4 ---- include/uapi/linux/v4l2-subdev.h | 13 ------------ 5 files changed, 103 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/v4l2-common.h b/include/uapi/linux/v4l2-common.h index 7d21c1634b4d..5a23a15d78ac 100644 --- a/include/uapi/linux/v4l2-common.h +++ b/include/uapi/linux/v4l2-common.h @@ -10,45 +10,6 @@ * * Copyright (C) 2012 Nokia Corporation * Contact: Sakari Ailus - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Alternatively you can redistribute this file under the terms of the - * BSD license as stated below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * 3. The names of its contributors may not be used to endorse or promote - * products derived from this software without specific prior written - * permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED - * TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR - * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * */ #ifndef __V4L2_COMMON__ diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 410d778c1243..b73a8ba7df6c 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -4,44 +4,6 @@ * * Copyright (C) 1999-2012 the contributors * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * Alternatively you can redistribute this file under the terms of the - * BSD license as stated below: - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * 3. The names of its contributors may not be used to endorse or promote - * products derived from this software without specific prior written - * permission. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED - * TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR - * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF - * LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING - * NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS - * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * * The contents of this header was split off from videodev2.h. All control * definitions should be added to this header, which is included by * videodev2.h. diff --git a/include/uapi/linux/v4l2-dv-timings.h b/include/uapi/linux/v4l2-dv-timings.h index b52b67c62562..ef0128c7369c 100644 --- a/include/uapi/linux/v4l2-dv-timings.h +++ b/include/uapi/linux/v4l2-dv-timings.h @@ -3,15 +3,6 @@ * V4L2 DV timings header. * * Copyright (C) 2012-2016 Hans Verkuil - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * version 2 as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ #ifndef _V4L2_DV_TIMINGS_H diff --git a/include/uapi/linux/v4l2-mediabus.h b/include/uapi/linux/v4l2-mediabus.h index 903e67b16711..6b07b73473b5 100644 --- a/include/uapi/linux/v4l2-mediabus.h +++ b/include/uapi/linux/v4l2-mediabus.h @@ -3,10 +3,6 @@ * Media Bus API header * * Copyright (C) 2009, Guennadi Liakhovetski - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. */ #ifndef __LINUX_V4L2_MEDIABUS_H diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h index 658106f5b5dc..ecce4c79f5c5 100644 --- a/include/uapi/linux/v4l2-subdev.h +++ b/include/uapi/linux/v4l2-subdev.h @@ -6,19 +6,6 @@ * * Contacts: Laurent Pinchart * Sakari Ailus - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA */ #ifndef __LINUX_V4L2_SUBDEV_H -- cgit From da65e9ff3bf614d2836e38e1d405c7073e6ba3b7 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Dec 2022 20:51:15 +0200 Subject: devlink: Expose port function commands to control RoCE Expose port function commands to enable / disable RoCE, this is used to control the port RoCE device capabilities. When RoCE is disabled for a function of the port, function cannot create any RoCE specific resources (e.g GID table). It also saves system memory utilization. For example disabling RoCE enable a VF/SF saves 1 Mbytes of system memory per function. Example of a PCI VF port which supports function configuration: Set RoCE of the VF's port function. $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 roce enable $ devlink port function set pci/0000:06:00.0/2 roce disable $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 roce disable Signed-off-by: Shay Drory Reviewed-by: Jiri Pirko Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 34 ++++++- include/net/devlink.h | 18 ++++ include/uapi/linux/devlink.h | 10 ++ net/core/devlink.c | 113 ++++++++++++++++++++++ 4 files changed, 174 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index 2c637f4aae8e..c3302d23e480 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -110,7 +110,7 @@ devlink ports for both the controllers. Function configuration ====================== -A user can configure the function attribute before enumerating the PCI +Users can configure one or more function attributes before enumerating the PCI function. Usually it means, user should configure function attribute before a bus specific device for the function is created. However, when SRIOV is enabled, virtual function devices are created on the PCI bus. @@ -122,6 +122,9 @@ A user may set the hardware address of the function using `devlink port function set hw_addr` command. For Ethernet port function this means a MAC address. +Users may also set the RoCE capability of the function using +`devlink port function set roce` command. + Function attributes =================== @@ -162,6 +165,35 @@ device created for the PCI VF/SF. function: hw_addr 00:00:00:00:88:88 +RoCE capability setup +--------------------- +Not all PCI VFs/SFs require RoCE capability. + +When RoCE capability is disabled, it saves system memory per PCI VF/SF. + +When user disables RoCE capability for a VF/SF, user application cannot send or +receive any RoCE packets through this VF/SF and RoCE GID table for this PCI +will be empty. + +When RoCE capability is disabled in the device using port function attribute, +VF/SF driver cannot override it. + +- Get RoCE capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 roce enable + +- Set RoCE capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 roce disable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 roce disable + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index 5f6eca5e4a40..ce4c65d2f2e7 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1451,6 +1451,24 @@ struct devlink_ops { int (*port_function_hw_addr_set)(struct devlink_port *port, const u8 *hw_addr, int hw_addr_len, struct netlink_ext_ack *extack); + /** + * @port_fn_roce_get: Port function's roce get function. + * + * Query RoCE state of a function managed by the devlink port. + * Return -EOPNOTSUPP if port function RoCE handling is not supported. + */ + int (*port_fn_roce_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + /** + * @port_fn_roce_set: Port function's roce set function. + * + * Enable/Disable the RoCE state of a function managed by the devlink + * port. + * Return -EOPNOTSUPP if port function RoCE handling is not supported. + */ + int (*port_fn_roce_set)(struct devlink_port *devlink_port, + bool enable, struct netlink_ext_ack *extack); /** * port_new() - Add a new port function of a specified flavor * @devlink: Devlink instance diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 70191d96af89..6cc2925bd478 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -658,11 +658,21 @@ enum devlink_resource_unit { DEVLINK_RESOURCE_UNIT_ENTRY, }; +enum devlink_port_fn_attr_cap { + DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, + + /* Add new caps above */ + __DEVLINK_PORT_FN_ATTR_CAPS_MAX, +}; + +#define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT) + enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR, /* binary */ DEVLINK_PORT_FN_ATTR_STATE, /* u8 */ DEVLINK_PORT_FN_ATTR_OPSTATE, /* u8 */ + DEVLINK_PORT_FN_ATTR_CAPS, /* bitfield32 */ __DEVLINK_PORT_FUNCTION_ATTR_MAX, DEVLINK_PORT_FUNCTION_ATTR_MAX = __DEVLINK_PORT_FUNCTION_ATTR_MAX - 1 diff --git a/net/core/devlink.c b/net/core/devlink.c index 035249c5dd17..8c0ad52431c5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -195,11 +195,16 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); +#define DEVLINK_PORT_FN_CAPS_VALID_MASK \ + (_BITUL(__DEVLINK_PORT_FN_ATTR_CAPS_MAX) - 1) + static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, [DEVLINK_PORT_FN_ATTR_STATE] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_PORT_FN_STATE_INACTIVE, DEVLINK_PORT_FN_STATE_ACTIVE), + [DEVLINK_PORT_FN_ATTR_CAPS] = + NLA_POLICY_BITFIELD32(DEVLINK_PORT_FN_CAPS_VALID_MASK), }; static const struct nla_policy devlink_selftest_nl_policy[DEVLINK_ATTR_SELFTEST_ID_MAX + 1] = { @@ -680,6 +685,60 @@ devlink_sb_tc_index_get_from_attrs(struct devlink_sb *devlink_sb, return 0; } +static void devlink_port_fn_cap_fill(struct nla_bitfield32 *caps, + u32 cap, bool is_enable) +{ + caps->selector |= cap; + if (is_enable) + caps->value |= cap; +} + +static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!ops->port_fn_roce_get) + return 0; + + err = ops->port_fn_roce_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_ROCE, is_enable); + return 0; +} + +static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct sk_buff *msg, + struct netlink_ext_ack *extack, + bool *msg_updated) +{ + struct nla_bitfield32 caps = {}; + int err; + + err = devlink_port_fn_roce_fill(ops, devlink_port, &caps, extack); + if (err) + return err; + + if (!caps.selector) + return 0; + err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, + caps.selector); + if (err) + return err; + + *msg_updated = true; + return 0; +} + static int devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, struct genl_info *info, @@ -1263,6 +1322,35 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops, return 0; } +static int +devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + return ops->port_fn_roce_set(devlink_port, enable, extack); +} + +static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, + const struct nlattr *attr, + struct netlink_ext_ack *extack) +{ + struct nla_bitfield32 caps; + u32 caps_value; + int err; + + caps = nla_get_bitfield32(attr); + caps_value = caps.value & caps.selector; + if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE) { + err = devlink_port_fn_roce_set(devlink_port, + caps_value & DEVLINK_PORT_FN_CAP_ROCE, + extack); + if (err) + return err; + } + return 0; +} + static int devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *port, struct netlink_ext_ack *extack) @@ -1281,6 +1369,10 @@ devlink_nl_port_function_attrs_put(struct sk_buff *msg, struct devlink_port *por &msg_updated); if (err) goto out; + err = devlink_port_fn_caps_fill(ops, port, msg, extack, + &msg_updated); + if (err) + goto out; err = devlink_port_fn_state_fill(ops, port, msg, extack, &msg_updated); out: if (err || !msg_updated) @@ -1653,6 +1745,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, struct netlink_ext_ack *extack) { const struct devlink_ops *ops = devlink_port->devlink->ops; + struct nlattr *attr; if (tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] && !ops->port_function_hw_addr_set) { @@ -1665,6 +1758,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, "Function does not support state setting"); return -EOPNOTSUPP; } + attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; + if (attr) { + struct nla_bitfield32 caps; + + caps = nla_get_bitfield32(attr); + if (caps.selector & DEVLINK_PORT_FN_CAP_ROCE && + !ops->port_fn_roce_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support RoCE function attribute"); + return -EOPNOTSUPP; + } + } return 0; } @@ -1692,6 +1797,14 @@ static int devlink_port_function_set(struct devlink_port *port, if (err) return err; } + + attr = tb[DEVLINK_PORT_FN_ATTR_CAPS]; + if (attr) { + err = devlink_port_fn_caps_set(port, attr, extack); + if (err) + return err; + } + /* Keep this as the last function attribute set, so that when * multiple port function attributes are set along with state, * Those can be applied first before activating the state. -- cgit From a8ce7b26a51efc4d7753b23d639ae092878a6193 Mon Sep 17 00:00:00 2001 From: Shay Drory Date: Tue, 6 Dec 2022 20:51:18 +0200 Subject: devlink: Expose port function commands to control migratable Expose port function commands to enable / disable migratable capability, this is used to set the port function as migratable. Live migration is the process of transferring a live virtual machine from one physical host to another without disrupting its normal operation. In order for a VM to be able to perform LM, all the VM components must be able to perform migration. e.g.: to be migratable. In order for VF to be migratable, VF must be bound to VFIO driver with migration support. When migratable capability is enabled for a function of the port, the device is making the necessary preparations for the function to be migratable, which might include disabling features which cannot be migrated. Example of LM with migratable function configuration: Set migratable of the VF's port function. $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 migratable disable $ devlink port function set pci/0000:06:00.0/2 migratable enable $ devlink port show pci/0000:06:00.0/2 pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 function: hw_addr 00:00:00:00:00:00 migratable enable Bind VF to VFIO driver with migration support: $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/unbind $ echo mlx5_vfio_pci > /sys/bus/pci/devices/0000:08:00.0/driver_override $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/bind Attach VF to the VM. Start the VM. Perform LM. Signed-off-by: Shay Drory Reviewed-by: Jiri Pirko Acked-by: Shannon Nelson Signed-off-by: Jakub Kicinski --- Documentation/networking/devlink/devlink-port.rst | 46 +++++++++++++++++++ include/net/devlink.h | 21 +++++++++ include/uapi/linux/devlink.h | 3 ++ net/core/devlink.c | 55 +++++++++++++++++++++++ 4 files changed, 125 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-port.rst b/Documentation/networking/devlink/devlink-port.rst index c3302d23e480..3da590953ce8 100644 --- a/Documentation/networking/devlink/devlink-port.rst +++ b/Documentation/networking/devlink/devlink-port.rst @@ -125,6 +125,9 @@ this means a MAC address. Users may also set the RoCE capability of the function using `devlink port function set roce` command. +Users may also set the function as migratable using +'devlink port function set migratable' command. + Function attributes =================== @@ -194,6 +197,49 @@ VF/SF driver cannot override it. function: hw_addr 00:00:00:00:00:00 roce disable +migratable capability setup +--------------------------- +Live migration is the process of transferring a live virtual machine +from one physical host to another without disrupting its normal +operation. + +User who want PCI VFs to be able to perform live migration need to +explicitly enable the VF migratable capability. + +When user enables migratable capability for a VF, and the HV binds the VF to VFIO driver +with migration support, the user can migrate the VM with this VF from one HV to a +different one. + +However, when migratable capability is enable, device will disable features which cannot +be migrated. Thus migratable cap can impose limitations on a VF so let the user decide. + +Example of LM with migratable function configuration: +- Get migratable capability of the VF device:: + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 migratable disable + +- Set migratable capability of the VF device:: + + $ devlink port function set pci/0000:06:00.0/2 migratable enable + + $ devlink port show pci/0000:06:00.0/2 + pci/0000:06:00.0/2: type eth netdev enp6s0pf0vf1 flavour pcivf pfnum 0 vfnum 1 + function: + hw_addr 00:00:00:00:00:00 migratable enable + +- Bind VF to VFIO driver with migration support:: + + $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/unbind + $ echo mlx5_vfio_pci > /sys/bus/pci/devices/0000:08:00.0/driver_override + $ echo > /sys/bus/pci/devices/0000:08:00.0/driver/bind + +Attach VF to the VM. +Start the VM. +Perform live migration. + Subfunction ============ diff --git a/include/net/devlink.h b/include/net/devlink.h index ce4c65d2f2e7..0f376a28b9c4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -1469,6 +1469,27 @@ struct devlink_ops { */ int (*port_fn_roce_set)(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack); + /** + * @port_fn_migratable_get: Port function's migratable get function. + * + * Query migratable state of a function managed by the devlink port. + * Return -EOPNOTSUPP if port function migratable handling is not + * supported. + */ + int (*port_fn_migratable_get)(struct devlink_port *devlink_port, + bool *is_enable, + struct netlink_ext_ack *extack); + /** + * @port_fn_migratable_set: Port function's migratable set function. + * + * Enable/Disable migratable state of a function managed by the devlink + * port. + * Return -EOPNOTSUPP if port function migratable handling is not + * supported. + */ + int (*port_fn_migratable_set)(struct devlink_port *devlink_port, + bool enable, + struct netlink_ext_ack *extack); /** * port_new() - Add a new port function of a specified flavor * @devlink: Devlink instance diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 6cc2925bd478..3782d4219ac9 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -660,12 +660,15 @@ enum devlink_resource_unit { enum devlink_port_fn_attr_cap { DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT, + DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT, /* Add new caps above */ __DEVLINK_PORT_FN_ATTR_CAPS_MAX, }; #define DEVLINK_PORT_FN_CAP_ROCE _BITUL(DEVLINK_PORT_FN_ATTR_CAP_ROCE_BIT) +#define DEVLINK_PORT_FN_CAP_MIGRATABLE \ + _BITUL(DEVLINK_PORT_FN_ATTR_CAP_MIGRATABLE_BIT) enum devlink_port_function_attr { DEVLINK_PORT_FUNCTION_ATTR_UNSPEC, diff --git a/net/core/devlink.c b/net/core/devlink.c index 8c0ad52431c5..ab40ebcb4aea 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -715,6 +715,29 @@ static int devlink_port_fn_roce_fill(const struct devlink_ops *ops, return 0; } +static int devlink_port_fn_migratable_fill(const struct devlink_ops *ops, + struct devlink_port *devlink_port, + struct nla_bitfield32 *caps, + struct netlink_ext_ack *extack) +{ + bool is_enable; + int err; + + if (!ops->port_fn_migratable_get || + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) + return 0; + + err = ops->port_fn_migratable_get(devlink_port, &is_enable, extack); + if (err) { + if (err == -EOPNOTSUPP) + return 0; + return err; + } + + devlink_port_fn_cap_fill(caps, DEVLINK_PORT_FN_CAP_MIGRATABLE, is_enable); + return 0; +} + static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, struct devlink_port *devlink_port, struct sk_buff *msg, @@ -728,6 +751,10 @@ static int devlink_port_fn_caps_fill(const struct devlink_ops *ops, if (err) return err; + err = devlink_port_fn_migratable_fill(ops, devlink_port, &caps, extack); + if (err) + return err; + if (!caps.selector) return 0; err = nla_put_bitfield32(msg, DEVLINK_PORT_FN_ATTR_CAPS, caps.value, @@ -1322,6 +1349,15 @@ static int devlink_port_fn_state_fill(const struct devlink_ops *ops, return 0; } +static int +devlink_port_fn_mig_set(struct devlink_port *devlink_port, bool enable, + struct netlink_ext_ack *extack) +{ + const struct devlink_ops *ops = devlink_port->devlink->ops; + + return ops->port_fn_migratable_set(devlink_port, enable, extack); +} + static int devlink_port_fn_roce_set(struct devlink_port *devlink_port, bool enable, struct netlink_ext_ack *extack) @@ -1348,6 +1384,13 @@ static int devlink_port_fn_caps_set(struct devlink_port *devlink_port, if (err) return err; } + if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { + err = devlink_port_fn_mig_set(devlink_port, caps_value & + DEVLINK_PORT_FN_CAP_MIGRATABLE, + extack); + if (err) + return err; + } return 0; } @@ -1769,6 +1812,18 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port, "Port doesn't support RoCE function attribute"); return -EOPNOTSUPP; } + if (caps.selector & DEVLINK_PORT_FN_CAP_MIGRATABLE) { + if (!ops->port_fn_migratable_set) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "Port doesn't support migratable function attribute"); + return -EOPNOTSUPP; + } + if (devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_PCI_VF) { + NL_SET_ERR_MSG_ATTR(extack, attr, + "migratable function attribute supported for VFs only"); + return -EOPNOTSUPP; + } + } } return 0; } -- cgit From 81c25247a2a03a0f97e4805d7aff7541ccff6baa Mon Sep 17 00:00:00 2001 From: Daniel Scally Date: Tue, 6 Dec 2022 16:12:03 +0000 Subject: usb: gadget: uvc: Rename bmInterfaceFlags -> bmInterlaceFlags In the specification documents for the Uncompressed and MJPEG USB Video Payloads, the field name is bmInterlaceFlags - it has been misnamed within the kernel. Although renaming the field does break the kernel's interface to userspace it should be low-risk in this instance. The field is read only and hardcoded to 0, so there was never any value in anyone reading it. A search of the uvc-gadget application and all the forks that I could find for it did not reveal any users either. Fixes: cdda479f15cd ("USB gadget: video class function driver") Reviewed-by: Laurent Pinchart Reviewed-by: Kieran Bingham Signed-off-by: Daniel Scally Link: https://lore.kernel.org/r/20221206161203.1562827-1-dan.scally@ideasonboard.com Signed-off-by: Greg Kroah-Hartman --- Documentation/ABI/testing/configfs-usb-gadget-uvc | 4 ++-- drivers/usb/gadget/function/uvc_configfs.c | 12 ++++++------ drivers/usb/gadget/legacy/webcam.c | 4 ++-- include/uapi/linux/usb/video.h | 4 ++-- 4 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/ABI/testing/configfs-usb-gadget-uvc b/Documentation/ABI/testing/configfs-usb-gadget-uvc index 611b23e6488d..f00cff6d8c5c 100644 --- a/Documentation/ABI/testing/configfs-usb-gadget-uvc +++ b/Documentation/ABI/testing/configfs-usb-gadget-uvc @@ -197,7 +197,7 @@ Description: Specific MJPEG format descriptors read-only bmaControls this format's data for bmaControls in the streaming header - bmInterfaceFlags specifies interlace information, + bmInterlaceFlags specifies interlace information, read-only bAspectRatioY the X dimension of the picture aspect ratio, read-only @@ -253,7 +253,7 @@ Description: Specific uncompressed format descriptors read-only bmaControls this format's data for bmaControls in the streaming header - bmInterfaceFlags specifies interlace information, + bmInterlaceFlags specifies interlace information, read-only bAspectRatioY the X dimension of the picture aspect ratio, read-only diff --git a/drivers/usb/gadget/function/uvc_configfs.c b/drivers/usb/gadget/function/uvc_configfs.c index 4303a3283ba0..76cb60d13049 100644 --- a/drivers/usb/gadget/function/uvc_configfs.c +++ b/drivers/usb/gadget/function/uvc_configfs.c @@ -1512,7 +1512,7 @@ UVCG_UNCOMPRESSED_ATTR(b_bits_per_pixel, bBitsPerPixel, 8); UVCG_UNCOMPRESSED_ATTR(b_default_frame_index, bDefaultFrameIndex, 8); UVCG_UNCOMPRESSED_ATTR_RO(b_aspect_ratio_x, bAspectRatioX, 8); UVCG_UNCOMPRESSED_ATTR_RO(b_aspect_ratio_y, bAspectRatioY, 8); -UVCG_UNCOMPRESSED_ATTR_RO(bm_interface_flags, bmInterfaceFlags, 8); +UVCG_UNCOMPRESSED_ATTR_RO(bm_interlace_flags, bmInterlaceFlags, 8); #undef UVCG_UNCOMPRESSED_ATTR #undef UVCG_UNCOMPRESSED_ATTR_RO @@ -1541,7 +1541,7 @@ static struct configfs_attribute *uvcg_uncompressed_attrs[] = { &uvcg_uncompressed_attr_b_default_frame_index, &uvcg_uncompressed_attr_b_aspect_ratio_x, &uvcg_uncompressed_attr_b_aspect_ratio_y, - &uvcg_uncompressed_attr_bm_interface_flags, + &uvcg_uncompressed_attr_bm_interlace_flags, &uvcg_uncompressed_attr_bma_controls, NULL, }; @@ -1574,7 +1574,7 @@ static struct config_group *uvcg_uncompressed_make(struct config_group *group, h->desc.bDefaultFrameIndex = 1; h->desc.bAspectRatioX = 0; h->desc.bAspectRatioY = 0; - h->desc.bmInterfaceFlags = 0; + h->desc.bmInterlaceFlags = 0; h->desc.bCopyProtect = 0; INIT_LIST_HEAD(&h->fmt.frames); @@ -1700,7 +1700,7 @@ UVCG_MJPEG_ATTR(b_default_frame_index, bDefaultFrameIndex, 8); UVCG_MJPEG_ATTR_RO(bm_flags, bmFlags, 8); UVCG_MJPEG_ATTR_RO(b_aspect_ratio_x, bAspectRatioX, 8); UVCG_MJPEG_ATTR_RO(b_aspect_ratio_y, bAspectRatioY, 8); -UVCG_MJPEG_ATTR_RO(bm_interface_flags, bmInterfaceFlags, 8); +UVCG_MJPEG_ATTR_RO(bm_interlace_flags, bmInterlaceFlags, 8); #undef UVCG_MJPEG_ATTR #undef UVCG_MJPEG_ATTR_RO @@ -1728,7 +1728,7 @@ static struct configfs_attribute *uvcg_mjpeg_attrs[] = { &uvcg_mjpeg_attr_bm_flags, &uvcg_mjpeg_attr_b_aspect_ratio_x, &uvcg_mjpeg_attr_b_aspect_ratio_y, - &uvcg_mjpeg_attr_bm_interface_flags, + &uvcg_mjpeg_attr_bm_interlace_flags, &uvcg_mjpeg_attr_bma_controls, NULL, }; @@ -1755,7 +1755,7 @@ static struct config_group *uvcg_mjpeg_make(struct config_group *group, h->desc.bDefaultFrameIndex = 1; h->desc.bAspectRatioX = 0; h->desc.bAspectRatioY = 0; - h->desc.bmInterfaceFlags = 0; + h->desc.bmInterlaceFlags = 0; h->desc.bCopyProtect = 0; INIT_LIST_HEAD(&h->fmt.frames); diff --git a/drivers/usb/gadget/legacy/webcam.c b/drivers/usb/gadget/legacy/webcam.c index 94e22867da1d..53e38f87472b 100644 --- a/drivers/usb/gadget/legacy/webcam.c +++ b/drivers/usb/gadget/legacy/webcam.c @@ -171,7 +171,7 @@ static const struct uvc_format_uncompressed uvc_format_yuv = { .bDefaultFrameIndex = 1, .bAspectRatioX = 0, .bAspectRatioY = 0, - .bmInterfaceFlags = 0, + .bmInterlaceFlags = 0, .bCopyProtect = 0, }; @@ -222,7 +222,7 @@ static const struct uvc_format_mjpeg uvc_format_mjpg = { .bDefaultFrameIndex = 1, .bAspectRatioX = 0, .bAspectRatioY = 0, - .bmInterfaceFlags = 0, + .bmInterlaceFlags = 0, .bCopyProtect = 0, }; diff --git a/include/uapi/linux/usb/video.h b/include/uapi/linux/usb/video.h index bfdae12cdacf..6e8e572c2980 100644 --- a/include/uapi/linux/usb/video.h +++ b/include/uapi/linux/usb/video.h @@ -466,7 +466,7 @@ struct uvc_format_uncompressed { __u8 bDefaultFrameIndex; __u8 bAspectRatioX; __u8 bAspectRatioY; - __u8 bmInterfaceFlags; + __u8 bmInterlaceFlags; __u8 bCopyProtect; } __attribute__((__packed__)); @@ -522,7 +522,7 @@ struct uvc_format_mjpeg { __u8 bDefaultFrameIndex; __u8 bAspectRatioX; __u8 bAspectRatioY; - __u8 bmInterfaceFlags; + __u8 bmInterlaceFlags; __u8 bCopyProtect; } __attribute__((__packed__)); -- cgit From c1f480b2d092960ecf8bb0bd1f27982c33ada42a Mon Sep 17 00:00:00 2001 From: Luca Boccassi Date: Tue, 6 Dec 2022 09:29:13 +0000 Subject: sed-opal: allow using IOC_OPAL_SAVE for locking too MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Usually when closing a crypto device (eg: dm-crypt with LUKS) the volume key is not required, as it requires root privileges anyway, and root can deny access to a disk in many ways regardless. Requiring the volume key to lock the device is a peculiarity of the OPAL specification. Given we might already have saved the key if the user requested it via the 'IOC_OPAL_SAVE' ioctl, we can use that key to lock the device if no key was provided here and the locking range matches, and the user sets the appropriate flag with 'IOC_OPAL_SAVE'. This allows integrating OPAL with tools and libraries that are used to the common behaviour and do not ask for the volume key when closing a device. Callers can always pass a non-zero key and it will be used regardless, as before. Suggested-by: Štěpán Horáček Signed-off-by: Luca Boccassi Reviewed-by: Christoph Hellwig Reviewed-by: Christian Brauner Link: https://lore.kernel.org/r/20221206092913.4625-1-luca.boccassi@gmail.com Signed-off-by: Jens Axboe --- block/sed-opal.c | 39 +++++++++++++++++++++++++++++++++++++++ include/uapi/linux/sed-opal.h | 8 +++++++- 2 files changed, 46 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/block/sed-opal.c b/block/sed-opal.c index 2c5327a0543a..1f926c0973f9 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -2437,6 +2437,44 @@ static int __opal_set_mbr_done(struct opal_dev *dev, struct opal_key *key) return execute_steps(dev, mbrdone_step, ARRAY_SIZE(mbrdone_step)); } +static void opal_lock_check_for_saved_key(struct opal_dev *dev, + struct opal_lock_unlock *lk_unlk) +{ + struct opal_suspend_data *iter; + + if (lk_unlk->l_state != OPAL_LK || + lk_unlk->session.opal_key.key_len > 0) + return; + + /* + * Usually when closing a crypto device (eg: dm-crypt with LUKS) the + * volume key is not required, as it requires root privileges anyway, + * and root can deny access to a disk in many ways regardless. + * Requiring the volume key to lock the device is a peculiarity of the + * OPAL specification. Given we might already have saved the key if + * the user requested it via the 'IOC_OPAL_SAVE' ioctl, we can use + * that key to lock the device if no key was provided here, the + * locking range matches and the appropriate flag was passed with + * 'IOC_OPAL_SAVE'. + * This allows integrating OPAL with tools and libraries that are used + * to the common behaviour and do not ask for the volume key when + * closing a device. + */ + setup_opal_dev(dev); + list_for_each_entry(iter, &dev->unlk_lst, node) { + if ((iter->unlk.flags & OPAL_SAVE_FOR_LOCK) && + iter->lr == lk_unlk->session.opal_key.lr && + iter->unlk.session.opal_key.key_len > 0) { + lk_unlk->session.opal_key.key_len = + iter->unlk.session.opal_key.key_len; + memcpy(lk_unlk->session.opal_key.key, + iter->unlk.session.opal_key.key, + iter->unlk.session.opal_key.key_len); + break; + } + } +} + static int opal_lock_unlock(struct opal_dev *dev, struct opal_lock_unlock *lk_unlk) { @@ -2446,6 +2484,7 @@ static int opal_lock_unlock(struct opal_dev *dev, return -EINVAL; mutex_lock(&dev->dev_lock); + opal_lock_check_for_saved_key(dev, lk_unlk); ret = __opal_lock_unlock(dev, lk_unlk); mutex_unlock(&dev->dev_lock); diff --git a/include/uapi/linux/sed-opal.h b/include/uapi/linux/sed-opal.h index 2573772e2fb3..1fed3c9294fc 100644 --- a/include/uapi/linux/sed-opal.h +++ b/include/uapi/linux/sed-opal.h @@ -44,6 +44,11 @@ enum opal_lock_state { OPAL_LK = 0x04, /* 0100 */ }; +enum opal_lock_flags { + /* IOC_OPAL_SAVE will also store the provided key for locking */ + OPAL_SAVE_FOR_LOCK = 0x01, +}; + struct opal_key { __u8 lr; __u8 key_len; @@ -76,7 +81,8 @@ struct opal_user_lr_setup { struct opal_lock_unlock { struct opal_session_info session; __u32 l_state; - __u8 __align[4]; + __u16 flags; + __u8 __align[2]; }; struct opal_new_pw { -- cgit From 270605317366e4535d8d9fc3d9da1ad0fb3c9d45 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 8 Dec 2022 02:11:37 +0530 Subject: bpf: Rework process_dynptr_func Recently, user ringbuf support introduced a PTR_TO_DYNPTR register type for use in callback state, because in case of user ringbuf helpers, there is no dynptr on the stack that is passed into the callback. To reflect such a state, a special register type was created. However, some checks have been bypassed incorrectly during the addition of this feature. First, for arg_type with MEM_UNINIT flag which initialize a dynptr, they must be rejected for such register type. Secondly, in the future, there are plans to add dynptr helpers that operate on the dynptr itself and may change its offset and other properties. In all of these cases, PTR_TO_DYNPTR shouldn't be allowed to be passed to such helpers, however the current code simply returns 0. The rejection for helpers that release the dynptr is already handled. For fixing this, we take a step back and rework existing code in a way that will allow fitting in all classes of helpers and have a coherent model for dealing with the variety of use cases in which dynptr is used. First, for ARG_PTR_TO_DYNPTR, it can either be set alone or together with a DYNPTR_TYPE_* constant that denotes the only type it accepts. Next, helpers which initialize a dynptr use MEM_UNINIT to indicate this fact. To make the distinction clear, use MEM_RDONLY flag to indicate that the helper only operates on the memory pointed to by the dynptr, not the dynptr itself. In C parlance, it would be equivalent to taking the dynptr as a point to const argument. When either of these flags are not present, the helper is allowed to mutate both the dynptr itself and also the memory it points to. Currently, the read only status of the memory is not tracked in the dynptr, but it would be trivial to add this support inside dynptr state of the register. With these changes and renaming PTR_TO_DYNPTR to CONST_PTR_TO_DYNPTR to better reflect its usage, it can no longer be passed to helpers that initialize a dynptr, i.e. bpf_dynptr_from_mem, bpf_ringbuf_reserve_dynptr. A note to reviewers is that in code that does mark_stack_slots_dynptr, and unmark_stack_slots_dynptr, we implicitly rely on the fact that PTR_TO_STACK reg is the only case that can reach that code path, as one cannot pass CONST_PTR_TO_DYNPTR to helpers that don't set MEM_RDONLY. In both cases such helpers won't be setting that flag. The next patch will add a couple of selftest cases to make sure this doesn't break. Fixes: 205715673844 ("bpf: Add bpf_user_ringbuf_drain() helper") Acked-by: Joanne Koong Signed-off-by: Kumar Kartikeya Dwivedi Link: https://lore.kernel.org/r/20221207204141.308952-4-memxor@gmail.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf.h | 4 +- include/uapi/linux/bpf.h | 8 +- kernel/bpf/helpers.c | 18 +- kernel/bpf/verifier.c | 227 +++++++++++++++------ scripts/bpf_doc.py | 1 + tools/include/uapi/linux/bpf.h | 8 +- .../selftests/bpf/prog_tests/user_ringbuf.c | 4 +- 7 files changed, 191 insertions(+), 79 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 4920ac252754..3de24cfb7a3d 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -775,7 +775,7 @@ enum bpf_reg_type { PTR_TO_MEM, /* reg points to valid memory region */ PTR_TO_BUF, /* reg points to a read/write buffer */ PTR_TO_FUNC, /* reg points to a bpf program function */ - PTR_TO_DYNPTR, /* reg points to a dynptr */ + CONST_PTR_TO_DYNPTR, /* reg points to a const struct bpf_dynptr */ __BPF_REG_TYPE_MAX, /* Extended reg_types. */ @@ -2828,7 +2828,7 @@ 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); int bpf_dynptr_check_size(u32 size); -u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr); +u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr); #ifdef CONFIG_BPF_LSM void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index f89de51a45db..464ca3f01fe7 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5293,7 +5293,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5303,7 +5303,7 @@ union bpf_attr { * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5313,7 +5313,7 @@ union bpf_attr { * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* * is a read-only dynptr or if *flags* is not 0. * - * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) * Description * Get a pointer to the underlying dynptr data. * @@ -5414,7 +5414,7 @@ union bpf_attr { * Drain samples from the specified user ring buffer, and invoke * the provided callback for each such sample: * - * long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx); + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); * * If **callback_fn** returns 0, the helper will continue to try * and drain the next sample, up to a maximum of diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 6ed5875b97a3..fa1093d4ad6b 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1404,7 +1404,7 @@ static const struct bpf_func_proto bpf_kptr_xchg_proto = { #define DYNPTR_SIZE_MASK 0xFFFFFF #define DYNPTR_RDONLY_BIT BIT(31) -static bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr) +static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_RDONLY_BIT; } @@ -1414,7 +1414,7 @@ static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_typ ptr->size |= type << DYNPTR_TYPE_SHIFT; } -u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr) +u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr) { return ptr->size & DYNPTR_SIZE_MASK; } @@ -1438,7 +1438,7 @@ void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr) memset(ptr, 0, sizeof(*ptr)); } -static int bpf_dynptr_check_off_len(struct bpf_dynptr_kern *ptr, u32 offset, u32 len) +static int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u32 offset, u32 len) { u32 size = bpf_dynptr_get_size(ptr); @@ -1483,7 +1483,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = { .arg4_type = ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT, }; -BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, +BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src, u32, offset, u64, flags) { int err; @@ -1506,12 +1506,12 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = { .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_UNINIT_MEM, .arg2_type = ARG_CONST_SIZE_OR_ZERO, - .arg3_type = ARG_PTR_TO_DYNPTR, + .arg3_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, .arg4_type = ARG_ANYTHING, .arg5_type = ARG_ANYTHING, }; -BPF_CALL_5(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, +BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len, u64, flags) { int err; @@ -1532,14 +1532,14 @@ static const struct bpf_func_proto bpf_dynptr_write_proto = { .func = bpf_dynptr_write, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_DYNPTR, + .arg1_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_PTR_TO_MEM | MEM_RDONLY, .arg4_type = ARG_CONST_SIZE_OR_ZERO, .arg5_type = ARG_ANYTHING, }; -BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) +BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len) { int err; @@ -1560,7 +1560,7 @@ static const struct bpf_func_proto bpf_dynptr_data_proto = { .func = bpf_dynptr_data, .gpl_only = false, .ret_type = RET_PTR_TO_DYNPTR_MEM_OR_NULL, - .arg1_type = ARG_PTR_TO_DYNPTR, + .arg1_type = ARG_PTR_TO_DYNPTR | MEM_RDONLY, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_CONST_ALLOC_SIZE_OR_ZERO, }; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index eb742ac75844..a880776bd999 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -592,7 +592,7 @@ static const char *reg_type_str(struct bpf_verifier_env *env, [PTR_TO_BUF] = "buf", [PTR_TO_FUNC] = "func", [PTR_TO_MAP_KEY] = "map_key", - [PTR_TO_DYNPTR] = "dynptr_ptr", + [CONST_PTR_TO_DYNPTR] = "dynptr_ptr", }; if (type & PTR_MAYBE_NULL) { @@ -725,6 +725,28 @@ static bool dynptr_type_refcounted(enum bpf_dynptr_type type) return type == BPF_DYNPTR_TYPE_RINGBUF; } +static void __mark_dynptr_reg(struct bpf_reg_state *reg, + enum bpf_dynptr_type type, + bool first_slot); + +static void __mark_reg_not_init(const struct bpf_verifier_env *env, + struct bpf_reg_state *reg); + +static void mark_dynptr_stack_regs(struct bpf_reg_state *sreg1, + struct bpf_reg_state *sreg2, + enum bpf_dynptr_type type) +{ + __mark_dynptr_reg(sreg1, type, true); + __mark_dynptr_reg(sreg2, type, false); +} + +static void mark_dynptr_cb_reg(struct bpf_reg_state *reg, + enum bpf_dynptr_type type) +{ + __mark_dynptr_reg(reg, type, true); +} + + static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg, enum bpf_arg_type arg_type, int insn_idx) { @@ -746,9 +768,8 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (type == BPF_DYNPTR_TYPE_INVALID) return -EINVAL; - state->stack[spi].spilled_ptr.dynptr.first_slot = true; - state->stack[spi].spilled_ptr.dynptr.type = type; - state->stack[spi - 1].spilled_ptr.dynptr.type = type; + mark_dynptr_stack_regs(&state->stack[spi].spilled_ptr, + &state->stack[spi - 1].spilled_ptr, type); if (dynptr_type_refcounted(type)) { /* The id is used to track proper releasing */ @@ -756,8 +777,8 @@ static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_ if (id < 0) return id; - state->stack[spi].spilled_ptr.id = id; - state->stack[spi - 1].spilled_ptr.id = id; + state->stack[spi].spilled_ptr.ref_obj_id = id; + state->stack[spi - 1].spilled_ptr.ref_obj_id = id; } return 0; @@ -779,25 +800,23 @@ static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_re } /* Invalidate any slices associated with this dynptr */ - if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) { - release_reference(env, state->stack[spi].spilled_ptr.id); - state->stack[spi].spilled_ptr.id = 0; - state->stack[spi - 1].spilled_ptr.id = 0; - } - - state->stack[spi].spilled_ptr.dynptr.first_slot = false; - state->stack[spi].spilled_ptr.dynptr.type = 0; - state->stack[spi - 1].spilled_ptr.dynptr.type = 0; + if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) + WARN_ON_ONCE(release_reference(env, state->stack[spi].spilled_ptr.ref_obj_id)); + __mark_reg_not_init(env, &state->stack[spi].spilled_ptr); + __mark_reg_not_init(env, &state->stack[spi - 1].spilled_ptr); return 0; } static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); - int i; + int spi, i; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return false; + spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS)) return true; @@ -813,9 +832,14 @@ static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_ static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); + int spi; int i; + /* This already represents first slot of initialized bpf_dynptr */ + if (reg->type == CONST_PTR_TO_DYNPTR) + return true; + + spi = get_spi(reg->off); if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || !state->stack[spi].spilled_ptr.dynptr.first_slot) return false; @@ -834,15 +858,19 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg { struct bpf_func_state *state = func(env, reg); enum bpf_dynptr_type dynptr_type; - int spi = get_spi(reg->off); + int spi; /* ARG_PTR_TO_DYNPTR takes any type of dynptr */ if (arg_type == ARG_PTR_TO_DYNPTR) return true; dynptr_type = arg_to_dynptr_type(arg_type); - - return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; + if (reg->type == CONST_PTR_TO_DYNPTR) { + return reg->dynptr.type == dynptr_type; + } else { + spi = get_spi(reg->off); + return state->stack[spi].spilled_ptr.dynptr.type == dynptr_type; + } } /* The reg state of a pointer or a bounded scalar was saved when @@ -1354,9 +1382,6 @@ static const int caller_saved[CALLER_SAVED_REGS] = { BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5 }; -static void __mark_reg_not_init(const struct bpf_verifier_env *env, - struct bpf_reg_state *reg); - /* This helper doesn't clear reg->id */ static void ___mark_reg_known(struct bpf_reg_state *reg, u64 imm) { @@ -1419,6 +1444,19 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env, __mark_reg_known_zero(regs + regno); } +static void __mark_dynptr_reg(struct bpf_reg_state *reg, enum bpf_dynptr_type type, + bool first_slot) +{ + /* reg->type has no meaning for STACK_DYNPTR, but when we set reg for + * callback arguments, it does need to be CONST_PTR_TO_DYNPTR, so simply + * set it unconditionally as it is ignored for STACK_DYNPTR anyway. + */ + __mark_reg_known_zero(reg); + reg->type = CONST_PTR_TO_DYNPTR; + reg->dynptr.type = type; + reg->dynptr.first_slot = first_slot; +} + static void mark_ptr_not_null_reg(struct bpf_reg_state *reg) { if (base_type(reg->type) == PTR_TO_MAP_VALUE) { @@ -5857,19 +5895,58 @@ static int process_kptr_func(struct bpf_verifier_env *env, int regno, return 0; } +/* There are two register types representing a bpf_dynptr, one is PTR_TO_STACK + * which points to a stack slot, and the other is CONST_PTR_TO_DYNPTR. + * + * In both cases we deal with the first 8 bytes, but need to mark the next 8 + * bytes as STACK_DYNPTR in case of PTR_TO_STACK. In case of + * CONST_PTR_TO_DYNPTR, we are guaranteed to get the beginning of the object. + * + * Mutability of bpf_dynptr is at two levels, one is at the level of struct + * bpf_dynptr itself, i.e. whether the helper is receiving a pointer to struct + * bpf_dynptr or pointer to const struct bpf_dynptr. In the former case, it can + * mutate the view of the dynptr and also possibly destroy it. In the latter + * case, it cannot mutate the bpf_dynptr itself but it can still mutate the + * memory that dynptr points to. + * + * The verifier will keep track both levels of mutation (bpf_dynptr's in + * reg->type and the memory's in reg->dynptr.type), but there is no support for + * readonly dynptr view yet, hence only the first case is tracked and checked. + * + * This is consistent with how C applies the const modifier to a struct object, + * where the pointer itself inside bpf_dynptr becomes const but not what it + * points to. + * + * Helpers which do not mutate the bpf_dynptr set MEM_RDONLY in their argument + * type, and declare it as 'const struct bpf_dynptr *' in their prototype. + */ int process_dynptr_func(struct bpf_verifier_env *env, int regno, - enum bpf_arg_type arg_type, - struct bpf_call_arg_meta *meta) + enum bpf_arg_type arg_type, struct bpf_call_arg_meta *meta) { struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno]; - /* We only need to check for initialized / uninitialized helper - * dynptr args if the dynptr is not PTR_TO_DYNPTR, as the - * assumption is that if it is, that a helper function - * initialized the dynptr on behalf of the BPF program. + /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an + * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*): + */ + if ((arg_type & (MEM_UNINIT | MEM_RDONLY)) == (MEM_UNINIT | MEM_RDONLY)) { + verbose(env, "verifier internal error: misconfigured dynptr helper type flags\n"); + return -EFAULT; + } + /* MEM_UNINIT - Points to memory that is an appropriate candidate for + * constructing a mutable bpf_dynptr object. + * + * Currently, this is only possible with PTR_TO_STACK + * pointing to a region of at least 16 bytes which doesn't + * contain an existing bpf_dynptr. + * + * MEM_RDONLY - Points to a initialized bpf_dynptr that will not be + * mutated or destroyed. However, the memory it points to + * may be mutated. + * + * None - Points to a initialized dynptr that can be mutated and + * destroyed, including mutation of the memory it points + * to. */ - if (base_type(reg->type) == PTR_TO_DYNPTR) - return 0; if (arg_type & MEM_UNINIT) { if (!is_dynptr_reg_valid_uninit(env, reg)) { verbose(env, "Dynptr has to be an uninitialized dynptr\n"); @@ -5885,7 +5962,13 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, } meta->uninit_dynptr_regno = regno; - } else { + } else /* MEM_RDONLY and None case from above */ { + /* For the reg->type == PTR_TO_STACK case, bpf_dynptr is never const */ + if (reg->type == CONST_PTR_TO_DYNPTR && !(arg_type & MEM_RDONLY)) { + verbose(env, "cannot pass pointer to const bpf_dynptr, the helper mutates it\n"); + return -EINVAL; + } + if (!is_dynptr_reg_valid_init(env, reg)) { verbose(env, "Expected an initialized dynptr as arg #%d\n", @@ -5893,7 +5976,8 @@ int process_dynptr_func(struct bpf_verifier_env *env, int regno, return -EINVAL; } - if (!is_dynptr_type_expected(env, reg, arg_type)) { + /* Fold modifiers (in this case, MEM_RDONLY) when checking expected type */ + if (!is_dynptr_type_expected(env, reg, arg_type & ~MEM_RDONLY)) { const char *err_extra = ""; switch (arg_type & DYNPTR_TYPE_FLAG_MASK) { @@ -6056,7 +6140,7 @@ static const struct bpf_reg_types kptr_types = { .types = { PTR_TO_MAP_VALUE } } static const struct bpf_reg_types dynptr_types = { .types = { PTR_TO_STACK, - PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL, + CONST_PTR_TO_DYNPTR, } }; @@ -6241,12 +6325,16 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env, return __check_ptr_off_reg(env, reg, regno, fixed_off_ok); } -static u32 stack_slot_get_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) +static u32 dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); + int spi; + + if (reg->type == CONST_PTR_TO_DYNPTR) + return reg->ref_obj_id; - return state->stack[spi].spilled_ptr.id; + spi = get_spi(reg->off); + return state->stack[spi].spilled_ptr.ref_obj_id; } static int check_func_arg(struct bpf_verifier_env *env, u32 arg, @@ -6311,11 +6399,22 @@ skip_type_check: if (arg_type_is_release(arg_type)) { if (arg_type_is_dynptr(arg_type)) { struct bpf_func_state *state = func(env, reg); - int spi = get_spi(reg->off); + int spi; - if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || - !state->stack[spi].spilled_ptr.id) { - verbose(env, "arg %d is an unacquired reference\n", regno); + /* Only dynptr created on stack can be released, thus + * the get_spi and stack state checks for spilled_ptr + * should only be done before process_dynptr_func for + * PTR_TO_STACK. + */ + if (reg->type == PTR_TO_STACK) { + spi = get_spi(reg->off); + if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) || + !state->stack[spi].spilled_ptr.ref_obj_id) { + verbose(env, "arg %d is an unacquired reference\n", regno); + return -EINVAL; + } + } else { + verbose(env, "cannot release unowned const bpf_dynptr\n"); return -EINVAL; } } else if (!reg->ref_obj_id && !register_is_null(reg)) { @@ -7289,11 +7388,10 @@ static int set_user_ringbuf_callback_state(struct bpf_verifier_env *env, { /* bpf_user_ringbuf_drain(struct bpf_map *map, void *callback_fn, void * callback_ctx, u64 flags); - * callback_fn(struct bpf_dynptr_t* dynptr, void *callback_ctx); + * callback_fn(const struct bpf_dynptr_t* dynptr, void *callback_ctx); */ __mark_reg_not_init(env, &callee->regs[BPF_REG_0]); - callee->regs[BPF_REG_1].type = PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL; - __mark_reg_known_zero(&callee->regs[BPF_REG_1]); + mark_dynptr_cb_reg(&callee->regs[BPF_REG_1], BPF_DYNPTR_TYPE_LOCAL); callee->regs[BPF_REG_2] = caller->regs[BPF_REG_3]; /* unused */ @@ -7687,7 +7785,15 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn regs = cur_regs(env); + /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot + * be reinitialized by any dynptr helper. Hence, mark_stack_slots_dynptr + * is safe to do directly. + */ if (meta.uninit_dynptr_regno) { + if (regs[meta.uninit_dynptr_regno].type == CONST_PTR_TO_DYNPTR) { + verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be initialized\n"); + return -EFAULT; + } /* we write BPF_DW bits (8 bytes) at a time */ for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) { err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno, @@ -7705,15 +7811,24 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn if (meta.release_regno) { err = -EINVAL; - if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) + /* This can only be set for PTR_TO_STACK, as CONST_PTR_TO_DYNPTR cannot + * be released by any dynptr helper. Hence, unmark_stack_slots_dynptr + * is safe to do directly. + */ + if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1])) { + if (regs[meta.release_regno].type == CONST_PTR_TO_DYNPTR) { + verbose(env, "verifier internal error: CONST_PTR_TO_DYNPTR cannot be released\n"); + return -EFAULT; + } err = unmark_stack_slots_dynptr(env, ®s[meta.release_regno]); - else if (meta.ref_obj_id) + } else if (meta.ref_obj_id) { err = release_reference(env, meta.ref_obj_id); - /* meta.ref_obj_id can only be 0 if register that is meant to be - * released is NULL, which must be > R0. - */ - else if (register_is_null(®s[meta.release_regno])) + } else if (register_is_null(®s[meta.release_regno])) { + /* meta.ref_obj_id can only be 0 if register that is meant to be + * released is NULL, which must be > R0. + */ err = 0; + } if (err) { verbose(env, "func %s#%d reference has not been acquired before\n", func_id_name(func_id), func_id); @@ -7787,11 +7902,7 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn return -EFAULT; } - if (base_type(reg->type) != PTR_TO_DYNPTR) - /* Find the id of the dynptr we're - * tracking the reference of - */ - meta.ref_obj_id = stack_slot_get_id(env, reg); + meta.ref_obj_id = dynptr_ref_obj_id(env, reg); break; } } @@ -8848,12 +8959,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; case KF_ARG_PTR_TO_DYNPTR: if (reg->type != PTR_TO_STACK && - reg->type != PTR_TO_DYNPTR) { + reg->type != CONST_PTR_TO_DYNPTR) { verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i); return -EINVAL; } - ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR, NULL); + ret = process_dynptr_func(env, regno, ARG_PTR_TO_DYNPTR | MEM_RDONLY, NULL); if (ret < 0) return ret; break; diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index fdb0aff8cb5a..e8d90829f23e 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -752,6 +752,7 @@ class PrinterHelpers(Printer): 'struct bpf_timer', 'struct mptcp_sock', 'struct bpf_dynptr', + 'const struct bpf_dynptr', 'struct iphdr', 'struct ipv6hdr', } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index f89de51a45db..464ca3f01fe7 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5293,7 +5293,7 @@ union bpf_attr { * Return * Nothing. Always succeeds. * - * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset, u64 flags) + * long bpf_dynptr_read(void *dst, u32 len, const struct bpf_dynptr *src, u32 offset, u64 flags) * Description * Read *len* bytes from *src* into *dst*, starting from *offset* * into *src*. @@ -5303,7 +5303,7 @@ union bpf_attr { * of *src*'s data, -EINVAL if *src* is an invalid dynptr or if * *flags* is not 0. * - * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) + * long bpf_dynptr_write(const struct bpf_dynptr *dst, u32 offset, void *src, u32 len, u64 flags) * Description * Write *len* bytes from *src* into *dst*, starting from *offset* * into *dst*. @@ -5313,7 +5313,7 @@ union bpf_attr { * of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst* * is a read-only dynptr or if *flags* is not 0. * - * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len) + * void *bpf_dynptr_data(const struct bpf_dynptr *ptr, u32 offset, u32 len) * Description * Get a pointer to the underlying dynptr data. * @@ -5414,7 +5414,7 @@ union bpf_attr { * Drain samples from the specified user ring buffer, and invoke * the provided callback for each such sample: * - * long (\*callback_fn)(struct bpf_dynptr \*dynptr, void \*ctx); + * long (\*callback_fn)(const struct bpf_dynptr \*dynptr, void \*ctx); * * If **callback_fn** returns 0, the helper will continue to try * and drain the next sample, up to a maximum of diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c index 02b18d018b36..aefa0a474e58 100644 --- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c +++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c @@ -673,8 +673,8 @@ static struct { {"user_ringbuf_callback_write_forbidden", "invalid mem access 'dynptr_ptr'"}, {"user_ringbuf_callback_null_context_write", "invalid mem access 'scalar'"}, {"user_ringbuf_callback_null_context_read", "invalid mem access 'scalar'"}, - {"user_ringbuf_callback_discard_dynptr", "arg 1 is an unacquired reference"}, - {"user_ringbuf_callback_submit_dynptr", "arg 1 is an unacquired reference"}, + {"user_ringbuf_callback_discard_dynptr", "cannot release unowned const bpf_dynptr"}, + {"user_ringbuf_callback_submit_dynptr", "cannot release unowned const bpf_dynptr"}, {"user_ringbuf_callback_invalid_return", "At callback return the register R0 has value"}, }; -- cgit From b534dc46c8ae0165b1b2509be24dbea4fa9c4011 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Wed, 7 Dec 2022 09:37:01 -0500 Subject: net_tstamp: add SOF_TIMESTAMPING_OPT_ID_TCP Add an option to initialize SOF_TIMESTAMPING_OPT_ID for TCP from write_seq sockets instead of snd_una. This should have been the behavior from the start. Because processes may now exist that rely on the established behavior, do not change behavior of the existing option, but add the right behavior with a new flag. It is encouraged to always set SOF_TIMESTAMPING_OPT_ID_TCP on stream sockets along with the existing SOF_TIMESTAMPING_OPT_ID. Intuitively the contract is that the counter is zero after the setsockopt, so that the next write N results in a notification for the last byte N - 1. On idle sockets snd_una == write_seq and this holds for both. But on sockets with data in transmission, snd_una records the unacked offset in the stream. This depends on the ACK response from the peer. A process cannot learn this in a race free manner (ioctl SIOCOUTQ is one racy approach). write_seq records the offset at the last byte written by the process. This is a better starting point. It matches the intuitive contract in all circumstances, unaffected by external behavior. The new timestamp flag necessitates increasing sk_tsflags to 32 bits. Move the field in struct sock to avoid growing the socket (for some common CONFIG variants). The UAPI interface so_timestamping.flags is already int, so 32 bits wide. Reported-by: Sotirios Delimanolis Signed-off-by: Willem de Bruijn Link: https://lore.kernel.org/r/20221207143701.29861-1-willemdebruijn.kernel@gmail.com Signed-off-by: Jakub Kicinski --- Documentation/networking/timestamping.rst | 32 ++++++++++++++++++++++++++++++- include/net/sock.h | 6 +++--- include/uapi/linux/net_tstamp.h | 3 ++- net/core/sock.c | 9 ++++++++- net/ethtool/common.c | 1 + 5 files changed, 45 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst index be4eb1242057..f17c01834a12 100644 --- a/Documentation/networking/timestamping.rst +++ b/Documentation/networking/timestamping.rst @@ -179,7 +179,8 @@ SOF_TIMESTAMPING_OPT_ID: identifier and returns that along with the timestamp. The identifier is derived from a per-socket u32 counter (that wraps). For datagram sockets, the counter increments with each sent packet. For stream - sockets, it increments with every byte. + sockets, it increments with every byte. For stream sockets, also set + SOF_TIMESTAMPING_OPT_ID_TCP, see the section below. The counter starts at zero. It is initialized the first time that the socket option is enabled. It is reset each time the option is @@ -192,6 +193,35 @@ SOF_TIMESTAMPING_OPT_ID: among all possibly concurrently outstanding timestamp requests for that socket. +SOF_TIMESTAMPING_OPT_ID_TCP: + Pass this modifier along with SOF_TIMESTAMPING_OPT_ID for new TCP + timestamping applications. SOF_TIMESTAMPING_OPT_ID defines how the + counter increments for stream sockets, but its starting point is + not entirely trivial. This option fixes that. + + For stream sockets, if SOF_TIMESTAMPING_OPT_ID is set, this should + always be set too. On datagram sockets the option has no effect. + + A reasonable expectation is that the counter is reset to zero with + the system call, so that a subsequent write() of N bytes generates + a timestamp with counter N-1. SOF_TIMESTAMPING_OPT_ID_TCP + implements this behavior under all conditions. + + SOF_TIMESTAMPING_OPT_ID without modifier often reports the same, + especially when the socket option is set when no data is in + transmission. If data is being transmitted, it may be off by the + length of the output queue (SIOCOUTQ). + + The difference is due to being based on snd_una versus write_seq. + snd_una is the offset in the stream acknowledged by the peer. This + depends on factors outside of process control, such as network RTT. + write_seq is the last byte written by the process. This offset is + not affected by external inputs. + + The difference is subtle and unlikely to be noticed when configured + at initial socket creation, when no data is queued or sent. But + SOF_TIMESTAMPING_OPT_ID_TCP behavior is more robust regardless of + when the socket option is set. SOF_TIMESTAMPING_OPT_CMSG: Support recv() cmsg for all timestamped packets. Control messages diff --git a/include/net/sock.h b/include/net/sock.h index 6d207e7c4ad0..ecea3dcc2217 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -503,10 +503,10 @@ struct sock { #if BITS_PER_LONG==32 seqlock_t sk_stamp_seq; #endif - u16 sk_tsflags; - u8 sk_shutdown; atomic_t sk_tskey; atomic_t sk_zckey; + u32 sk_tsflags; + u8 sk_shutdown; u8 sk_clockid; u8 sk_txtime_deadline_mode : 1, @@ -1899,7 +1899,7 @@ static inline void sock_replace_proto(struct sock *sk, struct proto *proto) struct sockcm_cookie { u64 transmit_time; u32 mark; - u16 tsflags; + u32 tsflags; }; static inline void sockcm_init(struct sockcm_cookie *sockc, diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 55501e5e7ac8..a2c66b3d7f0f 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -31,8 +31,9 @@ enum { SOF_TIMESTAMPING_OPT_PKTINFO = (1<<13), SOF_TIMESTAMPING_OPT_TX_SWHW = (1<<14), SOF_TIMESTAMPING_BIND_PHC = (1 << 15), + SOF_TIMESTAMPING_OPT_ID_TCP = (1 << 16), - SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_BIND_PHC, + SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_ID_TCP, SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) | SOF_TIMESTAMPING_LAST }; diff --git a/net/core/sock.c b/net/core/sock.c index 4571914a4aa8..b0ab841e0aed 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -901,13 +901,20 @@ int sock_set_timestamping(struct sock *sk, int optname, if (val & ~SOF_TIMESTAMPING_MASK) return -EINVAL; + if (val & SOF_TIMESTAMPING_OPT_ID_TCP && + !(val & SOF_TIMESTAMPING_OPT_ID)) + return -EINVAL; + if (val & SOF_TIMESTAMPING_OPT_ID && !(sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)) { if (sk_is_tcp(sk)) { if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) return -EINVAL; - atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); + if (val & SOF_TIMESTAMPING_OPT_ID_TCP) + atomic_set(&sk->sk_tskey, tcp_sk(sk)->write_seq); + else + atomic_set(&sk->sk_tskey, tcp_sk(sk)->snd_una); } else { atomic_set(&sk->sk_tskey, 0); } diff --git a/net/ethtool/common.c b/net/ethtool/common.c index 21cfe8557205..6f399afc2ff2 100644 --- a/net/ethtool/common.c +++ b/net/ethtool/common.c @@ -417,6 +417,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = { [const_ilog2(SOF_TIMESTAMPING_OPT_PKTINFO)] = "option-pktinfo", [const_ilog2(SOF_TIMESTAMPING_OPT_TX_SWHW)] = "option-tx-swhw", [const_ilog2(SOF_TIMESTAMPING_BIND_PHC)] = "bind-phc", + [const_ilog2(SOF_TIMESTAMPING_OPT_ID_TCP)] = "option-id-tcp", }; static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT); -- cgit From 1933ea365aa7a48ce26bea2ea09c9f7cc48cc668 Mon Sep 17 00:00:00 2001 From: wangchuanlei Date: Tue, 6 Dec 2022 20:38:57 -0500 Subject: net: openvswitch: Add support to count upcall packets Add support to count upall packets, when kmod of openvswitch upcall to count the number of packets for upcall succeed and failed, which is a better way to see how many packets upcalled on every interfaces. Signed-off-by: wangchuanlei Acked-by: Eelco Chaudron Signed-off-by: David S. Miller --- include/uapi/linux/openvswitch.h | 14 +++++++++++ net/openvswitch/datapath.c | 41 ++++++++++++++++++++++++++++++++ net/openvswitch/vport.c | 50 ++++++++++++++++++++++++++++++++++++++++ net/openvswitch/vport.h | 16 +++++++++++++ 4 files changed, 121 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 94066f87e9ee..c5d62ee82567 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -277,11 +277,25 @@ enum ovs_vport_attr { OVS_VPORT_ATTR_PAD, OVS_VPORT_ATTR_IFINDEX, OVS_VPORT_ATTR_NETNSID, + OVS_VPORT_ATTR_UPCALL_STATS, __OVS_VPORT_ATTR_MAX }; #define OVS_VPORT_ATTR_MAX (__OVS_VPORT_ATTR_MAX - 1) +/** + * enum ovs_vport_upcall_attr - attributes for %OVS_VPORT_UPCALL* commands + * @OVS_VPORT_UPCALL_SUCCESS: 64-bit upcall success packets. + * @OVS_VPORT_UPCALL_FAIL: 64-bit upcall fail packets. + */ +enum ovs_vport_upcall_attr { + OVS_VPORT_UPCALL_ATTR_SUCCESS, + OVS_VPORT_UPCALL_ATTR_FAIL, + __OVS_VPORT_UPCALL_ATTR_MAX +}; + +#define OVS_VPORT_UPCALL_ATTR_MAX (__OVS_VPORT_UPCALL_ATTR_MAX - 1) + enum { OVS_VXLAN_EXT_UNSPEC, OVS_VXLAN_EXT_GBP, /* Flag or __u32 */ diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 861dfb8daf4a..932bcf766d63 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -209,6 +209,26 @@ static struct vport *new_vport(const struct vport_parms *parms) return vport; } +static void ovs_vport_update_upcall_stats(struct sk_buff *skb, + const struct dp_upcall_info *upcall_info, + bool upcall_result) +{ + struct vport *p = OVS_CB(skb)->input_vport; + struct vport_upcall_stats_percpu *stats; + + if (upcall_info->cmd != OVS_PACKET_CMD_MISS && + upcall_info->cmd != OVS_PACKET_CMD_ACTION) + return; + + stats = this_cpu_ptr(p->upcall_stats); + u64_stats_update_begin(&stats->syncp); + if (upcall_result) + u64_stats_inc(&stats->n_success); + else + u64_stats_inc(&stats->n_fail); + u64_stats_update_end(&stats->syncp); +} + void ovs_dp_detach_port(struct vport *p) { ASSERT_OVSL(); @@ -216,6 +236,9 @@ void ovs_dp_detach_port(struct vport *p) /* First drop references to device. */ hlist_del_rcu(&p->dp_hash_node); + /* Free percpu memory */ + free_percpu(p->upcall_stats); + /* Then destroy it. */ ovs_vport_del(p); } @@ -305,6 +328,8 @@ int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, err = queue_userspace_packet(dp, skb, key, upcall_info, cutlen); else err = queue_gso_packets(dp, skb, key, upcall_info, cutlen); + + ovs_vport_update_upcall_stats(skb, upcall_info, !err); if (err) goto err; @@ -1826,6 +1851,12 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_portids; } + vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); + if (!vport->upcall_stats) { + err = -ENOMEM; + goto err_destroy_portids; + } + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, info->snd_seq, 0, OVS_DP_CMD_NEW); BUG_ON(err < 0); @@ -2098,6 +2129,9 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, OVS_VPORT_ATTR_PAD)) goto nla_put_failure; + if (ovs_vport_get_upcall_stats(vport, skb)) + goto nla_put_failure; + if (ovs_vport_get_upcall_portids(vport, skb)) goto nla_put_failure; @@ -2279,6 +2313,12 @@ restart: goto exit_unlock_free; } + vport->upcall_stats = netdev_alloc_pcpu_stats(struct vport_upcall_stats_percpu); + if (!vport->upcall_stats) { + err = -ENOMEM; + goto exit_unlock_free; + } + err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, OVS_VPORT_CMD_NEW, GFP_KERNEL); @@ -2508,6 +2548,7 @@ static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, [OVS_VPORT_ATTR_IFINDEX] = { .type = NLA_U32 }, [OVS_VPORT_ATTR_NETNSID] = { .type = NLA_S32 }, + [OVS_VPORT_ATTR_UPCALL_STATS] = { .type = NLA_NESTED }, }; static const struct genl_small_ops dp_vport_genl_ops[] = { diff --git a/net/openvswitch/vport.c b/net/openvswitch/vport.c index 82a74f998966..7e0f5c45b512 100644 --- a/net/openvswitch/vport.c +++ b/net/openvswitch/vport.c @@ -284,6 +284,56 @@ void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats) stats->tx_packets = dev_stats->tx_packets; } +/** + * ovs_vport_get_upcall_stats - retrieve upcall stats + * + * @vport: vport from which to retrieve the stats. + * @skb: sk_buff where upcall stats should be appended. + * + * Retrieves upcall stats for the given device. + * + * Must be called with ovs_mutex or rcu_read_lock. + */ +int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb) +{ + struct nlattr *nla; + int i; + + __u64 tx_success = 0; + __u64 tx_fail = 0; + + for_each_possible_cpu(i) { + const struct vport_upcall_stats_percpu *stats; + unsigned int start; + + stats = per_cpu_ptr(vport->upcall_stats, i); + do { + start = u64_stats_fetch_begin(&stats->syncp); + tx_success += u64_stats_read(&stats->n_success); + tx_fail += u64_stats_read(&stats->n_fail); + } while (u64_stats_fetch_retry(&stats->syncp, start)); + } + + nla = nla_nest_start_noflag(skb, OVS_VPORT_ATTR_UPCALL_STATS); + if (!nla) + return -EMSGSIZE; + + if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_SUCCESS, tx_success, + OVS_VPORT_ATTR_PAD)) { + nla_nest_cancel(skb, nla); + return -EMSGSIZE; + } + + if (nla_put_u64_64bit(skb, OVS_VPORT_UPCALL_ATTR_FAIL, tx_fail, + OVS_VPORT_ATTR_PAD)) { + nla_nest_cancel(skb, nla); + return -EMSGSIZE; + } + nla_nest_end(skb, nla); + + return 0; +} + /** * ovs_vport_get_options - retrieve device options * diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h index 6ff45e8a0868..3e71ca8ad8a7 100644 --- a/net/openvswitch/vport.h +++ b/net/openvswitch/vport.h @@ -32,6 +32,8 @@ struct vport *ovs_vport_locate(const struct net *net, const char *name); void ovs_vport_get_stats(struct vport *, struct ovs_vport_stats *); +int ovs_vport_get_upcall_stats(struct vport *vport, struct sk_buff *skb); + int ovs_vport_set_options(struct vport *, struct nlattr *options); int ovs_vport_get_options(const struct vport *, struct sk_buff *); @@ -65,6 +67,7 @@ struct vport_portids { * @hash_node: Element in @dev_table hash table in vport.c. * @dp_hash_node: Element in @datapath->ports hash table in datapath.c. * @ops: Class structure. + * @upcall_stats: Upcall stats of every ports. * @detach_list: list used for detaching vport in net-exit call. * @rcu: RCU callback head for deferred destruction. */ @@ -78,6 +81,7 @@ struct vport { struct hlist_node hash_node; struct hlist_node dp_hash_node; const struct vport_ops *ops; + struct vport_upcall_stats_percpu __percpu *upcall_stats; struct list_head detach_list; struct rcu_head rcu; @@ -137,6 +141,18 @@ struct vport_ops { struct list_head list; }; +/** + * struct vport_upcall_stats_percpu - per-cpu packet upcall statistics for + * a given vport. + * @n_success: Number of packets that upcall to userspace succeed. + * @n_fail: Number of packets that upcall to userspace failed. + */ +struct vport_upcall_stats_percpu { + struct u64_stats_sync syncp; + u64_stats_t n_success; + u64_stats_t n_fail; +}; + struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *, const struct vport_parms *); void ovs_vport_free(struct vport *); -- cgit From b22bbdd17a5af2cc99cf42048970b9355dcbec8b Mon Sep 17 00:00:00 2001 From: Andrew Melnychenko Date: Wed, 7 Dec 2022 13:35:54 +0200 Subject: uapi/linux/if_tun.h: Added new offload types for USO4/6. Added 2 additional offlloads for USO(IPv4 & IPv6). Separate offloads are required for Windows VM guests, g.e. Windows may set USO rx only for IPv4. Signed-off-by: Andrew Melnychenko Signed-off-by: David S. Miller --- include/uapi/linux/if_tun.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index b6d7b868f290..287cdc81c939 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -90,6 +90,8 @@ #define TUN_F_TSO6 0x04 /* I can handle TSO for IPv6 packets */ #define TUN_F_TSO_ECN 0x08 /* I can handle TSO with ECN bits. */ #define TUN_F_UFO 0x10 /* I can handle UFO packets */ +#define TUN_F_USO4 0x20 /* I can handle USO for IPv4 packets */ +#define TUN_F_USO6 0x40 /* I can handle USO for IPv6 packets */ /* Protocol info prepended to the packets (when IFF_NO_PI is not set) */ #define TUN_PKT_STRIP 0x0001 -- cgit From 34061b348ae912b9783fae7fabae69d46977a036 Mon Sep 17 00:00:00 2001 From: Andrew Melnychenko Date: Wed, 7 Dec 2022 13:35:56 +0200 Subject: uapi/linux/virtio_net.h: Added USO types. Added new GSO type for USO: VIRTIO_NET_HDR_GSO_UDP_L4. Feature VIRTIO_NET_F_HOST_USO allows to enable NETIF_F_GSO_UDP_L4. Separated VIRTIO_NET_F_GUEST_USO4 & VIRTIO_NET_F_GUEST_USO6 features required for Windows guests. Signed-off-by: Andrew Melnychenko Signed-off-by: David S. Miller --- include/uapi/linux/virtio_net.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 6cb842ea8979..b4062bed186a 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -57,6 +57,9 @@ * Steering */ #define VIRTIO_NET_F_CTRL_MAC_ADDR 23 /* Set MAC address */ #define VIRTIO_NET_F_NOTF_COAL 53 /* Device supports notifications coalescing */ +#define VIRTIO_NET_F_GUEST_USO4 54 /* Guest can handle USOv4 in. */ +#define VIRTIO_NET_F_GUEST_USO6 55 /* Guest can handle USOv6 in. */ +#define VIRTIO_NET_F_HOST_USO 56 /* Host can handle USO in. */ #define VIRTIO_NET_F_HASH_REPORT 57 /* Supports hash report */ #define VIRTIO_NET_F_RSS 60 /* Supports RSS RX steering */ #define VIRTIO_NET_F_RSC_EXT 61 /* extended coalescing info */ @@ -130,6 +133,7 @@ struct virtio_net_hdr_v1 { #define VIRTIO_NET_HDR_GSO_TCPV4 1 /* GSO frame, IPv4 TCP (TSO) */ #define VIRTIO_NET_HDR_GSO_UDP 3 /* GSO frame, IPv4 UDP (UFO) */ #define VIRTIO_NET_HDR_GSO_TCPV6 4 /* GSO frame, IPv6 TCP */ +#define VIRTIO_NET_HDR_GSO_UDP_L4 5 /* GSO frame, IPv4& IPv6 UDP (USO) */ #define VIRTIO_NET_HDR_GSO_ECN 0x80 /* TCP has ECN set */ __u8 gso_type; __virtio16 hdr_len; /* Ethernet + IP + tcp/udp hdrs */ -- cgit From 47c50853bb9c5c35bf5c3eb00b712310ec2969e2 Mon Sep 17 00:00:00 2001 From: Igor Skalkin Date: Mon, 24 Oct 2022 15:40:33 +0200 Subject: virtio_bt: Fix alignment in configuration struct The current version of the configuration structure has unaligned 16-bit fields, but according to the specification [1], access to the configuration space must be aligned. Add a second, aligned version of the configuration structure and a new feature bit indicating that this version is being used. [1] https://docs.oasis-open.org/virtio/virtio/v1.1/virtio-v1.1.pdf Signed-off-by: Igor Skalkin Signed-off-by: Luiz Augusto von Dentz --- drivers/bluetooth/virtio_bt.c | 16 +++++++++++++--- include/uapi/linux/virtio_bt.h | 8 ++++++++ 2 files changed, 21 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/bluetooth/virtio_bt.c b/drivers/bluetooth/virtio_bt.c index 2bbeb65b1cd3..c570c45d1480 100644 --- a/drivers/bluetooth/virtio_bt.c +++ b/drivers/bluetooth/virtio_bt.c @@ -313,7 +313,12 @@ static int virtbt_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BT_F_VND_HCI)) { __u16 vendor; - virtio_cread(vdev, struct virtio_bt_config, vendor, &vendor); + if (virtio_has_feature(vdev, VIRTIO_BT_F_CONFIG_V2)) + virtio_cread(vdev, struct virtio_bt_config_v2, + vendor, &vendor); + else + virtio_cread(vdev, struct virtio_bt_config, + vendor, &vendor); switch (vendor) { case VIRTIO_BT_CONFIG_VENDOR_ZEPHYR: @@ -346,8 +351,12 @@ static int virtbt_probe(struct virtio_device *vdev) if (virtio_has_feature(vdev, VIRTIO_BT_F_MSFT_EXT)) { __u16 msft_opcode; - virtio_cread(vdev, struct virtio_bt_config, - msft_opcode, &msft_opcode); + if (virtio_has_feature(vdev, VIRTIO_BT_F_CONFIG_V2)) + virtio_cread(vdev, struct virtio_bt_config_v2, + msft_opcode, &msft_opcode); + else + virtio_cread(vdev, struct virtio_bt_config, + msft_opcode, &msft_opcode); hci_set_msft_opcode(hdev, msft_opcode); } @@ -402,6 +411,7 @@ static const unsigned int virtbt_features[] = { VIRTIO_BT_F_VND_HCI, VIRTIO_BT_F_MSFT_EXT, VIRTIO_BT_F_AOSP_EXT, + VIRTIO_BT_F_CONFIG_V2, }; static struct virtio_driver virtbt_driver = { diff --git a/include/uapi/linux/virtio_bt.h b/include/uapi/linux/virtio_bt.h index a7bd48daa9a9..af798f4c9680 100644 --- a/include/uapi/linux/virtio_bt.h +++ b/include/uapi/linux/virtio_bt.h @@ -9,6 +9,7 @@ #define VIRTIO_BT_F_VND_HCI 0 /* Indicates vendor command support */ #define VIRTIO_BT_F_MSFT_EXT 1 /* Indicates MSFT vendor support */ #define VIRTIO_BT_F_AOSP_EXT 2 /* Indicates AOSP vendor support */ +#define VIRTIO_BT_F_CONFIG_V2 3 /* Use second version configuration */ enum virtio_bt_config_type { VIRTIO_BT_CONFIG_TYPE_PRIMARY = 0, @@ -28,4 +29,11 @@ struct virtio_bt_config { __u16 msft_opcode; } __attribute__((packed)); +struct virtio_bt_config_v2 { + __u8 type; + __u8 alignment; + __u16 vendor; + __u16 msft_opcode; +}; + #endif /* _UAPI_LINUX_VIRTIO_BT_H */ -- cgit From 6afaae6d12f54accf194e73ece617d1f456e438d Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 10 Dec 2022 16:56:29 +0200 Subject: bridge: mcast: Allow user space to add (*, G) with a source list and filter mode Add new netlink attributes to the RTM_NEWMDB request that allow user space to add (*, G) with a source list and filter mode. The RTM_NEWMDB message can already dump such entries (created by the kernel) so there is no need to add dump support. However, the message contains a different set of attributes depending if it is a request or a response. The naming and structure of the new attributes try to follow the existing ones used in the response. Request: [ struct nlmsghdr ] [ struct br_port_msg ] [ MDBA_SET_ENTRY ] struct br_mdb_entry [ MDBA_SET_ENTRY_ATTRS ] [ MDBE_ATTR_SOURCE ] struct in_addr / struct in6_addr [ MDBE_ATTR_SRC_LIST ] // new [ MDBE_SRC_LIST_ENTRY ] [ MDBE_SRCATTR_ADDRESS ] struct in_addr / struct in6_addr [ ...] [ MDBE_ATTR_GROUP_MODE ] // new u8 Response: [ struct nlmsghdr ] [ struct br_port_msg ] [ MDBA_MDB ] [ MDBA_MDB_ENTRY ] [ MDBA_MDB_ENTRY_INFO ] struct br_mdb_entry [ MDBA_MDB_EATTR_TIMER ] u32 [ MDBA_MDB_EATTR_SOURCE ] struct in_addr / struct in6_addr [ MDBA_MDB_EATTR_RTPROT ] u8 [ MDBA_MDB_EATTR_SRC_LIST ] [ MDBA_MDB_SRCLIST_ENTRY ] [ MDBA_MDB_SRCATTR_ADDRESS ] struct in_addr / struct in6_addr [ MDBA_MDB_SRCATTR_TIMER ] u8 [...] [ MDBA_MDB_EATTR_GROUP_MODE ] u8 Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 20 +++++++ net/bridge/br_mdb.c | 130 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 150 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index a86a7e7b811f..0d9fe73fc48c 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -723,10 +723,30 @@ enum { enum { MDBE_ATTR_UNSPEC, MDBE_ATTR_SOURCE, + MDBE_ATTR_SRC_LIST, + MDBE_ATTR_GROUP_MODE, __MDBE_ATTR_MAX, }; #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) +/* per mdb entry source */ +enum { + MDBE_SRC_LIST_UNSPEC, + MDBE_SRC_LIST_ENTRY, + __MDBE_SRC_LIST_MAX, +}; +#define MDBE_SRC_LIST_MAX (__MDBE_SRC_LIST_MAX - 1) + +/* per mdb entry per source attributes + * these are embedded in MDBE_SRC_LIST_ENTRY + */ +enum { + MDBE_SRCATTR_UNSPEC, + MDBE_SRCATTR_ADDRESS, + __MDBE_SRCATTR_MAX, +}; +#define MDBE_SRCATTR_MAX (__MDBE_SRCATTR_MAX - 1) + /* Embedded inside LINK_XSTATS_TYPE_BRIDGE */ enum { BRIDGE_XSTATS_UNSPEC, diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index e9a4b7e247e7..61d46b0a31b6 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -663,10 +663,25 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MDB, err); } +static const struct nla_policy +br_mdbe_src_list_entry_pol[MDBE_SRCATTR_MAX + 1] = { + [MDBE_SRCATTR_ADDRESS] = NLA_POLICY_RANGE(NLA_BINARY, + sizeof(struct in_addr), + sizeof(struct in6_addr)), +}; + +static const struct nla_policy +br_mdbe_src_list_pol[MDBE_SRC_LIST_MAX + 1] = { + [MDBE_SRC_LIST_ENTRY] = NLA_POLICY_NESTED(br_mdbe_src_list_entry_pol), +}; + static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_SOURCE] = NLA_POLICY_RANGE(NLA_BINARY, sizeof(struct in_addr), sizeof(struct in6_addr)), + [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, + MCAST_INCLUDE), + [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(br_mdbe_src_list_pol), }; static bool is_valid_mdb_entry(struct br_mdb_entry *entry, @@ -1051,6 +1066,76 @@ static int __br_mdb_add(const struct br_mdb_config *cfg, return ret; } +static int br_mdb_config_src_entry_init(struct nlattr *src_entry, + struct br_mdb_src_entry *src, + __be16 proto, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb[MDBE_SRCATTR_MAX + 1]; + int err; + + err = nla_parse_nested(tb, MDBE_SRCATTR_MAX, src_entry, + br_mdbe_src_list_entry_pol, extack); + if (err) + return err; + + if (NL_REQ_ATTR_CHECK(extack, src_entry, tb, MDBE_SRCATTR_ADDRESS)) + return -EINVAL; + + if (!is_valid_mdb_source(tb[MDBE_SRCATTR_ADDRESS], proto, extack)) + return -EINVAL; + + src->addr.proto = proto; + nla_memcpy(&src->addr.src, tb[MDBE_SRCATTR_ADDRESS], + nla_len(tb[MDBE_SRCATTR_ADDRESS])); + + return 0; +} + +static int br_mdb_config_src_list_init(struct nlattr *src_list, + struct br_mdb_config *cfg, + struct netlink_ext_ack *extack) +{ + struct nlattr *src_entry; + int rem, err; + int i = 0; + + nla_for_each_nested(src_entry, src_list, rem) + cfg->num_src_entries++; + + if (cfg->num_src_entries >= PG_SRC_ENT_LIMIT) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Exceeded maximum number of source entries (%u)", + PG_SRC_ENT_LIMIT - 1); + return -EINVAL; + } + + cfg->src_entries = kcalloc(cfg->num_src_entries, + sizeof(struct br_mdb_src_entry), GFP_KERNEL); + if (!cfg->src_entries) + return -ENOMEM; + + nla_for_each_nested(src_entry, src_list, rem) { + err = br_mdb_config_src_entry_init(src_entry, + &cfg->src_entries[i], + cfg->entry->addr.proto, + extack); + if (err) + goto err_src_entry_init; + i++; + } + + return 0; + +err_src_entry_init: + kfree(cfg->src_entries); + return err; +} + +static void br_mdb_config_src_list_fini(struct br_mdb_config *cfg) +{ + kfree(cfg->src_entries); +} + static int br_mdb_config_attrs_init(struct nlattr *set_attrs, struct br_mdb_config *cfg, struct netlink_ext_ack *extack) @@ -1070,6 +1155,44 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs, __mdb_entry_to_br_ip(cfg->entry, &cfg->group, mdb_attrs); + if (mdb_attrs[MDBE_ATTR_GROUP_MODE]) { + if (!cfg->p) { + NL_SET_ERR_MSG_MOD(extack, "Filter mode cannot be set for host groups"); + return -EINVAL; + } + if (!br_multicast_is_star_g(&cfg->group)) { + NL_SET_ERR_MSG_MOD(extack, "Filter mode can only be set for (*, G) entries"); + return -EINVAL; + } + cfg->filter_mode = nla_get_u8(mdb_attrs[MDBE_ATTR_GROUP_MODE]); + } else { + cfg->filter_mode = MCAST_EXCLUDE; + } + + if (mdb_attrs[MDBE_ATTR_SRC_LIST]) { + if (!cfg->p) { + NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set for host groups"); + return -EINVAL; + } + if (!br_multicast_is_star_g(&cfg->group)) { + NL_SET_ERR_MSG_MOD(extack, "Source list can only be set for (*, G) entries"); + return -EINVAL; + } + if (!mdb_attrs[MDBE_ATTR_GROUP_MODE]) { + NL_SET_ERR_MSG_MOD(extack, "Source list cannot be set without filter mode"); + return -EINVAL; + } + err = br_mdb_config_src_list_init(mdb_attrs[MDBE_ATTR_SRC_LIST], + cfg, extack); + if (err) + return err; + } + + if (!cfg->num_src_entries && cfg->filter_mode == MCAST_INCLUDE) { + NL_SET_ERR_MSG_MOD(extack, "Cannot add (*, G) INCLUDE with an empty source list"); + return -EINVAL; + } + return 0; } @@ -1162,6 +1285,11 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, return 0; } +static void br_mdb_config_fini(struct br_mdb_config *cfg) +{ + br_mdb_config_src_list_fini(cfg); +} + static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -1220,6 +1348,7 @@ static int br_mdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, } out: + br_mdb_config_fini(&cfg); return err; } @@ -1295,6 +1424,7 @@ static int br_mdb_del(struct sk_buff *skb, struct nlmsghdr *nlh, err = __br_mdb_del(&cfg); } + br_mdb_config_fini(&cfg); return err; } -- cgit From 1d7b66a7d9754c229d12c53ad6a1effe88c16ca4 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 10 Dec 2022 16:56:30 +0200 Subject: bridge: mcast: Allow user space to specify MDB entry routing protocol Add the 'MDBE_ATTR_RTPORT' attribute to allow user space to specify the routing protocol of the MDB port group entry. Enforce a minimum value of 'RTPROT_STATIC' to prevent user space from using protocol values that should only be set by the kernel (e.g., 'RTPROT_KERNEL'). Maintain backward compatibility by defaulting to 'RTPROT_STATIC'. The protocol is already visible to user space in RTM_NEWMDB responses and notifications via the 'MDBA_MDB_EATTR_RTPROT' attribute. The routing protocol allows a routing daemon to distinguish between entries configured by it and those configured by the administrator. Once MDB flush is supported, the protocol can be used as a criterion according to which the flush is performed. Examples: # bridge mdb add dev br0 port dummy10 grp 239.1.1.1 permanent proto kernel Error: integer out of range. # bridge mdb add dev br0 port dummy10 grp 239.1.1.1 permanent proto static # bridge mdb add dev br0 port dummy10 grp 239.1.1.1 src 192.0.2.1 permanent proto zebra # bridge mdb add dev br0 port dummy10 grp 239.1.1.2 permanent source_list 198.51.100.1,198.51.100.2 filter_mode include proto 250 # bridge -d mdb show dev br0 port dummy10 grp 239.1.1.2 src 198.51.100.2 permanent filter_mode include proto 250 dev br0 port dummy10 grp 239.1.1.2 src 198.51.100.1 permanent filter_mode include proto 250 dev br0 port dummy10 grp 239.1.1.2 permanent filter_mode include source_list 198.51.100.2/0.00,198.51.100.1/0.00 proto 250 dev br0 port dummy10 grp 239.1.1.1 src 192.0.2.1 permanent filter_mode include proto zebra dev br0 port dummy10 grp 239.1.1.1 permanent filter_mode exclude proto static Signed-off-by: Ido Schimmel Acked-by: Nikolay Aleksandrov Signed-off-by: Jakub Kicinski --- include/uapi/linux/if_bridge.h | 1 + net/bridge/br_mdb.c | 15 +++++++++++++-- net/bridge/br_private.h | 1 + 3 files changed, 15 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h index 0d9fe73fc48c..d9de241d90f9 100644 --- a/include/uapi/linux/if_bridge.h +++ b/include/uapi/linux/if_bridge.h @@ -725,6 +725,7 @@ enum { MDBE_ATTR_SOURCE, MDBE_ATTR_SRC_LIST, MDBE_ATTR_GROUP_MODE, + MDBE_ATTR_RTPROT, __MDBE_ATTR_MAX, }; #define MDBE_ATTR_MAX (__MDBE_ATTR_MAX - 1) diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c index 61d46b0a31b6..72d4e53193e5 100644 --- a/net/bridge/br_mdb.c +++ b/net/bridge/br_mdb.c @@ -682,6 +682,7 @@ static const struct nla_policy br_mdbe_attrs_pol[MDBE_ATTR_MAX + 1] = { [MDBE_ATTR_GROUP_MODE] = NLA_POLICY_RANGE(NLA_U8, MCAST_EXCLUDE, MCAST_INCLUDE), [MDBE_ATTR_SRC_LIST] = NLA_POLICY_NESTED(br_mdbe_src_list_pol), + [MDBE_ATTR_RTPROT] = NLA_POLICY_MIN(NLA_U8, RTPROT_STATIC), }; static bool is_valid_mdb_entry(struct br_mdb_entry *entry, @@ -823,7 +824,7 @@ static int br_mdb_add_group_sg(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - MCAST_INCLUDE, RTPROT_STATIC); + MCAST_INCLUDE, cfg->rt_protocol); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (S, G) port group"); return -ENOMEM; @@ -881,6 +882,7 @@ static int br_mdb_add_group_src_fwd(const struct br_mdb_config *cfg, sg_cfg.group = sg_ip; sg_cfg.src_entry = true; sg_cfg.filter_mode = MCAST_INCLUDE; + sg_cfg.rt_protocol = cfg->rt_protocol; return br_mdb_add_group_sg(&sg_cfg, sgmp, brmctx, flags, extack); } @@ -982,7 +984,7 @@ static int br_mdb_add_group_star_g(const struct br_mdb_config *cfg, } p = br_multicast_new_port_group(cfg->p, &cfg->group, *pp, flags, NULL, - cfg->filter_mode, RTPROT_STATIC); + cfg->filter_mode, cfg->rt_protocol); if (unlikely(!p)) { NL_SET_ERR_MSG_MOD(extack, "Couldn't allocate new (*, G) port group"); return -ENOMEM; @@ -1193,6 +1195,14 @@ static int br_mdb_config_attrs_init(struct nlattr *set_attrs, return -EINVAL; } + if (mdb_attrs[MDBE_ATTR_RTPROT]) { + if (!cfg->p) { + NL_SET_ERR_MSG_MOD(extack, "Protocol cannot be set for host groups"); + return -EINVAL; + } + cfg->rt_protocol = nla_get_u8(mdb_attrs[MDBE_ATTR_RTPROT]); + } + return 0; } @@ -1212,6 +1222,7 @@ static int br_mdb_config_init(struct net *net, const struct nlmsghdr *nlh, memset(cfg, 0, sizeof(*cfg)); cfg->filter_mode = MCAST_EXCLUDE; + cfg->rt_protocol = RTPROT_STATIC; bpm = nlmsg_data(nlh); if (!bpm->ifindex) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 368f5f6fa42b..cdc9e040f1f6 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -106,6 +106,7 @@ struct br_mdb_config { u8 filter_mode; struct br_mdb_src_entry *src_entries; int num_src_entries; + u8 rt_protocol; }; #endif -- cgit