From f64c4acea51fbe2c08c0b0f48b7f5d1657d7a5e4 Mon Sep 17 00:00:00 2001 From: Vadim Fedorenko Date: Fri, 10 Sep 2021 01:04:08 +0300 Subject: bpf: Add hardware timestamp field to __sk_buff BPF programs may want to know hardware timestamps if NIC supports such timestamping. Expose this data as hwtstamp field of __sk_buff the same way as gso_segs/gso_size. This field could be accessed from the same programs as tstamp field, but it's read-only field. Explicit test to deny access to padding data is added to bpf_skb_is_valid_access. Also update BPF_PROG_TEST_RUN tests of the feature. Signed-off-by: Vadim Fedorenko Signed-off-by: Daniel Borkmann Acked-by: Martin KaFai Lau Link: https://lore.kernel.org/bpf/20210909220409.8804-2-vfedorenko@novek.ru --- include/uapi/linux/bpf.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 791f31dd0abe..51cfd91cc387 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5284,6 +5284,8 @@ struct __sk_buff { __u32 gso_segs; __bpf_md_ptr(struct bpf_sock *, sk); __u32 gso_size; + __u32 :32; /* Padding, future use. */ + __u64 hwtstamp; }; struct bpf_tunnel_key { -- cgit v1.2.3 From dd47c104533dedb90434a3f142e94a671ac623a6 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Mon, 13 Sep 2021 17:44:15 +0200 Subject: io-wq: provide IO_WQ_* constants for IORING_REGISTER_IOWQ_MAX_WORKERS arg items The items passed in the array pointed by the arg parameter of IORING_REGISTER_IOWQ_MAX_WORKERS io_uring_register operation carry certain semantics: they refer to different io-wq worker categories; provide IO_WQ_* constants in the UAPI, so these categories can be referenced in the user space code. Suggested-by: Jens Axboe Complements: 2e480058ddc21ec5 ("io-wq: provide a way to limit max number of workers") Signed-off-by: Eugene Syromiatnikov Link: https://lore.kernel.org/r/20210913154415.GA12890@asgard.redhat.com Signed-off-by: Jens Axboe --- fs/io-wq.c | 5 +++++ include/uapi/linux/io_uring.h | 8 +++++++- 2 files changed, 12 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/io-wq.c b/fs/io-wq.c index 3d4460df845c..c2e0e8e80949 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "io-wq.h" @@ -1281,6 +1282,10 @@ int io_wq_max_workers(struct io_wq *wq, int *new_count) { int i, node, prev = 0; + BUILD_BUG_ON((int) IO_WQ_ACCT_BOUND != (int) IO_WQ_BOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_UNBOUND != (int) IO_WQ_UNBOUND); + BUILD_BUG_ON((int) IO_WQ_ACCT_NR != 2); + for (i = 0; i < 2; i++) { if (new_count[i] > task_rlimit(current, RLIMIT_NPROC)) new_count[i] = task_rlimit(current, RLIMIT_NPROC); diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 59ef35154e3d..b270a07b285e 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -317,13 +317,19 @@ enum { IORING_REGISTER_IOWQ_AFF = 17, IORING_UNREGISTER_IOWQ_AFF = 18, - /* set/get max number of workers */ + /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, /* this goes last */ IORING_REGISTER_LAST }; +/* io-wq worker categories */ +enum { + IO_WQ_BOUND, + IO_WQ_UNBOUND, +}; + /* deprecated, see struct io_uring_rsrc_update */ struct io_uring_files_update { __u32 offset; -- cgit v1.2.3 From 856c02dbce4f8d6a5644083db22c11750aa11481 Mon Sep 17 00:00:00 2001 From: Song Liu Date: Fri, 10 Sep 2021 11:33:51 -0700 Subject: bpf: Introduce helper bpf_get_branch_snapshot Introduce bpf_get_branch_snapshot(), which allows tracing pogram to get branch trace from hardware (e.g. Intel LBR). To use the feature, the user need to create perf_event with proper branch_record filtering on each cpu, and then calls bpf_get_branch_snapshot in the bpf function. On Intel CPUs, VLBR event (raw event 0x1b00) can be use for this. Signed-off-by: Song Liu Signed-off-by: Alexei Starovoitov Acked-by: John Fastabend Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210910183352.3151445-3-songliubraving@fb.com --- include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++ kernel/bpf/trampoline.c | 3 ++- kernel/trace/bpf_trace.c | 30 ++++++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 22 ++++++++++++++++++++++ 4 files changed, 76 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 51cfd91cc387..d21326558d42 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4877,6 +4877,27 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5076,7 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c index fe1e857324e6..39eaaff81953 100644 --- a/kernel/bpf/trampoline.c +++ b/kernel/bpf/trampoline.c @@ -10,6 +10,7 @@ #include #include #include +#include /* dummy _ops. The verifier will operate on target program's ops. */ const struct bpf_verifier_ops bpf_extension_verifier_ops = { @@ -526,7 +527,7 @@ out: } #define NO_START_TIME 1 -static u64 notrace bpf_prog_start_time(void) +static __always_inline u64 notrace bpf_prog_start_time(void) { u64 start = NO_START_TIME; diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 8e2eb950aa82..067e88c3d2ee 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1017,6 +1017,34 @@ static const struct bpf_func_proto bpf_get_attach_cookie_proto_pe = { .arg1_type = ARG_PTR_TO_CTX, }; +BPF_CALL_3(bpf_get_branch_snapshot, void *, buf, u32, size, u64, flags) +{ +#ifndef CONFIG_X86 + return -ENOENT; +#else + static const u32 br_entry_size = sizeof(struct perf_branch_entry); + u32 entry_cnt = size / br_entry_size; + + entry_cnt = static_call(perf_snapshot_branch_stack)(buf, entry_cnt); + + if (unlikely(flags)) + return -EINVAL; + + if (!entry_cnt) + return -ENOENT; + + return entry_cnt * br_entry_size; +#endif +} + +static const struct bpf_func_proto bpf_get_branch_snapshot_proto = { + .func = bpf_get_branch_snapshot, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_UNINIT_MEM, + .arg2_type = ARG_CONST_SIZE_OR_ZERO, +}; + static const struct bpf_func_proto * bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -1132,6 +1160,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_snprintf_proto; case BPF_FUNC_get_func_ip: return &bpf_get_func_ip_proto_tracing; + case BPF_FUNC_get_branch_snapshot: + return &bpf_get_branch_snapshot_proto; default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 51cfd91cc387..d21326558d42 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4877,6 +4877,27 @@ union bpf_attr { * Get the struct pt_regs associated with **task**. * Return * A pointer to struct pt_regs. + * + * long bpf_get_branch_snapshot(void *entries, u32 size, u64 flags) + * Description + * Get branch trace from hardware engines like Intel LBR. The + * hardware engine is stopped shortly after the helper is + * called. Therefore, the user need to filter branch entries + * based on the actual use case. To capture branch trace + * before the trigger point of the BPF program, the helper + * should be called at the beginning of the BPF program. + * + * The data is stored as struct perf_branch_entry into output + * buffer *entries*. *size* is the size of *entries* in bytes. + * *flags* is reserved for now and must be zero. + * + * Return + * On success, number of bytes written to *buf*. On error, a + * negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-ENOENT** if architecture does not support branch records. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5055,6 +5076,7 @@ union bpf_attr { FN(get_func_ip), \ FN(get_attach_cookie), \ FN(task_pt_regs), \ + FN(get_branch_snapshot), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From 099dd788e31b4f426ef49c2785069804925a84e1 Mon Sep 17 00:00:00 2001 From: Steve French Date: Mon, 13 Sep 2021 14:51:10 -0500 Subject: cifs: remove pathname for file from SPDX header checkpatch complains about source files with filenames (e.g. in these cases just below the SPDX header in comments at the top of various files in fs/cifs). It also is helpful to change this now so will be less confusing when the parent directory is renamed e.g. from fs/cifs to fs/smb_client (or fs/smbfs) Reviewed-by: Ronnie Sahlberg Signed-off-by: Steve French --- fs/cifs/cache.c | 2 +- fs/cifs/cifs_debug.c | 1 - fs/cifs/cifs_fs_sb.h | 1 - fs/cifs/cifs_ioctl.h | 1 - fs/cifs/cifs_spnego.c | 2 +- fs/cifs/cifs_spnego.h | 2 +- fs/cifs/cifs_unicode.c | 1 - fs/cifs/cifsacl.c | 1 - fs/cifs/cifsacl.h | 1 - fs/cifs/cifsencrypt.c | 1 - fs/cifs/cifsfs.c | 1 - fs/cifs/cifsfs.h | 1 - fs/cifs/cifsglob.h | 1 - fs/cifs/cifspdu.h | 1 - fs/cifs/cifsproto.h | 1 - fs/cifs/cifssmb.c | 1 - fs/cifs/connect.c | 1 - fs/cifs/dir.c | 1 - fs/cifs/dns_resolve.c | 1 - fs/cifs/dns_resolve.h | 4 ++-- fs/cifs/export.c | 1 - fs/cifs/file.c | 1 - fs/cifs/fscache.c | 2 +- fs/cifs/fscache.h | 2 +- fs/cifs/inode.c | 1 - fs/cifs/ioctl.c | 1 - fs/cifs/link.c | 1 - fs/cifs/misc.c | 1 - fs/cifs/netmisc.c | 1 - fs/cifs/ntlmssp.h | 1 - fs/cifs/readdir.c | 1 - fs/cifs/rfc1002pdu.h | 1 - fs/cifs/sess.c | 1 - fs/cifs/smb2file.c | 1 - fs/cifs/smb2glob.h | 1 - fs/cifs/smb2inode.c | 1 - fs/cifs/smb2misc.c | 1 - fs/cifs/smb2pdu.c | 1 - fs/cifs/smb2pdu.h | 1 - fs/cifs/smb2proto.h | 1 - fs/cifs/smb2status.h | 1 - fs/cifs/smb2transport.c | 1 - fs/cifs/smberr.h | 1 - fs/cifs/transport.c | 1 - fs/cifs/winucase.c | 1 - fs/cifs/xattr.c | 1 - fs/smbfs_common/smbfsctl.h | 2 +- include/uapi/linux/cifs/cifs_mount.h | 1 - 48 files changed, 8 insertions(+), 49 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c index 8a3b30ec860c..8be57aaedab6 100644 --- a/fs/cifs/cache.c +++ b/fs/cifs/cache.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cache.c - CIFS filesystem cache index structure definitions + * CIFS filesystem cache index structure definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 51a824fc926a..de2c12bcfa4b 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs_debug.c * * Copyright (C) International Business Machines Corp., 2000,2005 * diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 4fd788586399..f97407520ea1 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_fs_sb.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifs_ioctl.h b/fs/cifs/cifs_ioctl.h index ef723be358af..b87cbbe6d2d4 100644 --- a/fs/cifs/cifs_ioctl.h +++ b/fs/cifs/cifs_ioctl.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_ioctl.h * * Structure definitions for io control for cifs/smb3 * diff --git a/fs/cifs/cifs_spnego.c b/fs/cifs/cifs_spnego.c index 8fa26a8530f8..353bd0dd7026 100644 --- a/fs/cifs/cifs_spnego.c +++ b/fs/cifs/cifs_spnego.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifs_spnego.c -- SPNEGO upcall management for CIFS + * SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) diff --git a/fs/cifs/cifs_spnego.h b/fs/cifs/cifs_spnego.h index 31387d0ea32e..e6a0451877d4 100644 --- a/fs/cifs/cifs_spnego.h +++ b/fs/cifs/cifs_spnego.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifs_spnego.h -- SPNEGO upcall management for CIFS + * SPNEGO upcall management for CIFS * * Copyright (c) 2007 Red Hat, Inc. * Author(s): Jeff Layton (jlayton@redhat.com) diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c index 171ad8b42107..e7582dd79179 100644 --- a/fs/cifs/cifs_unicode.c +++ b/fs/cifs/cifs_unicode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/cifs_unicode.c * * Copyright (c) International Business Machines Corp., 2000,2009 * Modified by Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c index 388eb536cff1..ee3aab3dd4ac 100644 --- a/fs/cifs/cifsacl.c +++ b/fs/cifs/cifsacl.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsacl.c * * Copyright (C) International Business Machines Corp., 2007,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsacl.h b/fs/cifs/cifsacl.h index f8292bcf8594..ccbfc754bd3c 100644 --- a/fs/cifs/cifsacl.h +++ b/fs/cifs/cifsacl.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsacl.h * * Copyright (c) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c index 2e6f40344037..d118282071b3 100644 --- a/fs/cifs/cifsencrypt.c +++ b/fs/cifs/cifsencrypt.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsencrypt.c * * Encryption and hashing operations relating to NTLM, NTLMv2. See MS-NLMP * for more detailed information diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 8c20bfa187ac..9fa930dfd78d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifsfs.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index d25a4099b32e..b50da1901ebd 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsfs.h * * Copyright (c) International Business Machines Corp., 2002, 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index c068f7d8d879..7dd9878e26bf 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsglob.h * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h index 98e8e5aa0613..d2ff438fd31f 100644 --- a/fs/cifs/cifspdu.h +++ b/fs/cifs/cifspdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifspdu.h * * Copyright (c) International Business Machines Corp., 2002,2009 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index f9740c21ca3d..54966c1a8eb6 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/cifsproto.h * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c index a8e41c1e80ca..243d17696f06 100644 --- a/fs/cifs/cifssmb.c +++ b/fs/cifs/cifssmb.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/cifssmb.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 0db344807ef1..399a0f084573 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/connect.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index 5f8a302ffcb2..6e8e7cc26ae2 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/dir.c * * vfs operations that deal with dentries * diff --git a/fs/cifs/dns_resolve.c b/fs/cifs/dns_resolve.c index 8c616aaeb7c4..0458d28d71aa 100644 --- a/fs/cifs/dns_resolve.c +++ b/fs/cifs/dns_resolve.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/dns_resolve.c * * Copyright (c) 2007 Igor Mammedov * Author(s): Igor Mammedov (niallain@gmail.com) diff --git a/fs/cifs/dns_resolve.h b/fs/cifs/dns_resolve.h index 9fa2807ef79e..afc0df381246 100644 --- a/fs/cifs/dns_resolve.h +++ b/fs/cifs/dns_resolve.h @@ -1,7 +1,7 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/dns_resolve.h -- DNS Resolver upcall management for CIFS DFS - * Handles host name to IP address resolution + * DNS Resolver upcall management for CIFS DFS + * Handles host name to IP address resolution * * Copyright (c) International Business Machines Corp., 2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/export.c b/fs/cifs/export.c index 747a540db954..37c28415df1e 100644 --- a/fs/cifs/export.c +++ b/fs/cifs/export.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/export.c * * Copyright (C) International Business Machines Corp., 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/file.c b/fs/cifs/file.c index d0216472f1c6..4d10c9343890 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/file.c * * vfs operations that deal with files * diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c index fab47fa7df74..8eedd20c44ab 100644 --- a/fs/cifs/fscache.c +++ b/fs/cifs/fscache.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/fscache.c - CIFS filesystem cache interface + * CIFS filesystem cache interface * * Copyright (c) 2010 Novell, Inc. * Author(s): Suresh Jayaraman diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h index 82e856b9cf89..9baa1d0f22bd 100644 --- a/fs/cifs/fscache.h +++ b/fs/cifs/fscache.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/fscache.h - CIFS filesystem cache interface definitions + * CIFS filesystem cache interface definitions * * Copyright (c) 2010 Novell, Inc. * Authors(s): Suresh Jayaraman (sjayaraman@suse.de> diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index 50c01cff4c84..19af2d0ec8d5 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/inode.c * * Copyright (C) International Business Machines Corp., 2002,2010 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 42c6a0bac6c8..44ae99454fb3 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/ioctl.c * * vfs operations that deal with io control * diff --git a/fs/cifs/link.c b/fs/cifs/link.c index f0a6d63bc08c..852e54ee82c2 100644 --- a/fs/cifs/link.c +++ b/fs/cifs/link.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/link.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 9469f1cf0b46..f4313935e734 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/misc.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c index 0e728aac67e9..fa9fbd6a819c 100644 --- a/fs/cifs/netmisc.c +++ b/fs/cifs/netmisc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/netmisc.c * * Copyright (c) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/ntlmssp.h b/fs/cifs/ntlmssp.h index 378133ce8869..25a2b8ef88b9 100644 --- a/fs/cifs/ntlmssp.h +++ b/fs/cifs/ntlmssp.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/ntlmssp.h * * Copyright (c) International Business Machines Corp., 2002,2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c index 54d77c99e21c..1929e80c09ee 100644 --- a/fs/cifs/readdir.c +++ b/fs/cifs/readdir.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/readdir.c * * Directory search handling * diff --git a/fs/cifs/rfc1002pdu.h b/fs/cifs/rfc1002pdu.h index 137f7c95afd6..ae1d025da294 100644 --- a/fs/cifs/rfc1002pdu.h +++ b/fs/cifs/rfc1002pdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/rfc1002pdu.h * * Protocol Data Unit definitions for RFC 1001/1002 support * diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index 118403fbeda2..23e02db7923f 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/sess.c * * SMB/CIFS session setup handling routines * diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c index c9d8a50062b8..f5dcc4940b6d 100644 --- a/fs/cifs/smb2file.c +++ b/fs/cifs/smb2file.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2file.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Author(s): Steve French (sfrench@us.ibm.com), diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h index d0e9f3782bd9..ca692b2283cd 100644 --- a/fs/cifs/smb2glob.h +++ b/fs/cifs/smb2glob.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2glob.h * * Definitions for various global variables and structures * diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c index 957b2594f02e..8297703492ee 100644 --- a/fs/cifs/smb2inode.c +++ b/fs/cifs/smb2inode.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2inode.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 668f77108831..29b5554f6263 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2misc.c * * Copyright (C) International Business Machines Corp., 2002,2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c index b6d2e3591927..672ae78e866a 100644 --- a/fs/cifs/smb2pdu.c +++ b/fs/cifs/smb2pdu.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2pdu.c * * Copyright (C) International Business Machines Corp., 2009, 2013 * Etersoft, 2012 diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index e9cac7970b66..f32c99c9ba13 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2pdu.h * * Copyright (c) International Business Machines Corp., 2009, 2013 * Etersoft, 2012 diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h index 263767f644f8..547945443fa7 100644 --- a/fs/cifs/smb2proto.h +++ b/fs/cifs/smb2proto.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2proto.h * * Copyright (c) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smb2status.h b/fs/cifs/smb2status.h index 0215ef36e240..a9e958166fc5 100644 --- a/fs/cifs/smb2status.h +++ b/fs/cifs/smb2status.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smb2status.h * * SMB2 Status code (network error) definitions * Definitions are from MS-ERREF diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c index 6f7952ea4941..f59b956f9d25 100644 --- a/fs/cifs/smb2transport.c +++ b/fs/cifs/smb2transport.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/smb2transport.c * * Copyright (C) International Business Machines Corp., 2002, 2011 * Etersoft, 2012 diff --git a/fs/cifs/smberr.h b/fs/cifs/smberr.h index 60189efb3236..aeffdad829e2 100644 --- a/fs/cifs/smberr.h +++ b/fs/cifs/smberr.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1 */ /* - * fs/cifs/smberr.h * * Copyright (c) International Business Machines Corp., 2002,2004 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index 75a95de320cf..b7379329b741 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/transport.c * * Copyright (C) International Business Machines Corp., 2002,2008 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/cifs/winucase.c b/fs/cifs/winucase.c index 59b6c577aa0a..2f075b5b50df 100644 --- a/fs/cifs/winucase.c +++ b/fs/cifs/winucase.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: GPL-2.0-or-later /* - * fs/cifs/winucase.c * * Copyright (c) Jeffrey Layton , 2013 * diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c index 9ed481e79ce0..7d8b72d67c80 100644 --- a/fs/cifs/xattr.c +++ b/fs/cifs/xattr.c @@ -1,6 +1,5 @@ // SPDX-License-Identifier: LGPL-2.1 /* - * fs/cifs/xattr.c * * Copyright (c) International Business Machines Corp., 2003, 2007 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/fs/smbfs_common/smbfsctl.h b/fs/smbfs_common/smbfsctl.h index d01e8c9d7a31..926f87cd6af0 100644 --- a/fs/smbfs_common/smbfsctl.h +++ b/fs/smbfs_common/smbfsctl.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: LGPL-2.1+ */ /* - * fs/cifs/smbfsctl.h: SMB, CIFS, SMB2 FSCTL definitions + * SMB, CIFS, SMB2 FSCTL definitions * * Copyright (c) International Business Machines Corp., 2002,2013 * Author(s): Steve French (sfrench@us.ibm.com) diff --git a/include/uapi/linux/cifs/cifs_mount.h b/include/uapi/linux/cifs/cifs_mount.h index 69829205fdb5..8e87d27b0951 100644 --- a/include/uapi/linux/cifs/cifs_mount.h +++ b/include/uapi/linux/cifs/cifs_mount.h @@ -1,6 +1,5 @@ /* SPDX-License-Identifier: LGPL-2.1+ WITH Linux-syscall-note */ /* - * include/uapi/linux/cifs/cifs_mount.h * * Author(s): Scott Lovenberg (scott.lovenberg@gmail.com) * -- cgit v1.2.3 From b564171ade70570b7f335fa8ed17adb28409e3ac Mon Sep 17 00:00:00 2001 From: Li Li Date: Fri, 10 Sep 2021 09:42:10 -0700 Subject: binder: fix freeze race Currently cgroup freezer is used to freeze the application threads, and BINDER_FREEZE is used to freeze the corresponding binder interface. There's already a mechanism in ioctl(BINDER_FREEZE) to wait for any existing transactions to drain out before actually freezing the binder interface. But freezing an app requires 2 steps, freezing the binder interface with ioctl(BINDER_FREEZE) and then freezing the application main threads with cgroupfs. This is not an atomic operation. The following race issue might happen. 1) Binder interface is frozen by ioctl(BINDER_FREEZE); 2) Main thread A initiates a new sync binder transaction to process B; 3) Main thread A is frozen by "echo 1 > cgroup.freeze"; 4) The response from process B reaches the frozen thread, which will unexpectedly fail. This patch provides a mechanism to check if there's any new pending transaction happening between ioctl(BINDER_FREEZE) and freezing the main thread. If there's any, the main thread freezing operation can be rolled back to finish the pending transaction. Furthermore, the response might reach the binder driver before the rollback actually happens. That will still cause failed transaction. As the other process doesn't wait for another response of the response, the response transaction failure can be fixed by treating the response transaction like an oneway/async one, allowing it to reach the frozen thread. And it will be consumed when the thread gets unfrozen later. NOTE: This patch reuses the existing definition of struct binder_frozen_status_info but expands the bit assignments of __u32 member sync_recv. To ensure backward compatibility, bit 0 of sync_recv still indicates there's an outstanding sync binder transaction. This patch adds new information to bit 1 of sync_recv, indicating the binder transaction happens exactly when there's a race. If an existing userspace app runs on a new kernel, a sync binder call will set bit 0 of sync_recv so ioctl(BINDER_GET_FROZEN_INFO) still return the expected value (true). The app just doesn't check bit 1 intentionally so it doesn't have the ability to tell if there's a race. This behavior is aligned with what happens on an old kernel which doesn't set bit 1 at all. A new userspace app can 1) check bit 0 to know if there's a sync binder transaction happened when being frozen - same as before; and 2) check bit 1 to know if that sync binder transaction happened exactly when there's a race - a new information for rollback decision. the same time, confirmed the pending transactions succeeded. Fixes: 432ff1e91694 ("binder: BINDER_FREEZE ioctl") Acked-by: Todd Kjos Cc: stable Signed-off-by: Li Li Test: stress test with apps being frozen and initiating binder calls at Link: https://lore.kernel.org/r/20210910164210.2282716-2-dualli@chromium.org Signed-off-by: Greg Kroah-Hartman --- drivers/android/binder.c | 35 +++++++++++++++++++++++++++++------ drivers/android/binder_internal.h | 2 ++ include/uapi/linux/android/binder.h | 7 +++++++ 3 files changed, 38 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/android/binder.c b/drivers/android/binder.c index d9030cb6b1e4..1a68c2f590cf 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -3038,9 +3038,8 @@ static void binder_transaction(struct binder_proc *proc, if (reply) { binder_enqueue_thread_work(thread, tcomplete); binder_inner_proc_lock(target_proc); - if (target_thread->is_dead || target_proc->is_frozen) { - return_error = target_thread->is_dead ? - BR_DEAD_REPLY : BR_FROZEN_REPLY; + if (target_thread->is_dead) { + return_error = BR_DEAD_REPLY; binder_inner_proc_unlock(target_proc); goto err_dead_proc_or_thread; } @@ -4648,6 +4647,22 @@ static int binder_ioctl_get_node_debug_info(struct binder_proc *proc, return 0; } +static bool binder_txns_pending_ilocked(struct binder_proc *proc) +{ + struct rb_node *n; + struct binder_thread *thread; + + if (proc->outstanding_txns > 0) + return true; + + for (n = rb_first(&proc->threads); n; n = rb_next(n)) { + thread = rb_entry(n, struct binder_thread, rb_node); + if (thread->transaction_stack) + return true; + } + return false; +} + static int binder_ioctl_freeze(struct binder_freeze_info *info, struct binder_proc *target_proc) { @@ -4679,8 +4694,13 @@ static int binder_ioctl_freeze(struct binder_freeze_info *info, (!target_proc->outstanding_txns), msecs_to_jiffies(info->timeout_ms)); - if (!ret && target_proc->outstanding_txns) - ret = -EAGAIN; + /* Check pending transactions that wait for reply */ + if (ret >= 0) { + binder_inner_proc_lock(target_proc); + if (binder_txns_pending_ilocked(target_proc)) + ret = -EAGAIN; + binder_inner_proc_unlock(target_proc); + } if (ret < 0) { binder_inner_proc_lock(target_proc); @@ -4696,6 +4716,7 @@ static int binder_ioctl_get_freezer_info( { struct binder_proc *target_proc; bool found = false; + __u32 txns_pending; info->sync_recv = 0; info->async_recv = 0; @@ -4705,7 +4726,9 @@ static int binder_ioctl_get_freezer_info( if (target_proc->pid == info->pid) { found = true; binder_inner_proc_lock(target_proc); - info->sync_recv |= target_proc->sync_recv; + txns_pending = binder_txns_pending_ilocked(target_proc); + info->sync_recv |= target_proc->sync_recv | + (txns_pending << 1); info->async_recv |= target_proc->async_recv; binder_inner_proc_unlock(target_proc); } diff --git a/drivers/android/binder_internal.h b/drivers/android/binder_internal.h index 810c0b84d3f8..402c4d4362a8 100644 --- a/drivers/android/binder_internal.h +++ b/drivers/android/binder_internal.h @@ -378,6 +378,8 @@ struct binder_ref { * binder transactions * (protected by @inner_lock) * @sync_recv: process received sync transactions since last frozen + * bit 0: received sync transaction after being frozen + * bit 1: new pending sync transaction during freezing * (protected by @inner_lock) * @async_recv: process received async transactions since last frozen * (protected by @inner_lock) diff --git a/include/uapi/linux/android/binder.h b/include/uapi/linux/android/binder.h index 20e435fe657a..3246f2c74696 100644 --- a/include/uapi/linux/android/binder.h +++ b/include/uapi/linux/android/binder.h @@ -225,7 +225,14 @@ struct binder_freeze_info { struct binder_frozen_status_info { __u32 pid; + + /* process received sync transactions since last frozen + * bit 0: received sync transaction after being frozen + * bit 1: new pending sync transaction during freezing + */ __u32 sync_recv; + + /* process received async transactions since last frozen */ __u32 async_recv; }; -- cgit v1.2.3 From 844f7eaaed9267ae17d33778efe65548cc940205 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Sun, 12 Sep 2021 14:22:34 +0200 Subject: include/uapi/linux/xfrm.h: Fix XFRM_MSG_MAPPING ABI breakage Commit 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") broke ABI by changing the value of the XFRM_MSG_MAPPING enum item, thus also evading the build-time check in security/selinux/nlmsgtab.c:selinux_nlmsg_lookup for presence of proper security permission checks in nlmsg_xfrm_perms. Fix it by placing XFRM_MSG_SETDEFAULT/XFRM_MSG_GETDEFAULT to the end of the enum, right before __XFRM_MSG_MAX, and updating the nlmsg_xfrm_perms accordingly. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") References: https://lore.kernel.org/netdev/20210901151402.GA2557@altlinux.org/ Signed-off-by: Eugene Syromiatnikov Acked-by: Antony Antony Acked-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 6 +++--- security/selinux/nlmsgtab.c | 4 +++- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index b96c1ea7166d..26f456b1f33e 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -213,13 +213,13 @@ enum { XFRM_MSG_GETSPDINFO, #define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO + XFRM_MSG_MAPPING, +#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING + XFRM_MSG_SETDEFAULT, #define XFRM_MSG_SETDEFAULT XFRM_MSG_SETDEFAULT XFRM_MSG_GETDEFAULT, #define XFRM_MSG_GETDEFAULT XFRM_MSG_GETDEFAULT - - XFRM_MSG_MAPPING, -#define XFRM_MSG_MAPPING XFRM_MSG_MAPPING __XFRM_MSG_MAX }; #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1) diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index d59276f48d4f..94ea2a8b2bb7 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -126,6 +126,8 @@ static const struct nlmsg_perm nlmsg_xfrm_perms[] = { XFRM_MSG_NEWSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, { XFRM_MSG_GETSPDINFO, NETLINK_XFRM_SOCKET__NLMSG_READ }, { XFRM_MSG_MAPPING, NETLINK_XFRM_SOCKET__NLMSG_READ }, + { XFRM_MSG_SETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_WRITE }, + { XFRM_MSG_GETDEFAULT, NETLINK_XFRM_SOCKET__NLMSG_READ }, }; static const struct nlmsg_perm nlmsg_audit_perms[] = @@ -189,7 +191,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) * structures at the top of this file with the new mappings * before updating the BUILD_BUG_ON() macro! */ - BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_MAPPING); + BUILD_BUG_ON(XFRM_MSG_MAX != XFRM_MSG_GETDEFAULT); err = nlmsg_perm(nlmsg_type, perm, nlmsg_xfrm_perms, sizeof(nlmsg_xfrm_perms)); break; -- cgit v1.2.3 From 059ebe4fe332c5d1c25124166527cdf9fe43a3ce Mon Sep 17 00:00:00 2001 From: Andra Paraschiv Date: Fri, 27 Aug 2021 18:49:29 +0300 Subject: nitro_enclaves: Add fixes for checkpatch spell check reports Fix the typos in the words spelling as per the checkpatch script reports. Reviewed-by: George-Aurelian Popescu Signed-off-by: Andra Paraschiv Link: https://lore.kernel.org/r/20210827154930.40608-7-andraprs@amazon.com Signed-off-by: Greg Kroah-Hartman --- include/uapi/linux/nitro_enclaves.h | 10 +++++----- samples/nitro_enclaves/ne_ioctl_sample.c | 4 ++-- 2 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nitro_enclaves.h b/include/uapi/linux/nitro_enclaves.h index b945073fe544..e808f5ba124d 100644 --- a/include/uapi/linux/nitro_enclaves.h +++ b/include/uapi/linux/nitro_enclaves.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ /* - * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. */ #ifndef _UAPI_LINUX_NITRO_ENCLAVES_H_ @@ -60,7 +60,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() / copy_to_user() failure. @@ -95,7 +95,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() / copy_to_user() failure. @@ -118,7 +118,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() failure. @@ -161,7 +161,7 @@ * * Context: Process context. * Return: - * * 0 - Logic succesfully completed. + * * 0 - Logic successfully completed. * * -1 - There was a failure in the ioctl logic. * On failure, errno is set to: * * EFAULT - copy_from_user() / copy_to_user() failure. diff --git a/samples/nitro_enclaves/ne_ioctl_sample.c b/samples/nitro_enclaves/ne_ioctl_sample.c index 480b763142b3..6a60990b2e20 100644 --- a/samples/nitro_enclaves/ne_ioctl_sample.c +++ b/samples/nitro_enclaves/ne_ioctl_sample.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved. */ /** @@ -638,7 +638,7 @@ static int ne_start_enclave(int enclave_fd, struct ne_enclave_start_info *encla } /** - * ne_start_enclave_check_booted() - Start the enclave and wait for a hearbeat + * ne_start_enclave_check_booted() - Start the enclave and wait for a heartbeat * from it, on a newly created vsock channel, * to check it has booted. * @enclave_fd : The file descriptor associated with the enclave. -- cgit v1.2.3 From fa0866625543b4d8b3d026e4e0ef5ec25a453920 Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Tue, 14 Sep 2021 10:35:05 +0200 Subject: net/smc: add support for user defined EIDs SMC-Dv2 allows users to define EIDs which allows to create separate name spaces enabling users to cluster their SMC-Dv2 connections. Add support for user defined EIDs and extent the generic netlink interface so users can add, remove and dump EIDs. Signed-off-by: Karsten Graul Reviewed-by: Guvenc Gulce Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 15 +++ net/smc/af_smc.c | 34 +++--- net/smc/smc.h | 3 - net/smc/smc_clc.c | 263 ++++++++++++++++++++++++++++++++++++++++++++--- net/smc/smc_clc.h | 16 ++- net/smc/smc_core.h | 1 + net/smc/smc_netlink.c | 32 +++++- net/smc/smc_netlink.h | 2 + 8 files changed, 335 insertions(+), 31 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index 0f7f87c70baf..e3728af2832b 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -38,6 +38,9 @@ enum { /* SMC PNET Table commands */ #define SMC_GENL_FAMILY_VERSION 1 #define SMC_PCI_ID_STR_LEN 16 /* Max length of pci id string */ +#define SMC_MAX_HOSTNAME_LEN 32 /* Max length of the hostname */ +#define SMC_MAX_UEID 4 /* Max number of user EIDs */ +#define SMC_MAX_EID_LEN 32 /* Max length of an EID */ /* SMC_GENL_FAMILY commands */ enum { @@ -49,6 +52,10 @@ enum { SMC_NETLINK_GET_DEV_SMCR, SMC_NETLINK_GET_STATS, SMC_NETLINK_GET_FBACK_STATS, + SMC_NETLINK_DUMP_UEID, + SMC_NETLINK_ADD_UEID, + SMC_NETLINK_REMOVE_UEID, + SMC_NETLINK_FLUSH_UEID, }; /* SMC_GENL_FAMILY top level attributes */ @@ -242,4 +249,12 @@ enum { __SMC_NLA_FBACK_STATS_MAX, SMC_NLA_FBACK_STATS_MAX = __SMC_NLA_FBACK_STATS_MAX - 1 }; + +/* SMC_NETLINK_UEID attributes */ +enum { + SMC_NLA_EID_TABLE_UNSPEC, + SMC_NLA_EID_TABLE_ENTRY, /* string */ + __SMC_NLA_EID_TABLE_MAX, + SMC_NLA_EID_TABLE_MAX = __SMC_NLA_EID_TABLE_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index c038efc23ce3..e5d62acbe401 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -829,7 +829,7 @@ static int smc_connect_rdma(struct smc_sock *smc, smc_rmb_sync_sg_for_device(&smc->conn); reason_code = smc_clc_send_confirm(smc, ini->first_contact_local, - SMC_V1); + SMC_V1, NULL); if (reason_code) goto connect_abort; @@ -883,6 +883,7 @@ static int smc_connect_ism(struct smc_sock *smc, struct smc_clc_msg_accept_confirm *aclc, struct smc_init_info *ini) { + u8 *eid = NULL; int rc = 0; ini->is_smcd = true; @@ -918,8 +919,15 @@ static int smc_connect_ism(struct smc_sock *smc, smc_rx_init(smc); smc_tx_init(smc); + if (aclc->hdr.version > SMC_V1) { + struct smc_clc_msg_accept_confirm_v2 *clc_v2 = + (struct smc_clc_msg_accept_confirm_v2 *)aclc; + + eid = clc_v2->eid; + } + rc = smc_clc_send_confirm(smc, ini->first_contact_local, - aclc->hdr.version); + aclc->hdr.version, eid); if (rc) goto connect_abort; mutex_unlock(&smc_server_lgr_pending); @@ -1533,9 +1541,8 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, pclc_smcd = smc_get_clc_msg_smcd(pclc); smc_v2_ext = smc_get_clc_v2_ext(pclc); smcd_v2_ext = smc_get_clc_smcd_v2_ext(smc_v2_ext); - if (!smcd_v2_ext || - !smc_v2_ext->hdr.flag.seid) { /* no system EID support for SMCD */ - smc_find_ism_store_rc(SMC_CLC_DECL_NOSEID, ini); + if (!smcd_v2_ext) { + smc_find_ism_store_rc(SMC_CLC_DECL_NOV2DEXT, ini); goto not_found; } @@ -1555,13 +1562,13 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } mutex_unlock(&smcd_dev_list.mutex); - if (ini->ism_dev[0]) { - smc_ism_get_system_eid(ini->ism_dev[0], &eid); - if (memcmp(eid, smcd_v2_ext->system_eid, SMC_MAX_EID_LEN)) - goto not_found; - } else { + if (!ini->ism_dev[0]) + goto not_found; + + smc_ism_get_system_eid(ini->ism_dev[0], &eid); + if (!smc_clc_match_eid(ini->negotiated_eid, smc_v2_ext, + smcd_v2_ext->system_eid, eid)) goto not_found; - } /* separate - outside the smcd_dev_list.lock */ smcd_version = ini->smcd_version; @@ -1579,6 +1586,7 @@ static void smc_find_ism_v2_device_serv(struct smc_sock *new_smc, } /* no V2 ISM device could be initialized */ ini->smcd_version = smcd_version; /* restore original value */ + ini->negotiated_eid[0] = 0; not_found: ini->smcd_version &= ~SMC_V2; @@ -1788,7 +1796,8 @@ static void smc_listen_work(struct work_struct *work) /* send SMC Accept CLC message */ rc = smc_clc_send_accept(new_smc, ini->first_contact_local, - ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1); + ini->smcd_version == SMC_V2 ? SMC_V2 : SMC_V1, + ini->negotiated_eid); if (rc) goto out_unlock; @@ -2662,6 +2671,7 @@ static void __exit smc_exit(void) proto_unregister(&smc_proto); smc_pnet_exit(); smc_nl_exit(); + smc_clc_exit(); unregister_pernet_subsys(&smc_net_stat_ops); unregister_pernet_subsys(&smc_net_ops); rcu_barrier(); diff --git a/net/smc/smc.h b/net/smc/smc.h index d65e15f0c944..5e7def3ab730 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -29,9 +29,6 @@ * devices */ -#define SMC_MAX_HOSTNAME_LEN 32 -#define SMC_MAX_EID_LEN 32 - extern struct proto smc_proto; extern struct proto smc_proto6; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index e286dafd6e88..a3d99f894f52 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -26,6 +26,7 @@ #include "smc_clc.h" #include "smc_ib.h" #include "smc_ism.h" +#include "smc_netlink.h" #define SMCR_CLC_ACCEPT_CONFIRM_LEN 68 #define SMCD_CLC_ACCEPT_CONFIRM_LEN 48 @@ -39,6 +40,223 @@ static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'}; static u8 smc_hostname[SMC_MAX_HOSTNAME_LEN]; +struct smc_clc_eid_table { + rwlock_t lock; + struct list_head list; + u8 ueid_cnt; + u8 seid_enabled; +}; + +static struct smc_clc_eid_table smc_clc_eid_table; + +struct smc_clc_eid_entry { + struct list_head list; + u8 eid[SMC_MAX_EID_LEN]; +}; + +/* The size of a user EID is 32 characters. + * Valid characters should be (single-byte character set) A-Z, 0-9, '.' and '-'. + * Blanks should only be used to pad to the expected size. + * First character must be alphanumeric. + */ +static bool smc_clc_ueid_valid(char *ueid) +{ + char *end = ueid + SMC_MAX_EID_LEN; + + while (--end >= ueid && isspace(*end)) + ; + if (end < ueid) + return false; + if (!isalnum(*ueid) || islower(*ueid)) + return false; + while (ueid <= end) { + if ((!isalnum(*ueid) || islower(*ueid)) && *ueid != '.' && + *ueid != '-') + return false; + ueid++; + } + return true; +} + +static int smc_clc_ueid_add(char *ueid) +{ + struct smc_clc_eid_entry *new_ueid, *tmp_ueid; + int rc; + + if (!smc_clc_ueid_valid(ueid)) + return -EINVAL; + + /* add a new ueid entry to the ueid table if there isn't one */ + new_ueid = kzalloc(sizeof(*new_ueid), GFP_KERNEL); + if (!new_ueid) + return -ENOMEM; + memcpy(new_ueid->eid, ueid, SMC_MAX_EID_LEN); + + write_lock(&smc_clc_eid_table.lock); + if (smc_clc_eid_table.ueid_cnt >= SMC_MAX_UEID) { + rc = -ERANGE; + goto err_out; + } + list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { + if (!memcmp(tmp_ueid->eid, ueid, SMC_MAX_EID_LEN)) { + rc = -EEXIST; + goto err_out; + } + } + list_add_tail(&new_ueid->list, &smc_clc_eid_table.list); + smc_clc_eid_table.ueid_cnt++; + write_unlock(&smc_clc_eid_table.lock); + return 0; + +err_out: + write_unlock(&smc_clc_eid_table.lock); + kfree(new_ueid); + return rc; +} + +int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; + char *ueid; + + if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) + return -EINVAL; + ueid = (char *)nla_data(nla_ueid); + + return smc_clc_ueid_add(ueid); +} + +/* remove one or all ueid entries from the table */ +static int smc_clc_ueid_remove(char *ueid) +{ + struct smc_clc_eid_entry *lst_ueid, *tmp_ueid; + int rc = -ENOENT; + + /* remove table entry */ + write_lock(&smc_clc_eid_table.lock); + list_for_each_entry_safe(lst_ueid, tmp_ueid, &smc_clc_eid_table.list, + list) { + if (!ueid || !memcmp(lst_ueid->eid, ueid, SMC_MAX_EID_LEN)) { + list_del(&lst_ueid->list); + smc_clc_eid_table.ueid_cnt--; + kfree(lst_ueid); + rc = 0; + } + } + write_unlock(&smc_clc_eid_table.lock); + return rc; +} + +int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr *nla_ueid = info->attrs[SMC_NLA_EID_TABLE_ENTRY]; + char *ueid; + + if (!nla_ueid || nla_len(nla_ueid) != SMC_MAX_EID_LEN + 1) + return -EINVAL; + ueid = (char *)nla_data(nla_ueid); + + return smc_clc_ueid_remove(ueid); +} + +int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info) +{ + smc_clc_ueid_remove(NULL); + return 0; +} + +static int smc_nl_ueid_dumpinfo(struct sk_buff *skb, u32 portid, u32 seq, + u32 flags, char *ueid) +{ + char ueid_str[SMC_MAX_EID_LEN + 1]; + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &smc_gen_nl_family, + flags, SMC_NETLINK_DUMP_UEID); + if (!hdr) + return -ENOMEM; + snprintf(ueid_str, sizeof(ueid_str), "%s", ueid); + if (nla_put_string(skb, SMC_NLA_EID_TABLE_ENTRY, ueid_str)) { + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; + } + genlmsg_end(skb, hdr); + return 0; +} + +static int _smc_nl_ueid_dump(struct sk_buff *skb, u32 portid, u32 seq, + int start_idx) +{ + struct smc_clc_eid_entry *lst_ueid; + int idx = 0; + + read_lock(&smc_clc_eid_table.lock); + list_for_each_entry(lst_ueid, &smc_clc_eid_table.list, list) { + if (idx++ < start_idx) + continue; + if (smc_nl_ueid_dumpinfo(skb, portid, seq, NLM_F_MULTI, + lst_ueid->eid)) { + --idx; + break; + } + } + read_unlock(&smc_clc_eid_table.lock); + return idx; +} + +int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + int idx; + + idx = _smc_nl_ueid_dump(skb, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, cb_ctx->pos[0]); + + cb_ctx->pos[0] = idx; + return skb->len; +} + +static bool _smc_clc_match_ueid(u8 *peer_ueid) +{ + struct smc_clc_eid_entry *tmp_ueid; + + list_for_each_entry(tmp_ueid, &smc_clc_eid_table.list, list) { + if (!memcmp(tmp_ueid->eid, peer_ueid, SMC_MAX_EID_LEN)) + return true; + } + return false; +} + +bool smc_clc_match_eid(u8 *negotiated_eid, + struct smc_clc_v2_extension *smc_v2_ext, + u8 *peer_eid, u8 *local_eid) +{ + bool match = false; + int i; + + negotiated_eid[0] = 0; + read_lock(&smc_clc_eid_table.lock); + if (smc_clc_eid_table.seid_enabled && + smc_v2_ext->hdr.flag.seid && + !memcmp(peer_eid, local_eid, SMC_MAX_EID_LEN)) { + memcpy(negotiated_eid, peer_eid, SMC_MAX_EID_LEN); + match = true; + goto out; + } + + for (i = 0; i < smc_v2_ext->hdr.eid_cnt; i++) { + if (_smc_clc_match_ueid(smc_v2_ext->user_eids[i])) { + memcpy(negotiated_eid, smc_v2_ext->user_eids[i], + SMC_MAX_EID_LEN); + match = true; + goto out; + } + } +out: + read_unlock(&smc_clc_eid_table.lock); + return match; +} + /* check arriving CLC proposal */ static bool smc_clc_msg_prop_valid(struct smc_clc_msg_proposal *pclc) { @@ -550,6 +768,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) if (ini->smc_type_v2 == SMC_TYPE_N) { pclc_smcd->v2_ext_offset = 0; } else { + struct smc_clc_eid_entry *ueident; u16 v2_ext_offset; u8 *eid = NULL; @@ -560,10 +779,19 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) pclc_prfx->ipv6_prefixes_cnt * sizeof(ipv6_prfx[0]); pclc_smcd->v2_ext_offset = htons(v2_ext_offset); - v2_ext->hdr.eid_cnt = 0; + + read_lock(&smc_clc_eid_table.lock); + v2_ext->hdr.eid_cnt = smc_clc_eid_table.ueid_cnt; + plen += smc_clc_eid_table.ueid_cnt * SMC_MAX_EID_LEN; + i = 0; + list_for_each_entry(ueident, &smc_clc_eid_table.list, list) { + memcpy(v2_ext->user_eids[i++], ueident->eid, + sizeof(ueident->eid)); + } + v2_ext->hdr.flag.seid = smc_clc_eid_table.seid_enabled; + read_unlock(&smc_clc_eid_table.lock); v2_ext->hdr.ism_gid_cnt = ini->ism_offered_cnt; v2_ext->hdr.flag.release = SMC_RELEASE; - v2_ext->hdr.flag.seid = 1; v2_ext->hdr.smcd_v2_ext_offset = htons(sizeof(*v2_ext) - offsetofend(struct smc_clnt_opts_area_hdr, smcd_v2_ext_offset) + @@ -572,7 +800,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) smc_ism_get_system_eid(ini->ism_dev[0], &eid); else smc_ism_get_system_eid(ini->ism_dev[1], &eid); - if (eid) + if (eid && v2_ext->hdr.flag.seid) memcpy(smcd_v2_ext->system_eid, eid, SMC_MAX_EID_LEN); plen += sizeof(*v2_ext) + sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { @@ -607,7 +835,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) } if (ini->smc_type_v2 != SMC_TYPE_N) { vec[i].iov_base = v2_ext; - vec[i++].iov_len = sizeof(*v2_ext); + vec[i++].iov_len = sizeof(*v2_ext) + + (v2_ext->hdr.eid_cnt * SMC_MAX_EID_LEN); vec[i].iov_base = smcd_v2_ext; vec[i++].iov_len = sizeof(*smcd_v2_ext); if (ini->ism_offered_cnt) { @@ -635,7 +864,8 @@ int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini) /* build and send CLC CONFIRM / ACCEPT message */ static int smc_clc_send_confirm_accept(struct smc_sock *smc, struct smc_clc_msg_accept_confirm_v2 *clc_v2, - int first_contact, u8 version) + int first_contact, u8 version, + u8 *eid) { struct smc_connection *conn = &smc->conn; struct smc_clc_msg_accept_confirm *clc; @@ -663,11 +893,8 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, if (version == SMC_V1) { clc->hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN); } else { - u8 *eid = NULL; - clc_v2->chid = htons(smc_ism_get_chid(conn->lgr->smcd)); - smc_ism_get_system_eid(conn->lgr->smcd, &eid); - if (eid) + if (eid[0]) memcpy(clc_v2->eid, eid, SMC_MAX_EID_LEN); len = SMCD_CLC_ACCEPT_CONFIRM_LEN_V2; if (first_contact) @@ -732,7 +959,7 @@ static int smc_clc_send_confirm_accept(struct smc_sock *smc, /* send CLC CONFIRM message across internal TCP socket */ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version) + u8 version, u8 *eid) { struct smc_clc_msg_accept_confirm_v2 cclc_v2; int reason_code = 0; @@ -742,7 +969,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, memset(&cclc_v2, 0, sizeof(cclc_v2)); cclc_v2.hdr.type = SMC_CLC_CONFIRM; len = smc_clc_send_confirm_accept(smc, &cclc_v2, clnt_first_contact, - version); + version, eid); if (len < ntohs(cclc_v2.hdr.length)) { if (len >= 0) { reason_code = -ENETUNREACH; @@ -757,7 +984,7 @@ int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, /* send CLC ACCEPT message across internal TCP socket */ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, - u8 version) + u8 version, u8 *negotiated_eid) { struct smc_clc_msg_accept_confirm_v2 aclc_v2; int len; @@ -765,7 +992,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, bool srv_first_contact, memset(&aclc_v2, 0, sizeof(aclc_v2)); aclc_v2.hdr.type = SMC_CLC_ACCEPT; len = smc_clc_send_confirm_accept(new_smc, &aclc_v2, srv_first_contact, - version); + version, negotiated_eid); if (len < ntohs(aclc_v2.hdr.length)) len = len >= 0 ? -EPROTO : -new_smc->clcsock->sk->sk_err; @@ -785,4 +1012,14 @@ void __init smc_clc_init(void) u = utsname(); memcpy(smc_hostname, u->nodename, min_t(size_t, strlen(u->nodename), sizeof(smc_hostname))); + + INIT_LIST_HEAD(&smc_clc_eid_table.list); + rwlock_init(&smc_clc_eid_table.lock); + smc_clc_eid_table.ueid_cnt = 0; + smc_clc_eid_table.seid_enabled = 1; +} + +void smc_clc_exit(void) +{ + smc_clc_ueid_remove(NULL); } diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 32d37f7b70f2..0699e0cee308 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -14,8 +14,10 @@ #define _SMC_CLC_H #include +#include #include "smc.h" +#include "smc_netlink.h" #define SMC_CLC_PROPOSAL 0x01 #define SMC_CLC_ACCEPT 0x02 @@ -158,6 +160,7 @@ struct smc_clc_msg_proposal { /* clc proposal message sent by Linux */ } __aligned(4); #define SMC_CLC_MAX_V6_PREFIX 8 +#define SMC_CLC_MAX_UEID 8 struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal pclc_base; @@ -165,6 +168,7 @@ struct smc_clc_msg_proposal_area { struct smc_clc_msg_proposal_prefix pclc_prfx; struct smc_clc_ipv6_prefix pclc_prfx_ipv6[SMC_CLC_MAX_V6_PREFIX]; struct smc_clc_v2_extension pclc_v2_ext; + u8 user_eids[SMC_CLC_MAX_UEID][SMC_MAX_EID_LEN]; struct smc_clc_smcd_v2_extension pclc_smcd_v2_ext; struct smc_clc_smcd_gid_chid pclc_gidchids[SMC_MAX_ISM_DEVS]; struct smc_clc_msg_trail pclc_trl; @@ -330,10 +334,18 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info, u8 version); int smc_clc_send_proposal(struct smc_sock *smc, struct smc_init_info *ini); int smc_clc_send_confirm(struct smc_sock *smc, bool clnt_first_contact, - u8 version); + u8 version, u8 *eid); int smc_clc_send_accept(struct smc_sock *smc, bool srv_first_contact, - u8 version); + u8 version, u8 *negotiated_eid); void smc_clc_init(void) __init; +void smc_clc_exit(void); void smc_clc_get_hostname(u8 **host); +bool smc_clc_match_eid(u8 *negotiated_eid, + struct smc_clc_v2_extension *smc_v2_ext, + u8 *peer_eid, u8 *local_eid); +int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index c043ecdca5c4..83d30b06016f 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -310,6 +310,7 @@ struct smc_init_info { u8 first_contact_local; unsigned short vlan_id; u32 rc; + u8 negotiated_eid[SMC_MAX_EID_LEN]; /* SMC-R */ struct smc_clc_msg_local *ib_lcl; struct smc_ib_device *ib_dev; diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 6fb6f96c1d17..4548ff2df245 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -19,11 +19,19 @@ #include "smc_core.h" #include "smc_ism.h" #include "smc_ib.h" +#include "smc_clc.h" #include "smc_stats.h" #include "smc_netlink.h" -#define SMC_CMD_MAX_ATTR 1 +const struct nla_policy +smc_gen_ueid_policy[SMC_NLA_EID_TABLE_MAX + 1] = { + [SMC_NLA_EID_TABLE_UNSPEC] = { .type = NLA_UNSPEC }, + [SMC_NLA_EID_TABLE_ENTRY] = { .type = NLA_STRING, + .len = SMC_MAX_EID_LEN, + }, +}; +#define SMC_CMD_MAX_ATTR 1 /* SMC_GENL generic netlink operation definition */ static const struct genl_ops smc_gen_nl_ops[] = { { @@ -66,6 +74,28 @@ static const struct genl_ops smc_gen_nl_ops[] = { /* can be retrieved by unprivileged users */ .dumpit = smc_nl_get_fback_stats, }, + { + .cmd = SMC_NETLINK_DUMP_UEID, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_ueid, + }, + { + .cmd = SMC_NETLINK_ADD_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_add_ueid, + .policy = smc_gen_ueid_policy, + }, + { + .cmd = SMC_NETLINK_REMOVE_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_remove_ueid, + .policy = smc_gen_ueid_policy, + }, + { + .cmd = SMC_NETLINK_FLUSH_UEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_flush_ueid, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { diff --git a/net/smc/smc_netlink.h b/net/smc/smc_netlink.h index 5ce2c0a89ccd..e8c6c3f0e98c 100644 --- a/net/smc/smc_netlink.h +++ b/net/smc/smc_netlink.h @@ -17,6 +17,8 @@ extern struct genl_family smc_gen_nl_family; +extern const struct nla_policy smc_gen_ueid_policy[]; + struct smc_nl_dmp_ctx { int pos[3]; }; -- cgit v1.2.3 From 3c572145c24e21c24e1cd0fd168011eaba85da8e Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Tue, 14 Sep 2021 10:35:07 +0200 Subject: net/smc: add generic netlink support for system EID With SMC-Dv2 users can configure if the static system EID should be used during CLC handshake, or if only user EIDs are allowed. Add generic netlink support to enable and disable the system EID, and to retrieve the system EID and its current enabled state. Signed-off-by: Karsten Graul Reviewed-by: Guvenc Gulce Signed-off-by: Guvenc Gulce Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 12 ++++++++++ net/smc/smc_clc.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++ net/smc/smc_clc.h | 3 +++ net/smc/smc_netlink.c | 15 ++++++++++++ 4 files changed, 92 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index e3728af2832b..b175bd0165a1 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -56,6 +56,9 @@ enum { SMC_NETLINK_ADD_UEID, SMC_NETLINK_REMOVE_UEID, SMC_NETLINK_FLUSH_UEID, + SMC_NETLINK_DUMP_SEID, + SMC_NETLINK_ENABLE_SEID, + SMC_NETLINK_DISABLE_SEID, }; /* SMC_GENL_FAMILY top level attributes */ @@ -257,4 +260,13 @@ enum { __SMC_NLA_EID_TABLE_MAX, SMC_NLA_EID_TABLE_MAX = __SMC_NLA_EID_TABLE_MAX - 1 }; + +/* SMC_NETLINK_SEID attributes */ +enum { + SMC_NLA_SEID_UNSPEC, + SMC_NLA_SEID_ENTRY, /* string */ + SMC_NLA_SEID_ENABLED, /* u8 */ + __SMC_NLA_SEID_TABLE_MAX, + SMC_NLA_SEID_TABLE_MAX = __SMC_NLA_SEID_TABLE_MAX - 1 +}; #endif /* _UAPI_LINUX_SMC_H */ diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 5a5ebf752860..4afd9e71e5c2 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -143,6 +143,10 @@ static int smc_clc_ueid_remove(char *ueid) rc = 0; } } + if (!rc && !smc_clc_eid_table.ueid_cnt) { + smc_clc_eid_table.seid_enabled = 1; + rc = -EAGAIN; /* indicate success and enabling of seid */ + } write_unlock(&smc_clc_eid_table.lock); return rc; } @@ -216,6 +220,64 @@ int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } +int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct smc_nl_dmp_ctx *cb_ctx = smc_nl_dmp_ctx(cb); + char seid_str[SMC_MAX_EID_LEN + 1]; + u8 seid_enabled; + void *hdr; + u8 *seid; + + if (cb_ctx->pos[0]) + return skb->len; + + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + &smc_gen_nl_family, NLM_F_MULTI, + SMC_NETLINK_DUMP_SEID); + if (!hdr) + return -ENOMEM; + if (!smc_ism_is_v2_capable()) + goto end; + + smc_ism_get_system_eid(&seid); + snprintf(seid_str, sizeof(seid_str), "%s", seid); + if (nla_put_string(skb, SMC_NLA_SEID_ENTRY, seid_str)) + goto err; + read_lock(&smc_clc_eid_table.lock); + seid_enabled = smc_clc_eid_table.seid_enabled; + read_unlock(&smc_clc_eid_table.lock); + if (nla_put_u8(skb, SMC_NLA_SEID_ENABLED, seid_enabled)) + goto err; +end: + genlmsg_end(skb, hdr); + cb_ctx->pos[0]++; + return skb->len; +err: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info) +{ + write_lock(&smc_clc_eid_table.lock); + smc_clc_eid_table.seid_enabled = 1; + write_unlock(&smc_clc_eid_table.lock); + return 0; +} + +int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info) +{ + int rc = 0; + + write_lock(&smc_clc_eid_table.lock); + if (!smc_clc_eid_table.ueid_cnt) + rc = -ENOENT; + else + smc_clc_eid_table.seid_enabled = 0; + write_unlock(&smc_clc_eid_table.lock); + return rc; +} + static bool _smc_clc_match_ueid(u8 *peer_ueid) { struct smc_clc_eid_entry *tmp_ueid; diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h index 0699e0cee308..974d01d16bb5 100644 --- a/net/smc/smc_clc.h +++ b/net/smc/smc_clc.h @@ -347,5 +347,8 @@ int smc_nl_dump_ueid(struct sk_buff *skb, struct netlink_callback *cb); int smc_nl_add_ueid(struct sk_buff *skb, struct genl_info *info); int smc_nl_remove_ueid(struct sk_buff *skb, struct genl_info *info); int smc_nl_flush_ueid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_dump_seid(struct sk_buff *skb, struct netlink_callback *cb); +int smc_nl_enable_seid(struct sk_buff *skb, struct genl_info *info); +int smc_nl_disable_seid(struct sk_buff *skb, struct genl_info *info); #endif diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index 4548ff2df245..f13ab0661ed5 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -96,6 +96,21 @@ static const struct genl_ops smc_gen_nl_ops[] = { .flags = GENL_ADMIN_PERM, .doit = smc_nl_flush_ueid, }, + { + .cmd = SMC_NETLINK_DUMP_SEID, + /* can be retrieved by unprivileged users */ + .dumpit = smc_nl_dump_seid, + }, + { + .cmd = SMC_NETLINK_ENABLE_SEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_enable_seid, + }, + { + .cmd = SMC_NETLINK_DISABLE_SEID, + .flags = GENL_ADMIN_PERM, + .doit = smc_nl_disable_seid, + }, }; static const struct nla_policy smc_gen_nl_policy[2] = { -- cgit v1.2.3 From 41ced4cd88020c9d4b71ff7c50d020f081efa4a0 Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 14 Sep 2021 15:30:09 -0700 Subject: btf: Change BTF_KIND_* macros to enums Change BTF_KIND_* macros to enums so they are encoded in dwarf and appear in vmlinux.h. This will make it easier for bpf programs to use these constants without macro definitions. Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210914223009.245307-1-yhs@fb.com --- include/uapi/linux/btf.h | 41 ++++++++++++++++++++++------------------- tools/include/uapi/linux/btf.h | 41 ++++++++++++++++++++++------------------- 2 files changed, 44 insertions(+), 38 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index d27b1708efe9..10e401073dd1 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -56,25 +56,28 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index d27b1708efe9..10e401073dd1 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -56,25 +56,28 @@ struct btf_type { #define BTF_INFO_VLEN(info) ((info) & 0xffff) #define BTF_INFO_KFLAG(info) ((info) >> 31) -#define BTF_KIND_UNKN 0 /* Unknown */ -#define BTF_KIND_INT 1 /* Integer */ -#define BTF_KIND_PTR 2 /* Pointer */ -#define BTF_KIND_ARRAY 3 /* Array */ -#define BTF_KIND_STRUCT 4 /* Struct */ -#define BTF_KIND_UNION 5 /* Union */ -#define BTF_KIND_ENUM 6 /* Enumeration */ -#define BTF_KIND_FWD 7 /* Forward */ -#define BTF_KIND_TYPEDEF 8 /* Typedef */ -#define BTF_KIND_VOLATILE 9 /* Volatile */ -#define BTF_KIND_CONST 10 /* Const */ -#define BTF_KIND_RESTRICT 11 /* Restrict */ -#define BTF_KIND_FUNC 12 /* Function */ -#define BTF_KIND_FUNC_PROTO 13 /* Function Proto */ -#define BTF_KIND_VAR 14 /* Variable */ -#define BTF_KIND_DATASEC 15 /* Section */ -#define BTF_KIND_FLOAT 16 /* Floating point */ -#define BTF_KIND_MAX BTF_KIND_FLOAT -#define NR_BTF_KINDS (BTF_KIND_MAX + 1) +enum { + BTF_KIND_UNKN = 0, /* Unknown */ + BTF_KIND_INT = 1, /* Integer */ + BTF_KIND_PTR = 2, /* Pointer */ + BTF_KIND_ARRAY = 3, /* Array */ + BTF_KIND_STRUCT = 4, /* Struct */ + BTF_KIND_UNION = 5, /* Union */ + BTF_KIND_ENUM = 6, /* Enumeration */ + BTF_KIND_FWD = 7, /* Forward */ + BTF_KIND_TYPEDEF = 8, /* Typedef */ + BTF_KIND_VOLATILE = 9, /* Volatile */ + BTF_KIND_CONST = 10, /* Const */ + BTF_KIND_RESTRICT = 11, /* Restrict */ + BTF_KIND_FUNC = 12, /* Function */ + BTF_KIND_FUNC_PROTO = 13, /* Function Proto */ + BTF_KIND_VAR = 14, /* Variable */ + BTF_KIND_DATASEC = 15, /* Section */ + BTF_KIND_FLOAT = 16, /* Floating point */ + + NR_BTF_KINDS, + BTF_KIND_MAX = NR_BTF_KINDS - 1, +}; /* For some specific BTF_KIND, "struct btf_type" is immediately * followed by extra data. -- cgit v1.2.3 From b5ea834dde6b6e7f75e51d5f66dac8cd7c97b5ef Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 14 Sep 2021 15:30:15 -0700 Subject: bpf: Support for new btf kind BTF_KIND_TAG LLVM14 added support for a new C attribute ([1]) __attribute__((btf_tag("arbitrary_str"))) This attribute will be emitted to dwarf ([2]) and pahole will convert it to BTF. Or for bpf target, this attribute will be emitted to BTF directly ([3], [4]). The attribute is intended to provide additional information for - struct/union type or struct/union member - static/global variables - static/global function or function parameter. For linux kernel, the btf_tag can be applied in various places to specify user pointer, function pre- or post- condition, function allow/deny in certain context, etc. Such information will be encoded in vmlinux BTF and can be used by verifier. The btf_tag can also be applied to bpf programs to help global verifiable functions, e.g., specifying preconditions, etc. This patch added basic parsing and checking support in kernel for new BTF_KIND_TAG kind. [1] https://reviews.llvm.org/D106614 [2] https://reviews.llvm.org/D106621 [3] https://reviews.llvm.org/D106622 [4] https://reviews.llvm.org/D109560 Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210914223015.245546-1-yhs@fb.com --- include/uapi/linux/btf.h | 14 ++++- kernel/bpf/btf.c | 128 +++++++++++++++++++++++++++++++++++++++++ tools/include/uapi/linux/btf.h | 14 ++++- 3 files changed, 154 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 10e401073dd1..642b6ecb37d7 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -74,6 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -173,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index dfe61df4f974..c3d605b22473 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,6 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", + [BTF_KIND_TAG] = "TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -459,6 +460,17 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } +static bool btf_type_is_tag(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_TAG; +} + +static bool btf_type_is_tag_target(const struct btf_type *t) +{ + return btf_type_is_func(t) || btf_type_is_struct(t) || + btf_type_is_var(t); +} + u32 btf_nr_types(const struct btf *btf) { u32 total = 0; @@ -537,6 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || + btf_type_is_tag(t) || btf_type_is_datasec(t); } @@ -563,6 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || + btf_type_is_tag(t) || btf_type_is_datasec(t); } @@ -616,6 +630,11 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } +static const struct btf_tag *btf_type_tag(const struct btf_type *t) +{ + return (const struct btf_tag *)(t + 1); +} + static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) { return kind_ops[BTF_INFO_KIND(t->info)]; @@ -3801,6 +3820,110 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; +static s32 btf_tag_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_tag *tag; + u32 meta_needed = sizeof(*tag); + s32 component_idx; + const char *value; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + value = btf_name_by_offset(env->btf, t->name_off); + if (!value || !value[0]) { + btf_verifier_log_type(env, t, "Invalid value"); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (btf_type_kflag(t)) { + btf_verifier_log_type(env, t, "Invalid btf_info kind_flag"); + return -EINVAL; + } + + component_idx = btf_type_tag(t)->component_idx; + if (component_idx < -1) { + btf_verifier_log_type(env, t, "Invalid component_idx"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_tag_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + s32 component_idx; + u32 vlen; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type || !btf_type_is_tag_target(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + component_idx = btf_type_tag(t)->component_idx; + if (component_idx != -1) { + if (btf_type_is_var(next_type)) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + + if (btf_type_is_struct(next_type)) { + vlen = btf_type_vlen(next_type); + } else { + /* next_type should be a function */ + next_type = btf_type_by_id(btf, next_type->type); + vlen = btf_type_vlen(next_type); + } + + if ((u32)component_idx >= vlen) { + btf_verifier_log_type(env, v->t, "Invalid component_idx"); + return -EINVAL; + } + } + + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +{ + btf_verifier_log(env, "type=%u component_idx=%d", t->type, + btf_type_tag(t)->component_idx); +} + +static const struct btf_kind_operations tag_ops = { + .check_meta = btf_tag_check_meta, + .resolve = btf_tag_resolve, + .check_member = btf_df_check_member, + .check_kflag_member = btf_df_check_kflag_member, + .log_details = btf_tag_log, + .show = btf_df_show, +}; + static int btf_func_proto_check(struct btf_verifier_env *env, const struct btf_type *t) { @@ -3935,6 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, + [BTF_KIND_TAG] = &tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4019,6 +4143,10 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); + if (btf_type_is_tag(t)) + return btf_resolved_type_id(btf, type_id) && + !btf_resolved_type_size(btf, type_id); + if (btf_type_is_modifier(t) || btf_type_is_ptr(t) || btf_type_is_var(t)) { t = btf_type_id_resolve(btf, &type_id); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 10e401073dd1..642b6ecb37d7 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and VAR. + * FUNC, FUNC_PROTO, VAR and TAG. * "type" is a type_id referring to another type. */ union { @@ -74,6 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ + BTF_KIND_TAG = 17, /* Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -173,4 +174,15 @@ struct btf_var_secinfo { __u32 size; }; +/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe + * additional information related to the tag applied location. + * If component_idx == -1, the tag is applied to a struct, union, + * variable or function. Otherwise, it is applied to a struct/union + * member or a func argument, and component_idx indicates which member + * or argument (0 ... vlen-1). + */ +struct btf_tag { + __s32 component_idx; +}; + #endif /* _UAPI__LINUX_BTF_H__ */ -- cgit v1.2.3 From 67f1e027c27054e641584655020a417eaac9cb3a Mon Sep 17 00:00:00 2001 From: Lukas Prediger Date: Tue, 14 Sep 2021 00:09:42 +0100 Subject: drivers/cdrom: improved ioctl for media change detection The current implementation of the CDROM_MEDIA_CHANGED ioctl relies on global state, meaning that only one process can detect a disc change while the ioctl call will return 0 for other calling processes afterwards (see bug 213267). This introduces a new cdrom ioctl, CDROM_TIMED_MEDIA_CHANGE, that works by maintaining a timestamp of the last detected disc change instead of a boolean flag: Processes calling this ioctl command can provide a timestamp of the last disc change known to them and receive an indication whether the disc was changed since then and the updated timestamp. I considered fixing the buggy behavior in the original CDROM_MEDIA_CHANGED ioctl but that would require maintaining state for each calling process in the kernel, which seems like a worse solution than introducing this new ioctl. Signed-off-by: Lukas Prediger Link: https://lore.kernel.org/all/20210912191207.74449-1-lumip@lumip.de Signed-off-by: Phillip Potter Link: https://lore.kernel.org/r/20210913230942.1188-1-phil@philpotter.co.uk Signed-off-by: Jens Axboe --- Documentation/cdrom/cdrom-standard.rst | 11 ++++++ Documentation/userspace-api/ioctl/cdrom.rst | 3 ++ drivers/cdrom/cdrom.c | 59 +++++++++++++++++++++++++++-- include/linux/cdrom.h | 1 + include/uapi/linux/cdrom.h | 19 ++++++++++ 5 files changed, 89 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst index 5845960ca382..52ea7b6b2fe8 100644 --- a/Documentation/cdrom/cdrom-standard.rst +++ b/Documentation/cdrom/cdrom-standard.rst @@ -907,6 +907,17 @@ commands can be identified by the underscores in their names. specifies the slot for which the information is given. The special value *CDSL_CURRENT* requests that information about the currently selected slot be returned. +`CDROM_TIMED_MEDIA_CHANGE` + Checks whether the disc has been changed since a user supplied time + and returns the time of the last disc change. + + *arg* is a pointer to a *cdrom_timed_media_change_info* struct. + *arg->last_media_change* may be set by calling code to signal + the timestamp of the last known media change (by the caller). + Upon successful return, this ioctl call will set + *arg->last_media_change* to the latest media change timestamp (in ms) + known by the kernel/driver and set *arg->has_changed* to 1 if + that timestamp is more recent than the timestamp set by the caller. `CDROM_DRIVE_STATUS` Returns the status of the drive by a call to *drive_status()*. Return values are defined in cdrom_drive_status_. diff --git a/Documentation/userspace-api/ioctl/cdrom.rst b/Documentation/userspace-api/ioctl/cdrom.rst index 3b4c0506de46..bac5bbf93ca0 100644 --- a/Documentation/userspace-api/ioctl/cdrom.rst +++ b/Documentation/userspace-api/ioctl/cdrom.rst @@ -54,6 +54,9 @@ are as follows: CDROM_SELECT_SPEED Set the CD-ROM speed CDROM_SELECT_DISC Select disc (for juke-boxes) CDROM_MEDIA_CHANGED Check is media changed + CDROM_TIMED_MEDIA_CHANGE Check if media changed + since given time + (struct cdrom_timed_media_change_info) CDROM_DRIVE_STATUS Get tray position, etc. CDROM_DISC_STATUS Get disc type, etc. CDROM_CHANGER_NSLOTS Get number of slots diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index bd2e5b1560f5..89a68457820a 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -344,6 +344,12 @@ static void cdrom_sysctl_register(void); static LIST_HEAD(cdrom_list); +static void signal_media_change(struct cdrom_device_info *cdi) +{ + cdi->mc_flags = 0x3; /* set media changed bits, on both queues */ + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); +} + int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi, struct packet_command *cgc) { @@ -616,6 +622,7 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi) ENSURE(cdo, generic_packet, CDC_GENERIC_PACKET); cdi->mc_flags = 0; cdi->options = CDO_USE_FFLAGS; + cdi->last_media_change_ms = ktime_to_ms(ktime_get()); if (autoclose == 1 && CDROM_CAN(CDC_CLOSE_TRAY)) cdi->options |= (int) CDO_AUTO_CLOSE; @@ -1421,8 +1428,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) cdi->ops->check_events(cdi, 0, slot); if (slot == CDSL_NONE) { - /* set media changed bits, on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); return cdrom_load_unload(cdi, -1); } @@ -1455,7 +1461,7 @@ static int cdrom_select_disc(struct cdrom_device_info *cdi, int slot) slot = curslot; /* set media changed bits on both queues */ - cdi->mc_flags = 0x3; + signal_media_change(cdi); if ((ret = cdrom_load_unload(cdi, slot))) return ret; @@ -1521,7 +1527,7 @@ int media_changed(struct cdrom_device_info *cdi, int queue) cdi->ioctl_events = 0; if (changed) { - cdi->mc_flags = 0x3; /* set bit on both queues */ + signal_media_change(cdi); ret |= 1; cdi->media_written = 0; } @@ -2336,6 +2342,49 @@ static int cdrom_ioctl_media_changed(struct cdrom_device_info *cdi, return ret; } +/* + * Media change detection with timing information. + * + * arg is a pointer to a cdrom_timed_media_change_info struct. + * arg->last_media_change may be set by calling code to signal + * the timestamp (in ms) of the last known media change (by the caller). + * Upon successful return, ioctl call will set arg->last_media_change + * to the latest media change timestamp known by the kernel/driver + * and set arg->has_changed to 1 if that timestamp is more recent + * than the timestamp set by the caller. + */ +static int cdrom_ioctl_timed_media_change(struct cdrom_device_info *cdi, + unsigned long arg) +{ + int ret; + struct cdrom_timed_media_change_info __user *info; + struct cdrom_timed_media_change_info tmp_info; + + if (!CDROM_CAN(CDC_MEDIA_CHANGED)) + return -ENOSYS; + + info = (struct cdrom_timed_media_change_info __user *)arg; + cd_dbg(CD_DO_IOCTL, "entering CDROM_TIMED_MEDIA_CHANGE\n"); + + ret = cdrom_ioctl_media_changed(cdi, CDSL_CURRENT); + if (ret < 0) + return ret; + + if (copy_from_user(&tmp_info, info, sizeof(tmp_info)) != 0) + return -EFAULT; + + tmp_info.media_flags = 0; + if (tmp_info.last_media_change - cdi->last_media_change_ms < 0) + tmp_info.media_flags |= MEDIA_CHANGED_FLAG; + + tmp_info.last_media_change = cdi->last_media_change_ms; + + if (copy_to_user(info, &tmp_info, sizeof(*info)) != 0) + return -EFAULT; + + return 0; +} + static int cdrom_ioctl_set_options(struct cdrom_device_info *cdi, unsigned long arg) { @@ -3313,6 +3362,8 @@ int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, return cdrom_ioctl_eject_sw(cdi, arg); case CDROM_MEDIA_CHANGED: return cdrom_ioctl_media_changed(cdi, arg); + case CDROM_TIMED_MEDIA_CHANGE: + return cdrom_ioctl_timed_media_change(cdi, arg); case CDROM_SET_OPTIONS: return cdrom_ioctl_set_options(cdi, arg); case CDROM_CLEAR_OPTIONS: diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index c4fef00abdf3..0a89f111e00e 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -64,6 +64,7 @@ struct cdrom_device_info { int for_data; int (*exit)(struct cdrom_device_info *); int mrw_mode_page; + __s64 last_media_change_ms; }; struct cdrom_device_ops { diff --git a/include/uapi/linux/cdrom.h b/include/uapi/linux/cdrom.h index 6c34f6e2f1f7..804ff8d98f71 100644 --- a/include/uapi/linux/cdrom.h +++ b/include/uapi/linux/cdrom.h @@ -147,6 +147,8 @@ #define CDROM_NEXT_WRITABLE 0x5394 /* get next writable block */ #define CDROM_LAST_WRITTEN 0x5395 /* get last block written on disc */ +#define CDROM_TIMED_MEDIA_CHANGE 0x5396 /* get the timestamp of the last media change */ + /******************************************************* * CDROM IOCTL structures *******************************************************/ @@ -295,6 +297,23 @@ struct cdrom_generic_command }; }; +/* This struct is used by CDROM_TIMED_MEDIA_CHANGE */ +struct cdrom_timed_media_change_info { + __s64 last_media_change; /* Timestamp of the last detected media + * change in ms. May be set by caller, + * updated upon successful return of + * ioctl. + */ + __u64 media_flags; /* Flags returned by ioctl to indicate + * media status. + */ +}; +#define MEDIA_CHANGED_FLAG 0x1 /* Last detected media change was more + * recent than last_media_change set by + * caller. + */ +/* other bits of media_flags available for future use */ + /* * A CD-ROM physical sector size is 2048, 2052, 2056, 2324, 2332, 2336, * 2340, or 2352 bytes long. -- cgit v1.2.3 From f8d858e607b2a36808ac6d4218f5f5203d7a7d63 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 14 Sep 2021 16:46:33 +0200 Subject: xfrm: make user policy API complete >From a userland POV, this API was based on some magic values: - dirmask and action were bitfields but meaning of bits (XFRM_POL_DEFAULT_*) are not exported; - action is confusing, if a bit is set, does it mean drop or accept? Let's try to simplify this uapi by using explicit field and macros. Fixes: 2d151d39073a ("xfrm: Add possibility to set the default to block if we have no policy") Signed-off-by: Nicolas Dichtel Signed-off-by: Steffen Klassert --- include/uapi/linux/xfrm.h | 9 ++++++--- net/xfrm/xfrm_user.c | 36 +++++++++++++++++++----------------- 2 files changed, 25 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h index 26f456b1f33e..eda0426ec4c2 100644 --- a/include/uapi/linux/xfrm.h +++ b/include/uapi/linux/xfrm.h @@ -514,9 +514,12 @@ struct xfrm_user_offload { #define XFRM_OFFLOAD_INBOUND 2 struct xfrm_userpolicy_default { -#define XFRM_USERPOLICY_DIRMASK_MAX (sizeof(__u8) * 8) - __u8 dirmask; - __u8 action; +#define XFRM_USERPOLICY_UNSPEC 0 +#define XFRM_USERPOLICY_BLOCK 1 +#define XFRM_USERPOLICY_ACCEPT 2 + __u8 in; + __u8 fwd; + __u8 out; }; #ifndef __KERNEL__ diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 4719a6d54aa6..90c88390f1fe 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1966,16 +1966,21 @@ static int xfrm_set_default(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct xfrm_userpolicy_default *up = nlmsg_data(nlh); - u8 dirmask; - u8 old_default = net->xfrm.policy_default; - if (up->dirmask >= XFRM_USERPOLICY_DIRMASK_MAX) - return -EINVAL; + if (up->in == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_IN; + else if (up->in == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_IN; - dirmask = (1 << up->dirmask) & XFRM_POL_DEFAULT_MASK; + if (up->fwd == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_FWD; + else if (up->fwd == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_FWD; - net->xfrm.policy_default = (old_default & (0xff ^ dirmask)) - | (up->action << up->dirmask); + if (up->out == XFRM_USERPOLICY_BLOCK) + net->xfrm.policy_default |= XFRM_POL_DEFAULT_OUT; + else if (up->out == XFRM_USERPOLICY_ACCEPT) + net->xfrm.policy_default &= ~XFRM_POL_DEFAULT_OUT; rt_genid_bump_all(net); @@ -1988,13 +1993,11 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, struct sk_buff *r_skb; struct nlmsghdr *r_nlh; struct net *net = sock_net(skb->sk); - struct xfrm_userpolicy_default *r_up, *up; + struct xfrm_userpolicy_default *r_up; int len = NLMSG_ALIGN(sizeof(struct xfrm_userpolicy_default)); u32 portid = NETLINK_CB(skb).portid; u32 seq = nlh->nlmsg_seq; - up = nlmsg_data(nlh); - r_skb = nlmsg_new(len, GFP_ATOMIC); if (!r_skb) return -ENOMEM; @@ -2005,15 +2008,14 @@ static int xfrm_get_default(struct sk_buff *skb, struct nlmsghdr *nlh, return -EMSGSIZE; } - if (up->dirmask >= XFRM_USERPOLICY_DIRMASK_MAX) { - kfree_skb(r_skb); - return -EINVAL; - } - r_up = nlmsg_data(r_nlh); - r_up->action = ((net->xfrm.policy_default & (1 << up->dirmask)) >> up->dirmask); - r_up->dirmask = up->dirmask; + r_up->in = net->xfrm.policy_default & XFRM_POL_DEFAULT_IN ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + r_up->fwd = net->xfrm.policy_default & XFRM_POL_DEFAULT_FWD ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; + r_up->out = net->xfrm.policy_default & XFRM_POL_DEFAULT_OUT ? + XFRM_USERPOLICY_BLOCK : XFRM_USERPOLICY_ACCEPT; nlmsg_end(r_skb, r_nlh); return nlmsg_unicast(net->xfrm.nlsk, r_skb, portid); -- cgit v1.2.3 From 336562752acc1a723f9a24b5b8129ae22e0478c6 Mon Sep 17 00:00:00 2001 From: Matteo Croce Date: Wed, 15 Sep 2021 01:54:00 +0200 Subject: bpf: Update bpf_get_smp_processor_id() documentation BPF programs run with migration disabled regardless of preemption, as they are protected by migrate_disable(). Update the uapi documentation accordingly. Signed-off-by: Matteo Croce Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20210914235400.59427-1-mcroce@linux.microsoft.com --- include/uapi/linux/bpf.h | 2 +- tools/include/uapi/linux/bpf.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index d21326558d42..3e9785f1064a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index d21326558d42..3e9785f1064a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1629,7 +1629,7 @@ union bpf_attr { * u32 bpf_get_smp_processor_id(void) * Description * Get the SMP (symmetric multiprocessing) processor id. Note that - * all programs run with preemption disabled, which means that the + * all programs run with migration disabled, which means that the * SMP processor id is stable during all the execution of the * program. * Return -- cgit v1.2.3 From 227b9644ab16d2ecd98d593edbe15c32c0c9620a Mon Sep 17 00:00:00 2001 From: Tianjia Zhang Date: Thu, 16 Sep 2021 11:37:38 +0800 Subject: net/tls: support SM4 GCM/CCM algorithm The RFC8998 specification defines the use of the ShangMi algorithm cipher suites in TLS 1.3, and also supports the GCM/CCM mode using the SM4 algorithm. Signed-off-by: Tianjia Zhang Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- include/uapi/linux/tls.h | 30 ++++++++++++++++++++++++++++++ net/tls/tls_main.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++ net/tls/tls_sw.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/tls.h b/include/uapi/linux/tls.h index 0d54baea1d8d..5f38be0ec0f3 100644 --- a/include/uapi/linux/tls.h +++ b/include/uapi/linux/tls.h @@ -84,6 +84,20 @@ #define TLS_CIPHER_CHACHA20_POLY1305_TAG_SIZE 16 #define TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE 8 +#define TLS_CIPHER_SM4_GCM 55 +#define TLS_CIPHER_SM4_GCM_IV_SIZE 8 +#define TLS_CIPHER_SM4_GCM_KEY_SIZE 16 +#define TLS_CIPHER_SM4_GCM_SALT_SIZE 4 +#define TLS_CIPHER_SM4_GCM_TAG_SIZE 16 +#define TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE 8 + +#define TLS_CIPHER_SM4_CCM 56 +#define TLS_CIPHER_SM4_CCM_IV_SIZE 8 +#define TLS_CIPHER_SM4_CCM_KEY_SIZE 16 +#define TLS_CIPHER_SM4_CCM_SALT_SIZE 4 +#define TLS_CIPHER_SM4_CCM_TAG_SIZE 16 +#define TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE 8 + #define TLS_SET_RECORD_TYPE 1 #define TLS_GET_RECORD_TYPE 2 @@ -124,6 +138,22 @@ struct tls12_crypto_info_chacha20_poly1305 { unsigned char rec_seq[TLS_CIPHER_CHACHA20_POLY1305_REC_SEQ_SIZE]; }; +struct tls12_crypto_info_sm4_gcm { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_SM4_GCM_IV_SIZE]; + unsigned char key[TLS_CIPHER_SM4_GCM_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_SM4_GCM_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE]; +}; + +struct tls12_crypto_info_sm4_ccm { + struct tls_crypto_info info; + unsigned char iv[TLS_CIPHER_SM4_CCM_IV_SIZE]; + unsigned char key[TLS_CIPHER_SM4_CCM_KEY_SIZE]; + unsigned char salt[TLS_CIPHER_SM4_CCM_SALT_SIZE]; + unsigned char rec_seq[TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE]; +}; + enum { TLS_INFO_UNSPEC, TLS_INFO_VERSION, diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index fde56ff49163..d44399efeac6 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -421,6 +421,46 @@ static int do_tls_getsockopt_conf(struct sock *sk, char __user *optval, rc = -EFAULT; break; } + case TLS_CIPHER_SM4_GCM: { + struct tls12_crypto_info_sm4_gcm *sm4_gcm_info = + container_of(crypto_info, + struct tls12_crypto_info_sm4_gcm, info); + + if (len != sizeof(*sm4_gcm_info)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(sm4_gcm_info->iv, + cctx->iv + TLS_CIPHER_SM4_GCM_SALT_SIZE, + TLS_CIPHER_SM4_GCM_IV_SIZE); + memcpy(sm4_gcm_info->rec_seq, cctx->rec_seq, + TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, sm4_gcm_info, sizeof(*sm4_gcm_info))) + rc = -EFAULT; + break; + } + case TLS_CIPHER_SM4_CCM: { + struct tls12_crypto_info_sm4_ccm *sm4_ccm_info = + container_of(crypto_info, + struct tls12_crypto_info_sm4_ccm, info); + + if (len != sizeof(*sm4_ccm_info)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(sm4_ccm_info->iv, + cctx->iv + TLS_CIPHER_SM4_CCM_SALT_SIZE, + TLS_CIPHER_SM4_CCM_IV_SIZE); + memcpy(sm4_ccm_info->rec_seq, cctx->rec_seq, + TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, sm4_ccm_info, sizeof(*sm4_ccm_info))) + rc = -EFAULT; + break; + } default: rc = -EINVAL; } @@ -524,6 +564,12 @@ static int do_tls_setsockopt_conf(struct sock *sk, sockptr_t optval, case TLS_CIPHER_CHACHA20_POLY1305: optsize = sizeof(struct tls12_crypto_info_chacha20_poly1305); break; + case TLS_CIPHER_SM4_GCM: + optsize = sizeof(struct tls12_crypto_info_sm4_gcm); + break; + case TLS_CIPHER_SM4_CCM: + optsize = sizeof(struct tls12_crypto_info_sm4_ccm); + break; default: rc = -EINVAL; goto err_crypto_info; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 4feb95e34b64..989d1423a245 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -2424,6 +2424,40 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) cipher_name = "rfc7539(chacha20,poly1305)"; break; } + case TLS_CIPHER_SM4_GCM: { + struct tls12_crypto_info_sm4_gcm *sm4_gcm_info; + + sm4_gcm_info = (void *)crypto_info; + nonce_size = TLS_CIPHER_SM4_GCM_IV_SIZE; + tag_size = TLS_CIPHER_SM4_GCM_TAG_SIZE; + iv_size = TLS_CIPHER_SM4_GCM_IV_SIZE; + iv = sm4_gcm_info->iv; + rec_seq_size = TLS_CIPHER_SM4_GCM_REC_SEQ_SIZE; + rec_seq = sm4_gcm_info->rec_seq; + keysize = TLS_CIPHER_SM4_GCM_KEY_SIZE; + key = sm4_gcm_info->key; + salt = sm4_gcm_info->salt; + salt_size = TLS_CIPHER_SM4_GCM_SALT_SIZE; + cipher_name = "gcm(sm4)"; + break; + } + case TLS_CIPHER_SM4_CCM: { + struct tls12_crypto_info_sm4_ccm *sm4_ccm_info; + + sm4_ccm_info = (void *)crypto_info; + nonce_size = TLS_CIPHER_SM4_CCM_IV_SIZE; + tag_size = TLS_CIPHER_SM4_CCM_TAG_SIZE; + iv_size = TLS_CIPHER_SM4_CCM_IV_SIZE; + iv = sm4_ccm_info->iv; + rec_seq_size = TLS_CIPHER_SM4_CCM_REC_SEQ_SIZE; + rec_seq = sm4_ccm_info->rec_seq; + keysize = TLS_CIPHER_SM4_CCM_KEY_SIZE; + key = sm4_ccm_info->key; + salt = sm4_ccm_info->salt; + salt_size = TLS_CIPHER_SM4_CCM_SALT_SIZE; + cipher_name = "ccm(sm4)"; + break; + } default: rc = -EINVAL; goto free_priv; -- cgit v1.2.3 From 10aceb629e198429c849d5e995c3bb1ba7a9aaa3 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:05 -0700 Subject: bpf: Add bpf_trace_vprintk helper This helper is meant to be "bpf_trace_printk, but with proper vararg support". Follow bpf_snprintf's example and take a u64 pseudo-vararg array. Write to /sys/kernel/debug/tracing/trace_pipe using the same mechanism as bpf_trace_printk. The functionality of this helper was requested in the libbpf issue tracker [0]. [0] Closes: https://github.com/libbpf/libbpf/issues/315 Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-4-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 11 +++++++++ kernel/bpf/core.c | 5 ++++ kernel/bpf/helpers.c | 2 ++ kernel/trace/bpf_trace.c | 52 +++++++++++++++++++++++++++++++++++++++++- tools/include/uapi/linux/bpf.h | 11 +++++++++ 6 files changed, 81 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be8d57e6e78a..b6c45a6cbbba 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1088,6 +1088,7 @@ bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *f int bpf_prog_calc_tag(struct bpf_prog *fp); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void); typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src, unsigned long off, unsigned long len); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 9f4636d021b1..6fddc13fe67f 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2357,6 +2357,11 @@ const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void) return NULL; } +const struct bpf_func_proto * __weak bpf_get_trace_vprintk_proto(void) +{ + return NULL; +} + u64 __weak bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 8f9f392c1322..2c604ff8c7fb 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1435,6 +1435,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_snprintf_proto; case BPF_FUNC_task_pt_regs: return &bpf_task_pt_regs_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return NULL; } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 4ec779fa0c1d..6b3153841a33 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -398,7 +398,7 @@ static const struct bpf_func_proto bpf_trace_printk_proto = { .arg2_type = ARG_CONST_SIZE, }; -const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +static void __set_printk_clr_event(void) { /* * This program might be calling bpf_trace_printk, @@ -410,10 +410,58 @@ const struct bpf_func_proto *bpf_get_trace_printk_proto(void) */ if (trace_set_clr_event("bpf_trace", "bpf_trace_printk", 1)) pr_warn_ratelimited("could not enable bpf_trace_printk events"); +} +const struct bpf_func_proto *bpf_get_trace_printk_proto(void) +{ + __set_printk_clr_event(); return &bpf_trace_printk_proto; } +BPF_CALL_4(bpf_trace_vprintk, char *, fmt, u32, fmt_size, const void *, data, + u32, data_len) +{ + static char buf[BPF_TRACE_PRINTK_SIZE]; + unsigned long flags; + int ret, num_args; + u32 *bin_args; + + if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 || + (data_len && !data)) + return -EINVAL; + num_args = data_len / 8; + + ret = bpf_bprintf_prepare(fmt, fmt_size, data, &bin_args, num_args); + if (ret < 0) + return ret; + + raw_spin_lock_irqsave(&trace_printk_lock, flags); + ret = bstr_printf(buf, sizeof(buf), fmt, bin_args); + + trace_bpf_trace_printk(buf); + raw_spin_unlock_irqrestore(&trace_printk_lock, flags); + + bpf_bprintf_cleanup(); + + return ret; +} + +static const struct bpf_func_proto bpf_trace_vprintk_proto = { + .func = bpf_trace_vprintk, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_PTR_TO_MEM_OR_NULL, + .arg4_type = ARG_CONST_SIZE_OR_ZERO, +}; + +const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void) +{ + __set_printk_clr_event(); + return &bpf_trace_vprintk_proto; +} + BPF_CALL_5(bpf_seq_printf, struct seq_file *, m, char *, fmt, u32, fmt_size, const void *, data, u32, data_len) { @@ -1160,6 +1208,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_func_ip_proto_tracing; case BPF_FUNC_get_branch_snapshot: return &bpf_get_branch_snapshot_proto; + case BPF_FUNC_trace_vprintk: + return bpf_get_trace_vprintk_proto(); default: return bpf_base_func_proto(func_id); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 3e9785f1064a..98ca79a67937 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4898,6 +4898,16 @@ union bpf_attr { * **-EINVAL** if *flags* is not zero. * * **-ENOENT** if architecture does not support branch records. + * + * long bpf_trace_vprintk(const char *fmt, u32 fmt_size, const void *data, u32 data_len) + * Description + * Behaves like **bpf_trace_printk**\ () helper, but takes an array of u64 + * to format and can handle more format args as a result. + * + * Arguments are to be used as in **bpf_seq_printf**\ () helper. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5077,6 +5087,7 @@ union bpf_attr { FN(get_attach_cookie), \ FN(task_pt_regs), \ FN(get_branch_snapshot), \ + FN(trace_vprintk), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From a42effb0b24fcaf49513c2d7d77ef6daa9e32a6f Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Fri, 17 Sep 2021 11:29:11 -0700 Subject: bpf: Clarify data_len param in bpf_snprintf and bpf_seq_printf comments Since the data_len in these two functions is a byte len of the preceding u64 *data array, it must always be a multiple of 8. If this isn't the case both helpers error out, so let's make the requirement explicit so users don't need to infer it. Signed-off-by: Dave Marchevsky Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20210917182911.2426606-10-davemarchevsky@fb.com --- include/uapi/linux/bpf.h | 5 +++-- tools/include/uapi/linux/bpf.h | 5 +++-- 2 files changed, 6 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 98ca79a67937..6fc59d61937a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 98ca79a67937..6fc59d61937a 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4046,7 +4046,7 @@ union bpf_attr { * arguments. The *data* are a **u64** array and corresponding format string * values are stored in the array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* array. - * The *data_len* is the size of *data* in bytes. + * The *data_len* is the size of *data* in bytes - must be a multiple of 8. * * Formats **%s**, **%p{i,I}{4,6}** requires to read kernel memory. * Reading kernel memory may fail due to either invalid address or @@ -4751,7 +4751,8 @@ union bpf_attr { * Each format specifier in **fmt** corresponds to one u64 element * in the **data** array. For strings and pointers where pointees * are accessed, only the pointer values are stored in the *data* - * array. The *data_len* is the size of *data* in bytes. + * array. The *data_len* is the size of *data* in bytes - must be + * a multiple of 8. * * Formats **%s** and **%p{i,I}{4,6}** require to read kernel * memory. Reading kernel memory may fail due to either invalid -- cgit v1.2.3 From 55c42fa7fa331f98062c32799456420930b8bf8c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:19 -0700 Subject: mptcp: add MPTCP_INFO getsockopt Its not compatible with multipath-tcp.org kernel one. 1. The out-of-tree implementation defines a different 'struct mptcp_info', with embedded __user addresses for additional data such as endpoint addresses. 2. Mat Martineau points out that embedded __user addresses doesn't work with BPF_CGROUP_RUN_PROG_GETSOCKOPT() which assumes that copying in optsize bytes from optval provides all data that got copied to userspace. This provides mptcp_info data for the given mptcp socket. Userspace sets optlen to the size of the structure it expects. The kernel updates it to contain the number of bytes that it copied. This allows to append more information to the structure later. Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/uapi/linux/mptcp.h | 3 +++ net/mptcp/sockopt.c | 40 +++++++++++++++++++++++++++++++++++++++- 3 files changed, 43 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 041d6032a348..7612d760b6a9 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -364,6 +364,7 @@ struct ucred { #define SOL_KCM 281 #define SOL_TLS 282 #define SOL_XDP 283 +#define SOL_MPTCP 284 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index f66038b9551f..3e9caeddda7e 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -193,4 +193,7 @@ enum mptcp_event_attr { #define MPTCP_RST_EBADPERF 5 #define MPTCP_RST_EMIDDLEBOX 6 +/* MPTCP socket options */ +#define MPTCP_INFO 1 + #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 54f0d521a399..f7683c22911f 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -673,10 +673,14 @@ out: void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) { struct sock *sk = &msk->sk.icsk_inet.sk; - bool slow = lock_sock_fast(sk); u32 flags = 0; + bool slow; u8 val; + memset(info, 0, sizeof(*info)); + + slow = lock_sock_fast(sk); + info->mptcpi_subflows = READ_ONCE(msk->pm.subflows); info->mptcpi_add_addr_signal = READ_ONCE(msk->pm.add_addr_signaled); info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); @@ -702,6 +706,27 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); +static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, int __user *optlen) +{ + struct mptcp_info m_info; + int len; + + if (get_user(len, optlen)) + return -EFAULT; + + len = min_t(unsigned int, len, sizeof(struct mptcp_info)); + + mptcp_diag_fill_info(msk, &m_info); + + if (put_user(len, optlen)) + return -EFAULT; + + if (copy_to_user(optval, &m_info, len)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -716,6 +741,17 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, return -EOPNOTSUPP; } +static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, + char __user *optval, int __user *optlen) +{ + switch (optname) { + case MPTCP_INFO: + return mptcp_getsockopt_info(msk, optval, optlen); + } + + return -EOPNOTSUPP; +} + int mptcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *option) { @@ -738,6 +774,8 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname, if (level == SOL_TCP) return mptcp_getsockopt_sol_tcp(msk, optname, optval, option); + if (level == SOL_MPTCP) + return mptcp_getsockopt_sol_mptcp(msk, optname, optval, option); return -EOPNOTSUPP; } -- cgit v1.2.3 From 06f15cee369535a383c9c82ed37a25f0a413f6f1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:20 -0700 Subject: mptcp: add MPTCP_TCPINFO getsockopt support Allow users to retrieve TCP_INFO data of all subflows. Users need to pre-initialize a meta header that has to be prepended to the data buffer that will be filled with the tcp info data. The meta header looks like this: struct mptcp_subflow_data { __u32 size_subflow_data;/* size of this structure in userspace */ __u32 num_subflows; /* must be 0, set by kernel */ __u32 size_kernel; /* must be 0, set by kernel */ __u32 size_user; /* size of one element in data[] */ } __attribute__((aligned(8))); size_subflow_data has to be set to 'sizeof(struct mptcp_subflow_data)'. This allows to extend mptcp_subflow_data structure later on without breaking backwards compatibility. If the structure is extended later on, kernel knows where the userspace-provided meta header ends, even if userspace uses an older (smaller) version of the structure. num_subflows must be set to 0. If the getsockopt request succeeds (return value is 0), it will be updated to contain the number of active subflows for the given logical connection. size_kernel must be set to 0. If the getsockopt request is successful, it will contain the size of the 'struct tcp_info' as known by the kernel. This is informational only. size_user must be set to 'sizeof(struct tcp_info)'. This allows the kernel to only fill in the space reserved/expected by userspace. Example: struct my_tcp_info { struct mptcp_subflow_data d; struct tcp_info ti[2]; }; struct my_tcp_info ti; socklen_t olen; memset(&ti, 0, sizeof(ti)); ti.d.size_subflow_data = sizeof(struct mptcp_subflow_data); ti.d.size_user = sizeof(struct tcp_info); olen = sizeof(ti); ret = getsockopt(fd, SOL_MPTCP, MPTCP_TCPINFO, &ti, &olen); if (ret < 0) die_perror("getsockopt MPTCP_TCPINFO"); mptcp_subflow_data.num_subflows is populated with the number of subflows that exist on the kernel side for the logical mptcp connection. This allows userspace to re-try with a larger tcp_info array if the number of subflows was larger than the available space in the ti[] array. olen has to be set to the number of bytes that userspace has allocated to receive the kernel data. It will be updated to contain the real number bytes that have been copied to by the kernel. In the above example, if the number if subflows was 1, olen is equal to 'sizeof(struct mptcp_subflow_data) + sizeof(struct tcp_info). For 2 or more subflows olen is equal to 'sizeof(struct my_tcp_info)'. If there was more data that could not be copied due to lack of space in the option buffer, userspace can detect this by checking mptcp_subflow_data->num_subflows. Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 10 +++- net/mptcp/sockopt.c | 115 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 124 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3e9caeddda7e..3f013a513770 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -193,7 +193,15 @@ enum mptcp_event_attr { #define MPTCP_RST_EBADPERF 5 #define MPTCP_RST_EMIDDLEBOX 6 +struct mptcp_subflow_data { + __u32 size_subflow_data; /* size of this structure in userspace */ + __u32 num_subflows; /* must be 0, set by kernel */ + __u32 size_kernel; /* must be 0, set by kernel */ + __u32 size_user; /* size of one element in data[] */ +} __attribute__((aligned(8))); + /* MPTCP socket options */ -#define MPTCP_INFO 1 +#define MPTCP_INFO 1 +#define MPTCP_TCPINFO 2 #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index f7683c22911f..eb2905bfa089 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -14,6 +14,8 @@ #include #include "protocol.h" +#define MIN_INFO_OPTLEN_SIZE 16 + static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { sock_owned_by_me((const struct sock *)msk); @@ -727,6 +729,117 @@ static int mptcp_getsockopt_info(struct mptcp_sock *msk, char __user *optval, in return 0; } +static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd, + char __user *optval, + u32 copied, + int __user *optlen) +{ + u32 copylen = min_t(u32, sfd->size_subflow_data, sizeof(*sfd)); + + if (copied) + copied += sfd->size_subflow_data; + else + copied = copylen; + + if (put_user(copied, optlen)) + return -EFAULT; + + if (copy_to_user(optval, sfd, copylen)) + return -EFAULT; + + return 0; +} + +static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd, + char __user *optval, int __user *optlen) +{ + int len, copylen; + + if (get_user(len, optlen)) + return -EFAULT; + + /* if mptcp_subflow_data size is changed, need to adjust + * this function to deal with programs using old version. + */ + BUILD_BUG_ON(sizeof(*sfd) != MIN_INFO_OPTLEN_SIZE); + + if (len < MIN_INFO_OPTLEN_SIZE) + return -EINVAL; + + memset(sfd, 0, sizeof(*sfd)); + + copylen = min_t(unsigned int, len, sizeof(*sfd)); + if (copy_from_user(sfd, optval, copylen)) + return -EFAULT; + + /* size_subflow_data is u32, but len is signed */ + if (sfd->size_subflow_data > INT_MAX || + sfd->size_user > INT_MAX) + return -EINVAL; + + if (sfd->size_subflow_data < MIN_INFO_OPTLEN_SIZE || + sfd->size_subflow_data > len) + return -EINVAL; + + if (sfd->num_subflows || sfd->size_kernel) + return -EINVAL; + + return len - sfd->size_subflow_data; +} + +static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + struct mptcp_subflow_context *subflow; + struct sock *sk = &msk->sk.icsk_inet.sk; + unsigned int sfcount = 0, copied = 0; + struct mptcp_subflow_data sfd; + char __user *infoptr; + int len; + + len = mptcp_get_subflow_data(&sfd, optval, optlen); + if (len < 0) + return len; + + sfd.size_kernel = sizeof(struct tcp_info); + sfd.size_user = min_t(unsigned int, sfd.size_user, + sizeof(struct tcp_info)); + + infoptr = optval + sfd.size_subflow_data; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ++sfcount; + + if (len && len >= sfd.size_user) { + struct tcp_info info; + + tcp_get_info(ssk, &info); + + if (copy_to_user(infoptr, &info, sfd.size_user)) { + release_sock(sk); + return -EFAULT; + } + + infoptr += sfd.size_user; + copied += sfd.size_user; + len -= sfd.size_user; + } + } + + release_sock(sk); + + sfd.num_subflows = sfcount; + + if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -747,6 +860,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, switch (optname) { case MPTCP_INFO: return mptcp_getsockopt_info(msk, optval, optlen); + case MPTCP_TCPINFO: + return mptcp_getsockopt_tcpinfo(msk, optval, optlen); } return -EOPNOTSUPP; -- cgit v1.2.3 From c11c5906bc0aba62a78da69035f6b30c6da6d13b Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Fri, 17 Sep 2021 16:33:21 -0700 Subject: mptcp: add MPTCP_SUBFLOW_ADDRS getsockopt support This retrieves the address pairs of all subflows currently active for a given mptcp connection. It re-uses the same meta-header as for MPTCP_TCPINFO. A new structure is provided to hold the subflow address data: struct mptcp_subflow_addrs { union { __kernel_sa_family_t sa_family; struct sockaddr sa_local; struct sockaddr_in sin_local; struct sockaddr_in6 sin6_local; struct sockaddr_storage ss_local; }; union { struct sockaddr sa_remote; struct sockaddr_in sin_remote; struct sockaddr_in6 sin6_remote; struct sockaddr_storage ss_remote; }; }; Usage of the new getsockopt is very similar to MPTCP_TCPINFO one. Userspace allocates a 'struct mptcp_subflow_data', followed by one or more 'struct mptcp_subflow_addrs', then inits the mptcp_subflow_data structure as follows: struct mptcp_subflow_addrs *sf_addr; struct mptcp_subflow_data *addr; socklen_t olen = sizeof(*addr) + (8 * sizeof(*sf_addr)); addr = malloc(olen); addr->size_subflow_data = sizeof(*addr); addr->num_subflows = 0; addr->size_kernel = 0; addr->size_user = sizeof(struct mptcp_subflow_addrs); sf_addr = (struct mptcp_subflow_addrs *)(addr + 1); and then retrieves the endpoint addresses via: ret = getsockopt(fd, SOL_MPTCP, MPTCP_SUBFLOW_ADDRS, addr, &olen); If the call succeeds, kernel will have added up to 8 endpoint addresses after the 'mptcp_subflow_data' header. Userspace needs to re-check 'olen' value to detect how many bytes have been filled in by the kernel. Userspace can check addr->num_subflows to discover when there were more subflows that available data space. Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Florian Westphal Signed-off-by: Mat Martineau Signed-off-by: David S. Miller --- include/uapi/linux/mptcp.h | 24 ++++++++++++ net/mptcp/sockopt.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 115 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 3f013a513770..c8cc46f80a16 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -4,6 +4,13 @@ #include #include +#include /* for sockaddr_in */ +#include /* for sockaddr_in6 */ +#include /* for sockaddr_storage and sa_family */ + +#ifndef __KERNEL__ +#include /* for struct sockaddr */ +#endif #define MPTCP_SUBFLOW_FLAG_MCAP_REM _BITUL(0) #define MPTCP_SUBFLOW_FLAG_MCAP_LOC _BITUL(1) @@ -200,8 +207,25 @@ struct mptcp_subflow_data { __u32 size_user; /* size of one element in data[] */ } __attribute__((aligned(8))); +struct mptcp_subflow_addrs { + union { + __kernel_sa_family_t sa_family; + struct sockaddr sa_local; + struct sockaddr_in sin_local; + struct sockaddr_in6 sin6_local; + struct __kernel_sockaddr_storage ss_local; + }; + union { + struct sockaddr sa_remote; + struct sockaddr_in sin_remote; + struct sockaddr_in6 sin6_remote; + struct __kernel_sockaddr_storage ss_remote; + }; +}; + /* MPTCP socket options */ #define MPTCP_INFO 1 #define MPTCP_TCPINFO 2 +#define MPTCP_SUBFLOW_ADDRS 3 #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index eb2905bfa089..8137cc3a4296 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -840,6 +840,95 @@ static int mptcp_getsockopt_tcpinfo(struct mptcp_sock *msk, char __user *optval, return 0; } +static void mptcp_get_sub_addrs(const struct sock *sk, struct mptcp_subflow_addrs *a) +{ + struct inet_sock *inet = inet_sk(sk); + + memset(a, 0, sizeof(*a)); + + if (sk->sk_family == AF_INET) { + a->sin_local.sin_family = AF_INET; + a->sin_local.sin_port = inet->inet_sport; + a->sin_local.sin_addr.s_addr = inet->inet_rcv_saddr; + + if (!a->sin_local.sin_addr.s_addr) + a->sin_local.sin_addr.s_addr = inet->inet_saddr; + + a->sin_remote.sin_family = AF_INET; + a->sin_remote.sin_port = inet->inet_dport; + a->sin_remote.sin_addr.s_addr = inet->inet_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_family == AF_INET6) { + const struct ipv6_pinfo *np = inet6_sk(sk); + + a->sin6_local.sin6_family = AF_INET6; + a->sin6_local.sin6_port = inet->inet_sport; + + if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) + a->sin6_local.sin6_addr = np->saddr; + else + a->sin6_local.sin6_addr = sk->sk_v6_rcv_saddr; + + a->sin6_remote.sin6_family = AF_INET6; + a->sin6_remote.sin6_port = inet->inet_dport; + a->sin6_remote.sin6_addr = sk->sk_v6_daddr; +#endif + } +} + +static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + struct sock *sk = &msk->sk.icsk_inet.sk; + struct mptcp_subflow_context *subflow; + unsigned int sfcount = 0, copied = 0; + struct mptcp_subflow_data sfd; + char __user *addrptr; + int len; + + len = mptcp_get_subflow_data(&sfd, optval, optlen); + if (len < 0) + return len; + + sfd.size_kernel = sizeof(struct mptcp_subflow_addrs); + sfd.size_user = min_t(unsigned int, sfd.size_user, + sizeof(struct mptcp_subflow_addrs)); + + addrptr = optval + sfd.size_subflow_data; + + lock_sock(sk); + + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + + ++sfcount; + + if (len && len >= sfd.size_user) { + struct mptcp_subflow_addrs a; + + mptcp_get_sub_addrs(ssk, &a); + + if (copy_to_user(addrptr, &a, sfd.size_user)) { + release_sock(sk); + return -EFAULT; + } + + addrptr += sfd.size_user; + copied += sfd.size_user; + len -= sfd.size_user; + } + } + + release_sock(sk); + + sfd.num_subflows = sfcount; + + if (mptcp_put_subflow_data(&sfd, optval, copied, optlen)) + return -EFAULT; + + return 0; +} + static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname, char __user *optval, int __user *optlen) { @@ -862,6 +951,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, return mptcp_getsockopt_info(msk, optval, optlen); case MPTCP_TCPINFO: return mptcp_getsockopt_tcpinfo(msk, optval, optlen); + case MPTCP_SUBFLOW_ADDRS: + return mptcp_getsockopt_subflow_addrs(msk, optval, optlen); } return -EOPNOTSUPP; -- cgit v1.2.3 From 5bd2182d58e9d9c6279b7a8a2f9b41add0e7f9cb Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Tue, 16 Feb 2021 19:46:48 -0500 Subject: audit,io_uring,io-wq: add some basic audit support to io_uring This patch adds basic auditing to io_uring operations, regardless of their context. This is accomplished by allocating audit_context structures for the io-wq worker and io_uring SQPOLL kernel threads as well as explicitly auditing the io_uring operations in io_issue_sqe(). Individual io_uring operations can bypass auditing through the "audit_skip" field in the struct io_op_def definition for the operation; although great care must be taken so that security relevant io_uring operations do not bypass auditing; please contact the audit mailing list (see the MAINTAINERS file) with any questions. The io_uring operations are audited using a new AUDIT_URINGOP record, an example is shown below: type=UNKNOWN[1336] msg=audit(1631800225.981:37289): uring_op=19 success=yes exit=0 items=0 ppid=15454 pid=15681 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null) Thanks to Richard Guy Briggs for review and feedback. Signed-off-by: Paul Moore --- fs/io-wq.c | 4 ++ fs/io_uring.c | 55 +++++++++++++-- include/linux/audit.h | 26 +++++++ include/uapi/linux/audit.h | 1 + kernel/audit.h | 2 + kernel/auditsc.c | 166 +++++++++++++++++++++++++++++++++++++++++++++ 6 files changed, 248 insertions(+), 6 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io-wq.c b/fs/io-wq.c index 6c55362c1f99..dac5c5961c9d 100644 --- a/fs/io-wq.c +++ b/fs/io-wq.c @@ -14,6 +14,7 @@ #include #include #include +#include #include "io-wq.h" @@ -562,6 +563,8 @@ static int io_wqe_worker(void *data) snprintf(buf, sizeof(buf), "iou-wrk-%d", wq->task->pid); set_task_comm(current, buf); + audit_alloc_kernel(current); + while (!test_bit(IO_WQ_BIT_EXIT, &wq->state)) { long ret; @@ -601,6 +604,7 @@ loop: io_worker_handle_work(worker); } + audit_free(current); io_worker_exit(worker); return 0; } diff --git a/fs/io_uring.c b/fs/io_uring.c index 16fb7436043c..388754b24785 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -79,6 +79,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -917,6 +918,8 @@ struct io_op_def { unsigned needs_async_setup : 1; /* should block plug */ unsigned plug : 1; + /* skip auditing */ + unsigned audit_skip : 1; /* size of async data needed, if any */ unsigned short async_size; }; @@ -930,6 +933,7 @@ static const struct io_op_def io_op_defs[] = { .buffer_select = 1, .needs_async_setup = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITEV] = { @@ -939,16 +943,19 @@ static const struct io_op_def io_op_defs[] = { .pollout = 1, .needs_async_setup = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FSYNC] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_READ_FIXED] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE_FIXED] = { @@ -957,15 +964,20 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_POLL_ADD] = { .needs_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, + }, + [IORING_OP_POLL_REMOVE] = { + .audit_skip = 1, }, - [IORING_OP_POLL_REMOVE] = {}, [IORING_OP_SYNC_FILE_RANGE] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_SENDMSG] = { .needs_file = 1, @@ -983,18 +995,23 @@ static const struct io_op_def io_op_defs[] = { .async_size = sizeof(struct io_async_msghdr), }, [IORING_OP_TIMEOUT] = { + .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_TIMEOUT_REMOVE] = { /* used by timeout updates' prep() */ + .audit_skip = 1, }, [IORING_OP_ACCEPT] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, }, - [IORING_OP_ASYNC_CANCEL] = {}, + [IORING_OP_ASYNC_CANCEL] = { + .audit_skip = 1, + }, [IORING_OP_LINK_TIMEOUT] = { + .audit_skip = 1, .async_size = sizeof(struct io_timeout_data), }, [IORING_OP_CONNECT] = { @@ -1009,14 +1026,19 @@ static const struct io_op_def io_op_defs[] = { }, [IORING_OP_OPENAT] = {}, [IORING_OP_CLOSE] = {}, - [IORING_OP_FILES_UPDATE] = {}, - [IORING_OP_STATX] = {}, + [IORING_OP_FILES_UPDATE] = { + .audit_skip = 1, + }, + [IORING_OP_STATX] = { + .audit_skip = 1, + }, [IORING_OP_READ] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_WRITE] = { @@ -1025,39 +1047,50 @@ static const struct io_op_def io_op_defs[] = { .unbound_nonreg_file = 1, .pollout = 1, .plug = 1, + .audit_skip = 1, .async_size = sizeof(struct io_async_rw), }, [IORING_OP_FADVISE] = { .needs_file = 1, + .audit_skip = 1, }, [IORING_OP_MADVISE] = {}, [IORING_OP_SEND] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollout = 1, + .audit_skip = 1, }, [IORING_OP_RECV] = { .needs_file = 1, .unbound_nonreg_file = 1, .pollin = 1, .buffer_select = 1, + .audit_skip = 1, }, [IORING_OP_OPENAT2] = { }, [IORING_OP_EPOLL_CTL] = { .unbound_nonreg_file = 1, + .audit_skip = 1, }, [IORING_OP_SPLICE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, + }, + [IORING_OP_PROVIDE_BUFFERS] = { + .audit_skip = 1, + }, + [IORING_OP_REMOVE_BUFFERS] = { + .audit_skip = 1, }, - [IORING_OP_PROVIDE_BUFFERS] = {}, - [IORING_OP_REMOVE_BUFFERS] = {}, [IORING_OP_TEE] = { .needs_file = 1, .hash_reg_file = 1, .unbound_nonreg_file = 1, + .audit_skip = 1, }, [IORING_OP_SHUTDOWN] = { .needs_file = 1, @@ -6591,6 +6624,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) if ((req->flags & REQ_F_CREDS) && req->creds != current_cred()) creds = override_creds(req->creds); + if (!io_op_defs[req->opcode].audit_skip) + audit_uring_entry(req->opcode); + switch (req->opcode) { case IORING_OP_NOP: ret = io_nop(req, issue_flags); @@ -6706,6 +6742,9 @@ static int io_issue_sqe(struct io_kiocb *req, unsigned int issue_flags) break; } + if (!io_op_defs[req->opcode].audit_skip) + audit_uring_exit(!ret, ret); + if (creds) revert_creds(creds); if (ret) @@ -7360,6 +7399,8 @@ static int io_sq_thread(void *data) set_cpus_allowed_ptr(current, cpu_online_mask); current->flags |= PF_NO_SETAFFINITY; + audit_alloc_kernel(current); + mutex_lock(&sqd->lock); while (1) { bool cap_entries, sqt_spin = false; @@ -7425,6 +7466,8 @@ static int io_sq_thread(void *data) io_run_task_work(); mutex_unlock(&sqd->lock); + audit_free(current); + complete(&sqd->exited); do_exit(0); } diff --git a/include/linux/audit.h b/include/linux/audit.h index 82b7c1116a85..d656a06dd909 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -286,7 +286,10 @@ static inline int audit_signal_info(int sig, struct task_struct *t) /* These are defined in auditsc.c */ /* Public API */ extern int audit_alloc(struct task_struct *task); +extern int audit_alloc_kernel(struct task_struct *task); extern void __audit_free(struct task_struct *task); +extern void __audit_uring_entry(u8 op); +extern void __audit_uring_exit(int success, long code); extern void __audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3); extern void __audit_syscall_exit(int ret_success, long ret_value); @@ -323,6 +326,21 @@ static inline void audit_free(struct task_struct *task) if (unlikely(task->audit_context)) __audit_free(task); } +static inline void audit_uring_entry(u8 op) +{ + /* + * We intentionally check audit_context() before audit_enabled as most + * Linux systems (as of ~2021) rely on systemd which forces audit to + * be enabled regardless of the user's audit configuration. + */ + if (unlikely(audit_context() && audit_enabled)) + __audit_uring_entry(op); +} +static inline void audit_uring_exit(int success, long code) +{ + if (unlikely(!audit_dummy_context())) + __audit_uring_exit(success, code); +} static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) @@ -554,8 +572,16 @@ static inline int audit_alloc(struct task_struct *task) { return 0; } +static inline int audit_alloc_kernel(struct task_struct *task) +{ + return 0; +} static inline void audit_free(struct task_struct *task) { } +static inline void audit_uring_entry(u8 op) +{ } +static inline void audit_uring_exit(int success, long code) +{ } static inline void audit_syscall_entry(int major, unsigned long a0, unsigned long a1, unsigned long a2, unsigned long a3) diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..a1997697c8b1 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,7 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_URINGOP 1336 /* io_uring operation */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.h b/kernel/audit.h index 13abc48de0bd..d1161e3b83e2 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -103,10 +103,12 @@ struct audit_context { enum { AUDIT_CTX_UNUSED, /* audit_context is currently unused */ AUDIT_CTX_SYSCALL, /* in use by syscall */ + AUDIT_CTX_URING, /* in use by io_uring */ } context; enum audit_state state, current_state; unsigned int serial; /* serial number for record */ int major; /* syscall number */ + int uring_op; /* uring operation */ struct timespec64 ctime; /* time of syscall entry */ unsigned long argv[4]; /* syscall arguments */ long return_code;/* syscall return code */ diff --git a/kernel/auditsc.c b/kernel/auditsc.c index f3d309b05c2d..6dda448fb826 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -959,6 +959,7 @@ static void audit_reset_context(struct audit_context *ctx) ctx->current_state = ctx->state; ctx->serial = 0; ctx->major = 0; + ctx->uring_op = 0; ctx->ctime = (struct timespec64){ .tv_sec = 0, .tv_nsec = 0 }; memset(ctx->argv, 0, sizeof(ctx->argv)); ctx->return_code = 0; @@ -1044,6 +1045,31 @@ int audit_alloc(struct task_struct *tsk) return 0; } +/** + * audit_alloc_kernel - allocate an audit_context for a kernel task + * @tsk: the kernel task + * + * Similar to the audit_alloc() function, but intended for kernel private + * threads. Returns zero on success, negative values on failure. + */ +int audit_alloc_kernel(struct task_struct *tsk) +{ + /* + * At the moment we are just going to call into audit_alloc() to + * simplify the code, but there two things to keep in mind with this + * approach: + * + * 1. Filtering internal kernel tasks is a bit laughable in almost all + * cases, but there is at least one case where there is a benefit: + * the '-a task,never' case allows the admin to effectively disable + * task auditing at runtime. + * + * 2. The {set,clear}_task_syscall_work() ops likely have zero effect + * on these internal kernel tasks, but they probably don't hurt either. + */ + return audit_alloc(tsk); +} + static inline void audit_free_context(struct audit_context *context) { /* resetting is extra work, but it is likely just noise */ @@ -1546,6 +1572,44 @@ out: audit_log_end(ab); } +/** + * audit_log_uring - generate a AUDIT_URINGOP record + * @ctx: the audit context + */ +static void audit_log_uring(struct audit_context *ctx) +{ + struct audit_buffer *ab; + const struct cred *cred; + + ab = audit_log_start(ctx, GFP_ATOMIC, AUDIT_URINGOP); + if (!ab) + return; + cred = current_cred(); + audit_log_format(ab, "uring_op=%d", ctx->uring_op); + if (ctx->return_valid != AUDITSC_INVALID) + audit_log_format(ab, " success=%s exit=%ld", + (ctx->return_valid == AUDITSC_SUCCESS ? + "yes" : "no"), + ctx->return_code); + audit_log_format(ab, + " items=%d" + " ppid=%d pid=%d uid=%u gid=%u euid=%u suid=%u" + " fsuid=%u egid=%u sgid=%u fsgid=%u", + ctx->name_count, + task_ppid_nr(current), task_tgid_nr(current), + from_kuid(&init_user_ns, cred->uid), + from_kgid(&init_user_ns, cred->gid), + from_kuid(&init_user_ns, cred->euid), + from_kuid(&init_user_ns, cred->suid), + from_kuid(&init_user_ns, cred->fsuid), + from_kgid(&init_user_ns, cred->egid), + from_kgid(&init_user_ns, cred->sgid), + from_kgid(&init_user_ns, cred->fsgid)); + audit_log_task_context(ab); + audit_log_key(ab, ctx->filterkey); + audit_log_end(ab); +} + static void audit_log_exit(void) { int i, call_panic = 0; @@ -1581,6 +1645,9 @@ static void audit_log_exit(void) audit_log_key(ab, context->filterkey); audit_log_end(ab); break; + case AUDIT_CTX_URING: + audit_log_uring(context); + break; default: BUG(); break; @@ -1751,6 +1818,105 @@ static void audit_return_fixup(struct audit_context *ctx, ctx->return_valid = (success ? AUDITSC_SUCCESS : AUDITSC_FAILURE); } +/** + * __audit_uring_entry - prepare the kernel task's audit context for io_uring + * @op: the io_uring opcode + * + * This is similar to audit_syscall_entry() but is intended for use by io_uring + * operations. This function should only ever be called from + * audit_uring_entry() as we rely on the audit context checking present in that + * function. + */ +void __audit_uring_entry(u8 op) +{ + struct audit_context *ctx = audit_context(); + + if (ctx->state == AUDIT_STATE_DISABLED) + return; + + /* + * NOTE: It's possible that we can be called from the process' context + * before it returns to userspace, and before audit_syscall_exit() + * is called. In this case there is not much to do, just record + * the io_uring details and return. + */ + ctx->uring_op = op; + if (ctx->context == AUDIT_CTX_SYSCALL) + return; + + ctx->dummy = !audit_n_rules; + if (!ctx->dummy && ctx->state == AUDIT_STATE_BUILD) + ctx->prio = 0; + + ctx->context = AUDIT_CTX_URING; + ctx->current_state = ctx->state; + ktime_get_coarse_real_ts64(&ctx->ctime); +} + +/** + * __audit_uring_exit - wrap up the kernel task's audit context after io_uring + * @success: true/false value to indicate if the operation succeeded or not + * @code: operation return code + * + * This is similar to audit_syscall_exit() but is intended for use by io_uring + * operations. This function should only ever be called from + * audit_uring_exit() as we rely on the audit context checking present in that + * function. + */ +void __audit_uring_exit(int success, long code) +{ + struct audit_context *ctx = audit_context(); + + /* + * TODO: At some point we will likely want to filter on io_uring ops + * and other things similar to what we do for syscalls, but that + * is something for another day; just record what we can here. + */ + + if (ctx->context == AUDIT_CTX_SYSCALL) { + /* + * NOTE: See the note in __audit_uring_entry() about the case + * where we may be called from process context before we + * return to userspace via audit_syscall_exit(). In this + * case we simply emit a URINGOP record and bail, the + * normal syscall exit handling will take care of + * everything else. + * It is also worth mentioning that when we are called, + * the current process creds may differ from the creds + * used during the normal syscall processing; keep that + * in mind if/when we move the record generation code. + */ + + /* + * We need to filter on the syscall info here to decide if we + * should emit a URINGOP record. I know it seems odd but this + * solves the problem where users have a filter to block *all* + * syscall records in the "exit" filter; we want to preserve + * the behavior here. + */ + audit_filter_syscall(current, ctx); + audit_filter_inodes(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + return; + + audit_log_uring(ctx); + return; + } + + /* this may generate CONFIG_CHANGE records */ + if (!list_empty(&ctx->killed_trees)) + audit_kill_trees(ctx); + + audit_filter_inodes(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + goto out; + audit_return_fixup(ctx, success, code); + audit_log_exit(); + +out: + audit_reset_context(ctx); +} + /** * __audit_syscall_entry - fill in an audit record at syscall entry * @major: major syscall type (function) -- cgit v1.2.3 From 67daf270cebcf7aab4b3292b36f9adf357b23ddc Mon Sep 17 00:00:00 2001 From: Paul Moore Date: Sun, 18 Apr 2021 21:54:47 -0400 Subject: audit: add filtering for io_uring records This patch adds basic audit io_uring filtering, using as much of the existing audit filtering infrastructure as possible. In order to do this we reuse the audit filter rule's syscall mask for the io_uring operation and we create a new filter for io_uring operations as AUDIT_FILTER_URING_EXIT/audit_filter_list[7]. Thanks to Richard Guy Briggs for his review, feedback, and work on the corresponding audit userspace changes. Acked-by: Richard Guy Briggs Signed-off-by: Paul Moore --- include/uapi/linux/audit.h | 3 ++- kernel/audit_tree.c | 3 ++- kernel/audit_watch.c | 3 ++- kernel/auditfilter.c | 15 +++++++++--- kernel/auditsc.c | 60 +++++++++++++++++++++++++++++++++++----------- 5 files changed, 64 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index a1997697c8b1..ecf1edd2affa 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -167,8 +167,9 @@ #define AUDIT_FILTER_EXCLUDE 0x05 /* Apply rule before record creation */ #define AUDIT_FILTER_TYPE AUDIT_FILTER_EXCLUDE /* obsolete misleading naming */ #define AUDIT_FILTER_FS 0x06 /* Apply rule at __audit_inode_child */ +#define AUDIT_FILTER_URING_EXIT 0x07 /* Apply rule at io_uring op exit */ -#define AUDIT_NR_FILTERS 7 +#define AUDIT_NR_FILTERS 8 #define AUDIT_FILTER_PREPEND 0x10 /* Prepend to front of list */ diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c index 2cd7b5694422..338c53a961c5 100644 --- a/kernel/audit_tree.c +++ b/kernel/audit_tree.c @@ -726,7 +726,8 @@ int audit_make_tree(struct audit_krule *rule, char *pathname, u32 op) { if (pathname[0] != '/' || - rule->listnr != AUDIT_FILTER_EXIT || + (rule->listnr != AUDIT_FILTER_EXIT && + rule->listnr != AUDIT_FILTER_URING_EXIT) || op != Audit_equal || rule->inode_f || rule->watch || rule->tree) return -EINVAL; diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 2acf7ca49154..698b62b4a2ec 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -183,7 +183,8 @@ int audit_to_watch(struct audit_krule *krule, char *path, int len, u32 op) return -EOPNOTSUPP; if (path[0] != '/' || path[len-1] == '/' || - krule->listnr != AUDIT_FILTER_EXIT || + (krule->listnr != AUDIT_FILTER_EXIT && + krule->listnr != AUDIT_FILTER_URING_EXIT) || op != Audit_equal || krule->inode_f || krule->watch || krule->tree) return -EINVAL; diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c index db2c6b59dfc3..d75acb014ccd 100644 --- a/kernel/auditfilter.c +++ b/kernel/auditfilter.c @@ -44,7 +44,8 @@ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), -#if AUDIT_NR_FILTERS != 7 + LIST_HEAD_INIT(audit_filter_list[7]), +#if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; @@ -56,6 +57,7 @@ static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), + LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); @@ -151,7 +153,8 @@ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { - if (krule->listnr != AUDIT_FILTER_EXIT || + if ((krule->listnr != AUDIT_FILTER_EXIT && + krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; @@ -248,6 +251,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data * pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: + case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: @@ -332,6 +336,10 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; + case AUDIT_PERM: + if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) + return -EINVAL; + break; } switch (entry->rule.listnr) { @@ -980,7 +988,8 @@ static inline int audit_add_rule(struct audit_entry *entry) } entry->rule.prio = ~0ULL; - if (entry->rule.listnr == AUDIT_FILTER_EXIT) { + if (entry->rule.listnr == AUDIT_FILTER_EXIT || + entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 6dda448fb826..3c9fb842a8f0 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -805,6 +805,34 @@ static int audit_in_mask(const struct audit_krule *rule, unsigned long val) return rule->mask[word] & bit; } +/** + * audit_filter_uring - apply filters to an io_uring operation + * @tsk: associated task + * @ctx: audit context + */ +static void audit_filter_uring(struct task_struct *tsk, + struct audit_context *ctx) +{ + struct audit_entry *e; + enum audit_state state; + + if (auditd_test_task(tsk)) + return; + + rcu_read_lock(); + list_for_each_entry_rcu(e, &audit_filter_list[AUDIT_FILTER_URING_EXIT], + list) { + if (audit_in_mask(&e->rule, ctx->uring_op) && + audit_filter_rules(tsk, &e->rule, ctx, NULL, &state, + false)) { + rcu_read_unlock(); + ctx->current_state = state; + return; + } + } + rcu_read_unlock(); +} + /* At syscall exit time, this filter is called if the audit_state is * not low enough that auditing cannot take place, but is also not * high enough that we already know we have to write an audit record @@ -1757,7 +1785,7 @@ static void audit_log_exit(void) * __audit_free - free a per-task audit context * @tsk: task whose audit context block to free * - * Called from copy_process and do_exit + * Called from copy_process, do_exit, and the io_uring code */ void __audit_free(struct task_struct *tsk) { @@ -1775,15 +1803,21 @@ void __audit_free(struct task_struct *tsk) * random task_struct that doesn't doesn't have any meaningful data we * need to log via audit_log_exit(). */ - if (tsk == current && !context->dummy && - context->context == AUDIT_CTX_SYSCALL) { + if (tsk == current && !context->dummy) { context->return_valid = AUDITSC_INVALID; context->return_code = 0; - - audit_filter_syscall(tsk, context); - audit_filter_inodes(tsk, context); - if (context->current_state == AUDIT_STATE_RECORD) - audit_log_exit(); + if (context->context == AUDIT_CTX_SYSCALL) { + audit_filter_syscall(tsk, context); + audit_filter_inodes(tsk, context); + if (context->current_state == AUDIT_STATE_RECORD) + audit_log_exit(); + } else if (context->context == AUDIT_CTX_URING) { + /* TODO: verify this case is real and valid */ + audit_filter_uring(tsk, context); + audit_filter_inodes(tsk, context); + if (context->current_state == AUDIT_STATE_RECORD) + audit_log_uring(context); + } } audit_set_context(tsk, NULL); @@ -1867,12 +1901,6 @@ void __audit_uring_exit(int success, long code) { struct audit_context *ctx = audit_context(); - /* - * TODO: At some point we will likely want to filter on io_uring ops - * and other things similar to what we do for syscalls, but that - * is something for another day; just record what we can here. - */ - if (ctx->context == AUDIT_CTX_SYSCALL) { /* * NOTE: See the note in __audit_uring_entry() about the case @@ -1895,6 +1923,8 @@ void __audit_uring_exit(int success, long code) * the behavior here. */ audit_filter_syscall(current, ctx); + if (ctx->current_state != AUDIT_STATE_RECORD) + audit_filter_uring(current, ctx); audit_filter_inodes(current, ctx); if (ctx->current_state != AUDIT_STATE_RECORD) return; @@ -1907,6 +1937,8 @@ void __audit_uring_exit(int success, long code) if (!list_empty(&ctx->killed_trees)) audit_kill_trees(ctx); + /* run through both filters to ensure we set the filterkey properly */ + audit_filter_uring(current, ctx); audit_filter_inodes(current, ctx); if (ctx->current_state != AUDIT_STATE_RECORD) goto out; -- cgit v1.2.3 From 50d7bd38c3aafc4749e05e8d7fcb616979143602 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 17 May 2021 20:01:15 -0700 Subject: stddef: Introduce struct_group() helper macro Kernel code has a regular need to describe groups of members within a structure usually when they need to be copied or initialized separately from the rest of the surrounding structure. The generally accepted design pattern in C is to use a named sub-struct: struct foo { int one; struct { int two; int three, four; } thing; int five; }; This would allow for traditional references and sizing: memcpy(&dst.thing, &src.thing, sizeof(dst.thing)); However, doing this would mean that referencing struct members enclosed by such named structs would always require including the sub-struct name in identifiers: do_something(dst.thing.three); This has tended to be quite inflexible, especially when such groupings need to be added to established code which causes huge naming churn. Three workarounds exist in the kernel for this problem, and each have other negative properties. To avoid the naming churn, there is a design pattern of adding macro aliases for the named struct: #define f_three thing.three This ends up polluting the global namespace, and makes it difficult to search for identifiers. Another common work-around in kernel code avoids the pollution by avoiding the named struct entirely, instead identifying the group's boundaries using either a pair of empty anonymous structs of a pair of zero-element arrays: struct foo { int one; struct { } start; int two; int three, four; struct { } finish; int five; }; struct foo { int one; int start[0]; int two; int three, four; int finish[0]; int five; }; This allows code to avoid needing to use a sub-struct named for member references within the surrounding structure, but loses the benefits of being able to actually use such a struct, making it rather fragile. Using these requires open-coded calculation of sizes and offsets. The efforts made to avoid common mistakes include lots of comments, or adding various BUILD_BUG_ON()s. Such code is left with no way for the compiler to reason about the boundaries (e.g. the "start" object looks like it's 0 bytes in length), making bounds checking depend on open-coded calculations: if (length > offsetof(struct foo, finish) - offsetof(struct foo, start)) return -EINVAL; memcpy(&dst.start, &src.start, offsetof(struct foo, finish) - offsetof(struct foo, start)); However, the vast majority of places in the kernel that operate on groups of members do so without any identification of the grouping, relying either on comments or implicit knowledge of the struct contents, which is even harder for the compiler to reason about, and results in even more fragile manual sizing, usually depending on member locations outside of the region (e.g. to copy "two" and "three", use the start of "four" to find the size): BUILD_BUG_ON((offsetof(struct foo, four) < offsetof(struct foo, two)) || (offsetof(struct foo, four) < offsetof(struct foo, three)); if (length > offsetof(struct foo, four) - offsetof(struct foo, two)) return -EINVAL; memcpy(&dst.two, &src.two, length); In order to have a regular programmatic way to describe a struct region that can be used for references and sizing, can be examined for bounds checking, avoids forcing the use of intermediate identifiers, and avoids polluting the global namespace, introduce the struct_group() macro. This macro wraps the member declarations to create an anonymous union of an anonymous struct (no intermediate name) and a named struct (for references and sizing): struct foo { int one; struct_group(thing, int two; int three, four; ); int five; }; if (length > sizeof(src.thing)) return -EINVAL; memcpy(&dst.thing, &src.thing, length); do_something(dst.three); There are some rare cases where the resulting struct_group() needs attributes added, so struct_group_attr() is also introduced to allow for specifying struct attributes (e.g. __align(x) or __packed). Additionally, there are places where such declarations would like to have the struct be tagged, so struct_group_tagged() is added. Given there is a need for a handful of UAPI uses too, the underlying __struct_group() macro has been defined in UAPI so it can be used there too. To avoid confusing scripts/kernel-doc, hide the macro from its struct parsing. Co-developed-by: Keith Packard Signed-off-by: Keith Packard Acked-by: Gustavo A. R. Silva Link: https://lore.kernel.org/lkml/20210728023217.GC35706@embeddedor Enhanced-by: Rasmus Villemoes Link: https://lore.kernel.org/lkml/41183a98-bdb9-4ad6-7eab-5a7292a6df84@rasmusvillemoes.dk Enhanced-by: Dan Williams Link: https://lore.kernel.org/lkml/1d9a2e6df2a9a35b2cdd50a9a68cac5991e7e5f0.camel@intel.com Enhanced-by: Daniel Vetter Link: https://lore.kernel.org/lkml/YQKa76A6XuFqgM03@phenom.ffwll.local Acked-by: Dan Williams Signed-off-by: Kees Cook --- include/linux/stddef.h | 48 +++++++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/stddef.h | 21 ++++++++++++++++++++ scripts/kernel-doc | 7 +++++++ 3 files changed, 76 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 8553b33143d1..8b103a53b000 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -36,4 +36,52 @@ enum { #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +/** + * struct_group() - Wrap a set of declarations in a mirrored struct + * + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. + */ +#define struct_group(NAME, MEMBERS...) \ + __struct_group(/* no tag */, NAME, /* no attrs */, MEMBERS) + +/** + * struct_group_attr() - Create a struct_group() with trailing attributes + * + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes to apply + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes structure attributes argument. + */ +#define struct_group_attr(NAME, ATTRS, MEMBERS...) \ + __struct_group(/* no tag */, NAME, ATTRS, MEMBERS) + +/** + * struct_group_tagged() - Create a struct_group with a reusable tag + * + * @TAG: The tag name for the named sub-struct + * @NAME: The identifier name of the mirrored sub-struct + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical + * layout and size: one anonymous and one named. The former can be + * used normally without sub-struct naming, and the latter can be + * used to reason about the start, end, and size of the group of + * struct members. Includes struct tag argument for the named copy, + * so the specified layout can be reused later. + */ +#define struct_group_tagged(TAG, NAME, MEMBERS...) \ + __struct_group(TAG, NAME, /* no attrs */, MEMBERS) + #endif diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index ee8220f8dcf5..610204f7c275 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -4,3 +4,24 @@ #ifndef __always_inline #define __always_inline inline #endif + +/** + * __struct_group() - Create a mirrored named and anonyomous struct + * + * @TAG: The tag name for the named sub-struct (usually empty) + * @NAME: The identifier name of the mirrored sub-struct + * @ATTRS: Any struct attributes (usually empty) + * @MEMBERS: The member declarations for the mirrored structs + * + * Used to create an anonymous union of two structs with identical layout + * and size: one anonymous and one named. The former's members can be used + * normally without sub-struct naming, and the latter can be used to + * reason about the start, end, and size of the group of struct members. + * The named struct can also be explicitly tagged for layer reuse, as well + * as both having struct attributes appended. + */ +#define __struct_group(TAG, NAME, ATTRS, MEMBERS...) \ + union { \ + struct { MEMBERS } ATTRS; \ + struct TAG { MEMBERS } ATTRS NAME; \ + } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index cfcb60737957..38aa799a776c 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1245,6 +1245,13 @@ sub dump_struct($$) { $members =~ s/\s*CRYPTO_MINALIGN_ATTR/ /gos; $members =~ s/\s*____cacheline_aligned_in_smp/ /gos; $members =~ s/\s*____cacheline_aligned/ /gos; + # unwrap struct_group(): + # - first eat non-declaration parameters and rewrite for final match + # - then remove macro, outer parens, and trailing semicolon + $members =~ s/\bstruct_group\s*\(([^,]*,)/STRUCT_GROUP(/gos; + $members =~ s/\bstruct_group_(attr|tagged)\s*\(([^,]*,){2}/STRUCT_GROUP(/gos; + $members =~ s/\b__struct_group\s*\(([^,]*,){3}/STRUCT_GROUP(/gos; + $members =~ s/\bSTRUCT_GROUP(\(((?:(?>[^)(]+)|(?1))*)\))[^;]*;/$2/gos; my $args = qr{([^,)]+)}; # replace DECLARE_BITMAP -- cgit v1.2.3 From e306784a8de08868d0ecbf78dd42a0051d0e14ce Mon Sep 17 00:00:00 2001 From: Subrat Mishra Date: Wed, 15 Sep 2021 11:22:23 +0530 Subject: cfg80211: AP mode driver offload for FILS association crypto Add a driver FILS crypto offload extended capability flag to indicate that the driver running in AP mode is capable of handling encryption and decryption of (Re)Association request and response frames. Add a command to set FILS AAD data to driver. This feature is supported on drivers running in AP mode only. This extended capability is exchanged with hostapd during cfg80211 init. If the driver indicates this capability, then before sending the Authentication response frame, hostapd sets FILS AAD data to the driver. This allows the driver to decrypt (Re)Association Request frame and encrypt (Re)Association Response frame. FILS Key derivation will still be done in hostapd. Signed-off-by: Subrat Mishra Link: https://lore.kernel.org/r/1631685143-13530-1-git-send-email-subratm@codeaurora.org [fix whitespace] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 22 ++++++++++++++++++++++ include/uapi/linux/nl80211.h | 37 +++++++++++++++++++++++++++++++++++++ net/wireless/nl80211.c | 30 ++++++++++++++++++++++++++++++ net/wireless/rdev-ops.h | 14 ++++++++++++++ net/wireless/trace.h | 31 +++++++++++++++++++++++++++++++ 5 files changed, 134 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 62dd8422e0dc..125f563d66a1 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -739,6 +739,22 @@ struct cfg80211_tid_config { struct cfg80211_tid_cfg tid_conf[]; }; +/** + * struct cfg80211_fils_aad - FILS AAD data + * @macaddr: STA MAC address + * @kek: FILS KEK + * @kek_len: FILS KEK length + * @snonce: STA Nonce + * @anonce: AP Nonce + */ +struct cfg80211_fils_aad { + const u8 *macaddr; + const u8 *kek; + u8 kek_len; + const u8 *snonce; + const u8 *anonce; +}; + /** * cfg80211_get_chandef_type - return old channel type from chandef * @chandef: the channel definition @@ -4018,6 +4034,10 @@ struct mgmt_frame_regs { * @set_sar_specs: Update the SAR (TX power) settings. * * @color_change: Initiate a color change. + * + * @set_fils_aad: Set FILS AAD data to the AP driver so that the driver can use + * those to decrypt (Re)Association Request and encrypt (Re)Association + * Response frame. */ struct cfg80211_ops { int (*suspend)(struct wiphy *wiphy, struct cfg80211_wowlan *wow); @@ -4348,6 +4368,8 @@ struct cfg80211_ops { int (*color_change)(struct wiphy *wiphy, struct net_device *dev, struct cfg80211_color_change_settings *params); + int (*set_fils_aad)(struct wiphy *wiphy, struct net_device *dev, + struct cfg80211_fils_aad *fils_aad); }; /* diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c2efea98e060..e89bbf856228 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -300,6 +300,29 @@ * the interface goes down. */ +/** + * DOC: FILS shared key crypto offload + * + * This feature is applicable to drivers running in AP mode. + * + * FILS shared key crypto offload can be advertised by drivers by setting + * @NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD flag. The drivers that support + * FILS shared key crypto offload should be able to encrypt and decrypt + * association frames for FILS shared key authentication as per IEEE 802.11ai. + * With this capability, for FILS key derivation, drivers depend on userspace. + * + * After FILS key derivation, userspace shares the FILS AAD details with the + * driver and the driver stores the same to use in decryption of association + * request and in encryption of association response. The below parameters + * should be given to the driver in %NL80211_CMD_SET_FILS_AAD. + * %NL80211_ATTR_MAC - STA MAC address, used for storing FILS AAD per STA + * %NL80211_ATTR_FILS_KEK - Used for encryption or decryption + * %NL80211_ATTR_FILS_NONCES - Used for encryption or decryption + * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) + * + * Once the association is done, the driver cleans the FILS AAD data. + */ + /** * enum nl80211_commands - supported nl80211 commands * @@ -1200,6 +1223,12 @@ * @NL80211_CMD_COLOR_CHANGE_COMPLETED: Notify userland that the color change * has completed * + * @NL80211_CMD_SET_FILS_AAD: Set FILS AAD data to the driver using - + * &NL80211_ATTR_MAC - for STA MAC address + * &NL80211_ATTR_FILS_KEK - for KEK + * &NL80211_ATTR_FILS_NONCES - for FILS Nonces + * (STA Nonce 16 bytes followed by AP Nonce 16 bytes) + * * @NL80211_CMD_MAX: highest used command number * @__NL80211_CMD_AFTER_LAST: internal use */ @@ -1440,6 +1469,8 @@ enum nl80211_commands { NL80211_CMD_COLOR_CHANGE_ABORTED, NL80211_CMD_COLOR_CHANGE_COMPLETED, + NL80211_CMD_SET_FILS_AAD, + /* add new commands above here */ /* used to define NL80211_CMD_MAX below */ @@ -5995,6 +6026,11 @@ enum nl80211_feature_flags { * @NL80211_EXT_FEATURE_BSS_COLOR: The driver supports BSS color collision * detection and change announcemnts. * + * @NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD: Driver running in AP mode supports + * FILS encryption and decryption for (Re)Association Request and Response + * frames. Userspace has to share FILS AAD details to the driver by using + * @NL80211_CMD_SET_FILS_AAD. + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@ -6060,6 +6096,7 @@ enum nl80211_ext_feature_index { NL80211_EXT_FEATURE_SECURE_RTT, NL80211_EXT_FEATURE_PROT_RANGE_NEGO_AND_MEASURE, NL80211_EXT_FEATURE_BSS_COLOR, + NL80211_EXT_FEATURE_FILS_CRYPTO_OFFLOAD, /* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0b4f29d689d2..d7c03f6145f0 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -14936,6 +14936,29 @@ out: return err; } +static int nl80211_set_fils_aad(struct sk_buff *skb, + struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct cfg80211_fils_aad fils_aad = {}; + u8 *nonces; + + if (!info->attrs[NL80211_ATTR_MAC] || + !info->attrs[NL80211_ATTR_FILS_KEK] || + !info->attrs[NL80211_ATTR_FILS_NONCES]) + return -EINVAL; + + fils_aad.macaddr = nla_data(info->attrs[NL80211_ATTR_MAC]); + fils_aad.kek_len = nla_len(info->attrs[NL80211_ATTR_FILS_KEK]); + fils_aad.kek = nla_data(info->attrs[NL80211_ATTR_FILS_KEK]); + nonces = nla_data(info->attrs[NL80211_ATTR_FILS_NONCES]); + fils_aad.snonce = nonces; + fils_aad.anonce = nonces + FILS_NONCE_LEN; + + return rdev_set_fils_aad(rdev, dev, &fils_aad); +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -15937,6 +15960,13 @@ static const struct genl_small_ops nl80211_small_ops[] = { .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_FILS_AAD, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = nl80211_set_fils_aad, + .flags = GENL_UNS_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP, + }, }; static struct genl_family nl80211_fam __ro_after_init = { diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index ce6bf218a1a3..cc1efec4b27b 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -1381,4 +1381,18 @@ static inline int rdev_color_change(struct cfg80211_registered_device *rdev, return ret; } +static inline int +rdev_set_fils_aad(struct cfg80211_registered_device *rdev, + struct net_device *dev, struct cfg80211_fils_aad *fils_aad) +{ + int ret = -EOPNOTSUPP; + + trace_rdev_set_fils_aad(&rdev->wiphy, dev, fils_aad); + if (rdev->ops->set_fils_aad) + ret = rdev->ops->set_fils_aad(&rdev->wiphy, dev, fils_aad); + trace_rdev_return_int(&rdev->wiphy, ret); + + return ret; +} + #endif /* __CFG80211_RDEV_OPS */ diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 19b78d472283..ad6c16a06bcb 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -167,6 +167,19 @@ __entry->center_freq1, __entry->freq1_offset, \ __entry->center_freq2 +#define FILS_AAD_ASSIGN(fa) \ + do { \ + if (fa) { \ + ether_addr_copy(__entry->macaddr, fa->macaddr); \ + __entry->kek_len = fa->kek_len; \ + } else { \ + eth_zero_addr(__entry->macaddr); \ + __entry->kek_len = 0; \ + } \ + } while (0) +#define FILS_AAD_PR_FMT \ + "macaddr: %pM, kek_len: %d" + #define SINFO_ENTRY __field(int, generation) \ __field(u32, connected_time) \ __field(u32, inactive_time) \ @@ -2614,6 +2627,24 @@ DEFINE_EVENT(wiphy_wdev_cookie_evt, rdev_abort_pmsr, TP_ARGS(wiphy, wdev, cookie) ); +TRACE_EVENT(rdev_set_fils_aad, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, + struct cfg80211_fils_aad *fils_aad), + TP_ARGS(wiphy, netdev, fils_aad), + TP_STRUCT__entry(WIPHY_ENTRY + NETDEV_ENTRY + __array(u8, macaddr, ETH_ALEN) + __field(u8, kek_len) + ), + TP_fast_assign(WIPHY_ASSIGN; + NETDEV_ASSIGN; + FILS_AAD_ASSIGN(fils_aad); + ), + TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", " FILS_AAD_PR_FMT, + WIPHY_PR_ARG, NETDEV_PR_ARG, __entry->macaddr, + __entry->kek_len) +); + /************************************************************* * cfg80211 exported functions traces * *************************************************************/ -- cgit v1.2.3 From dc1e3cb8da8b414b37208b2fb6755fef8122504b Mon Sep 17 00:00:00 2001 From: John Crispin Date: Wed, 15 Sep 2021 19:54:34 -0700 Subject: nl80211: MBSSID and EMA support in AP mode Add new attributes to configure support for multiple BSSID and advanced multi-BSSID advertisements (EMA) in AP mode. - NL80211_ATTR_MBSSID_CONFIG used for per interface configuration. - NL80211_ATTR_MBSSID_ELEMS used to MBSSID elements for beacons. Memory for the elements is allocated dynamically. This change frees the memory in existing functions which call nl80211_parse_beacon(), a comment is added to indicate the new references to do the same. Signed-off-by: John Crispin Co-developed-by: Aloka Dixit Signed-off-by: Aloka Dixit Link: https://lore.kernel.org/r/20210916025437.29138-2-alokad@codeaurora.org [don't leave ERR_PTR hanging around] Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 44 +++++++++++ include/uapi/linux/nl80211.h | 76 +++++++++++++++++- net/wireless/nl80211.c | 178 ++++++++++++++++++++++++++++++++++++++++++- 3 files changed, 293 insertions(+), 5 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 125f563d66a1..e9e313aa991f 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1056,6 +1056,36 @@ struct cfg80211_crypto_settings { enum nl80211_sae_pwe_mechanism sae_pwe; }; +/** + * struct cfg80211_mbssid_config - AP settings for multi bssid + * + * @tx_wdev: pointer to the transmitted interface in the MBSSID set + * @index: index of this AP in the multi bssid group. + * @ema: set to true if the beacons should be sent out in EMA mode. + */ +struct cfg80211_mbssid_config { + struct wireless_dev *tx_wdev; + u8 index; + bool ema; +}; + +/** + * struct cfg80211_mbssid_elems - Multiple BSSID elements + * + * @cnt: Number of elements in array %elems. + * + * @elem: Array of multiple BSSID element(s) to be added into Beacon frames. + * @elem.data: Data for multiple BSSID elements. + * @elem.len: Length of data. + */ +struct cfg80211_mbssid_elems { + u8 cnt; + struct { + const u8 *data; + size_t len; + } elem[]; +}; + /** * struct cfg80211_beacon_data - beacon data * @head: head portion of beacon (before TIM IE) @@ -1074,6 +1104,7 @@ struct cfg80211_crypto_settings { * @assocresp_ies_len: length of assocresp_ies in octets * @probe_resp_len: length of probe response template (@probe_resp) * @probe_resp: probe response template (AP mode only) + * @mbssid_ies: multiple BSSID elements * @ftm_responder: enable FTM responder functionality; -1 for no change * (which also implies no change in LCI/civic location data) * @lci: Measurement Report element content, starting with Measurement Token @@ -1091,6 +1122,7 @@ struct cfg80211_beacon_data { const u8 *probe_resp; const u8 *lci; const u8 *civicloc; + struct cfg80211_mbssid_elems *mbssid_ies; s8 ftm_responder; size_t head_len, tail_len; @@ -1205,6 +1237,7 @@ enum cfg80211_ap_settings_flags { * @he_oper: HE operation IE (or %NULL if HE isn't enabled) * @fils_discovery: FILS discovery transmission parameters * @unsol_bcast_probe_resp: Unsolicited broadcast probe response parameters + * @mbssid_config: AP settings for multiple bssid */ struct cfg80211_ap_settings { struct cfg80211_chan_def chandef; @@ -1237,6 +1270,7 @@ struct cfg80211_ap_settings { struct cfg80211_he_bss_color he_bss_color; struct cfg80211_fils_discovery fils_discovery; struct cfg80211_unsol_bcast_probe_resp unsol_bcast_probe_resp; + struct cfg80211_mbssid_config mbssid_config; }; /** @@ -5003,6 +5037,13 @@ struct wiphy_iftype_akm_suites { * %NL80211_TID_CONFIG_ATTR_RETRY_LONG attributes * @sar_capa: SAR control capabilities * @rfkill: a pointer to the rfkill structure + * + * @mbssid_max_interfaces: maximum number of interfaces supported by the driver + * in a multiple BSSID set. This field must be set to a non-zero value + * by the driver to advertise MBSSID support. + * @mbssid_max_ema_profile_periodicity: maximum profile periodicity supported by + * the driver. Setting this field to a non-zero value indicates that the + * driver supports enhanced multi-BSSID advertisements (EMA AP). */ struct wiphy { struct mutex mtx; @@ -5147,6 +5188,9 @@ struct wiphy { struct rfkill *rfkill; + u8 mbssid_max_interfaces; + u8 ema_max_profile_periodicity; + char priv[] __aligned(NETDEV_ALIGN); }; diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index e89bbf856228..eda608b1eb09 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -360,7 +360,10 @@ * @NL80211_CMD_DEL_INTERFACE: Virtual interface was deleted, has attributes * %NL80211_ATTR_IFINDEX and %NL80211_ATTR_WIPHY. Can also be sent from * userspace to request deletion of a virtual interface, then requires - * attribute %NL80211_ATTR_IFINDEX. + * attribute %NL80211_ATTR_IFINDEX. If multiple BSSID advertisements are + * enabled using %NL80211_ATTR_MBSSID_CONFIG, %NL80211_ATTR_MBSSID_ELEMS, + * and if this command is used for the transmitting interface, then all + * the non-transmitting interfaces are deleted as well. * * @NL80211_CMD_GET_KEY: Get sequence counter information for a key specified * by %NL80211_ATTR_KEY_IDX and/or %NL80211_ATTR_MAC. @@ -2624,6 +2627,18 @@ enum nl80211_commands { * @NL80211_ATTR_COLOR_CHANGE_ELEMS: Nested set of attributes containing the IE * information for the time while performing a color switch. * + * @NL80211_ATTR_MBSSID_CONFIG: Nested attribute for multiple BSSID + * advertisements (MBSSID) parameters in AP mode. + * Kernel uses this attribute to indicate the driver's support for MBSSID + * and enhanced multi-BSSID advertisements (EMA AP) to the userspace. + * Userspace should use this attribute to configure per interface MBSSID + * parameters. + * See &enum nl80211_mbssid_config_attributes for details. + * + * @NL80211_ATTR_MBSSID_ELEMS: Nested parameter to pass multiple BSSID elements. + * Mandatory parameter for the transmitting interface to enable MBSSID. + * Optional for the non-transmitting interfaces. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@ -3127,6 +3142,9 @@ enum nl80211_attrs { NL80211_ATTR_COLOR_CHANGE_COLOR, NL80211_ATTR_COLOR_CHANGE_ELEMS, + NL80211_ATTR_MBSSID_CONFIG, + NL80211_ATTR_MBSSID_ELEMS, + /* add attributes here, update the policy in nl80211.c */ __NL80211_ATTR_AFTER_LAST, @@ -7386,4 +7404,60 @@ enum nl80211_sar_specs_attrs { NL80211_SAR_ATTR_SPECS_MAX = __NL80211_SAR_ATTR_SPECS_LAST - 1, }; +/** + * enum nl80211_mbssid_config_attributes - multiple BSSID (MBSSID) and enhanced + * multi-BSSID advertisements (EMA) in AP mode. + * Kernel uses some of these attributes to advertise driver's support for + * MBSSID and EMA. + * Remaining attributes should be used by the userspace to configure the + * features. + * + * @__NL80211_MBSSID_CONFIG_ATTR_INVALID: Invalid + * + * @NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES: Used by the kernel to advertise + * the maximum number of MBSSID interfaces supported by the driver. + * Driver should indicate MBSSID support by setting + * wiphy->mbssid_max_interfaces to a value more than or equal to 2. + * + * @NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY: Used by the kernel + * to advertise the maximum profile periodicity supported by the driver + * if EMA is enabled. Driver should indicate EMA support to the userspace + * by setting wiphy->mbssid_max_ema_profile_periodicity to + * a non-zero value. + * + * @NL80211_MBSSID_CONFIG_ATTR_INDEX: Mandatory parameter to pass the index of + * this BSS (u8) in the multiple BSSID set. + * Value must be set to 0 for the transmitting interface and non-zero for + * all non-transmitting interfaces. The userspace will be responsible + * for using unique indices for the interfaces. + * Range: 0 to wiphy->mbssid_max_interfaces-1. + * + * @NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX: Mandatory parameter for + * a non-transmitted profile which provides the interface index (u32) of + * the transmitted profile. The value must match one of the interface + * indices advertised by the kernel. Optional if the interface being set up + * is the transmitting one, however, if provided then the value must match + * the interface index of the same. + * + * @NL80211_MBSSID_CONFIG_ATTR_EMA: Flag used to enable EMA AP feature. + * Setting this flag is permitted only if the driver advertises EMA support + * by setting wiphy->mbssid_max_ema_profile_periodicity to non-zero. + * + * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal + * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute + */ +enum nl80211_mbssid_config_attributes { + __NL80211_MBSSID_CONFIG_ATTR_INVALID, + + NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES, + NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY, + NL80211_MBSSID_CONFIG_ATTR_INDEX, + NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX, + NL80211_MBSSID_CONFIG_ATTR_EMA, + + /* keep last */ + __NL80211_MBSSID_CONFIG_ATTR_LAST, + NL80211_MBSSID_CONFIG_ATTR_MAX = __NL80211_MBSSID_CONFIG_ATTR_LAST - 1, +}; + #endif /* __LINUX_NL80211_H */ diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0f728de36f33..3f37e4d5c5d2 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -437,6 +437,16 @@ sar_policy[NL80211_SAR_ATTR_MAX + 1] = { [NL80211_SAR_ATTR_SPECS] = NLA_POLICY_NESTED_ARRAY(sar_specs_policy), }; +static const struct nla_policy +nl80211_mbssid_config_policy[NL80211_MBSSID_CONFIG_ATTR_MAX + 1] = { + [NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES] = NLA_POLICY_MIN(NLA_U8, 2), + [NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY] = + NLA_POLICY_MIN(NLA_U8, 1), + [NL80211_MBSSID_CONFIG_ATTR_INDEX] = { .type = NLA_U8 }, + [NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX] = { .type = NLA_U32 }, + [NL80211_MBSSID_CONFIG_ATTR_EMA] = { .type = NLA_FLAG }, +}; + static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [0] = { .strict_start_type = NL80211_ATTR_HE_OBSS_PD }, [NL80211_ATTR_WIPHY] = { .type = NLA_U32 }, @@ -763,6 +773,9 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_COLOR_CHANGE_COUNT] = { .type = NLA_U8 }, [NL80211_ATTR_COLOR_CHANGE_COLOR] = { .type = NLA_U8 }, [NL80211_ATTR_COLOR_CHANGE_ELEMS] = NLA_POLICY_NESTED(nl80211_policy), + [NL80211_ATTR_MBSSID_CONFIG] = + NLA_POLICY_NESTED(nl80211_mbssid_config_policy), + [NL80211_ATTR_MBSSID_ELEMS] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -2207,6 +2220,35 @@ fail: return -ENOBUFS; } +static int nl80211_put_mbssid_support(struct wiphy *wiphy, struct sk_buff *msg) +{ + struct nlattr *config; + + if (!wiphy->mbssid_max_interfaces) + return 0; + + config = nla_nest_start(msg, NL80211_ATTR_MBSSID_CONFIG); + if (!config) + return -ENOBUFS; + + if (nla_put_u8(msg, NL80211_MBSSID_CONFIG_ATTR_MAX_INTERFACES, + wiphy->mbssid_max_interfaces)) + goto fail; + + if (wiphy->ema_max_profile_periodicity && + nla_put_u8(msg, + NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY, + wiphy->ema_max_profile_periodicity)) + goto fail; + + nla_nest_end(msg, config); + return 0; + +fail: + nla_nest_cancel(msg, config); + return -ENOBUFS; +} + struct nl80211_dump_wiphy_state { s64 filter_wiphy; long start; @@ -2792,6 +2834,9 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_put_sar_specs(rdev, msg)) goto nla_put_failure; + if (nl80211_put_mbssid_support(&rdev->wiphy, msg)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -4981,6 +5026,96 @@ static int validate_beacon_tx_rate(struct cfg80211_registered_device *rdev, return 0; } +static int nl80211_parse_mbssid_config(struct wiphy *wiphy, + struct net_device *dev, + struct nlattr *attrs, + struct cfg80211_mbssid_config *config, + u8 num_elems) +{ + struct nlattr *tb[NL80211_MBSSID_CONFIG_ATTR_MAX + 1]; + + if (!wiphy->mbssid_max_interfaces) + return -EOPNOTSUPP; + + if (nla_parse_nested(tb, NL80211_MBSSID_CONFIG_ATTR_MAX, attrs, NULL, + NULL) || + !tb[NL80211_MBSSID_CONFIG_ATTR_INDEX]) + return -EINVAL; + + config->ema = nla_get_flag(tb[NL80211_MBSSID_CONFIG_ATTR_EMA]); + if (config->ema) { + if (!wiphy->ema_max_profile_periodicity) + return -EOPNOTSUPP; + + if (num_elems > wiphy->ema_max_profile_periodicity) + return -EINVAL; + } + + config->index = nla_get_u8(tb[NL80211_MBSSID_CONFIG_ATTR_INDEX]); + if (config->index >= wiphy->mbssid_max_interfaces || + (!config->index && !num_elems)) + return -EINVAL; + + if (tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]) { + u32 tx_ifindex = + nla_get_u32(tb[NL80211_MBSSID_CONFIG_ATTR_TX_IFINDEX]); + + if ((!config->index && tx_ifindex != dev->ifindex) || + (config->index && tx_ifindex == dev->ifindex)) + return -EINVAL; + + if (tx_ifindex != dev->ifindex) { + struct net_device *tx_netdev = + dev_get_by_index(wiphy_net(wiphy), tx_ifindex); + + if (!tx_netdev || !tx_netdev->ieee80211_ptr || + tx_netdev->ieee80211_ptr->wiphy != wiphy || + tx_netdev->ieee80211_ptr->iftype != + NL80211_IFTYPE_AP) { + dev_put(tx_netdev); + return -EINVAL; + } + + config->tx_wdev = tx_netdev->ieee80211_ptr; + } else { + config->tx_wdev = dev->ieee80211_ptr; + } + } else if (!config->index) { + config->tx_wdev = dev->ieee80211_ptr; + } else { + return -EINVAL; + } + + return 0; +} + +static struct cfg80211_mbssid_elems * +nl80211_parse_mbssid_elems(struct wiphy *wiphy, struct nlattr *attrs) +{ + struct nlattr *nl_elems; + struct cfg80211_mbssid_elems *elems; + int rem_elems; + u8 i = 0, num_elems = 0; + + if (!wiphy->mbssid_max_interfaces) + return ERR_PTR(-EINVAL); + + nla_for_each_nested(nl_elems, attrs, rem_elems) + num_elems++; + + elems = kzalloc(struct_size(elems, elem, num_elems), GFP_KERNEL); + if (!elems) + return ERR_PTR(-ENOMEM); + + nla_for_each_nested(nl_elems, attrs, rem_elems) { + elems->elem[i].data = nla_data(nl_elems); + elems->elem[i].len = nla_len(nl_elems); + i++; + } + elems->cnt = num_elems; + return elems; +} + static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, struct nlattr *attrs[], struct cfg80211_beacon_data *bcn) @@ -5061,6 +5196,17 @@ static int nl80211_parse_beacon(struct cfg80211_registered_device *rdev, bcn->ftm_responder = -1; } + if (attrs[NL80211_ATTR_MBSSID_ELEMS]) { + struct cfg80211_mbssid_elems *mbssid = + nl80211_parse_mbssid_elems(&rdev->wiphy, + attrs[NL80211_ATTR_MBSSID_ELEMS]); + + if (IS_ERR(mbssid)) + return PTR_ERR(mbssid); + + bcn->mbssid_ies = mbssid; + } + return 0; } @@ -5547,6 +5693,17 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) goto out; } + if (info->attrs[NL80211_ATTR_MBSSID_CONFIG]) { + err = nl80211_parse_mbssid_config(&rdev->wiphy, dev, + info->attrs[NL80211_ATTR_MBSSID_CONFIG], + ¶ms->mbssid_config, + params->beacon.mbssid_ies ? + params->beacon.mbssid_ies->cnt : + 0); + if (err) + goto out; + } + nl80211_calculate_ap_params(params); if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) @@ -5568,6 +5725,11 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) out: kfree(params->acl); + kfree(params->beacon.mbssid_ies); + if (params->mbssid_config.tx_wdev && + params->mbssid_config.tx_wdev->netdev && + params->mbssid_config.tx_wdev->netdev != dev) + dev_put(params->mbssid_config.tx_wdev->netdev); kfree(params); return err; @@ -5593,12 +5755,14 @@ static int nl80211_set_beacon(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_beacon(rdev, info->attrs, ¶ms); if (err) - return err; + goto out; wdev_lock(wdev); err = rdev_change_beacon(rdev, dev, ¶ms); wdev_unlock(wdev); +out: + kfree(params.mbssid_ies); return err; } @@ -9275,12 +9439,14 @@ static int nl80211_channel_switch(struct sk_buff *skb, struct genl_info *info) err = nl80211_parse_beacon(rdev, info->attrs, ¶ms.beacon_after); if (err) - return err; + goto free; csa_attrs = kcalloc(NL80211_ATTR_MAX + 1, sizeof(*csa_attrs), GFP_KERNEL); - if (!csa_attrs) - return -ENOMEM; + if (!csa_attrs) { + err = -ENOMEM; + goto free; + } err = nla_parse_nested_deprecated(csa_attrs, NL80211_ATTR_MAX, info->attrs[NL80211_ATTR_CSA_IES], @@ -9398,6 +9564,8 @@ skip_beacons: wdev_unlock(wdev); free: + kfree(params.beacon_after.mbssid_ies); + kfree(params.beacon_csa.mbssid_ies); kfree(csa_attrs); return err; } @@ -14933,6 +15101,8 @@ static int nl80211_color_change(struct sk_buff *skb, struct genl_info *info) wdev_unlock(wdev); out: + kfree(params.beacon_next.mbssid_ies); + kfree(params.beacon_color_change.mbssid_ies); kfree(tb); return err; } -- cgit v1.2.3 From 61bc346ce64a3864ac55f5d18bdc1572cda4fb18 Mon Sep 17 00:00:00 2001 From: Eugene Syromiatnikov Date: Wed, 25 Aug 2021 19:06:13 +0200 Subject: uapi/linux/prctl: provide macro definitions for the PR_SCHED_CORE type argument Commit 7ac592aa35a684ff ("sched: prctl() core-scheduling interface") made use of enum pid_type in prctl's arg4; this type and the associated enumeration definitions are not exposed to userspace. Christian has suggested to provide additional macro definitions that convey the meaning of the type argument more in alignment with its actual usage, and this patch does exactly that. Link: https://lore.kernel.org/r/20210825170613.GA3884@asgard.redhat.com Suggested-by: Christian Brauner Acked-by: Christian Brauner Signed-off-by: Eugene Syromiatnikov Complements: 7ac592aa35a684ff ("sched: prctl() core-scheduling interface") Signed-off-by: Christian Brauner --- Documentation/admin-guide/hw-vuln/core-scheduling.rst | 5 +++-- include/uapi/linux/prctl.h | 3 +++ kernel/sched/core_sched.c | 4 ++++ 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/hw-vuln/core-scheduling.rst b/Documentation/admin-guide/hw-vuln/core-scheduling.rst index 0febe458597c..cf1eeefdfc32 100644 --- a/Documentation/admin-guide/hw-vuln/core-scheduling.rst +++ b/Documentation/admin-guide/hw-vuln/core-scheduling.rst @@ -61,8 +61,9 @@ arg3: ``pid`` of the task for which the operation applies. arg4: - ``pid_type`` for which the operation applies. It is of type ``enum pid_type``. - For example, if arg4 is ``PIDTYPE_TGID``, then the operation of this command + ``pid_type`` for which the operation applies. It is one of + ``PR_SCHED_CORE_SCOPE_``-prefixed macro constants. For example, if arg4 + is ``PR_SCHED_CORE_SCOPE_THREAD_GROUP``, then the operation of this command will be performed for all tasks in the task group of ``pid``. arg5: diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 43bd7f713c39..b2e4dc1449b9 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -268,5 +268,8 @@ struct prctl_mm_map { # define PR_SCHED_CORE_SHARE_TO 2 /* push core_sched cookie to pid */ # define PR_SCHED_CORE_SHARE_FROM 3 /* pull core_sched cookie to pid */ # define PR_SCHED_CORE_MAX 4 +# define PR_SCHED_CORE_SCOPE_THREAD 0 +# define PR_SCHED_CORE_SCOPE_THREAD_GROUP 1 +# define PR_SCHED_CORE_SCOPE_PROCESS_GROUP 2 #endif /* _LINUX_PRCTL_H */ diff --git a/kernel/sched/core_sched.c b/kernel/sched/core_sched.c index 9a80e9a474c0..20f640949450 100644 --- a/kernel/sched/core_sched.c +++ b/kernel/sched/core_sched.c @@ -134,6 +134,10 @@ int sched_core_share_pid(unsigned int cmd, pid_t pid, enum pid_type type, if (!static_branch_likely(&sched_smt_present)) return -ENODEV; + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD != PIDTYPE_PID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_THREAD_GROUP != PIDTYPE_TGID); + BUILD_BUG_ON(PR_SCHED_CORE_SCOPE_PROCESS_GROUP != PIDTYPE_PGID); + if (type > PIDTYPE_PGID || cmd >= PR_SCHED_CORE_MAX || pid < 0 || (cmd != PR_SCHED_CORE_GET && uaddr)) return -EINVAL; -- cgit v1.2.3 From b84f60a307f09debe30cc171b0f0a5c36797cf67 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:49 +0200 Subject: media: Rename V4L2_PIX_FMT_SUNXI_TILED_NV12 to V4L2_PIX_FMT_NV12_32L32 The V4L2_PIX_FMT_SUNXI_TILED_NV12 format is actually a fairly common NV12 tiled format, with 32x32 linear tiles. Rename the format and move its documentation together with the other tiled NV12 formats. Keep V4L2_PIX_FMT_SUNXI_TILED_NV12 for application compatibility. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 14 -------------- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 13 ++++++++++--- .../userspace-api/media/videodev2.h.rst.exceptions | 1 + drivers/media/v4l2-core/v4l2-ioctl.c | 2 +- drivers/staging/media/sunxi/cedrus/cedrus.c | 2 +- drivers/staging/media/sunxi/cedrus/cedrus_hw.c | 2 +- drivers/staging/media/sunxi/cedrus/cedrus_video.c | 4 ++-- include/uapi/linux/videodev2.h | 9 ++++++++- 8 files changed, 24 insertions(+), 23 deletions(-) (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 0b879c0da713..e762f911737a 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -246,20 +246,6 @@ please make a proposal on the linux-media mailing list. It is an opaque intermediate format and the MDP hardware must be used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``, ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``. - * .. _V4L2-PIX-FMT-SUNXI-TILED-NV12: - - - ``V4L2_PIX_FMT_SUNXI_TILED_NV12`` - - 'ST12' - - Two-planar NV12-based format used by the video engine found on Allwinner - (codenamed sunxi) platforms, with 32x32 tiles for the luminance plane - and 32x64 tiles for the chrominance plane. The data in each tile is - stored in linear order, within the tile bounds. Each tile follows the - previous one linearly in memory (from left to right, top to bottom). - - The associated buffer dimensions are aligned to match an integer number - of tiles, resulting in 32-aligned resolutions for the luminance plane - and 16-aligned resolutions for the chrominance plane (with 2x2 - subsampling). .. raw:: latex diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index 090c091affd2..edeaf7628b28 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -254,14 +254,16 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: +.. _V4L2-PIX-FMT-NV12-32L32: -NV12MT and MV12MT_16X16 ------------------------ +Tiled NV12 +---------- Semi-planar YUV 4:2:0 formats, using macroblock tiling. The chroma plane is subsampled by 2 in each direction. Chroma lines contain half the number of pixels and the same number of bytes as luma lines, and the chroma plane -contains half the number of lines of the luma plane. +contains half the number of lines of the luma plane. Each tile follows the +previous one linearly in memory (from left to right, top to bottom). ``V4L2_PIX_FMT_NV12MT_16X16`` stores pixel in 2D 16x16 macroblocks, and stores macroblocks linearly in memory. The line stride and image height must be @@ -276,6 +278,11 @@ If the vertical resolution is an odd number of macroblocks, the last row of macroblocks is stored in linear order. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_32L32`` stores pixel in 32x32 tiles, and stores +tiles linearly in memory. The line stride and image height must be +aligned to a multiple of 32. The layouts of the luma and chroma planes are +identical. + .. _nv12mt: .. kernel-figure:: nv12mt.svg diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 2217b56c2686..982675a2342e 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -187,6 +187,7 @@ replace define V4L2_CAP_IO_MC device-capabilities # V4L2 pix flags replace define V4L2_PIX_FMT_PRIV_MAGIC :c:type:`v4l2_pix_format` replace define V4L2_PIX_FMT_FLAG_PREMUL_ALPHA format-flags +replace define V4L2_PIX_FMT_SUNXI_TILED_NV12 :c:type:`v4l2_pix_format` # V4L2 format flags replace define V4L2_FMT_FLAG_COMPRESSED fmtdesc-flags diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 05d5db3d85e5..ed194e9da7b0 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1282,6 +1282,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV21M: descr = "Y/CrCb 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV16M: descr = "Y/CbCr 4:2:2 (N-C)"; break; @@ -1415,7 +1416,6 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_SE401: descr = "GSPCA SE401"; break; case V4L2_PIX_FMT_S5C_UYVY_JPG: descr = "S5C73MX interleaved UYVY/JPEG"; break; case V4L2_PIX_FMT_MT21C: descr = "Mediatek Compressed Format"; break; - case V4L2_PIX_FMT_SUNXI_TILED_NV12: descr = "Sunxi Tiled NV12 Format"; break; default: if (fmt->description[0]) return; diff --git a/drivers/staging/media/sunxi/cedrus/cedrus.c b/drivers/staging/media/sunxi/cedrus/cedrus.c index 8114e2167013..144286920749 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus.c @@ -288,7 +288,7 @@ static int cedrus_open(struct file *file) ret = PTR_ERR(ctx->fh.m2m_ctx); goto err_ctrls; } - ctx->dst_fmt.pixelformat = V4L2_PIX_FMT_SUNXI_TILED_NV12; + ctx->dst_fmt.pixelformat = V4L2_PIX_FMT_NV12_32L32; cedrus_prepare_format(&ctx->dst_fmt); ctx->src_fmt.pixelformat = V4L2_PIX_FMT_MPEG2_SLICE; /* diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c index e2f2ff609c7e..2d7663726467 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c @@ -99,7 +99,7 @@ void cedrus_dst_format_set(struct cedrus_dev *dev, cedrus_write(dev, VE_PRIMARY_FB_LINE_STRIDE, reg); break; - case V4L2_PIX_FMT_SUNXI_TILED_NV12: + case V4L2_PIX_FMT_NV12_32L32: default: reg = VE_PRIMARY_OUT_FMT_TILED_32_NV12; cedrus_write(dev, VE_PRIMARY_OUT_FMT, reg); diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_video.c b/drivers/staging/media/sunxi/cedrus/cedrus_video.c index f3cd452575d4..ee7353086641 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_video.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_video.c @@ -56,7 +56,7 @@ static struct cedrus_format cedrus_formats[] = { .capabilities = CEDRUS_CAPABILITY_VP8_DEC, }, { - .pixelformat = V4L2_PIX_FMT_SUNXI_TILED_NV12, + .pixelformat = V4L2_PIX_FMT_NV12_32L32, .directions = CEDRUS_DECODE_DST, }, { @@ -124,7 +124,7 @@ void cedrus_prepare_format(struct v4l2_pix_format *pix_fmt) sizeimage = max_t(u32, SZ_1K, sizeimage); break; - case V4L2_PIX_FMT_SUNXI_TILED_NV12: + case V4L2_PIX_FMT_NV12_32L32: /* 32-aligned stride. */ bytesperline = ALIGN(width, 32); diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9260791b8438..0188cd39468f 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -627,6 +627,9 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YUV444M v4l2_fourcc('Y', 'M', '2', '4') /* 24 YUV444 planar */ #define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24 YVU444 planar */ +/* Tiled YUV formats */ +#define V4L2_PIX_FMT_NV12_32L32 v4l2_fourcc('S', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 32x32 tiles */ + /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G', 'B', 'R', 'G') /* 8 GBGB.. RGRG.. */ @@ -734,7 +737,6 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Z16 v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */ #define V4L2_PIX_FMT_MT21C v4l2_fourcc('M', 'T', '2', '1') /* Mediatek compressed block mode */ #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ -#define V4L2_PIX_FMT_SUNXI_TILED_NV12 v4l2_fourcc('S', 'T', '1', '2') /* Sunxi Tiled NV12 Format */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ @@ -2615,4 +2617,9 @@ struct v4l2_create_buffers { #define BASE_VIDIOC_PRIVATE 192 /* 192-255 are private */ +/* Deprecated definitions kept for backwards compatibility */ +#ifndef __KERNEL__ +#define V4L2_PIX_FMT_SUNXI_TILED_NV12 V4L2_PIX_FMT_NV12_32L32 +#endif + #endif /* _UAPI__LINUX_VIDEODEV2_H */ -- cgit v1.2.3 From 78eee7b5f110c9884c8ffd1dfcdd9c29296f3e43 Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:50 +0200 Subject: media: Rename V4L2_PIX_FMT_HM12 to V4L2_PIX_FMT_NV12_16L16 The V4L2_PIX_FMT_HM12 format is actually a simple NV12 tiled format, with 16x16 linear tiles. Rename the format and move its documentation together with the other tiled NV12 formats. Keep V4L2_PIX_FMT_HM12 for application compatibility. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/admin-guide/media/ivtv.rst | 2 +- Documentation/userspace-api/media/drivers/cx2341x-uapi.rst | 8 +++----- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 8 -------- Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst | 6 ++++++ Documentation/userspace-api/media/videodev2.h.rst.exceptions | 1 + drivers/media/pci/cx18/cx18-ioctl.c | 4 ++-- drivers/media/pci/cx18/cx18-streams.c | 8 ++++---- drivers/media/pci/ivtv/ivtv-ioctl.c | 8 ++++---- drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c | 10 +++++----- drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h | 2 +- drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c | 2 +- drivers/media/v4l2-core/v4l2-ioctl.c | 2 +- include/uapi/linux/videodev2.h | 3 ++- 13 files changed, 31 insertions(+), 33 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/admin-guide/media/ivtv.rst b/Documentation/admin-guide/media/ivtv.rst index 7b8775d20214..101f16d0263e 100644 --- a/Documentation/admin-guide/media/ivtv.rst +++ b/Documentation/admin-guide/media/ivtv.rst @@ -159,7 +159,7 @@ whatever). Otherwise the device numbers can get confusing. The ivtv Read-only The raw YUV video output from the current video input. The YUV format - is non-standard (V4L2_PIX_FMT_HM12). + is a 16x16 linear tiled NV12 format (V4L2_PIX_FMT_NV12_16L16) Note that the YUV and PCM streams are not synchronized, so they are of limited use. diff --git a/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst b/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst index 8a7977af79d5..debde65fb8cd 100644 --- a/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst +++ b/Documentation/userspace-api/media/drivers/cx2341x-uapi.rst @@ -7,9 +7,7 @@ Non-compressed file format -------------------------- The cx23416 can produce (and the cx23415 can also read) raw YUV output. The -format of a YUV frame is specific to this chip and is called HM12. 'HM' stands -for 'Hauppauge Macroblock', which is a misnomer as 'Conexant Macroblock' would -be more accurate. +format of a YUV frame is 16x16 linear tiled NV12 (V4L2_PIX_FMT_NV12_16L16). The format is YUV 4:2:0 which uses 1 Y byte per pixel and 1 U and V byte per four pixels. @@ -34,8 +32,8 @@ second line of 8 UV pairs of the top-left block, etc. After transmitting this block the first line of the block on the right to the first block is transmitted, etc. -The code below is given as an example on how to convert HM12 to separate -Y, U and V planes. This code assumes frames of 720x576 (PAL) pixels. +The code below is given as an example on how to convert V4L2_PIX_FMT_NV12_16L16 +to separate Y, U and V planes. This code assumes frames of 720x576 (PAL) pixels. The width of a frame is always 720 pixels, regardless of the actual specified width. diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst index e762f911737a..adcad9454175 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -48,14 +48,6 @@ please make a proposal on the linux-media mailing list. - ``V4L2_PIX_FMT_HI240`` - 'HI24' - 8 bit RGB format used by the BTTV driver. - * .. _V4L2-PIX-FMT-HM12: - - - ``V4L2_PIX_FMT_HM12`` - - 'HM12' - - YUV 4:2:0 format used by the IVTV driver. - - The format is documented in the kernel sources in the file - ``Documentation/userspace-api/media/drivers/cx2341x-uapi.rst`` * .. _V4L2-PIX-FMT-CPIA1: - ``V4L2_PIX_FMT_CPIA1`` diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst index edeaf7628b28..884828f2272c 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -254,6 +254,7 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: +.. _V4L2-PIX-FMT-NV12-16L16: .. _V4L2-PIX-FMT-NV12-32L32: Tiled NV12 @@ -278,6 +279,11 @@ If the vertical resolution is an odd number of macroblocks, the last row of macroblocks is stored in linear order. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_16L16`` stores pixel in 16x16 tiles, and stores +tiles linearly in memory. The line stride and image height must be +aligned to a multiple of 16. The layouts of the luma and chroma planes are +identical. + ``V4L2_PIX_FMT_NV12_32L32`` stores pixel in 32x32 tiles, and stores tiles linearly in memory. The line stride and image height must be aligned to a multiple of 32. The layouts of the luma and chroma planes are diff --git a/Documentation/userspace-api/media/videodev2.h.rst.exceptions b/Documentation/userspace-api/media/videodev2.h.rst.exceptions index 982675a2342e..eb0b1cd37abd 100644 --- a/Documentation/userspace-api/media/videodev2.h.rst.exceptions +++ b/Documentation/userspace-api/media/videodev2.h.rst.exceptions @@ -187,6 +187,7 @@ replace define V4L2_CAP_IO_MC device-capabilities # V4L2 pix flags replace define V4L2_PIX_FMT_PRIV_MAGIC :c:type:`v4l2_pix_format` replace define V4L2_PIX_FMT_FLAG_PREMUL_ALPHA format-flags +replace define V4L2_PIX_FMT_HM12 :c:type:`v4l2_pix_format` replace define V4L2_PIX_FMT_SUNXI_TILED_NV12 :c:type:`v4l2_pix_format` # V4L2 format flags diff --git a/drivers/media/pci/cx18/cx18-ioctl.c b/drivers/media/pci/cx18/cx18-ioctl.c index 4864def20676..ce3f0141f94e 100644 --- a/drivers/media/pci/cx18/cx18-ioctl.c +++ b/drivers/media/pci/cx18/cx18-ioctl.c @@ -276,7 +276,7 @@ static int cx18_s_fmt_vid_cap(struct file *file, void *fh, s->pixelformat = fmt->fmt.pix.pixelformat; /* HM12 YUV size is (Y=(h*720) + UV=(h*(720/2))) UYUV YUV size is (Y=(h*720) + UV=(h*(720))) */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) { + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) { s->vb_bytes_per_frame = h * 720 * 3 / 2; s->vb_bytes_per_line = 720; /* First plane */ } else { @@ -470,7 +470,7 @@ static int cx18_enum_fmt_vid_cap(struct file *file, void *fh, .index = 0, .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .description = "HM12 (YUV 4:1:1)", - .pixelformat = V4L2_PIX_FMT_HM12, + .pixelformat = V4L2_PIX_FMT_NV12_16L16, }, { .index = 1, diff --git a/drivers/media/pci/cx18/cx18-streams.c b/drivers/media/pci/cx18/cx18-streams.c index c41bae118415..16d37ab48906 100644 --- a/drivers/media/pci/cx18/cx18-streams.c +++ b/drivers/media/pci/cx18/cx18-streams.c @@ -133,7 +133,7 @@ static int cx18_prepare_buffer(struct videobuf_queue *q, /* HM12 YUV size is (Y=(h*720) + UV=(h*(720/2))) UYUV YUV size is (Y=(h*720) + UV=(h*(720))) */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) s->vb_bytes_per_frame = height * 720 * 3 / 2; else s->vb_bytes_per_frame = height * 720 * 2; @@ -155,7 +155,7 @@ static int cx18_prepare_buffer(struct videobuf_queue *q, /* HM12 YUV size is (Y=(h*720) + UV=(h*(720/2))) UYUV YUV size is (Y=(h*720) + UV=(h*(720))) */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) s->vb_bytes_per_frame = height * 720 * 3 / 2; else s->vb_bytes_per_frame = height * 720 * 2; @@ -287,7 +287,7 @@ static void cx18_stream_init(struct cx18 *cx, int type) s, &cx->serialize_lock); /* Assume the previous pixel default */ - s->pixelformat = V4L2_PIX_FMT_HM12; + s->pixelformat = V4L2_PIX_FMT_NV12_16L16; s->vb_bytes_per_frame = cx->cxhdl.height * 720 * 3 / 2; s->vb_bytes_per_line = 720; } @@ -733,7 +733,7 @@ static void cx18_stream_configure_mdls(struct cx18_stream *s) * Set the MDL size to the exact size needed for one frame. * Use enough buffers per MDL to cover the MDL size */ - if (s->pixelformat == V4L2_PIX_FMT_HM12) + if (s->pixelformat == V4L2_PIX_FMT_NV12_16L16) s->mdl_size = 720 * s->cx->cxhdl.height * 3 / 2; else s->mdl_size = 720 * s->cx->cxhdl.height * 2; diff --git a/drivers/media/pci/ivtv/ivtv-ioctl.c b/drivers/media/pci/ivtv/ivtv-ioctl.c index da19b2e95e6c..0cdf6b3210c2 100644 --- a/drivers/media/pci/ivtv/ivtv-ioctl.c +++ b/drivers/media/pci/ivtv/ivtv-ioctl.c @@ -339,7 +339,7 @@ static int ivtv_g_fmt_vid_cap(struct file *file, void *fh, struct v4l2_format *f pixfmt->colorspace = V4L2_COLORSPACE_SMPTE170M; pixfmt->field = V4L2_FIELD_INTERLACED; if (id->type == IVTV_ENC_STREAM_TYPE_YUV) { - pixfmt->pixelformat = V4L2_PIX_FMT_HM12; + pixfmt->pixelformat = V4L2_PIX_FMT_NV12_16L16; /* YUV size is (Y=(h*720) + UV=(h*(720/2))) */ pixfmt->sizeimage = pixfmt->height * 720 * 3 / 2; pixfmt->bytesperline = 720; @@ -417,7 +417,7 @@ static int ivtv_g_fmt_vid_out(struct file *file, void *fh, struct v4l2_format *f pixfmt->field = V4L2_FIELD_ANY; break; } - pixfmt->pixelformat = V4L2_PIX_FMT_HM12; + pixfmt->pixelformat = V4L2_PIX_FMT_NV12_16L16; pixfmt->bytesperline = 720; pixfmt->width = itv->yuv_info.v4l2_src_w; pixfmt->height = itv->yuv_info.v4l2_src_h; @@ -917,7 +917,7 @@ static int ivtv_enum_fmt_vid_cap(struct file *file, void *fh, struct v4l2_fmtdes static const struct v4l2_fmtdesc hm12 = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, .description = "HM12 (YUV 4:2:0)", - .pixelformat = V4L2_PIX_FMT_HM12, + .pixelformat = V4L2_PIX_FMT_NV12_16L16, }; static const struct v4l2_fmtdesc mpeg = { .type = V4L2_BUF_TYPE_VIDEO_CAPTURE, @@ -944,7 +944,7 @@ static int ivtv_enum_fmt_vid_out(struct file *file, void *fh, struct v4l2_fmtdes static const struct v4l2_fmtdesc hm12 = { .type = V4L2_BUF_TYPE_VIDEO_OUTPUT, .description = "HM12 (YUV 4:2:0)", - .pixelformat = V4L2_PIX_FMT_HM12, + .pixelformat = V4L2_PIX_FMT_NV12_16L16, }; static const struct v4l2_fmtdesc mpeg = { .type = V4L2_BUF_TYPE_VIDEO_OUTPUT, diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c index 08df0c833423..4b8d66fec3cf 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.c @@ -61,7 +61,7 @@ bool sun6i_csi_is_format_supported(struct sun6i_csi *csi, || sdev->csi.v4l2_ep.bus_type == V4L2_MBUS_BT656) && sdev->csi.v4l2_ep.bus.parallel.bus_width == 16) { switch (pixformat) { - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_NV16: @@ -124,7 +124,7 @@ bool sun6i_csi_is_format_supported(struct sun6i_csi *csi, case V4L2_PIX_FMT_VYUY: return (mbus_code == MEDIA_BUS_FMT_VYUY8_2X8); - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_NV16: @@ -269,7 +269,7 @@ static enum csi_output_fmt get_csi_output_format(struct sun6i_csi_dev *sdev, case V4L2_PIX_FMT_VYUY: return buf_interlaced ? CSI_FRAME_RAW_8 : CSI_FIELD_RAW_8; - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: return buf_interlaced ? CSI_FRAME_MB_YUV420 : CSI_FIELD_MB_YUV420; case V4L2_PIX_FMT_NV12: @@ -311,7 +311,7 @@ static enum csi_input_seq get_csi_input_seq(struct sun6i_csi_dev *sdev, return 0; switch (pixformat) { - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV16: case V4L2_PIX_FMT_YUV420: @@ -526,7 +526,7 @@ static void sun6i_csi_set_window(struct sun6i_csi_dev *sdev) planar_offset[0] = 0; switch (config->pixelformat) { - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_NV16: diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h index c626821aaedb..3a38d107ae3f 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_csi.h @@ -105,7 +105,7 @@ static inline int sun6i_csi_get_bpp(unsigned int pixformat) case V4L2_PIX_FMT_SGBRG12: case V4L2_PIX_FMT_SGRBG12: case V4L2_PIX_FMT_SRGGB12: - case V4L2_PIX_FMT_HM12: + case V4L2_PIX_FMT_NV12_16L16: case V4L2_PIX_FMT_NV12: case V4L2_PIX_FMT_NV21: case V4L2_PIX_FMT_YUV420: diff --git a/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c b/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c index 07b2161392d2..33459892c1a9 100644 --- a/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c +++ b/drivers/media/platform/sunxi/sun6i-csi/sun6i_video.c @@ -48,7 +48,7 @@ static const u32 supported_pixformats[] = { V4L2_PIX_FMT_YVYU, V4L2_PIX_FMT_UYVY, V4L2_PIX_FMT_VYUY, - V4L2_PIX_FMT_HM12, + V4L2_PIX_FMT_NV12_16L16, V4L2_PIX_FMT_NV12, V4L2_PIX_FMT_NV21, V4L2_PIX_FMT_YUV420, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ed194e9da7b0..8731d65ad39e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1274,7 +1274,6 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_YUV410: descr = "Planar YUV 4:1:0"; break; case V4L2_PIX_FMT_YUV420: descr = "Planar YUV 4:2:0"; break; case V4L2_PIX_FMT_HI240: descr = "8-bit Dithered RGB (BTTV)"; break; - case V4L2_PIX_FMT_HM12: descr = "YUV 4:2:0 (16x16 Macroblocks)"; break; case V4L2_PIX_FMT_M420: descr = "YUV 4:2:0 (M420)"; break; case V4L2_PIX_FMT_NV12: descr = "Y/CbCr 4:2:0"; break; case V4L2_PIX_FMT_NV21: descr = "Y/CrCb 4:2:0"; break; @@ -1282,6 +1281,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_NV12_16L16: descr = "Y/CbCr 4:2:0 (16x16 Linear)"; break; case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; case V4L2_PIX_FMT_NV21M: descr = "Y/CrCb 4:2:0 (N-C)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 0188cd39468f..40fec00ce73a 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -601,7 +601,6 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV61 v4l2_fourcc('N', 'V', '6', '1') /* 16 Y/CrCb 4:2:2 */ #define V4L2_PIX_FMT_NV24 v4l2_fourcc('N', 'V', '2', '4') /* 24 Y/CbCr 4:4:4 */ #define V4L2_PIX_FMT_NV42 v4l2_fourcc('N', 'V', '4', '2') /* 24 Y/CrCb 4:4:4 */ -#define V4L2_PIX_FMT_HM12 v4l2_fourcc('H', 'M', '1', '2') /* 8 YUV 4:2:0 16x16 macroblocks */ /* two non contiguous planes - one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12M v4l2_fourcc('N', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 */ @@ -628,6 +627,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24 YVU444 planar */ /* Tiled YUV formats */ +#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 */ /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ @@ -2619,6 +2619,7 @@ struct v4l2_create_buffers { /* Deprecated definitions kept for backwards compatibility */ #ifndef __KERNEL__ +#define V4L2_PIX_FMT_HM12 V4L2_PIX_FMT_NV12_16L16 #define V4L2_PIX_FMT_SUNXI_TILED_NV12 V4L2_PIX_FMT_NV12_32L32 #endif -- cgit v1.2.3 From 683f71ebb35d9223b4a22488e2eaffac30af104d Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:51 +0200 Subject: media: Add NV12_4L4 tiled format This format is produced by VeriSilicon Hantro G2 and VC8000D cores. It is a simple 4x4 tiling layout in a linear way. The pixel format was introduced by GStreamer using FourCC VT12, so let's stick to it. Link: https://gstreamer.freedesktop.org/documentation/video/video-format.html Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst | 6 ++++++ drivers/media/v4l2-core/v4l2-common.c | 3 +++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 4 files changed, 11 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 884828f2272c..0fc74351605a 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -254,6 +254,7 @@ of the luma plane. .. _V4L2-PIX-FMT-NV12MT: .. _V4L2-PIX-FMT-NV12MT-16X16: +.. _V4L2-PIX-FMT-NV12-4L4: .. _V4L2-PIX-FMT-NV12-16L16: .. _V4L2-PIX-FMT-NV12-32L32: @@ -279,6 +280,11 @@ If the vertical resolution is an odd number of macroblocks, the last row of macroblocks is stored in linear order. The layouts of the luma and chroma planes are identical. +``V4L2_PIX_FMT_NV12_4L4`` stores pixel in 4x4 tiles, and stores +tiles linearly in memory. The line stride and image height must be +aligned to a multiple of 4. The layouts of the luma and chroma planes are +identical. + ``V4L2_PIX_FMT_NV12_16L16`` stores pixel in 16x16 tiles, and stores tiles linearly in memory. The line stride and image height must be aligned to a multiple of 16. The layouts of the luma and chroma planes are diff --git a/drivers/media/v4l2-core/v4l2-common.c b/drivers/media/v4l2-core/v4l2-common.c index 04af03285a20..df34b2a283bc 100644 --- a/drivers/media/v4l2-core/v4l2-common.c +++ b/drivers/media/v4l2-core/v4l2-common.c @@ -275,6 +275,9 @@ const struct v4l2_format_info *v4l2_format_info(u32 format) { .format = V4L2_PIX_FMT_YUV422P, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 1 }, { .format = V4L2_PIX_FMT_GREY, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 1, .bpp = { 1, 0, 0, 0 }, .hdiv = 1, .vdiv = 1 }, + /* Tiled YUV formats */ + { .format = V4L2_PIX_FMT_NV12_4L4, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 1, .comp_planes = 2, .bpp = { 1, 2, 0, 0 }, .hdiv = 2, .vdiv = 2 }, + /* YUV planar formats, non contiguous variant */ { .format = V4L2_PIX_FMT_YUV420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 }, { .format = V4L2_PIX_FMT_YVU420M, .pixel_enc = V4L2_PIXEL_ENC_YUV, .mem_planes = 3, .comp_planes = 3, .bpp = { 1, 1, 1, 0 }, .hdiv = 2, .vdiv = 2 }, diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index 8731d65ad39e..ec6fc1ef291e 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1281,6 +1281,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_NV61: descr = "Y/CrCb 4:2:2"; break; case V4L2_PIX_FMT_NV24: descr = "Y/CbCr 4:4:4"; break; case V4L2_PIX_FMT_NV42: descr = "Y/CrCb 4:4:4"; break; + case V4L2_PIX_FMT_NV12_4L4: descr = "Y/CbCr 4:2:0 (4x4 Linear)"; break; case V4L2_PIX_FMT_NV12_16L16: descr = "Y/CbCr 4:2:0 (16x16 Linear)"; break; case V4L2_PIX_FMT_NV12_32L32: descr = "Y/CbCr 4:2:0 (32x32 Linear)"; break; case V4L2_PIX_FMT_NV12M: descr = "Y/CbCr 4:2:0 (N-C)"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 40fec00ce73a..56003a5467fc 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -627,6 +627,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_YVU444M v4l2_fourcc('Y', 'M', '4', '2') /* 24 YVU444 planar */ /* Tiled YUV formats */ +#define V4L2_PIX_FMT_NV12_4L4 v4l2_fourcc('V', 'T', '1', '2') /* 12 Y/CbCr 4:2:0 4x4 tiles */ #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 */ -- cgit v1.2.3 From 75b8f8f2646ccaf085a87983329be8e47bd8b6bc Mon Sep 17 00:00:00 2001 From: Ezequiel Garcia Date: Thu, 5 Aug 2021 04:47:52 +0200 Subject: media: Clean V4L2_PIX_FMT_NV12MT documentation Add more information about V4L2_PIX_FMT_NV12MT and V4L2_PIX_FMT_NV12M_16X16, so it's clearer for driver authors and users. Also, group the two pixel formats with the other tiled formats, for clarity. Unlike the recently introduced tiled formats (V4L2_PIX_FMT_NV12_4L4, etc) these formats have remained Samsung-specific until now. Therefore, and although the NV12MT and NV12MT_16X16 nomenclatures are less clear, we are keeping them as-is. Signed-off-by: Ezequiel Garcia Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/pixfmt-yuv-planar.rst | 25 +++++++++++----------- include/uapi/linux/videodev2.h | 6 ++++-- 2 files changed, 17 insertions(+), 14 deletions(-) (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 0fc74351605a..3a09d93d405b 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-planar.rst @@ -99,7 +99,7 @@ All components are stored with the same number of bits per component. - 4:2:0 - Cb, Cr - No - - 64x32 macroblocks + - 64x32 tiles Horizontal Z order * - V4L2_PIX_FMT_NV12MT_16X16 @@ -108,7 +108,7 @@ All components are stored with the same number of bits per component. - 4:2:2 - Cb, Cr - No - - 16x16 macroblocks + - 16x16 tiles * - V4L2_PIX_FMT_NV16 - 'NV16' - 8 @@ -267,17 +267,18 @@ pixels and the same number of bytes as luma lines, and the chroma plane contains half the number of lines of the luma plane. Each tile follows the previous one linearly in memory (from left to right, top to bottom). -``V4L2_PIX_FMT_NV12MT_16X16`` stores pixel in 2D 16x16 macroblocks, and stores -macroblocks linearly in memory. The line stride and image height must be -aligned to a multiple of 16. The layouts of the luma and chroma planes are -identical. +``V4L2_PIX_FMT_NV12MT_16X16`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores +pixels in 2D 16x16 tiles, and stores tiles linearly in memory. +The line stride and image height must be aligned to a multiple of 16. +The layouts of the luma and chroma planes are identical. -``V4L2_PIX_FMT_NV12MT`` stores pixels in 2D 64x32 macroblocks, and stores 2x2 -groups of macroblocks in Z-order in memory, alternating Z and mirrored Z shapes -horizontally. The line stride must be a multiple of 128 pixels to ensure an +``V4L2_PIX_FMT_NV12MT`` is similar to ``V4L2_PIX_FMT_NV12M`` but stores +pixels in 2D 64x32 tiles, and stores 2x2 groups of tiles in +Z-order in memory, alternating Z and mirrored Z shapes horizontally. +The line stride must be a multiple of 128 pixels to ensure an integer number of Z shapes. The image height must be a multiple of 32 pixels. -If the vertical resolution is an odd number of macroblocks, the last row of -macroblocks is stored in linear order. The layouts of the luma and chroma +If the vertical resolution is an odd number of tiles, the last row of +tiles is stored in linear order. The layouts of the luma and chroma planes are identical. ``V4L2_PIX_FMT_NV12_4L4`` stores pixel in 4x4 tiles, and stores @@ -309,7 +310,7 @@ identical. :alt: nv12mt_example.svg :align: center - Example V4L2_PIX_FMT_NV12MT memory layout of macroblocks + Example V4L2_PIX_FMT_NV12MT memory layout of tiles .. _V4L2-PIX-FMT-NV16: diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 56003a5467fc..58392dcd3bf5 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -607,8 +607,6 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_NV21M v4l2_fourcc('N', 'M', '2', '1') /* 21 Y/CrCb 4:2:0 */ #define V4L2_PIX_FMT_NV16M v4l2_fourcc('N', 'M', '1', '6') /* 16 Y/CbCr 4:2:2 */ #define V4L2_PIX_FMT_NV61M v4l2_fourcc('N', 'M', '6', '1') /* 16 Y/CrCb 4:2:2 */ -#define V4L2_PIX_FMT_NV12MT v4l2_fourcc('T', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 64x32 macroblocks */ -#define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 macroblocks */ /* three planes - Y Cb, Cr */ #define V4L2_PIX_FMT_YUV410 v4l2_fourcc('Y', 'U', 'V', '9') /* 9 YUV 4:1:0 */ @@ -631,6 +629,10 @@ 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 */ +/* 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 */ +#define V4L2_PIX_FMT_NV12MT_16X16 v4l2_fourcc('V', 'M', '1', '2') /* 12 Y/CbCr 4:2:0 16x16 tiles */ + /* Bayer formats - see http://www.siliconimaging.com/RGB%20Bayer.htm */ #define V4L2_PIX_FMT_SBGGR8 v4l2_fourcc('B', 'A', '8', '1') /* 8 BGBG.. GRGR.. */ #define V4L2_PIX_FMT_SGBRG8 v4l2_fourcc('G', 'B', 'R', 'G') /* 8 GBGB.. RGRG.. */ -- cgit v1.2.3 From ffe5350c016a0de8ac77d32d9d4ea378cc9ff402 Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Fri, 6 Aug 2021 06:15:25 +0200 Subject: media: add Mediatek's MM21 format Add Mediatek's non-compressed 8 bit block video mode. This format is produced by the MT8183 codec and can be converted to a non-proprietary format by the MDP3 component. Signed-off-by: Alexandre Courbot Signed-off-by: Tzung-Bi Shih Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 7 +++++++ drivers/media/v4l2-core/v4l2-ioctl.c | 1 + include/uapi/linux/videodev2.h | 1 + 3 files changed, 9 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 adcad9454175..2f2133b4cd9c 100644 --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst @@ -238,6 +238,13 @@ please make a proposal on the linux-media mailing list. It is an opaque intermediate format and the MDP hardware must be used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``, ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``. + * .. _V4L2-PIX-FMT-MM21: + + - ``V4L2_PIX_FMT_MM21`` + - 'MM21' + - Non-compressed, tiled two-planar format used by Mediatek MT8183. + This is an opaque intermediate format and the MDP3 hardware can be + used to convert it to other formats. .. raw:: latex diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index ec6fc1ef291e..d4f97ab1b237 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -1348,6 +1348,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt) case V4L2_PIX_FMT_TM6000: descr = "A/V + VBI Mux Packet"; break; case V4L2_PIX_FMT_CIT_YYVYUY: descr = "GSPCA CIT YYVYUY"; break; case V4L2_PIX_FMT_KONICA420: descr = "GSPCA KONICA420"; break; + case V4L2_PIX_FMT_MM21: descr = "Mediatek 8-bit Block Format"; break; case V4L2_PIX_FMT_HSV24: descr = "24-bit HSV 8-8-8"; break; case V4L2_PIX_FMT_HSV32: descr = "32-bit XHSV 8-8-8-8"; break; case V4L2_SDR_FMT_CU8: descr = "Complex U8"; break; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 58392dcd3bf5..5cc9545feb40 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -739,6 +739,7 @@ struct v4l2_pix_format { #define V4L2_PIX_FMT_Y12I v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */ #define V4L2_PIX_FMT_Z16 v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */ #define V4L2_PIX_FMT_MT21C v4l2_fourcc('M', 'T', '2', '1') /* Mediatek compressed block mode */ +#define V4L2_PIX_FMT_MM21 v4l2_fourcc('M', 'M', '2', '1') /* Mediatek 8-bit block mode, two non-contiguous planes */ #define V4L2_PIX_FMT_INZI v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */ #define V4L2_PIX_FMT_CNF4 v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */ #define V4L2_PIX_FMT_HI240 v4l2_fourcc('H', 'I', '2', '4') /* BTTV 8-bit dithered RGB */ -- cgit v1.2.3 From a9c80593ff80ddb7c6496624e5384e1ea3460a72 Mon Sep 17 00:00:00 2001 From: David Plowman Date: Mon, 16 Aug 2021 13:39:08 +0200 Subject: media: v4l2-ctrls: Add V4L2_CID_NOTIFY_GAINS control We add a new control V4L2_CID_NOTIFY_GAINS which allows the sensor to be notified what gains will be applied to the different colour channels by subsequent processing (such as by an ISP), even though the sensor will not apply any of these gains itself. For Bayer sensors this will be an array control taking 4 values which are the 4 gains arranged in the fixed order B, Gb, Gr and R, irrespective of the exact Bayer order of the sensor itself. The use of an array makes it straightforward to extend this control to non-Bayer sensors (for example, sensors with an RGBW pattern) in future. The units are in all cases linear with the default value indicating a gain of exactly 1.0. For example, if the default value were reported as 128 then the value 192 would represent a gain of exactly 1.5. Signed-off-by: David Plowman Reviewed-by: Laurent Pinchart Signed-off-by: Sakari Ailus Signed-off-by: Mauro Carvalho Chehab --- drivers/media/v4l2-core/v4l2-ctrls-defs.c | 1 + include/uapi/linux/v4l2-controls.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/media/v4l2-core/v4l2-ctrls-defs.c b/drivers/media/v4l2-core/v4l2-ctrls-defs.c index eae300c58274..ebe82b6ba6e6 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls-defs.c +++ b/drivers/media/v4l2-core/v4l2-ctrls-defs.c @@ -1108,6 +1108,7 @@ const char *v4l2_ctrl_get_name(u32 id) case V4L2_CID_TEST_PATTERN_GREENR: return "Green (Red) Pixel Value"; case V4L2_CID_TEST_PATTERN_BLUE: return "Blue Pixel Value"; case V4L2_CID_TEST_PATTERN_GREENB: return "Green (Blue) Pixel Value"; + case V4L2_CID_NOTIFY_GAINS: return "Notify Gains"; /* Image processing controls */ /* Keep the order of the 'case's the same as in v4l2-controls.h! */ diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 5532b5f68493..133e20444939 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -1118,6 +1118,7 @@ enum v4l2_jpeg_chroma_subsampling { #define V4L2_CID_TEST_PATTERN_BLUE (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 6) #define V4L2_CID_TEST_PATTERN_GREENB (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 7) #define V4L2_CID_UNIT_CELL_SIZE (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 8) +#define V4L2_CID_NOTIFY_GAINS (V4L2_CID_IMAGE_SOURCE_CLASS_BASE + 9) /* Image processing controls */ -- cgit v1.2.3 From 965c1e0bfeb66888fb000540c1fc4e8b55533d9c Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 9 Sep 2021 13:24:27 +0200 Subject: media: videobuf2: add V4L2_MEMORY_FLAG_NON_COHERENT flag By setting or clearing the V4L2_MEMORY_FLAG_NON_COHERENT flag user-space should be able to hint vb2 that either non-coherent (if supported) or coherent memory should be used for the buffer allocation. Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- Documentation/userspace-api/media/v4l/buffer.rst | 40 ++++++++++++++++++++-- .../userspace-api/media/v4l/vidioc-reqbufs.rst | 5 +-- include/uapi/linux/videodev2.h | 2 ++ 3 files changed, 43 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/buffer.rst b/Documentation/userspace-api/media/v4l/buffer.rst index e991ba73d873..4638ec64db00 100644 --- a/Documentation/userspace-api/media/v4l/buffer.rst +++ b/Documentation/userspace-api/media/v4l/buffer.rst @@ -676,8 +676,6 @@ Buffer Flags \normalsize -.. _memory-flags: - enum v4l2_memory ================ @@ -701,6 +699,44 @@ enum v4l2_memory - 4 - The buffer is used for :ref:`DMA shared buffer ` I/O. +.. _memory-flags: + +Memory Consistency Flags +------------------------ + +.. raw:: latex + + \small + +.. tabularcolumns:: |p{7.0cm}|p{2.1cm}|p{8.4cm}| + +.. cssclass:: longtable + +.. flat-table:: + :header-rows: 0 + :stub-columns: 0 + :widths: 3 1 4 + + * .. _`V4L2-MEMORY-FLAG-NON-COHERENT`: + + - ``V4L2_MEMORY_FLAG_NON_COHERENT`` + - 0x00000001 + - A buffer is allocated either in coherent (it will be automatically + coherent between the CPU and the bus) or non-coherent memory. The + latter can provide performance gains, for instance the CPU cache + sync/flush operations can be avoided if the buffer is accessed by the + corresponding device only and the CPU does not read/write to/from that + buffer. However, this requires extra care from the driver -- it must + guarantee memory consistency by issuing a cache flush/sync when + consistency is needed. If this flag is set V4L2 will attempt to + allocate the buffer in non-coherent memory. The flag takes effect + only if the buffer is used for :ref:`memory mapping ` I/O and the + queue reports the :ref:`V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS + ` capability. + +.. raw:: latex + + \normalsize Timecodes ========= diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index 50ea72043bb0..e59306aba2b0 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -158,8 +158,9 @@ aborting or finishing any DMA in progress, an implicit - This capability is set by the driver to indicate that the queue supports cache and memory management hints. However, it's only valid when the queue is used for :ref:`memory mapping ` streaming I/O. See - :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE ` and - :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN `. + :ref:`V4L2_BUF_FLAG_NO_CACHE_INVALIDATE `, + :ref:`V4L2_BUF_FLAG_NO_CACHE_CLEAN ` and + :ref:`V4L2_MEMORY_FLAG_NON_COHERENT `. .. raw:: latex diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 5cc9545feb40..9b7032abb2c7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -962,6 +962,8 @@ struct v4l2_requestbuffers { __u32 reserved[1]; }; +#define V4L2_MEMORY_FLAG_NON_COHERENT (1 << 0) + /* capabilities for struct v4l2_requestbuffers and v4l2_create_buffers */ #define V4L2_BUF_CAP_SUPPORTS_MMAP (1 << 0) #define V4L2_BUF_CAP_SUPPORTS_USERPTR (1 << 1) -- cgit v1.2.3 From c0acf9cfeee061f041fab778dbdcb34b6ca5e2e7 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 9 Sep 2021 13:24:29 +0200 Subject: media: videobuf2: handle V4L2_MEMORY_FLAG_NON_COHERENT flag This patch lets user-space request a non-coherent memory allocation during CREATE_BUFS and REQBUFS ioctl calls. = CREATE_BUFS struct v4l2_create_buffers has seven 4-byte reserved areas, so reserved[0] is renamed to ->flags. The struct, thus, now has six reserved 4-byte regions. = CREATE_BUFS32 struct v4l2_create_buffers32 has seven 4-byte reserved areas, so reserved[0] is renamed to ->flags. The struct, thus, now has six reserved 4-byte regions. = REQBUFS We use one byte of a 4 byte ->reserved[1] member of struct v4l2_requestbuffers. The struct, thus, now has reserved 3 bytes. Signed-off-by: Sergey Senozhatsky Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- .../userspace-api/media/v4l/vidioc-create-bufs.rst | 7 ++++- .../userspace-api/media/v4l/vidioc-reqbufs.rst | 11 +++++--- drivers/media/common/videobuf2/videobuf2-core.c | 4 +-- drivers/media/common/videobuf2/videobuf2-v4l2.c | 31 +++++++++++++++++++--- drivers/media/v4l2-core/v4l2-compat-ioctl32.c | 9 ++++++- drivers/media/v4l2-core/v4l2-ioctl.c | 4 +-- include/uapi/linux/videodev2.h | 9 +++++-- 7 files changed, 60 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst index f98f18c9e91c..a048a9f6b7b6 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-create-bufs.rst @@ -113,7 +113,12 @@ than the number requested. ``V4L2_MEMORY_MMAP`` and ``format.type`` to the buffer type. * - __u32 - - ``reserved``\ [7] + - ``flags`` + - Specifies additional buffer management attributes. + See :ref:`memory-flags`. + + * - __u32 + - ``reserved``\ [6] - A place holder for future extensions. Drivers and applications must set the array to zero. diff --git a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst index e59306aba2b0..099fa6695167 100644 --- a/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst +++ b/Documentation/userspace-api/media/v4l/vidioc-reqbufs.rst @@ -104,10 +104,13 @@ aborting or finishing any DMA in progress, an implicit ``V4L2_MEMORY_MMAP`` and ``type`` set to the buffer type. This will free any previously allocated buffers, so this is typically something that will be done at the start of the application. - * - __u32 - - ``reserved``\ [1] - - A place holder for future extensions. Drivers and applications - must set the array to zero. + * - __u8 + - ``flags`` + - Specifies additional buffer management attributes. + See :ref:`memory-flags`. + * - __u8 + - ``reserved``\ [3] + - Reserved for future extensions. .. _v4l2-buf-capabilities: .. _V4L2-BUF-CAP-SUPPORTS-MMAP: diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 60fb43b8f134..2266bbd239ab 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -761,7 +761,7 @@ int vb2_core_reqbufs(struct vb2_queue *q, enum vb2_memory memory, { unsigned int num_buffers, allocated_buffers, num_planes = 0; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool non_coherent_mem = false; + bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; unsigned int i; int ret; @@ -905,7 +905,7 @@ int vb2_core_create_bufs(struct vb2_queue *q, enum vb2_memory memory, { unsigned int num_planes = 0, num_buffers, allocated_buffers; unsigned plane_sizes[VB2_MAX_PLANES] = { }; - bool non_coherent_mem = false; + bool non_coherent_mem = flags & V4L2_MEMORY_FLAG_NON_COHERENT; int ret; if (q->num_buffers == VB2_MAX_FRAME) { diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index b4f70ddb09b0..6edf4508c636 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -692,12 +692,32 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps) #endif } +static void validate_memory_flags(struct vb2_queue *q, + int memory, + u32 *flags) +{ + if (!q->allow_cache_hints || memory != V4L2_MEMORY_MMAP) { + /* + * This needs to clear V4L2_MEMORY_FLAG_NON_COHERENT only, + * but in order to avoid bugs we zero out all bits. + */ + *flags = 0; + } else { + /* Clear all unknown flags. */ + *flags &= V4L2_MEMORY_FLAG_NON_COHERENT; + } +} + int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) { int ret = vb2_verify_memory_type(q, req->memory, req->type); + u32 flags = req->flags; fill_buf_caps(q, &req->capabilities); - return ret ? ret : vb2_core_reqbufs(q, req->memory, 0, &req->count); + validate_memory_flags(q, req->memory, &flags); + req->flags = flags; + return ret ? ret : vb2_core_reqbufs(q, req->memory, + req->flags, &req->count); } EXPORT_SYMBOL_GPL(vb2_reqbufs); @@ -729,6 +749,7 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) unsigned i; fill_buf_caps(q, &create->capabilities); + validate_memory_flags(q, create->memory, &create->flags); create->index = q->num_buffers; if (create->count == 0) return ret != -EBUSY ? ret : 0; @@ -772,7 +793,7 @@ int vb2_create_bufs(struct vb2_queue *q, struct v4l2_create_buffers *create) if (requested_sizes[i] == 0) return -EINVAL; return ret ? ret : vb2_core_create_bufs(q, create->memory, - 0, + create->flags, &create->count, requested_planes, requested_sizes); @@ -969,13 +990,16 @@ int vb2_ioctl_reqbufs(struct file *file, void *priv, { struct video_device *vdev = video_devdata(file); int res = vb2_verify_memory_type(vdev->queue, p->memory, p->type); + u32 flags = p->flags; fill_buf_caps(vdev->queue, &p->capabilities); + validate_memory_flags(vdev->queue, p->memory, &flags); + p->flags = flags; if (res) return res; if (vb2_queue_is_busy(vdev, file)) return -EBUSY; - res = vb2_core_reqbufs(vdev->queue, p->memory, 0, &p->count); + res = vb2_core_reqbufs(vdev->queue, p->memory, p->flags, &p->count); /* If count == 0, then the owner has released all buffers and he is no longer owner of the queue. Otherwise we have a new owner. */ if (res == 0) @@ -993,6 +1017,7 @@ int vb2_ioctl_create_bufs(struct file *file, void *priv, p->index = vdev->queue->num_buffers; fill_buf_caps(vdev->queue, &p->capabilities); + validate_memory_flags(vdev->queue, p->memory, &p->flags); /* * If count == 0, then just check if memory and type are valid. * Any -EBUSY result from vb2_verify_memory_type can be mapped to 0. diff --git a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c index 47aff3b19742..8176769a89fa 100644 --- a/drivers/media/v4l2-core/v4l2-compat-ioctl32.c +++ b/drivers/media/v4l2-core/v4l2-compat-ioctl32.c @@ -126,6 +126,9 @@ struct v4l2_format32 { * @memory: buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. + * @flags: additional buffer management attributes (ignored unless the + * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability and + * configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers32 { @@ -134,7 +137,8 @@ struct v4l2_create_buffers32 { __u32 memory; /* enum v4l2_memory */ struct v4l2_format32 format; __u32 capabilities; - __u32 reserved[7]; + __u32 flags; + __u32 reserved[6]; }; static int get_v4l2_format32(struct v4l2_format *p64, @@ -182,6 +186,8 @@ static int get_v4l2_create32(struct v4l2_create_buffers *p64, if (copy_from_user(p64, p32, offsetof(struct v4l2_create_buffers32, format))) return -EFAULT; + if (copy_from_user(&p64->flags, &p32->flags, sizeof(p32->flags))) + return -EFAULT; return get_v4l2_format32(&p64->format, &p32->format); } @@ -227,6 +233,7 @@ static int put_v4l2_create32(struct v4l2_create_buffers *p64, if (copy_to_user(p32, p64, offsetof(struct v4l2_create_buffers32, format)) || put_user(p64->capabilities, &p32->capabilities) || + put_user(p64->flags, &p32->flags) || copy_to_user(p32->reserved, p64->reserved, sizeof(p64->reserved))) return -EFAULT; return put_v4l2_format32(&p64->format, &p32->format); diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c index bc83d23ce25d..31d0109ce5a8 100644 --- a/drivers/media/v4l2-core/v4l2-ioctl.c +++ b/drivers/media/v4l2-core/v4l2-ioctl.c @@ -2024,7 +2024,7 @@ static int v4l_reqbufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; - CLEAR_AFTER_FIELD(p, capabilities); + CLEAR_AFTER_FIELD(p, flags); return ops->vidioc_reqbufs(file, fh, p); } @@ -2065,7 +2065,7 @@ static int v4l_create_bufs(const struct v4l2_ioctl_ops *ops, if (ret) return ret; - CLEAR_AFTER_FIELD(create, capabilities); + CLEAR_AFTER_FIELD(create, flags); v4l_sanitize_format(&create->format); diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index 9b7032abb2c7..f118fe7a9f58 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -959,7 +959,8 @@ struct v4l2_requestbuffers { __u32 type; /* enum v4l2_buf_type */ __u32 memory; /* enum v4l2_memory */ __u32 capabilities; - __u32 reserved[1]; + __u8 flags; + __u8 reserved[3]; }; #define V4L2_MEMORY_FLAG_NON_COHERENT (1 << 0) @@ -2507,6 +2508,9 @@ struct v4l2_dbg_chip_info { * @memory: enum v4l2_memory; buffer memory type * @format: frame format, for which buffers are requested * @capabilities: capabilities of this buffer type. + * @flags: additional buffer management attributes (ignored unless the + * queue has V4L2_BUF_CAP_SUPPORTS_MMAP_CACHE_HINTS capability + * and configured for MMAP streaming I/O). * @reserved: future extensions */ struct v4l2_create_buffers { @@ -2515,7 +2519,8 @@ struct v4l2_create_buffers { __u32 memory; struct v4l2_format format; __u32 capabilities; - __u32 reserved[7]; + __u32 flags; + __u32 reserved[6]; }; /* -- cgit v1.2.3 From a70e3f024d5f4ec7edb17ab5d927eb55397f1d15 Mon Sep 17 00:00:00 2001 From: Jacob Keller Date: Thu, 30 Sep 2021 14:21:04 -0700 Subject: devlink: report maximum number of snapshots with regions Each region has an independently configurable number of maximum snapshots. This information is not reported to userspace, making it not very discoverable. Fix this by adding a new DEVLINK_ATTR_REGION_MAX_SNAPSHOST attribute which is used to report this maximum. Ex: $devlink region pci/0000:af:00.0/nvm-flash: size 10485760 snapshot [] max 1 pci/0000:af:00.0/device-caps: size 4096 snapshot [] max 10 pci/0000:af:00.1/nvm-flash: size 10485760 snapshot [] max 1 pci/0000:af:00.1/device-caps: size 4096 snapshot [] max 10 This information enables users to understand why a new region command may fail due to having too many existing snapshots. Reported-by: Gurucharan G (A Contingent worker at Intel) Signed-off-by: Jacob Keller Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-region.rst | 4 ++-- Documentation/networking/devlink/ice.rst | 4 ++++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 5 +++++ 4 files changed, 13 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/devlink/devlink-region.rst b/Documentation/networking/devlink/devlink-region.rst index 58fe95e9a49d..f06dca9a1eb6 100644 --- a/Documentation/networking/devlink/devlink-region.rst +++ b/Documentation/networking/devlink/devlink-region.rst @@ -44,8 +44,8 @@ example usage # Show all of the exposed regions with region sizes: $ devlink region show - pci/0000:00:05.0/cr-space: size 1048576 snapshot [1 2] - pci/0000:00:05.0/fw-health: size 64 snapshot [1 2] + pci/0000:00:05.0/cr-space: size 1048576 snapshot [1 2] max 8 + pci/0000:00:05.0/fw-health: size 64 snapshot [1 2] max 8 # Delete a snapshot using: $ devlink region del pci/0000:00:05.0/cr-space snapshot 1 diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst index a432dc419fa4..32aea1f7d7f7 100644 --- a/Documentation/networking/devlink/ice.rst +++ b/Documentation/networking/devlink/ice.rst @@ -141,6 +141,10 @@ Users can request an immediate capture of a snapshot via the .. code:: shell + $ devlink region show + pci/0000:01:00.0/nvm-flash: size 10485760 snapshot [] max 1 + pci/0000:01:00.0/device-caps: size 4096 snapshot [] max 10 + $ devlink region new pci/0000:01:00.0/nvm-flash snapshot 1 $ devlink region dump pci/0000:01:00.0/nvm-flash snapshot 1 diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 32f53a0069d6..b897b80770f6 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -551,6 +551,8 @@ enum devlink_attr { DEVLINK_ATTR_RATE_NODE_NAME, /* string */ DEVLINK_ATTR_RATE_PARENT_NODE_NAME, /* string */ + DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, /* 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 b64303085d0e..4917112406a0 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -5078,6 +5078,11 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, + region->max_snapshots); + if (err) + goto nla_put_failure; + err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; -- cgit v1.2.3 From ef5825e3cf0d0af657f5fb4dd86d750ed42fee0a Mon Sep 17 00:00:00 2001 From: NeilBrown Date: Thu, 2 Sep 2021 11:14:47 +1000 Subject: NFSD: move filehandle format declarations out of "uapi". A small part of the declaration concerning filehandle format are currently in the "uapi" include directory: include/uapi/linux/nfsd/nfsfh.h There is a lot more to the filehandle format, including "enum fid_type" and "enum nfsd_fsid" which are not exported via "uapi". This small part of the filehandle definition is of minimal use outside of the kernel, and I can find no evidence that an other code is using it. Certainly nfs-utils and wireshark (The most likely candidates) do not use these declarations. So move it out of "uapi" by copying the content from include/uapi/linux/nfsd/nfsfh.h into fs/nfsd/nfsfh.h A few unnecessary "#include" directives are not copied, and neither is the #define of fh_auth, which is annotated as being for userspace only. The copyright claims in the uapi file are identical to those in the nfsd file, so there is no need to copy those. The "__u32" style integer types are only needed in "uapi". In kernel-only code we can use the more familiar "u32" style. Signed-off-by: NeilBrown Signed-off-by: J. Bruce Fields --- fs/nfsd/nfsfh.h | 97 ++++++++++++++++++++++++++++++++- fs/nfsd/vfs.c | 1 + include/uapi/linux/nfsd/nfsfh.h | 115 ---------------------------------------- 3 files changed, 97 insertions(+), 116 deletions(-) delete mode 100644 include/uapi/linux/nfsd/nfsfh.h (limited to 'include/uapi/linux') diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 6106697adc04..ad47f16676a8 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -10,9 +10,104 @@ #include #include -#include #include #include +#include + + +/* + * This is the old "dentry style" Linux NFSv2 file handle. + * + * The xino and xdev fields are currently used to transport the + * ino/dev of the exported inode. + */ +struct nfs_fhbase_old { + u32 fb_dcookie; /* dentry cookie - always 0xfeebbaca */ + u32 fb_ino; /* our inode number */ + u32 fb_dirino; /* dir inode number, 0 for directories */ + u32 fb_dev; /* our device */ + u32 fb_xdev; + u32 fb_xino; + u32 fb_generation; +}; + +/* + * This is the new flexible, extensible style NFSv2/v3/v4 file handle. + * + * The file handle starts with a sequence of four-byte words. + * The first word contains a version number (1) and three descriptor bytes + * that tell how the remaining 3 variable length fields should be handled. + * These three bytes are auth_type, fsid_type and fileid_type. + * + * All four-byte values are in host-byte-order. + * + * The auth_type field is deprecated and must be set to 0. + * + * The fsid_type identifies how the filesystem (or export point) is + * encoded. + * Current values: + * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number + * NOTE: we cannot use the kdev_t device id value, because kdev_t.h + * says we mustn't. We must break it up and reassemble. + * 1 - 4 byte user specified identifier + * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED + * 3 - 4 byte device id, encoded for user-space, 4 byte inode number + * 4 - 4 byte inode number and 4 byte uuid + * 5 - 8 byte uuid + * 6 - 16 byte uuid + * 7 - 8 byte inode number and 16 byte uuid + * + * The fileid_type identified how the file within the filesystem is encoded. + * The values for this field are filesystem specific, exccept that + * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' + * in include/linux/exportfs.h for currently registered values. + */ +struct nfs_fhbase_new { + union { + struct { + u8 fb_version_aux; /* == 1, even => nfs_fhbase_old */ + u8 fb_auth_type_aux; + u8 fb_fsid_type_aux; + u8 fb_fileid_type_aux; + u32 fb_auth[1]; + /* u32 fb_fsid[0]; floating */ + /* u32 fb_fileid[0]; floating */ + }; + struct { + u8 fb_version; /* == 1, even => nfs_fhbase_old */ + u8 fb_auth_type; + u8 fb_fsid_type; + u8 fb_fileid_type; + u32 fb_auth_flex[]; /* flexible-array member */ + }; + }; +}; + +struct knfsd_fh { + unsigned int fh_size; /* significant for NFSv3. + * Points to the current size while building + * a new file handle + */ + union { + struct nfs_fhbase_old fh_old; + u32 fh_pad[NFS4_FHSIZE/4]; + struct nfs_fhbase_new fh_new; + } fh_base; +}; + +#define ofh_dcookie fh_base.fh_old.fb_dcookie +#define ofh_ino fh_base.fh_old.fb_ino +#define ofh_dirino fh_base.fh_old.fb_dirino +#define ofh_dev fh_base.fh_old.fb_dev +#define ofh_xdev fh_base.fh_old.fb_xdev +#define ofh_xino fh_base.fh_old.fb_xino +#define ofh_generation fh_base.fh_old.fb_generation + +#define fh_version fh_base.fh_new.fb_version +#define fh_fsid_type fh_base.fh_new.fb_fsid_type +#define fh_auth_type fh_base.fh_new.fb_auth_type +#define fh_fileid_type fh_base.fh_new.fb_fileid_type +#define fh_fsid fh_base.fh_new.fb_auth_flex static inline __u32 ino_t_to_u32(ino_t ino) { diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 738d564ca4ce..e9c406fd05b6 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -244,6 +244,7 @@ out_nfserr: * returned. Otherwise the covered directory is returned. * NOTE: this mountpoint crossing is not supported properly by all * clients and is explicitly disallowed for NFSv3 + * NeilBrown */ __be32 nfsd_lookup(struct svc_rqst *rqstp, struct svc_fh *fhp, const char *name, diff --git a/include/uapi/linux/nfsd/nfsfh.h b/include/uapi/linux/nfsd/nfsfh.h deleted file mode 100644 index e29e8accc4f4..000000000000 --- a/include/uapi/linux/nfsd/nfsfh.h +++ /dev/null @@ -1,115 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -/* - * This file describes the layout of the file handles as passed - * over the wire. - * - * Copyright (C) 1995, 1996, 1997 Olaf Kirch - */ - -#ifndef _UAPI_LINUX_NFSD_FH_H -#define _UAPI_LINUX_NFSD_FH_H - -#include -#include -#include -#include -#include - -/* - * This is the old "dentry style" Linux NFSv2 file handle. - * - * The xino and xdev fields are currently used to transport the - * ino/dev of the exported inode. - */ -struct nfs_fhbase_old { - __u32 fb_dcookie; /* dentry cookie - always 0xfeebbaca */ - __u32 fb_ino; /* our inode number */ - __u32 fb_dirino; /* dir inode number, 0 for directories */ - __u32 fb_dev; /* our device */ - __u32 fb_xdev; - __u32 fb_xino; - __u32 fb_generation; -}; - -/* - * This is the new flexible, extensible style NFSv2/v3/v4 file handle. - * - * The file handle starts with a sequence of four-byte words. - * The first word contains a version number (1) and three descriptor bytes - * that tell how the remaining 3 variable length fields should be handled. - * These three bytes are auth_type, fsid_type and fileid_type. - * - * All four-byte values are in host-byte-order. - * - * The auth_type field is deprecated and must be set to 0. - * - * The fsid_type identifies how the filesystem (or export point) is - * encoded. - * Current values: - * 0 - 4 byte device id (ms-2-bytes major, ls-2-bytes minor), 4byte inode number - * NOTE: we cannot use the kdev_t device id value, because kdev_t.h - * says we mustn't. We must break it up and reassemble. - * 1 - 4 byte user specified identifier - * 2 - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED - * 3 - 4 byte device id, encoded for user-space, 4 byte inode number - * 4 - 4 byte inode number and 4 byte uuid - * 5 - 8 byte uuid - * 6 - 16 byte uuid - * 7 - 8 byte inode number and 16 byte uuid - * - * The fileid_type identified how the file within the filesystem is encoded. - * The values for this field are filesystem specific, exccept that - * filesystems must not use the values '0' or '0xff'. 'See enum fid_type' - * in include/linux/exportfs.h for currently registered values. - */ -struct nfs_fhbase_new { - union { - struct { - __u8 fb_version_aux; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type_aux; - __u8 fb_fsid_type_aux; - __u8 fb_fileid_type_aux; - __u32 fb_auth[1]; - /* __u32 fb_fsid[0]; floating */ - /* __u32 fb_fileid[0]; floating */ - }; - struct { - __u8 fb_version; /* == 1, even => nfs_fhbase_old */ - __u8 fb_auth_type; - __u8 fb_fsid_type; - __u8 fb_fileid_type; - __u32 fb_auth_flex[]; /* flexible-array member */ - }; - }; -}; - -struct knfsd_fh { - unsigned int fh_size; /* significant for NFSv3. - * Points to the current size while building - * a new file handle - */ - union { - struct nfs_fhbase_old fh_old; - __u32 fh_pad[NFS4_FHSIZE/4]; - struct nfs_fhbase_new fh_new; - } fh_base; -}; - -#define ofh_dcookie fh_base.fh_old.fb_dcookie -#define ofh_ino fh_base.fh_old.fb_ino -#define ofh_dirino fh_base.fh_old.fb_dirino -#define ofh_dev fh_base.fh_old.fb_dev -#define ofh_xdev fh_base.fh_old.fb_xdev -#define ofh_xino fh_base.fh_old.fb_xino -#define ofh_generation fh_base.fh_old.fb_generation - -#define fh_version fh_base.fh_new.fb_version -#define fh_fsid_type fh_base.fh_new.fb_fsid_type -#define fh_auth_type fh_base.fh_new.fb_auth_type -#define fh_fileid_type fh_base.fh_new.fb_fileid_type -#define fh_fsid fh_base.fh_new.fb_auth_flex - -/* Do not use, provided for userspace compatiblity. */ -#define fh_auth fh_base.fh_new.fb_auth - -#endif /* _UAPI_LINUX_NFSD_FH_H */ -- cgit v1.2.3 From dea8ee31a039277576c215fffa13957970246366 Mon Sep 17 00:00:00 2001 From: Atish Patra Date: Mon, 27 Sep 2021 17:10:14 +0530 Subject: RISC-V: KVM: Add SBI v0.1 support The KVM host kernel is running in HS-mode needs so we need to handle the SBI calls coming from guest kernel running in VS-mode. This patch adds SBI v0.1 support in KVM RISC-V. Almost all SBI v0.1 calls are implemented in KVM kernel module except GETCHAR and PUTCHART calls which are forwarded to user space because these calls cannot be implemented in kernel space. In future, when we implement SBI v0.2 for Guest, we will forward SBI v0.2 experimental and vendor extension calls to user space. Signed-off-by: Atish Patra Signed-off-by: Anup Patel Acked-by: Paolo Bonzini Reviewed-by: Paolo Bonzini Acked-by: Palmer Dabbelt --- arch/riscv/include/asm/kvm_host.h | 10 +++ arch/riscv/kvm/Makefile | 1 + arch/riscv/kvm/vcpu.c | 9 ++ arch/riscv/kvm/vcpu_exit.c | 4 + arch/riscv/kvm/vcpu_sbi.c | 185 ++++++++++++++++++++++++++++++++++++++ include/uapi/linux/kvm.h | 8 ++ 6 files changed, 217 insertions(+) create mode 100644 arch/riscv/kvm/vcpu_sbi.c (limited to 'include/uapi/linux') diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h index be159686da46..d7e1696cd2ec 100644 --- a/arch/riscv/include/asm/kvm_host.h +++ b/arch/riscv/include/asm/kvm_host.h @@ -74,6 +74,10 @@ struct kvm_mmio_decode { int return_handled; }; +struct kvm_sbi_context { + int return_handled; +}; + #define KVM_MMU_PAGE_CACHE_NR_OBJS 32 struct kvm_mmu_page_cache { @@ -186,6 +190,9 @@ struct kvm_vcpu_arch { /* MMIO instruction details */ struct kvm_mmio_decode mmio_decode; + /* SBI context */ + struct kvm_sbi_context sbi_context; + /* Cache pages needed to program page tables with spinlock held */ struct kvm_mmu_page_cache mmu_page_cache; @@ -253,4 +260,7 @@ bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask); void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu); void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu); +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run); +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run); + #endif /* __RISCV_KVM_HOST_H__ */ diff --git a/arch/riscv/kvm/Makefile b/arch/riscv/kvm/Makefile index 4beb4e277e96..3226696b8340 100644 --- a/arch/riscv/kvm/Makefile +++ b/arch/riscv/kvm/Makefile @@ -21,4 +21,5 @@ kvm-y += mmu.o kvm-y += vcpu.o kvm-y += vcpu_exit.o kvm-y += vcpu_switch.o +kvm-y += vcpu_sbi.o kvm-y += vcpu_timer.o diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c index 5acec47236c9..c44cabce7dd8 100644 --- a/arch/riscv/kvm/vcpu.c +++ b/arch/riscv/kvm/vcpu.c @@ -867,6 +867,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) } } + /* Process SBI value returned from user-space */ + if (run->exit_reason == KVM_EXIT_RISCV_SBI) { + ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run); + if (ret) { + srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); + return ret; + } + } + if (run->immediate_exit) { srcu_read_unlock(&vcpu->kvm->srcu, vcpu->arch.srcu_idx); return -EINTR; diff --git a/arch/riscv/kvm/vcpu_exit.c b/arch/riscv/kvm/vcpu_exit.c index f659be94231d..13bbc3f73713 100644 --- a/arch/riscv/kvm/vcpu_exit.c +++ b/arch/riscv/kvm/vcpu_exit.c @@ -678,6 +678,10 @@ int kvm_riscv_vcpu_exit(struct kvm_vcpu *vcpu, struct kvm_run *run, if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) ret = stage2_page_fault(vcpu, run, trap); break; + case EXC_SUPERVISOR_SYSCALL: + if (vcpu->arch.guest_context.hstatus & HSTATUS_SPV) + ret = kvm_riscv_vcpu_sbi_ecall(vcpu, run); + break; default: break; }; diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c new file mode 100644 index 000000000000..ebdcdbade9c6 --- /dev/null +++ b/arch/riscv/kvm/vcpu_sbi.c @@ -0,0 +1,185 @@ +// SPDX-License-Identifier: GPL-2.0 +/** + * Copyright (c) 2019 Western Digital Corporation or its affiliates. + * + * Authors: + * Atish Patra + */ + +#include +#include +#include +#include +#include +#include + +#define SBI_VERSION_MAJOR 0 +#define SBI_VERSION_MINOR 1 + +static void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, + struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + vcpu->arch.sbi_context.return_handled = 0; + vcpu->stat.ecall_exit_stat++; + run->exit_reason = KVM_EXIT_RISCV_SBI; + run->riscv_sbi.extension_id = cp->a7; + run->riscv_sbi.function_id = cp->a6; + run->riscv_sbi.args[0] = cp->a0; + run->riscv_sbi.args[1] = cp->a1; + run->riscv_sbi.args[2] = cp->a2; + run->riscv_sbi.args[3] = cp->a3; + run->riscv_sbi.args[4] = cp->a4; + run->riscv_sbi.args[5] = cp->a5; + run->riscv_sbi.ret[0] = cp->a0; + run->riscv_sbi.ret[1] = cp->a1; +} + +int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + /* Handle SBI return only once */ + if (vcpu->arch.sbi_context.return_handled) + return 0; + vcpu->arch.sbi_context.return_handled = 1; + + /* Update return values */ + cp->a0 = run->riscv_sbi.ret[0]; + cp->a1 = run->riscv_sbi.ret[1]; + + /* Move to next instruction */ + vcpu->arch.guest_context.sepc += 4; + + return 0; +} + +#ifdef CONFIG_RISCV_SBI_V01 + +static void kvm_sbi_system_shutdown(struct kvm_vcpu *vcpu, + struct kvm_run *run, u32 type) +{ + int i; + struct kvm_vcpu *tmp; + + kvm_for_each_vcpu(i, tmp, vcpu->kvm) + tmp->arch.power_off = true; + kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP); + + memset(&run->system_event, 0, sizeof(run->system_event)); + run->system_event.type = type; + run->exit_reason = KVM_EXIT_SYSTEM_EVENT; +} + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + ulong hmask; + int i, ret = 1; + u64 next_cycle; + struct kvm_vcpu *rvcpu; + bool next_sepc = true; + struct cpumask cm, hm; + struct kvm *kvm = vcpu->kvm; + struct kvm_cpu_trap utrap = { 0 }; + struct kvm_cpu_context *cp = &vcpu->arch.guest_context; + + if (!cp) + return -EINVAL; + + switch (cp->a7) { + case SBI_EXT_0_1_CONSOLE_GETCHAR: + case SBI_EXT_0_1_CONSOLE_PUTCHAR: + /* + * The CONSOLE_GETCHAR/CONSOLE_PUTCHAR SBI calls cannot be + * handled in kernel so we forward these to user-space + */ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + next_sepc = false; + ret = 0; + break; + case SBI_EXT_0_1_SET_TIMER: +#if __riscv_xlen == 32 + next_cycle = ((u64)cp->a1 << 32) | (u64)cp->a0; +#else + next_cycle = (u64)cp->a0; +#endif + kvm_riscv_vcpu_timer_next_event(vcpu, next_cycle); + break; + case SBI_EXT_0_1_CLEAR_IPI: + kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_SOFT); + break; + case SBI_EXT_0_1_SEND_IPI: + if (cp->a0) + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, + &utrap); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap.scause) { + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + break; + } + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + kvm_riscv_vcpu_set_interrupt(rvcpu, IRQ_VS_SOFT); + } + break; + case SBI_EXT_0_1_SHUTDOWN: + kvm_sbi_system_shutdown(vcpu, run, KVM_SYSTEM_EVENT_SHUTDOWN); + next_sepc = false; + ret = 0; + break; + case SBI_EXT_0_1_REMOTE_FENCE_I: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA: + case SBI_EXT_0_1_REMOTE_SFENCE_VMA_ASID: + if (cp->a0) + hmask = kvm_riscv_vcpu_unpriv_read(vcpu, false, cp->a0, + &utrap); + else + hmask = (1UL << atomic_read(&kvm->online_vcpus)) - 1; + if (utrap.scause) { + utrap.sepc = cp->sepc; + kvm_riscv_vcpu_trap_redirect(vcpu, &utrap); + next_sepc = false; + break; + } + cpumask_clear(&cm); + for_each_set_bit(i, &hmask, BITS_PER_LONG) { + rvcpu = kvm_get_vcpu_by_id(vcpu->kvm, i); + if (rvcpu->cpu < 0) + continue; + cpumask_set_cpu(rvcpu->cpu, &cm); + } + riscv_cpuid_to_hartid_mask(&cm, &hm); + if (cp->a7 == SBI_EXT_0_1_REMOTE_FENCE_I) + sbi_remote_fence_i(cpumask_bits(&hm)); + else if (cp->a7 == SBI_EXT_0_1_REMOTE_SFENCE_VMA) + sbi_remote_hfence_vvma(cpumask_bits(&hm), + cp->a1, cp->a2); + else + sbi_remote_hfence_vvma_asid(cpumask_bits(&hm), + cp->a1, cp->a2, cp->a3); + break; + default: + /* Return error for unsupported SBI calls */ + cp->a0 = SBI_ERR_NOT_SUPPORTED; + break; + }; + + if (next_sepc) + cp->sepc += 4; + + return ret; +} + +#else + +int kvm_riscv_vcpu_sbi_ecall(struct kvm_vcpu *vcpu, struct kvm_run *run) +{ + kvm_riscv_vcpu_sbi_forward(vcpu, run); + return 0; +} + +#endif diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index a067410ebea5..322b4b588d75 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -269,6 +269,7 @@ struct kvm_xen_exit { #define KVM_EXIT_AP_RESET_HOLD 32 #define KVM_EXIT_X86_BUS_LOCK 33 #define KVM_EXIT_XEN 34 +#define KVM_EXIT_RISCV_SBI 35 /* For KVM_EXIT_INTERNAL_ERROR */ /* Emulate instruction failed. */ @@ -469,6 +470,13 @@ struct kvm_run { } msr; /* KVM_EXIT_XEN */ struct kvm_xen_exit xen; + /* KVM_EXIT_RISCV_SBI */ + struct { + unsigned long extension_id; + unsigned long function_id; + unsigned long args[6]; + unsigned long ret[2]; + } riscv_sbi; /* Fix the size of the union. */ char padding[256]; }; -- cgit v1.2.3 From 8cb3bf8bff3c47e171f6b66f9ccfc3f1451a11a2 Mon Sep 17 00:00:00 2001 From: Justin Iurman Date: Sun, 3 Oct 2021 20:45:38 +0200 Subject: ipv6: ioam: Add support for the ip6ip6 encapsulation This patch adds support for the ip6ip6 encapsulation by providing three encap modes: inline, encap and auto. Signed-off-by: Justin Iurman Signed-off-by: David S. Miller --- include/uapi/linux/ioam6_iptunnel.h | 29 ++++ net/ipv6/Kconfig | 6 +- net/ipv6/ioam6_iptunnel.c | 261 +++++++++++++++++++++++++++++------- 3 files changed, 242 insertions(+), 54 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ioam6_iptunnel.h b/include/uapi/linux/ioam6_iptunnel.h index bae14636a8c8..829ffdfcacca 100644 --- a/include/uapi/linux/ioam6_iptunnel.h +++ b/include/uapi/linux/ioam6_iptunnel.h @@ -9,9 +9,38 @@ #ifndef _UAPI_LINUX_IOAM6_IPTUNNEL_H #define _UAPI_LINUX_IOAM6_IPTUNNEL_H +/* Encap modes: + * - inline: direct insertion + * - encap: ip6ip6 encapsulation + * - auto: inline for local packets, encap for in-transit packets + */ +enum { + __IOAM6_IPTUNNEL_MODE_MIN, + + IOAM6_IPTUNNEL_MODE_INLINE, + IOAM6_IPTUNNEL_MODE_ENCAP, + IOAM6_IPTUNNEL_MODE_AUTO, + + __IOAM6_IPTUNNEL_MODE_MAX, +}; + +#define IOAM6_IPTUNNEL_MODE_MIN (__IOAM6_IPTUNNEL_MODE_MIN + 1) +#define IOAM6_IPTUNNEL_MODE_MAX (__IOAM6_IPTUNNEL_MODE_MAX - 1) + enum { IOAM6_IPTUNNEL_UNSPEC, + + /* Encap mode */ + IOAM6_IPTUNNEL_MODE, /* u8 */ + + /* Tunnel dst address. + * For encap,auto modes. + */ + IOAM6_IPTUNNEL_DST, /* struct in6_addr */ + + /* IOAM Trace Header */ IOAM6_IPTUNNEL_TRACE, /* struct ioam6_trace_hdr */ + __IOAM6_IPTUNNEL_MAX, }; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index e504204bca92..bf2e5e5fe142 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -332,10 +332,10 @@ config IPV6_IOAM6_LWTUNNEL bool "IPv6: IOAM Pre-allocated Trace insertion support" depends on IPV6 select LWTUNNEL + select DST_CACHE help - Support for the inline insertion of IOAM Pre-allocated - Trace Header (only on locally generated packets), using - the lightweight tunnels mechanism. + Support for the insertion of IOAM Pre-allocated Trace + Header using the lightweight tunnels mechanism. If unsure, say N. diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c index 5d03101724b9..392c183076ce 100644 --- a/net/ipv6/ioam6_iptunnel.c +++ b/net/ipv6/ioam6_iptunnel.c @@ -17,6 +17,10 @@ #include #include #include +#include +#include +#include +#include #define IOAM6_MASK_SHORT_FIELDS 0xff100000 #define IOAM6_MASK_WIDE_FIELDS 0xe00000 @@ -29,6 +33,9 @@ struct ioam6_lwt_encap { } __packed; struct ioam6_lwt { + struct dst_cache cache; + u8 mode; + struct in6_addr tundst; struct ioam6_lwt_encap tuninfo; }; @@ -48,6 +55,10 @@ static struct ioam6_trace_hdr *ioam6_lwt_trace(struct lwtunnel_state *lwt) } static const struct nla_policy ioam6_iptunnel_policy[IOAM6_IPTUNNEL_MAX + 1] = { + [IOAM6_IPTUNNEL_MODE] = NLA_POLICY_RANGE(NLA_U8, + IOAM6_IPTUNNEL_MODE_MIN, + IOAM6_IPTUNNEL_MODE_MAX), + [IOAM6_IPTUNNEL_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)), [IOAM6_IPTUNNEL_TRACE] = NLA_POLICY_EXACT_LEN(sizeof(struct ioam6_trace_hdr)), }; @@ -78,9 +89,10 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, struct nlattr *tb[IOAM6_IPTUNNEL_MAX + 1]; struct ioam6_lwt_encap *tuninfo; struct ioam6_trace_hdr *trace; - struct lwtunnel_state *s; - int len_aligned; - int len, err; + struct lwtunnel_state *lwt; + struct ioam6_lwt *ilwt; + int len_aligned, err; + u8 mode; if (family != AF_INET6) return -EINVAL; @@ -90,6 +102,16 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, if (err < 0) return err; + if (!tb[IOAM6_IPTUNNEL_MODE]) + mode = IOAM6_IPTUNNEL_MODE_INLINE; + else + mode = nla_get_u8(tb[IOAM6_IPTUNNEL_MODE]); + + if (!tb[IOAM6_IPTUNNEL_DST] && mode != IOAM6_IPTUNNEL_MODE_INLINE) { + NL_SET_ERR_MSG(extack, "this mode needs a tunnel destination"); + return -EINVAL; + } + if (!tb[IOAM6_IPTUNNEL_TRACE]) { NL_SET_ERR_MSG(extack, "missing trace"); return -EINVAL; @@ -102,15 +124,24 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, return -EINVAL; } - len = sizeof(*tuninfo) + trace->remlen * 4; - len_aligned = ALIGN(len, 8); - - s = lwtunnel_state_alloc(len_aligned); - if (!s) + len_aligned = ALIGN(trace->remlen * 4, 8); + lwt = lwtunnel_state_alloc(sizeof(*ilwt) + len_aligned); + if (!lwt) return -ENOMEM; - tuninfo = ioam6_lwt_info(s); - tuninfo->eh.hdrlen = (len_aligned >> 3) - 1; + ilwt = ioam6_lwt_state(lwt); + err = dst_cache_init(&ilwt->cache, GFP_ATOMIC); + if (err) { + kfree(lwt); + return err; + } + + ilwt->mode = mode; + if (tb[IOAM6_IPTUNNEL_DST]) + ilwt->tundst = nla_get_in6_addr(tb[IOAM6_IPTUNNEL_DST]); + + tuninfo = ioam6_lwt_info(lwt); + tuninfo->eh.hdrlen = ((sizeof(*tuninfo) + len_aligned) >> 3) - 1; tuninfo->pad[0] = IPV6_TLV_PADN; tuninfo->ioamh.type = IOAM6_TYPE_PREALLOC; tuninfo->ioamh.opt_type = IPV6_TLV_IOAM; @@ -119,27 +150,39 @@ static int ioam6_build_state(struct net *net, struct nlattr *nla, memcpy(&tuninfo->traceh, trace, sizeof(*trace)); - len = len_aligned - len; - if (len == 1) { - tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PAD1; - } else if (len > 0) { + if (len_aligned - trace->remlen * 4) { tuninfo->traceh.data[trace->remlen * 4] = IPV6_TLV_PADN; - tuninfo->traceh.data[trace->remlen * 4 + 1] = len - 2; + tuninfo->traceh.data[trace->remlen * 4 + 1] = 2; } - s->type = LWTUNNEL_ENCAP_IOAM6; - s->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; + lwt->type = LWTUNNEL_ENCAP_IOAM6; + lwt->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT; - *ts = s; + *ts = lwt; return 0; } -static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo) +static int ioam6_do_fill(struct net *net, struct sk_buff *skb) { struct ioam6_trace_hdr *trace; - struct ipv6hdr *oldhdr, *hdr; struct ioam6_namespace *ns; + + trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb) + + sizeof(struct ipv6_hopopt_hdr) + 2 + + sizeof(struct ioam6_hdr)); + + ns = ioam6_namespace(net, trace->namespace_id); + if (ns) + ioam6_fill_trace_data(skb, ns, trace, false); + + return 0; +} + +static int ioam6_do_inline(struct net *net, struct sk_buff *skb, + struct ioam6_lwt_encap *tuninfo) +{ + struct ipv6hdr *oldhdr, *hdr; int hdrlen, err; hdrlen = (tuninfo->eh.hdrlen + 1) << 3; @@ -168,79 +211,195 @@ static int ioam6_do_inline(struct sk_buff *skb, struct ioam6_lwt_encap *tuninfo) hdr->nexthdr = NEXTHDR_HOP; hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); - trace = (struct ioam6_trace_hdr *)(skb_transport_header(skb) - + sizeof(struct ipv6_hopopt_hdr) + 2 - + sizeof(struct ioam6_hdr)); + return ioam6_do_fill(net, skb); +} - ns = ioam6_namespace(dev_net(skb_dst(skb)->dev), trace->namespace_id); - if (ns) - ioam6_fill_trace_data(skb, ns, trace); +static int ioam6_do_encap(struct net *net, struct sk_buff *skb, + struct ioam6_lwt_encap *tuninfo, + struct in6_addr *tundst) +{ + struct dst_entry *dst = skb_dst(skb); + struct ipv6hdr *hdr, *inner_hdr; + int hdrlen, len, err; - return 0; + hdrlen = (tuninfo->eh.hdrlen + 1) << 3; + len = sizeof(*hdr) + hdrlen; + + err = skb_cow_head(skb, len + skb->mac_len); + if (unlikely(err)) + return err; + + inner_hdr = ipv6_hdr(skb); + + skb_push(skb, len); + skb_reset_network_header(skb); + skb_mac_header_rebuild(skb); + skb_set_transport_header(skb, sizeof(*hdr)); + + tuninfo->eh.nexthdr = NEXTHDR_IPV6; + memcpy(skb_transport_header(skb), (u8 *)tuninfo, hdrlen); + + hdr = ipv6_hdr(skb); + memcpy(hdr, inner_hdr, sizeof(*hdr)); + + hdr->nexthdr = NEXTHDR_HOP; + hdr->payload_len = cpu_to_be16(skb->len - sizeof(*hdr)); + hdr->daddr = *tundst; + ipv6_dev_get_saddr(net, dst->dev, &hdr->daddr, + IPV6_PREFER_SRC_PUBLIC, &hdr->saddr); + + skb_postpush_rcsum(skb, hdr, len); + + return ioam6_do_fill(net, skb); } static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct lwtunnel_state *lwt = skb_dst(skb)->lwtstate; + struct dst_entry *dst = skb_dst(skb); + struct in6_addr orig_daddr; + struct ioam6_lwt *ilwt; int err = -EINVAL; if (skb->protocol != htons(ETH_P_IPV6)) goto drop; - /* Only for packets we send and - * that do not contain a Hop-by-Hop yet - */ - if (skb->dev || ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) - goto out; - - err = ioam6_do_inline(skb, ioam6_lwt_info(lwt)); - if (unlikely(err)) + ilwt = ioam6_lwt_state(dst->lwtstate); + orig_daddr = ipv6_hdr(skb)->daddr; + + switch (ilwt->mode) { + case IOAM6_IPTUNNEL_MODE_INLINE: +do_inline: + /* Direct insertion - if there is no Hop-by-Hop yet */ + if (ipv6_hdr(skb)->nexthdr == NEXTHDR_HOP) + goto out; + + err = ioam6_do_inline(net, skb, &ilwt->tuninfo); + if (unlikely(err)) + goto drop; + + break; + case IOAM6_IPTUNNEL_MODE_ENCAP: +do_encap: + /* Encapsulation (ip6ip6) */ + err = ioam6_do_encap(net, skb, &ilwt->tuninfo, &ilwt->tundst); + if (unlikely(err)) + goto drop; + + break; + case IOAM6_IPTUNNEL_MODE_AUTO: + /* Automatic (RFC8200 compliant): + * - local packets -> INLINE mode + * - in-transit packets -> ENCAP mode + */ + if (!skb->dev) + goto do_inline; + + goto do_encap; + default: goto drop; + } - err = skb_cow_head(skb, LL_RESERVED_SPACE(skb_dst(skb)->dev)); + err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev)); if (unlikely(err)) goto drop; + if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) { + preempt_disable(); + dst = dst_cache_get(&ilwt->cache); + preempt_enable(); + + if (unlikely(!dst)) { + struct ipv6hdr *hdr = ipv6_hdr(skb); + struct flowi6 fl6; + + memset(&fl6, 0, sizeof(fl6)); + fl6.daddr = hdr->daddr; + fl6.saddr = hdr->saddr; + fl6.flowlabel = ip6_flowinfo(hdr); + fl6.flowi6_mark = skb->mark; + fl6.flowi6_proto = hdr->nexthdr; + + dst = ip6_route_output(net, NULL, &fl6); + if (dst->error) { + err = dst->error; + dst_release(dst); + goto drop; + } + + preempt_disable(); + dst_cache_set_ip6(&ilwt->cache, dst, &fl6.saddr); + preempt_enable(); + } + + skb_dst_drop(skb); + skb_dst_set(skb, dst); + + return dst_output(net, sk, skb); + } out: - return lwt->orig_output(net, sk, skb); - + return dst->lwtstate->orig_output(net, sk, skb); drop: kfree_skb(skb); return err; } +static void ioam6_destroy_state(struct lwtunnel_state *lwt) +{ + dst_cache_destroy(&ioam6_lwt_state(lwt)->cache); +} + static int ioam6_fill_encap_info(struct sk_buff *skb, struct lwtunnel_state *lwtstate) { - struct ioam6_trace_hdr *trace; + struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); int err; - trace = ioam6_lwt_trace(lwtstate); - - err = nla_put(skb, IOAM6_IPTUNNEL_TRACE, sizeof(*trace), trace); + err = nla_put_u8(skb, IOAM6_IPTUNNEL_MODE, ilwt->mode); if (err) - return err; + goto ret; - return 0; + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) { + err = nla_put_in6_addr(skb, IOAM6_IPTUNNEL_DST, &ilwt->tundst); + if (err) + goto ret; + } + + err = nla_put(skb, IOAM6_IPTUNNEL_TRACE, sizeof(ilwt->tuninfo.traceh), + &ilwt->tuninfo.traceh); +ret: + return err; } static int ioam6_encap_nlsize(struct lwtunnel_state *lwtstate) { - struct ioam6_trace_hdr *trace = ioam6_lwt_trace(lwtstate); + struct ioam6_lwt *ilwt = ioam6_lwt_state(lwtstate); + int nlsize; + + nlsize = nla_total_size(sizeof(ilwt->mode)) + + nla_total_size(sizeof(ilwt->tuninfo.traceh)); - return nla_total_size(sizeof(*trace)); + if (ilwt->mode != IOAM6_IPTUNNEL_MODE_INLINE) + nlsize += nla_total_size(sizeof(ilwt->tundst)); + + return nlsize; } static int ioam6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b) { - struct ioam6_trace_hdr *a_hdr = ioam6_lwt_trace(a); - struct ioam6_trace_hdr *b_hdr = ioam6_lwt_trace(b); - - return (a_hdr->namespace_id != b_hdr->namespace_id); + struct ioam6_trace_hdr *trace_a = ioam6_lwt_trace(a); + struct ioam6_trace_hdr *trace_b = ioam6_lwt_trace(b); + struct ioam6_lwt *ilwt_a = ioam6_lwt_state(a); + struct ioam6_lwt *ilwt_b = ioam6_lwt_state(b); + + return (ilwt_a->mode != ilwt_b->mode || + (ilwt_a->mode != IOAM6_IPTUNNEL_MODE_INLINE && + !ipv6_addr_equal(&ilwt_a->tundst, &ilwt_b->tundst)) || + trace_a->namespace_id != trace_b->namespace_id); } static const struct lwtunnel_encap_ops ioam6_iptun_ops = { .build_state = ioam6_build_state, + .destroy_state = ioam6_destroy_state, .output = ioam6_output, .fill_encap = ioam6_fill_encap_info, .get_encap_size = ioam6_encap_nlsize, -- cgit v1.2.3 From 571e5c0efcb29c5dac8cf2949d3eed84ec43056c Mon Sep 17 00:00:00 2001 From: Richard Guy Briggs Date: Wed, 19 May 2021 16:00:22 -0400 Subject: audit: add OPENAT2 record to list "how" info Since the openat2(2) syscall uses a struct open_how pointer to communicate its parameters they are not usefully recorded by the audit SYSCALL record's four existing arguments. Add a new audit record type OPENAT2 that reports the parameters in its third argument, struct open_how with fields oflag, mode and resolve. The new record in the context of an event would look like: time->Wed Mar 17 16:28:53 2021 type=PROCTITLE msg=audit(1616012933.531:184): proctitle= 73797363616C6C735F66696C652F6F70656E617432002F746D702F61756469742D 7465737473756974652D737641440066696C652D6F70656E617432 type=PATH msg=audit(1616012933.531:184): item=1 name="file-openat2" inode=29 dev=00:1f mode=0100600 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=CREATE cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 cap_frootid=0 type=PATH msg=audit(1616012933.531:184): item=0 name="/root/rgb/git/audit-testsuite/tests" inode=25 dev=00:1f mode=040700 ouid=0 ogid=0 rdev=00:00 obj=unconfined_u:object_r:user_tmp_t:s0 nametype=PARENT cap_fp=0 cap_fi=0 cap_fe=0 cap_fver=0 cap_frootid=0 type=CWD msg=audit(1616012933.531:184): cwd="/root/rgb/git/audit-testsuite/tests" type=OPENAT2 msg=audit(1616012933.531:184): oflag=0100302 mode=0600 resolve=0xa type=SYSCALL msg=audit(1616012933.531:184): arch=c000003e syscall=437 success=yes exit=4 a0=3 a1=7ffe315f1c53 a2=7ffe315f1550 a3=18 items=2 ppid=528 pid=540 auid=0 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=ttyS0 ses=1 comm="openat2" exe="/root/rgb/git/audit-testsuite/tests/syscalls_file/openat2" subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key="testsuite-1616012933-bjAUcEPO" Link: https://lore.kernel.org/r/d23fbb89186754487850367224b060e26f9b7181.1621363275.git.rgb@redhat.com Signed-off-by: Richard Guy Briggs Acked-by: Christian Brauner [PM: tweak subject, wrap example, move AUDIT_OPENAT2 to 1337] Signed-off-by: Paul Moore --- fs/open.c | 2 ++ include/linux/audit.h | 10 ++++++++++ include/uapi/linux/audit.h | 1 + kernel/audit.h | 2 ++ kernel/auditsc.c | 18 +++++++++++++++++- 5 files changed, 32 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/open.c b/fs/open.c index daa324606a41..a7f6cab81267 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1248,6 +1248,8 @@ SYSCALL_DEFINE4(openat2, int, dfd, const char __user *, filename, if (err) return err; + audit_openat2_how(&tmp); + /* O_LARGEFILE is only allowed for non-O_PATH. */ if (!(tmp.flags & O_PATH) && force_o_largefile()) tmp.flags |= O_LARGEFILE; diff --git a/include/linux/audit.h b/include/linux/audit.h index 5fbeeeb6b726..0e0eb4c0fa10 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -399,6 +399,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, const struct cred *old); extern void __audit_log_capset(const struct cred *new, const struct cred *old); extern void __audit_mmap_fd(int fd, int flags); +extern void __audit_openat2_how(struct open_how *how); extern void __audit_log_kern_module(char *name); extern void __audit_fanotify(unsigned int response); extern void __audit_tk_injoffset(struct timespec64 offset); @@ -495,6 +496,12 @@ static inline void audit_mmap_fd(int fd, int flags) __audit_mmap_fd(fd, flags); } +static inline void audit_openat2_how(struct open_how *how) +{ + if (unlikely(!audit_dummy_context())) + __audit_openat2_how(how); +} + static inline void audit_log_kern_module(char *name) { if (!audit_dummy_context()) @@ -646,6 +653,9 @@ static inline void audit_log_capset(const struct cred *new, static inline void audit_mmap_fd(int fd, int flags) { } +static inline void audit_openat2_how(struct open_how *how) +{ } + static inline void audit_log_kern_module(char *name) { } diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..afa2472ad5d6 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,7 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_OPENAT2 1337 /* Record showing openat2 how args */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/kernel/audit.h b/kernel/audit.h index d6a2c899a8db..3b64a97f6091 100644 --- a/kernel/audit.h +++ b/kernel/audit.h @@ -14,6 +14,7 @@ #include #include #include +#include // struct open_how /* AUDIT_NAMES is the number of slots we reserve in the audit_context * for saving names from getname(). If we get more names we will allocate @@ -188,6 +189,7 @@ struct audit_context { int fd; int flags; } mmap; + struct open_how openat2; struct { int argc; } execve; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 8c4335a35274..a4ba53f5354e 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -63,7 +63,7 @@ #include #include #include -#include +#include // struct open_how #include "audit.h" @@ -1306,6 +1306,12 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "fd=%d flags=0x%x", context->mmap.fd, context->mmap.flags); break; + case AUDIT_OPENAT2: + audit_log_format(ab, "oflag=0%llo mode=0%llo resolve=0x%llx", + context->openat2.flags, + context->openat2.mode, + context->openat2.resolve); + break; case AUDIT_EXECVE: audit_log_execve_info(context, &ab); break; @@ -2536,6 +2542,16 @@ void __audit_mmap_fd(int fd, int flags) context->type = AUDIT_MMAP; } +void __audit_openat2_how(struct open_how *how) +{ + struct audit_context *context = audit_context(); + + context->openat2.flags = how->flags; + context->openat2.mode = how->mode; + context->openat2.resolve = how->resolve; + context->type = AUDIT_OPENAT2; +} + void __audit_log_kern_module(char *name) { struct audit_context *context = audit_context(); -- cgit v1.2.3 From d154abdda6dcac92c63141035e477ac18077ffd8 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 24 Sep 2021 07:13:54 -0500 Subject: ipmi: Fix a typo Spell "RESPONSE" correctly in a comment. Signed-off-by: Corey Minyard --- include/uapi/linux/ipmi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index 32d148309b16..007e65f9243b 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -158,7 +158,7 @@ struct kernel_ipmi_msg { * is used for the receive in-kernel interface and in the receive * IOCTL. * - * The "IPMI_RESPONSE_RESPNOSE_TYPE" is a little strange sounding, but + * The "IPMI_RESPONSE_RESPONSE_TYPE" is a little strange sounding, but * it allows you to get the message results when you send a response * message. */ -- cgit v1.2.3 From 059747c245f0e9af5e109eece7d3414dbe08d513 Mon Sep 17 00:00:00 2001 From: Corey Minyard Date: Fri, 24 Sep 2021 11:42:56 -0500 Subject: ipmi: Add support for IPMB direct messages An application has come up that has a device sitting right on the IPMB that would like to communicate with the BMC on the IPMB using normal IPMI commands. Sending these commands and handling the responses is easy enough, no modifications are needed to the IPMI infrastructure. But if this is an application that also needs to receive IPMB commands and respond, some way is needed to handle these incoming commands and send the responses. Currently, the IPMI message handler only sends commands to the interface and only receives responses from interface. This change extends the interface to receive commands/responses and send commands/responses. These are formatted differently in support of receiving/sending IPMB messages directly. Signed-off-by: Corey Minyard Tested-by: Andrew Manley Reviewed-by: Andrew Manley --- drivers/char/ipmi/ipmi_msghandler.c | 288 +++++++++++++++++++++++++++++++----- include/linux/ipmi_smi.h | 59 ++++++++ include/uapi/linux/ipmi.h | 14 ++ 3 files changed, 328 insertions(+), 33 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/char/ipmi/ipmi_msghandler.c b/drivers/char/ipmi/ipmi_msghandler.c index ad1a8fc379b9..a60201d3f735 100644 --- a/drivers/char/ipmi/ipmi_msghandler.c +++ b/drivers/char/ipmi/ipmi_msghandler.c @@ -653,6 +653,11 @@ static int is_ipmb_bcast_addr(struct ipmi_addr *addr) return addr->addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE; } +static int is_ipmb_direct_addr(struct ipmi_addr *addr) +{ + return addr->addr_type == IPMI_IPMB_DIRECT_ADDR_TYPE; +} + static void free_recv_msg_list(struct list_head *q) { struct ipmi_recv_msg *msg, *msg2; @@ -805,6 +810,17 @@ ipmi_addr_equal(struct ipmi_addr *addr1, struct ipmi_addr *addr2) && (ipmb_addr1->lun == ipmb_addr2->lun)); } + if (is_ipmb_direct_addr(addr1)) { + struct ipmi_ipmb_direct_addr *daddr1 + = (struct ipmi_ipmb_direct_addr *) addr1; + struct ipmi_ipmb_direct_addr *daddr2 + = (struct ipmi_ipmb_direct_addr *) addr2; + + return daddr1->slave_addr == daddr2->slave_addr && + daddr1->rq_lun == daddr2->rq_lun && + daddr1->rs_lun == daddr2->rs_lun; + } + if (is_lan_addr(addr1)) { struct ipmi_lan_addr *lan_addr1 = (struct ipmi_lan_addr *) addr1; @@ -843,6 +859,23 @@ int ipmi_validate_addr(struct ipmi_addr *addr, int len) return 0; } + if (is_ipmb_direct_addr(addr)) { + struct ipmi_ipmb_direct_addr *daddr = (void *) addr; + + if (addr->channel != 0) + return -EINVAL; + if (len < sizeof(struct ipmi_ipmb_direct_addr)) + return -EINVAL; + + if (daddr->slave_addr & 0x01) + return -EINVAL; + if (daddr->rq_lun >= 4) + return -EINVAL; + if (daddr->rs_lun >= 4) + return -EINVAL; + return 0; + } + if (is_lan_addr(addr)) { if (len < sizeof(struct ipmi_lan_addr)) return -EINVAL; @@ -862,6 +895,9 @@ unsigned int ipmi_addr_length(int addr_type) || (addr_type == IPMI_IPMB_BROADCAST_ADDR_TYPE)) return sizeof(struct ipmi_ipmb_addr); + if (addr_type == IPMI_IPMB_DIRECT_ADDR_TYPE) + return sizeof(struct ipmi_ipmb_direct_addr); + if (addr_type == IPMI_LAN_ADDR_TYPE) return sizeof(struct ipmi_lan_addr); @@ -2052,6 +2088,58 @@ out_err: return rv; } +static int i_ipmi_req_ipmb_direct(struct ipmi_smi *intf, + struct ipmi_addr *addr, + long msgid, + struct kernel_ipmi_msg *msg, + struct ipmi_smi_msg *smi_msg, + struct ipmi_recv_msg *recv_msg, + unsigned char source_lun) +{ + struct ipmi_ipmb_direct_addr *daddr; + bool is_cmd = !(recv_msg->msg.netfn & 0x1); + + if (!(intf->handlers->flags & IPMI_SMI_CAN_HANDLE_IPMB_DIRECT)) + return -EAFNOSUPPORT; + + /* Responses must have a completion code. */ + if (!is_cmd && msg->data_len < 1) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EINVAL; + } + + if ((msg->data_len + 4) > IPMI_MAX_MSG_LENGTH) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EMSGSIZE; + } + + daddr = (struct ipmi_ipmb_direct_addr *) addr; + if (daddr->rq_lun > 3 || daddr->rs_lun > 3) { + ipmi_inc_stat(intf, sent_invalid_commands); + return -EINVAL; + } + + smi_msg->type = IPMI_SMI_MSG_TYPE_IPMB_DIRECT; + smi_msg->msgid = msgid; + + if (is_cmd) { + smi_msg->data[0] = msg->netfn << 2 | daddr->rs_lun; + smi_msg->data[2] = recv_msg->msgid << 2 | daddr->rq_lun; + } else { + smi_msg->data[0] = msg->netfn << 2 | daddr->rq_lun; + smi_msg->data[2] = recv_msg->msgid << 2 | daddr->rs_lun; + } + smi_msg->data[1] = daddr->slave_addr; + smi_msg->data[3] = msg->cmd; + + memcpy(smi_msg->data + 4, msg->data, msg->data_len); + smi_msg->data_size = msg->data_len + 4; + + smi_msg->user_data = recv_msg; + + return 0; +} + static int i_ipmi_req_lan(struct ipmi_smi *intf, struct ipmi_addr *addr, long msgid, @@ -2241,6 +2329,9 @@ static int i_ipmi_request(struct ipmi_user *user, rv = i_ipmi_req_ipmb(intf, addr, msgid, msg, smi_msg, recv_msg, source_address, source_lun, retries, retry_time_ms); + } else if (is_ipmb_direct_addr(addr)) { + rv = i_ipmi_req_ipmb_direct(intf, addr, msgid, msg, smi_msg, + recv_msg, source_lun); } else if (is_lan_addr(addr)) { rv = i_ipmi_req_lan(intf, addr, msgid, msg, smi_msg, recv_msg, source_lun, retries, retry_time_ms); @@ -3802,6 +3893,123 @@ static int handle_ipmb_get_msg_cmd(struct ipmi_smi *intf, return rv; } +static int handle_ipmb_direct_rcv_cmd(struct ipmi_smi *intf, + struct ipmi_smi_msg *msg) +{ + struct cmd_rcvr *rcvr; + int rv = 0; + struct ipmi_user *user = NULL; + struct ipmi_ipmb_direct_addr *daddr; + struct ipmi_recv_msg *recv_msg; + unsigned char netfn = msg->rsp[0] >> 2; + unsigned char cmd = msg->rsp[3]; + + rcu_read_lock(); + /* We always use channel 0 for direct messages. */ + rcvr = find_cmd_rcvr(intf, netfn, cmd, 0); + if (rcvr) { + user = rcvr->user; + kref_get(&user->refcount); + } else + user = NULL; + rcu_read_unlock(); + + if (user == NULL) { + /* We didn't find a user, deliver an error response. */ + ipmi_inc_stat(intf, unhandled_commands); + + msg->data[0] = ((netfn + 1) << 2) | (msg->rsp[4] & 0x3); + msg->data[1] = msg->rsp[2]; + msg->data[2] = msg->rsp[4] & ~0x3; + msg->data[3] = cmd; + msg->data[4] = IPMI_INVALID_CMD_COMPLETION_CODE; + msg->data_size = 5; + + rcu_read_lock(); + if (!intf->in_shutdown) { + smi_send(intf, intf->handlers, msg, 0); + /* + * We used the message, so return the value + * that causes it to not be freed or + * queued. + */ + rv = -1; + } + rcu_read_unlock(); + } else { + recv_msg = ipmi_alloc_recv_msg(); + if (!recv_msg) { + /* + * We couldn't allocate memory for the + * message, so requeue it for handling + * later. + */ + rv = 1; + kref_put(&user->refcount, free_user); + } else { + /* Extract the source address from the data. */ + daddr = (struct ipmi_ipmb_direct_addr *)&recv_msg->addr; + daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE; + daddr->channel = 0; + daddr->slave_addr = msg->rsp[1]; + daddr->rs_lun = msg->rsp[0] & 3; + daddr->rq_lun = msg->rsp[2] & 3; + + /* + * Extract the rest of the message information + * from the IPMB header. + */ + recv_msg->user = user; + recv_msg->recv_type = IPMI_CMD_RECV_TYPE; + recv_msg->msgid = (msg->rsp[2] >> 2); + recv_msg->msg.netfn = msg->rsp[0] >> 2; + recv_msg->msg.cmd = msg->rsp[3]; + recv_msg->msg.data = recv_msg->msg_data; + + recv_msg->msg.data_len = msg->rsp_size - 4; + memcpy(recv_msg->msg_data, msg->rsp + 4, + msg->rsp_size - 4); + if (deliver_response(intf, recv_msg)) + ipmi_inc_stat(intf, unhandled_commands); + else + ipmi_inc_stat(intf, handled_commands); + } + } + + return rv; +} + +static int handle_ipmb_direct_rcv_rsp(struct ipmi_smi *intf, + struct ipmi_smi_msg *msg) +{ + struct ipmi_recv_msg *recv_msg; + struct ipmi_ipmb_direct_addr *daddr; + + recv_msg = (struct ipmi_recv_msg *) msg->user_data; + if (recv_msg == NULL) { + dev_warn(intf->si_dev, + "IPMI message received with no owner. This could be because of a malformed message, or because of a hardware error. Contact your hardware vendor for assistance.\n"); + return 0; + } + + recv_msg->recv_type = IPMI_RESPONSE_RECV_TYPE; + recv_msg->msgid = msg->msgid; + daddr = (struct ipmi_ipmb_direct_addr *) &recv_msg->addr; + daddr->addr_type = IPMI_IPMB_DIRECT_ADDR_TYPE; + daddr->channel = 0; + daddr->slave_addr = msg->rsp[1]; + daddr->rq_lun = msg->rsp[0] & 3; + daddr->rs_lun = msg->rsp[2] & 3; + recv_msg->msg.netfn = msg->rsp[0] >> 2; + recv_msg->msg.cmd = msg->rsp[3]; + memcpy(recv_msg->msg_data, &msg->rsp[4], msg->rsp_size - 4); + recv_msg->msg.data = recv_msg->msg_data; + recv_msg->msg.data_len = msg->rsp_size - 4; + deliver_local_response(intf, recv_msg); + + return 0; +} + static int handle_lan_get_msg_rsp(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { @@ -4227,18 +4435,40 @@ static int handle_bmc_rsp(struct ipmi_smi *intf, static int handle_one_recv_msg(struct ipmi_smi *intf, struct ipmi_smi_msg *msg) { - int requeue; + int requeue = 0; int chan; + unsigned char cc; + bool is_cmd = !((msg->rsp[0] >> 2) & 1); pr_debug("Recv: %*ph\n", msg->rsp_size, msg->rsp); - if ((msg->data_size >= 2) + if (msg->rsp_size < 2) { + /* Message is too small to be correct. */ + dev_warn(intf->si_dev, + "BMC returned too small a message for netfn %x cmd %x, got %d bytes\n", + (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp_size); + +return_unspecified: + /* Generate an error response for the message. */ + msg->rsp[0] = msg->data[0] | (1 << 2); + msg->rsp[1] = msg->data[1]; + msg->rsp[2] = IPMI_ERR_UNSPECIFIED; + msg->rsp_size = 3; + } else if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { + /* commands must have at least 3 bytes, responses 4. */ + if (is_cmd && (msg->rsp_size < 3)) { + ipmi_inc_stat(intf, invalid_commands); + goto out; + } + if (!is_cmd && (msg->rsp_size < 4)) + goto return_unspecified; + } else if ((msg->data_size >= 2) && (msg->data[0] == (IPMI_NETFN_APP_REQUEST << 2)) && (msg->data[1] == IPMI_SEND_MSG_CMD) && (msg->user_data == NULL)) { if (intf->in_shutdown) - goto free_msg; + goto out; /* * This is the local response to a command send, start @@ -4273,21 +4503,6 @@ static int handle_one_recv_msg(struct ipmi_smi *intf, } else /* The message was sent, start the timer. */ intf_start_seq_timer(intf, msg->msgid); -free_msg: - requeue = 0; - goto out; - - } else if (msg->rsp_size < 2) { - /* Message is too small to be correct. */ - dev_warn(intf->si_dev, - "BMC returned too small a message for netfn %x cmd %x, got %d bytes\n", - (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp_size); - - /* Generate an error response for the message. */ - msg->rsp[0] = msg->data[0] | (1 << 2); - msg->rsp[1] = msg->data[1]; - msg->rsp[2] = IPMI_ERR_UNSPECIFIED; - msg->rsp_size = 3; } else if (((msg->rsp[0] >> 2) != ((msg->data[0] >> 2) | 1)) || (msg->rsp[1] != msg->data[1])) { /* @@ -4299,39 +4514,46 @@ free_msg: (msg->data[0] >> 2) | 1, msg->data[1], msg->rsp[0] >> 2, msg->rsp[1]); - /* Generate an error response for the message. */ - msg->rsp[0] = msg->data[0] | (1 << 2); - msg->rsp[1] = msg->data[1]; - msg->rsp[2] = IPMI_ERR_UNSPECIFIED; - msg->rsp_size = 3; + goto return_unspecified; } - if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) - && (msg->rsp[1] == IPMI_SEND_MSG_CMD) - && (msg->user_data != NULL)) { + if (msg->type == IPMI_SMI_MSG_TYPE_IPMB_DIRECT) { + if ((msg->data[0] >> 2) & 1) { + /* It's a response to a sent response. */ + chan = 0; + cc = msg->rsp[4]; + goto process_response_response; + } + if (is_cmd) + requeue = handle_ipmb_direct_rcv_cmd(intf, msg); + else + requeue = handle_ipmb_direct_rcv_rsp(intf, msg); + } else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) + && (msg->rsp[1] == IPMI_SEND_MSG_CMD) + && (msg->user_data != NULL)) { /* * It's a response to a response we sent. For this we * deliver a send message response to the user. */ - struct ipmi_recv_msg *recv_msg = msg->user_data; - - requeue = 0; - if (msg->rsp_size < 2) - /* Message is too small to be correct. */ - goto out; + struct ipmi_recv_msg *recv_msg; chan = msg->data[2] & 0x0f; if (chan >= IPMI_MAX_CHANNELS) /* Invalid channel number */ goto out; + cc = msg->rsp[2]; +process_response_response: + recv_msg = msg->user_data; + + requeue = 0; if (!recv_msg) goto out; recv_msg->recv_type = IPMI_RESPONSE_RESPONSE_TYPE; recv_msg->msg.data = recv_msg->msg_data; + recv_msg->msg_data[0] = cc; recv_msg->msg.data_len = 1; - recv_msg->msg_data[0] = msg->rsp[2]; deliver_local_response(intf, recv_msg); } else if ((msg->rsp[0] == ((IPMI_NETFN_APP_REQUEST|1) << 2)) && (msg->rsp[1] == IPMI_GET_MSG_CMD)) { diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h index deec18b8944a..9277d21c2690 100644 --- a/include/linux/ipmi_smi.h +++ b/include/linux/ipmi_smi.h @@ -38,6 +38,59 @@ struct ipmi_smi; #define IPMI_WATCH_MASK_CHECK_WATCHDOG (1 << 1) #define IPMI_WATCH_MASK_CHECK_COMMANDS (1 << 2) +/* + * SMI messages + * + * When communicating with an SMI, messages come in two formats: + * + * * Normal (to a BMC over a BMC interface) + * + * * IPMB (over a IPMB to another MC) + * + * When normal, commands are sent using the format defined by a + * standard message over KCS (NetFn must be even): + * + * +-----------+-----+------+ + * | NetFn/LUN | Cmd | Data | + * +-----------+-----+------+ + * + * And responses, similarly, with an completion code added (NetFn must + * be odd): + * + * +-----------+-----+------+------+ + * | NetFn/LUN | Cmd | CC | Data | + * +-----------+-----+------+------+ + * + * With normal messages, only commands are sent and only responses are + * received. + * + * In IPMB mode, we are acting as an IPMB device. Commands will be in + * the following format (NetFn must be even): + * + * +-------------+------+-------------+-----+------+ + * | NetFn/rsLUN | Addr | rqSeq/rqLUN | Cmd | Data | + * +-------------+------+-------------+-----+------+ + * + * Responses will using the following format: + * + * +-------------+------+-------------+-----+------+------+ + * | NetFn/rqLUN | Addr | rqSeq/rsLUN | Cmd | CC | Data | + * +-------------+------+-------------+-----+------+------+ + * + * This is similar to the format defined in the IPMB manual section + * 2.11.1 with the checksums and the first address removed. Also, the + * address is always the remote address. + * + * IPMB messages can be commands and responses in both directions. + * Received commands are handled as received commands from the message + * queue. + */ + +enum ipmi_smi_msg_type { + IPMI_SMI_MSG_TYPE_NORMAL = 0, + IPMI_SMI_MSG_TYPE_IPMB_DIRECT +}; + /* * Messages to/from the lower layer. The smi interface will take one * of these to send. After the send has occurred and a response has @@ -54,6 +107,8 @@ struct ipmi_smi; struct ipmi_smi_msg { struct list_head link; + enum ipmi_smi_msg_type type; + long msgid; void *user_data; @@ -73,6 +128,10 @@ struct ipmi_smi_msg { struct ipmi_smi_handlers { struct module *owner; + /* Capabilities of the SMI. */ +#define IPMI_SMI_CAN_HANDLE_IPMB_DIRECT (1 << 0) + unsigned int flags; + /* * The low-level interface cannot start sending messages to * the upper layer until this function is called. This may diff --git a/include/uapi/linux/ipmi.h b/include/uapi/linux/ipmi.h index 007e65f9243b..966c3070959b 100644 --- a/include/uapi/linux/ipmi.h +++ b/include/uapi/linux/ipmi.h @@ -80,6 +80,20 @@ struct ipmi_ipmb_addr { unsigned char lun; }; +/* + * Used for messages received directly from an IPMB that have not gone + * through a MC. This is for systems that sit right on an IPMB so + * they can receive commands and respond to them. + */ +#define IPMI_IPMB_DIRECT_ADDR_TYPE 0x81 +struct ipmi_ipmb_direct_addr { + int addr_type; + short channel; + unsigned char slave_addr; + unsigned char rs_lun; + unsigned char rq_lun; +}; + /* * A LAN Address. This is an address to/from a LAN interface bridged * by the BMC, not an address actually out on the LAN. -- cgit v1.2.3 From 29a9f27574692a71c04fd41ca4bbf8eae842af13 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Thu, 23 Sep 2021 16:41:27 +0800 Subject: virt: acrn: Introduce interfaces for MMIO device passthrough MMIO device passthrough enables an OS in a virtual machine to directly access a MMIO device in the host. It promises almost the native performance, which is required in performance-critical scenarios of ACRN. HSM provides the following ioctls: - Assign - ACRN_IOCTL_ASSIGN_MMIODEV Pass data struct acrn_mmiodev from userspace to the hypervisor, and inform the hypervisor to assign a MMIO device to a User VM. - De-assign - ACRN_IOCTL_DEASSIGN_PCIDEV Pass data struct acrn_mmiodev from userspace to the hypervisor, and inform the hypervisor to de-assign a MMIO device from a User VM. These new APIs will be used by user space code vm_assign_mmiodev and vm_deassign_mmiodev in https://github.com/projectacrn/acrn-hypervisor/blob/master/devicemodel/core/vmmapi.c Signed-off-by: Shuo Liu Signed-off-by: Fei Li Link: https://lore.kernel.org/r/20210923084128.18902-2-fei1.li@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 25 +++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 28 ++++++++++++++++++++++++++++ 3 files changed, 79 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index 130e12b8652a..f567ca59d7c2 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -114,6 +114,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_ptdev_irq *irq_info; struct acrn_ioeventfd ioeventfd; struct acrn_vm_memmap memmap; + struct acrn_mmiodev *mmiodev; struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; struct acrn_irqfd irqfd; @@ -217,6 +218,30 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, ret = acrn_vm_memseg_unmap(vm, &memmap); break; + case ACRN_IOCTL_ASSIGN_MMIODEV: + mmiodev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_mmiodev)); + if (IS_ERR(mmiodev)) + return PTR_ERR(mmiodev); + + ret = hcall_assign_mmiodev(vm->vmid, virt_to_phys(mmiodev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to assign MMIO device!\n"); + kfree(mmiodev); + break; + case ACRN_IOCTL_DEASSIGN_MMIODEV: + mmiodev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_mmiodev)); + if (IS_ERR(mmiodev)) + return PTR_ERR(mmiodev); + + ret = hcall_deassign_mmiodev(vm->vmid, virt_to_phys(mmiodev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to deassign MMIO device!\n"); + kfree(mmiodev); + break; case ACRN_IOCTL_ASSIGN_PCIDEV: pcidev = memdup_user((void __user *)ioctl_param, sizeof(struct acrn_pcidev)); diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index 0cfad05bd1a9..f0c78e52cebb 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -41,6 +41,8 @@ #define HC_RESET_PTDEV_INTR _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x04) #define HC_ASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05) #define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) +#define HC_ASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x07) +#define HC_DEASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x08) #define HC_ID_PM_BASE 0x80UL #define HC_PM_GET_CPU_STATE _HC_ID(HC_ID, HC_ID_PM_BASE + 0x00) @@ -194,6 +196,30 @@ static inline long hcall_set_memory_regions(u64 regions_pa) return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); } +/** + * hcall_assign_mmiodev() - Assign a MMIO device to a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_mmiodev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_assign_mmiodev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_ASSIGN_MMIODEV, vmid, addr); +} + +/** + * hcall_deassign_mmiodev() - De-assign a PCI device from a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_mmiodev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_deassign_mmiodev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_DEASSIGN_MMIODEV, vmid, addr); +} + /** * hcall_assign_pcidev() - Assign a PCI device to a User VM * @vmid: User VM ID diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 353b2a2e4536..470036d6b1ac 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -396,6 +396,7 @@ struct acrn_ptdev_irq { /* Type of PCI device assignment */ #define ACRN_PTDEV_QUIRK_ASSIGN (1U << 0) +#define ACRN_MMIODEV_RES_NUM 3 #define ACRN_PCI_NUM_BARS 6 /** * struct acrn_pcidev - Info for assigning or de-assigning a PCI device @@ -417,6 +418,29 @@ struct acrn_pcidev { __u32 bar[ACRN_PCI_NUM_BARS]; }; +/** + * struct acrn_mmiodev - Info for assigning or de-assigning a MMIO device + * @name: Name of the MMIO device. + * @res[].user_vm_pa: Physical address of User VM of the MMIO region + * for the MMIO device. + * @res[].service_vm_pa: Physical address of Service VM of the MMIO + * region for the MMIO device. + * @res[].size: Size of the MMIO region for the MMIO device. + * @res[].mem_type: Memory type of the MMIO region for the MMIO + * device. + * + * This structure will be passed to hypervisor directly. + */ +struct acrn_mmiodev { + __u8 name[8]; + struct { + __u64 user_vm_pa; + __u64 service_vm_pa; + __u64 size; + __u64 mem_type; + } res[ACRN_MMIODEV_RES_NUM]; +}; + /** * struct acrn_msi_entry - Info for injecting a MSI interrupt to a VM * @msi_addr: MSI addr[19:12] with dest vCPU ID @@ -568,6 +592,10 @@ struct acrn_irqfd { _IOW(ACRN_IOCTL_TYPE, 0x55, struct acrn_pcidev) #define ACRN_IOCTL_DEASSIGN_PCIDEV \ _IOW(ACRN_IOCTL_TYPE, 0x56, struct acrn_pcidev) +#define ACRN_IOCTL_ASSIGN_MMIODEV \ + _IOW(ACRN_IOCTL_TYPE, 0x57, struct acrn_mmiodev) +#define ACRN_IOCTL_DEASSIGN_MMIODEV \ + _IOW(ACRN_IOCTL_TYPE, 0x58, struct acrn_mmiodev) #define ACRN_IOCTL_PM_GET_CPU_STATE \ _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) -- cgit v1.2.3 From 424f1ac2d832f31a2814c799bd50decf6a9f8e74 Mon Sep 17 00:00:00 2001 From: Shuo Liu Date: Thu, 23 Sep 2021 16:41:28 +0800 Subject: virt: acrn: Introduce interfaces for virtual device creating/destroying The ACRN hypervisor can emulate a virtual device within hypervisor for a Guest VM. The emulated virtual device can work without the ACRN userspace after creation. The hypervisor do the emulation of that device. To support the virtual device creating/destroying, HSM provides the following ioctls: - ACRN_IOCTL_CREATE_VDEV Pass data struct acrn_vdev from userspace to the hypervisor, and inform the hypervisor to create a virtual device for a User VM. - ACRN_IOCTL_DESTROY_VDEV Pass data struct acrn_vdev from userspace to the hypervisor, and inform the hypervisor to destroy a virtual device of a User VM. These new APIs will be used by user space code vm_add_hv_vdev and vm_remove_hv_vdev in https://github.com/projectacrn/acrn-hypervisor/blob/master/devicemodel/core/vmmapi.c Signed-off-by: Shuo Liu Signed-off-by: Fei Li Link: https://lore.kernel.org/r/20210923084128.18902-3-fei1.li@intel.com Signed-off-by: Greg Kroah-Hartman --- drivers/virt/acrn/hsm.c | 24 ++++++++++++++++++++++++ drivers/virt/acrn/hypercall.h | 26 ++++++++++++++++++++++++++ include/uapi/linux/acrn.h | 42 ++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 92 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c index f567ca59d7c2..5419794fccf1 100644 --- a/drivers/virt/acrn/hsm.c +++ b/drivers/virt/acrn/hsm.c @@ -118,6 +118,7 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, struct acrn_msi_entry *msi; struct acrn_pcidev *pcidev; struct acrn_irqfd irqfd; + struct acrn_vdev *vdev; struct page *page; u64 cstate_cmd; int i, ret = 0; @@ -266,6 +267,29 @@ static long acrn_dev_ioctl(struct file *filp, unsigned int cmd, "Failed to deassign pci device!\n"); kfree(pcidev); break; + case ACRN_IOCTL_CREATE_VDEV: + vdev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vdev)); + if (IS_ERR(vdev)) + return PTR_ERR(vdev); + + ret = hcall_create_vdev(vm->vmid, virt_to_phys(vdev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to create virtual device!\n"); + kfree(vdev); + break; + case ACRN_IOCTL_DESTROY_VDEV: + vdev = memdup_user((void __user *)ioctl_param, + sizeof(struct acrn_vdev)); + if (IS_ERR(vdev)) + return PTR_ERR(vdev); + ret = hcall_destroy_vdev(vm->vmid, virt_to_phys(vdev)); + if (ret < 0) + dev_dbg(acrn_dev.this_device, + "Failed to destroy virtual device!\n"); + kfree(vdev); + break; case ACRN_IOCTL_SET_PTDEV_INTR: irq_info = memdup_user((void __user *)ioctl_param, sizeof(struct acrn_ptdev_irq)); diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h index f0c78e52cebb..71d300821a18 100644 --- a/drivers/virt/acrn/hypercall.h +++ b/drivers/virt/acrn/hypercall.h @@ -43,6 +43,8 @@ #define HC_DEASSIGN_PCIDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06) #define HC_ASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x07) #define HC_DEASSIGN_MMIODEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x08) +#define HC_CREATE_VDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x09) +#define HC_DESTROY_VDEV _HC_ID(HC_ID, HC_ID_PCI_BASE + 0x0A) #define HC_ID_PM_BASE 0x80UL #define HC_PM_GET_CPU_STATE _HC_ID(HC_ID, HC_ID_PM_BASE + 0x00) @@ -196,6 +198,30 @@ static inline long hcall_set_memory_regions(u64 regions_pa) return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa); } +/** + * hcall_create_vdev() - Create a virtual device for a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_vdev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_create_vdev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_CREATE_VDEV, vmid, addr); +} + +/** + * hcall_destroy_vdev() - Destroy a virtual device of a User VM + * @vmid: User VM ID + * @addr: Service VM GPA of the &struct acrn_vdev + * + * Return: 0 on success, <0 on failure + */ +static inline long hcall_destroy_vdev(u64 vmid, u64 addr) +{ + return acrn_hypercall2(HC_DESTROY_VDEV, vmid, addr); +} + /** * hcall_assign_mmiodev() - Assign a MMIO device to a User VM * @vmid: User VM ID diff --git a/include/uapi/linux/acrn.h b/include/uapi/linux/acrn.h index 470036d6b1ac..ccf47ed92500 100644 --- a/include/uapi/linux/acrn.h +++ b/include/uapi/linux/acrn.h @@ -441,6 +441,44 @@ struct acrn_mmiodev { } res[ACRN_MMIODEV_RES_NUM]; }; +/** + * struct acrn_vdev - Info for creating or destroying a virtual device + * @id: Union of identifier of the virtual device + * @id.value: Raw data of the identifier + * @id.fields.vendor: Vendor id of the virtual PCI device + * @id.fields.device: Device id of the virtual PCI device + * @id.fields.legacy_id: ID of the virtual device if not a PCI device + * @slot: Virtual Bus/Device/Function of the virtual + * device + * @io_base: IO resource base address of the virtual device + * @io_size: IO resource size of the virtual device + * @args: Arguments for the virtual device creation + * + * The created virtual device can be a PCI device or a legacy device (e.g. + * a virtual UART controller) and it is emulated by the hypervisor. This + * structure will be passed to hypervisor directly. + */ +struct acrn_vdev { + /* + * the identifier of the device, the low 32 bits represent the vendor + * id and device id of PCI device and the high 32 bits represent the + * device number of the legacy device + */ + union { + __u64 value; + struct { + __le16 vendor; + __le16 device; + __le32 legacy_id; + } fields; + } id; + + __u64 slot; + __u32 io_addr[ACRN_PCI_NUM_BARS]; + __u32 io_size[ACRN_PCI_NUM_BARS]; + __u8 args[128]; +}; + /** * struct acrn_msi_entry - Info for injecting a MSI interrupt to a VM * @msi_addr: MSI addr[19:12] with dest vCPU ID @@ -596,6 +634,10 @@ struct acrn_irqfd { _IOW(ACRN_IOCTL_TYPE, 0x57, struct acrn_mmiodev) #define ACRN_IOCTL_DEASSIGN_MMIODEV \ _IOW(ACRN_IOCTL_TYPE, 0x58, struct acrn_mmiodev) +#define ACRN_IOCTL_CREATE_VDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x59, struct acrn_vdev) +#define ACRN_IOCTL_DESTROY_VDEV \ + _IOW(ACRN_IOCTL_TYPE, 0x5A, struct acrn_vdev) #define ACRN_IOCTL_PM_GET_CPU_STATE \ _IOWR(ACRN_IOCTL_TYPE, 0x60, __u64) -- cgit v1.2.3 From 95a13ee858c9e426e63c97063677736f74af7163 Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 1 Oct 2021 16:55:44 +0300 Subject: hyper-v: Replace uuid.h with types.h There is no user of anything in uuid.h in the hyperv.h. Replace it with more appropriate types.h. Fixes: f081bbb3fd03 ("hyper-v: Remove internal types from UAPI header") Reported-by: Greg Kroah-Hartman Signed-off-by: Andy Shevchenko Reviewed-by: Haiyang Zhang Link: https://lore.kernel.org/r/20211001135544.1823-1-andriy.shevchenko@linux.intel.com Signed-off-by: Wei Liu --- include/uapi/linux/hyperv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/hyperv.h b/include/uapi/linux/hyperv.h index 6135d92e0d47..daf82a230c0e 100644 --- a/include/uapi/linux/hyperv.h +++ b/include/uapi/linux/hyperv.h @@ -26,7 +26,7 @@ #ifndef _UAPI_HYPERV_H #define _UAPI_HYPERV_H -#include +#include /* * Framework version for util services. -- cgit v1.2.3 From 353407d917b2d87cd8104a0453d012439c6ca4be Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Oct 2021 13:46:42 +0300 Subject: ethtool: Add ability to control transceiver modules' power mode Add a pair of new ethtool messages, 'ETHTOOL_MSG_MODULE_SET' and 'ETHTOOL_MSG_MODULE_GET', that can be used to control transceiver modules parameters and retrieve their status. The first parameter to control is the power mode of the module. It is only relevant for paged memory modules, as flat memory modules always operate in low power mode. When a paged memory module is in low power mode, its power consumption is reduced to the minimum, the management interface towards the host is available and the data path is deactivated. User space can choose to put modules that are not currently in use in low power mode and transition them to high power mode before putting the associated ports administratively up. This is useful for user space that favors reduced power consumption and lower temperatures over reduced link up times. In QSFP-DD modules the transition from low power mode to high power mode can take a few seconds and this transition is only expected to get longer with future / more complex modules. User space can control the power mode of the module via the power mode policy attribute ('ETHTOOL_A_MODULE_POWER_MODE_POLICY'). Possible values: * high: Module is always in high power mode. * auto: Module is transitioned by the host to high power mode when the first port using it is put administratively up and to low power mode when the last port using it is put administratively down. The operational power mode of the module is available to user space via the 'ETHTOOL_A_MODULE_POWER_MODE' attribute. The attribute is not reported to user space when a module is not plugged-in. The user API is designed to be generic enough so that it could be used for modules with different memory maps (e.g., SFF-8636, CMIS). The only implementation of the device driver API in this series is for a MAC driver (mlxsw) where the module is controlled by the device's firmware, but it is designed to be generic enough so that it could also be used by implementations where the module is controlled by the CPU. CMIS testing ============ # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x03 (ModuleReady) LowPwrAllowRequestHW : Off LowPwrRequestSW : Off The module is not in low power mode, as it is not forced by hardware (LowPwrAllowRequestHW is off) or by software (LowPwrRequestSW is off). The power mode can be queried from the kernel. In case LowPwrAllowRequestHW was on, the kernel would need to take into account the state of the LowPwrRequestHW signal, which is not visible to user space. $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy high power-mode high Change the power mode policy to 'auto': # ethtool --set-module swp11 power-mode-policy auto Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x01 (ModuleLowPwr) LowPwrAllowRequestHW : Off LowPwrRequestSW : On Put the associated port administratively up which will instruct the host to transition the module to high power mode: # ip link set dev swp11 up Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode high Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x03 (ModuleReady) LowPwrAllowRequestHW : Off LowPwrRequestSW : Off Put the associated port administratively down which will instruct the host to transition the module to low power mode: # ip link set dev swp11 down Query the power mode again: $ ethtool --show-module swp11 Module parameters for swp11: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp11 Identifier : 0x18 (QSFP-DD Double Density 8X Pluggable Transceiver (INF-8628)) ... Module State : 0x01 (ModuleLowPwr) LowPwrAllowRequestHW : Off LowPwrRequestSW : On SFF-8636 testing ================ # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) enabled Power set : Off Power override : On ... Transmit avg optical power (Channel 1) : 0.7733 mW / -1.12 dBm Transmit avg optical power (Channel 2) : 0.7649 mW / -1.16 dBm Transmit avg optical power (Channel 3) : 0.7790 mW / -1.08 dBm Transmit avg optical power (Channel 4) : 0.7837 mW / -1.06 dBm Rcvr signal avg optical power(Channel 1) : 0.9302 mW / -0.31 dBm Rcvr signal avg optical power(Channel 2) : 0.9079 mW / -0.42 dBm Rcvr signal avg optical power(Channel 3) : 0.8993 mW / -0.46 dBm Rcvr signal avg optical power(Channel 4) : 0.8778 mW / -0.57 dBm The module is not in low power mode, as it is not forced by hardware (Power override is on) or by software (Power set is off). The power mode can be queried from the kernel. In case Power override was off, the kernel would need to take into account the state of the LPMode signal, which is not visible to user space. $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy high power-mode high Change the power mode policy to 'auto': # ethtool --set-module swp13 power-mode-policy auto Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) not enabled Power set : On Power override : On ... Transmit avg optical power (Channel 1) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 2) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 3) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 4) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 1) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 2) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 3) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 4) : 0.0000 mW / -inf dBm Put the associated port administratively up which will instruct the host to transition the module to high power mode: # ip link set dev swp13 up Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode high Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) enabled Power set : Off Power override : On ... Transmit avg optical power (Channel 1) : 0.7934 mW / -1.01 dBm Transmit avg optical power (Channel 2) : 0.7859 mW / -1.05 dBm Transmit avg optical power (Channel 3) : 0.7885 mW / -1.03 dBm Transmit avg optical power (Channel 4) : 0.7985 mW / -0.98 dBm Rcvr signal avg optical power(Channel 1) : 0.9325 mW / -0.30 dBm Rcvr signal avg optical power(Channel 2) : 0.9034 mW / -0.44 dBm Rcvr signal avg optical power(Channel 3) : 0.9086 mW / -0.42 dBm Rcvr signal avg optical power(Channel 4) : 0.8885 mW / -0.51 dBm Put the associated port administratively down which will instruct the host to transition the module to low power mode: # ip link set dev swp13 down Query the power mode again: $ ethtool --show-module swp13 Module parameters for swp13: power-mode-policy auto power-mode low Verify with the data read from the EEPROM: # ethtool -m swp13 Identifier : 0x11 (QSFP28) ... Extended identifier description : 5.0W max. Power consumption, High Power Class (> 3.5 W) not enabled Power set : On Power override : On ... Transmit avg optical power (Channel 1) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 2) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 3) : 0.0000 mW / -inf dBm Transmit avg optical power (Channel 4) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 1) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 2) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 3) : 0.0000 mW / -inf dBm Rcvr signal avg optical power(Channel 4) : 0.0000 mW / -inf dBm Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 71 ++++++++++- include/linux/ethtool.h | 22 ++++ include/uapi/linux/ethtool.h | 23 ++++ include/uapi/linux/ethtool_netlink.h | 17 +++ net/ethtool/Makefile | 2 +- net/ethtool/module.c | 180 +++++++++++++++++++++++++++ net/ethtool/netlink.c | 19 +++ net/ethtool/netlink.h | 4 + 8 files changed, 335 insertions(+), 3 deletions(-) create mode 100644 net/ethtool/module.c (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d9b55b7a1a4d..d6fd4b2e243c 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -41,6 +41,11 @@ In the message structure descriptions below, if an attribute name is suffixed with "+", parent nest can contain multiple attributes of the same type. This implements an array of entries. +Attributes that need to be filled-in by device drivers and that are dumped to +user space based on whether they are valid or not should not use zero as a +valid value. This avoids the need to explicitly signal the validity of the +attribute in the device driver API. + Request header ============== @@ -179,7 +184,7 @@ according to message purpose: Userspace to kernel: - ===================================== ================================ + ===================================== ================================= ``ETHTOOL_MSG_STRSET_GET`` get string set ``ETHTOOL_MSG_LINKINFO_GET`` get link settings ``ETHTOOL_MSG_LINKINFO_SET`` set link settings @@ -213,7 +218,9 @@ Userspace to kernel: ``ETHTOOL_MSG_MODULE_EEPROM_GET`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET`` get standard statistics ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` get PHC virtual clocks info - ===================================== ================================ + ``ETHTOOL_MSG_MODULE_SET`` set transceiver module parameters + ``ETHTOOL_MSG_MODULE_GET`` get transceiver module parameters + ===================================== ================================= Kernel to userspace: @@ -252,6 +259,7 @@ Kernel to userspace: ``ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY`` read SFP module EEPROM ``ETHTOOL_MSG_STATS_GET_REPLY`` standard statistics ``ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY`` PHC virtual clocks info + ``ETHTOOL_MSG_MODULE_GET_REPLY`` transceiver module parameters ======================================== ================================= ``GET`` requests are sent by userspace applications to retrieve device @@ -1521,6 +1529,63 @@ Kernel response contents: ``ETHTOOL_A_PHC_VCLOCKS_INDEX`` s32 PHC index array ==================================== ====== ========================== +MODULE_GET +========== + +Gets transceiver module parameters. + +Request contents: + + ===================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested request header + ===================================== ====== ========================== + +Kernel response contents: + + ====================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested reply header + ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` u8 power mode policy + ``ETHTOOL_A_MODULE_POWER_MODE`` u8 operational power mode + ====================================== ====== ========================== + +The optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute encodes the +transceiver module power mode policy enforced by the host. The default policy +is driver-dependent, but "auto" is the recommended default and it should be +implemented by new drivers and drivers where conformance to a legacy behavior +is not critical. + +The optional ``ETHTHOOL_A_MODULE_POWER_MODE`` attribute encodes the operational +power mode policy of the transceiver module. It is only reported when a module +is plugged-in. Possible values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_power_mode + +MODULE_SET +========== + +Sets transceiver module parameters. + +Request contents: + + ====================================== ====== ========================== + ``ETHTOOL_A_MODULE_HEADER`` nested request header + ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` u8 power mode policy + ====================================== ====== ========================== + +When set, the optional ``ETHTOOL_A_MODULE_POWER_MODE_POLICY`` attribute is used +to set the transceiver module power policy enforced by the host. Possible +values are: + +.. kernel-doc:: include/uapi/linux/ethtool.h + :identifiers: ethtool_module_power_mode_policy + +For SFF-8636 modules, low power mode is forced by the host according to table +6-10 in revision 2.10a of the specification. + +For CMIS modules, low power mode is forced by the host according to table 6-12 +in revision 5.0 of the specification. + Request translation =================== @@ -1620,4 +1685,6 @@ are netlink only. n/a ``ETHTOOL_MSG_CABLE_TEST_TDR_ACT`` n/a ``ETHTOOL_MSG_TUNNEL_INFO_GET`` n/a ``ETHTOOL_MSG_PHC_VCLOCKS_GET`` + n/a ``ETHTOOL_MSG_MODULE_GET`` + n/a ``ETHTOOL_MSG_MODULE_SET`` =================================== ===================================== diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 849524b55d89..9adf8d2c3144 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -415,6 +415,17 @@ struct ethtool_module_eeprom { u8 *data; }; +/** + * struct ethtool_module_power_mode_params - module power mode parameters + * @policy: The power mode policy enforced by the host for the plug-in module. + * @mode: The operational power mode of the plug-in module. Should be filled by + * device drivers on get operations. + */ +struct ethtool_module_power_mode_params { + enum ethtool_module_power_mode_policy policy; + enum ethtool_module_power_mode mode; +}; + /** * struct ethtool_ops - optional netdev operations * @cap_link_lanes_supported: indicates if the driver supports lanes @@ -580,6 +591,11 @@ struct ethtool_module_eeprom { * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics. * @get_rmon_stats: Query some of the RMON (RFC 2819) statistics. * Set %ranges to a pointer to zero-terminated array of byte ranges. + * @get_module_power_mode: Get the power mode policy for the plug-in module + * used by the network device and its operational power mode, if + * plugged-in. + * @set_module_power_mode: Set the power mode policy for the plug-in module + * used by the network device. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -705,6 +721,12 @@ struct ethtool_ops { void (*get_rmon_stats)(struct net_device *dev, struct ethtool_rmon_stats *rmon_stats, const struct ethtool_rmon_hist_range **ranges); + int (*get_module_power_mode)(struct net_device *dev, + struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); + int (*set_module_power_mode)(struct net_device *dev, + const struct ethtool_module_power_mode_params *params, + struct netlink_ext_ack *extack); }; int ethtool_check_ops(const struct ethtool_ops *ops); diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index b6db6590baf0..6de61d53ca5d 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -706,6 +706,29 @@ enum ethtool_stringset { ETH_SS_COUNT }; +/** + * enum ethtool_module_power_mode_policy - plug-in module power mode policy + * @ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH: Module is always in high power mode. + * @ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO: Module is transitioned by the host + * to high power mode when the first port using it is put administratively + * up and to low power mode when the last port using it is put + * administratively down. + */ +enum ethtool_module_power_mode_policy { + ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH = 1, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO, +}; + +/** + * enum ethtool_module_power_mode - plug-in module power mode + * @ETHTOOL_MODULE_POWER_MODE_LOW: Module is in low power mode. + * @ETHTOOL_MODULE_POWER_MODE_HIGH: Module is in high power mode. + */ +enum ethtool_module_power_mode { + ETHTOOL_MODULE_POWER_MODE_LOW = 1, + ETHTOOL_MODULE_POWER_MODE_HIGH, +}; + /** * struct ethtool_gstrings - string set for data tagging * @cmd: Command number = %ETHTOOL_GSTRINGS diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index 5545f1ca9237..ca5fbb59fa42 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -47,6 +47,8 @@ enum { ETHTOOL_MSG_MODULE_EEPROM_GET, ETHTOOL_MSG_STATS_GET, ETHTOOL_MSG_PHC_VCLOCKS_GET, + ETHTOOL_MSG_MODULE_GET, + ETHTOOL_MSG_MODULE_SET, /* add new constants above here */ __ETHTOOL_MSG_USER_CNT, @@ -90,6 +92,8 @@ enum { ETHTOOL_MSG_MODULE_EEPROM_GET_REPLY, ETHTOOL_MSG_STATS_GET_REPLY, ETHTOOL_MSG_PHC_VCLOCKS_GET_REPLY, + ETHTOOL_MSG_MODULE_GET_REPLY, + ETHTOOL_MSG_MODULE_NTF, /* add new constants above here */ __ETHTOOL_MSG_KERNEL_CNT, @@ -833,6 +837,19 @@ enum { ETHTOOL_A_STATS_RMON_MAX = (__ETHTOOL_A_STATS_RMON_CNT - 1) }; +/* MODULE */ + +enum { + ETHTOOL_A_MODULE_UNSPEC, + ETHTOOL_A_MODULE_HEADER, /* nest - _A_HEADER_* */ + ETHTOOL_A_MODULE_POWER_MODE_POLICY, /* u8 */ + ETHTOOL_A_MODULE_POWER_MODE, /* u8 */ + + /* add new constants above here */ + __ETHTOOL_A_MODULE_CNT, + ETHTOOL_A_MODULE_MAX = (__ETHTOOL_A_MODULE_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 0a19470efbfb..b76432e70e6b 100644 --- a/net/ethtool/Makefile +++ b/net/ethtool/Makefile @@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK) += ethtool_nl.o ethtool_nl-y := netlink.o bitset.o strset.o linkinfo.o linkmodes.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 + tunnels.o fec.o eeprom.o stats.o phc_vclocks.o module.o diff --git a/net/ethtool/module.c b/net/ethtool/module.c new file mode 100644 index 000000000000..bc2cef11bbda --- /dev/null +++ b/net/ethtool/module.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include + +#include "netlink.h" +#include "common.h" +#include "bitset.h" + +struct module_req_info { + struct ethnl_req_info base; +}; + +struct module_reply_data { + struct ethnl_reply_data base; + struct ethtool_module_power_mode_params power; +}; + +#define MODULE_REPDATA(__reply_base) \ + container_of(__reply_base, struct module_reply_data, base) + +/* MODULE_GET */ + +const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1] = { + [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), +}; + +static int module_get_power_mode(struct net_device *dev, + struct module_reply_data *data, + struct netlink_ext_ack *extack) +{ + const struct ethtool_ops *ops = dev->ethtool_ops; + + if (!ops->get_module_power_mode) + return 0; + + return ops->get_module_power_mode(dev, &data->power, extack); +} + +static int module_prepare_data(const struct ethnl_req_info *req_base, + struct ethnl_reply_data *reply_base, + struct genl_info *info) +{ + struct module_reply_data *data = MODULE_REPDATA(reply_base); + struct netlink_ext_ack *extack = info ? info->extack : NULL; + struct net_device *dev = reply_base->dev; + int ret; + + ret = ethnl_ops_begin(dev); + if (ret < 0) + return ret; + + ret = module_get_power_mode(dev, data, extack); + if (ret < 0) + goto out_complete; + +out_complete: + ethnl_ops_complete(dev); + return ret; +} + +static int module_reply_size(const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + struct module_reply_data *data = MODULE_REPDATA(reply_base); + int len = 0; + + if (data->power.policy) + len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE_POLICY */ + + if (data->power.mode) + len += nla_total_size(sizeof(u8)); /* _MODULE_POWER_MODE */ + + return len; +} + +static int module_fill_reply(struct sk_buff *skb, + const struct ethnl_req_info *req_base, + const struct ethnl_reply_data *reply_base) +{ + const struct module_reply_data *data = MODULE_REPDATA(reply_base); + + if (data->power.policy && + nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE_POLICY, + data->power.policy)) + return -EMSGSIZE; + + if (data->power.mode && + nla_put_u8(skb, ETHTOOL_A_MODULE_POWER_MODE, data->power.mode)) + return -EMSGSIZE; + + return 0; +} + +const struct ethnl_request_ops ethnl_module_request_ops = { + .request_cmd = ETHTOOL_MSG_MODULE_GET, + .reply_cmd = ETHTOOL_MSG_MODULE_GET_REPLY, + .hdr_attr = ETHTOOL_A_MODULE_HEADER, + .req_info_size = sizeof(struct module_req_info), + .reply_data_size = sizeof(struct module_reply_data), + + .prepare_data = module_prepare_data, + .reply_size = module_reply_size, + .fill_reply = module_fill_reply, +}; + +/* MODULE_SET */ + +const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 1] = { + [ETHTOOL_A_MODULE_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy), + [ETHTOOL_A_MODULE_POWER_MODE_POLICY] = + NLA_POLICY_RANGE(NLA_U8, ETHTOOL_MODULE_POWER_MODE_POLICY_HIGH, + ETHTOOL_MODULE_POWER_MODE_POLICY_AUTO), +}; + +static int module_set_power_mode(struct net_device *dev, struct nlattr **tb, + bool *p_mod, struct netlink_ext_ack *extack) +{ + struct ethtool_module_power_mode_params power = {}; + struct ethtool_module_power_mode_params power_new; + const struct ethtool_ops *ops = dev->ethtool_ops; + int ret; + + if (!tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]) + return 0; + + if (!ops->get_module_power_mode || !ops->set_module_power_mode) { + NL_SET_ERR_MSG_ATTR(extack, + tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY], + "Setting power mode policy is not supported by this device"); + return -EOPNOTSUPP; + } + + power_new.policy = nla_get_u8(tb[ETHTOOL_A_MODULE_POWER_MODE_POLICY]); + ret = ops->get_module_power_mode(dev, &power, extack); + if (ret < 0) + return ret; + + if (power_new.policy == power.policy) + return 0; + *p_mod = true; + + return ops->set_module_power_mode(dev, &power_new, extack); +} + +int ethnl_set_module(struct sk_buff *skb, struct genl_info *info) +{ + struct ethnl_req_info req_info = {}; + struct nlattr **tb = info->attrs; + struct net_device *dev; + bool mod = false; + int ret; + + ret = ethnl_parse_header_dev_get(&req_info, tb[ETHTOOL_A_MODULE_HEADER], + genl_info_net(info), info->extack, + true); + if (ret < 0) + return ret; + dev = req_info.dev; + + rtnl_lock(); + ret = ethnl_ops_begin(dev); + if (ret < 0) + goto out_rtnl; + + ret = module_set_power_mode(dev, tb, &mod, info->extack); + if (ret < 0) + goto out_ops; + + if (!mod) + goto out_ops; + + ethtool_notify(dev, ETHTOOL_MSG_MODULE_NTF, NULL); + +out_ops: + ethnl_ops_complete(dev); +out_rtnl: + rtnl_unlock(); + dev_put(dev); + return ret; +} diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 1797a0a90019..38b44c0291b1 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -282,6 +282,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = { [ETHTOOL_MSG_MODULE_EEPROM_GET] = ðnl_module_eeprom_request_ops, [ETHTOOL_MSG_STATS_GET] = ðnl_stats_request_ops, [ETHTOOL_MSG_PHC_VCLOCKS_GET] = ðnl_phc_vclocks_request_ops, + [ETHTOOL_MSG_MODULE_GET] = ðnl_module_request_ops, }; static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb) @@ -593,6 +594,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = { [ETHTOOL_MSG_PAUSE_NTF] = ðnl_pause_request_ops, [ETHTOOL_MSG_EEE_NTF] = ðnl_eee_request_ops, [ETHTOOL_MSG_FEC_NTF] = ðnl_fec_request_ops, + [ETHTOOL_MSG_MODULE_NTF] = ðnl_module_request_ops, }; /* default notification handler */ @@ -686,6 +688,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = { [ETHTOOL_MSG_PAUSE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_EEE_NTF] = ethnl_default_notify, [ETHTOOL_MSG_FEC_NTF] = ethnl_default_notify, + [ETHTOOL_MSG_MODULE_NTF] = ethnl_default_notify, }; void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) @@ -999,6 +1002,22 @@ static const struct genl_ops ethtool_genl_ops[] = { .policy = ethnl_phc_vclocks_get_policy, .maxattr = ARRAY_SIZE(ethnl_phc_vclocks_get_policy) - 1, }, + { + .cmd = ETHTOOL_MSG_MODULE_GET, + .doit = ethnl_default_doit, + .start = ethnl_default_start, + .dumpit = ethnl_default_dumpit, + .done = ethnl_default_done, + .policy = ethnl_module_get_policy, + .maxattr = ARRAY_SIZE(ethnl_module_get_policy) - 1, + }, + { + .cmd = ETHTOOL_MSG_MODULE_SET, + .flags = GENL_UNS_ADMIN_PERM, + .doit = ethnl_set_module, + .policy = ethnl_module_set_policy, + .maxattr = ARRAY_SIZE(ethnl_module_set_policy) - 1, + }, }; static const struct genl_multicast_group ethtool_nl_mcgrps[] = { diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h index e8987e28036f..836ee7157848 100644 --- a/net/ethtool/netlink.h +++ b/net/ethtool/netlink.h @@ -337,6 +337,7 @@ extern const struct ethnl_request_ops ethnl_fec_request_ops; extern const struct ethnl_request_ops ethnl_module_eeprom_request_ops; 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 nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1]; extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1]; @@ -373,6 +374,8 @@ extern const struct nla_policy ethnl_fec_set_policy[ETHTOOL_A_FEC_AUTO + 1]; extern const struct nla_policy ethnl_module_eeprom_get_policy[ETHTOOL_A_MODULE_EEPROM_I2C_ADDRESS + 1]; extern const struct nla_policy ethnl_stats_get_policy[ETHTOOL_A_STATS_GROUPS + 1]; extern const struct nla_policy ethnl_phc_vclocks_get_policy[ETHTOOL_A_PHC_VCLOCKS_HEADER + 1]; +extern const struct nla_policy ethnl_module_get_policy[ETHTOOL_A_MODULE_HEADER + 1]; +extern const struct nla_policy ethnl_module_set_policy[ETHTOOL_A_MODULE_POWER_MODE_POLICY + 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); @@ -391,6 +394,7 @@ int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info); int ethnl_tunnel_info_start(struct netlink_callback *cb); int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb); int ethnl_set_fec(struct sk_buff *skb, struct genl_info *info); +int ethnl_set_module(struct sk_buff *skb, struct genl_info *info); extern const char stats_std_names[__ETHTOOL_STATS_CNT][ETH_GSTRING_LEN]; extern const char stats_eth_phy_names[__ETHTOOL_A_STATS_ETH_PHY_CNT][ETH_GSTRING_LEN]; -- cgit v1.2.3 From 3dfb51126064b594470b9c0b278188fbc9194709 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 6 Oct 2021 13:46:46 +0300 Subject: ethtool: Add transceiver module extended state Add an extended state and sub-state to describe link issues related to transceiver modules. The 'ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY' extended sub-state tells user space that port is unable to gain a carrier because the CMIS Module State Machine did not reach the ModuleReady (Fully Operational) state. For example, if the module is stuck at ModuleLowPwr or ModuleFault state. In case of the latter, user space can read the fault reason from the module's EEPROM and potentially reset it. Signed-off-by: Ido Schimmel Signed-off-by: Jakub Kicinski --- Documentation/networking/ethtool-netlink.rst | 10 ++++++++++ include/linux/ethtool.h | 1 + include/uapi/linux/ethtool.h | 6 ++++++ 3 files changed, 17 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst index d6fd4b2e243c..7b598c7e3912 100644 --- a/Documentation/networking/ethtool-netlink.rst +++ b/Documentation/networking/ethtool-netlink.rst @@ -528,6 +528,8 @@ Link extended states: power required from cable or module ``ETHTOOL_LINK_EXT_STATE_OVERHEAT`` The module is overheated + + ``ETHTOOL_LINK_EXT_STATE_MODULE`` Transceiver module issue ================================================ ============================================ Link extended substates: @@ -621,6 +623,14 @@ Link extended substates: ``ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE`` Cable test failure =================================================== ============================================ + Transceiver module issue substates: + + =================================================== ============================================ + ``ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY`` The CMIS Module State Machine did not reach + the ModuleReady state. For example, if the + module is stuck at ModuleFault state + =================================================== ============================================ + DEBUG_GET ========= diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 9adf8d2c3144..845a0ffc16ee 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -94,6 +94,7 @@ struct ethtool_link_ext_state_info { enum ethtool_link_ext_substate_link_logical_mismatch link_logical_mismatch; enum ethtool_link_ext_substate_bad_signal_integrity bad_signal_integrity; enum ethtool_link_ext_substate_cable_issue cable_issue; + enum ethtool_link_ext_substate_module module; u8 __link_ext_substate; }; }; diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h index 6de61d53ca5d..a2223b685451 100644 --- a/include/uapi/linux/ethtool.h +++ b/include/uapi/linux/ethtool.h @@ -603,6 +603,7 @@ enum ethtool_link_ext_state { ETHTOOL_LINK_EXT_STATE_CALIBRATION_FAILURE, ETHTOOL_LINK_EXT_STATE_POWER_BUDGET_EXCEEDED, ETHTOOL_LINK_EXT_STATE_OVERHEAT, + ETHTOOL_LINK_EXT_STATE_MODULE, }; /* More information in addition to ETHTOOL_LINK_EXT_STATE_AUTONEG. */ @@ -649,6 +650,11 @@ enum ethtool_link_ext_substate_cable_issue { ETHTOOL_LINK_EXT_SUBSTATE_CI_CABLE_TEST_FAILURE, }; +/* More information in addition to ETHTOOL_LINK_EXT_STATE_MODULE. */ +enum ethtool_link_ext_substate_module { + ETHTOOL_LINK_EXT_SUBSTATE_MODULE_CMIS_NOT_READY = 1, +}; + #define ETH_GSTRING_LEN 32 /** -- cgit v1.2.3 From bf69bad38cf63d980e8a603f8d1bd1f85b5ed3d9 Mon Sep 17 00:00:00 2001 From: André Almeida Date: Thu, 23 Sep 2021 14:11:05 -0300 Subject: futex: Implement sys_futex_waitv() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add support to wait on multiple futexes. This is the interface implemented by this syscall: futex_waitv(struct futex_waitv *waiters, unsigned int nr_futexes, unsigned int flags, struct timespec *timeout, clockid_t clockid) struct futex_waitv { __u64 val; __u64 uaddr; __u32 flags; __u32 __reserved; }; Given an array of struct futex_waitv, wait on each uaddr. The thread wakes if a futex_wake() is performed at any uaddr. The syscall returns immediately if any waiter has *uaddr != val. *timeout is an optional absolute timeout value for the operation. This syscall supports only 64bit sized timeout structs. The flags argument of the syscall should be empty, but it can be used for future extensions. Flags for shared futexes, sizes, etc. should be used on the individual flags of each waiter. __reserved is used for explicit padding and should be 0, but it might be used for future extensions. If the userspace uses 32-bit pointers, it should make sure to explicitly cast it when assigning to waitv::uaddr. Returns the array index of one of the woken futexes. There’s no given information of how many were woken, or any particular attribute of it (if it’s the first woken, if it is of the smaller index...). Signed-off-by: André Almeida Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20210923171111.300673-17-andrealmeid@collabora.com --- MAINTAINERS | 1 + include/linux/syscalls.h | 5 + include/uapi/asm-generic/unistd.h | 5 +- include/uapi/linux/futex.h | 25 +++++ kernel/futex/futex.h | 15 +++ kernel/futex/syscalls.c | 119 ++++++++++++++++++++++ kernel/futex/waitwake.c | 201 ++++++++++++++++++++++++++++++++++++++ kernel/sys_ni.c | 1 + 8 files changed, 371 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index b3094cb1afdd..310fb018acf9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -7718,6 +7718,7 @@ M: Ingo Molnar R: Peter Zijlstra R: Darren Hart R: Davidlohr Bueso +R: André Almeida L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git locking/core diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 25979682ade5..528a478dbda8 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -58,6 +58,7 @@ struct mq_attr; struct compat_stat; struct old_timeval32; struct robust_list_head; +struct futex_waitv; struct getcpu_cache; struct old_linux_dirent; struct perf_event_attr; @@ -623,6 +624,10 @@ asmlinkage long sys_get_robust_list(int pid, asmlinkage long sys_set_robust_list(struct robust_list_head __user *head, size_t len); +asmlinkage long sys_futex_waitv(struct futex_waitv *waiters, + unsigned int nr_futexes, unsigned int flags, + struct __kernel_timespec __user *timeout, clockid_t clockid); + /* kernel/hrtimer.c */ asmlinkage long sys_nanosleep(struct __kernel_timespec __user *rqtp, struct __kernel_timespec __user *rmtp); diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 1c5fb86d455a..4557a8b6086f 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -880,8 +880,11 @@ __SYSCALL(__NR_memfd_secret, sys_memfd_secret) #define __NR_process_mrelease 448 __SYSCALL(__NR_process_mrelease, sys_process_mrelease) +#define __NR_futex_waitv 449 +__SYSCALL(__NR_futex_waitv, sys_futex_waitv) + #undef __NR_syscalls -#define __NR_syscalls 449 +#define __NR_syscalls 450 /* * 32 bit systems traditionally used different diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index 235e5b2facaa..71a5df8d2689 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -43,6 +43,31 @@ #define FUTEX_CMP_REQUEUE_PI_PRIVATE (FUTEX_CMP_REQUEUE_PI | \ FUTEX_PRIVATE_FLAG) +/* + * Flags to specify the bit length of the futex word for futex2 syscalls. + * Currently, only 32 is supported. + */ +#define FUTEX_32 2 + +/* + * Max numbers of elements in a futex_waitv array + */ +#define FUTEX_WAITV_MAX 128 + +/** + * struct futex_waitv - A waiter for vectorized wait + * @val: Expected value at uaddr + * @uaddr: User address to wait on + * @flags: Flags for this waiter + * @__reserved: Reserved member to preserve data alignment. Should be 0. + */ +struct futex_waitv { + __u64 val; + __u64 uaddr; + __u32 flags; + __u32 __reserved; +}; + /* * Support for robust futexes: the kernel cleans up held futexes at * thread exit time. diff --git a/kernel/futex/futex.h b/kernel/futex/futex.h index 465f7bd5caef..948fcf317681 100644 --- a/kernel/futex/futex.h +++ b/kernel/futex/futex.h @@ -268,6 +268,21 @@ extern int futex_requeue(u32 __user *uaddr1, unsigned int flags, extern int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val, ktime_t *abs_time, u32 bitset); +/** + * struct futex_vector - Auxiliary struct for futex_waitv() + * @w: Userspace provided data + * @q: Kernel side data + * + * Struct used to build an array with all data need for futex_waitv() + */ +struct futex_vector { + struct futex_waitv w; + struct futex_q q; +}; + +extern int futex_wait_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to); + extern int futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset); extern int futex_wake_op(u32 __user *uaddr1, unsigned int flags, diff --git a/kernel/futex/syscalls.c b/kernel/futex/syscalls.c index 6e7e36c640a1..6f91a07a6a83 100644 --- a/kernel/futex/syscalls.c +++ b/kernel/futex/syscalls.c @@ -199,6 +199,125 @@ SYSCALL_DEFINE6(futex, u32 __user *, uaddr, int, op, u32, val, return do_futex(uaddr, op, val, tp, uaddr2, (unsigned long)utime, val3); } +/* Mask of available flags for each futex in futex_waitv list */ +#define FUTEXV_WAITER_MASK (FUTEX_32 | FUTEX_PRIVATE_FLAG) + +/** + * futex_parse_waitv - Parse a waitv array from userspace + * @futexv: Kernel side list of waiters to be filled + * @uwaitv: Userspace list to be parsed + * @nr_futexes: Length of futexv + * + * Return: Error code on failure, 0 on success + */ +static int futex_parse_waitv(struct futex_vector *futexv, + struct futex_waitv __user *uwaitv, + unsigned int nr_futexes) +{ + struct futex_waitv aux; + unsigned int i; + + for (i = 0; i < nr_futexes; i++) { + if (copy_from_user(&aux, &uwaitv[i], sizeof(aux))) + return -EFAULT; + + if ((aux.flags & ~FUTEXV_WAITER_MASK) || aux.__reserved) + return -EINVAL; + + if (!(aux.flags & FUTEX_32)) + return -EINVAL; + + futexv[i].w.flags = aux.flags; + futexv[i].w.val = aux.val; + futexv[i].w.uaddr = aux.uaddr; + futexv[i].q = futex_q_init; + } + + return 0; +} + +/** + * sys_futex_waitv - Wait on a list of futexes + * @waiters: List of futexes to wait on + * @nr_futexes: Length of futexv + * @flags: Flag for timeout (monotonic/realtime) + * @timeout: Optional absolute timeout. + * @clockid: Clock to be used for the timeout, realtime or monotonic. + * + * Given an array of `struct futex_waitv`, wait on each uaddr. The thread wakes + * if a futex_wake() is performed at any uaddr. The syscall returns immediately + * if any waiter has *uaddr != val. *timeout is an optional timeout value for + * the operation. Each waiter has individual flags. The `flags` argument for + * the syscall should be used solely for specifying the timeout as realtime, if + * needed. Flags for private futexes, sizes, etc. should be used on the + * individual flags of each waiter. + * + * Returns the array index of one of the woken futexes. No further information + * is provided: any number of other futexes may also have been woken by the + * same event, and if more than one futex was woken, the retrned index may + * refer to any one of them. (It is not necessaryily the futex with the + * smallest index, nor the one most recently woken, nor...) + */ + +SYSCALL_DEFINE5(futex_waitv, struct futex_waitv __user *, waiters, + unsigned int, nr_futexes, unsigned int, flags, + struct __kernel_timespec __user *, timeout, clockid_t, clockid) +{ + struct hrtimer_sleeper to; + struct futex_vector *futexv; + struct timespec64 ts; + ktime_t time; + int ret; + + /* This syscall supports no flags for now */ + if (flags) + return -EINVAL; + + if (!nr_futexes || nr_futexes > FUTEX_WAITV_MAX || !waiters) + return -EINVAL; + + if (timeout) { + int flag_clkid = 0, flag_init = 0; + + if (clockid == CLOCK_REALTIME) { + flag_clkid = FLAGS_CLOCKRT; + flag_init = FUTEX_CLOCK_REALTIME; + } + + if (clockid != CLOCK_REALTIME && clockid != CLOCK_MONOTONIC) + return -EINVAL; + + if (get_timespec64(&ts, timeout)) + return -EFAULT; + + /* + * Since there's no opcode for futex_waitv, use + * FUTEX_WAIT_BITSET that uses absolute timeout as well + */ + ret = futex_init_timeout(FUTEX_WAIT_BITSET, flag_init, &ts, &time); + if (ret) + return ret; + + futex_setup_timer(&time, &to, flag_clkid, 0); + } + + futexv = kcalloc(nr_futexes, sizeof(*futexv), GFP_KERNEL); + if (!futexv) + return -ENOMEM; + + ret = futex_parse_waitv(futexv, waiters, nr_futexes); + if (!ret) + ret = futex_wait_multiple(futexv, nr_futexes, timeout ? &to : NULL); + + if (timeout) { + hrtimer_cancel(&to.timer); + destroy_hrtimer_on_stack(&to.timer); + } + + kfree(futexv); + return ret; +} + #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(set_robust_list, struct compat_robust_list_head __user *, head, diff --git a/kernel/futex/waitwake.c b/kernel/futex/waitwake.c index 36880784aa11..4ce0923f1ce3 100644 --- a/kernel/futex/waitwake.c +++ b/kernel/futex/waitwake.c @@ -357,6 +357,207 @@ void futex_wait_queue(struct futex_hash_bucket *hb, struct futex_q *q, __set_current_state(TASK_RUNNING); } +/** + * unqueue_multiple - Remove various futexes from their hash bucket + * @v: The list of futexes to unqueue + * @count: Number of futexes in the list + * + * Helper to unqueue a list of futexes. This can't fail. + * + * Return: + * - >=0 - Index of the last futex that was awoken; + * - -1 - No futex was awoken + */ +static int unqueue_multiple(struct futex_vector *v, int count) +{ + int ret = -1, i; + + for (i = 0; i < count; i++) { + if (!futex_unqueue(&v[i].q)) + ret = i; + } + + return ret; +} + +/** + * futex_wait_multiple_setup - Prepare to wait and enqueue multiple futexes + * @vs: The futex list to wait on + * @count: The size of the list + * @woken: Index of the last woken futex, if any. Used to notify the + * caller that it can return this index to userspace (return parameter) + * + * Prepare multiple futexes in a single step and enqueue them. This may fail if + * the futex list is invalid or if any futex was already awoken. On success the + * task is ready to interruptible sleep. + * + * Return: + * - 1 - One of the futexes was woken by another thread + * - 0 - Success + * - <0 - -EFAULT, -EWOULDBLOCK or -EINVAL + */ +static int futex_wait_multiple_setup(struct futex_vector *vs, int count, int *woken) +{ + struct futex_hash_bucket *hb; + bool retry = false; + int ret, i; + u32 uval; + + /* + * Enqueuing multiple futexes is tricky, because we need to enqueue + * each futex on the list before dealing with the next one to avoid + * deadlocking on the hash bucket. But, before enqueuing, we need to + * make sure that current->state is TASK_INTERRUPTIBLE, so we don't + * lose any wake events, which cannot be done before the get_futex_key + * of the next key, because it calls get_user_pages, which can sleep. + * Thus, we fetch the list of futexes keys in two steps, by first + * pinning all the memory keys in the futex key, and only then we read + * each key and queue the corresponding futex. + * + * Private futexes doesn't need to recalculate hash in retry, so skip + * get_futex_key() when retrying. + */ +retry: + for (i = 0; i < count; i++) { + if ((vs[i].w.flags & FUTEX_PRIVATE_FLAG) && retry) + continue; + + ret = get_futex_key(u64_to_user_ptr(vs[i].w.uaddr), + !(vs[i].w.flags & FUTEX_PRIVATE_FLAG), + &vs[i].q.key, FUTEX_READ); + + if (unlikely(ret)) + return ret; + } + + set_current_state(TASK_INTERRUPTIBLE); + + for (i = 0; i < count; i++) { + u32 __user *uaddr = (u32 __user *)(unsigned long)vs[i].w.uaddr; + struct futex_q *q = &vs[i].q; + u32 val = (u32)vs[i].w.val; + + hb = futex_q_lock(q); + ret = futex_get_value_locked(&uval, uaddr); + + if (!ret && uval == val) { + /* + * The bucket lock can't be held while dealing with the + * next futex. Queue each futex at this moment so hb can + * be unlocked. + */ + futex_queue(q, hb); + continue; + } + + futex_q_unlock(hb); + __set_current_state(TASK_RUNNING); + + /* + * Even if something went wrong, if we find out that a futex + * was woken, we don't return error and return this index to + * userspace + */ + *woken = unqueue_multiple(vs, i); + if (*woken >= 0) + return 1; + + if (ret) { + /* + * If we need to handle a page fault, we need to do so + * without any lock and any enqueued futex (otherwise + * we could lose some wakeup). So we do it here, after + * undoing all the work done so far. In success, we + * retry all the work. + */ + if (get_user(uval, uaddr)) + return -EFAULT; + + retry = true; + goto retry; + } + + if (uval != val) + return -EWOULDBLOCK; + } + + return 0; +} + +/** + * futex_sleep_multiple - Check sleeping conditions and sleep + * @vs: List of futexes to wait for + * @count: Length of vs + * @to: Timeout + * + * Sleep if and only if the timeout hasn't expired and no futex on the list has + * been woken up. + */ +static void futex_sleep_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to) +{ + if (to && !to->task) + return; + + for (; count; count--, vs++) { + if (!READ_ONCE(vs->q.lock_ptr)) + return; + } + + freezable_schedule(); +} + +/** + * futex_wait_multiple - Prepare to wait on and enqueue several futexes + * @vs: The list of futexes to wait on + * @count: The number of objects + * @to: Timeout before giving up and returning to userspace + * + * Entry point for the FUTEX_WAIT_MULTIPLE futex operation, this function + * sleeps on a group of futexes and returns on the first futex that is + * wake, or after the timeout has elapsed. + * + * Return: + * - >=0 - Hint to the futex that was awoken + * - <0 - On error + */ +int futex_wait_multiple(struct futex_vector *vs, unsigned int count, + struct hrtimer_sleeper *to) +{ + int ret, hint = 0; + + if (to) + hrtimer_sleeper_start_expires(to, HRTIMER_MODE_ABS); + + while (1) { + ret = futex_wait_multiple_setup(vs, count, &hint); + if (ret) { + if (ret > 0) { + /* A futex was woken during setup */ + ret = hint; + } + return ret; + } + + futex_sleep_multiple(vs, count, to); + + __set_current_state(TASK_RUNNING); + + ret = unqueue_multiple(vs, count); + if (ret >= 0) + return ret; + + if (to && !to->task) + return -ETIMEDOUT; + else if (signal_pending(current)) + return -ERESTARTSYS; + /* + * The final case is a spurious wakeup, for + * which just retry. + */ + } +} + /** * futex_wait_setup() - Prepare to wait on a futex * @uaddr: the futex userspace address diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 13ee8334ab6e..d1944258cfc0 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -150,6 +150,7 @@ COND_SYSCALL(set_robust_list); COND_SYSCALL_COMPAT(set_robust_list); COND_SYSCALL(get_robust_list); COND_SYSCALL_COMPAT(get_robust_list); +COND_SYSCALL(futex_waitv); /* kernel/hrtimer.c */ -- cgit v1.2.3 From 460275f124fb072dca218a6b43b6370eebbab20d Mon Sep 17 00:00:00 2001 From: Pali Rohár Date: Tue, 5 Oct 2021 20:09:40 +0200 Subject: PCI: Add PCI_EXP_DEVCTL_PAYLOAD_* macros MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Define a macro PCI_EXP_DEVCTL_PAYLOAD_* for every possible Max Payload Size in linux/pci_regs.h, in the same style as PCI_EXP_DEVCTL_READRQ_*. Link: https://lore.kernel.org/r/20211005180952.6812-2-kabel@kernel.org Signed-off-by: Pali Rohár Signed-off-by: Marek Behún Signed-off-by: Lorenzo Pieralisi Reviewed-by: Marek Behún Reviewed-by: Bjorn Helgaas --- include/uapi/linux/pci_regs.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index e709ae8235e7..ff6ccbc6efe9 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -504,6 +504,12 @@ #define PCI_EXP_DEVCTL_URRE 0x0008 /* Unsupported Request Reporting En. */ #define PCI_EXP_DEVCTL_RELAX_EN 0x0010 /* Enable relaxed ordering */ #define PCI_EXP_DEVCTL_PAYLOAD 0x00e0 /* Max_Payload_Size */ +#define PCI_EXP_DEVCTL_PAYLOAD_128B 0x0000 /* 128 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_256B 0x0020 /* 256 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_512B 0x0040 /* 512 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_1024B 0x0060 /* 1024 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_2048B 0x0080 /* 2048 Bytes */ +#define PCI_EXP_DEVCTL_PAYLOAD_4096B 0x00a0 /* 4096 Bytes */ #define PCI_EXP_DEVCTL_EXT_TAG 0x0100 /* Extended Tag Field Enable */ #define PCI_EXP_DEVCTL_PHANTOM 0x0200 /* Phantom Functions Enable */ #define PCI_EXP_DEVCTL_AUX_PME 0x0400 /* Auxiliary Power PM Enable */ -- cgit v1.2.3 From 4c1e34c0dbffb17accdfe16ac97ab432df9024ff Mon Sep 17 00:00:00 2001 From: Richard Palethorpe Date: Fri, 8 Oct 2021 11:00:53 +0100 Subject: vsock: Enable y2038 safe timeval for timeout Reuse the timeval compat code from core/sock to handle 32-bit and 64-bit timeval structures. Also introduce a new socket option define to allow using y2038 safe timeval under 32-bit. The existing behavior of sock_set_timeout and vsock's timeout setter differ when the time value is out of bounds. vsocks current behavior is retained at the expense of not being able to share the full implementation. This allows the LTP test vsock01 to pass under 32-bit compat mode. Fixes: fe0c72f3db11 ("socket: move compat timeout handling into sock.c") Signed-off-by: Richard Palethorpe Cc: Richard Palethorpe Reviewed-by: Arnd Bergmann Signed-off-by: David S. Miller --- include/net/sock.h | 4 ++++ include/uapi/linux/vm_sockets.h | 13 ++++++++++++- net/core/sock.c | 35 ++++++++++++++++++++++++----------- net/vmw_vsock/af_vsock.c | 25 +++++++++++++++---------- 4 files changed, 55 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/sock.h b/include/net/sock.h index caaec7c55e8e..d08ab55fa4a0 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2836,4 +2836,8 @@ void sock_set_sndtimeo(struct sock *sk, s64 secs); int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len); +int sock_get_timeout(long timeo, void *optval, bool old_timeval); +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval); + #endif /* _SOCK_H */ diff --git a/include/uapi/linux/vm_sockets.h b/include/uapi/linux/vm_sockets.h index 46918a1852d7..c60ca33eac59 100644 --- a/include/uapi/linux/vm_sockets.h +++ b/include/uapi/linux/vm_sockets.h @@ -64,7 +64,7 @@ * timeout for a STREAM socket. */ -#define SO_VM_SOCKETS_CONNECT_TIMEOUT 6 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD 6 /* Option name for using non-blocking send/receive. Use as the option name * for setsockopt(3) or getsockopt(3) to set or get the non-blocking @@ -81,6 +81,17 @@ #define SO_VM_SOCKETS_NONBLOCK_TXRX 7 +#define SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW 8 + +#if !defined(__KERNEL__) +#if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) +#define SO_VM_SOCKETS_CONNECT_TIMEOUT SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD +#else +#define SO_VM_SOCKETS_CONNECT_TIMEOUT \ + (sizeof(time_t) == sizeof(__kernel_long_t) ? SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD : SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW) +#endif +#endif + /* The vSocket equivalent of INADDR_ANY. This works for the svm_cid field of * sockaddr_vm and indicates the context ID of the current endpoint. */ diff --git a/net/core/sock.c b/net/core/sock.c index beda31764df9..9862eefce21e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -350,7 +350,7 @@ void sk_error_report(struct sock *sk) } EXPORT_SYMBOL(sk_error_report); -static int sock_get_timeout(long timeo, void *optval, bool old_timeval) +int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -379,12 +379,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } +EXPORT_SYMBOL(sock_get_timeout); -static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, - bool old_timeval) +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval) { - struct __kernel_sock_timeval tv; - if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; @@ -393,8 +392,8 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; - tv.tv_sec = tv32.tv_sec; - tv.tv_usec = tv32.tv_usec; + tv->tv_sec = tv32.tv_sec; + tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; @@ -402,14 +401,28 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; - tv.tv_sec = old_tv.tv_sec; - tv.tv_usec = old_tv.tv_usec; + tv->tv_sec = old_tv.tv_sec; + tv->tv_usec = old_tv.tv_usec; } else { - if (optlen < sizeof(tv)) + if (optlen < sizeof(*tv)) return -EINVAL; - if (copy_from_sockptr(&tv, optval, sizeof(tv))) + if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } + + return 0; +} +EXPORT_SYMBOL(sock_copy_user_timeval); + +static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, + bool old_timeval) +{ + struct __kernel_sock_timeval tv; + int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + + if (err) + return err; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 9d0de37b9ec0..7d851eb3a683 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1614,13 +1614,18 @@ static int vsock_connectible_setsockopt(struct socket *sock, vsock_update_buffer_size(vsk, transport, vsk->buffer_size); break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct __kernel_old_timeval tv; - COPY_IN(tv); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: { + struct __kernel_sock_timeval tv; + + err = sock_copy_user_timeval(&tv, optval, optlen, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); + if (err) + break; if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { vsk->connect_timeout = tv.tv_sec * HZ + - DIV_ROUND_UP(tv.tv_usec, (1000000 / HZ)); + DIV_ROUND_UP((unsigned long)tv.tv_usec, (USEC_PER_SEC / HZ)); if (vsk->connect_timeout == 0) vsk->connect_timeout = VSOCK_DEFAULT_CONNECT_TIMEOUT; @@ -1653,7 +1658,9 @@ static int vsock_connectible_getsockopt(struct socket *sock, union { u64 val64; + struct old_timeval32 tm32; struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; } v; int lv = sizeof(v.val64); @@ -1680,12 +1687,10 @@ static int vsock_connectible_getsockopt(struct socket *sock, v.val64 = vsk->buffer_min_size; break; - case SO_VM_SOCKETS_CONNECT_TIMEOUT: - lv = sizeof(v.tm); - v.tm.tv_sec = vsk->connect_timeout / HZ; - v.tm.tv_usec = - (vsk->connect_timeout - - v.tm.tv_sec * HZ) * (1000000 / HZ); + case SO_VM_SOCKETS_CONNECT_TIMEOUT_NEW: + case SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD: + lv = sock_get_timeout(vsk->connect_timeout, &v, + optname == SO_VM_SOCKETS_CONNECT_TIMEOUT_OLD); break; default: -- cgit v1.2.3 From 2c611ad97a82b51221bb0920cc6cac0b1d4c0e52 Mon Sep 17 00:00:00 2001 From: Roopa Prabhu Date: Mon, 11 Oct 2021 14:12:37 +0200 Subject: net, neigh: Extend neigh->flags to 32 bit to allow for extensions Currently, all bits in struct ndmsg's ndm_flags are used up with the most recent addition of 435f2e7cc0b7 ("net: bridge: add support for sticky fdb entries"). This makes it impossible to extend the neighboring subsystem with new NTF_* flags: struct ndmsg { __u8 ndm_family; __u8 ndm_pad1; __u16 ndm_pad2; __s32 ndm_ifindex; __u16 ndm_state; __u8 ndm_flags; __u8 ndm_type; }; There are ndm_pad{1,2} attributes which are not used. However, due to uncareful design, the kernel does not enforce them to be zero upon new neighbor entry addition, and given they've been around forever, it is not possible to reuse them today due to risk of breakage. One option to overcome this limitation is to add a new NDA_FLAGS_EXT attribute for extended flags. In struct neighbour, there is a 3 byte hole between protocol and ha_lock, which allows neigh->flags to be extended from 8 to 32 bits while still being on the same cacheline as before. This also allows for all future NTF_* flags being in neigh->flags rather than yet another flags field. Unknown flags in NDA_FLAGS_EXT will be rejected by the kernel. Co-developed-by: Daniel Borkmann Signed-off-by: Daniel Borkmann Signed-off-by: Roopa Prabhu Signed-off-by: David S. Miller --- include/net/neighbour.h | 14 +++++++---- include/uapi/linux/neighbour.h | 1 + net/core/neighbour.c | 55 ++++++++++++++++++++++++++++++------------ 3 files changed, 50 insertions(+), 20 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index eb2a7c03a5b0..26d4ada0aea9 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -144,11 +144,11 @@ struct neighbour { struct timer_list timer; unsigned long used; atomic_t probes; - __u8 flags; - __u8 nud_state; - __u8 type; - __u8 dead; + u8 nud_state; + u8 type; + u8 dead; u8 protocol; + u32 flags; seqlock_t ha_lock; unsigned char ha[ALIGN(MAX_ADDR_LEN, sizeof(unsigned long))] __aligned(8); struct hh_cache hh; @@ -172,7 +172,7 @@ struct pneigh_entry { struct pneigh_entry *next; possible_net_t net; struct net_device *dev; - u8 flags; + u32 flags; u8 protocol; u8 key[]; }; @@ -258,6 +258,10 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 +/* In-kernel representation for NDA_FLAGS_EXT flags: */ +#define NTF_OLD_MASK 0xff +#define NTF_EXT_SHIFT 8 + extern const struct nla_policy nda_policy[]; static inline bool neigh_key_eq16(const struct neighbour *n, const void *pkey) diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index 00a60695fa53..a80cca141855 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -31,6 +31,7 @@ enum { NDA_PROTOCOL, /* Originator of entry */ NDA_NH_ID, NDA_FDB_EXT_ATTRS, + NDA_FLAGS_EXT, __NDA_MAX }; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 3e58037a8ae6..5245e888c981 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -159,7 +159,7 @@ static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, int *notify) { bool rc = false; - u8 ndm_flags; + u32 ndm_flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) return rc; @@ -379,7 +379,7 @@ EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, - u8 flags, bool exempt_from_gc) + u32 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -578,7 +578,7 @@ EXPORT_SYMBOL(neigh_lookup_nodev); static struct neighbour * ___neigh_create(struct neigh_table *tbl, const void *pkey, - struct net_device *dev, u8 flags, + struct net_device *dev, u32 flags, bool exempt_from_gc, bool want_ref) { u32 hash_val, key_len = tbl->key_len; @@ -1789,6 +1789,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, + [NDA_FLAGS_EXT] = { .type = NLA_U32 }, [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; @@ -1861,7 +1862,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_OVERRIDE_ISROUTER; + NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1870,6 +1871,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; + u32 ndm_flags; int err; ASSERT_RTNL(); @@ -1885,6 +1887,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } ndm = nlmsg_data(nlh); + ndm_flags = ndm->ndm_flags; + if (tb[NDA_FLAGS_EXT]) { + u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext & ~0) { + NL_SET_ERR_MSG(extack, "Invalid extended flags"); + goto out; + } + ndm_flags |= (ext << NTF_EXT_SHIFT); + } if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { @@ -1912,14 +1924,13 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); - - if (ndm->ndm_flags & NTF_PROXY) { + if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { - pn->flags = ndm->ndm_flags; + pn->flags = ndm_flags; if (protocol) pn->protocol = protocol; err = 0; @@ -1947,9 +1958,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || - ndm->ndm_flags & NTF_EXT_LEARNED; + ndm_flags & NTF_EXT_LEARNED; neigh = ___neigh_create(tbl, dst, dev, - ndm->ndm_flags & NTF_EXT_LEARNED, + ndm_flags & NTF_EXT_LEARNED, exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); @@ -1969,16 +1980,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (protocol) neigh->protocol = protocol; - if (ndm->ndm_flags & NTF_EXT_LEARNED) + if (ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; - if (ndm->ndm_flags & NTF_ROUTER) + if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; - if (ndm->ndm_flags & NTF_USE) + if (ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (!err && ndm->ndm_flags & NTF_USE) { + if (!err && ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; } @@ -2433,6 +2444,7 @@ out: static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { + u32 neigh_flags, neigh_flags_ext; unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -2442,11 +2454,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = neigh->flags >> NTF_EXT_SHIFT; + neigh_flags = neigh->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = neigh->flags; + ndm->ndm_flags = neigh_flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; @@ -2477,6 +2492,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2490,6 +2507,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { + u32 neigh_flags, neigh_flags_ext; struct nlmsghdr *nlh; struct ndmsg *ndm; @@ -2497,11 +2515,14 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT; + neigh_flags = pn->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_flags = neigh_flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; @@ -2511,6 +2532,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2826,6 +2849,7 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } @@ -2854,6 +2878,7 @@ static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } -- cgit v1.2.3 From 7482e3841d520a368426ac196720601687e2dc47 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 11 Oct 2021 14:12:38 +0200 Subject: net, neigh: Add NTF_MANAGED flag for managed neighbor entries Allow a user space control plane to insert entries with a new NTF_EXT_MANAGED flag. The flag then indicates to the kernel that the neighbor entry should be periodically probed for keeping the entry in NUD_REACHABLE state iff possible. The use case for this is targeting XDP or tc BPF load-balancers which use the bpf_fib_lookup() BPF helper in order to piggyback on neighbor resolution for their backends. Given they cannot be resolved in fast-path, a control plane inserts the L3 (without L2) entries manually into the neighbor table and lets the kernel do the neighbor resolution either on the gateway or on the backend directly in case the latter resides in the same L2. This avoids to deal with L2 in the control plane and to rebuild what the kernel already does best anyway. NTF_EXT_MANAGED can be combined with NTF_EXT_LEARNED in order to avoid GC eviction. The kernel then adds NTF_MANAGED flagged entries to a per-neighbor table which gets triggered by the system work queue to periodically call neigh_event_send() for performing the resolution. The implementation allows migration from/to NTF_MANAGED neighbor entries, so that already existing entries can be converted by the control plane if needed. Potentially, we could make the interval for periodically calling neigh_event_send() configurable; right now it's set to DELAY_PROBE_TIME which is also in line with mlxsw which has similar driver-internal infrastructure c723c735fa6b ("mlxsw: spectrum_router: Periodically update the kernel's neigh table"). In future, the latter could possibly reuse the NTF_MANAGED neighbors as well. Example: # ./ip/ip n replace 192.168.178.30 dev enp5s0 managed extern_learn # ./ip/ip n 192.168.178.30 dev enp5s0 lladdr f4:8c:50:5e:71:9a managed extern_learn REACHABLE [...] Signed-off-by: Daniel Borkmann Acked-by: Roopa Prabhu Link: https://linuxplumbersconf.org/event/11/contributions/953/ Signed-off-by: David S. Miller --- include/net/neighbour.h | 21 +++++--- include/uapi/linux/neighbour.h | 34 +++++++++---- net/core/neighbour.c | 113 ++++++++++++++++++++++++++++++----------- 3 files changed, 120 insertions(+), 48 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/neighbour.h b/include/net/neighbour.h index 26d4ada0aea9..e8e48be66755 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -155,6 +155,7 @@ struct neighbour { int (*output)(struct neighbour *, struct sk_buff *); const struct neigh_ops *ops; struct list_head gc_list; + struct list_head managed_list; struct rcu_head rcu; struct net_device *dev; u8 primary_key[0]; @@ -216,11 +217,13 @@ struct neigh_table { int gc_thresh3; unsigned long last_flush; struct delayed_work gc_work; + struct delayed_work managed_work; struct timer_list proxy_timer; struct sk_buff_head proxy_queue; atomic_t entries; atomic_t gc_entries; struct list_head gc_list; + struct list_head managed_list; rwlock_t lock; unsigned long last_rand; struct neigh_statistics __percpu *stats; @@ -250,17 +253,21 @@ static inline void *neighbour_priv(const struct neighbour *n) } /* flags for neigh_update() */ -#define NEIGH_UPDATE_F_OVERRIDE 0x00000001 -#define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 -#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 -#define NEIGH_UPDATE_F_USE 0x10000000 -#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 -#define NEIGH_UPDATE_F_ISROUTER 0x40000000 -#define NEIGH_UPDATE_F_ADMIN 0x80000000 +#define NEIGH_UPDATE_F_OVERRIDE BIT(0) +#define NEIGH_UPDATE_F_WEAK_OVERRIDE BIT(1) +#define NEIGH_UPDATE_F_OVERRIDE_ISROUTER BIT(2) +#define NEIGH_UPDATE_F_USE BIT(3) +#define NEIGH_UPDATE_F_MANAGED BIT(4) +#define NEIGH_UPDATE_F_EXT_LEARNED BIT(5) +#define NEIGH_UPDATE_F_ISROUTER BIT(6) +#define NEIGH_UPDATE_F_ADMIN BIT(7) /* In-kernel representation for NDA_FLAGS_EXT flags: */ #define NTF_OLD_MASK 0xff #define NTF_EXT_SHIFT 8 +#define NTF_EXT_MASK (NTF_EXT_MANAGED) + +#define NTF_MANAGED (NTF_EXT_MANAGED << NTF_EXT_SHIFT) extern const struct nla_policy nda_policy[]; diff --git a/include/uapi/linux/neighbour.h b/include/uapi/linux/neighbour.h index a80cca141855..db05fb55055e 100644 --- a/include/uapi/linux/neighbour.h +++ b/include/uapi/linux/neighbour.h @@ -41,14 +41,16 @@ enum { * Neighbor Cache Entry Flags */ -#define NTF_USE 0x01 -#define NTF_SELF 0x02 -#define NTF_MASTER 0x04 -#define NTF_PROXY 0x08 /* == ATF_PUBL */ -#define NTF_EXT_LEARNED 0x10 -#define NTF_OFFLOADED 0x20 -#define NTF_STICKY 0x40 -#define NTF_ROUTER 0x80 +#define NTF_USE (1 << 0) +#define NTF_SELF (1 << 1) +#define NTF_MASTER (1 << 2) +#define NTF_PROXY (1 << 3) /* == ATF_PUBL */ +#define NTF_EXT_LEARNED (1 << 4) +#define NTF_OFFLOADED (1 << 5) +#define NTF_STICKY (1 << 6) +#define NTF_ROUTER (1 << 7) +/* Extended flags under NDA_FLAGS_EXT: */ +#define NTF_EXT_MANAGED (1 << 0) /* * Neighbor Cache Entry States. @@ -66,12 +68,22 @@ enum { #define NUD_PERMANENT 0x80 #define NUD_NONE 0x00 -/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change - * and make no address resolution or NUD. - * NUD_PERMANENT also cannot be deleted by garbage collectors. +/* NUD_NOARP & NUD_PERMANENT are pseudostates, they never change and make no + * address resolution or NUD. + * + * NUD_PERMANENT also cannot be deleted by garbage collectors. This holds true + * for dynamic entries with NTF_EXT_LEARNED flag as well. However, upon carrier + * down event, NUD_PERMANENT entries are not flushed whereas NTF_EXT_LEARNED + * flagged entries explicitly are (which is also consistent with the routing + * subsystem). + * * When NTF_EXT_LEARNED is set for a bridge fdb entry the different cache entry * states don't make sense and thus are ignored. Such entries don't age and * can roam. + * + * 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. */ struct nda_cacheinfo { diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5245e888c981..eae73efa9245 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,6 +122,8 @@ static void neigh_mark_dead(struct neighbour *n) list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } + if (!list_empty(&n->managed_list)) + list_del_init(&n->managed_list); } static void neigh_update_gc_list(struct neighbour *n) @@ -130,7 +132,6 @@ static void neigh_update_gc_list(struct neighbour *n) write_lock_bh(&n->tbl->lock); write_lock(&n->lock); - if (n->dead) goto out; @@ -149,32 +150,59 @@ static void neigh_update_gc_list(struct neighbour *n) list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } +out: + write_unlock(&n->lock); + write_unlock_bh(&n->tbl->lock); +} + +static void neigh_update_managed_list(struct neighbour *n) +{ + bool on_managed_list, add_to_managed; + + write_lock_bh(&n->tbl->lock); + write_lock(&n->lock); + if (n->dead) + goto out; + + add_to_managed = n->flags & NTF_MANAGED; + on_managed_list = !list_empty(&n->managed_list); + if (!add_to_managed && on_managed_list) + list_del_init(&n->managed_list); + else if (add_to_managed && !on_managed_list) + list_add_tail(&n->managed_list, &n->tbl->managed_list); out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } -static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, - int *notify) +static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, + bool *gc_update, bool *managed_update) { - bool rc = false; - u32 ndm_flags; + u32 ndm_flags, old_flags = neigh->flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) - return rc; + return; + + ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0; - ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; - if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; - rc = true; *notify = 1; + *gc_update = true; + } + if ((old_flags ^ ndm_flags) & NTF_MANAGED) { + if (ndm_flags & NTF_MANAGED) + neigh->flags |= NTF_MANAGED; + else + neigh->flags &= ~NTF_MANAGED; + *notify = 1; + *managed_update = true; } - - return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, @@ -422,6 +450,7 @@ do_alloc: refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); + INIT_LIST_HEAD(&n->managed_list); atomic_inc(&tbl->entries); out: @@ -650,7 +679,8 @@ ___neigh_create(struct neigh_table *tbl, const void *pkey, n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); - + if (n->flags & NTF_MANAGED) + list_add_tail(&n->managed_list, &n->tbl->managed_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, @@ -1205,8 +1235,6 @@ static void neigh_update_hhs(struct neighbour *neigh) } } - - /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. @@ -1218,6 +1246,7 @@ static void neigh_update_hhs(struct neighbour *neigh) if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. NEIGH_UPDATE_F_USE means that the entry is user triggered. + NEIGH_UPDATE_F_MANAGED means that the entry will be auto-refreshed. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as @@ -1225,17 +1254,15 @@ static void neigh_update_hhs(struct neighbour *neigh) Caller MUST hold reference count on the entry. */ - static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { - bool ext_learn_change = false; - u8 old; - int err; - int notify = 0; - struct net_device *dev; + bool gc_update = false, managed_update = false; int update_isrouter = 0; + struct net_device *dev; + int err, notify = 0; + u8 old; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); @@ -1254,8 +1281,8 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, (old & (NUD_NOARP | NUD_PERMANENT))) goto out; - ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); - if (flags & NEIGH_UPDATE_F_USE) { + neigh_update_flags(neigh, flags, ¬ify, &gc_update, &managed_update); + if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) { new = old & ~NUD_PERMANENT; neigh->nud_state = new; err = 0; @@ -1405,15 +1432,13 @@ out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); - - if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) + if (((new ^ old) & NUD_PERMANENT) || gc_update) neigh_update_gc_list(neigh); - + if (managed_update) + neigh_update_managed_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); - trace_neigh_update_done(neigh, err); - return err; } @@ -1539,6 +1564,20 @@ int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) } EXPORT_SYMBOL(neigh_direct_output); +static void neigh_managed_work(struct work_struct *work) +{ + struct neigh_table *tbl = container_of(work, struct neigh_table, + managed_work.work); + struct neighbour *neigh; + + write_lock_bh(&tbl->lock); + list_for_each_entry(neigh, &tbl->managed_list, managed_list) + neigh_event_send(neigh, NULL); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, + NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); + write_unlock_bh(&tbl->lock); +} + static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); @@ -1685,6 +1724,8 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); + INIT_LIST_HEAD(&tbl->managed_list); + list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); @@ -1716,9 +1757,13 @@ void neigh_table_init(int index, struct neigh_table *tbl) WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); + INIT_DEFERRABLE_WORK(&tbl->managed_work, neigh_managed_work); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, 0); + timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1891,7 +1936,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_FLAGS_EXT]) { u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); - if (ext & ~0) { + if (ext & ~NTF_EXT_MASK) { NL_SET_ERR_MSG(extack, "Invalid extended flags"); goto out; } @@ -1927,6 +1972,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; + if (ndm_flags & NTF_MANAGED) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); + goto out; + } + err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { @@ -1960,7 +2010,8 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || ndm_flags & NTF_EXT_LEARNED; neigh = ___neigh_create(tbl, dst, dev, - ndm_flags & NTF_EXT_LEARNED, + ndm_flags & + (NTF_EXT_LEARNED | NTF_MANAGED), exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); @@ -1984,12 +2035,14 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, flags |= NEIGH_UPDATE_F_EXT_LEARNED; if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; + if (ndm_flags & NTF_MANAGED) + flags |= NEIGH_UPDATE_F_MANAGED; if (ndm_flags & NTF_USE) flags |= NEIGH_UPDATE_F_USE; err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (!err && ndm_flags & NTF_USE) { + if (!err && ndm_flags & (NTF_USE | NTF_MANAGED)) { neigh_event_send(neigh, NULL); err = 0; } -- cgit v1.2.3 From 42df6e1d221dddc0f2acf2be37e68d553ad65f96 Mon Sep 17 00:00:00 2001 From: Lukas Wunner Date: Fri, 8 Oct 2021 22:06:03 +0200 Subject: netfilter: Introduce egress hook MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Support classifying packets with netfilter on egress to satisfy user requirements such as: * outbound security policies for containers (Laura) * filtering and mangling intra-node Direct Server Return (DSR) traffic on a load balancer (Laura) * filtering locally generated traffic coming in through AF_PACKET, such as local ARP traffic generated for clustering purposes or DHCP (Laura; the AF_PACKET plumbing is contained in a follow-up commit) * L2 filtering from ingress and egress for AVB (Audio Video Bridging) and gPTP with nftables (Pablo) * in the future: in-kernel NAT64/NAT46 (Pablo) The egress hook introduced herein complements the ingress hook added by commit e687ad60af09 ("netfilter: add netfilter ingress hook after handle_ing() under unique static key"). A patch for nftables to hook up egress rules from user space has been submitted separately, so users may immediately take advantage of the feature. Alternatively or in addition to netfilter, packets can be classified with traffic control (tc). On ingress, packets are classified first by tc, then by netfilter. On egress, the order is reversed for symmetry. Conceptually, tc and netfilter can be thought of as layers, with netfilter layered above tc. Traffic control is capable of redirecting packets to another interface (man 8 tc-mirred). E.g., an ingress packet may be redirected from the host namespace to a container via a veth connection: tc ingress (host) -> tc egress (veth host) -> tc ingress (veth container) In this case, netfilter egress classifying is not performed when leaving the host namespace! That's because the packet is still on the tc layer. If tc redirects the packet to a physical interface in the host namespace such that it leaves the system, the packet is never subjected to netfilter egress classifying. That is only logical since it hasn't passed through netfilter ingress classifying either. Packets can alternatively be redirected at the netfilter layer using nft fwd. Such a packet *is* subjected to netfilter egress classifying since it has reached the netfilter layer. Internally, the skb->nf_skip_egress flag controls whether netfilter is invoked on egress by __dev_queue_xmit(). Because __dev_queue_xmit() may be called recursively by tunnel drivers such as vxlan, the flag is reverted to false after sch_handle_egress(). This ensures that netfilter is applied both on the overlay and underlying network. Interaction between tc and netfilter is possible by setting and querying skb->mark. If netfilter egress classifying is not enabled on any interface, it is patched out of the data path by way of a static_key and doesn't make a performance difference that is discernible from noise: Before: 1537 1538 1538 1537 1538 1537 Mb/sec After: 1536 1534 1539 1539 1539 1540 Mb/sec Before + tc accept: 1418 1418 1418 1419 1419 1418 Mb/sec After + tc accept: 1419 1424 1418 1419 1422 1420 Mb/sec Before + tc drop: 1620 1619 1619 1619 1620 1620 Mb/sec After + tc drop: 1616 1624 1625 1624 1622 1619 Mb/sec When netfilter egress classifying is enabled on at least one interface, a minimal performance penalty is incurred for every egress packet, even if the interface it's transmitted over doesn't have any netfilter egress rules configured. That is caused by checking dev->nf_hooks_egress against NULL. Measurements were performed on a Core i7-3615QM. Commands to reproduce: ip link add dev foo type dummy ip link set dev foo up modprobe pktgen echo "add_device foo" > /proc/net/pktgen/kpktgend_3 samples/pktgen/pktgen_bench_xmit_mode_queue_xmit.sh -i foo -n 400000000 -m "11:11:11:11:11:11" -d 1.1.1.1 Accept all traffic with tc: tc qdisc add dev foo clsact tc filter add dev foo egress bpf da bytecode '1,6 0 0 0,' Drop all traffic with tc: tc qdisc add dev foo clsact tc filter add dev foo egress bpf da bytecode '1,6 0 0 2,' Apply this patch when measuring packet drops to avoid errors in dmesg: https://lore.kernel.org/netdev/a73dda33-57f4-95d8-ea51-ed483abd6a7a@iogearbox.net/ Signed-off-by: Lukas Wunner Cc: Laura García Liébana Cc: John Fastabend Cc: Daniel Borkmann Cc: Alexei Starovoitov Cc: Eric Dumazet Cc: Thomas Graf Signed-off-by: Pablo Neira Ayuso --- drivers/net/ifb.c | 3 ++ include/linux/netdevice.h | 4 ++ include/linux/netfilter_netdev.h | 86 ++++++++++++++++++++++++++++++++++++++++ include/linux/skbuff.h | 4 ++ include/uapi/linux/netfilter.h | 1 + net/core/dev.c | 15 ++++++- net/netfilter/Kconfig | 11 +++++ net/netfilter/core.c | 34 ++++++++++++++-- net/netfilter/nfnetlink_hook.c | 16 ++++++-- net/netfilter/nft_chain_filter.c | 4 +- 10 files changed, 168 insertions(+), 10 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/ifb.c b/drivers/net/ifb.c index e9258a9f3702..2c319dd27f29 100644 --- a/drivers/net/ifb.c +++ b/drivers/net/ifb.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include @@ -75,8 +76,10 @@ static void ifb_ri_tasklet(struct tasklet_struct *t) } while ((skb = __skb_dequeue(&txp->tq)) != NULL) { + /* Skip tc and netfilter to prevent redirection loop. */ skb->redirected = 0; skb->tc_skip_classify = 1; + nf_skip_egress(skb, true); u64_stats_update_begin(&txp->tsync); txp->tx_packets++; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d79163208dfd..e9a48068f306 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1861,6 +1861,7 @@ enum netdev_ml_priv_type { * @xps_maps: XXX: need comments on this one * @miniq_egress: clsact qdisc specific data for * egress processing + * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) @@ -2161,6 +2162,9 @@ struct net_device { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc __rcu *miniq_egress; #endif +#ifdef CONFIG_NETFILTER_EGRESS + struct nf_hook_entries __rcu *nf_hooks_egress; +#endif #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h index 5812b0fb0278..b71b57a83bb4 100644 --- a/include/linux/netfilter_netdev.h +++ b/include/linux/netfilter_netdev.h @@ -50,11 +50,97 @@ static inline int nf_hook_ingress(struct sk_buff *skb) } #endif /* CONFIG_NETFILTER_INGRESS */ +#ifdef CONFIG_NETFILTER_EGRESS +static inline bool nf_hook_egress_active(void) +{ +#ifdef CONFIG_JUMP_LABEL + if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) + return false; +#endif + return true; +} + +/** + * nf_hook_egress - classify packets before transmission + * @skb: packet to be classified + * @rc: result code which shall be returned by __dev_queue_xmit() on failure + * @dev: netdev whose egress hooks shall be applied to @skb + * + * Returns @skb on success or %NULL if the packet was consumed or filtered. + * Caller must hold rcu_read_lock. + * + * On ingress, packets are classified first by tc, then by netfilter. + * On egress, the order is reversed for symmetry. Conceptually, tc and + * netfilter can be thought of as layers, with netfilter layered above tc: + * When tc redirects a packet to another interface, netfilter is not applied + * because the packet is on the tc layer. + * + * The nf_skip_egress flag controls whether netfilter is applied on egress. + * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the + * packet passes through tc and netfilter. Because __dev_queue_xmit() may be + * called recursively by tunnel drivers such as vxlan, the flag is reverted to + * false after sch_handle_egress(). This ensures that netfilter is applied + * both on the overlay and underlying network. + */ +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + struct nf_hook_entries *e; + struct nf_hook_state state; + int ret; + +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + if (skb->nf_skip_egress) + return skb; +#endif + + e = rcu_dereference(dev->nf_hooks_egress); + if (!e) + return skb; + + nf_hook_state_init(&state, NF_NETDEV_EGRESS, + NFPROTO_NETDEV, dev, NULL, NULL, + dev_net(dev), NULL); + ret = nf_hook_slow(skb, &state, e, 0); + + if (ret == 1) { + return skb; + } else if (ret < 0) { + *rc = NET_XMIT_DROP; + return NULL; + } else { /* ret == 0 */ + *rc = NET_XMIT_SUCCESS; + return NULL; + } +} +#else /* CONFIG_NETFILTER_EGRESS */ +static inline bool nf_hook_egress_active(void) +{ + return false; +} + +static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, + struct net_device *dev) +{ + return skb; +} +#endif /* CONFIG_NETFILTER_EGRESS */ + +static inline void nf_skip_egress(struct sk_buff *skb, bool skip) +{ +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + skb->nf_skip_egress = skip; +#endif +} + static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif +#ifdef CONFIG_NETFILTER_EGRESS + RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); +#endif } #endif /* _NETFILTER_NETDEV_H_ */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 841e2f0f5240..cb96f1e6460c 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -652,6 +652,7 @@ typedef unsigned char *sk_buff_data_t; * @tc_at_ingress: used within tc_classify to distinguish in/egress * @redirected: packet was redirected by packet classifier * @from_ingress: packet was redirected from the ingress path + * @nf_skip_egress: packet shall skip nf egress - see netfilter_netdev.h * @peeked: this packet has been seen already, so stats have been * done for it, don't do them again * @nf_trace: netfilter packet trace flag @@ -868,6 +869,9 @@ struct sk_buff { #ifdef CONFIG_NET_REDIRECT __u8 from_ingress:1; #endif +#ifdef CONFIG_NETFILTER_SKIP_EGRESS + __u8 nf_skip_egress:1; +#endif #ifdef CONFIG_TLS_DEVICE __u8 decrypted:1; #endif diff --git a/include/uapi/linux/netfilter.h b/include/uapi/linux/netfilter.h index ef9a44286e23..53411ccc69db 100644 --- a/include/uapi/linux/netfilter.h +++ b/include/uapi/linux/netfilter.h @@ -51,6 +51,7 @@ enum nf_inet_hooks { enum nf_dev_hooks { NF_NETDEV_INGRESS, + NF_NETDEV_EGRESS, NF_NETDEV_NUMHOOKS }; diff --git a/net/core/dev.c b/net/core/dev.c index e4c683029c61..09d74798b440 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3920,6 +3920,7 @@ EXPORT_SYMBOL(dev_loopback_xmit); static struct sk_buff * sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) { +#ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(dev->miniq_egress); struct tcf_result cl_res; @@ -3955,6 +3956,7 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev) default: break; } +#endif /* CONFIG_NET_CLS_ACT */ return skb; } @@ -4148,13 +4150,20 @@ static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev) qdisc_pkt_len_init(skb); #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; -# ifdef CONFIG_NET_EGRESS +#endif +#ifdef CONFIG_NET_EGRESS if (static_branch_unlikely(&egress_needed_key)) { + if (nf_hook_egress_active()) { + skb = nf_hook_egress(skb, &rc, dev); + if (!skb) + goto out; + } + nf_skip_egress(skb, true); skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; + nf_skip_egress(skb, false); } -# endif #endif /* If device/qdisc don't need skb->dst, release it right now while * its hot in this cpu cache. @@ -5296,6 +5305,7 @@ skip_taps: if (static_branch_unlikely(&ingress_needed_key)) { bool another = false; + nf_skip_egress(skb, true); skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, &another); if (another) @@ -5303,6 +5313,7 @@ skip_taps: if (!skb) goto out; + nf_skip_egress(skb, false); if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0) goto out; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 54395266339d..49c9fae9c62c 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -10,6 +10,17 @@ config NETFILTER_INGRESS This allows you to classify packets from ingress using the Netfilter infrastructure. +config NETFILTER_EGRESS + bool "Netfilter egress support" + default y + select NET_EGRESS + help + This allows you to classify packets before transmission using the + Netfilter infrastructure. + +config NETFILTER_SKIP_EGRESS + def_bool NETFILTER_EGRESS && (NET_CLS_ACT || IFB) + config NETFILTER_NETLINK tristate diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 63d032191e62..3a32a813fcde 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -316,6 +316,12 @@ nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hooknum == NF_NETDEV_EGRESS) { + if (dev && dev_net(dev) == net) + return &dev->nf_hooks_egress; + } #endif WARN_ON_ONCE(1); return NULL; @@ -344,6 +350,11 @@ static inline bool nf_ingress_hook(const struct nf_hook_ops *reg, int pf) return false; } +static inline bool nf_egress_hook(const struct nf_hook_ops *reg, int pf) +{ + return pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_EGRESS; +} + static void nf_static_key_inc(const struct nf_hook_ops *reg, int pf) { #ifdef CONFIG_JUMP_LABEL @@ -383,9 +394,18 @@ static int __nf_register_net_hook(struct net *net, int pf, switch (pf) { case NFPROTO_NETDEV: - err = nf_ingress_check(net, reg, NF_NETDEV_INGRESS); - if (err < 0) - return err; +#ifndef CONFIG_NETFILTER_INGRESS + if (reg->hooknum == NF_NETDEV_INGRESS) + return -EOPNOTSUPP; +#endif +#ifndef CONFIG_NETFILTER_EGRESS + if (reg->hooknum == NF_NETDEV_EGRESS) + return -EOPNOTSUPP; +#endif + if ((reg->hooknum != NF_NETDEV_INGRESS && + reg->hooknum != NF_NETDEV_EGRESS) || + !reg->dev || dev_net(reg->dev) != net) + return -EINVAL; break; case NFPROTO_INET: if (reg->hooknum != NF_INET_INGRESS) @@ -417,6 +437,10 @@ static int __nf_register_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_inc_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_inc_egress_queue(); #endif nf_static_key_inc(reg, pf); @@ -474,6 +498,10 @@ static void __nf_unregister_net_hook(struct net *net, int pf, #ifdef CONFIG_NETFILTER_INGRESS if (nf_ingress_hook(reg, pf)) net_dec_ingress_queue(); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (nf_egress_hook(reg, pf)) + net_dec_egress_queue(); #endif nf_static_key_dec(reg, pf); } else { diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c index f554e2ea32ee..d5c719c9e36c 100644 --- a/net/netfilter/nfnetlink_hook.c +++ b/net/netfilter/nfnetlink_hook.c @@ -185,7 +185,7 @@ static const struct nf_hook_entries * nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *dev) { const struct nf_hook_entries *hook_head = NULL; -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) struct net_device *netdev; #endif @@ -221,9 +221,9 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de hook_head = rcu_dereference(net->nf.hooks_decnet[hook]); break; #endif -#ifdef CONFIG_NETFILTER_INGRESS +#if defined(CONFIG_NETFILTER_INGRESS) || defined(CONFIG_NETFILTER_EGRESS) case NFPROTO_NETDEV: - if (hook != NF_NETDEV_INGRESS) + if (hook >= NF_NETDEV_NUMHOOKS) return ERR_PTR(-EOPNOTSUPP); if (!dev) @@ -233,7 +233,15 @@ nfnl_hook_entries_head(u8 pf, unsigned int hook, struct net *net, const char *de if (!netdev) return ERR_PTR(-ENODEV); - return rcu_dereference(netdev->nf_hooks_ingress); +#ifdef CONFIG_NETFILTER_INGRESS + if (hook == NF_NETDEV_INGRESS) + return rcu_dereference(netdev->nf_hooks_ingress); +#endif +#ifdef CONFIG_NETFILTER_EGRESS + if (hook == NF_NETDEV_EGRESS) + return rcu_dereference(netdev->nf_hooks_egress); +#endif + fallthrough; #endif default: return ERR_PTR(-EPROTONOSUPPORT); diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 5b02408a920b..680fe557686e 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -310,9 +310,11 @@ static const struct nft_chain_type nft_chain_filter_netdev = { .name = "filter", .type = NFT_CHAIN_T_DEFAULT, .family = NFPROTO_NETDEV, - .hook_mask = (1 << NF_NETDEV_INGRESS), + .hook_mask = (1 << NF_NETDEV_INGRESS) | + (1 << NF_NETDEV_EGRESS), .hooks = { [NF_NETDEV_INGRESS] = nft_do_chain_netdev, + [NF_NETDEV_EGRESS] = nft_do_chain_netdev, }, }; -- cgit v1.2.3 From 8b8ff8cc3b8155c18162e8b1f70e1230db176862 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 7 Sep 2021 19:39:01 +0300 Subject: perf/x86: Add new event for AUX output counter index PEBS-via-PT records contain a mask of applicable counters. To identify which event belongs to which counter, a side-band event is needed. Until now, there has been no side-band event, and consequently users were limited to using a single event. Add such a side-band event. Note the event is optimised to output only when the counter index changes for an event. That works only so long as all PEBS-via-PT events are scheduled together, which they are for a recording session because they are in a single group. Also no attribute bit is used to select the new event, so a new kernel is not compatible with older perf tools. The assumption being that PEBS-via-PT is sufficiently esoteric that users will not be troubled by this. Signed-off-by: Adrian Hunter Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20210907163903.11820-2-adrian.hunter@intel.com --- arch/x86/events/core.c | 6 ++++++ arch/x86/events/intel/core.c | 16 ++++++++++++++++ arch/x86/events/perf_event.h | 1 + include/linux/perf_event.h | 1 + include/uapi/linux/perf_event.h | 15 +++++++++++++++ kernel/events/core.c | 30 ++++++++++++++++++++++++++++++ 6 files changed, 69 insertions(+) (limited to 'include/uapi/linux') diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 2a57dbed4894..be33423e9762 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -66,6 +66,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_enable_all, *x86_pmu.enable_all); DEFINE_STATIC_CALL_NULL(x86_pmu_enable, *x86_pmu.enable); DEFINE_STATIC_CALL_NULL(x86_pmu_disable, *x86_pmu.disable); +DEFINE_STATIC_CALL_NULL(x86_pmu_assign, *x86_pmu.assign); + DEFINE_STATIC_CALL_NULL(x86_pmu_add, *x86_pmu.add); DEFINE_STATIC_CALL_NULL(x86_pmu_del, *x86_pmu.del); DEFINE_STATIC_CALL_NULL(x86_pmu_read, *x86_pmu.read); @@ -1215,6 +1217,8 @@ static inline void x86_assign_hw_event(struct perf_event *event, hwc->last_cpu = smp_processor_id(); hwc->last_tag = ++cpuc->tags[i]; + static_call_cond(x86_pmu_assign)(event, idx); + switch (hwc->idx) { case INTEL_PMC_IDX_FIXED_BTS: case INTEL_PMC_IDX_FIXED_VLBR: @@ -2005,6 +2009,8 @@ static void x86_pmu_static_call_update(void) static_call_update(x86_pmu_enable, x86_pmu.enable); static_call_update(x86_pmu_disable, x86_pmu.disable); + static_call_update(x86_pmu_assign, x86_pmu.assign); + static_call_update(x86_pmu_add, x86_pmu.add); static_call_update(x86_pmu_del, x86_pmu.del); static_call_update(x86_pmu_read, x86_pmu.read); diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 7011e87be6d0..a555e7c2dce9 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2402,6 +2402,12 @@ static void intel_pmu_disable_event(struct perf_event *event) intel_pmu_pebs_disable(event); } +static void intel_pmu_assign_event(struct perf_event *event, int idx) +{ + if (is_pebs_pt(event)) + perf_report_aux_output_id(event, idx); +} + static void intel_pmu_del_event(struct perf_event *event) { if (needs_branch_stack(event)) @@ -4494,8 +4500,16 @@ static int intel_pmu_check_period(struct perf_event *event, u64 value) return intel_pmu_has_bts_period(event, value) ? -EINVAL : 0; } +static void intel_aux_output_init(void) +{ + /* Refer also intel_pmu_aux_output_match() */ + if (x86_pmu.intel_cap.pebs_output_pt_available) + x86_pmu.assign = intel_pmu_assign_event; +} + static int intel_pmu_aux_output_match(struct perf_event *event) { + /* intel_pmu_assign_event() is needed, refer intel_aux_output_init() */ if (!x86_pmu.intel_cap.pebs_output_pt_available) return 0; @@ -6301,6 +6315,8 @@ __init int intel_pmu_init(void) if (is_hybrid()) intel_pmu_check_hybrid_pmus((u64)fixed_mask); + intel_aux_output_init(); + return 0; } diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index e3ac05c97b5e..76436a55d9ba 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -726,6 +726,7 @@ struct x86_pmu { void (*enable_all)(int added); void (*enable)(struct perf_event *); void (*disable)(struct perf_event *); + void (*assign)(struct perf_event *event, int idx); void (*add)(struct perf_event *); void (*del)(struct perf_event *); void (*read)(struct perf_event *event); diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 2d510ad750ed..126b3a314f3a 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1397,6 +1397,7 @@ perf_event_addr_filters(struct perf_event *event) } extern void perf_event_addr_filters_sync(struct perf_event *event); +extern void perf_report_aux_output_id(struct perf_event *event, u64 hw_id); extern int perf_output_begin(struct perf_output_handle *handle, struct perf_sample_data *data, diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index f92880a15645..c89535de1ec8 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1141,6 +1141,21 @@ enum perf_event_type { */ PERF_RECORD_TEXT_POKE = 20, + /* + * Data written to the AUX area by hardware due to aux_output, may need + * to be matched to the event by an architecture-specific hardware ID. + * This records the hardware ID, but requires sample_id to provide the + * event ID. e.g. Intel PT uses this record to disambiguate PEBS-via-PT + * records from multiple events. + * + * struct { + * struct perf_event_header header; + * u64 hw_id; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + PERF_RECORD_MAX, /* non-ABI */ }; diff --git a/kernel/events/core.c b/kernel/events/core.c index 1cb1f9b8392e..0e90a5084f18 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -9062,6 +9062,36 @@ static void perf_log_itrace_start(struct perf_event *event) perf_output_end(&handle); } +void perf_report_aux_output_id(struct perf_event *event, u64 hw_id) +{ + struct perf_output_handle handle; + struct perf_sample_data sample; + struct perf_aux_event { + struct perf_event_header header; + u64 hw_id; + } rec; + int ret; + + if (event->parent) + event = event->parent; + + rec.header.type = PERF_RECORD_AUX_OUTPUT_HW_ID; + rec.header.misc = 0; + rec.header.size = sizeof(rec); + rec.hw_id = hw_id; + + perf_event_header__init_id(&rec.header, &sample, event); + ret = perf_output_begin(&handle, &sample, event, rec.header.size); + + if (ret) + return; + + perf_output_put(&handle, rec); + perf_event__output_id_sample(event, &handle, &sample); + + perf_output_end(&handle); +} + static int __perf_event_account_interrupt(struct perf_event *event, int throttle) { -- cgit v1.2.3 From e72aeb9ee0e34c57dc90793d0bf82cab9624d64e Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 14 Oct 2021 10:59:18 -0700 Subject: fq_codel: implement L4S style ce_threshold_ect1 marking Add TCA_FQ_CODEL_CE_THRESHOLD_ECT1 boolean option to select Low Latency, Low Loss, Scalable Throughput (L4S) style marking, along with ce_threshold. If enabled, only packets with ECT(1) can be transformed to CE if their sojourn time is above the ce_threshold. Note that this new option does not change rules for codel law. In particular, if TCA_FQ_CODEL_ECN is left enabled (this is the default when fq_codel qdisc is created), ECT(0) packets can still get CE if codel law (as governed by limit/target) decides so. Section 4.3.b of current draft [1] states: b. A scheduler with per-flow queues such as FQ-CoDel or FQ-PIE can be used for L4S. For instance within each queue of an FQ-CoDel system, as well as a CoDel AQM, there is typically also ECN marking at an immediate (unsmoothed) shallow threshold to support use in data centres (see Sec.5.2.7 of [RFC8290]). This can be modified so that the shallow threshold is solely applied to ECT(1) packets. Then if there is a flow of non-ECN or ECT(0) packets in the per-flow-queue, the Classic AQM (e.g. CoDel) is applied; while if there is a flow of ECT(1) packets in the queue, the shallower (typically sub-millisecond) threshold is applied. Tested: tc qd replace dev eth1 root fq_codel ce_threshold_ect1 50usec netperf ... -t TCP_STREAM -- K dctcp tc -s -d qd sh dev eth1 qdisc fq_codel 8022: root refcnt 32 limit 10240p flows 1024 quantum 9212 target 5ms ce_threshold_ect1 49us interval 100ms memory_limit 32Mb ecn drop_batch 64 Sent 14388596616 bytes 9543449 pkt (dropped 0, overlimits 0 requeues 152013) backlog 0b 0p requeues 152013 maxpacket 68130 drop_overlimit 0 new_flow_count 95678 ecn_mark 0 ce_mark 7639 new_flows_len 0 old_flows_len 0 [1] L4S current draft: https://datatracker.ietf.org/doc/html/draft-ietf-tsvwg-l4s-arch Signed-off-by: Eric Dumazet Cc: Neal Cardwell Cc: Ingemar Johansson S Cc: Tom Henderson Cc: Bob Briscoe Signed-off-by: David S. Miller --- include/net/codel.h | 2 ++ include/net/codel_impl.h | 18 +++++++++++++++--- include/uapi/linux/pkt_sched.h | 1 + net/mac80211/sta_info.c | 1 + net/sched/sch_fq_codel.c | 15 +++++++++++---- 5 files changed, 30 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/codel.h b/include/net/codel.h index a6e428f80135..5e8b181b76b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,6 +102,7 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled + * @ce_threshold_ect1: if ce_threshold only marks ECT(1) packets */ struct codel_params { codel_time_t target; @@ -109,6 +110,7 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; + bool ce_threshold_ect1; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index d289b91dcd65..7af2c3eb3c43 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,6 +54,7 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; + params->ce_threshold_ect1 = false; params->ecn = false; } @@ -246,9 +247,20 @@ static struct sk_buff *codel_dequeue(void *ctx, vars->rec_inv_sqrt); } end: - if (skb && codel_time_after(vars->ldelay, params->ce_threshold) && - INET_ECN_set_ce(skb)) - stats->ce_mark++; + if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { + bool set_ce = true; + + if (params->ce_threshold_ect1) { + /* Note: if skb_get_dsfield() returns -1, following + * gives INET_ECN_MASK, which is != INET_ECN_ECT_1. + */ + u8 ecn = skb_get_dsfield(skb) & INET_ECN_MASK; + + set_ce = (ecn == INET_ECN_ECT_1); + } + if (set_ce && INET_ECN_set_ce(skb)) + stats->ce_mark++; + } return skb; } diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index ec88590b3198..6be9a84cccfa 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -840,6 +840,7 @@ enum { TCA_FQ_CODEL_CE_THRESHOLD, TCA_FQ_CODEL_DROP_BATCH_SIZE, TCA_FQ_CODEL_MEMORY_LIMIT, + TCA_FQ_CODEL_CE_THRESHOLD_ECT1, __TCA_FQ_CODEL_MAX }; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2b5acb37587f..a39830418434 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -513,6 +513,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->cparams.target = MS2TIME(20); sta->cparams.interval = MS2TIME(100); sta->cparams.ecn = true; + sta->cparams.ce_threshold_ect1 = false; sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index bb0cd6d3d2c2..033d65d06eb1 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -362,6 +362,7 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, + [TCA_FQ_CODEL_CE_THRESHOLD_ECT1] = { .type = NLA_U8 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, @@ -408,6 +409,9 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]) + q->cparams.ce_threshold_ect1 = !!nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]); + if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -544,10 +548,13 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) q->flows_cnt)) goto nla_put_failure; - if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD && - nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, - codel_time_to_us(q->cparams.ce_threshold))) - goto nla_put_failure; + if (q->cparams.ce_threshold != CODEL_DISABLED_THRESHOLD) { + if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, + codel_time_to_us(q->cparams.ce_threshold))) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_ECT1, q->cparams.ce_threshold_ect1)) + goto nla_put_failure; + } return nla_nest_end(skb, opts); -- cgit v1.2.3 From b0539f5eddc2eefd24378bda3ee9cbbca916f58d Mon Sep 17 00:00:00 2001 From: Karsten Graul Date: Sat, 16 Oct 2021 11:37:51 +0200 Subject: net/smc: add netlink support for SMC-Rv2 Implement the netlink support for SMC-Rv2 related attributes that are provided to user space. Signed-off-by: Karsten Graul Signed-off-by: David S. Miller --- include/uapi/linux/smc.h | 17 ++++++++- net/smc/smc_core.c | 98 ++++++++++++++++++++++++++++++++++++------------ 2 files changed, 88 insertions(+), 27 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/smc.h b/include/uapi/linux/smc.h index b175bd0165a1..20f33b27787f 100644 --- a/include/uapi/linux/smc.h +++ b/include/uapi/linux/smc.h @@ -84,17 +84,28 @@ enum { SMC_NLA_SYS_IS_ISM_V2, /* u8 */ SMC_NLA_SYS_LOCAL_HOST, /* string */ SMC_NLA_SYS_SEID, /* string */ + SMC_NLA_SYS_IS_SMCR_V2, /* u8 */ __SMC_NLA_SYS_MAX, SMC_NLA_SYS_MAX = __SMC_NLA_SYS_MAX - 1 }; -/* SMC_NLA_LGR_V2 nested attributes */ +/* SMC_NLA_LGR_D_V2_COMMON and SMC_NLA_LGR_R_V2_COMMON nested attributes */ enum { SMC_NLA_LGR_V2_VER, /* u8 */ SMC_NLA_LGR_V2_REL, /* u8 */ SMC_NLA_LGR_V2_OS, /* u8 */ SMC_NLA_LGR_V2_NEG_EID, /* string */ SMC_NLA_LGR_V2_PEER_HOST, /* string */ + __SMC_NLA_LGR_V2_MAX, + SMC_NLA_LGR_V2_MAX = __SMC_NLA_LGR_V2_MAX - 1 +}; + +/* SMC_NLA_LGR_R_V2 nested attributes */ +enum { + SMC_NLA_LGR_R_V2_UNSPEC, + SMC_NLA_LGR_R_V2_DIRECT, /* u8 */ + __SMC_NLA_LGR_R_V2_MAX, + SMC_NLA_LGR_R_V2_MAX = __SMC_NLA_LGR_R_V2_MAX - 1 }; /* SMC_GEN_LGR_SMCR attributes */ @@ -106,6 +117,8 @@ enum { SMC_NLA_LGR_R_PNETID, /* string */ SMC_NLA_LGR_R_VLAN_ID, /* u8 */ SMC_NLA_LGR_R_CONNS_NUM, /* u32 */ + SMC_NLA_LGR_R_V2_COMMON, /* nest */ + SMC_NLA_LGR_R_V2, /* nest */ __SMC_NLA_LGR_R_MAX, SMC_NLA_LGR_R_MAX = __SMC_NLA_LGR_R_MAX - 1 }; @@ -138,7 +151,7 @@ enum { SMC_NLA_LGR_D_PNETID, /* string */ SMC_NLA_LGR_D_CHID, /* u16 */ SMC_NLA_LGR_D_PAD, /* flag */ - SMC_NLA_LGR_V2, /* nest */ + SMC_NLA_LGR_D_V2_COMMON, /* nest */ __SMC_NLA_LGR_D_MAX, SMC_NLA_LGR_D_MAX = __SMC_NLA_LGR_D_MAX - 1 }; diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 1ccab993683d..8e642f8f334f 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -244,6 +244,8 @@ int smc_nl_get_sys_info(struct sk_buff *skb, struct netlink_callback *cb) goto errattr; if (nla_put_u8(skb, SMC_NLA_SYS_IS_ISM_V2, smc_ism_is_v2_capable())) goto errattr; + if (nla_put_u8(skb, SMC_NLA_SYS_IS_SMCR_V2, true)) + goto errattr; smc_clc_get_hostname(&host); if (host) { memcpy(hostname, host, SMC_MAX_HOSTNAME_LEN); @@ -271,12 +273,65 @@ errmsg: return skb->len; } +/* Fill SMC_NLA_LGR_D_V2_COMMON/SMC_NLA_LGR_R_V2_COMMON nested attributes */ +static int smc_nl_fill_lgr_v2_common(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb, + struct nlattr *v2_attrs) +{ + char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; + char smc_eid[SMC_MAX_EID_LEN + 1]; + + if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) + goto errv2attr; + if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) + goto errv2attr; + memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); + smc_host[SMC_MAX_HOSTNAME_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) + goto errv2attr; + memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); + smc_eid[SMC_MAX_EID_LEN] = 0; + if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); + return -EMSGSIZE; +} + +static int smc_nl_fill_smcr_lgr_v2(struct smc_link_group *lgr, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct nlattr *v2_attrs; + + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2); + if (!v2_attrs) + goto errattr; + if (nla_put_u8(skb, SMC_NLA_LGR_R_V2_DIRECT, !lgr->uses_gateway)) + goto errv2attr; + + nla_nest_end(skb, v2_attrs); + return 0; + +errv2attr: + nla_nest_cancel(skb, v2_attrs); +errattr: + return -EMSGSIZE; +} + static int smc_nl_fill_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { char smc_target[SMC_MAX_PNETID_LEN + 1]; - struct nlattr *attrs; + struct nlattr *attrs, *v2_attrs; attrs = nla_nest_start(skb, SMC_GEN_LGR_SMCR); if (!attrs) @@ -296,6 +351,15 @@ static int smc_nl_fill_lgr(struct smc_link_group *lgr, smc_target[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_R_PNETID, smc_target)) goto errattr; + if (lgr->smc_version > SMC_V1) { + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_R_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + if (smc_nl_fill_smcr_lgr_v2(lgr, skb, cb)) + goto errattr; + } nla_nest_end(skb, attrs); return 0; @@ -428,10 +492,7 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, struct sk_buff *skb, struct netlink_callback *cb) { - char smc_host[SMC_MAX_HOSTNAME_LEN + 1]; char smc_pnet[SMC_MAX_PNETID_LEN + 1]; - char smc_eid[SMC_MAX_EID_LEN + 1]; - struct nlattr *v2_attrs; struct nlattr *attrs; void *nlh; @@ -463,32 +524,19 @@ static int smc_nl_fill_smcd_lgr(struct smc_link_group *lgr, smc_pnet[SMC_MAX_PNETID_LEN] = 0; if (nla_put_string(skb, SMC_NLA_LGR_D_PNETID, smc_pnet)) goto errattr; + if (lgr->smc_version > SMC_V1) { + struct nlattr *v2_attrs; - v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_V2); - if (!v2_attrs) - goto errattr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_VER, lgr->smc_version)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_REL, lgr->peer_smc_release)) - goto errv2attr; - if (nla_put_u8(skb, SMC_NLA_LGR_V2_OS, lgr->peer_os)) - goto errv2attr; - memcpy(smc_host, lgr->peer_hostname, SMC_MAX_HOSTNAME_LEN); - smc_host[SMC_MAX_HOSTNAME_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_PEER_HOST, smc_host)) - goto errv2attr; - memcpy(smc_eid, lgr->negotiated_eid, SMC_MAX_EID_LEN); - smc_eid[SMC_MAX_EID_LEN] = 0; - if (nla_put_string(skb, SMC_NLA_LGR_V2_NEG_EID, smc_eid)) - goto errv2attr; - - nla_nest_end(skb, v2_attrs); + v2_attrs = nla_nest_start(skb, SMC_NLA_LGR_D_V2_COMMON); + if (!v2_attrs) + goto errattr; + if (smc_nl_fill_lgr_v2_common(lgr, skb, cb, v2_attrs)) + goto errattr; + } nla_nest_end(skb, attrs); genlmsg_end(skb, nlh); return 0; -errv2attr: - nla_nest_cancel(skb, v2_attrs); errattr: nla_nest_cancel(skb, attrs); errout: -- cgit v1.2.3 From e65c26f413718ed2e6d788491adcd8cebc0f44b6 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 29 Sep 2021 12:15:58 +0900 Subject: counter: Move counter enums to uapi header This is in preparation for a subsequent patch implementing a character device interface for the Counter subsystem. Reviewed-by: David Lechner Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/962a5f2027fafcf4f77c10e1baf520463960d1ee.1632884256.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- MAINTAINERS | 1 + include/linux/counter.h | 42 +-------------------------------- include/uapi/linux/counter.h | 56 ++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 58 insertions(+), 41 deletions(-) create mode 100644 include/uapi/linux/counter.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index b98a34fcec4b..8310a42abdab 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4804,6 +4804,7 @@ F: Documentation/ABI/testing/sysfs-bus-counter F: Documentation/driver-api/generic-counter.rst F: drivers/counter/ F: include/linux/counter.h +F: include/uapi/linux/counter.h CP2615 I2C DRIVER M: Bence Csókás diff --git a/include/linux/counter.h b/include/linux/counter.h index 445f22d8bfe2..7c9f7e23953a 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -9,6 +9,7 @@ #include #include #include +#include struct counter_device; struct counter_count; @@ -27,47 +28,6 @@ enum counter_comp_type { COUNTER_COMP_COUNT_MODE, }; -enum counter_scope { - COUNTER_SCOPE_DEVICE, - COUNTER_SCOPE_SIGNAL, - COUNTER_SCOPE_COUNT, -}; - -enum counter_count_direction { - COUNTER_COUNT_DIRECTION_FORWARD, - COUNTER_COUNT_DIRECTION_BACKWARD, -}; - -enum counter_count_mode { - COUNTER_COUNT_MODE_NORMAL, - COUNTER_COUNT_MODE_RANGE_LIMIT, - COUNTER_COUNT_MODE_NON_RECYCLE, - COUNTER_COUNT_MODE_MODULO_N, -}; - -enum counter_function { - COUNTER_FUNCTION_INCREASE, - COUNTER_FUNCTION_DECREASE, - COUNTER_FUNCTION_PULSE_DIRECTION, - COUNTER_FUNCTION_QUADRATURE_X1_A, - COUNTER_FUNCTION_QUADRATURE_X1_B, - COUNTER_FUNCTION_QUADRATURE_X2_A, - COUNTER_FUNCTION_QUADRATURE_X2_B, - COUNTER_FUNCTION_QUADRATURE_X4, -}; - -enum counter_signal_level { - COUNTER_SIGNAL_LEVEL_LOW, - COUNTER_SIGNAL_LEVEL_HIGH, -}; - -enum counter_synapse_action { - COUNTER_SYNAPSE_ACTION_NONE, - COUNTER_SYNAPSE_ACTION_RISING_EDGE, - COUNTER_SYNAPSE_ACTION_FALLING_EDGE, - COUNTER_SYNAPSE_ACTION_BOTH_EDGES, -}; - /** * struct counter_comp - Counter component node * @type: Counter component data type diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h new file mode 100644 index 000000000000..6113938a6044 --- /dev/null +++ b/include/uapi/linux/counter.h @@ -0,0 +1,56 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * Userspace ABI for Counter character devices + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _UAPI_COUNTER_H_ +#define _UAPI_COUNTER_H_ + +/* Component scope definitions */ +enum counter_scope { + COUNTER_SCOPE_DEVICE, + COUNTER_SCOPE_SIGNAL, + COUNTER_SCOPE_COUNT, +}; + +/* Count direction values */ +enum counter_count_direction { + COUNTER_COUNT_DIRECTION_FORWARD, + COUNTER_COUNT_DIRECTION_BACKWARD, +}; + +/* Count mode values */ +enum counter_count_mode { + COUNTER_COUNT_MODE_NORMAL, + COUNTER_COUNT_MODE_RANGE_LIMIT, + COUNTER_COUNT_MODE_NON_RECYCLE, + COUNTER_COUNT_MODE_MODULO_N, +}; + +/* Count function values */ +enum counter_function { + COUNTER_FUNCTION_INCREASE, + COUNTER_FUNCTION_DECREASE, + COUNTER_FUNCTION_PULSE_DIRECTION, + COUNTER_FUNCTION_QUADRATURE_X1_A, + COUNTER_FUNCTION_QUADRATURE_X1_B, + COUNTER_FUNCTION_QUADRATURE_X2_A, + COUNTER_FUNCTION_QUADRATURE_X2_B, + COUNTER_FUNCTION_QUADRATURE_X4, +}; + +/* Signal values */ +enum counter_signal_level { + COUNTER_SIGNAL_LEVEL_LOW, + COUNTER_SIGNAL_LEVEL_HIGH, +}; + +/* Action mode values */ +enum counter_synapse_action { + COUNTER_SYNAPSE_ACTION_NONE, + COUNTER_SYNAPSE_ACTION_RISING_EDGE, + COUNTER_SYNAPSE_ACTION_FALLING_EDGE, + COUNTER_SYNAPSE_ACTION_BOTH_EDGES, +}; + +#endif /* _UAPI_COUNTER_H_ */ -- cgit v1.2.3 From b6c50affda5957a3629b149a91c7f6688ffce7f7 Mon Sep 17 00:00:00 2001 From: William Breathitt Gray Date: Wed, 29 Sep 2021 12:15:59 +0900 Subject: counter: Add character device interface This patch introduces a character device interface for the Counter subsystem. Device data is exposed through standard character device read operations. Device data is gathered when a Counter event is pushed by the respective Counter device driver. Configuration is handled via ioctl operations on the respective Counter character device node. Cc: David Lechner Cc: Gwendal Grignou Cc: Dan Carpenter Cc: Oleksij Rempel Signed-off-by: William Breathitt Gray Link: https://lore.kernel.org/r/b8b8c64b4065aedff43699ad1f0e2f8d1419c15b.1632884256.git.vilhelm.gray@gmail.com Signed-off-by: Jonathan Cameron --- drivers/counter/Makefile | 2 +- drivers/counter/counter-chrdev.c | 578 +++++++++++++++++++++++++++++++++++++++ drivers/counter/counter-chrdev.h | 14 + drivers/counter/counter-core.c | 56 +++- include/linux/counter.h | 56 ++++ include/uapi/linux/counter.h | 98 +++++++ 6 files changed, 798 insertions(+), 6 deletions(-) create mode 100644 drivers/counter/counter-chrdev.c create mode 100644 drivers/counter/counter-chrdev.h (limited to 'include/uapi/linux') diff --git a/drivers/counter/Makefile b/drivers/counter/Makefile index 1ab7e087fdc2..8fde6c100ebc 100644 --- a/drivers/counter/Makefile +++ b/drivers/counter/Makefile @@ -4,7 +4,7 @@ # obj-$(CONFIG_COUNTER) += counter.o -counter-y := counter-core.o counter-sysfs.o +counter-y := counter-core.o counter-sysfs.o counter-chrdev.o obj-$(CONFIG_104_QUAD_8) += 104-quad-8.o obj-$(CONFIG_INTERRUPT_CNT) += interrupt-cnt.o diff --git a/drivers/counter/counter-chrdev.c b/drivers/counter/counter-chrdev.c new file mode 100644 index 000000000000..967c94ae95bb --- /dev/null +++ b/drivers/counter/counter-chrdev.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic Counter character device interface + * Copyright (C) 2020 William Breathitt Gray + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "counter-chrdev.h" + +struct counter_comp_node { + struct list_head l; + struct counter_component component; + struct counter_comp comp; + void *parent; +}; + +#define counter_comp_read_is_equal(a, b) \ + (a.action_read == b.action_read || \ + a.device_u8_read == b.device_u8_read || \ + a.count_u8_read == b.count_u8_read || \ + a.signal_u8_read == b.signal_u8_read || \ + a.device_u32_read == b.device_u32_read || \ + a.count_u32_read == b.count_u32_read || \ + a.signal_u32_read == b.signal_u32_read || \ + a.device_u64_read == b.device_u64_read || \ + a.count_u64_read == b.count_u64_read || \ + a.signal_u64_read == b.signal_u64_read) + +#define counter_comp_read_is_set(comp) \ + (comp.action_read || \ + comp.device_u8_read || \ + comp.count_u8_read || \ + comp.signal_u8_read || \ + comp.device_u32_read || \ + comp.count_u32_read || \ + comp.signal_u32_read || \ + comp.device_u64_read || \ + comp.count_u64_read || \ + comp.signal_u64_read) + +static ssize_t counter_chrdev_read(struct file *filp, char __user *buf, + size_t len, loff_t *f_ps) +{ + struct counter_device *const counter = filp->private_data; + int err; + unsigned int copied; + + if (!counter->ops) + return -ENODEV; + + if (len < sizeof(struct counter_event)) + return -EINVAL; + + do { + if (kfifo_is_empty(&counter->events)) { + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + err = wait_event_interruptible(counter->events_wait, + !kfifo_is_empty(&counter->events) || + !counter->ops); + if (err < 0) + return err; + if (!counter->ops) + return -ENODEV; + } + + if (mutex_lock_interruptible(&counter->events_lock)) + return -ERESTARTSYS; + err = kfifo_to_user(&counter->events, buf, len, &copied); + mutex_unlock(&counter->events_lock); + if (err < 0) + return err; + } while (!copied); + + return copied; +} + +static __poll_t counter_chrdev_poll(struct file *filp, + struct poll_table_struct *pollt) +{ + struct counter_device *const counter = filp->private_data; + __poll_t events = 0; + + if (!counter->ops) + return events; + + poll_wait(filp, &counter->events_wait, pollt); + + if (!kfifo_is_empty(&counter->events)) + events = EPOLLIN | EPOLLRDNORM; + + return events; +} + +static void counter_events_list_free(struct list_head *const events_list) +{ + struct counter_event_node *p, *n; + struct counter_comp_node *q, *o; + + list_for_each_entry_safe(p, n, events_list, l) { + /* Free associated component nodes */ + list_for_each_entry_safe(q, o, &p->comp_list, l) { + list_del(&q->l); + kfree(q); + } + + /* Free event node */ + list_del(&p->l); + kfree(p); + } +} + +static int counter_set_event_node(struct counter_device *const counter, + struct counter_watch *const watch, + const struct counter_comp_node *const cfg) +{ + struct counter_event_node *event_node; + int err = 0; + struct counter_comp_node *comp_node; + + /* Search for event in the list */ + list_for_each_entry(event_node, &counter->next_events_list, l) + if (event_node->event == watch->event && + event_node->channel == watch->channel) + break; + + /* If event is not already in the list */ + if (&event_node->l == &counter->next_events_list) { + /* Allocate new event node */ + event_node = kmalloc(sizeof(*event_node), GFP_KERNEL); + if (!event_node) + return -ENOMEM; + + /* Configure event node and add to the list */ + event_node->event = watch->event; + event_node->channel = watch->channel; + INIT_LIST_HEAD(&event_node->comp_list); + list_add(&event_node->l, &counter->next_events_list); + } + + /* Check if component watch has already been set before */ + list_for_each_entry(comp_node, &event_node->comp_list, l) + if (comp_node->parent == cfg->parent && + counter_comp_read_is_equal(comp_node->comp, cfg->comp)) { + err = -EINVAL; + goto exit_free_event_node; + } + + /* Allocate component node */ + comp_node = kmalloc(sizeof(*comp_node), GFP_KERNEL); + if (!comp_node) { + err = -ENOMEM; + goto exit_free_event_node; + } + *comp_node = *cfg; + + /* Add component node to event node */ + list_add_tail(&comp_node->l, &event_node->comp_list); + +exit_free_event_node: + /* Free event node if no one else is watching */ + if (list_empty(&event_node->comp_list)) { + list_del(&event_node->l); + kfree(event_node); + } + + return err; +} + +static int counter_enable_events(struct counter_device *const counter) +{ + unsigned long flags; + int err = 0; + + mutex_lock(&counter->n_events_list_lock); + spin_lock_irqsave(&counter->events_list_lock, flags); + + counter_events_list_free(&counter->events_list); + list_replace_init(&counter->next_events_list, + &counter->events_list); + + if (counter->ops->events_configure) + err = counter->ops->events_configure(counter); + + spin_unlock_irqrestore(&counter->events_list_lock, flags); + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static int counter_disable_events(struct counter_device *const counter) +{ + unsigned long flags; + int err = 0; + + spin_lock_irqsave(&counter->events_list_lock, flags); + + counter_events_list_free(&counter->events_list); + + if (counter->ops->events_configure) + err = counter->ops->events_configure(counter); + + spin_unlock_irqrestore(&counter->events_list_lock, flags); + + mutex_lock(&counter->n_events_list_lock); + + counter_events_list_free(&counter->next_events_list); + + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static int counter_add_watch(struct counter_device *const counter, + const unsigned long arg) +{ + void __user *const uwatch = (void __user *)arg; + struct counter_watch watch; + struct counter_comp_node comp_node = {}; + size_t parent, id; + struct counter_comp *ext; + size_t num_ext; + int err = 0; + + if (copy_from_user(&watch, uwatch, sizeof(watch))) + return -EFAULT; + + if (watch.component.type == COUNTER_COMPONENT_NONE) + goto no_component; + + parent = watch.component.parent; + + /* Configure parent component info for comp node */ + switch (watch.component.scope) { + case COUNTER_SCOPE_DEVICE: + ext = counter->ext; + num_ext = counter->num_ext; + break; + case COUNTER_SCOPE_SIGNAL: + if (parent >= counter->num_signals) + return -EINVAL; + parent = array_index_nospec(parent, counter->num_signals); + + comp_node.parent = counter->signals + parent; + + ext = counter->signals[parent].ext; + num_ext = counter->signals[parent].num_ext; + break; + case COUNTER_SCOPE_COUNT: + if (parent >= counter->num_counts) + return -EINVAL; + parent = array_index_nospec(parent, counter->num_counts); + + comp_node.parent = counter->counts + parent; + + ext = counter->counts[parent].ext; + num_ext = counter->counts[parent].num_ext; + break; + default: + return -EINVAL; + } + + id = watch.component.id; + + /* Configure component info for comp node */ + switch (watch.component.type) { + case COUNTER_COMPONENT_SIGNAL: + if (watch.component.scope != COUNTER_SCOPE_SIGNAL) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_SIGNAL_LEVEL; + comp_node.comp.signal_u32_read = counter->ops->signal_read; + break; + case COUNTER_COMPONENT_COUNT: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_U64; + comp_node.comp.count_u64_read = counter->ops->count_read; + break; + case COUNTER_COMPONENT_FUNCTION: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + + comp_node.comp.type = COUNTER_COMP_FUNCTION; + comp_node.comp.count_u32_read = counter->ops->function_read; + break; + case COUNTER_COMPONENT_SYNAPSE_ACTION: + if (watch.component.scope != COUNTER_SCOPE_COUNT) + return -EINVAL; + if (id >= counter->counts[parent].num_synapses) + return -EINVAL; + id = array_index_nospec(id, counter->counts[parent].num_synapses); + + comp_node.comp.type = COUNTER_COMP_SYNAPSE_ACTION; + comp_node.comp.action_read = counter->ops->action_read; + comp_node.comp.priv = counter->counts[parent].synapses + id; + break; + case COUNTER_COMPONENT_EXTENSION: + if (id >= num_ext) + return -EINVAL; + id = array_index_nospec(id, num_ext); + + comp_node.comp = ext[id]; + break; + default: + return -EINVAL; + } + if (!counter_comp_read_is_set(comp_node.comp)) + return -EOPNOTSUPP; + +no_component: + mutex_lock(&counter->n_events_list_lock); + + if (counter->ops->watch_validate) { + err = counter->ops->watch_validate(counter, &watch); + if (err < 0) + goto err_exit; + } + + comp_node.component = watch.component; + + err = counter_set_event_node(counter, &watch, &comp_node); + +err_exit: + mutex_unlock(&counter->n_events_list_lock); + + return err; +} + +static long counter_chrdev_ioctl(struct file *filp, unsigned int cmd, + unsigned long arg) +{ + struct counter_device *const counter = filp->private_data; + int ret = -ENODEV; + + mutex_lock(&counter->ops_exist_lock); + + if (!counter->ops) + goto out_unlock; + + switch (cmd) { + case COUNTER_ADD_WATCH_IOCTL: + ret = counter_add_watch(counter, arg); + break; + case COUNTER_ENABLE_EVENTS_IOCTL: + ret = counter_enable_events(counter); + break; + case COUNTER_DISABLE_EVENTS_IOCTL: + ret = counter_disable_events(counter); + break; + default: + ret = -ENOIOCTLCMD; + break; + } + +out_unlock: + mutex_unlock(&counter->ops_exist_lock); + + return ret; +} + +static int counter_chrdev_open(struct inode *inode, struct file *filp) +{ + struct counter_device *const counter = container_of(inode->i_cdev, + typeof(*counter), + chrdev); + + /* Ensure chrdev is not opened more than 1 at a time */ + if (!atomic_add_unless(&counter->chrdev_lock, 1, 1)) + return -EBUSY; + + get_device(&counter->dev); + filp->private_data = counter; + + return nonseekable_open(inode, filp); +} + +static int counter_chrdev_release(struct inode *inode, struct file *filp) +{ + struct counter_device *const counter = filp->private_data; + int ret = 0; + + mutex_lock(&counter->ops_exist_lock); + + if (!counter->ops) { + /* Free any lingering held memory */ + counter_events_list_free(&counter->events_list); + counter_events_list_free(&counter->next_events_list); + ret = -ENODEV; + goto out_unlock; + } + + ret = counter_disable_events(counter); + if (ret < 0) { + mutex_unlock(&counter->ops_exist_lock); + return ret; + } + +out_unlock: + mutex_unlock(&counter->ops_exist_lock); + + put_device(&counter->dev); + atomic_dec(&counter->chrdev_lock); + + return ret; +} + +static const struct file_operations counter_fops = { + .owner = THIS_MODULE, + .llseek = no_llseek, + .read = counter_chrdev_read, + .poll = counter_chrdev_poll, + .unlocked_ioctl = counter_chrdev_ioctl, + .open = counter_chrdev_open, + .release = counter_chrdev_release, +}; + +int counter_chrdev_add(struct counter_device *const counter) +{ + /* Initialize Counter events lists */ + INIT_LIST_HEAD(&counter->events_list); + INIT_LIST_HEAD(&counter->next_events_list); + spin_lock_init(&counter->events_list_lock); + mutex_init(&counter->n_events_list_lock); + init_waitqueue_head(&counter->events_wait); + mutex_init(&counter->events_lock); + + /* Initialize character device */ + atomic_set(&counter->chrdev_lock, 0); + cdev_init(&counter->chrdev, &counter_fops); + + /* Allocate Counter events queue */ + return kfifo_alloc(&counter->events, 64, GFP_KERNEL); +} + +void counter_chrdev_remove(struct counter_device *const counter) +{ + kfifo_free(&counter->events); +} + +static int counter_get_data(struct counter_device *const counter, + const struct counter_comp_node *const comp_node, + u64 *const value) +{ + const struct counter_comp *const comp = &comp_node->comp; + void *const parent = comp_node->parent; + u8 value_u8 = 0; + u32 value_u32 = 0; + int ret; + + if (comp_node->component.type == COUNTER_COMPONENT_NONE) + return 0; + + switch (comp->type) { + case COUNTER_COMP_U8: + case COUNTER_COMP_BOOL: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + ret = comp->device_u8_read(counter, &value_u8); + break; + case COUNTER_SCOPE_SIGNAL: + ret = comp->signal_u8_read(counter, parent, &value_u8); + break; + case COUNTER_SCOPE_COUNT: + ret = comp->count_u8_read(counter, parent, &value_u8); + break; + } + *value = value_u8; + return ret; + case COUNTER_COMP_SIGNAL_LEVEL: + case COUNTER_COMP_FUNCTION: + case COUNTER_COMP_ENUM: + case COUNTER_COMP_COUNT_DIRECTION: + case COUNTER_COMP_COUNT_MODE: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + ret = comp->device_u32_read(counter, &value_u32); + break; + case COUNTER_SCOPE_SIGNAL: + ret = comp->signal_u32_read(counter, parent, + &value_u32); + break; + case COUNTER_SCOPE_COUNT: + ret = comp->count_u32_read(counter, parent, &value_u32); + break; + } + *value = value_u32; + return ret; + case COUNTER_COMP_U64: + switch (comp_node->component.scope) { + case COUNTER_SCOPE_DEVICE: + return comp->device_u64_read(counter, value); + case COUNTER_SCOPE_SIGNAL: + return comp->signal_u64_read(counter, parent, value); + case COUNTER_SCOPE_COUNT: + return comp->count_u64_read(counter, parent, value); + default: + return -EINVAL; + } + case COUNTER_COMP_SYNAPSE_ACTION: + ret = comp->action_read(counter, parent, comp->priv, + &value_u32); + *value = value_u32; + return ret; + default: + return -EINVAL; + } +} + +/** + * counter_push_event - queue event for userspace reading + * @counter: pointer to Counter structure + * @event: triggered event + * @channel: event channel + * + * Note: If no one is watching for the respective event, it is silently + * discarded. + */ +void counter_push_event(struct counter_device *const counter, const u8 event, + const u8 channel) +{ + struct counter_event ev; + unsigned int copied = 0; + unsigned long flags; + struct counter_event_node *event_node; + struct counter_comp_node *comp_node; + + ev.timestamp = ktime_get_ns(); + ev.watch.event = event; + ev.watch.channel = channel; + + /* Could be in an interrupt context, so use a spin lock */ + spin_lock_irqsave(&counter->events_list_lock, flags); + + /* Search for event in the list */ + list_for_each_entry(event_node, &counter->events_list, l) + if (event_node->event == event && + event_node->channel == channel) + break; + + /* If event is not in the list */ + if (&event_node->l == &counter->events_list) + goto exit_early; + + /* Read and queue relevant comp for userspace */ + list_for_each_entry(comp_node, &event_node->comp_list, l) { + ev.watch.component = comp_node->component; + ev.status = -counter_get_data(counter, comp_node, &ev.value); + + copied += kfifo_in(&counter->events, &ev, 1); + } + +exit_early: + spin_unlock_irqrestore(&counter->events_list_lock, flags); + + if (copied) + wake_up_poll(&counter->events_wait, EPOLLIN); +} +EXPORT_SYMBOL_GPL(counter_push_event); diff --git a/drivers/counter/counter-chrdev.h b/drivers/counter/counter-chrdev.h new file mode 100644 index 000000000000..5529d16703c4 --- /dev/null +++ b/drivers/counter/counter-chrdev.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Counter character device interface + * Copyright (C) 2020 William Breathitt Gray + */ +#ifndef _COUNTER_CHRDEV_H_ +#define _COUNTER_CHRDEV_H_ + +#include + +int counter_chrdev_add(struct counter_device *const counter); +void counter_chrdev_remove(struct counter_device *const counter); + +#endif /* _COUNTER_CHRDEV_H_ */ diff --git a/drivers/counter/counter-core.c b/drivers/counter/counter-core.c index 3cda2c47bacb..5acc54539623 100644 --- a/drivers/counter/counter-core.c +++ b/drivers/counter/counter-core.c @@ -3,14 +3,22 @@ * Generic Counter interface * Copyright (C) 2020 William Breathitt Gray */ +#include #include #include +#include #include +#include #include #include #include +#include #include +#include +#include +#include +#include "counter-chrdev.h" #include "counter-sysfs.h" /* Provides a unique ID for each counter device */ @@ -18,6 +26,9 @@ static DEFINE_IDA(counter_ida); static void counter_device_release(struct device *dev) { + struct counter_device *const counter = dev_get_drvdata(dev); + + counter_chrdev_remove(counter); ida_free(&counter_ida, dev->id); } @@ -31,6 +42,8 @@ static struct bus_type counter_bus_type = { .dev_name = "counter", }; +static dev_t counter_devt; + /** * counter_register - register Counter to the system * @counter: pointer to Counter to register @@ -53,10 +66,13 @@ int counter_register(struct counter_device *const counter) if (id < 0) return id; + mutex_init(&counter->ops_exist_lock); + /* Configure device structure for Counter */ dev->id = id; dev->type = &counter_device_type; dev->bus = &counter_bus_type; + dev->devt = MKDEV(MAJOR(counter_devt), id); if (counter->parent) { dev->parent = counter->parent; dev->of_node = counter->parent->of_node; @@ -64,18 +80,22 @@ int counter_register(struct counter_device *const counter) device_initialize(dev); dev_set_drvdata(dev, counter); - /* Add Counter sysfs attributes */ err = counter_sysfs_add(counter); if (err < 0) goto err_free_id; - /* Add device to system */ - err = device_add(dev); + err = counter_chrdev_add(counter); if (err < 0) goto err_free_id; + err = cdev_device_add(&counter->chrdev, dev); + if (err < 0) + goto err_remove_chrdev; + return 0; +err_remove_chrdev: + counter_chrdev_remove(counter); err_free_id: put_device(dev); return err; @@ -93,7 +113,16 @@ void counter_unregister(struct counter_device *const counter) if (!counter) return; - device_unregister(&counter->dev); + cdev_device_del(&counter->chrdev, &counter->dev); + + mutex_lock(&counter->ops_exist_lock); + + counter->ops = NULL; + wake_up(&counter->events_wait); + + mutex_unlock(&counter->ops_exist_lock); + + put_device(&counter->dev); } EXPORT_SYMBOL_GPL(counter_unregister); @@ -127,13 +156,30 @@ int devm_counter_register(struct device *dev, } EXPORT_SYMBOL_GPL(devm_counter_register); +#define COUNTER_DEV_MAX 256 + static int __init counter_init(void) { - return bus_register(&counter_bus_type); + int err; + + err = bus_register(&counter_bus_type); + if (err < 0) + return err; + + err = alloc_chrdev_region(&counter_devt, 0, COUNTER_DEV_MAX, "counter"); + if (err < 0) + goto err_unregister_bus; + + return 0; + +err_unregister_bus: + bus_unregister(&counter_bus_type); + return err; } static void __exit counter_exit(void) { + unregister_chrdev_region(counter_devt, COUNTER_DEV_MAX); bus_unregister(&counter_bus_type); } diff --git a/include/linux/counter.h b/include/linux/counter.h index 7c9f7e23953a..22b14a552b1d 100644 --- a/include/linux/counter.h +++ b/include/linux/counter.h @@ -6,9 +6,14 @@ #ifndef _COUNTER_H_ #define _COUNTER_H_ +#include #include #include +#include +#include +#include #include +#include #include struct counter_device; @@ -199,6 +204,20 @@ struct counter_count { size_t num_ext; }; +/** + * struct counter_event_node - Counter Event node + * @l: list of current watching Counter events + * @event: event that triggers + * @channel: event channel + * @comp_list: list of components to watch when event triggers + */ +struct counter_event_node { + struct list_head l; + u8 event; + u8 channel; + struct list_head comp_list; +}; + /** * struct counter_ops - Callbacks from driver * @signal_read: optional read callback for Signals. The read level of @@ -222,6 +241,13 @@ struct counter_count { * @action_write: optional write callback for Synapse action modes. The * action mode to write for the respective Synapse is * passed in via the action parameter. + * @events_configure: optional write callback to configure events. The list of + * struct counter_event_node may be accessed via the + * events_list member of the counter parameter. + * @watch_validate: optional callback to validate a watch. The Counter + * component watch configuration is passed in via the watch + * parameter. A return value of 0 indicates a valid Counter + * component watch configuration. */ struct counter_ops { int (*signal_read)(struct counter_device *counter, @@ -245,6 +271,9 @@ struct counter_ops { struct counter_count *count, struct counter_synapse *synapse, enum counter_synapse_action action); + int (*events_configure)(struct counter_device *counter); + int (*watch_validate)(struct counter_device *counter, + const struct counter_watch *watch); }; /** @@ -260,6 +289,16 @@ struct counter_ops { * @num_ext: number of Counter device extensions specified in @ext * @priv: optional private data supplied by driver * @dev: internal device structure + * @chrdev: internal character device structure + * @events_list: list of current watching Counter events + * @events_list_lock: lock to protect Counter events list operations + * @next_events_list: list of next watching Counter events + * @n_events_list_lock: lock to protect Counter next events list operations + * @events: queue of detected Counter events + * @events_wait: wait queue to allow blocking reads of Counter events + * @events_lock: lock to protect Counter events queue read operations + * @chrdev_lock: lock to limit chrdev to a single open at a time + * @ops_exist_lock: lock to prevent use during removal */ struct counter_device { const char *name; @@ -278,12 +317,29 @@ struct counter_device { void *priv; struct device dev; + struct cdev chrdev; + struct list_head events_list; + spinlock_t events_list_lock; + struct list_head next_events_list; + struct mutex n_events_list_lock; + DECLARE_KFIFO_PTR(events, struct counter_event); + wait_queue_head_t events_wait; + struct mutex events_lock; + /* + * chrdev_lock is locked by counter_chrdev_open() and unlocked by + * counter_chrdev_release(), so a mutex is not possible here because + * chrdev_lock will invariably be held when returning to user space + */ + atomic_t chrdev_lock; + struct mutex ops_exist_lock; }; int counter_register(struct counter_device *const counter); void counter_unregister(struct counter_device *const counter); int devm_counter_register(struct device *dev, struct counter_device *const counter); +void counter_push_event(struct counter_device *const counter, const u8 event, + const u8 channel); #define COUNTER_COMP_DEVICE_U8(_name, _read, _write) \ { \ diff --git a/include/uapi/linux/counter.h b/include/uapi/linux/counter.h index 6113938a6044..d0aa95aeff7b 100644 --- a/include/uapi/linux/counter.h +++ b/include/uapi/linux/counter.h @@ -6,6 +6,19 @@ #ifndef _UAPI_COUNTER_H_ #define _UAPI_COUNTER_H_ +#include +#include + +/* Component type definitions */ +enum counter_component_type { + COUNTER_COMPONENT_NONE, + COUNTER_COMPONENT_SIGNAL, + COUNTER_COMPONENT_COUNT, + COUNTER_COMPONENT_FUNCTION, + COUNTER_COMPONENT_SYNAPSE_ACTION, + COUNTER_COMPONENT_EXTENSION, +}; + /* Component scope definitions */ enum counter_scope { COUNTER_SCOPE_DEVICE, @@ -13,6 +26,91 @@ enum counter_scope { COUNTER_SCOPE_COUNT, }; +/** + * struct counter_component - Counter component identification + * @type: component type (one of enum counter_component_type) + * @scope: component scope (one of enum counter_scope) + * @parent: parent ID (matching the ID suffix of the respective parent sysfs + * path as described by the ABI documentation file + * Documentation/ABI/testing/sysfs-bus-counter) + * @id: component ID (matching the ID provided by the respective *_component_id + * sysfs attribute of the desired component) + * + * For example, if the Count 2 ceiling extension of Counter device 4 is desired, + * set type equal to COUNTER_COMPONENT_EXTENSION, scope equal to + * COUNTER_COUNT_SCOPE, parent equal to 2, and id equal to the value provided by + * the respective /sys/bus/counter/devices/counter4/count2/ceiling_component_id + * sysfs attribute. + */ +struct counter_component { + __u8 type; + __u8 scope; + __u8 parent; + __u8 id; +}; + +/* Event type definitions */ +enum counter_event_type { + /* Count value increased past ceiling */ + COUNTER_EVENT_OVERFLOW, + /* Count value decreased past floor */ + COUNTER_EVENT_UNDERFLOW, + /* Count value increased past ceiling, or decreased past floor */ + COUNTER_EVENT_OVERFLOW_UNDERFLOW, + /* Count value reached threshold */ + COUNTER_EVENT_THRESHOLD, + /* Index signal detected */ + COUNTER_EVENT_INDEX, +}; + +/** + * struct counter_watch - Counter component watch configuration + * @component: component to watch when event triggers + * @event: event that triggers (one of enum counter_event_type) + * @channel: event channel (typically 0 unless the device supports concurrent + * events of the same type) + */ +struct counter_watch { + struct counter_component component; + __u8 event; + __u8 channel; +}; + +/* + * Queues a Counter watch for the specified event. + * + * The queued watches will not be applied until COUNTER_ENABLE_EVENTS_IOCTL is + * called. + */ +#define COUNTER_ADD_WATCH_IOCTL _IOW(0x3E, 0x00, struct counter_watch) +/* + * Enables monitoring the events specified by the Counter watches that were + * queued by COUNTER_ADD_WATCH_IOCTL. + * + * If events are already enabled, the new set of watches replaces the old one. + * Calling this ioctl also has the effect of clearing the queue of watches added + * by COUNTER_ADD_WATCH_IOCTL. + */ +#define COUNTER_ENABLE_EVENTS_IOCTL _IO(0x3E, 0x01) +/* + * Stops monitoring the previously enabled events. + */ +#define COUNTER_DISABLE_EVENTS_IOCTL _IO(0x3E, 0x02) + +/** + * struct counter_event - Counter event data + * @timestamp: best estimate of time of event occurrence, in nanoseconds + * @value: component value + * @watch: component watch configuration + * @status: return status (system error number) + */ +struct counter_event { + __aligned_u64 timestamp; + __aligned_u64 value; + struct counter_watch watch; + __u8 status; +}; + /* Count direction values */ enum counter_count_direction { COUNTER_COUNT_DIRECTION_FORWARD, -- cgit v1.2.3 From b416beb25d9317499c823aea1522eefd8d72ea36 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Mon, 18 Oct 2021 11:29:34 +0800 Subject: mctp: unify sockaddr_mctp types Use the more precise __kernel_sa_family_t for smctp_family, to match struct sockaddr. Also, use an unsigned int for the network member; negative networks don't make much sense. We're already using unsigned for mctp_dev and mctp_skb_cb, but need to change mctp_sock to suit. Fixes: 60fc63981693 ("mctp: Add sockaddr_mctp to uapi") Signed-off-by: Jeremy Kerr Acked-by: Eugene Syromiatnikov Signed-off-by: David S. Miller --- Documentation/networking/mctp.rst | 10 +++++----- include/net/mctp.h | 2 +- include/uapi/linux/mctp.h | 5 +++-- 3 files changed, 9 insertions(+), 8 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/mctp.rst b/Documentation/networking/mctp.rst index 6100cdc220f6..fa7730dbf7b9 100644 --- a/Documentation/networking/mctp.rst +++ b/Documentation/networking/mctp.rst @@ -59,11 +59,11 @@ specified with a ``sockaddr`` type, with a single-byte endpoint address: }; struct sockaddr_mctp { - unsigned short int smctp_family; - int smctp_network; - struct mctp_addr smctp_addr; - __u8 smctp_type; - __u8 smctp_tag; + __kernel_sa_family_t smctp_family; + unsigned int smctp_network; + struct mctp_addr smctp_addr; + __u8 smctp_type; + __u8 smctp_tag; }; #define MCTP_NET_ANY 0x0 diff --git a/include/net/mctp.h b/include/net/mctp.h index a824d47c3c6d..ffd2c23bd76d 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -54,7 +54,7 @@ struct mctp_sock { struct sock sk; /* bind() params */ - int bind_net; + unsigned int bind_net; mctp_eid_t bind_addr; __u8 bind_type; diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 52b54d13f385..f384962d8ff2 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -10,6 +10,7 @@ #define __UAPI_MCTP_H #include +#include typedef __u8 mctp_eid_t; @@ -18,8 +19,8 @@ struct mctp_addr { }; struct sockaddr_mctp { - unsigned short int smctp_family; - int smctp_network; + __kernel_sa_family_t smctp_family; + unsigned int smctp_network; struct mctp_addr smctp_addr; __u8 smctp_type; __u8 smctp_tag; -- cgit v1.2.3 From 5a20dd46b8b8459382685969cf0f196ae9fb9766 Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Mon, 18 Oct 2021 11:29:35 +0800 Subject: mctp: Be explicit about struct sockaddr_mctp padding We currently have some implicit padding in struct sockaddr_mctp. This patch makes this padding explicit, and ensures we have consistent layout on platforms with <32bit alignmnent. Fixes: 60fc63981693 ("mctp: Add sockaddr_mctp to uapi") Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/uapi/linux/mctp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index f384962d8ff2..6acd4ccafbf7 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -20,10 +20,12 @@ struct mctp_addr { struct sockaddr_mctp { __kernel_sa_family_t smctp_family; + __u16 __smctp_pad0; unsigned int smctp_network; struct mctp_addr smctp_addr; __u8 smctp_type; __u8 smctp_tag; + __u8 __smctp_pad1; }; #define MCTP_NET_ANY 0x0 -- cgit v1.2.3 From 7bbbbfaa7a1b0b03890f25fba5f28bb8c7ef145a Mon Sep 17 00:00:00 2001 From: Alvin Šipraga Date: Mon, 18 Oct 2021 11:37:56 +0200 Subject: ether: add EtherType for proprietary Realtek protocols MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add a new EtherType ETH_P_REALTEK to the if_ether.h uapi header. The EtherType 0x8899 is used in a number of different protocols from Realtek Semiconductor Corp [1], so no general assumptions should be made when trying to decode such packets. Observed protocols include: 0x1 - Realtek Remote Control protocol [2] 0x2 - Echo protocol [2] 0x3 - Loop detection protocol [2] 0x4 - RTL8365MB 4- and 8-byte switch CPU tag protocols [3] 0x9 - RTL8306 switch CPU tag protocol [4] 0xA - RTL8366RB switch CPU tag protocol [4] [1] https://lore.kernel.org/netdev/CACRpkdYQthFgjwVzHyK3DeYUOdcYyWmdjDPG=Rf9B3VrJ12Rzg@mail.gmail.com/ [2] https://www.wireshark.org/lists/ethereal-dev/200409/msg00090.html [3] https://lore.kernel.org/netdev/20210822193145.1312668-4-alvin@pqrs.dk/ [4] https://lore.kernel.org/netdev/20200708122537.1341307-2-linus.walleij@linaro.org/ Suggested-by: Andrew Lunn Signed-off-by: Alvin Šipraga Reviewed-by: Vladimir Oltean Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5f589c7a8382..5da4ee234e0b 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -86,6 +86,7 @@ * over Ethernet */ #define ETH_P_PAE 0x888E /* Port Access Entity (IEEE 802.1X) */ +#define ETH_P_REALTEK 0x8899 /* Multiple proprietary protocols */ #define ETH_P_AOE 0x88A2 /* ATA over Ethernet */ #define ETH_P_8021AD 0x88A8 /* 802.1ad Service VLAN */ #define ETH_P_802_EX1 0x88B5 /* 802.1 Local Experimental 1. */ -- cgit v1.2.3 From 917425f71f36ce6f61841497040e10d0166106d8 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:27 +0200 Subject: rtc: add alarm related features Add more alarm related features to be declared by drivers. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-2-alexandre.belloni@bootlin.com --- include/uapi/linux/rtc.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index f950bff75e97..f4037c541925 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -114,7 +114,9 @@ struct rtc_pll_info { #define RTC_FEATURE_ALARM 0 #define RTC_FEATURE_ALARM_RES_MINUTE 1 #define RTC_FEATURE_NEED_WEEK_DAY 2 -#define RTC_FEATURE_CNT 3 +#define RTC_FEATURE_ALARM_RES_2S 3 +#define RTC_FEATURE_UPDATE_INTERRUPT 4 +#define RTC_FEATURE_CNT 5 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 6a8af1b6568ad9ee08a419fb12c793f7992cf8a4 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:28 +0200 Subject: rtc: add parameter ioctl Add an ioctl allowing to get and set extra parameters for an RTC. For now, only handle getting available features. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-3-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 40 ++++++++++++++++++++++++++++++++++++++++ include/uapi/linux/rtc.h | 18 ++++++++++++++++++ 2 files changed, 58 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 5b8ebe86124a..143c097eff0f 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -208,6 +208,7 @@ static long rtc_dev_ioctl(struct file *file, const struct rtc_class_ops *ops = rtc->ops; struct rtc_time tm; struct rtc_wkalrm alarm; + struct rtc_param param; void __user *uarg = (void __user *)arg; err = mutex_lock_interruptible(&rtc->ops_lock); @@ -221,6 +222,7 @@ static long rtc_dev_ioctl(struct file *file, switch (cmd) { case RTC_EPOCH_SET: case RTC_SET_TIME: + case RTC_PARAM_SET: if (!capable(CAP_SYS_TIME)) err = -EACCES; break; @@ -382,6 +384,44 @@ static long rtc_dev_ioctl(struct file *file, err = -EFAULT; return err; + case RTC_PARAM_GET: + if (copy_from_user(¶m, uarg, sizeof(param))) { + mutex_unlock(&rtc->ops_lock); + return -EFAULT; + } + + switch(param.param) { + long offset; + case RTC_PARAM_FEATURES: + if (param.index != 0) + err = -EINVAL; + param.uvalue = rtc->features[0]; + break; + + default: + err = -EINVAL; + } + + if (!err) + if (copy_to_user(uarg, ¶m, sizeof(param))) + err = -EFAULT; + + break; + + case RTC_PARAM_SET: + if (copy_from_user(¶m, uarg, sizeof(param))) { + mutex_unlock(&rtc->ops_lock); + return -EFAULT; + } + + switch(param.param) { + case RTC_PARAM_FEATURES: + default: + err = -EINVAL; + } + + break; + default: /* Finally try the driver's ioctl interface */ if (ops->ioctl) { diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index f4037c541925..3241f9ecc639 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -14,6 +14,7 @@ #include #include +#include /* * The struct used to pass data via the following ioctl. Similar to the @@ -66,6 +67,17 @@ struct rtc_pll_info { long pll_clock; /* base PLL frequency */ }; +struct rtc_param { + __u64 param; + union { + __u64 uvalue; + __s64 svalue; + __u64 ptr; + }; + __u32 index; + __u32 __pad; +}; + /* * ioctl calls that are permitted to the /dev/rtc interface, if * any of the RTC drivers are enabled. @@ -95,6 +107,9 @@ struct rtc_pll_info { #define RTC_PLL_GET _IOR('p', 0x11, struct rtc_pll_info) /* Get PLL correction */ #define RTC_PLL_SET _IOW('p', 0x12, struct rtc_pll_info) /* Set PLL correction */ +#define RTC_PARAM_GET _IOW('p', 0x13, struct rtc_param) /* Get parameter */ +#define RTC_PARAM_SET _IOW('p', 0x14, struct rtc_param) /* Set parameter */ + #define RTC_VL_DATA_INVALID _BITUL(0) /* Voltage too low, RTC data is invalid */ #define RTC_VL_BACKUP_LOW _BITUL(1) /* Backup voltage is low */ #define RTC_VL_BACKUP_EMPTY _BITUL(2) /* Backup empty or not present */ @@ -118,6 +133,9 @@ struct rtc_pll_info { #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CNT 5 +/* parameter list */ +#define RTC_PARAM_FEATURES 0 + #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 2268551935dbf1abcbb4d4fb7b1ad74dbe0d1be0 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:29 +0200 Subject: rtc: expose correction feature Add a new feature for RTCs able to correct the oscillator imprecision. This is also called offset or trimming. Such drivers have a .set_offset callback, use that to set the feature bit from the core. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-4-alexandre.belloni@bootlin.com --- drivers/rtc/class.c | 3 +++ include/uapi/linux/rtc.h | 3 ++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/drivers/rtc/class.c b/drivers/rtc/class.c index dbccd71589b9..2e0cbc190a8a 100644 --- a/drivers/rtc/class.c +++ b/drivers/rtc/class.c @@ -389,6 +389,9 @@ int __devm_rtc_register_device(struct module *owner, struct rtc_device *rtc) if (!rtc->ops->set_alarm) clear_bit(RTC_FEATURE_ALARM, rtc->features); + if (rtc->ops->set_offset) + set_bit(RTC_FEATURE_CORRECTION, rtc->features); + rtc->owner = owner; rtc_device_get_offset(rtc); diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 3241f9ecc639..c83bb9a4fa4f 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -131,7 +131,8 @@ struct rtc_param { #define RTC_FEATURE_NEED_WEEK_DAY 2 #define RTC_FEATURE_ALARM_RES_2S 3 #define RTC_FEATURE_UPDATE_INTERRUPT 4 -#define RTC_FEATURE_CNT 5 +#define RTC_FEATURE_CORRECTION 5 +#define RTC_FEATURE_CNT 6 /* parameter list */ #define RTC_PARAM_FEATURES 0 -- cgit v1.2.3 From a6d8c6e1a5c6fb982964861dc84c0c7cb0151c7c Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:30 +0200 Subject: rtc: add correction parameter Add a new parameter allowing the get and set the correction using ioctls instead of just sysfs. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-5-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 19 +++++++++++++++++++ include/uapi/linux/rtc.h | 1 + 2 files changed, 20 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index 143c097eff0f..abee1fc4705e 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -398,6 +398,16 @@ static long rtc_dev_ioctl(struct file *file, param.uvalue = rtc->features[0]; break; + case RTC_PARAM_CORRECTION: + mutex_unlock(&rtc->ops_lock); + if (param.index != 0) + return -EINVAL; + err = rtc_read_offset(rtc, &offset); + mutex_lock(&rtc->ops_lock); + if (err == 0) + param.svalue = offset; + break; + default: err = -EINVAL; } @@ -416,6 +426,15 @@ static long rtc_dev_ioctl(struct file *file, switch(param.param) { case RTC_PARAM_FEATURES: + err = -EINVAL; + break; + + case RTC_PARAM_CORRECTION: + mutex_unlock(&rtc->ops_lock); + if (param.index != 0) + return -EINVAL; + return rtc_set_offset(rtc, param.svalue); + default: err = -EINVAL; } diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index c83bb9a4fa4f..5debe82439c2 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -136,6 +136,7 @@ struct rtc_param { /* parameter list */ #define RTC_PARAM_FEATURES 0 +#define RTC_PARAM_CORRECTION 1 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From 0d20e9fb1262b1f9ac895b287db892bc75b05b84 Mon Sep 17 00:00:00 2001 From: Alexandre Belloni Date: Mon, 18 Oct 2021 17:19:31 +0200 Subject: rtc: add BSM parameter BSM or Backup Switch Mode is a common feature on RTCs, allowing to select how the RTC will decide when to switch from its primary power supply to the backup power supply. It is necessary to be able to set it from userspace as there are uses cases where it has to be done dynamically. Supported values are: RTC_BSM_DISABLED: disabled RTC_BSM_DIRECT: switching will happen as soon as Vbackup > Vdd RTC_BSM_LEVEL: switching will happen around a threshold, usually with an hysteresis RTC_BSM_STANDBY: switching will not happen until Vdd > Vbackup, this is useful to ensure the RTC doesn't draw any power until the device is first powered on. Signed-off-by: Alexandre Belloni Link: https://lore.kernel.org/r/20211018151933.76865-6-alexandre.belloni@bootlin.com --- drivers/rtc/dev.c | 10 ++++++++-- include/linux/rtc.h | 2 ++ include/uapi/linux/rtc.h | 9 ++++++++- 3 files changed, 18 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/rtc/dev.c b/drivers/rtc/dev.c index abee1fc4705e..e104972a28fd 100644 --- a/drivers/rtc/dev.c +++ b/drivers/rtc/dev.c @@ -409,7 +409,10 @@ static long rtc_dev_ioctl(struct file *file, break; default: - err = -EINVAL; + if (rtc->ops->param_get) + err = rtc->ops->param_get(rtc->dev.parent, ¶m); + else + err = -EINVAL; } if (!err) @@ -436,7 +439,10 @@ static long rtc_dev_ioctl(struct file *file, return rtc_set_offset(rtc, param.svalue); default: - err = -EINVAL; + if (rtc->ops->param_set) + err = rtc->ops->param_set(rtc->dev.parent, ¶m); + else + err = -EINVAL; } break; diff --git a/include/linux/rtc.h b/include/linux/rtc.h index 354e0843ab17..47fd1c2d3a57 100644 --- a/include/linux/rtc.h +++ b/include/linux/rtc.h @@ -66,6 +66,8 @@ struct rtc_class_ops { int (*alarm_irq_enable)(struct device *, unsigned int enabled); int (*read_offset)(struct device *, long *offset); int (*set_offset)(struct device *, long offset); + int (*param_get)(struct device *, struct rtc_param *param); + int (*param_set)(struct device *, struct rtc_param *param); }; struct rtc_device; diff --git a/include/uapi/linux/rtc.h b/include/uapi/linux/rtc.h index 5debe82439c2..03e5b776e597 100644 --- a/include/uapi/linux/rtc.h +++ b/include/uapi/linux/rtc.h @@ -132,11 +132,18 @@ struct rtc_param { #define RTC_FEATURE_ALARM_RES_2S 3 #define RTC_FEATURE_UPDATE_INTERRUPT 4 #define RTC_FEATURE_CORRECTION 5 -#define RTC_FEATURE_CNT 6 +#define RTC_FEATURE_BACKUP_SWITCH_MODE 6 +#define RTC_FEATURE_CNT 7 /* parameter list */ #define RTC_PARAM_FEATURES 0 #define RTC_PARAM_CORRECTION 1 +#define RTC_PARAM_BACKUP_SWITCH_MODE 2 + +#define RTC_BSM_DISABLED 0 +#define RTC_BSM_DIRECT 1 +#define RTC_BSM_LEVEL 2 +#define RTC_BSM_STANDBY 3 #define RTC_MAX_FREQ 8192 -- cgit v1.2.3 From c68dc1b577eabd5605c6c7c08f3e07ae18d30d5d Mon Sep 17 00:00:00 2001 From: Oliver Upton Date: Thu, 16 Sep 2021 18:15:35 +0000 Subject: KVM: x86: Report host tsc and realtime values in KVM_GET_CLOCK Handling the migration of TSCs correctly is difficult, in part because Linux does not provide userspace with the ability to retrieve a (TSC, realtime) clock pair for a single instant in time. In lieu of a more convenient facility, KVM can report similar information in the kvm_clock structure. Provide userspace with a host TSC & realtime pair iff the realtime clock is based on the TSC. If userspace provides KVM_SET_CLOCK with a valid realtime value, advance the KVM clock by the amount of elapsed time. Do not step the KVM clock backwards, though, as it is a monotonic oscillator. Suggested-by: Paolo Bonzini Signed-off-by: Oliver Upton Signed-off-by: Paolo Bonzini Message-Id: <20210916181538.968978-5-oupton@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 48 +++++++++++++++++++++++++++++++++-------- arch/x86/include/asm/kvm_host.h | 3 +++ arch/x86/kvm/x86.c | 47 ++++++++++++++++++++++++++++------------ include/uapi/linux/kvm.h | 7 +++++- 4 files changed, 81 insertions(+), 24 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 0c0bf26426b3..3b093d6dbe22 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -1010,20 +1010,37 @@ such as migration. When KVM_CAP_ADJUST_CLOCK is passed to KVM_CHECK_EXTENSION, it returns the set of bits that KVM can return in struct kvm_clock_data's flag member. -The only flag defined now is KVM_CLOCK_TSC_STABLE. If set, the returned -value is the exact kvmclock value seen by all VCPUs at the instant -when KVM_GET_CLOCK was called. If clear, the returned value is simply -CLOCK_MONOTONIC plus a constant offset; the offset can be modified -with KVM_SET_CLOCK. KVM will try to make all VCPUs follow this clock, -but the exact value read by each VCPU could differ, because the host -TSC is not stable. +The following flags are defined: + +KVM_CLOCK_TSC_STABLE + If set, the returned value is the exact kvmclock + value seen by all VCPUs at the instant when KVM_GET_CLOCK was called. + If clear, the returned value is simply CLOCK_MONOTONIC plus a constant + offset; the offset can be modified with KVM_SET_CLOCK. KVM will try + to make all VCPUs follow this clock, but the exact value read by each + VCPU could differ, because the host TSC is not stable. + +KVM_CLOCK_REALTIME + If set, the `realtime` field in the kvm_clock_data + structure is populated with the value of the host's real time + clocksource at the instant when KVM_GET_CLOCK was called. If clear, + the `realtime` field does not contain a value. + +KVM_CLOCK_HOST_TSC + If set, the `host_tsc` field in the kvm_clock_data + structure is populated with the value of the host's timestamp counter (TSC) + at the instant when KVM_GET_CLOCK was called. If clear, the `host_tsc` field + does not contain a value. :: struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; @@ -1040,12 +1057,25 @@ Sets the current timestamp of kvmclock to the value specified in its parameter. In conjunction with KVM_GET_CLOCK, it is used to ensure monotonicity on scenarios such as migration. +The following flags can be passed: + +KVM_CLOCK_REALTIME + If set, KVM will compare the value of the `realtime` field + with the value of the host's real time clocksource at the instant when + KVM_SET_CLOCK was called. The difference in elapsed time is added to the final + kvmclock value that will be provided to guests. + +Other flags returned by ``KVM_GET_CLOCK`` are accepted but ignored. + :: struct kvm_clock_data { __u64 clock; /* kvmclock current value */ __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5271fce6cd65..8b16fa504cd4 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1942,4 +1942,7 @@ int kvm_cpu_dirty_log_size(void); int alloc_all_memslots_rmaps(struct kvm *kvm); +#define KVM_CLOCK_VALID_FLAGS \ + (KVM_CLOCK_TSC_STABLE | KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC) + #endif /* _ASM_X86_KVM_HOST_H */ diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 3ea4f6ef2474..d3631d149187 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -2787,6 +2787,7 @@ static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) struct pvclock_vcpu_time_info hv_clock; unsigned long flags; + data->flags = 0; spin_lock_irqsave(&ka->pvclock_gtod_sync_lock, flags); if (!ka->use_master_clock) { spin_unlock_irqrestore(&ka->pvclock_gtod_sync_lock, flags); @@ -2803,10 +2804,20 @@ static void get_kvmclock(struct kvm *kvm, struct kvm_clock_data *data) get_cpu(); if (__this_cpu_read(cpu_tsc_khz)) { +#ifdef CONFIG_X86_64 + struct timespec64 ts; + + if (kvm_get_walltime_and_clockread(&ts, &data->host_tsc)) { + data->realtime = ts.tv_nsec + NSEC_PER_SEC * ts.tv_sec; + data->flags |= KVM_CLOCK_REALTIME | KVM_CLOCK_HOST_TSC; + } else +#endif + data->host_tsc = rdtsc(); + kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL, &hv_clock.tsc_shift, &hv_clock.tsc_to_system_mul); - data->clock = __pvclock_read_cycles(&hv_clock, rdtsc()); + data->clock = __pvclock_read_cycles(&hv_clock, data->host_tsc); } else { data->clock = get_kvmclock_base_ns() + ka->kvmclock_offset; } @@ -2818,12 +2829,6 @@ u64 get_kvmclock_ns(struct kvm *kvm) { struct kvm_clock_data data; - /* - * Zero flags as it's accessed RMW, leave everything else uninitialized - * as clock is always written and no other fields are consumed. - */ - data.flags = 0; - get_kvmclock(kvm, &data); return data.clock; } @@ -4050,7 +4055,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext) r = KVM_SYNC_X86_VALID_FIELDS; break; case KVM_CAP_ADJUST_CLOCK: - r = KVM_CLOCK_TSC_STABLE; + r = KVM_CLOCK_VALID_FLAGS; break; case KVM_CAP_X86_DISABLE_EXITS: r |= KVM_X86_DISABLE_EXITS_HLT | KVM_X86_DISABLE_EXITS_PAUSE | @@ -5847,12 +5852,16 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) { struct kvm_arch *ka = &kvm->arch; struct kvm_clock_data data; - u64 now_ns; + u64 now_raw_ns; if (copy_from_user(&data, argp, sizeof(data))) return -EFAULT; - if (data.flags) + /* + * Only KVM_CLOCK_REALTIME is used, but allow passing the + * result of KVM_GET_CLOCK back to KVM_SET_CLOCK. + */ + if (data.flags & ~KVM_CLOCK_VALID_FLAGS) return -EINVAL; kvm_hv_invalidate_tsc_page(kvm); @@ -5866,11 +5875,21 @@ static int kvm_vm_ioctl_set_clock(struct kvm *kvm, void __user *argp) * is slightly ahead) here we risk going negative on unsigned * 'system_time' when 'data.clock' is very small. */ - if (kvm->arch.use_master_clock) - now_ns = ka->master_kernel_ns; + if (data.flags & KVM_CLOCK_REALTIME) { + u64 now_real_ns = ktime_get_real_ns(); + + /* + * Avoid stepping the kvmclock backwards. + */ + if (now_real_ns > data.realtime) + data.clock += now_real_ns - data.realtime; + } + + if (ka->use_master_clock) + now_raw_ns = ka->master_kernel_ns; else - now_ns = get_kvmclock_base_ns(); - ka->kvmclock_offset = data.clock - now_ns; + now_raw_ns = get_kvmclock_base_ns(); + ka->kvmclock_offset = data.clock - now_raw_ns; kvm_end_pvclock_update(kvm); return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 322b4b588d75..5ca5ffe16cb4 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1231,11 +1231,16 @@ struct kvm_irqfd { /* Do not use 1, KVM_CHECK_EXTENSION returned it before we had flags. */ #define KVM_CLOCK_TSC_STABLE 2 +#define KVM_CLOCK_REALTIME (1 << 2) +#define KVM_CLOCK_HOST_TSC (1 << 3) struct kvm_clock_data { __u64 clock; __u32 flags; - __u32 pad[9]; + __u32 pad0; + __u64 realtime; + __u64 host_tsc; + __u32 pad[4]; }; /* For KVM_CAP_SW_TLB */ -- cgit v1.2.3 From 3080ea5553cc909b000d1f1d964a9041962f2c5b Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Mon, 9 Aug 2021 11:21:23 -0700 Subject: stddef: Introduce DECLARE_FLEX_ARRAY() helper There are many places where kernel code wants to have several different typed trailing flexible arrays. This would normally be done with multiple flexible arrays in a union, but since GCC and Clang don't (on the surface) allow this, there have been many open-coded workarounds, usually involving neighboring 0-element arrays at the end of a structure. For example, instead of something like this: struct thing { ... union { struct type1 foo[]; struct type2 bar[]; }; }; code works around the compiler with: struct thing { ... struct type1 foo[0]; struct type2 bar[]; }; Another case is when a flexible array is wanted as the single member within a struct (which itself is usually in a union). For example, this would be worked around as: union many { ... struct { struct type3 baz[0]; }; }; These kinds of work-arounds cause problems with size checks against such zero-element arrays (for example when building with -Warray-bounds and -Wzero-length-bounds, and with the coming FORTIFY_SOURCE improvements), so they must all be converted to "real" flexible arrays, avoiding warnings like this: fs/hpfs/anode.c: In function 'hpfs_add_sector_to_btree': fs/hpfs/anode.c:209:27: warning: array subscript 0 is outside the bounds of an interior zero-length array 'struct bplus_internal_node[0]' [-Wzero-length-bounds] 209 | anode->btree.u.internal[0].down = cpu_to_le32(a); | ~~~~~~~~~~~~~~~~~~~~~~~^~~ In file included from fs/hpfs/hpfs_fn.h:26, from fs/hpfs/anode.c:10: fs/hpfs/hpfs.h:412:32: note: while referencing 'internal' 412 | struct bplus_internal_node internal[0]; /* (internal) 2-word entries giving | ^~~~~~~~ drivers/net/can/usb/etas_es58x/es58x_fd.c: In function 'es58x_fd_tx_can_msg': drivers/net/can/usb/etas_es58x/es58x_fd.c:360:35: warning: array subscript 65535 is outside the bounds of an interior zero-length array 'u8[0]' {aka 'unsigned char[]'} [-Wzero-length-bounds] 360 | tx_can_msg = (typeof(tx_can_msg))&es58x_fd_urb_cmd->raw_msg[msg_len]; | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ In file included from drivers/net/can/usb/etas_es58x/es58x_core.h:22, from drivers/net/can/usb/etas_es58x/es58x_fd.c:17: drivers/net/can/usb/etas_es58x/es58x_fd.h:231:6: note: while referencing 'raw_msg' 231 | u8 raw_msg[0]; | ^~~~~~~ However, it _is_ entirely possible to have one or more flexible arrays in a struct or union: it just has to be in another struct. And since it cannot be alone in a struct, such a struct must have at least 1 other named member -- but that member can be zero sized. Wrap all this nonsense into the new DECLARE_FLEX_ARRAY() in support of having flexible arrays in unions (or alone in a struct). As with struct_group(), since this is needed in UAPI headers as well, implement the core there, with a non-UAPI wrapper. Additionally update kernel-doc to understand its existence. https://github.com/KSPP/linux/issues/137 Cc: Arnd Bergmann Cc: "Gustavo A. R. Silva" Signed-off-by: Kees Cook --- include/linux/stddef.h | 13 +++++++++++++ include/uapi/linux/stddef.h | 16 ++++++++++++++++ scripts/kernel-doc | 2 ++ 3 files changed, 31 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/stddef.h b/include/linux/stddef.h index 8b103a53b000..ca507bd5f808 100644 --- a/include/linux/stddef.h +++ b/include/linux/stddef.h @@ -84,4 +84,17 @@ enum { #define struct_group_tagged(TAG, NAME, MEMBERS...) \ __struct_group(TAG, NAME, /* no attrs */, MEMBERS) +/** + * DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define DECLARE_FLEX_ARRAY(TYPE, NAME) \ + __DECLARE_FLEX_ARRAY(TYPE, NAME) + #endif diff --git a/include/uapi/linux/stddef.h b/include/uapi/linux/stddef.h index 610204f7c275..3021ea25a284 100644 --- a/include/uapi/linux/stddef.h +++ b/include/uapi/linux/stddef.h @@ -25,3 +25,19 @@ struct { MEMBERS } ATTRS; \ struct TAG { MEMBERS } ATTRS NAME; \ } + +/** + * __DECLARE_FLEX_ARRAY() - Declare a flexible array usable in a union + * + * @TYPE: The type of each flexible array element + * @NAME: The name of the flexible array member + * + * In order to have a flexible array member in a union or alone in a + * struct, it needs to be wrapped in an anonymous struct with at least 1 + * named member, but that member can be empty. + */ +#define __DECLARE_FLEX_ARRAY(TYPE, NAME) \ + struct { \ + struct { } __empty_ ## NAME; \ + TYPE NAME[]; \ + } diff --git a/scripts/kernel-doc b/scripts/kernel-doc index 38aa799a776c..5d54b57ff90c 100755 --- a/scripts/kernel-doc +++ b/scripts/kernel-doc @@ -1263,6 +1263,8 @@ sub dump_struct($$) { $members =~ s/DECLARE_KFIFO\s*\($args,\s*$args,\s*$args\)/$2 \*$1/gos; # replace DECLARE_KFIFO_PTR $members =~ s/DECLARE_KFIFO_PTR\s*\($args,\s*$args\)/$2 \*$1/gos; + # replace DECLARE_FLEX_ARRAY + $members =~ s/(?:__)?DECLARE_FLEX_ARRAY\s*\($args,\s*$args\)/$1 $2\[\]/gos; my $declaration = $members; # Split nested struct/union elements as newer ones -- cgit v1.2.3 From 47c662486cccf03e7062139d069b07ab0126ef59 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 13 Aug 2021 12:19:24 -0700 Subject: treewide: Replace 0-element memcpy() destinations with flexible arrays The 0-element arrays that are used as memcpy() destinations are actually flexible arrays. Adjust their structures accordingly so that memcpy() can better reason able their destination size (i.e. they need to be seen as "unknown" length rather than "zero"). In some cases, use of the DECLARE_FLEX_ARRAY() helper is needed when a flexible array is alone in a struct. Cc: "Gustavo A. R. Silva" Cc: Arnd Bergmann Cc: Kalle Valo Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Nilesh Javali Cc: Manish Rangankar Cc: GR-QLogic-Storage-Upstream@marvell.com Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Larry Finger Cc: Phillip Potter Cc: Greg Kroah-Hartman Cc: Florian Schilhabel Cc: Johannes Berg Cc: Christophe JAILLET Cc: Fabio Aiuto Cc: Ross Schmidt Cc: Marco Cesati Cc: ath10k@lists.infradead.org Cc: linux-wireless@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-scsi@vger.kernel.org Cc: linux-staging@lists.linux.dev Signed-off-by: Kees Cook --- drivers/net/wireless/ath/ath10k/bmi.h | 10 ++++----- drivers/scsi/qla4xxx/ql4_def.h | 4 ++-- drivers/staging/r8188eu/include/ieee80211.h | 6 +++--- drivers/staging/rtl8712/ieee80211.h | 4 ++-- drivers/staging/rtl8723bs/include/ieee80211.h | 6 +++--- include/linux/ieee80211.h | 30 +++++++++++++-------------- include/uapi/linux/dlm_device.h | 4 ++-- 7 files changed, 32 insertions(+), 32 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/wireless/ath/ath10k/bmi.h b/drivers/net/wireless/ath/ath10k/bmi.h index f6fadcbdd86e..0685c0d2d4ea 100644 --- a/drivers/net/wireless/ath/ath10k/bmi.h +++ b/drivers/net/wireless/ath/ath10k/bmi.h @@ -109,7 +109,7 @@ struct bmi_cmd { struct { __le32 addr; __le32 len; - u8 payload[0]; + u8 payload[]; } write_mem; struct { __le32 addr; @@ -138,18 +138,18 @@ struct bmi_cmd { } rompatch_uninstall; struct { __le32 count; - __le32 patch_ids[0]; /* length of @count */ + __le32 patch_ids[]; /* length of @count */ } rompatch_activate; struct { __le32 count; - __le32 patch_ids[0]; /* length of @count */ + __le32 patch_ids[]; /* length of @count */ } rompatch_deactivate; struct { __le32 addr; } lz_start; struct { __le32 len; /* max BMI_MAX_DATA_SIZE */ - u8 payload[0]; /* length of @len */ + u8 payload[]; /* length of @len */ } lz_data; struct { u8 name[BMI_NVRAM_SEG_NAME_SZ]; @@ -160,7 +160,7 @@ struct bmi_cmd { union bmi_resp { struct { - u8 payload[0]; + DECLARE_FLEX_ARRAY(u8, payload); } read_mem; struct { __le32 result; diff --git a/drivers/scsi/qla4xxx/ql4_def.h b/drivers/scsi/qla4xxx/ql4_def.h index 031569c496e5..69a590546bf9 100644 --- a/drivers/scsi/qla4xxx/ql4_def.h +++ b/drivers/scsi/qla4xxx/ql4_def.h @@ -366,13 +366,13 @@ struct qla4_work_evt { struct { enum iscsi_host_event_code code; uint32_t data_size; - uint8_t data[0]; + uint8_t data[]; } aen; struct { uint32_t status; uint32_t pid; uint32_t data_size; - uint8_t data[0]; + uint8_t data[]; } ping; } u; }; diff --git a/drivers/staging/r8188eu/include/ieee80211.h b/drivers/staging/r8188eu/include/ieee80211.h index bc5b030e9c40..9204dd42f319 100644 --- a/drivers/staging/r8188eu/include/ieee80211.h +++ b/drivers/staging/r8188eu/include/ieee80211.h @@ -185,7 +185,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct { int command; @@ -198,7 +198,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; #ifdef CONFIG_88EU_AP_MODE struct { @@ -210,7 +210,7 @@ struct ieee_param { } add_sta; struct { u8 reserved[2];/* for set max_num_sta */ - u8 buf[0]; + u8 buf[]; } bcn_ie; #endif diff --git a/drivers/staging/rtl8712/ieee80211.h b/drivers/staging/rtl8712/ieee80211.h index 61eff7c5746b..65ceaca9b51e 100644 --- a/drivers/staging/rtl8712/ieee80211.h +++ b/drivers/staging/rtl8712/ieee80211.h @@ -78,7 +78,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct { int command; @@ -91,7 +91,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; } u; }; diff --git a/drivers/staging/rtl8723bs/include/ieee80211.h b/drivers/staging/rtl8723bs/include/ieee80211.h index d6236f5b069d..c11d7e2d2347 100644 --- a/drivers/staging/rtl8723bs/include/ieee80211.h +++ b/drivers/staging/rtl8723bs/include/ieee80211.h @@ -172,7 +172,7 @@ struct ieee_param { struct { u32 len; u8 reserved[32]; - u8 data[0]; + u8 data[]; } wpa_ie; struct{ int command; @@ -185,7 +185,7 @@ struct ieee_param { u8 idx; u8 seq[8]; /* sequence counter (set: RX, get: TX) */ u16 key_len; - u8 key[0]; + u8 key[]; } crypt; struct { u16 aid; @@ -196,7 +196,7 @@ struct ieee_param { } add_sta; struct { u8 reserved[2];/* for set max_num_sta */ - u8 buf[0]; + u8 buf[]; } bcn_ie; } u; }; diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h index 694264503119..ada3dd79cd08 100644 --- a/include/linux/ieee80211.h +++ b/include/linux/ieee80211.h @@ -1143,7 +1143,7 @@ struct ieee80211_mgmt { __le16 auth_transaction; __le16 status_code; /* possibly followed by Challenge text */ - u8 variable[0]; + u8 variable[]; } __packed auth; struct { __le16 reason_code; @@ -1152,26 +1152,26 @@ struct ieee80211_mgmt { __le16 capab_info; __le16 listen_interval; /* followed by SSID and Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed assoc_req; struct { __le16 capab_info; __le16 status_code; __le16 aid; /* followed by Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed assoc_resp, reassoc_resp; struct { __le16 capab_info; __le16 status_code; - u8 variable[0]; + u8 variable[]; } __packed s1g_assoc_resp, s1g_reassoc_resp; struct { __le16 capab_info; __le16 listen_interval; u8 current_ap[ETH_ALEN]; /* followed by SSID and Supported rates */ - u8 variable[0]; + u8 variable[]; } __packed reassoc_req; struct { __le16 reason_code; @@ -1182,11 +1182,11 @@ struct ieee80211_mgmt { __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params, TIM */ - u8 variable[0]; + u8 variable[]; } __packed beacon; struct { /* only variable items: SSID, Supported rates */ - u8 variable[0]; + DECLARE_FLEX_ARRAY(u8, variable); } __packed probe_req; struct { __le64 timestamp; @@ -1194,7 +1194,7 @@ struct ieee80211_mgmt { __le16 capab_info; /* followed by some of SSID, Supported rates, * FH Params, DS Params, CF Params, IBSS Params */ - u8 variable[0]; + u8 variable[]; } __packed probe_resp; struct { u8 category; @@ -1203,16 +1203,16 @@ struct ieee80211_mgmt { u8 action_code; u8 dialog_token; u8 status_code; - u8 variable[0]; + u8 variable[]; } __packed wme_action; struct{ u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed chan_switch; struct{ u8 action_code; struct ieee80211_ext_chansw_ie data; - u8 variable[0]; + u8 variable[]; } __packed ext_chan_switch; struct{ u8 action_code; @@ -1228,7 +1228,7 @@ struct ieee80211_mgmt { __le16 timeout; __le16 start_seq_num; /* followed by BA Extension */ - u8 variable[0]; + u8 variable[]; } __packed addba_req; struct{ u8 action_code; @@ -1244,11 +1244,11 @@ struct ieee80211_mgmt { } __packed delba; struct { u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed self_prot; struct{ u8 action_code; - u8 variable[0]; + u8 variable[]; } __packed mesh_action; struct { u8 action; @@ -1292,7 +1292,7 @@ struct ieee80211_mgmt { u8 toa[6]; __le16 tod_error; __le16 toa_error; - u8 variable[0]; + u8 variable[]; } __packed ftm; struct { u8 action_code; diff --git a/include/uapi/linux/dlm_device.h b/include/uapi/linux/dlm_device.h index f880d2831160..e83954c69fff 100644 --- a/include/uapi/linux/dlm_device.h +++ b/include/uapi/linux/dlm_device.h @@ -45,13 +45,13 @@ struct dlm_lock_params { void __user *bastaddr; struct dlm_lksb __user *lksb; char lvb[DLM_USER_LVB_LEN]; - char name[0]; + char name[]; }; struct dlm_lspace_params { __u32 flags; __u32 minor; - char name[0]; + char name[]; }; struct dlm_purge_params { -- cgit v1.2.3 From 223f903e9c832699f4e5f422281a60756c1c6cfe Mon Sep 17 00:00:00 2001 From: Yonghong Song Date: Tue, 12 Oct 2021 09:48:38 -0700 Subject: bpf: Rename BTF_KIND_TAG to BTF_KIND_DECL_TAG Patch set [1] introduced BTF_KIND_TAG to allow tagging declarations for struct/union, struct/union field, var, func and func arguments and these tags will be encoded into dwarf. They are also encoded to btf by llvm for the bpf target. After BTF_KIND_TAG is introduced, we intended to use it for kernel __user attributes. But kernel __user is actually a type attribute. Upstream and internal discussion showed it is not a good idea to mix declaration attribute and type attribute. So we proposed to introduce btf_type_tag as a type attribute and existing btf_tag renamed to btf_decl_tag ([2]). This patch renamed BTF_KIND_TAG to BTF_KIND_DECL_TAG and some other declarations with *_tag to *_decl_tag to make it clear the tag is for declaration. In the future, BTF_KIND_TYPE_TAG might be introduced per [3]. [1] https://lore.kernel.org/bpf/20210914223004.244411-1-yhs@fb.com/ [2] https://reviews.llvm.org/D111588 [3] https://reviews.llvm.org/D111199 Fixes: b5ea834dde6b ("bpf: Support for new btf kind BTF_KIND_TAG") Fixes: 5b84bd10363e ("libbpf: Add support for BTF_KIND_TAG") Fixes: 5c07f2fec003 ("bpftool: Add support for BTF_KIND_TAG") Signed-off-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20211012164838.3345699-1-yhs@fb.com --- Documentation/bpf/btf.rst | 24 ++-- include/uapi/linux/btf.h | 8 +- kernel/bpf/btf.c | 44 +++--- tools/bpf/bpftool/btf.c | 6 +- tools/include/uapi/linux/btf.h | 8 +- tools/lib/bpf/btf.c | 36 ++--- tools/lib/bpf/btf.h | 12 +- tools/lib/bpf/btf_dump.c | 6 +- tools/lib/bpf/libbpf.c | 24 ++-- tools/lib/bpf/libbpf.map | 2 +- tools/lib/bpf/libbpf_internal.h | 4 +- tools/testing/selftests/bpf/README.rst | 4 +- tools/testing/selftests/bpf/btf_helpers.c | 8 +- tools/testing/selftests/bpf/prog_tests/btf.c | 160 ++++++++++----------- tools/testing/selftests/bpf/prog_tests/btf_write.c | 30 ++-- tools/testing/selftests/bpf/progs/tag.c | 6 +- tools/testing/selftests/bpf/test_btf.h | 4 +- 17 files changed, 193 insertions(+), 193 deletions(-) (limited to 'include/uapi/linux') diff --git a/Documentation/bpf/btf.rst b/Documentation/bpf/btf.rst index 1bfe4072f5fc..9e5b4a98af76 100644 --- a/Documentation/bpf/btf.rst +++ b/Documentation/bpf/btf.rst @@ -85,7 +85,7 @@ sequentially and type id is assigned to each recognized type starting from id #define BTF_KIND_VAR 14 /* Variable */ #define BTF_KIND_DATASEC 15 /* Section */ #define BTF_KIND_FLOAT 16 /* Floating point */ - #define BTF_KIND_TAG 17 /* Tag */ + #define BTF_KIND_DECL_TAG 17 /* Decl Tag */ Note that the type section encodes debug info, not just pure types. ``BTF_KIND_FUNC`` is not a type, and it represents a defined subprogram. @@ -107,7 +107,7 @@ Each type contains the following common data:: * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO and TAG. + * FUNC, FUNC_PROTO and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -466,30 +466,30 @@ map definition. No additional type data follow ``btf_type``. -2.2.17 BTF_KIND_TAG -~~~~~~~~~~~~~~~~~~~ +2.2.17 BTF_KIND_DECL_TAG +~~~~~~~~~~~~~~~~~~~~~~~~ ``struct btf_type`` encoding requirement: * ``name_off``: offset to a non-empty string * ``info.kind_flag``: 0 - * ``info.kind``: BTF_KIND_TAG + * ``info.kind``: BTF_KIND_DECL_TAG * ``info.vlen``: 0 * ``type``: ``struct``, ``union``, ``func`` or ``var`` -``btf_type`` is followed by ``struct btf_tag``.:: +``btf_type`` is followed by ``struct btf_decl_tag``.:: - struct btf_tag { + struct btf_decl_tag { __u32 component_idx; }; -The ``name_off`` encodes btf_tag attribute string. +The ``name_off`` encodes btf_decl_tag attribute string. The ``type`` should be ``struct``, ``union``, ``func`` or ``var``. -For ``var`` type, ``btf_tag.component_idx`` must be ``-1``. -For the other three types, if the btf_tag attribute is +For ``var`` type, ``btf_decl_tag.component_idx`` must be ``-1``. +For the other three types, if the btf_decl_tag attribute is applied to the ``struct``, ``union`` or ``func`` itself, -``btf_tag.component_idx`` must be ``-1``. Otherwise, +``btf_decl_tag.component_idx`` must be ``-1``. Otherwise, the attribute is applied to a ``struct``/``union`` member or -a ``func`` argument, and ``btf_tag.component_idx`` should be a +a ``func`` argument, and ``btf_decl_tag.component_idx`` should be a valid index (starting from 0) pointing to a member or an argument. 3. BTF Kernel API diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h index 642b6ecb37d7..deb12f755f0f 100644 --- a/include/uapi/linux/btf.h +++ b/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and TAG. + * FUNC, FUNC_PROTO, VAR and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -74,7 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ - BTF_KIND_TAG = 17, /* Tag */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -174,14 +174,14 @@ struct btf_var_secinfo { __u32 size; }; -/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe * additional information related to the tag applied location. * If component_idx == -1, the tag is applied to a struct, union, * variable or function. Otherwise, it is applied to a struct/union * member or a func argument, and component_idx indicates which member * or argument (0 ... vlen-1). */ -struct btf_tag { +struct btf_decl_tag { __s32 component_idx; }; diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 2ebffb9f57eb..9059053088b9 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -281,7 +281,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; const char *btf_type_str(const struct btf_type *t) @@ -460,12 +460,12 @@ static bool btf_type_is_datasec(const struct btf_type *t) return BTF_INFO_KIND(t->info) == BTF_KIND_DATASEC; } -static bool btf_type_is_tag(const struct btf_type *t) +static bool btf_type_is_decl_tag(const struct btf_type *t) { - return BTF_INFO_KIND(t->info) == BTF_KIND_TAG; + return BTF_INFO_KIND(t->info) == BTF_KIND_DECL_TAG; } -static bool btf_type_is_tag_target(const struct btf_type *t) +static bool btf_type_is_decl_tag_target(const struct btf_type *t) { return btf_type_is_func(t) || btf_type_is_struct(t) || btf_type_is_var(t); @@ -549,7 +549,7 @@ const struct btf_type *btf_type_resolve_func_ptr(const struct btf *btf, static bool btf_type_is_resolve_source_only(const struct btf_type *t) { return btf_type_is_var(t) || - btf_type_is_tag(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -576,7 +576,7 @@ static bool btf_type_needs_resolve(const struct btf_type *t) btf_type_is_struct(t) || btf_type_is_array(t) || btf_type_is_var(t) || - btf_type_is_tag(t) || + btf_type_is_decl_tag(t) || btf_type_is_datasec(t); } @@ -630,9 +630,9 @@ static const struct btf_var *btf_type_var(const struct btf_type *t) return (const struct btf_var *)(t + 1); } -static const struct btf_tag *btf_type_tag(const struct btf_type *t) +static const struct btf_decl_tag *btf_type_decl_tag(const struct btf_type *t) { - return (const struct btf_tag *)(t + 1); + return (const struct btf_decl_tag *)(t + 1); } static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) @@ -3820,11 +3820,11 @@ static const struct btf_kind_operations float_ops = { .show = btf_df_show, }; -static s32 btf_tag_check_meta(struct btf_verifier_env *env, +static s32 btf_decl_tag_check_meta(struct btf_verifier_env *env, const struct btf_type *t, u32 meta_left) { - const struct btf_tag *tag; + const struct btf_decl_tag *tag; u32 meta_needed = sizeof(*tag); s32 component_idx; const char *value; @@ -3852,7 +3852,7 @@ static s32 btf_tag_check_meta(struct btf_verifier_env *env, return -EINVAL; } - component_idx = btf_type_tag(t)->component_idx; + component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx < -1) { btf_verifier_log_type(env, t, "Invalid component_idx"); return -EINVAL; @@ -3863,7 +3863,7 @@ static s32 btf_tag_check_meta(struct btf_verifier_env *env, return meta_needed; } -static int btf_tag_resolve(struct btf_verifier_env *env, +static int btf_decl_tag_resolve(struct btf_verifier_env *env, const struct resolve_vertex *v) { const struct btf_type *next_type; @@ -3874,7 +3874,7 @@ static int btf_tag_resolve(struct btf_verifier_env *env, u32 vlen; next_type = btf_type_by_id(btf, next_type_id); - if (!next_type || !btf_type_is_tag_target(next_type)) { + if (!next_type || !btf_type_is_decl_tag_target(next_type)) { btf_verifier_log_type(env, v->t, "Invalid type_id"); return -EINVAL; } @@ -3883,7 +3883,7 @@ static int btf_tag_resolve(struct btf_verifier_env *env, !env_type_is_resolved(env, next_type_id)) return env_stack_push(env, next_type, next_type_id); - component_idx = btf_type_tag(t)->component_idx; + component_idx = btf_type_decl_tag(t)->component_idx; if (component_idx != -1) { if (btf_type_is_var(next_type)) { btf_verifier_log_type(env, v->t, "Invalid component_idx"); @@ -3909,18 +3909,18 @@ static int btf_tag_resolve(struct btf_verifier_env *env, return 0; } -static void btf_tag_log(struct btf_verifier_env *env, const struct btf_type *t) +static void btf_decl_tag_log(struct btf_verifier_env *env, const struct btf_type *t) { btf_verifier_log(env, "type=%u component_idx=%d", t->type, - btf_type_tag(t)->component_idx); + btf_type_decl_tag(t)->component_idx); } -static const struct btf_kind_operations tag_ops = { - .check_meta = btf_tag_check_meta, - .resolve = btf_tag_resolve, +static const struct btf_kind_operations decl_tag_ops = { + .check_meta = btf_decl_tag_check_meta, + .resolve = btf_decl_tag_resolve, .check_member = btf_df_check_member, .check_kflag_member = btf_df_check_kflag_member, - .log_details = btf_tag_log, + .log_details = btf_decl_tag_log, .show = btf_df_show, }; @@ -4058,7 +4058,7 @@ static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { [BTF_KIND_VAR] = &var_ops, [BTF_KIND_DATASEC] = &datasec_ops, [BTF_KIND_FLOAT] = &float_ops, - [BTF_KIND_TAG] = &tag_ops, + [BTF_KIND_DECL_TAG] = &decl_tag_ops, }; static s32 btf_check_meta(struct btf_verifier_env *env, @@ -4143,7 +4143,7 @@ static bool btf_resolve_valid(struct btf_verifier_env *env, return !btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); - if (btf_type_is_tag(t)) + if (btf_type_is_decl_tag(t)) return btf_resolved_type_id(btf, type_id) && !btf_resolved_type_size(btf, type_id); diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index 49743ad96851..7b68d4f65fe6 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -37,7 +37,7 @@ static const char * const btf_kind_str[NR_BTF_KINDS] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; struct btf_attach_table { @@ -348,8 +348,8 @@ static int dump_btf_type(const struct btf *btf, __u32 id, printf(" size=%u", t->size); break; } - case BTF_KIND_TAG: { - const struct btf_tag *tag = (const void *)(t + 1); + case BTF_KIND_DECL_TAG: { + const struct btf_decl_tag *tag = (const void *)(t + 1); if (json_output) { jsonw_uint_field(w, "type_id", t->type); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h index 642b6ecb37d7..deb12f755f0f 100644 --- a/tools/include/uapi/linux/btf.h +++ b/tools/include/uapi/linux/btf.h @@ -43,7 +43,7 @@ struct btf_type { * "size" tells the size of the type it is describing. * * "type" is used by PTR, TYPEDEF, VOLATILE, CONST, RESTRICT, - * FUNC, FUNC_PROTO, VAR and TAG. + * FUNC, FUNC_PROTO, VAR and DECL_TAG. * "type" is a type_id referring to another type. */ union { @@ -74,7 +74,7 @@ enum { BTF_KIND_VAR = 14, /* Variable */ BTF_KIND_DATASEC = 15, /* Section */ BTF_KIND_FLOAT = 16, /* Floating point */ - BTF_KIND_TAG = 17, /* Tag */ + BTF_KIND_DECL_TAG = 17, /* Decl Tag */ NR_BTF_KINDS, BTF_KIND_MAX = NR_BTF_KINDS - 1, @@ -174,14 +174,14 @@ struct btf_var_secinfo { __u32 size; }; -/* BTF_KIND_TAG is followed by a single "struct btf_tag" to describe +/* BTF_KIND_DECL_TAG is followed by a single "struct btf_decl_tag" to describe * additional information related to the tag applied location. * If component_idx == -1, the tag is applied to a struct, union, * variable or function. Otherwise, it is applied to a struct/union * member or a func argument, and component_idx indicates which member * or argument (0 ... vlen-1). */ -struct btf_tag { +struct btf_decl_tag { __s32 component_idx; }; diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 60fbd1c6d466..1f6dea11f600 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -309,8 +309,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); - case BTF_KIND_TAG: - return base_size + sizeof(struct btf_tag); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); return -EINVAL; @@ -383,8 +383,8 @@ static int btf_bswap_type_rest(struct btf_type *t) v->size = bswap_32(v->size); } return 0; - case BTF_KIND_TAG: - btf_tag(t)->component_idx = bswap_32(btf_tag(t)->component_idx); + case BTF_KIND_DECL_TAG: + btf_decl_tag(t)->component_idx = bswap_32(btf_decl_tag(t)->component_idx); return 0; default: pr_debug("Unsupported BTF_KIND:%u\n", btf_kind(t)); @@ -596,7 +596,7 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id) case BTF_KIND_CONST: case BTF_KIND_RESTRICT: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: type_id = t->type; break; case BTF_KIND_ARRAY: @@ -2569,7 +2569,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ } /* - * Append new BTF_KIND_TAG type with: + * Append new BTF_KIND_DECL_TAG type with: * - *value* - non-empty/non-NULL string; * - *ref_type_id* - referenced type ID, it might not exist yet; * - *component_idx* - -1 for tagging reference type, otherwise struct/union @@ -2578,7 +2578,7 @@ int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __ * - >0, type ID of newly added BTF type; * - <0, on error. */ -int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, +int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx) { struct btf_type *t; @@ -2593,7 +2593,7 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, if (btf_ensure_modifiable(btf)) return libbpf_err(-ENOMEM); - sz = sizeof(struct btf_type) + sizeof(struct btf_tag); + sz = sizeof(struct btf_type) + sizeof(struct btf_decl_tag); t = btf_add_type_mem(btf, sz); if (!t) return libbpf_err(-ENOMEM); @@ -2603,9 +2603,9 @@ int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, return value_off; t->name_off = value_off; - t->info = btf_type_info(BTF_KIND_TAG, 0, false); + t->info = btf_type_info(BTF_KIND_DECL_TAG, 0, false); t->type = ref_type_id; - btf_tag(t)->component_idx = component_idx; + btf_decl_tag(t)->component_idx = component_idx; return btf_commit_type(btf, sz); } @@ -3427,7 +3427,7 @@ static bool btf_equal_common(struct btf_type *t1, struct btf_type *t2) } /* Calculate type signature hash of INT or TAG. */ -static long btf_hash_int_tag(struct btf_type *t) +static long btf_hash_int_decl_tag(struct btf_type *t) { __u32 info = *(__u32 *)(t + 1); long h; @@ -3705,8 +3705,8 @@ static int btf_dedup_prep(struct btf_dedup *d) h = btf_hash_common(t); break; case BTF_KIND_INT: - case BTF_KIND_TAG: - h = btf_hash_int_tag(t); + case BTF_KIND_DECL_TAG: + h = btf_hash_int_decl_tag(t); break; case BTF_KIND_ENUM: h = btf_hash_enum(t); @@ -3761,11 +3761,11 @@ static int btf_dedup_prim_type(struct btf_dedup *d, __u32 type_id) case BTF_KIND_FUNC_PROTO: case BTF_KIND_VAR: case BTF_KIND_DATASEC: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: return 0; case BTF_KIND_INT: - h = btf_hash_int_tag(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); @@ -4382,13 +4382,13 @@ static int btf_dedup_ref_type(struct btf_dedup *d, __u32 type_id) } break; - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: ref_type_id = btf_dedup_ref_type(d, t->type); if (ref_type_id < 0) return ref_type_id; t->type = ref_type_id; - h = btf_hash_int_tag(t); + h = btf_hash_int_decl_tag(t); for_each_dedup_cand(d, hash_entry, h) { cand_id = (__u32)(long)hash_entry->value; cand = btf_type_by_id(d->btf, cand_id); @@ -4671,7 +4671,7 @@ int btf_type_visit_type_ids(struct btf_type *t, type_id_visit_fn visit, void *ct case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: return visit(&t->type, ctx); case BTF_KIND_ARRAY: { diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 864eb51753a1..4011e206e6f7 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -236,7 +236,7 @@ LIBBPF_API int btf__add_datasec_var_info(struct btf *btf, int var_type_id, __u32 offset, __u32 byte_sz); /* tag construction API */ -LIBBPF_API int btf__add_tag(struct btf *btf, const char *value, int ref_type_id, +LIBBPF_API int btf__add_decl_tag(struct btf *btf, const char *value, int ref_type_id, int component_idx); struct btf_dedup_opts { @@ -426,9 +426,9 @@ static inline bool btf_is_float(const struct btf_type *t) return btf_kind(t) == BTF_KIND_FLOAT; } -static inline bool btf_is_tag(const struct btf_type *t) +static inline bool btf_is_decl_tag(const struct btf_type *t) { - return btf_kind(t) == BTF_KIND_TAG; + return btf_kind(t) == BTF_KIND_DECL_TAG; } static inline __u8 btf_int_encoding(const struct btf_type *t) @@ -499,10 +499,10 @@ btf_var_secinfos(const struct btf_type *t) return (struct btf_var_secinfo *)(t + 1); } -struct btf_tag; -static inline struct btf_tag *btf_tag(const struct btf_type *t) +struct btf_decl_tag; +static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t) { - return (struct btf_tag *)(t + 1); + return (struct btf_decl_tag *)(t + 1); } #ifdef __cplusplus diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c index ad6df97295ae..5ef42f0abed1 100644 --- a/tools/lib/bpf/btf_dump.c +++ b/tools/lib/bpf/btf_dump.c @@ -316,7 +316,7 @@ static int btf_dump_mark_referenced(struct btf_dump *d) case BTF_KIND_TYPEDEF: case BTF_KIND_FUNC: case BTF_KIND_VAR: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: d->type_states[t->type].referenced = 1; break; @@ -584,7 +584,7 @@ static int btf_dump_order_type(struct btf_dump *d, __u32 id, bool through_ptr) case BTF_KIND_FUNC: case BTF_KIND_VAR: case BTF_KIND_DATASEC: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: d->type_states[id].order_state = ORDERED; return 0; @@ -2217,7 +2217,7 @@ static int btf_dump_dump_type_data(struct btf_dump *d, case BTF_KIND_FWD: case BTF_KIND_FUNC: case BTF_KIND_FUNC_PROTO: - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: err = btf_dump_unsupported_data(d, t, id); break; case BTF_KIND_INT: diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index ae0889bebe32..63d738654ff6 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -195,8 +195,8 @@ enum kern_feature_id { FEAT_BTF_FLOAT, /* BPF perf link support */ FEAT_PERF_LINK, - /* BTF_KIND_TAG support */ - FEAT_BTF_TAG, + /* BTF_KIND_DECL_TAG support */ + FEAT_BTF_DECL_TAG, __FEAT_CNT, }; @@ -2024,7 +2024,7 @@ static const char *__btf_kind_str(__u16 kind) case BTF_KIND_VAR: return "var"; case BTF_KIND_DATASEC: return "datasec"; case BTF_KIND_FLOAT: return "float"; - case BTF_KIND_TAG: return "tag"; + case BTF_KIND_DECL_TAG: return "decl_tag"; default: return "unknown"; } } @@ -2524,9 +2524,9 @@ static bool btf_needs_sanitization(struct bpf_object *obj) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); - bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); - return !has_func || !has_datasec || !has_func_global || !has_float || !has_tag; + return !has_func || !has_datasec || !has_func_global || !has_float || !has_decl_tag; } static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) @@ -2535,15 +2535,15 @@ static void bpf_object__sanitize_btf(struct bpf_object *obj, struct btf *btf) bool has_datasec = kernel_supports(obj, FEAT_BTF_DATASEC); bool has_float = kernel_supports(obj, FEAT_BTF_FLOAT); bool has_func = kernel_supports(obj, FEAT_BTF_FUNC); - bool has_tag = kernel_supports(obj, FEAT_BTF_TAG); + bool has_decl_tag = kernel_supports(obj, FEAT_BTF_DECL_TAG); struct btf_type *t; int i, j, vlen; for (i = 1; i <= btf__get_nr_types(btf); i++) { t = (struct btf_type *)btf__type_by_id(btf, i); - if ((!has_datasec && btf_is_var(t)) || (!has_tag && btf_is_tag(t))) { - /* replace VAR/TAG with INT */ + if ((!has_datasec && btf_is_var(t)) || (!has_decl_tag && btf_is_decl_tag(t))) { + /* replace VAR/DECL_TAG with INT */ t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0); /* * using size = 1 is the safest choice, 4 will be too @@ -4248,7 +4248,7 @@ static int probe_kern_btf_float(void) strs, sizeof(strs))); } -static int probe_kern_btf_tag(void) +static int probe_kern_btf_decl_tag(void) { static const char strs[] = "\0tag"; __u32 types[] = { @@ -4258,7 +4258,7 @@ static int probe_kern_btf_tag(void) BTF_TYPE_ENC(1, BTF_INFO_ENC(BTF_KIND_VAR, 0, 0), 1), BTF_VAR_STATIC, /* attr */ - BTF_TYPE_TAG_ENC(1, 2, -1), + BTF_TYPE_DECL_TAG_ENC(1, 2, -1), }; return probe_fd(libbpf__load_raw_btf((char *)types, sizeof(types), @@ -4481,8 +4481,8 @@ static struct kern_feature_desc { [FEAT_PERF_LINK] = { "BPF perf link support", probe_perf_link, }, - [FEAT_BTF_TAG] = { - "BTF_KIND_TAG support", probe_kern_btf_tag, + [FEAT_BTF_DECL_TAG] = { + "BTF_KIND_DECL_TAG support", probe_kern_btf_decl_tag, }, }; diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index f270d25e4af3..e6fb1ba49369 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -394,5 +394,5 @@ LIBBPF_0.6.0 { bpf_object__prev_map; bpf_object__prev_program; btf__add_btf; - btf__add_tag; + btf__add_decl_tag; } LIBBPF_0.5.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index f7fd3944d46d..f6a5748dd318 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -69,8 +69,8 @@ #define BTF_VAR_SECINFO_ENC(type, offset, size) (type), (offset), (size) #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) -#define BTF_TYPE_TAG_ENC(value, type, component_idx) \ - BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) +#define BTF_TYPE_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) #ifndef likely #define likely(x) __builtin_expect(!!(x), 1) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index 554553acc6d9..5e287e445f75 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -204,7 +204,7 @@ __ https://reviews.llvm.org/D93563 btf_tag test and Clang version ============================== -The btf_tag selftest require LLVM support to recognize the btf_tag attribute. +The btf_tag selftest require LLVM support to recognize the btf_decl_tag attribute. It was introduced in `Clang 14`__. Without it, the btf_tag selftest will be skipped and you will observe: @@ -213,7 +213,7 @@ Without it, the btf_tag selftest will be skipped and you will observe: # btf_tag:SKIP -__ https://reviews.llvm.org/D106614 +__ https://reviews.llvm.org/D111588 Clang dependencies for static linking tests =========================================== diff --git a/tools/testing/selftests/bpf/btf_helpers.c b/tools/testing/selftests/bpf/btf_helpers.c index ce103fb0ad1b..668cfa20bb1b 100644 --- a/tools/testing/selftests/bpf/btf_helpers.c +++ b/tools/testing/selftests/bpf/btf_helpers.c @@ -24,12 +24,12 @@ static const char * const btf_kind_str_mapping[] = { [BTF_KIND_VAR] = "VAR", [BTF_KIND_DATASEC] = "DATASEC", [BTF_KIND_FLOAT] = "FLOAT", - [BTF_KIND_TAG] = "TAG", + [BTF_KIND_DECL_TAG] = "DECL_TAG", }; static const char *btf_kind_str(__u16 kind) { - if (kind > BTF_KIND_TAG) + if (kind > BTF_KIND_DECL_TAG) return "UNKNOWN"; return btf_kind_str_mapping[kind]; } @@ -178,9 +178,9 @@ int fprintf_btf_type_raw(FILE *out, const struct btf *btf, __u32 id) case BTF_KIND_FLOAT: fprintf(out, " size=%u", t->size); break; - case BTF_KIND_TAG: + case BTF_KIND_DECL_TAG: fprintf(out, " type_id=%u component_idx=%d", - t->type, btf_tag(t)->component_idx); + t->type, btf_decl_tag(t)->component_idx); break; default: break; diff --git a/tools/testing/selftests/bpf/prog_tests/btf.c b/tools/testing/selftests/bpf/prog_tests/btf.c index acd33d0cd5d9..fa67f25bbef5 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf.c +++ b/tools/testing/selftests/bpf/prog_tests/btf.c @@ -3662,15 +3662,15 @@ static struct btf_raw_test raw_tests[] = { }, { - .descr = "tag test #1, struct/member, well-formed", + .descr = "decl_tag test #1, struct/member, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_STRUCT_ENC(0, 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 32), - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 2, 0), - BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), BTF_END_RAW, }, BTF_STR_SEC("\0m1\0m2\0tag1\0tag2\0tag3"), @@ -3683,15 +3683,15 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #2, union/member, well-formed", + .descr = "decl_tag test #2, union/member, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_UNION_ENC(NAME_TBD, 2, 4), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 0), - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 2, 0), - BTF_TAG_ENC(NAME_TBD, 2, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 1), BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -3704,13 +3704,13 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #3, variable, well-formed", + .descr = "decl_tag test #3, variable, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ BTF_VAR_ENC(NAME_TBD, 1, 1), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 2, -1), - BTF_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 2, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0global\0tag1\0tag2"), @@ -3723,16 +3723,16 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #4, func/parameter, well-formed", + .descr = "decl_tag test #4, func/parameter, well-formed", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, -1), - BTF_TAG_ENC(NAME_TBD, 3, 0), - BTF_TAG_ENC(NAME_TBD, 3, 1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 1), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag1\0tag2\0tag3"), @@ -3745,11 +3745,11 @@ static struct btf_raw_test raw_tests[] = { .max_entries = 1, }, { - .descr = "tag test #5, invalid value", + .descr = "decl_tag test #5, invalid value", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TAG_ENC(0, 2, -1), + BTF_DECL_TAG_ENC(0, 2, -1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag"), @@ -3764,10 +3764,10 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid value", }, { - .descr = "tag test #6, invalid target type", + .descr = "decl_tag test #6, invalid target type", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ - BTF_TAG_ENC(NAME_TBD, 1, -1), + BTF_DECL_TAG_ENC(NAME_TBD, 1, -1), BTF_END_RAW, }, BTF_STR_SEC("\0tag1"), @@ -3782,11 +3782,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid type", }, { - .descr = "tag test #7, invalid vlen", + .descr = "decl_tag test #7, invalid vlen", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 0, 1), 2), (0), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 1), 2), (0), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3801,11 +3801,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "vlen != 0", }, { - .descr = "tag test #8, invalid kflag", + .descr = "decl_tag test #8, invalid kflag", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TAG, 1, 0), 2), (-1), + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 1, 0), 2), (-1), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag1"), @@ -3820,11 +3820,11 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid btf_info kind_flag", }, { - .descr = "tag test #9, var, invalid component_idx", + .descr = "decl_tag test #9, var, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_VAR_ENC(NAME_TBD, 1, 0), /* [2] */ - BTF_TAG_ENC(NAME_TBD, 2, 0), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 0), BTF_END_RAW, }, BTF_STR_SEC("\0local\0tag"), @@ -3839,13 +3839,13 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #10, struct member, invalid component_idx", + .descr = "decl_tag test #10, struct member, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_STRUCT_ENC(0, 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_TBD, 1, 0), BTF_MEMBER_ENC(NAME_TBD, 1, 32), - BTF_TAG_ENC(NAME_TBD, 2, 2), + BTF_DECL_TAG_ENC(NAME_TBD, 2, 2), BTF_END_RAW, }, BTF_STR_SEC("\0m1\0m2\0tag"), @@ -3860,14 +3860,14 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #11, func parameter, invalid component_idx", + .descr = "decl_tag test #11, func parameter, invalid component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, 2), + BTF_DECL_TAG_ENC(NAME_TBD, 3, 2), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), @@ -3882,14 +3882,14 @@ static struct btf_raw_test raw_tests[] = { .err_str = "Invalid component_idx", }, { - .descr = "tag test #12, < -1 component_idx", + .descr = "decl_tag test #12, < -1 component_idx", .raw_types = { BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ BTF_FUNC_PROTO_ENC(0, 2), /* [2] */ BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 1), BTF_FUNC_ENC(NAME_TBD, 2), /* [3] */ - BTF_TAG_ENC(NAME_TBD, 3, -2), + BTF_DECL_TAG_ENC(NAME_TBD, 3, -2), BTF_END_RAW, }, BTF_STR_SEC("\0arg1\0arg2\0f\0tag"), @@ -6672,9 +6672,9 @@ const struct btf_dedup_test dedup_tests[] = { /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ /* tag -> [3] struct s */ - BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ /* tag -> [3] struct s, member 1 */ - BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ /* full copy of the above */ BTF_TYPE_INT_ENC(NAME_NTH(1), BTF_INT_SIGNED, 0, 32, 4), /* [9] */ @@ -6689,8 +6689,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_PTR_ENC(14), /* [13] */ BTF_CONST_ENC(9), /* [14] */ BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [15] */ - BTF_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ - BTF_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, -1), /* [16] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 11, 1), /* [17] */ BTF_END_RAW, }, BTF_STR_SEC("\0int\0s\0next\0a\0b\0c\0float\0d"), @@ -6714,8 +6714,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_PTR_ENC(6), /* [5] */ /* const -> [1] int */ BTF_CONST_ENC(1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(2), 3, 1), /* [8] */ BTF_TYPE_FLOAT_ENC(NAME_NTH(7), 4), /* [9] */ BTF_END_RAW, }, @@ -6841,8 +6841,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ - BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ - BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), @@ -6869,8 +6869,8 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_TBD, 8), BTF_FUNC_ENC(NAME_TBD, 12), /* [13] func */ BTF_TYPE_FLOAT_ENC(NAME_TBD, 2), /* [14] float */ - BTF_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ - BTF_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, -1), /* [15] tag */ + BTF_DECL_TAG_ENC(NAME_TBD, 13, 1), /* [16] tag */ BTF_END_RAW, }, BTF_STR_SEC("\0A\0B\0C\0D\0E\0F\0G\0H\0I\0J\0K\0L\0M\0N\0O\0P"), @@ -7036,14 +7036,14 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ /* tag -> t */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [6] */ /* tag -> func */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [8] */ /* tag -> func arg a1 */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [10] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), @@ -7056,9 +7056,9 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(3), 1), BTF_FUNC_ENC(NAME_NTH(4), 2), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 4, 1), /* [7] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0a1\0a2\0f\0tag"), @@ -7084,17 +7084,17 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_ENC(NAME_NTH(3), 4), /* [5] */ /* tag -> f: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [7] */ /* tag -> f/a2: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [9] */ /* tag -> f: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ - BTF_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, -1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, -1), /* [11] */ /* tag -> f/a2: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ - BTF_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 5, 1), /* [12] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 5, 1), /* [13] */ BTF_END_RAW, }, BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), @@ -7106,12 +7106,12 @@ const struct btf_dedup_test dedup_tests[] = { BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(1), 1), BTF_FUNC_PROTO_ARG_ENC(NAME_NTH(2), 1), BTF_FUNC_ENC(NAME_NTH(3), 2), /* [3] */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 3, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [9] */ BTF_END_RAW, }, BTF_STR_SEC("\0a1\0a2\0f\0tag1\0tag2\0tag3"), @@ -7133,17 +7133,17 @@ const struct btf_dedup_test dedup_tests[] = { BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), /* tag -> t: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [5] */ /* tag -> t/m2: tag1, tag2 */ - BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ /* tag -> t: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ - BTF_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, -1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, -1), /* [9] */ /* tag -> t/m2: tag1, tag3 */ - BTF_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ - BTF_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 3, 1), /* [10] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 3, 1), /* [11] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -7154,12 +7154,12 @@ const struct btf_dedup_test dedup_tests[] = { BTF_STRUCT_ENC(NAME_NTH(1), 2, 8), /* [2] */ BTF_MEMBER_ENC(NAME_NTH(2), 1, 0), BTF_MEMBER_ENC(NAME_NTH(3), 1, 32), - BTF_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ - BTF_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ - BTF_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ - BTF_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ - BTF_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ - BTF_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, -1), /* [3] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, -1), /* [4] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, -1), /* [5] */ + BTF_DECL_TAG_ENC(NAME_NTH(4), 2, 1), /* [6] */ + BTF_DECL_TAG_ENC(NAME_NTH(5), 2, 1), /* [7] */ + BTF_DECL_TAG_ENC(NAME_NTH(6), 2, 1), /* [8] */ BTF_END_RAW, }, BTF_STR_SEC("\0t\0m1\0m2\0tag1\0tag2\0tag3"), @@ -7202,8 +7202,8 @@ static int btf_type_size(const struct btf_type *t) return base_size + sizeof(struct btf_var); case BTF_KIND_DATASEC: return base_size + vlen * sizeof(struct btf_var_secinfo); - case BTF_KIND_TAG: - return base_size + sizeof(struct btf_tag); + case BTF_KIND_DECL_TAG: + return base_size + sizeof(struct btf_decl_tag); default: fprintf(stderr, "Unsupported BTF_KIND:%u\n", kind); return -EINVAL; diff --git a/tools/testing/selftests/bpf/prog_tests/btf_write.c b/tools/testing/selftests/bpf/prog_tests/btf_write.c index 886e0fc1efb1..b912eeb0b6b4 100644 --- a/tools/testing/selftests/bpf/prog_tests/btf_write.c +++ b/tools/testing/selftests/bpf/prog_tests/btf_write.c @@ -277,26 +277,26 @@ static void gen_btf(struct btf *btf) "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", "raw_dump"); - /* TAG */ - id = btf__add_tag(btf, "tag1", 16, -1); + /* DECL_TAG */ + id = btf__add_decl_tag(btf, "tag1", 16, -1); ASSERT_EQ(id, 18, "tag_id"); t = btf__type_by_id(btf, 18); ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag1", "tag_value"); - ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); ASSERT_EQ(t->type, 16, "tag_type"); - ASSERT_EQ(btf_tag(t)->component_idx, -1, "tag_component_idx"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, -1, "tag_component_idx"); ASSERT_STREQ(btf_type_raw_dump(btf, 18), - "[18] TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", "raw_dump"); - id = btf__add_tag(btf, "tag2", 14, 1); + id = btf__add_decl_tag(btf, "tag2", 14, 1); ASSERT_EQ(id, 19, "tag_id"); t = btf__type_by_id(btf, 19); ASSERT_STREQ(btf__str_by_offset(btf, t->name_off), "tag2", "tag_value"); - ASSERT_EQ(btf_kind(t), BTF_KIND_TAG, "tag_kind"); + ASSERT_EQ(btf_kind(t), BTF_KIND_DECL_TAG, "tag_kind"); ASSERT_EQ(t->type, 14, "tag_type"); - ASSERT_EQ(btf_tag(t)->component_idx, 1, "tag_component_idx"); + ASSERT_EQ(btf_decl_tag(t)->component_idx, 1, "tag_component_idx"); ASSERT_STREQ(btf_type_raw_dump(btf, 19), - "[19] TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", "raw_dump"); } static void test_btf_add() @@ -336,8 +336,8 @@ static void test_btf_add() "[16] VAR 'var1' type_id=1, linkage=global-alloc", "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", - "[18] TAG 'tag1' type_id=16 component_idx=-1", - "[19] TAG 'tag2' type_id=14 component_idx=1"); + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1"); btf__free(btf); } @@ -389,8 +389,8 @@ static void test_btf_add_btf() "[16] VAR 'var1' type_id=1, linkage=global-alloc", "[17] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=1 offset=4 size=8", - "[18] TAG 'tag1' type_id=16 component_idx=-1", - "[19] TAG 'tag2' type_id=14 component_idx=1", + "[18] DECL_TAG 'tag1' type_id=16 component_idx=-1", + "[19] DECL_TAG 'tag2' type_id=14 component_idx=1", /* types appended from the second BTF */ "[20] INT 'int' size=4 bits_offset=0 nr_bits=32 encoding=SIGNED", @@ -418,8 +418,8 @@ static void test_btf_add_btf() "[35] VAR 'var1' type_id=20, linkage=global-alloc", "[36] DATASEC 'datasec1' size=12 vlen=1\n" "\ttype_id=20 offset=4 size=8", - "[37] TAG 'tag1' type_id=35 component_idx=-1", - "[38] TAG 'tag2' type_id=33 component_idx=1"); + "[37] DECL_TAG 'tag1' type_id=35 component_idx=-1", + "[38] DECL_TAG 'tag2' type_id=33 component_idx=1"); cleanup: btf__free(btf1); diff --git a/tools/testing/selftests/bpf/progs/tag.c b/tools/testing/selftests/bpf/progs/tag.c index b46b1bfac7da..672d19e7b120 100644 --- a/tools/testing/selftests/bpf/progs/tag.c +++ b/tools/testing/selftests/bpf/progs/tag.c @@ -8,9 +8,9 @@ #define __has_attribute(x) 0 #endif -#if __has_attribute(btf_tag) -#define __tag1 __attribute__((btf_tag("tag1"))) -#define __tag2 __attribute__((btf_tag("tag2"))) +#if __has_attribute(btf_decl_tag) +#define __tag1 __attribute__((btf_decl_tag("tag1"))) +#define __tag2 __attribute__((btf_decl_tag("tag2"))) volatile const bool skip_tests __tag1 __tag2 = false; #else #define __tag1 diff --git a/tools/testing/selftests/bpf/test_btf.h b/tools/testing/selftests/bpf/test_btf.h index 0619e06d745e..32c7a57867da 100644 --- a/tools/testing/selftests/bpf/test_btf.h +++ b/tools/testing/selftests/bpf/test_btf.h @@ -69,7 +69,7 @@ #define BTF_TYPE_FLOAT_ENC(name, sz) \ BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_FLOAT, 0, 0), sz) -#define BTF_TAG_ENC(value, type, component_idx) \ - BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_TAG, 0, 0), type), (component_idx) +#define BTF_DECL_TAG_ENC(value, type, component_idx) \ + BTF_TYPE_ENC(value, BTF_INFO_ENC(BTF_KIND_DECL_TAG, 0, 0), type), (component_idx) #endif /* _TEST_BTF_H */ -- cgit v1.2.3 From 6224590d242fc8c6b26941328e02a40b4384949b Mon Sep 17 00:00:00 2001 From: Pavel Begunkov Date: Sat, 2 Oct 2021 19:36:14 +0100 Subject: io_uring: add flag to not fail link after timeout For some reason non-off IORING_OP_TIMEOUT always fails links, it's pretty inconvenient and unnecessary limits chaining after it to hard linking, which is far from ideal, e.g. doesn't pair well with timeout cancellation. Add a flag forcing it to not fail links on -ETIME. Signed-off-by: Pavel Begunkov Link: https://lore.kernel.org/r/17c7ec0fb7a6113cc6be8cdaedcada0ba836ac0e.1633199723.git.asml.silence@gmail.com Signed-off-by: Jens Axboe --- fs/io_uring.c | 8 ++++++-- include/uapi/linux/io_uring.h | 1 + 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/io_uring.c b/fs/io_uring.c index 5b3b52815b88..5b3b4f8f9659 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -5857,7 +5857,10 @@ err: static void io_req_task_timeout(struct io_kiocb *req, bool *locked) { - req_set_fail(req); + struct io_timeout_data *data = req->async_data; + + if (!(data->flags & IORING_TIMEOUT_ETIME_SUCCESS)) + req_set_fail(req); io_req_complete_post(req, -ETIME, 0); } @@ -6063,7 +6066,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe, if (off && is_timeout_link) return -EINVAL; flags = READ_ONCE(sqe->timeout_flags); - if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK)) + if (flags & ~(IORING_TIMEOUT_ABS | IORING_TIMEOUT_CLOCK_MASK | + IORING_TIMEOUT_ETIME_SUCCESS)) return -EINVAL; /* more than one clock specified is invalid, obviously */ if (hweight32(flags & IORING_TIMEOUT_CLOCK_MASK) > 1) diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index b270a07b285e..c45b5e9a9387 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -158,6 +158,7 @@ enum { #define IORING_TIMEOUT_BOOTTIME (1U << 2) #define IORING_TIMEOUT_REALTIME (1U << 3) #define IORING_LINK_TIMEOUT_UPDATE (1U << 4) +#define IORING_TIMEOUT_ETIME_SUCCESS (1U << 5) #define IORING_TIMEOUT_CLOCK_MASK (IORING_TIMEOUT_BOOTTIME | IORING_TIMEOUT_REALTIME) #define IORING_TIMEOUT_UPDATE_MASK (IORING_TIMEOUT_UPDATE | IORING_LINK_TIMEOUT_UPDATE) /* -- cgit v1.2.3 From f4c6217f7f5936f7173d028559ff5d25cce10816 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 6 Oct 2021 19:36:51 +0530 Subject: perf: Add comment about current state of PERF_MEM_LVL_* namespace and remove an extra line Add a comment about PERF_MEM_LVL_* namespace being depricated to some extent in favour of added PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. Remove an extra line present in perf_mem__lvl_scnprintf function. Signed-off-by: Kajol Jain Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211006140654.298352-2-kjain@linux.ibm.com --- include/uapi/linux/perf_event.h | 8 +++++++- tools/include/uapi/linux/perf_event.h | 8 +++++++- tools/perf/util/mem-events.c | 1 - 3 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index c89535de1ec8..a74538c5b4b5 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1256,7 +1256,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index f92880a15645..e1701e9c7858 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -1241,7 +1241,13 @@ union perf_mem_data_src { #define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ #define PERF_MEM_OP_SHIFT 0 -/* memory hierarchy (memory level, hit or miss) */ +/* + * PERF_MEM_LVL_* namespace being depricated to some extent in the + * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. + * Supporting this namespace inorder to not break defined ABIs. + * + * memory hierarchy (memory level, hit or miss) + */ #define PERF_MEM_LVL_NA 0x01 /* not available */ #define PERF_MEM_LVL_HIT 0x02 /* hit level */ #define PERF_MEM_LVL_MISS 0x04 /* miss level */ diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c index f0e75df72b80..ff7289e28192 100644 --- a/tools/perf/util/mem-events.c +++ b/tools/perf/util/mem-events.c @@ -320,7 +320,6 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info) /* already taken care of */ m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS); - if (mem_info && mem_info->data_src.mem_remote) { strcat(out, "Remote "); l += 7; -- cgit v1.2.3 From fec9cc6175d0ec1e13efe12be491d9bd4de62f80 Mon Sep 17 00:00:00 2001 From: Kajol Jain Date: Wed, 6 Oct 2021 19:36:52 +0530 Subject: perf: Add mem_hops field in perf_mem_data_src structure Going forward, future generation systems can have more hierarchy within the node/package level but currently we don't have any data source encoding field in perf, which can be used to represent this level of data. Add a new field called 'mem_hops' in the perf_mem_data_src structure which can be used to represent intra-node/package or inter-node/off-package details. This field is of size 3 bits where PERF_MEM_HOPS_{NA, 0..6} value can be used to present different hop levels data. Also add corresponding macros to define mem_hop field values and shift value. Currently we define macro for HOPS_0 which corresponds to data coming from another core but same node. For ex: Encodings for mem_hops fields with L2 cache: L2 - local L2 L2 | REMOTE | HOPS_0 - remote core, same node L2 Signed-off-by: Kajol Jain Signed-off-by: Peter Zijlstra (Intel) Link: https://lore.kernel.org/r/20211006140654.298352-3-kjain@linux.ibm.com --- include/uapi/linux/perf_event.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index a74538c5b4b5..bd8860eeb291 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1225,14 +1225,16 @@ union perf_mem_data_src { mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ mem_blk:3, /* access blocked */ - mem_rsvd:21; + mem_hops:3, /* hop level */ + mem_rsvd:18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:21, + __u64 mem_rsvd:18, + mem_hops:3, /* hop level */ mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ @@ -1328,6 +1330,11 @@ union perf_mem_data_src { #define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ #define PERF_MEM_BLK_SHIFT 40 +/* hop level */ +#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ +/* 2-7 available */ +#define PERF_MEM_HOPS_SHIFT 43 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit v1.2.3 From 0a2b3e363566c4cc8792d37c5e73b9d9295e075c Mon Sep 17 00:00:00 2001 From: Coly Li Date: Wed, 20 Oct 2021 22:38:06 +0800 Subject: bcache: reserve never used bits from bkey.high There sre 3 bits in member high of struct bkey are never used, and no plan to support them in future, - HEADER_SIZE, start at bit 58, length 2 bits - KEY_PINNED, start at bit 55, length 1 bit No any kernel code, or user space tool references or accesses the three bits. Therefore it is possible and feasible to reserve the valuable bits from bkey.high. They can be used in future for other purpose. Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20211020143812.6403-3-colyli@suse.de Signed-off-by: Jens Axboe --- include/uapi/linux/bcache.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h index cf7399f03b71..97413586195b 100644 --- a/include/uapi/linux/bcache.h +++ b/include/uapi/linux/bcache.h @@ -43,9 +43,9 @@ static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ #define KEY_MAX_U64S 8 KEY_FIELD(KEY_PTRS, high, 60, 3) -KEY_FIELD(HEADER_SIZE, high, 58, 2) +KEY_FIELD(__PAD0, high, 58, 2) KEY_FIELD(KEY_CSUM, high, 56, 2) -KEY_FIELD(KEY_PINNED, high, 55, 1) +KEY_FIELD(__PAD1, high, 55, 1) KEY_FIELD(KEY_DIRTY, high, 36, 1) KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) -- cgit v1.2.3 From 7aea2c0b48a568e6732c1d30516febe36bf555f1 Mon Sep 17 00:00:00 2001 From: Michael Tretter Date: Wed, 8 Sep 2021 14:03:15 +0100 Subject: media: allegro: add control to disable encoder buffer The encoder buffer can have a negative impact on the quality of the encoded video. Add a control to allow user space to disable the encoder buffer per channel if the VCU supports the encoder buffer but the quality is not sufficient. Signed-off-by: Michael Tretter Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/media/platform/allegro-dvt/allegro-core.c | 32 +++++++++++++++++++++-- include/uapi/linux/v4l2-controls.h | 5 ++++ 2 files changed, 35 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/media/platform/allegro-dvt/allegro-core.c b/drivers/media/platform/allegro-dvt/allegro-core.c index cb42b6e3d85a..7ec85299d03e 100644 --- a/drivers/media/platform/allegro-dvt/allegro-core.c +++ b/drivers/media/platform/allegro-dvt/allegro-core.c @@ -105,6 +105,12 @@ #define BETA_OFFSET_DIV_2 -1 #define TC_OFFSET_DIV_2 -1 +/* + * This control allows applications to explicitly disable the encoder buffer. + * This value is Allegro specific. + */ +#define V4L2_CID_USER_ALLEGRO_ENCODER_BUFFER (V4L2_CID_USER_ALLEGRO_BASE + 0) + static int debug; module_param(debug, int, 0644); MODULE_PARM_DESC(debug, "Debug level (0-2)"); @@ -275,6 +281,8 @@ struct allegro_channel { struct v4l2_ctrl *mpeg_video_cpb_size; struct v4l2_ctrl *mpeg_video_gop_size; + struct v4l2_ctrl *encoder_buffer; + /* user_id is used to identify the channel during CREATE_CHANNEL */ /* not sure, what to set here and if this is actually required */ int user_id; @@ -1255,7 +1263,7 @@ static int fill_create_channel_param(struct allegro_channel *channel, param->max_transfo_depth_intra = channel->max_transfo_depth_intra; param->max_transfo_depth_inter = channel->max_transfo_depth_inter; - param->encoder_buffer_enabled = channel->dev->has_encoder_buffer; + param->encoder_buffer_enabled = v4l2_ctrl_g_ctrl(channel->encoder_buffer); param->encoder_buffer_offset = 0; param->rate_control_mode = channel->frame_rc_enable ? @@ -1381,7 +1389,7 @@ static int allegro_mcu_send_encode_frame(struct allegro_dev *dev, u64 src_handle) { struct mcu_msg_encode_frame msg; - bool use_encoder_buffer = channel->dev->has_encoder_buffer; + bool use_encoder_buffer = v4l2_ctrl_g_ctrl(channel->encoder_buffer); memset(&msg, 0, sizeof(msg)); @@ -2466,6 +2474,8 @@ static void allegro_destroy_channel(struct allegro_channel *channel) v4l2_ctrl_grab(channel->mpeg_video_cpb_size, false); v4l2_ctrl_grab(channel->mpeg_video_gop_size, false); + v4l2_ctrl_grab(channel->encoder_buffer, false); + if (channel->user_id != -1) { clear_bit(channel->user_id, &dev->channel_user_ids); channel->user_id = -1; @@ -2532,6 +2542,8 @@ static int allegro_create_channel(struct allegro_channel *channel) v4l2_ctrl_grab(channel->mpeg_video_cpb_size, true); v4l2_ctrl_grab(channel->mpeg_video_gop_size, true); + v4l2_ctrl_grab(channel->encoder_buffer, true); + reinit_completion(&channel->completion); allegro_mcu_send_create_channel(dev, channel); timeout = wait_for_completion_timeout(&channel->completion, @@ -2915,6 +2927,10 @@ static int allegro_try_ctrl(struct v4l2_ctrl *ctrl) case V4L2_CID_MPEG_VIDEO_BITRATE_MODE: allegro_clamp_bitrate(channel, ctrl); break; + case V4L2_CID_USER_ALLEGRO_ENCODER_BUFFER: + if (!channel->dev->has_encoder_buffer) + ctrl->val = 0; + break; } return 0; @@ -2955,6 +2971,16 @@ static const struct v4l2_ctrl_ops allegro_ctrl_ops = { .s_ctrl = allegro_s_ctrl, }; +static const struct v4l2_ctrl_config allegro_encoder_buffer_ctrl_config = { + .id = V4L2_CID_USER_ALLEGRO_ENCODER_BUFFER, + .name = "Encoder Buffer Enable", + .type = V4L2_CTRL_TYPE_BOOLEAN, + .min = 0, + .max = 1, + .step = 1, + .def = 1, +}; + static int allegro_open(struct file *file) { struct video_device *vdev = video_devdata(file); @@ -3106,6 +3132,8 @@ static int allegro_open(struct file *file) V4L2_CID_MPEG_VIDEO_GOP_SIZE, 0, ALLEGRO_GOP_SIZE_MAX, 1, ALLEGRO_GOP_SIZE_DEFAULT); + channel->encoder_buffer = v4l2_ctrl_new_custom(handler, + &allegro_encoder_buffer_ctrl_config, NULL); v4l2_ctrl_new_std(handler, &allegro_ctrl_ops, V4L2_CID_MIN_BUFFERS_FOR_OUTPUT, diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h index 133e20444939..5fea5feb0412 100644 --- a/include/uapi/linux/v4l2-controls.h +++ b/include/uapi/linux/v4l2-controls.h @@ -211,6 +211,11 @@ enum v4l2_colorfx { * We reserve 128 controls for this driver. */ #define V4L2_CID_USER_CCS_BASE (V4L2_CID_USER_BASE + 0x10f0) +/* + * The base for Allegro driver controls. + * We reserve 16 controls for this driver. + */ +#define V4L2_CID_USER_ALLEGRO_BASE (V4L2_CID_USER_BASE + 0x1170) /* MPEG-class control IDs */ /* The MPEG controls are applicable to all codec controls -- cgit v1.2.3 From dfcb63ce1de6b10ba98dee928f9463f37e5a5512 Mon Sep 17 00:00:00 2001 From: Toke Høiland-Jørgensen Date: Tue, 19 Oct 2021 19:47:09 +0200 Subject: fq_codel: generalise ce_threshold marking for subset of traffic MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit e72aeb9ee0e3 ("fq_codel: implement L4S style ce_threshold_ect1 marking") expanded the ce_threshold feature of FQ-CoDel so it can be applied to a subset of the traffic, using the ECT(1) bit of the ECN field as the classifier. However, hard-coding ECT(1) as the only classifier for this feature seems limiting, so let's expand it to be more general. To this end, change the parameter from a ce_threshold_ect1 boolean, to a one-byte selector/mask pair (ce_threshold_{selector,mask}) which is applied to the whole diffserv/ECN field in the IP header. This makes it possible to classify packets by any value in either the ECN field or the diffserv field. In particular, setting a selector of INET_ECN_ECT_1 and a mask of INET_ECN_MASK corresponds to the functionality before this patch, and a mask of ~INET_ECN_MASK allows using the selector as a straight-forward match against a diffserv code point: # apply ce_threshold to ECT(1) traffic tc qdisc replace dev eth0 root fq_codel ce_threshold 1ms ce_threshold_selector 0x1/0x3 # apply ce_threshold to ECN-capable traffic marked as diffserv AF22 tc qdisc replace dev eth0 root fq_codel ce_threshold 1ms ce_threshold_selector 0x50/0xfc Regardless of the selector chosen, the normal rules for ECN-marking of packets still apply, i.e., the flow must still declare itself ECN-capable by setting one of the bits in the ECN field to get marked at all. v2: - Add tc usage examples to patch description Signed-off-by: Toke Høiland-Jørgensen Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20211019174709.69081-1-toke@redhat.com Signed-off-by: Jakub Kicinski --- include/net/codel.h | 7 +++++-- include/net/codel_impl.h | 14 +++++++------- include/uapi/linux/pkt_sched.h | 3 ++- net/mac80211/sta_info.c | 3 ++- net/sched/sch_fq_codel.c | 13 +++++++++---- 5 files changed, 25 insertions(+), 15 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/codel.h b/include/net/codel.h index 5e8b181b76b8..a6c9e34e62b8 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -102,7 +102,9 @@ static inline u32 codel_time_to_us(codel_time_t val) * @interval: width of moving time window * @mtu: device mtu, or minimal queue backlog in bytes. * @ecn: is Explicit Congestion Notification enabled - * @ce_threshold_ect1: if ce_threshold only marks ECT(1) packets + * @ce_threshold_selector: apply ce_threshold to packets matching this value + * in the diffserv/ECN byte of the IP header + * @ce_threshold_mask: mask to apply to ce_threshold_selector comparison */ struct codel_params { codel_time_t target; @@ -110,7 +112,8 @@ struct codel_params { codel_time_t interval; u32 mtu; bool ecn; - bool ce_threshold_ect1; + u8 ce_threshold_selector; + u8 ce_threshold_mask; }; /** diff --git a/include/net/codel_impl.h b/include/net/codel_impl.h index 7af2c3eb3c43..137d40d8cbeb 100644 --- a/include/net/codel_impl.h +++ b/include/net/codel_impl.h @@ -54,7 +54,8 @@ static void codel_params_init(struct codel_params *params) params->interval = MS2TIME(100); params->target = MS2TIME(5); params->ce_threshold = CODEL_DISABLED_THRESHOLD; - params->ce_threshold_ect1 = false; + params->ce_threshold_mask = 0; + params->ce_threshold_selector = 0; params->ecn = false; } @@ -250,13 +251,12 @@ end: if (skb && codel_time_after(vars->ldelay, params->ce_threshold)) { bool set_ce = true; - if (params->ce_threshold_ect1) { - /* Note: if skb_get_dsfield() returns -1, following - * gives INET_ECN_MASK, which is != INET_ECN_ECT_1. - */ - u8 ecn = skb_get_dsfield(skb) & INET_ECN_MASK; + if (params->ce_threshold_mask) { + int dsfield = skb_get_dsfield(skb); - set_ce = (ecn == INET_ECN_ECT_1); + set_ce = (dsfield >= 0 && + (((u8)dsfield & params->ce_threshold_mask) == + params->ce_threshold_selector)); } if (set_ce && INET_ECN_set_ce(skb)) stats->ce_mark++; diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h index 6be9a84cccfa..f292b467b27f 100644 --- a/include/uapi/linux/pkt_sched.h +++ b/include/uapi/linux/pkt_sched.h @@ -840,7 +840,8 @@ enum { TCA_FQ_CODEL_CE_THRESHOLD, TCA_FQ_CODEL_DROP_BATCH_SIZE, TCA_FQ_CODEL_MEMORY_LIMIT, - TCA_FQ_CODEL_CE_THRESHOLD_ECT1, + TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, + TCA_FQ_CODEL_CE_THRESHOLD_MASK, __TCA_FQ_CODEL_MAX }; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index a39830418434..bd52ac3bee90 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -513,7 +513,8 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, sta->cparams.target = MS2TIME(20); sta->cparams.interval = MS2TIME(100); sta->cparams.ecn = true; - sta->cparams.ce_threshold_ect1 = false; + sta->cparams.ce_threshold_selector = 0; + sta->cparams.ce_threshold_mask = 0; sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr); diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index 033d65d06eb1..839e1235db05 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -362,7 +362,8 @@ static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = { [TCA_FQ_CODEL_CE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CODEL_DROP_BATCH_SIZE] = { .type = NLA_U32 }, [TCA_FQ_CODEL_MEMORY_LIMIT] = { .type = NLA_U32 }, - [TCA_FQ_CODEL_CE_THRESHOLD_ECT1] = { .type = NLA_U8 }, + [TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR] = { .type = NLA_U8 }, + [TCA_FQ_CODEL_CE_THRESHOLD_MASK] = { .type = NLA_U8 }, }; static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, @@ -409,8 +410,10 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->cparams.ce_threshold = (val * NSEC_PER_USEC) >> CODEL_SHIFT; } - if (tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]) - q->cparams.ce_threshold_ect1 = !!nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_ECT1]); + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]) + q->cparams.ce_threshold_selector = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR]); + if (tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]) + q->cparams.ce_threshold_mask = nla_get_u8(tb[TCA_FQ_CODEL_CE_THRESHOLD_MASK]); if (tb[TCA_FQ_CODEL_INTERVAL]) { u64 interval = nla_get_u32(tb[TCA_FQ_CODEL_INTERVAL]); @@ -552,7 +555,9 @@ static int fq_codel_dump(struct Qdisc *sch, struct sk_buff *skb) if (nla_put_u32(skb, TCA_FQ_CODEL_CE_THRESHOLD, codel_time_to_us(q->cparams.ce_threshold))) goto nla_put_failure; - if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_ECT1, q->cparams.ce_threshold_ect1)) + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_SELECTOR, q->cparams.ce_threshold_selector)) + goto nla_put_failure; + if (nla_put_u8(skb, TCA_FQ_CODEL_CE_THRESHOLD_MASK, q->cparams.ce_threshold_mask)) goto nla_put_failure; } -- cgit v1.2.3 From 1add667da24273631d4b1f5529789ec5253227f6 Mon Sep 17 00:00:00 2001 From: Emmanuel Grumbach Date: Wed, 20 Oct 2021 08:11:47 +0300 Subject: nl80211: vendor-cmd: intel: add more details for IWL_MVM_VENDOR_CMD_HOST_GET_OWNERSHIP Explain more the expected flow for this command. Signed-off-by: Emmanuel Grumbach Link: https://lore.kernel.org/r/20211020051147.29297-1-emmanuel.grumbach@intel.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211-vnd-intel.h | 29 +++++++++++++++++++++++++++++ 1 file changed, 29 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211-vnd-intel.h b/include/uapi/linux/nl80211-vnd-intel.h index 0bf177b84fd9..4ed7d0b24512 100644 --- a/include/uapi/linux/nl80211-vnd-intel.h +++ b/include/uapi/linux/nl80211-vnd-intel.h @@ -13,6 +13,35 @@ * enum iwl_mvm_vendor_cmd - supported vendor commands * @IWL_MVM_VENDOR_CMD_GET_CSME_CONN_INFO: reports CSME connection info. * @IWL_MVM_VENDOR_CMD_HOST_GET_OWNERSHIP: asks for ownership on the device. + * This is useful when the CSME firmware owns the device and the kernel + * wants to use it. In case the CSME firmware has no connection active the + * kernel will manage on its own to get ownership of the device. + * When the CSME firmware has an active connection, the user space + * involvement is required. The kernel will assert the RFKILL signal with + * the "device not owned" reason so that nobody can touch the device. Then + * the user space can run the following flow to be able to get connected + * to the very same AP the CSME firmware is currently connected to: + * + * 1) The user space (NetworkManager) boots and sees that the device is + * in RFKILL because the host doesn't own the device + * 2) The user space asks the kernel what AP the CSME firmware is + * connected to (with %IWL_MVM_VENDOR_CMD_GET_CSME_CONN_INFO) + * 3) The user space checks if it has a profile that matches the reply + * from the CSME firmware + * 4) The user space installs a network to the wpa_supplicant with a + * specific BSSID and a specific frequency + * 5) The user space prevents any type of full scan + * 6) The user space asks iwlmei to request ownership on the device (with + * this command) + * 7) iwlmei requests ownership from the CSME firmware + * 8) The CSME firmware grants ownership + * 9) iwlmei tells iwlwifi to lift the RFKILL + * 10) RFKILL OFF is reported to user space + * 11) The host boots the device, loads the firwmare, and connects to a + * specific BSSID without scanning including IP as fast as it can + * 12) The host reports to the CSME firmware that there is a connection + * 13) The TCP connection is preserved and the host has connectivity + * * @IWL_MVM_VENDOR_CMD_ROAMING_FORBIDDEN_EVENT: notifies if roaming is allowed. * It contains a &IWL_MVM_VENDOR_ATTR_ROAMING_FORBIDDEN and a * &IWL_MVM_VENDOR_ATTR_VIF_ADDR attributes. -- cgit v1.2.3 From 63fa04266629b9559d66c4dc18b03e0f9fc04a02 Mon Sep 17 00:00:00 2001 From: Srinivasan Raju Date: Mon, 18 Oct 2021 11:00:54 +0100 Subject: nl80211: Add LC placeholder band definition to nl80211_band Define LC band which is a draft under IEEE 802.11bb. Current NL80211_BAND_LC is a placeholder band and will be more defined IEEE 802.11bb progresses. Signed-off-by: Srinivasan Raju Link: https://lore.kernel.org/r/20211018100143.7565-2-srini.raju@purelifi.com Signed-off-by: Johannes Berg --- include/uapi/linux/nl80211.h | 2 ++ net/mac80211/mlme.c | 1 + net/mac80211/sta_info.c | 1 + net/mac80211/tx.c | 3 ++- net/wireless/nl80211.c | 1 + net/wireless/util.c | 2 ++ 6 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index eda608b1eb09..6b816ef0155f 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -4978,6 +4978,7 @@ enum nl80211_txrate_gi { * @NL80211_BAND_60GHZ: around 60 GHz band (58.32 - 69.12 GHz) * @NL80211_BAND_6GHZ: around 6 GHz band (5.9 - 7.2 GHz) * @NL80211_BAND_S1GHZ: around 900MHz, supported by S1G PHYs + * @NL80211_BAND_LC: light communication band (placeholder) * @NUM_NL80211_BANDS: number of bands, avoid using this in userspace * since newer kernel versions may support more bands */ @@ -4987,6 +4988,7 @@ enum nl80211_band { NL80211_BAND_60GHZ, NL80211_BAND_6GHZ, NL80211_BAND_S1GHZ, + NL80211_BAND_LC, NUM_NL80211_BANDS, }; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index ac32a1998a7e..16ef7396b6da 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -1490,6 +1490,7 @@ ieee80211_find_80211h_pwr_constr(struct ieee80211_sub_if_data *sdata, fallthrough; case NL80211_BAND_2GHZ: case NL80211_BAND_60GHZ: + case NL80211_BAND_LC: chan_increment = 1; break; case NL80211_BAND_5GHZ: diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2b5acb37587f..36524101d11f 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -444,6 +444,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, switch (i) { case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: /* * We use both here, even if we cannot really know for * sure the station will support both, but the only use diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index ac9ab007dc6f..5c426b093ee2 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -146,7 +146,8 @@ static __le16 ieee80211_duration(struct ieee80211_tx_data *tx, rate = DIV_ROUND_UP(r->bitrate, 1 << shift); switch (sband->band) { - case NL80211_BAND_2GHZ: { + case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: { u32 flag; if (tx->sdata->flags & IEEE80211_SDATA_OPERATING_GMODE) flag = IEEE80211_RATE_MANDATORY_G; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index e72efe146d58..81232b73df8f 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -866,6 +866,7 @@ nl80211_match_band_rssi_policy[NUM_NL80211_BANDS] = { [NL80211_BAND_5GHZ] = { .type = NLA_S32 }, [NL80211_BAND_6GHZ] = { .type = NLA_S32 }, [NL80211_BAND_60GHZ] = { .type = NLA_S32 }, + [NL80211_BAND_LC] = { .type = NLA_S32 }, }; static const struct nla_policy diff --git a/net/wireless/util.c b/net/wireless/util.c index 18dba3d7c638..2991f711491a 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -80,6 +80,7 @@ u32 ieee80211_channel_to_freq_khz(int chan, enum nl80211_band band) return 0; /* not supported */ switch (band) { case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: if (chan == 14) return MHZ_TO_KHZ(2484); else if (chan < 14) @@ -209,6 +210,7 @@ static void set_mandatory_flags_band(struct ieee80211_supported_band *sband) WARN_ON(want); break; case NL80211_BAND_2GHZ: + case NL80211_BAND_LC: want = 7; for (i = 0; i < sband->n_bitrates; i++) { switch (sband->bitrates[i].bitrate) { -- cgit v1.2.3 From f9d366d420af4ce8719c59e60853573c02831f61 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 21 Oct 2021 17:30:39 +0200 Subject: cfg80211: fix kernel-doc for MBSSID EMA The struct member ema_max_profile_periodicity was listed with the wrong name in the kernel-doc, fix that. Link: https://lore.kernel.org/r/20211021173038.18ec2030c66b.Iac731bb299525940948adad2c41f514b7dd81c47@changeid Signed-off-by: Johannes Berg --- include/net/cfg80211.h | 2 +- include/uapi/linux/nl80211.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 241b29b0796e..7c9d5db4f0e6 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -5041,7 +5041,7 @@ struct wiphy_iftype_akm_suites { * @mbssid_max_interfaces: maximum number of interfaces supported by the driver * in a multiple BSSID set. This field must be set to a non-zero value * by the driver to advertise MBSSID support. - * @mbssid_max_ema_profile_periodicity: maximum profile periodicity supported by + * @ema_max_profile_periodicity: maximum profile periodicity supported by * the driver. Setting this field to a non-zero value indicates that the * driver supports enhanced multi-BSSID advertisements (EMA AP). */ diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index 6b816ef0155f..61cab81e920d 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -7424,7 +7424,7 @@ enum nl80211_sar_specs_attrs { * @NL80211_MBSSID_CONFIG_ATTR_MAX_EMA_PROFILE_PERIODICITY: Used by the kernel * to advertise the maximum profile periodicity supported by the driver * if EMA is enabled. Driver should indicate EMA support to the userspace - * by setting wiphy->mbssid_max_ema_profile_periodicity to + * by setting wiphy->ema_max_profile_periodicity to * a non-zero value. * * @NL80211_MBSSID_CONFIG_ATTR_INDEX: Mandatory parameter to pass the index of @@ -7443,7 +7443,7 @@ enum nl80211_sar_specs_attrs { * * @NL80211_MBSSID_CONFIG_ATTR_EMA: Flag used to enable EMA AP feature. * Setting this flag is permitted only if the driver advertises EMA support - * by setting wiphy->mbssid_max_ema_profile_periodicity to non-zero. + * by setting wiphy->ema_max_profile_periodicity to non-zero. * * @__NL80211_MBSSID_CONFIG_ATTR_LAST: Internal * @NL80211_MBSSID_CONFIG_ATTR_MAX: highest attribute -- cgit v1.2.3 From c353d7ce76bfbb87a89155616916cea1f0f1e78e Mon Sep 17 00:00:00 2001 From: Geert Uytterhoeven Date: Tue, 19 Oct 2021 16:45:00 +0200 Subject: uapi: Add Add a header file providing translation primitives and tables for the conversion of (ASCII) characters to a 14-segments notation, as used by 14-segment alphanumeric displays. This follows the spirit of include/uapi/linux/map_to_7segment.h. Signed-off-by: Geert Uytterhoeven Signed-off-by: Miguel Ojeda --- include/uapi/linux/map_to_14segment.h | 241 ++++++++++++++++++++++++++++++++++ 1 file changed, 241 insertions(+) create mode 100644 include/uapi/linux/map_to_14segment.h (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/map_to_14segment.h b/include/uapi/linux/map_to_14segment.h new file mode 100644 index 000000000000..0346ef76543b --- /dev/null +++ b/include/uapi/linux/map_to_14segment.h @@ -0,0 +1,241 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (C) 2021 Glider bv + * + * Based on include/uapi/linux/map_to_7segment.h: + + * Copyright (c) 2005 Henk Vergonet + */ + +#ifndef MAP_TO_14SEGMENT_H +#define MAP_TO_14SEGMENT_H + +/* This file provides translation primitives and tables for the conversion + * of (ASCII) characters to a 14-segments notation. + * + * The 14 segment's wikipedia notation below is used as standard. + * See: https://en.wikipedia.org/wiki/Fourteen-segment_display + * + * Notation: +---a---+ + * |\ | /| + * f h i j b + * | \|/ | + * +-g1+-g2+ + * | /|\ | + * e k l m c + * |/ | \| + * +---d---+ + * + * Usage: + * + * Register a map variable, and fill it with a character set: + * static SEG14_DEFAULT_MAP(map_seg14); + * + * + * Then use for conversion: + * seg14 = map_to_seg14(&map_seg14, some_char); + * ... + * + * In device drivers it is recommended, if required, to make the char map + * accessible via the sysfs interface using the following scheme: + * + * static ssize_t map_seg14_show(struct device *dev, + * struct device_attribute *attr, char *buf) + * { + * memcpy(buf, &map_seg14, sizeof(map_seg14)); + * return sizeof(map_seg14); + * } + * static ssize_t map_seg14_store(struct device *dev, + * struct device_attribute *attr, + * const char *buf, size_t cnt) + * { + * if (cnt != sizeof(map_seg14)) + * return -EINVAL; + * memcpy(&map_seg14, buf, cnt); + * return cnt; + * } + * static DEVICE_ATTR_RW(map_seg14); + */ +#include +#include + +#include + +#define BIT_SEG14_A 0 +#define BIT_SEG14_B 1 +#define BIT_SEG14_C 2 +#define BIT_SEG14_D 3 +#define BIT_SEG14_E 4 +#define BIT_SEG14_F 5 +#define BIT_SEG14_G1 6 +#define BIT_SEG14_G2 7 +#define BIT_SEG14_H 8 +#define BIT_SEG14_I 9 +#define BIT_SEG14_J 10 +#define BIT_SEG14_K 11 +#define BIT_SEG14_L 12 +#define BIT_SEG14_M 13 +#define BIT_SEG14_RESERVED1 14 +#define BIT_SEG14_RESERVED2 15 + +struct seg14_conversion_map { + __be16 table[128]; +}; + +static __inline__ int map_to_seg14(struct seg14_conversion_map *map, int c) +{ + if (c < 0 || c >= sizeof(map->table) / sizeof(map->table[0])) + return -EINVAL; + + return __be16_to_cpu(map->table[c]); +} + +#define SEG14_CONVERSION_MAP(_name, _map) \ + struct seg14_conversion_map _name = { .table = { _map } } + +/* + * It is recommended to use a facility that allows user space to redefine + * custom character sets for LCD devices. Please use a sysfs interface + * as described above. + */ +#define MAP_TO_SEG14_SYSFS_FILE "map_seg14" + +/******************************************************************************* + * ASCII conversion table + ******************************************************************************/ + +#define _SEG14(sym, a, b, c, d, e, f, g1, g2, h, j, k, l, m, n) \ + __cpu_to_be16( a << BIT_SEG14_A | b << BIT_SEG14_B | \ + c << BIT_SEG14_C | d << BIT_SEG14_D | \ + e << BIT_SEG14_E | f << BIT_SEG14_F | \ + g1 << BIT_SEG14_G1 | g2 << BIT_SEG14_G2 | \ + h << BIT_SEG14_H | j << BIT_SEG14_I | \ + k << BIT_SEG14_J | l << BIT_SEG14_K | \ + m << BIT_SEG14_L | n << BIT_SEG14_M ) + +#define _MAP_0_32_ASCII_SEG14_NON_PRINTABLE \ + 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0, + +#define _MAP_33_47_ASCII_SEG14_SYMBOL \ + _SEG14('!', 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('"', 0, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0), \ + _SEG14('#', 0, 1, 1, 1, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14('$', 1, 0, 1, 1, 0, 1, 1, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14('%', 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 1, 0, 0), \ + _SEG14('&', 1, 0, 0, 1, 1, 0, 1, 0, 1, 0, 1, 0, 0, 1), \ + _SEG14('\'',0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0), \ + _SEG14('(', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1), \ + _SEG14(')', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0), \ + _SEG14('*', 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1), \ + _SEG14('+', 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14(',', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0), \ + _SEG14('-', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('.', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('/', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0), + +#define _MAP_48_57_ASCII_SEG14_NUMERIC \ + _SEG14('0', 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0), \ + _SEG14('1', 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0), \ + _SEG14('2', 1, 1, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('3', 1, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('4', 0, 1, 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('5', 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('6', 1, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('7', 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0), \ + _SEG14('8', 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('9', 1, 1, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0), + +#define _MAP_58_64_ASCII_SEG14_SYMBOL \ + _SEG14(':', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14(';', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0), \ + _SEG14('<', 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1), \ + _SEG14('=', 0, 0, 0, 1, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('>', 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 0), \ + _SEG14('?', 1, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0), \ + _SEG14('@', 1, 1, 0, 1, 1, 1, 0, 1, 0, 1, 0, 0, 0, 0), + +#define _MAP_65_90_ASCII_SEG14_ALPHA_UPPER \ + _SEG14('A', 1, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('B', 1, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 1, 0), \ + _SEG14('C', 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('D', 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('E', 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('F', 1, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('G', 1, 0, 1, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('H', 0, 1, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('I', 1, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('J', 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('K', 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1), \ + _SEG14('L', 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('M', 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 1, 0, 0, 0), \ + _SEG14('N', 0, 1, 1, 0, 1, 1, 0, 0, 1, 0, 0, 0, 0, 1), \ + _SEG14('O', 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('P', 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('Q', 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('R', 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1), \ + _SEG14('S', 1, 0, 1, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('T', 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('U', 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('V', 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 1, 1, 0, 0), \ + _SEG14('W', 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1), \ + _SEG14('X', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 0, 1), \ + _SEG14('Y', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 1, 0), \ + _SEG14('Z', 1, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 1, 0, 0), + +#define _MAP_91_96_ASCII_SEG14_SYMBOL \ + _SEG14('[', 1, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('\\',0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 1), \ + _SEG14(']', 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('^', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1), \ + _SEG14('_', 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('`', 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0), + +#define _MAP_97_122_ASCII_SEG14_ALPHA_LOWER \ + _SEG14('a', 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('b', 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1), \ + _SEG14('c', 0, 0, 0, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('d', 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 0, 1, 0, 0), \ + _SEG14('e', 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0, 1, 0, 0), \ + _SEG14('f', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 0, 1, 0), \ + _SEG14('g', 0, 1, 1, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0), \ + _SEG14('h', 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('i', 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('j', 0, 0, 0, 0, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0), \ + _SEG14('k', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 0, 1, 1), \ + _SEG14('l', 0, 0, 0, 0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('m', 0, 0, 1, 0, 1, 0, 1, 1, 0, 0, 0, 0, 1, 0), \ + _SEG14('n', 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 1, 0), \ + _SEG14('o', 0, 0, 1, 1, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0), \ + _SEG14('p', 0, 0, 0, 0, 1, 1, 1, 0, 1, 0, 0, 0, 0, 0), \ + _SEG14('q', 0, 1, 1, 0, 0, 0, 0, 1, 0, 0, 1, 0, 0, 0), \ + _SEG14('r', 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('s', 0, 0, 0, 1, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1), \ + _SEG14('t', 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('u', 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0), \ + _SEG14('v', 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 0), \ + _SEG14('w', 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 1, 0, 1), \ + _SEG14('x', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 0, 1, 0, 1), \ + _SEG14('y', 0, 1, 1, 1, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0), \ + _SEG14('z', 0, 0, 0, 1, 0, 0, 1, 0, 0, 0, 0, 1, 0, 0), + +#define _MAP_123_126_ASCII_SEG14_SYMBOL \ + _SEG14('{', 1, 0, 0, 1, 0, 0, 1, 0, 1, 0, 0, 1, 0, 0), \ + _SEG14('|', 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 1, 0), \ + _SEG14('}', 1, 0, 0, 1, 0, 0, 0, 1, 0, 0, 1, 0, 0, 1), \ + _SEG14('~', 0, 0, 0, 0, 0, 0, 1, 1, 0, 0, 1, 1, 0, 0), + +/* Maps */ +#define MAP_ASCII14SEG_ALPHANUM \ + _MAP_0_32_ASCII_SEG14_NON_PRINTABLE \ + _MAP_33_47_ASCII_SEG14_SYMBOL \ + _MAP_48_57_ASCII_SEG14_NUMERIC \ + _MAP_58_64_ASCII_SEG14_SYMBOL \ + _MAP_65_90_ASCII_SEG14_ALPHA_UPPER \ + _MAP_91_96_ASCII_SEG14_SYMBOL \ + _MAP_97_122_ASCII_SEG14_ALPHA_LOWER \ + _MAP_123_126_ASCII_SEG14_SYMBOL + +#define SEG14_DEFAULT_MAP(_name) \ + SEG14_CONVERSION_MAP(_name, MAP_ASCII14SEG_ALPHANUM) + +#endif /* MAP_TO_14SEGMENT_H */ -- cgit v1.2.3 From 9eeb3aa33ae005526f672b394c1791578463513f Mon Sep 17 00:00:00 2001 From: Hengqi Chen Date: Thu, 21 Oct 2021 21:47:51 +0800 Subject: bpf: Add bpf_skc_to_unix_sock() helper The helper is used in tracing programs to cast a socket pointer to a unix_sock pointer. The return value could be NULL if the casting is illegal. Suggested-by: Yonghong Song Signed-off-by: Hengqi Chen Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211021134752.1223426-2-hengqi.chen@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 7 +++++++ kernel/trace/bpf_trace.c | 2 ++ net/core/filter.c | 23 +++++++++++++++++++++++ scripts/bpf_doc.py | 2 ++ tools/include/uapi/linux/bpf.h | 7 +++++++ 6 files changed, 42 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index d604c8251d88..be3102b4554b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2093,6 +2093,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto; extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto; extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto; +extern const struct bpf_func_proto bpf_skc_to_unix_sock_proto; extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_snprintf_proto; diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 6b3153841a33..cbcd0d6fca7c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1608,6 +1608,8 @@ tracing_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_to_tcp_request_sock_proto; case BPF_FUNC_skc_to_udp6_sock: return &bpf_skc_to_udp6_sock_proto; + case BPF_FUNC_skc_to_unix_sock: + return &bpf_skc_to_unix_sock_proto; case BPF_FUNC_sk_storage_get: return &bpf_sk_storage_get_tracing_proto; case BPF_FUNC_sk_storage_delete: diff --git a/net/core/filter.c b/net/core/filter.c index 4bace37a6a44..8e8d3b49c297 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -10723,6 +10723,26 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; +BPF_CALL_1(bpf_skc_to_unix_sock, struct sock *, sk) +{ + /* unix_sock type is not generated in dwarf and hence btf, + * trigger an explicit type generation here. + */ + BTF_TYPE_EMIT(struct unix_sock); + if (sk && sk_fullsock(sk) && sk->sk_family == AF_UNIX) + return (unsigned long)sk; + + return (unsigned long)NULL; +} + +const struct bpf_func_proto bpf_skc_to_unix_sock_proto = { + .func = bpf_skc_to_unix_sock, + .gpl_only = false, + .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UNIX], +}; + BPF_CALL_1(bpf_sock_from_file, struct file *, file) { return (unsigned long)sock_from_file(file); @@ -10762,6 +10782,9 @@ bpf_sk_base_func_proto(enum bpf_func_id func_id) case BPF_FUNC_skc_to_udp6_sock: func = &bpf_skc_to_udp6_sock_proto; break; + case BPF_FUNC_skc_to_unix_sock: + func = &bpf_skc_to_unix_sock_proto; + break; default: return bpf_base_func_proto(func_id); } diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 00ac7b79cddb..a6403ddf5de7 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -537,6 +537,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct __sk_buff', @@ -589,6 +590,7 @@ class PrinterHelpers(Printer): 'struct tcp_timewait_sock', 'struct tcp_request_sock', 'struct udp6_sock', + 'struct unix_sock', 'struct task_struct', 'struct path', 'struct btf_ptr', diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 6fc59d61937a..22e7a3f38b9f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4909,6 +4909,12 @@ union bpf_attr { * Return * The number of bytes written to the buffer, or a negative error * in case of failure. + * + * struct unix_sock *bpf_skc_to_unix_sock(void *sk) + * Description + * Dynamically cast a *sk* pointer to a *unix_sock* pointer. + * Return + * *sk* if casting is valid, or **NULL** otherwise. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5089,6 +5095,7 @@ union bpf_attr { FN(task_pt_regs), \ FN(get_branch_snapshot), \ FN(trace_vprintk), \ + FN(skc_to_unix_sock), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From aba64c7da98330141dcdadd5612f088043a83696 Mon Sep 17 00:00:00 2001 From: Dave Marchevsky Date: Wed, 20 Oct 2021 00:48:17 -0700 Subject: bpf: Add verified_insns to bpf_prog_info and fdinfo This stat is currently printed in the verifier log and not stored anywhere. To ease consumption of this data, add a field to bpf_prog_aux so it can be exposed via BPF_OBJ_GET_INFO_BY_FD and fdinfo. Signed-off-by: Dave Marchevsky Signed-off-by: Andrii Nakryiko Acked-by: John Fastabend Link: https://lore.kernel.org/bpf/20211020074818.1017682-2-davemarchevsky@fb.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/syscall.c | 8 ++++++-- kernel/bpf/verifier.c | 1 + tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index be3102b4554b..31421c74ba08 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -887,6 +887,7 @@ struct bpf_prog_aux { struct bpf_prog *prog; struct user_struct *user; u64 load_time; /* ns since boottime */ + u32 verified_insns; struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE]; char name[BPF_OBJ_NAME_LEN]; #ifdef CONFIG_SECURITY diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 4e50c0bfdb7d..5beb321b3b3b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1848,7 +1848,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) "prog_id:\t%u\n" "run_time_ns:\t%llu\n" "run_cnt:\t%llu\n" - "recursion_misses:\t%llu\n", + "recursion_misses:\t%llu\n" + "verified_insns:\t%u\n", prog->type, prog->jited, prog_tag, @@ -1856,7 +1857,8 @@ static void bpf_prog_show_fdinfo(struct seq_file *m, struct file *filp) prog->aux->id, stats.nsecs, stats.cnt, - stats.misses); + stats.misses, + prog->aux->verified_insns); } #endif @@ -3625,6 +3627,8 @@ static int bpf_prog_get_info_by_fd(struct file *file, info.run_cnt = stats.cnt; info.recursion_misses = stats.misses; + info.verified_insns = prog->aux->verified_insns; + if (!bpf_capable()) { info.jited_prog_len = 0; info.xlated_prog_len = 0; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 21cdff35a2f9..c6616e325803 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -14033,6 +14033,7 @@ skip_full_check: env->verification_time = ktime_get_ns() - start_time; print_verification_stats(env); + env->prog->aux->verified_insns = env->insn_processed; if (log->level && bpf_verifier_log_full(log)) ret = -ENOSPC; diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 22e7a3f38b9f..c10820037883 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5620,6 +5620,7 @@ struct bpf_prog_info { __u64 run_time_ns; __u64 run_cnt; __u64 recursion_misses; + __u32 verified_insns; } __attribute__((aligned(8))); struct bpf_map_info { -- cgit v1.2.3 From 63dfe0709643528290c8a6825f278eda0e3f3c2e Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:32 +0900 Subject: can: bittiming: allow TDC{V,O} to be zero and add can_tdc_const::tdc{v,o,f}_min ISO 11898-1 specifies in section 11.3.3 "Transmitter delay compensation" that "the configuration range for [the] SSP position shall be at least 0 to 63 minimum time quanta." Because SSP = TDCV + TDCO, it means that we should allow both TDCV and TDCO to hold zero value in order to honor SSP's minimum possible value. However, current implementation assigned special meaning to TDCV and TDCO's zero values: * TDCV = 0 -> TDCV is automatically measured by the transceiver. * TDCO = 0 -> TDC is off. In order to allow for those values to really be zero and to maintain current features, we introduce two new flags: * CAN_CTRLMODE_TDC_AUTO indicates that the controller support automatic measurement of TDCV. * CAN_CTRLMODE_TDC_MANUAL indicates that the controller support manual configuration of TDCV. N.B.: current implementation failed to provide an option for the driver to indicate that only manual mode was supported. TDC is disabled if both CAN_CTRLMODE_TDC_AUTO and CAN_CTRLMODE_TDC_MANUAL flags are off, c.f. the helper function can_tdc_is_enabled() which is also introduced in this patch. Also, this patch adds three fields: tdcv_min, tdco_min and tdcf_min to struct can_tdc_const. While we are not convinced that those three fields could be anything else than zero, we can imagine that some controllers might specify a lower bound on these. Thus, those minimums are really added "just in case". Comments of struct can_tdc and can_tdc_const are updated accordingly. Finally, the changes are applied to the etas_es58x driver. Link: https://lore.kernel.org/all/20210918095637.20108-2-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/bittiming.c | 10 +++-- drivers/net/can/usb/etas_es58x/es58x_fd.c | 7 +++- include/linux/can/bittiming.h | 64 +++++++++++++++++++++++-------- include/linux/can/dev.h | 4 ++ include/uapi/linux/can/netlink.h | 2 + 5 files changed, 65 insertions(+), 22 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/can/dev/bittiming.c b/drivers/net/can/dev/bittiming.c index b1b5a82f0829..9dda44c0ae9d 100644 --- a/drivers/net/can/dev/bittiming.c +++ b/drivers/net/can/dev/bittiming.c @@ -182,9 +182,12 @@ void can_calc_tdco(struct net_device *dev) struct can_tdc *tdc = &priv->tdc; const struct can_tdc_const *tdc_const = priv->tdc_const; - if (!tdc_const) + if (!tdc_const || + !(priv->ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO)) return; + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + /* As specified in ISO 11898-1 section 11.3.3 "Transmitter * delay compensation" (TDC) is only applicable if data BRP is * one or two. @@ -193,9 +196,10 @@ void can_calc_tdco(struct net_device *dev) /* Reuse "normal" sample point and convert it to time quanta */ u32 sample_point_in_tq = can_bit_time(dbt) * dbt->sample_point / 1000; + if (sample_point_in_tq < tdc_const->tdco_min) + return; tdc->tdco = min(sample_point_in_tq, tdc_const->tdco_max); - } else { - tdc->tdco = 0; + priv->ctrlmode |= CAN_CTRLMODE_TDC_AUTO; } } #endif /* CONFIG_CAN_CALC_BITTIMING */ diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c index af042aa55f59..4f0cae29f4d8 100644 --- a/drivers/net/can/usb/etas_es58x/es58x_fd.c +++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c @@ -428,7 +428,7 @@ static int es58x_fd_enable_channel(struct es58x_priv *priv) es58x_fd_convert_bittiming(&tx_conf_msg.data_bittiming, &priv->can.data_bittiming); - if (priv->can.tdc.tdco) { + if (can_tdc_is_enabled(&priv->can)) { tx_conf_msg.tdc_enabled = 1; tx_conf_msg.tdco = cpu_to_le16(priv->can.tdc.tdco); tx_conf_msg.tdcf = cpu_to_le16(priv->can.tdc.tdcf); @@ -505,8 +505,11 @@ static const struct can_bittiming_const es58x_fd_data_bittiming_const = { * Register" from Microchip. */ static const struct can_tdc_const es58x_tdc_const = { + .tdcv_min = 0, .tdcv_max = 0, /* Manual mode not supported. */ + .tdco_min = 0, .tdco_max = 127, + .tdcf_min = 0, .tdcf_max = 127 }; @@ -523,7 +526,7 @@ const struct es58x_parameters es58x_fd_param = { .clock = {.freq = 80 * CAN_MHZ}, .ctrlmode_supported = CAN_CTRLMODE_LOOPBACK | CAN_CTRLMODE_LISTENONLY | CAN_CTRLMODE_3_SAMPLES | CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO | - CAN_CTRLMODE_CC_LEN8_DLC, + CAN_CTRLMODE_CC_LEN8_DLC | CAN_CTRLMODE_TDC_AUTO, .tx_start_of_frame = 0xCEFA, /* FACE in little endian */ .rx_start_of_frame = 0xFECA, /* CAFE in little endian */ .tx_urb_cmd_max_len = ES58X_FD_TX_URB_CMD_MAX_LEN, diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h index 9de6e9053e34..9e20260611cc 100644 --- a/include/linux/can/bittiming.h +++ b/include/linux/can/bittiming.h @@ -19,6 +19,9 @@ /* Megahertz */ #define CAN_MHZ 1000000UL +#define CAN_CTRLMODE_TDC_MASK \ + (CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL) + /* * struct can_tdc - CAN FD Transmission Delay Compensation parameters * @@ -33,29 +36,43 @@ * * This structure contains the parameters to calculate that SSP. * - * @tdcv: Transmitter Delay Compensation Value. Distance, in time - * quanta, from when the bit is sent on the TX pin to when it is - * received on the RX pin of the transmitter. Possible options: + * -+----------- one bit ----------+-- TX pin + * |<--- Sample Point --->| + * + * --+----------- one bit ----------+-- RX pin + * |<-------- TDCV -------->| + * |<------- TDCO ------->| + * |<----------- Secondary Sample Point ---------->| + * + * @tdcv: Transmitter Delay Compensation Value. The time needed for + * the signal to propagate, i.e. the distance, in time quanta, + * from the start of the bit on the TX pin to when it is received + * on the RX pin. @tdcv depends on the controller modes: + * + * CAN_CTRLMODE_TDC_AUTO is set: The transceiver dynamically + * measures @tdcv for each transmitted CAN FD frame and the + * value provided here should be ignored. * - * 0: automatic mode. The controller dynamically measures @tdcv - * for each transmitted CAN FD frame. + * CAN_CTRLMODE_TDC_MANUAL is set: use the fixed provided @tdcv + * value. * - * Other values: manual mode. Use the fixed provided value. + * N.B. CAN_CTRLMODE_TDC_AUTO and CAN_CTRLMODE_TDC_MANUAL are + * mutually exclusive. Only one can be set at a time. If both + * CAN_TDC_CTRLMODE_AUTO and CAN_TDC_CTRLMODE_MANUAL are unset, + * TDC is disabled and all the values of this structure should be + * ignored. * * @tdco: Transmitter Delay Compensation Offset. Offset value, in time * quanta, defining the distance between the start of the bit * reception on the RX pin of the transceiver and the SSP * position such that SSP = @tdcv + @tdco. * - * If @tdco is zero, then TDC is disabled and both @tdcv and - * @tdcf should be ignored. - * * @tdcf: Transmitter Delay Compensation Filter window. Defines the - * minimum value for the SSP position in time quanta. If SSP is - * less than @tdcf, then no delay compensations occur and the - * normal sampling point is used instead. The feature is enabled - * if and only if @tdcv is set to zero (automatic mode) and @tdcf - * is configured to a value greater than @tdco. + * minimum value for the SSP position in time quanta. If the SSP + * position is less than @tdcf, then no delay compensations occur + * and the normal sampling point is used instead. The feature is + * enabled if and only if @tdcv is set to zero (automatic mode) + * and @tdcf is configured to a value greater than @tdco. */ struct can_tdc { u32 tdcv; @@ -67,19 +84,32 @@ struct can_tdc { * struct can_tdc_const - CAN hardware-dependent constant for * Transmission Delay Compensation * - * @tdcv_max: Transmitter Delay Compensation Value maximum value. - * Should be set to zero if the controller does not support - * manual mode for tdcv. + * @tdcv_min: Transmitter Delay Compensation Value minimum value. If + * the controller does not support manual mode for tdcv + * (c.f. flag CAN_CTRLMODE_TDC_MANUAL) then this value is + * ignored. + * @tdcv_max: Transmitter Delay Compensation Value maximum value. If + * the controller does not support manual mode for tdcv + * (c.f. flag CAN_CTRLMODE_TDC_MANUAL) then this value is + * ignored. + * + * @tdco_min: Transmitter Delay Compensation Offset minimum value. * @tdco_max: Transmitter Delay Compensation Offset maximum value. * Should not be zero. If the controller does not support TDC, * then the pointer to this structure should be NULL. + * + * @tdcf_min: Transmitter Delay Compensation Filter window minimum + * value. If @tdcf_max is zero, this value is ignored. * @tdcf_max: Transmitter Delay Compensation Filter window maximum * value. Should be set to zero if the controller does not * support this feature. */ struct can_tdc_const { + u32 tdcv_min; u32 tdcv_max; + u32 tdco_min; u32 tdco_max; + u32 tdcf_min; u32 tdcf_max; }; diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 2413253e54c7..6dacbbb41e68 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -96,6 +96,10 @@ struct can_priv { #endif }; +static inline bool can_tdc_is_enabled(const struct can_priv *priv) +{ + return !!(priv->ctrlmode & CAN_CTRLMODE_TDC_MASK); +} /* helper to define static CAN controller features at device creation time */ static inline void can_set_static_ctrlmode(struct net_device *dev, diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index f730d443b918..004cd09a7d49 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -101,6 +101,8 @@ struct can_ctrlmode { #define CAN_CTRLMODE_PRESUME_ACK 0x40 /* Ignore missing CAN ACKs */ #define CAN_CTRLMODE_FD_NON_ISO 0x80 /* CAN FD in non-ISO mode */ #define CAN_CTRLMODE_CC_LEN8_DLC 0x100 /* Classic CAN DLC option */ +#define CAN_CTRLMODE_TDC_AUTO 0x200 /* CAN transiver automatically calculates TDCV */ +#define CAN_CTRLMODE_TDC_MANUAL 0x400 /* TDCV is manually set up by user */ /* * CAN device statistics -- cgit v1.2.3 From d99755f71a80df33b981484f0d3bb956ed15a247 Mon Sep 17 00:00:00 2001 From: Vincent Mailhol Date: Sat, 18 Sep 2021 18:56:35 +0900 Subject: can: netlink: add interface for CAN-FD Transmitter Delay Compensation (TDC) Add the netlink interface for TDC parameters of struct can_tdc_const and can_tdc. Contrary to the can_bittiming(_const) structures for which there is just a single IFLA_CAN(_DATA)_BITTMING(_CONST) entry per structure, here, we create a nested entry IFLA_CAN_TDC. Within this nested entry, additional IFLA_CAN_TDC_TDC* entries are added for each of the TDC parameters of the newly introduced struct can_tdc_const and struct can_tdc. For struct can_tdc_const, these are: IFLA_CAN_TDC_TDCV_MIN IFLA_CAN_TDC_TDCV_MAX IFLA_CAN_TDC_TDCO_MIN IFLA_CAN_TDC_TDCO_MAX IFLA_CAN_TDC_TDCF_MIN IFLA_CAN_TDC_TDCF_MAX For struct can_tdc, these are: IFLA_CAN_TDC_TDCV IFLA_CAN_TDC_TDCO IFLA_CAN_TDC_TDCF This is done so that changes can be applied in the future to the structures without breaking the netlink interface. The TDC netlink logic works as follow: * CAN_CTRLMODE_FD is not provided: - if any TDC parameters are provided: error. - TDC parameters not provided: TDC parameters unchanged. * CAN_CTRLMODE_FD is provided and is false: - TDC is deactivated: both the structure and the CAN_CTRLMODE_TDC_{AUTO,MANUAL} flags are flushed. * CAN_CTRLMODE_FD provided and is true: - CAN_CTRLMODE_TDC_{AUTO,MANUAL} and tdc{v,o,f} not provided: call can_calc_tdco() to automatically decide whether TDC should be activated and, if so, set CAN_CTRLMODE_TDC_AUTO and uses the calculated tdco value. - CAN_CTRLMODE_TDC_AUTO and tdco provided: set CAN_CTRLMODE_TDC_AUTO and use the provided tdco value. Here, tdcv is illegal and tdcf is optional. - CAN_CTRLMODE_TDC_MANUAL and both of tdcv and tdco provided: set CAN_CTRLMODE_TDC_MANUAL and use the provided tdcv and tdco value. Here, tdcf is optional. - CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually exclusive. Whenever one flag is turned on, the other will automatically be turned off. Providing both returns an error. - Combination other than the one listed above are illegal and will return an error. N.B. above rules mean that whenever CAN_CTRLMODE_FD is provided, the previous TDC values will be overwritten. The only option to reuse previous TDC value is to not provide CAN_CTRLMODE_FD. All the new parameters are defined as u32. This arbitrary choice is done to mimic the other bittiming values with are also all of type u32. An u16 would have been sufficient to hold the TDC values. This patch completes below series (c.f. [1]): - commit 289ea9e4ae59 ("can: add new CAN FD bittiming parameters: Transmitter Delay Compensation (TDC)") - commit c25cc7993243 ("can: bittiming: add calculation for CAN FD Transmitter Delay Compensation (TDC)") [1] https://lore.kernel.org/linux-can/20210224002008.4158-1-mailhol.vincent@wanadoo.fr/T/#t Link: https://lore.kernel.org/all/20210918095637.20108-5-mailhol.vincent@wanadoo.fr Signed-off-by: Vincent Mailhol Signed-off-by: Marc Kleine-Budde --- drivers/net/can/dev/netlink.c | 213 ++++++++++++++++++++++++++++++++++++++- include/uapi/linux/can/netlink.h | 29 +++++- 2 files changed, 235 insertions(+), 7 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c index e79c9a2ffbfc..c77cc6ae88b6 100644 --- a/drivers/net/can/dev/netlink.c +++ b/drivers/net/can/dev/netlink.c @@ -2,6 +2,7 @@ /* Copyright (C) 2005 Marc Kleine-Budde, Pengutronix * Copyright (C) 2006 Andrey Volkov, Varma Electronics * Copyright (C) 2008-2009 Wolfgang Grandegger + * Copyright (C) 2021 Vincent Mailhol */ #include @@ -19,6 +20,19 @@ static const struct nla_policy can_policy[IFLA_CAN_MAX + 1] = { [IFLA_CAN_DATA_BITTIMING] = { .len = sizeof(struct can_bittiming) }, [IFLA_CAN_DATA_BITTIMING_CONST] = { .len = sizeof(struct can_bittiming_const) }, [IFLA_CAN_TERMINATION] = { .type = NLA_U16 }, + [IFLA_CAN_TDC] = { .type = NLA_NESTED }, +}; + +static const struct nla_policy can_tdc_policy[IFLA_CAN_TDC_MAX + 1] = { + [IFLA_CAN_TDC_TDCV_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCV_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCO_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCO_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCF_MIN] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCF_MAX] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCV] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCO] = { .type = NLA_U32 }, + [IFLA_CAN_TDC_TDCF] = { .type = NLA_U32 }, }; static int can_validate(struct nlattr *tb[], struct nlattr *data[], @@ -30,6 +44,7 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], * - nominal/arbitration bittiming * - data bittiming * - control mode with CAN_CTRLMODE_FD set + * - TDC parameters are coherent (details below) */ if (!data) @@ -37,8 +52,43 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_CAN_CTRLMODE]) { struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]); + u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK; is_can_fd = cm->flags & cm->mask & CAN_CTRLMODE_FD; + + /* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually exclusive */ + if (tdc_flags == CAN_CTRLMODE_TDC_MASK) + return -EOPNOTSUPP; + /* If one of the CAN_CTRLMODE_TDC_* flag is set then + * TDC must be set and vice-versa + */ + if (!!tdc_flags != !!data[IFLA_CAN_TDC]) + return -EOPNOTSUPP; + /* If providing TDC parameters, at least TDCO is + * needed. TDCV is needed if and only if + * CAN_CTRLMODE_TDC_MANUAL is set + */ + if (data[IFLA_CAN_TDC]) { + struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; + int err; + + err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, + data[IFLA_CAN_TDC], + can_tdc_policy, extack); + if (err) + return err; + + if (tb_tdc[IFLA_CAN_TDC_TDCV]) { + if (tdc_flags & CAN_CTRLMODE_TDC_AUTO) + return -EOPNOTSUPP; + } else { + if (tdc_flags & CAN_CTRLMODE_TDC_MANUAL) + return -EOPNOTSUPP; + } + + if (!tb_tdc[IFLA_CAN_TDC_TDCO]) + return -EOPNOTSUPP; + } } if (is_can_fd) { @@ -46,7 +96,7 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], return -EOPNOTSUPP; } - if (data[IFLA_CAN_DATA_BITTIMING]) { + if (data[IFLA_CAN_DATA_BITTIMING] || data[IFLA_CAN_TDC]) { if (!is_can_fd) return -EOPNOTSUPP; } @@ -54,11 +104,60 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla, + struct netlink_ext_ack *extack) +{ + struct nlattr *tb_tdc[IFLA_CAN_TDC_MAX + 1]; + struct can_tdc tdc = { 0 }; + const struct can_tdc_const *tdc_const = priv->tdc_const; + int err; + + if (!tdc_const || !can_tdc_is_enabled(priv)) + return -EOPNOTSUPP; + + err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, nla, + can_tdc_policy, extack); + if (err) + return err; + + if (tb_tdc[IFLA_CAN_TDC_TDCV]) { + u32 tdcv = nla_get_u32(tb_tdc[IFLA_CAN_TDC_TDCV]); + + if (tdcv < tdc_const->tdcv_min || tdcv > tdc_const->tdcv_max) + return -EINVAL; + + tdc.tdcv = tdcv; + } + + if (tb_tdc[IFLA_CAN_TDC_TDCO]) { + u32 tdco = nla_get_u32(tb_tdc[IFLA_CAN_TDC_TDCO]); + + if (tdco < tdc_const->tdco_min || tdco > tdc_const->tdco_max) + return -EINVAL; + + tdc.tdco = tdco; + } + + if (tb_tdc[IFLA_CAN_TDC_TDCF]) { + u32 tdcf = nla_get_u32(tb_tdc[IFLA_CAN_TDC_TDCF]); + + if (tdcf < tdc_const->tdcf_min || tdcf > tdc_const->tdcf_max) + return -EINVAL; + + tdc.tdcf = tdcf; + } + + priv->tdc = tdc; + + return 0; +} + static int can_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct can_priv *priv = netdev_priv(dev); + u32 tdc_mask = 0; int err; /* We need synchronization with dev->stop() */ @@ -138,7 +237,16 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], dev->mtu = CAN_MTU; memset(&priv->data_bittiming, 0, sizeof(priv->data_bittiming)); + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + memset(&priv->tdc, 0, sizeof(priv->tdc)); } + + tdc_mask = cm->mask & CAN_CTRLMODE_TDC_MASK; + /* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually + * exclusive: make sure to turn the other one off + */ + if (tdc_mask) + priv->ctrlmode &= cm->flags | ~CAN_CTRLMODE_TDC_MASK; } if (data[IFLA_CAN_RESTART_MS]) { @@ -187,10 +295,26 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], return -EINVAL; } - memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); + memset(&priv->tdc, 0, sizeof(priv->tdc)); + if (data[IFLA_CAN_TDC]) { + /* TDC parameters are provided: use them */ + err = can_tdc_changelink(priv, data[IFLA_CAN_TDC], + extack); + if (err) { + priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK; + return err; + } + } else if (!tdc_mask) { + /* Neither of TDC parameters nor TDC flags are + * provided: do calculation + */ + can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, + &priv->ctrlmode, priv->ctrlmode_supported); + } /* else: both CAN_CTRLMODE_TDC_{AUTO,MANUAL} are explicitly + * turned off. TDC is disabled: do nothing + */ - can_calc_tdco(&priv->tdc, priv->tdc_const, &priv->data_bittiming, - &priv->ctrlmode, priv->ctrlmode_supported); + memcpy(&priv->data_bittiming, &dbt, sizeof(dbt)); if (priv->do_set_data_bittiming) { /* Finally, set the bit-timing registers */ @@ -227,6 +351,37 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[], return 0; } +static size_t can_tdc_get_size(const struct net_device *dev) +{ + struct can_priv *priv = netdev_priv(dev); + size_t size; + + if (!priv->tdc_const) + return 0; + + size = nla_total_size(0); /* nest IFLA_CAN_TDC */ + if (priv->ctrlmode_supported & CAN_CTRLMODE_TDC_MANUAL) { + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV_MAX */ + } + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO_MAX */ + if (priv->tdc_const->tdcf_max) { + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCF_MIN */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCF_MAX */ + } + + if (can_tdc_is_enabled(priv)) { + if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL) + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCV */ + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCO */ + if (priv->tdc_const->tdcf_max) + size += nla_total_size(sizeof(u32)); /* IFLA_CAN_TDCF */ + } + + return size; +} + static size_t can_get_size(const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -258,10 +413,56 @@ static size_t can_get_size(const struct net_device *dev) size += nla_total_size(sizeof(*priv->data_bitrate_const) * priv->data_bitrate_const_cnt); size += sizeof(priv->bitrate_max); /* IFLA_CAN_BITRATE_MAX */ + size += can_tdc_get_size(dev); /* IFLA_CAN_TDC */ return size; } +static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct nlattr *nest; + struct can_priv *priv = netdev_priv(dev); + struct can_tdc *tdc = &priv->tdc; + const struct can_tdc_const *tdc_const = priv->tdc_const; + + if (!tdc_const) + return 0; + + nest = nla_nest_start(skb, IFLA_CAN_TDC); + if (!nest) + return -EMSGSIZE; + + if (priv->ctrlmode_supported & CAN_CTRLMODE_TDC_MANUAL && + (nla_put_u32(skb, IFLA_CAN_TDC_TDCV_MIN, tdc_const->tdcv_min) || + nla_put_u32(skb, IFLA_CAN_TDC_TDCV_MAX, tdc_const->tdcv_max))) + goto err_cancel; + if (nla_put_u32(skb, IFLA_CAN_TDC_TDCO_MIN, tdc_const->tdco_min) || + nla_put_u32(skb, IFLA_CAN_TDC_TDCO_MAX, tdc_const->tdco_max)) + goto err_cancel; + if (tdc_const->tdcf_max && + (nla_put_u32(skb, IFLA_CAN_TDC_TDCF_MIN, tdc_const->tdcf_min) || + nla_put_u32(skb, IFLA_CAN_TDC_TDCF_MAX, tdc_const->tdcf_max))) + goto err_cancel; + + if (can_tdc_is_enabled(priv)) { + if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL && + nla_put_u32(skb, IFLA_CAN_TDC_TDCV, tdc->tdcv)) + goto err_cancel; + if (nla_put_u32(skb, IFLA_CAN_TDC_TDCO, tdc->tdco)) + goto err_cancel; + if (tdc_const->tdcf_max && + nla_put_u32(skb, IFLA_CAN_TDC_TDCF, tdc->tdcf)) + goto err_cancel; + } + + nla_nest_end(skb, nest); + return 0; + +err_cancel: + nla_nest_cancel(skb, nest); + return -EMSGSIZE; +} + static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct can_priv *priv = netdev_priv(dev); @@ -319,7 +520,9 @@ static int can_fill_info(struct sk_buff *skb, const struct net_device *dev) (nla_put(skb, IFLA_CAN_BITRATE_MAX, sizeof(priv->bitrate_max), - &priv->bitrate_max)) + &priv->bitrate_max)) || + + (can_tdc_fill_info(skb, dev)) ) return -EMSGSIZE; diff --git a/include/uapi/linux/can/netlink.h b/include/uapi/linux/can/netlink.h index 004cd09a7d49..75b85c60efb2 100644 --- a/include/uapi/linux/can/netlink.h +++ b/include/uapi/linux/can/netlink.h @@ -136,10 +136,35 @@ enum { IFLA_CAN_BITRATE_CONST, IFLA_CAN_DATA_BITRATE_CONST, IFLA_CAN_BITRATE_MAX, - __IFLA_CAN_MAX + IFLA_CAN_TDC, + + /* add new constants above here */ + __IFLA_CAN_MAX, + IFLA_CAN_MAX = __IFLA_CAN_MAX - 1 }; -#define IFLA_CAN_MAX (__IFLA_CAN_MAX - 1) +/* + * CAN FD Transmitter Delay Compensation (TDC) + * + * Please refer to struct can_tdc_const and can_tdc in + * include/linux/can/bittiming.h for further details. + */ +enum { + IFLA_CAN_TDC_UNSPEC, + IFLA_CAN_TDC_TDCV_MIN, /* u32 */ + IFLA_CAN_TDC_TDCV_MAX, /* u32 */ + IFLA_CAN_TDC_TDCO_MIN, /* u32 */ + IFLA_CAN_TDC_TDCO_MAX, /* u32 */ + IFLA_CAN_TDC_TDCF_MIN, /* u32 */ + IFLA_CAN_TDC_TDCF_MAX, /* u32 */ + IFLA_CAN_TDC_TDCV, /* u32 */ + IFLA_CAN_TDC_TDCO, /* u32 */ + IFLA_CAN_TDC_TDCF, /* u32 */ + + /* add new constants above here */ + __IFLA_CAN_TDC, + IFLA_CAN_TDC_MAX = __IFLA_CAN_TDC - 1 +}; /* u16 termination range: 1..65535 Ohms */ #define CAN_TERMINATION_DISABLED 0 -- cgit v1.2.3 From a9d496d8e08ca1eb43d14cb734839b24ab0e8083 Mon Sep 17 00:00:00 2001 From: David Edmondson Date: Mon, 20 Sep 2021 11:37:34 +0100 Subject: KVM: x86: Clarify the kvm_run.emulation_failure structure layout Until more flags for kvm_run.emulation_failure flags are defined, it is undetermined whether new payload elements corresponding to those flags will be additive or alternative. As a hint to userspace that an alternative is possible, wrap the current payload elements in a union. Suggested-by: Sean Christopherson Signed-off-by: David Edmondson Reviewed-by: Sean Christopherson Message-Id: <20210920103737.2696756-2-david.edmondson@oracle.com> Signed-off-by: Paolo Bonzini --- include/uapi/linux/kvm.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 5ca5ffe16cb4..2c8aa8d4dac1 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -403,8 +403,12 @@ struct kvm_run { __u32 suberror; __u32 ndata; __u64 flags; - __u8 insn_size; - __u8 insn_bytes[15]; + union { + struct { + __u8 insn_size; + __u8 insn_bytes[15]; + }; + }; } emulation_failure; /* KVM_EXIT_OSI */ struct { -- cgit v1.2.3 From e615e355894e619785af81479ad6f5a05a8a2e3f Mon Sep 17 00:00:00 2001 From: David Edmondson Date: Mon, 20 Sep 2021 11:37:36 +0100 Subject: KVM: x86: On emulation failure, convey the exit reason, etc. to userspace Should instruction emulation fail, include the VM exit reason, etc. in the emulation_failure data passed to userspace, in order that the VMM can report it as a debugging aid when describing the failure. Suggested-by: Joao Martins Signed-off-by: David Edmondson Reviewed-by: Sean Christopherson Message-Id: <20210920103737.2696756-4-david.edmondson@oracle.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 3 ++ arch/x86/kvm/vmx/vmx.c | 5 +-- arch/x86/kvm/x86.c | 73 +++++++++++++++++++++++++++++++++-------- include/uapi/linux/kvm.h | 6 ++++ 4 files changed, 69 insertions(+), 18 deletions(-) (limited to 'include/uapi/linux') diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 0b8a9ea7a47b..88fce6ab4bbd 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1667,6 +1667,9 @@ extern u64 kvm_mce_cap_supported; int kvm_emulate_instruction(struct kvm_vcpu *vcpu, int emulation_type); int kvm_emulate_instruction_from_buffer(struct kvm_vcpu *vcpu, void *insn, int insn_len); +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, + u64 *data, u8 ndata); +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu); void kvm_enable_efer_bits(u64); bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer); diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 85ce11dac8fd..71f54d85f104 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -5408,10 +5408,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu) if (vmx->emulation_required && !vmx->rmode.vm86_active && vcpu->arch.exception.pending) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = - KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0377e61b8fc0..ac83d873d65b 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -7664,29 +7664,78 @@ void kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip) } EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt); -static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +static void prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata, u8 *insn_bytes, u8 insn_size) { - struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; - u32 insn_size = ctxt->fetch.end - ctxt->fetch.data; struct kvm_run *run = vcpu->run; + u64 info[5]; + u8 info_start; + + /* + * Zero the whole array used to retrieve the exit info, as casting to + * u32 for select entries will leave some chunks uninitialized. + */ + memset(&info, 0, sizeof(info)); + + static_call(kvm_x86_get_exit_info)(vcpu, (u32 *)&info[0], &info[1], + &info[2], (u32 *)&info[3], + (u32 *)&info[4]); run->exit_reason = KVM_EXIT_INTERNAL_ERROR; run->emulation_failure.suberror = KVM_INTERNAL_ERROR_EMULATION; - run->emulation_failure.ndata = 0; + + /* + * There's currently space for 13 entries, but 5 are used for the exit + * reason and info. Restrict to 4 to reduce the maintenance burden + * when expanding kvm_run.emulation_failure in the future. + */ + if (WARN_ON_ONCE(ndata > 4)) + ndata = 4; + + /* Always include the flags as a 'data' entry. */ + info_start = 1; run->emulation_failure.flags = 0; if (insn_size) { - run->emulation_failure.ndata = 3; + BUILD_BUG_ON((sizeof(run->emulation_failure.insn_size) + + sizeof(run->emulation_failure.insn_bytes) != 16)); + info_start += 2; run->emulation_failure.flags |= KVM_INTERNAL_ERROR_EMULATION_FLAG_INSTRUCTION_BYTES; run->emulation_failure.insn_size = insn_size; memset(run->emulation_failure.insn_bytes, 0x90, sizeof(run->emulation_failure.insn_bytes)); - memcpy(run->emulation_failure.insn_bytes, - ctxt->fetch.data, insn_size); + memcpy(run->emulation_failure.insn_bytes, insn_bytes, insn_size); } + + memcpy(&run->internal.data[info_start], info, sizeof(info)); + memcpy(&run->internal.data[info_start + ARRAY_SIZE(info)], data, + ndata * sizeof(data[0])); + + run->emulation_failure.ndata = info_start + ARRAY_SIZE(info) + ndata; } +static void prepare_emulation_ctxt_failure_exit(struct kvm_vcpu *vcpu) +{ + struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt; + + prepare_emulation_failure_exit(vcpu, NULL, 0, ctxt->fetch.data, + ctxt->fetch.end - ctxt->fetch.data); +} + +void __kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu, u64 *data, + u8 ndata) +{ + prepare_emulation_failure_exit(vcpu, data, ndata, NULL, 0); +} +EXPORT_SYMBOL_GPL(__kvm_prepare_emulation_failure_exit); + +void kvm_prepare_emulation_failure_exit(struct kvm_vcpu *vcpu) +{ + __kvm_prepare_emulation_failure_exit(vcpu, NULL, 0); +} +EXPORT_SYMBOL_GPL(kvm_prepare_emulation_failure_exit); + static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) { struct kvm *kvm = vcpu->kvm; @@ -7701,16 +7750,14 @@ static int handle_emulation_failure(struct kvm_vcpu *vcpu, int emulation_type) if (kvm->arch.exit_on_emulation_error || (emulation_type & EMULTYPE_SKIP)) { - prepare_emulation_failure_exit(vcpu); + prepare_emulation_ctxt_failure_exit(vcpu); return 0; } kvm_queue_exception(vcpu, UD_VECTOR); if (!is_guest_mode(vcpu) && static_call(kvm_x86_get_cpl)(vcpu) == 0) { - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + prepare_emulation_ctxt_failure_exit(vcpu); return 0; } @@ -12336,9 +12383,7 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r, * doesn't seem to be a real use-case behind such requests, just return * KVM_EXIT_INTERNAL_ERROR for now. */ - vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR; - vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION; - vcpu->run->internal.ndata = 0; + kvm_prepare_emulation_failure_exit(vcpu); return 0; } diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 2c8aa8d4dac1..78f0719cc2a3 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -398,6 +398,11 @@ struct kvm_run { * "ndata" is correct, that new fields are enumerated in "flags", * and that each flag enumerates fields that are 64-bit aligned * and sized (so that ndata+internal.data[] is valid/accurate). + * + * Space beyond the defined fields may be used to store arbitrary + * debug information relating to the emulation failure. It is + * accounted for in "ndata" but the format is unspecified and is + * not represented in "flags". Any such information is *not* ABI! */ struct { __u32 suberror; @@ -409,6 +414,7 @@ struct kvm_run { __u8 insn_bytes[15]; }; }; + /* Arbitrary debug data may follow. */ } emulation_failure; /* KVM_EXIT_OSI */ struct { -- cgit v1.2.3 From 1cf4e9a6fbdbc9850216a2a6d8ed52888679a077 Mon Sep 17 00:00:00 2001 From: Luo Jie Date: Sun, 24 Oct 2021 16:27:33 +0800 Subject: net: phy: add constants for fast retrain related register Add the constants for 2.5G fast retrain capability in 10G AN control register, fast retrain status and control register and THP bypass register into mdio.h. Signed-off-by: Luo Jie Reviewed-by: Andrew Lunn Signed-off-by: David S. Miller --- include/uapi/linux/mdio.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/mdio.h b/include/uapi/linux/mdio.h index bdf77dffa5a4..c54e6eae5366 100644 --- a/include/uapi/linux/mdio.h +++ b/include/uapi/linux/mdio.h @@ -53,12 +53,14 @@ #define MDIO_AN_EEE_LPABLE 61 /* EEE link partner ability */ #define MDIO_AN_EEE_ADV2 62 /* EEE advertisement 2 */ #define MDIO_AN_EEE_LPABLE2 63 /* EEE link partner ability 2 */ +#define MDIO_AN_CTRL2 64 /* AN THP bypass request control */ /* Media-dependent registers. */ #define MDIO_PMA_10GBT_SWAPPOL 130 /* 10GBASE-T pair swap & polarity */ #define MDIO_PMA_10GBT_TXPWR 131 /* 10GBASE-T TX power control */ #define MDIO_PMA_10GBT_SNR 133 /* 10GBASE-T SNR margin, lane A. * Lanes B-D are numbered 134-136. */ +#define MDIO_PMA_10GBR_FSRT_CSR 147 /* 10GBASE-R fast retrain status and control */ #define MDIO_PMA_10GBR_FECABLE 170 /* 10GBASE-R FEC ability */ #define MDIO_PCS_10GBX_STAT1 24 /* 10GBASE-X PCS status 1 */ #define MDIO_PCS_10GBRT_STAT1 32 /* 10GBASE-R/-T PCS status 1 */ @@ -239,6 +241,9 @@ #define MDIO_PMA_10GBR_FECABLE_ABLE 0x0001 /* FEC ability */ #define MDIO_PMA_10GBR_FECABLE_ERRABLE 0x0002 /* FEC error indic. ability */ +/* PMA 10GBASE-R Fast Retrain status and control register. */ +#define MDIO_PMA_10GBR_FSRT_ENABLE 0x0001 /* Fast retrain enable */ + /* PCS 10GBASE-R/-T status register 1. */ #define MDIO_PCS_10GBRT_STAT1_BLKLK 0x0001 /* Block lock attained */ @@ -247,6 +252,7 @@ #define MDIO_PCS_10GBRT_STAT2_BER 0x3f00 /* AN 10GBASE-T control register. */ +#define MDIO_AN_10GBT_CTRL_ADVFSRT2_5G 0x0020 /* Advertise 2.5GBASE-T fast retrain */ #define MDIO_AN_10GBT_CTRL_ADV2_5G 0x0080 /* Advertise 2.5GBASE-T */ #define MDIO_AN_10GBT_CTRL_ADV5G 0x0100 /* Advertise 5GBASE-T */ #define MDIO_AN_10GBT_CTRL_ADV10G 0x1000 /* Advertise 10GBASE-T */ @@ -289,6 +295,9 @@ #define MDIO_EEE_2_5GT 0x0001 /* 2.5GT EEE cap */ #define MDIO_EEE_5GT 0x0002 /* 5GT EEE cap */ +/* AN MultiGBASE-T AN control 2 */ +#define MDIO_AN_THP_BP2_5GT 0x0008 /* 2.5GT THP bypass request */ + /* 2.5G/5G Extended abilities register. */ #define MDIO_PMA_NG_EXTABLE_2_5GBT 0x0001 /* 2.5GBASET ability */ #define MDIO_PMA_NG_EXTABLE_5GBT 0x0002 /* 5GBASET ability */ -- cgit v1.2.3 From 99ce45d5e7dbde399997a630f45ac9f654fa4bcc Mon Sep 17 00:00:00 2001 From: Jeremy Kerr Date: Tue, 26 Oct 2021 09:57:28 +0800 Subject: mctp: Implement extended addressing This change allows an extended address struct - struct sockaddr_mctp_ext - to be passed to sendmsg/recvmsg. This allows userspace to specify output ifindex and physical address information (for sendmsg) or receive the input ifindex/physaddr for incoming messages (for recvmsg). This is typically used by userspace for MCTP address discovery and assignment operations. The extended addressing facility is conditional on a new sockopt: MCTP_OPT_ADDR_EXT; userspace must explicitly enable addressing before the kernel will consume/populate the extended address data. Includes a fix for an uninitialised var: Reported-by: kernel test robot Signed-off-by: Jeremy Kerr Signed-off-by: David S. Miller --- include/linux/socket.h | 1 + include/net/mctp.h | 13 +++++-- include/uapi/linux/mctp.h | 11 ++++++ net/mctp/af_mctp.c | 86 ++++++++++++++++++++++++++++++++++++----- net/mctp/route.c | 98 +++++++++++++++++++++++++++++++++++------------ 5 files changed, 170 insertions(+), 39 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/socket.h b/include/linux/socket.h index 7612d760b6a9..8ef26d89ef49 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -365,6 +365,7 @@ struct ucred { #define SOL_TLS 282 #define SOL_XDP 283 #define SOL_MPTCP 284 +#define SOL_MCTP 285 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/net/mctp.h b/include/net/mctp.h index 2a83443bdfac..23bec708f4c7 100644 --- a/include/net/mctp.h +++ b/include/net/mctp.h @@ -11,6 +11,7 @@ #include #include +#include #include #include @@ -58,6 +59,9 @@ struct mctp_sock { mctp_eid_t bind_addr; __u8 bind_type; + /* sendmsg()/recvmsg() uses struct sockaddr_mctp_ext */ + bool addr_ext; + /* list of mctp_sk_key, for incoming tag lookup. updates protected * by sk->net->keys_lock */ @@ -153,7 +157,10 @@ struct mctp_sk_key { struct mctp_skb_cb { unsigned int magic; unsigned int net; + int ifindex; /* extended/direct addressing if set */ mctp_eid_t src; + unsigned char halen; + unsigned char haddr[MAX_ADDR_LEN]; }; /* skb control-block accessors with a little extra debugging for initial @@ -177,6 +184,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) { struct mctp_skb_cb *cb = (void *)skb->cb; + BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb)); WARN_ON(cb->magic != 0x4d435450); return (void *)(skb->cb); } @@ -189,8 +197,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb) * * Updates to the route table are performed under rtnl; all reads under RCU, * so routes cannot be referenced over a RCU grace period. Specifically: A - * caller cannot block between mctp_route_lookup and passing the route to - * mctp_do_route. + * caller cannot block between mctp_route_lookup and mctp_route_release() */ struct mctp_route { mctp_eid_t min, max; @@ -210,8 +217,6 @@ struct mctp_route { struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet, mctp_eid_t daddr); -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb); - int mctp_local_output(struct sock *sk, struct mctp_route *rt, struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag); diff --git a/include/uapi/linux/mctp.h b/include/uapi/linux/mctp.h index 6acd4ccafbf7..07b0318716fc 100644 --- a/include/uapi/linux/mctp.h +++ b/include/uapi/linux/mctp.h @@ -11,6 +11,7 @@ #include #include +#include typedef __u8 mctp_eid_t; @@ -28,6 +29,14 @@ struct sockaddr_mctp { __u8 __smctp_pad1; }; +struct sockaddr_mctp_ext { + struct sockaddr_mctp smctp_base; + int smctp_ifindex; + __u8 smctp_halen; + __u8 __smctp_pad0[3]; + __u8 smctp_haddr[MAX_ADDR_LEN]; +}; + #define MCTP_NET_ANY 0x0 #define MCTP_ADDR_NULL 0x00 @@ -36,4 +45,6 @@ struct sockaddr_mctp { #define MCTP_TAG_MASK 0x07 #define MCTP_TAG_OWNER 0x08 +#define MCTP_OPT_ADDR_EXT 1 + #endif /* __UAPI_MCTP_H */ diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index 66a411d60b6c..d344b02a1cde 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -77,6 +77,7 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) const int hlen = MCTP_HEADER_MAXLEN + sizeof(struct mctp_hdr); int rc, addrlen = msg->msg_namelen; struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb; struct mctp_route *rt; struct sk_buff *skb; @@ -100,11 +101,6 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (addr->smctp_network == MCTP_NET_ANY) addr->smctp_network = mctp_default_net(sock_net(sk)); - rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, - addr->smctp_addr.s_addr); - if (!rt) - return -EHOSTUNREACH; - skb = sock_alloc_send_skb(sk, hlen + 1 + len, msg->msg_flags & MSG_DONTWAIT, &rc); if (!skb) @@ -116,19 +112,45 @@ static int mctp_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) *(u8 *)skb_put(skb, 1) = addr->smctp_type; rc = memcpy_from_msg((void *)skb_put(skb, len), msg, len); - if (rc < 0) { - kfree_skb(skb); - return rc; - } + if (rc < 0) + goto err_free; /* set up cb */ cb = __mctp_cb(skb); cb->net = addr->smctp_network; + /* direct addressing */ + if (msk->addr_ext && addrlen >= sizeof(struct sockaddr_mctp_ext)) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, + extaddr, msg->msg_name); + + if (extaddr->smctp_halen > sizeof(cb->haddr)) { + rc = -EINVAL; + goto err_free; + } + + cb->ifindex = extaddr->smctp_ifindex; + cb->halen = extaddr->smctp_halen; + memcpy(cb->haddr, extaddr->smctp_haddr, cb->halen); + + rt = NULL; + } else { + rt = mctp_route_lookup(sock_net(sk), addr->smctp_network, + addr->smctp_addr.s_addr); + if (!rt) { + rc = -EHOSTUNREACH; + goto err_free; + } + } + rc = mctp_local_output(sk, rt, skb, addr->smctp_addr.s_addr, addr->smctp_tag); return rc ? : len; + +err_free: + kfree_skb(skb); + return rc; } static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, @@ -136,6 +158,7 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, { DECLARE_SOCKADDR(struct sockaddr_mctp *, addr, msg->msg_name); struct sock *sk = sock->sk; + struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct sk_buff *skb; size_t msglen; u8 type; @@ -181,6 +204,16 @@ static int mctp_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, addr->smctp_tag = hdr->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO); msg->msg_namelen = sizeof(*addr); + + if (msk->addr_ext) { + DECLARE_SOCKADDR(struct sockaddr_mctp_ext *, ae, + msg->msg_name); + msg->msg_namelen = sizeof(*ae); + ae->smctp_ifindex = cb->ifindex; + ae->smctp_halen = cb->halen; + memset(ae->smctp_haddr, 0x0, sizeof(ae->smctp_haddr)); + memcpy(ae->smctp_haddr, cb->haddr, cb->halen); + } } rc = len; @@ -196,12 +229,45 @@ out_free: static int mctp_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { - return -EINVAL; + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + int val; + + if (level != SOL_MCTP) + return -EINVAL; + + if (optname == MCTP_OPT_ADDR_EXT) { + if (optlen != sizeof(int)) + return -EINVAL; + if (copy_from_sockptr(&val, optval, sizeof(int))) + return -EFAULT; + msk->addr_ext = val; + return 0; + } + + return -ENOPROTOOPT; } static int mctp_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { + struct mctp_sock *msk = container_of(sock->sk, struct mctp_sock, sk); + int len, val; + + if (level != SOL_MCTP) + return -EINVAL; + + if (get_user(len, optlen)) + return -EFAULT; + + if (optname == MCTP_OPT_ADDR_EXT) { + if (len != sizeof(int)) + return -EINVAL; + val = !!msk->addr_ext; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; + } + return -EINVAL; } diff --git a/net/mctp/route.c b/net/mctp/route.c index 82fb5ae524f6..c23ab3547ee5 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -434,6 +434,7 @@ static unsigned int mctp_route_mtu(struct mctp_route *rt) static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) { + struct mctp_skb_cb *cb = mctp_cb(skb); struct mctp_hdr *hdr = mctp_hdr(skb); char daddr_buf[MAX_ADDR_LEN]; char *daddr = NULL; @@ -448,9 +449,14 @@ static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb) return -EMSGSIZE; } - /* If lookup fails let the device handle daddr==NULL */ - if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) - daddr = daddr_buf; + if (cb->ifindex) { + /* direct route; use the hwaddr we stashed in sendmsg */ + daddr = cb->haddr; + } else { + /* If lookup fails let the device handle daddr==NULL */ + if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0) + daddr = daddr_buf; + } rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol), daddr, skb->dev->dev_addr, skb->len); @@ -649,16 +655,6 @@ static struct mctp_route *mctp_route_lookup_null(struct net *net, return NULL; } -/* sends a skb to rt and releases the route. */ -int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb) -{ - int rc; - - rc = rt->output(rt, skb); - mctp_route_release(rt); - return rc; -} - static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, unsigned int mtu, u8 tag) { @@ -725,7 +721,7 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, /* copy message payload */ skb_copy_bits(skb, pos, skb_transport_header(skb2), size); - /* do route, but don't drop the rt reference */ + /* do route */ rc = rt->output(rt, skb2); if (rc) break; @@ -734,7 +730,6 @@ static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb, pos += size; } - mctp_route_release(rt); consume_skb(skb); return rc; } @@ -744,15 +739,51 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, { struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk); struct mctp_skb_cb *cb = mctp_cb(skb); + struct mctp_route tmp_rt; + struct net_device *dev; struct mctp_hdr *hdr; unsigned long flags; unsigned int mtu; mctp_eid_t saddr; + bool ext_rt; int rc; u8 tag; - if (WARN_ON(!rt->dev)) + rc = -ENODEV; + + if (rt) { + ext_rt = false; + dev = NULL; + + if (WARN_ON(!rt->dev)) + goto out_release; + + } else if (cb->ifindex) { + ext_rt = true; + rt = &tmp_rt; + + rcu_read_lock(); + dev = dev_get_by_index_rcu(sock_net(sk), cb->ifindex); + if (!dev) { + rcu_read_unlock(); + return rc; + } + + rt->dev = __mctp_dev_get(dev); + rcu_read_unlock(); + + if (!rt->dev) + goto out_release; + + /* establish temporary route - we set up enough to keep + * mctp_route_output happy + */ + rt->output = mctp_route_output; + rt->mtu = 0; + + } else { return -EINVAL; + } spin_lock_irqsave(&rt->dev->addrs_lock, flags); if (rt->dev->num_addrs == 0) { @@ -765,18 +796,17 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, spin_unlock_irqrestore(&rt->dev->addrs_lock, flags); if (rc) - return rc; + goto out_release; if (req_tag & MCTP_HDR_FLAG_TO) { rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag); if (rc) - return rc; + goto out_release; tag |= MCTP_HDR_FLAG_TO; } else { tag = req_tag; } - skb->protocol = htons(ETH_P_MCTP); skb->priority = 0; skb_reset_transport_header(skb); @@ -796,12 +826,22 @@ int mctp_local_output(struct sock *sk, struct mctp_route *rt, mtu = mctp_route_mtu(rt); if (skb->len + sizeof(struct mctp_hdr) <= mtu) { - hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM | - tag; - return mctp_do_route(rt, skb); + hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | + MCTP_HDR_FLAG_EOM | tag; + rc = rt->output(rt, skb); } else { - return mctp_do_fragment_route(rt, skb, mtu, tag); + rc = mctp_do_fragment_route(rt, skb, mtu, tag); } + +out_release: + if (!ext_rt) + mctp_route_release(rt); + + if (dev) + dev_put(dev); + + return rc; + } /* route management */ @@ -942,8 +982,15 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX) goto err_drop; - cb = __mctp_cb(skb); + /* MCTP drivers must populate halen/haddr */ + if (dev->type == ARPHRD_MCTP) { + cb = mctp_cb(skb); + } else { + cb = __mctp_cb(skb); + cb->halen = 0; + } cb->net = READ_ONCE(mdev->net); + cb->ifindex = dev->ifindex; rt = mctp_route_lookup(net, cb->net, mh->dest); @@ -954,7 +1001,8 @@ static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev, if (!rt) goto err_drop; - mctp_do_route(rt, skb); + rt->output(rt, skb); + mctp_route_release(rt); return NET_RX_SUCCESS; -- cgit v1.2.3 From 8d11a4f43ef4679be0908026907a7613b33d7127 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:33 -0300 Subject: fanotify: Reserve UAPI bits for FAN_FS_ERROR FAN_FS_ERROR allows reporting of event type FS_ERROR to userspace, which is a mechanism to report file system wide problems via fanotify. This commit preallocate userspace visible bits to match the FS_ERROR event. Link: https://lore.kernel.org/r/20211025192746.66445-19-krisman@collabora.com Reviewed-by: Jan Kara Reviewed-by: Amir Goldstein Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 1 + include/uapi/linux/fanotify.h | 1 + 2 files changed, 2 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index c64d61b673ca..8f152445d75c 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -752,6 +752,7 @@ static int fanotify_handle_event(struct fsnotify_group *group, u32 mask, BUILD_BUG_ON(FAN_ONDIR != FS_ISDIR); BUILD_BUG_ON(FAN_OPEN_EXEC != FS_OPEN_EXEC); BUILD_BUG_ON(FAN_OPEN_EXEC_PERM != FS_OPEN_EXEC_PERM); + BUILD_BUG_ON(FAN_FS_ERROR != FS_ERROR); BUILD_BUG_ON(HWEIGHT32(ALL_FANOTIFY_EVENT_BITS) != 19); diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 64553df9d735..2990731ddc8b 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -20,6 +20,7 @@ #define FAN_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FAN_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ +#define FAN_FS_ERROR 0x00008000 /* Filesystem error */ #define FAN_OPEN_PERM 0x00010000 /* File open in perm check */ #define FAN_ACCESS_PERM 0x00020000 /* File accessed in perm check */ -- cgit v1.2.3 From 130a3c742107acff985541c28360c8b40203559c Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Mon, 25 Oct 2021 16:27:42 -0300 Subject: fanotify: Emit generic error info for error event The error info is a record sent to users on FAN_FS_ERROR events documenting the type of error. It also carries an error count, documenting how many errors were observed since the last reporting. Link: https://lore.kernel.org/r/20211025192746.66445-28-krisman@collabora.com Reviewed-by: Amir Goldstein Reviewed-by: Jan Kara Signed-off-by: Gabriel Krisman Bertazi Signed-off-by: Jan Kara --- fs/notify/fanotify/fanotify.c | 1 + fs/notify/fanotify/fanotify.h | 1 + fs/notify/fanotify/fanotify_user.c | 36 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/fanotify.h | 7 +++++++ 4 files changed, 45 insertions(+) (limited to 'include/uapi/linux') diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c index 465f07e70e6d..af61425e6e3b 100644 --- a/fs/notify/fanotify/fanotify.c +++ b/fs/notify/fanotify/fanotify.c @@ -621,6 +621,7 @@ static struct fanotify_event *fanotify_alloc_error_event( return NULL; fee->fae.type = FANOTIFY_EVENT_TYPE_FS_ERROR; + fee->error = report->error; fee->err_count = 1; fee->fsid = *fsid; diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h index edd7587adcc5..d25f500bf7e7 100644 --- a/fs/notify/fanotify/fanotify.h +++ b/fs/notify/fanotify/fanotify.h @@ -205,6 +205,7 @@ FANOTIFY_NE(struct fanotify_event *event) struct fanotify_error_event { struct fanotify_event fae; + s32 error; /* Error reported by the Filesystem. */ u32 err_count; /* Suppressed errors count */ __kernel_fsid_t fsid; /* FSID this error refers to. */ diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c index ff4a7373f7a5..fb817028d0b6 100644 --- a/fs/notify/fanotify/fanotify_user.c +++ b/fs/notify/fanotify/fanotify_user.c @@ -115,6 +115,8 @@ struct kmem_cache *fanotify_perm_event_cachep __read_mostly; (sizeof(struct fanotify_event_info_fid) + sizeof(struct file_handle)) #define FANOTIFY_PIDFD_INFO_HDR_LEN \ sizeof(struct fanotify_event_info_pidfd) +#define FANOTIFY_ERROR_INFO_LEN \ + (sizeof(struct fanotify_event_info_error)) static int fanotify_fid_info_len(int fh_len, int name_len) { @@ -139,6 +141,9 @@ static size_t fanotify_event_len(unsigned int info_mode, if (!info_mode) return event_len; + if (fanotify_is_error_event(event->mask)) + event_len += FANOTIFY_ERROR_INFO_LEN; + info = fanotify_event_info(event); if (fanotify_event_has_dir_fh(event)) { @@ -324,6 +329,28 @@ static int process_access_response(struct fsnotify_group *group, return -ENOENT; } +static size_t copy_error_info_to_user(struct fanotify_event *event, + char __user *buf, int count) +{ + struct fanotify_event_info_error info; + struct fanotify_error_event *fee = FANOTIFY_EE(event); + + info.hdr.info_type = FAN_EVENT_INFO_TYPE_ERROR; + info.hdr.pad = 0; + info.hdr.len = FANOTIFY_ERROR_INFO_LEN; + + if (WARN_ON(count < info.hdr.len)) + return -EFAULT; + + info.error = fee->error; + info.error_count = fee->err_count; + + if (copy_to_user(buf, &info, sizeof(info))) + return -EFAULT; + + return info.hdr.len; +} + static int copy_fid_info_to_user(__kernel_fsid_t *fsid, struct fanotify_fh *fh, int info_type, const char *name, size_t name_len, @@ -530,6 +557,15 @@ static int copy_info_records_to_user(struct fanotify_event *event, total_bytes += ret; } + if (fanotify_is_error_event(event->mask)) { + ret = copy_error_info_to_user(event, buf, count); + if (ret < 0) + return ret; + buf += ret; + count -= ret; + total_bytes += ret; + } + return total_bytes; } diff --git a/include/uapi/linux/fanotify.h b/include/uapi/linux/fanotify.h index 2990731ddc8b..bd1932c2074d 100644 --- a/include/uapi/linux/fanotify.h +++ b/include/uapi/linux/fanotify.h @@ -126,6 +126,7 @@ struct fanotify_event_metadata { #define FAN_EVENT_INFO_TYPE_DFID_NAME 2 #define FAN_EVENT_INFO_TYPE_DFID 3 #define FAN_EVENT_INFO_TYPE_PIDFD 4 +#define FAN_EVENT_INFO_TYPE_ERROR 5 /* Variable length info record following event metadata */ struct fanotify_event_info_header { @@ -160,6 +161,12 @@ struct fanotify_event_info_pidfd { __s32 pidfd; }; +struct fanotify_event_info_error { + struct fanotify_event_info_header hdr; + __s32 error; + __u32 error_count; +}; + struct fanotify_response { __s32 fd; __u32 response; -- cgit v1.2.3 From 2cc1ae4878282c75a569e8ec677d569601c99dda Mon Sep 17 00:00:00 2001 From: Michael Weiß Date: Sat, 4 Sep 2021 11:59:28 +0200 Subject: dm: introduce audit event module for device mapper MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit To be able to send auditing events to user space, we introduce a generic dm-audit module. It provides helper functions to emit audit events through the kernel audit subsystem. We claim the AUDIT_DM_CTRL type=1336 and AUDIT_DM_EVENT type=1337 out of the audit event messages range in the corresponding userspace api in 'include/uapi/linux/audit.h' for those events. AUDIT_DM_CTRL is used to provide information about creation and destruction of device mapper targets which are triggered by user space admin control actions. AUDIT_DM_EVENT is used to provide information about actual errors during operation of the mapped device, showing e.g. integrity violations in audit log. Following commits to device mapper targets actually will make use of this to emit those events in relevant cases. The audit logs look like this if executing the following simple test: # dd if=/dev/zero of=test.img bs=1M count=1024 # losetup -f test.img # integritysetup -vD format --integrity sha256 -t 32 /dev/loop0 # integritysetup open -D /dev/loop0 --integrity sha256 integritytest # integritysetup status integritytest # integritysetup close integritytest # integritysetup open -D /dev/loop0 --integrity sha256 integritytest # integritysetup status integritytest # dd if=/dev/urandom of=/dev/loop0 bs=512 count=1 seek=100000 # dd if=/dev/mapper/integritytest of=/dev/null ------------------------- audit.log from auditd type=UNKNOWN[1336] msg=audit(1630425039.363:184): module=integrity op=ctr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425039.471:185): module=integrity op=dtr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425039.611:186): module=integrity op=ctr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425054.475:187): module=integrity op=dtr ppid=3807 pid=3819 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425073.171:191): module=integrity op=ctr ppid=3807 pid=3883 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425087.239:192): module=integrity op=dtr ppid=3807 pid=3902 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1336] msg=audit(1630425093.755:193): module=integrity op=ctr ppid=3807 pid=3906 auid=1000 uid=0 gid=0 euid=0 suid=0 fsuid=0 egid=0 sgid=0 fsgid=0 tty=pts2 ses=3 comm="integritysetup" exe="/sbin/integritysetup" subj==unconfined dev=254:3 error_msg='success' res=1 type=UNKNOWN[1337] msg=audit(1630425112.119:194): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:195): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:196): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:197): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:198): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:199): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:200): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:201): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:202): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 type=UNKNOWN[1337] msg=audit(1630425112.119:203): module=integrity op=integrity-checksum dev=254:3 sector=77480 res=0 Signed-off-by: Michael Weiß Signed-off-by: Paul Moore # fix audit.h numbering Signed-off-by: Mike Snitzer --- drivers/md/Kconfig | 9 +++++ drivers/md/Makefile | 4 +++ drivers/md/dm-audit.c | 84 ++++++++++++++++++++++++++++++++++++++++++++++ drivers/md/dm-audit.h | 66 ++++++++++++++++++++++++++++++++++++ include/uapi/linux/audit.h | 2 ++ 5 files changed, 165 insertions(+) create mode 100644 drivers/md/dm-audit.c create mode 100644 drivers/md/dm-audit.h (limited to 'include/uapi/linux') diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig index f45fb372e51b..1bc4f48e9765 100644 --- a/drivers/md/Kconfig +++ b/drivers/md/Kconfig @@ -642,4 +642,13 @@ config DM_ZONED If unsure, say N. +config DM_AUDIT + bool "DM audit events" + depends on AUDIT + help + Generate audit events for device-mapper. + + Enables audit logging of several security relevant events in the + particular device-mapper targets, especially the integrity target. + endif # MD diff --git a/drivers/md/Makefile b/drivers/md/Makefile index 816945eeed7f..0454b0885b01 100644 --- a/drivers/md/Makefile +++ b/drivers/md/Makefile @@ -107,3 +107,7 @@ endif ifeq ($(CONFIG_DM_VERITY_VERIFY_ROOTHASH_SIG),y) dm-verity-objs += dm-verity-verify-sig.o endif + +ifeq ($(CONFIG_DM_AUDIT),y) +dm-mod-objs += dm-audit.o +endif diff --git a/drivers/md/dm-audit.c b/drivers/md/dm-audit.c new file mode 100644 index 000000000000..3049dfe67e50 --- /dev/null +++ b/drivers/md/dm-audit.c @@ -0,0 +1,84 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Creating audit records for mapped devices. + * + * Copyright (C) 2021 Fraunhofer AISEC. All rights reserved. + * + * Authors: Michael Weiß + */ + +#include +#include +#include +#include +#include + +#include "dm-audit.h" +#include "dm-core.h" + +static struct audit_buffer *dm_audit_log_start(int audit_type, + const char *dm_msg_prefix, + const char *op) +{ + struct audit_buffer *ab; + + if (audit_enabled == AUDIT_OFF) + return NULL; + + ab = audit_log_start(audit_context(), GFP_KERNEL, audit_type); + if (unlikely(!ab)) + return NULL; + + audit_log_format(ab, "module=%s op=%s", dm_msg_prefix, op); + return ab; +} + +void dm_audit_log_ti(int audit_type, const char *dm_msg_prefix, const char *op, + struct dm_target *ti, int result) +{ + struct audit_buffer *ab = NULL; + struct mapped_device *md = dm_table_get_md(ti->table); + int dev_major = dm_disk(md)->major; + int dev_minor = dm_disk(md)->first_minor; + + switch (audit_type) { + case AUDIT_DM_CTRL: + ab = dm_audit_log_start(audit_type, dm_msg_prefix, op); + if (unlikely(!ab)) + return; + audit_log_task_info(ab); + audit_log_format(ab, " dev=%d:%d error_msg='%s'", dev_major, + dev_minor, !result ? ti->error : "success"); + break; + case AUDIT_DM_EVENT: + ab = dm_audit_log_start(audit_type, dm_msg_prefix, op); + if (unlikely(!ab)) + return; + audit_log_format(ab, " dev=%d:%d sector=?", dev_major, + dev_minor); + break; + default: /* unintended use */ + return; + } + + audit_log_format(ab, " res=%d", result); + audit_log_end(ab); +} +EXPORT_SYMBOL_GPL(dm_audit_log_ti); + +void dm_audit_log_bio(const char *dm_msg_prefix, const char *op, + struct bio *bio, sector_t sector, int result) +{ + struct audit_buffer *ab; + int dev_major = MAJOR(bio->bi_bdev->bd_dev); + int dev_minor = MINOR(bio->bi_bdev->bd_dev); + + ab = dm_audit_log_start(AUDIT_DM_EVENT, dm_msg_prefix, op); + if (unlikely(!ab)) + return; + + audit_log_format(ab, " dev=%d:%d sector=%llu res=%d", + dev_major, dev_minor, sector, result); + audit_log_end(ab); +} +EXPORT_SYMBOL_GPL(dm_audit_log_bio); diff --git a/drivers/md/dm-audit.h b/drivers/md/dm-audit.h new file mode 100644 index 000000000000..2385f2b659be --- /dev/null +++ b/drivers/md/dm-audit.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Creating audit records for mapped devices. + * + * Copyright (C) 2021 Fraunhofer AISEC. All rights reserved. + * + * Authors: Michael Weiß + */ + +#ifndef DM_AUDIT_H +#define DM_AUDIT_H + +#include +#include + +#ifdef CONFIG_DM_AUDIT +void dm_audit_log_bio(const char *dm_msg_prefix, const char *op, + struct bio *bio, sector_t sector, int result); + +/* + * dm_audit_log_ti() is not intended to be used directly in dm modules, + * the wrapper functions below should be called by dm modules instead. + */ +void dm_audit_log_ti(int audit_type, const char *dm_msg_prefix, const char *op, + struct dm_target *ti, int result); + +static inline void dm_audit_log_ctr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ + dm_audit_log_ti(AUDIT_DM_CTRL, dm_msg_prefix, "ctr", ti, result); +} + +static inline void dm_audit_log_dtr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ + dm_audit_log_ti(AUDIT_DM_CTRL, dm_msg_prefix, "dtr", ti, result); +} + +static inline void dm_audit_log_target(const char *dm_msg_prefix, const char *op, + struct dm_target *ti, int result) +{ + dm_audit_log_ti(AUDIT_DM_EVENT, dm_msg_prefix, op, ti, result); +} +#else +static inline void dm_audit_log_bio(const char *dm_msg_prefix, const char *op, + struct bio *bio, sector_t sector, + int result) +{ +} +static inline void dm_audit_log_target(const char *dm_msg_prefix, + const char *op, struct dm_target *ti, + int result) +{ +} +static inline void dm_audit_log_ctr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ +} + +static inline void dm_audit_log_dtr(const char *dm_msg_prefix, + struct dm_target *ti, int result) +{ +} +#endif + +#endif diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h index daa481729e9b..809e4c2041b3 100644 --- a/include/uapi/linux/audit.h +++ b/include/uapi/linux/audit.h @@ -118,6 +118,8 @@ #define AUDIT_TIME_ADJNTPVAL 1333 /* NTP value adjustment */ #define AUDIT_BPF 1334 /* BPF subsystem */ #define AUDIT_EVENT_LISTENER 1335 /* Task joined multicast read socket */ +#define AUDIT_DM_CTRL 1338 /* Device Mapper target control */ +#define AUDIT_DM_EVENT 1339 /* Device Mapper events */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ -- cgit v1.2.3 From a390ccb316beb8ea594b8695d53926710ca454a3 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Sun, 24 Oct 2021 16:26:07 +0300 Subject: fuse: add FOPEN_NOFLUSH Add flag returned by FUSE_OPEN and FUSE_CREATE requests to avoid flushing data cache on close. Different filesystems implement ->flush() is different ways: - Most disk filesystems do not implement ->flush() at all - Some network filesystem (e.g. nfs) flush local write cache of FMODE_WRITE file and send a "flush" command to server - Some network filesystem (e.g. cifs) flush local write cache of FMODE_WRITE file without sending an additional command to server FUSE flushes local write cache of ANY file, even non FMODE_WRITE and sends a "flush" command to server (if server implements it). The FUSE implementation of ->flush() seems over agressive and arbitrary and does not make a lot of sense when writeback caching is disabled. Instead of deciding on another arbitrary implementation that makes sense, leave the choice of per-file flush behavior in the hands of the server. Link: https://lore.kernel.org/linux-fsdevel/CAJfpegspE8e6aKd47uZtSYX8Y-1e1FWS0VL0DH2Skb9gQP5RJQ@mail.gmail.com/ Suggested-by: Miklos Szeredi Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- fs/fuse/file.c | 3 +++ include/uapi/linux/fuse.h | 7 ++++++- 2 files changed, 9 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 26730e699d68..b7f1a164e18a 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -476,6 +476,9 @@ static int fuse_flush(struct file *file, fl_owner_t id) if (fuse_is_bad(inode)) return -EIO; + if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache) + return 0; + err = write_inode_now(inode, 1); if (err) return err; diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 36ed092227fa..a1dc3ee1d17c 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -184,6 +184,9 @@ * * 7.34 * - add FUSE_SYNCFS + * + * 7.35 + * - add FOPEN_NOFLUSH */ #ifndef _LINUX_FUSE_H @@ -219,7 +222,7 @@ #define FUSE_KERNEL_VERSION 7 /** Minor version number of this interface */ -#define FUSE_KERNEL_MINOR_VERSION 34 +#define FUSE_KERNEL_MINOR_VERSION 35 /** The node ID of the root inode */ #define FUSE_ROOT_ID 1 @@ -290,12 +293,14 @@ struct fuse_file_lock { * FOPEN_NONSEEKABLE: the file is not seekable * 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) */ #define FOPEN_DIRECT_IO (1 << 0) #define FOPEN_KEEP_CACHE (1 << 1) #define FOPEN_NONSEEKABLE (1 << 2) #define FOPEN_CACHE_DIR (1 << 3) #define FOPEN_STREAM (1 << 4) +#define FOPEN_NOFLUSH (1 << 5) /** * INIT request/reply flags -- cgit v1.2.3 From 9330986c03006ab1d33d243b7cfe598a7a3c1baa Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Wed, 27 Oct 2021 16:45:00 -0700 Subject: bpf: Add bloom filter map implementation This patch adds the kernel-side changes for the implementation of a bpf bloom filter map. The bloom filter map supports peek (determining whether an element is present in the map) and push (adding an element to the map) operations.These operations are exposed to userspace applications through the already existing syscalls in the following way: BPF_MAP_LOOKUP_ELEM -> peek BPF_MAP_UPDATE_ELEM -> push The bloom filter map does not have keys, only values. In light of this, the bloom filter map's API matches that of queue stack maps: user applications use BPF_MAP_LOOKUP_ELEM/BPF_MAP_UPDATE_ELEM which correspond internally to bpf_map_peek_elem/bpf_map_push_elem, and bpf programs must use the bpf_map_peek_elem and bpf_map_push_elem APIs to query or add an element to the bloom filter map. When the bloom filter map is created, it must be created with a key_size of 0. For updates, the user will pass in the element to add to the map as the value, with a NULL key. For lookups, the user will pass in the element to query in the map as the value, with a NULL key. In the verifier layer, this requires us to modify the argument type of a bloom filter's BPF_FUNC_map_peek_elem call to ARG_PTR_TO_MAP_VALUE; as well, in the syscall layer, we need to copy over the user value so that in bpf_map_peek_elem, we know which specific value to query. A few things to please take note of: * If there are any concurrent lookups + updates, the user is responsible for synchronizing this to ensure no false negative lookups occur. * The number of hashes to use for the bloom filter is configurable from userspace. If no number is specified, the default used will be 5 hash functions. The benchmarks later in this patchset can help compare the performance of using different number of hashes on different entry sizes. In general, using more hashes decreases both the false positive rate and the speed of a lookup. * Deleting an element in the bloom filter map is not supported. * The bloom filter map may be used as an inner map. * The "max_entries" size that is specified at map creation time is used to approximate a reasonable bitmap size for the bloom filter, and is not otherwise strictly enforced. If the user wishes to insert more entries into the bloom filter than "max_entries", they may do so but they should be aware that this may lead to a higher false positive rate. Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/bpf/20211027234504.30744-2-joannekoong@fb.com --- include/linux/bpf.h | 1 + include/linux/bpf_types.h | 1 + include/uapi/linux/bpf.h | 9 ++ kernel/bpf/Makefile | 2 +- kernel/bpf/bloom_filter.c | 195 +++++++++++++++++++++++++++++++++++++++++ kernel/bpf/syscall.c | 24 ++++- kernel/bpf/verifier.c | 19 +++- tools/include/uapi/linux/bpf.h | 9 ++ 8 files changed, 253 insertions(+), 7 deletions(-) create mode 100644 kernel/bpf/bloom_filter.c (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 31421c74ba08..50105e0b8fcc 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -169,6 +169,7 @@ struct bpf_map { u32 value_size; u32 max_entries; u32 map_flags; + u64 map_extra; /* any per-map-type extra fields */ int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 9c81724e4b98..c4424ac2fa02 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -125,6 +125,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops) +BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops) BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint) BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index 7f33098ca63f..cf6ca339f3cd 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -7,7 +7,7 @@ endif CFLAGS_core.o += $(call cc-disable-warning, override-init) $(cflags-nogcse-yy) obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o bpf_iter.o map_iter.o task_iter.o prog_iter.o -obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o +obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o bloom_filter.o obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o ringbuf.o obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o obj-${CONFIG_BPF_LSM} += bpf_inode_storage.o diff --git a/kernel/bpf/bloom_filter.c b/kernel/bpf/bloom_filter.c new file mode 100644 index 000000000000..7c50232b7571 --- /dev/null +++ b/kernel/bpf/bloom_filter.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021 Facebook */ + +#include +#include +#include +#include +#include +#include + +#define BLOOM_CREATE_FLAG_MASK \ + (BPF_F_NUMA_NODE | BPF_F_ZERO_SEED | BPF_F_ACCESS_MASK) + +struct bpf_bloom_filter { + struct bpf_map map; + u32 bitset_mask; + u32 hash_seed; + /* If the size of the values in the bloom filter is u32 aligned, + * then it is more performant to use jhash2 as the underlying hash + * function, else we use jhash. This tracks the number of u32s + * in an u32-aligned value size. If the value size is not u32 aligned, + * this will be 0. + */ + u32 aligned_u32_count; + u32 nr_hash_funcs; + unsigned long bitset[]; +}; + +static u32 hash(struct bpf_bloom_filter *bloom, void *value, + u32 value_size, u32 index) +{ + u32 h; + + if (bloom->aligned_u32_count) + h = jhash2(value, bloom->aligned_u32_count, + bloom->hash_seed + index); + else + h = jhash(value, value_size, bloom->hash_seed + index); + + return h & bloom->bitset_mask; +} + +static int peek_elem(struct bpf_map *map, void *value) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + if (!test_bit(h, bloom->bitset)) + return -ENOENT; + } + + return 0; +} + +static int push_elem(struct bpf_map *map, void *value, u64 flags) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + u32 i, h; + + if (flags != BPF_ANY) + return -EINVAL; + + for (i = 0; i < bloom->nr_hash_funcs; i++) { + h = hash(bloom, value, map->value_size, i); + set_bit(h, bloom->bitset); + } + + return 0; +} + +static int pop_elem(struct bpf_map *map, void *value) +{ + return -EOPNOTSUPP; +} + +static struct bpf_map *map_alloc(union bpf_attr *attr) +{ + u32 bitset_bytes, bitset_mask, nr_hash_funcs, nr_bits; + int numa_node = bpf_map_attr_numa_node(attr); + struct bpf_bloom_filter *bloom; + + if (!bpf_capable()) + return ERR_PTR(-EPERM); + + if (attr->key_size != 0 || attr->value_size == 0 || + attr->max_entries == 0 || + attr->map_flags & ~BLOOM_CREATE_FLAG_MASK || + !bpf_map_flags_access_ok(attr->map_flags) || + (attr->map_extra & ~0xF)) + return ERR_PTR(-EINVAL); + + /* The lower 4 bits of map_extra specify the number of hash functions */ + nr_hash_funcs = attr->map_extra & 0xF; + if (nr_hash_funcs == 0) + /* Default to using 5 hash functions if unspecified */ + nr_hash_funcs = 5; + + /* For the bloom filter, the optimal bit array size that minimizes the + * false positive probability is n * k / ln(2) where n is the number of + * expected entries in the bloom filter and k is the number of hash + * functions. We use 7 / 5 to approximate 1 / ln(2). + * + * We round this up to the nearest power of two to enable more efficient + * hashing using bitmasks. The bitmask will be the bit array size - 1. + * + * If this overflows a u32, the bit array size will have 2^32 (4 + * GB) bits. + */ + if (check_mul_overflow(attr->max_entries, nr_hash_funcs, &nr_bits) || + check_mul_overflow(nr_bits / 5, (u32)7, &nr_bits) || + nr_bits > (1UL << 31)) { + /* The bit array size is 2^32 bits but to avoid overflowing the + * u32, we use U32_MAX, which will round up to the equivalent + * number of bytes + */ + bitset_bytes = BITS_TO_BYTES(U32_MAX); + bitset_mask = U32_MAX; + } else { + if (nr_bits <= BITS_PER_LONG) + nr_bits = BITS_PER_LONG; + else + nr_bits = roundup_pow_of_two(nr_bits); + bitset_bytes = BITS_TO_BYTES(nr_bits); + bitset_mask = nr_bits - 1; + } + + bitset_bytes = roundup(bitset_bytes, sizeof(unsigned long)); + bloom = bpf_map_area_alloc(sizeof(*bloom) + bitset_bytes, numa_node); + + if (!bloom) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&bloom->map, attr); + + bloom->nr_hash_funcs = nr_hash_funcs; + bloom->bitset_mask = bitset_mask; + + /* Check whether the value size is u32-aligned */ + if ((attr->value_size & (sizeof(u32) - 1)) == 0) + bloom->aligned_u32_count = + attr->value_size / sizeof(u32); + + if (!(attr->map_flags & BPF_F_ZERO_SEED)) + bloom->hash_seed = get_random_int(); + + return &bloom->map; +} + +static void map_free(struct bpf_map *map) +{ + struct bpf_bloom_filter *bloom = + container_of(map, struct bpf_bloom_filter, map); + + bpf_map_area_free(bloom); +} + +static void *lookup_elem(struct bpf_map *map, void *key) +{ + /* The eBPF program should use map_peek_elem instead */ + return ERR_PTR(-EINVAL); +} + +static int update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + /* The eBPF program should use map_push_elem instead */ + return -EINVAL; +} + +static int check_btf(const struct bpf_map *map, const struct btf *btf, + const struct btf_type *key_type, + const struct btf_type *value_type) +{ + /* Bloom filter maps are keyless */ + return btf_type_is_void(key_type) ? 0 : -EINVAL; +} + +static int bpf_bloom_btf_id; +const struct bpf_map_ops bloom_filter_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc = map_alloc, + .map_free = map_free, + .map_push_elem = push_elem, + .map_peek_elem = peek_elem, + .map_pop_elem = pop_elem, + .map_lookup_elem = lookup_elem, + .map_update_elem = update_elem, + .map_check_btf = check_btf, + .map_btf_name = "bpf_bloom_filter", + .map_btf_id = &bpf_bloom_btf_id, +}; diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 3e1c024ce3ed..f7c2c6354add 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -199,7 +199,8 @@ static int bpf_map_update_value(struct bpf_map *map, struct fd f, void *key, err = bpf_fd_reuseport_array_update_elem(map, key, value, flags); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_push_elem(map, value, flags); } else { rcu_read_lock(); @@ -238,7 +239,8 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, } else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) { err = bpf_fd_reuseport_array_lookup_elem(map, key, value); } else if (map->map_type == BPF_MAP_TYPE_QUEUE || - map->map_type == BPF_MAP_TYPE_STACK) { + map->map_type == BPF_MAP_TYPE_STACK || + map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { err = map->ops->map_peek_elem(map, value); } else if (map->map_type == BPF_MAP_TYPE_STRUCT_OPS) { /* struct_ops map requires directly updating "value" */ @@ -348,6 +350,7 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->max_entries = attr->max_entries; map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags); map->numa_node = bpf_map_attr_numa_node(attr); + map->map_extra = attr->map_extra; } static int bpf_map_alloc_id(struct bpf_map *map) @@ -553,6 +556,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" + "map_extra:\t%#llx\n" "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", @@ -561,6 +565,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, + (unsigned long long)map->map_extra, bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); @@ -810,7 +815,7 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, return ret; } -#define BPF_MAP_CREATE_LAST_FIELD btf_vmlinux_value_type_id +#define BPF_MAP_CREATE_LAST_FIELD map_extra /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -831,6 +836,10 @@ static int map_create(union bpf_attr *attr) return -EINVAL; } + if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER && + attr->map_extra != 0) + return -EINVAL; + f_flags = bpf_get_file_flag(attr->map_flags); if (f_flags < 0) return f_flags; @@ -1080,6 +1089,14 @@ static int map_lookup_elem(union bpf_attr *attr) if (!value) goto free_key; + if (map->map_type == BPF_MAP_TYPE_BLOOM_FILTER) { + if (copy_from_user(value, uvalue, value_size)) + err = -EFAULT; + else + err = bpf_map_copy_value(map, key, value, attr->flags); + goto free_value; + } + err = bpf_map_copy_value(map, key, value, attr->flags); if (err) goto free_value; @@ -3881,6 +3898,7 @@ static int bpf_map_get_info_by_fd(struct file *file, info.value_size = map->value_size; info.max_entries = map->max_entries; info.map_flags = map->map_flags; + info.map_extra = map->map_extra; memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c6616e325803..3c8aa7df1773 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5002,7 +5002,10 @@ static int resolve_map_arg_type(struct bpf_verifier_env *env, return -EINVAL; } break; - + case BPF_MAP_TYPE_BLOOM_FILTER: + if (meta->func_id == BPF_FUNC_map_peek_elem) + *arg_type = ARG_PTR_TO_MAP_VALUE; + break; default: break; } @@ -5577,6 +5580,11 @@ 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_BLOOM_FILTER: + if (func_id != BPF_FUNC_map_peek_elem && + func_id != BPF_FUNC_map_push_elem) + goto error; + break; default: break; } @@ -5644,13 +5652,18 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, map->map_type != BPF_MAP_TYPE_SOCKHASH) goto error; break; - case BPF_FUNC_map_peek_elem: case BPF_FUNC_map_pop_elem: - case BPF_FUNC_map_push_elem: if (map->map_type != BPF_MAP_TYPE_QUEUE && map->map_type != BPF_MAP_TYPE_STACK) goto error; break; + case BPF_FUNC_map_peek_elem: + case BPF_FUNC_map_push_elem: + if (map->map_type != BPF_MAP_TYPE_QUEUE && + map->map_type != BPF_MAP_TYPE_STACK && + map->map_type != BPF_MAP_TYPE_BLOOM_FILTER) + goto error; + break; case BPF_FUNC_sk_storage_get: case BPF_FUNC_sk_storage_delete: if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c10820037883..8bead4aa3ad0 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -906,6 +906,7 @@ enum bpf_map_type { BPF_MAP_TYPE_RINGBUF, BPF_MAP_TYPE_INODE_STORAGE, BPF_MAP_TYPE_TASK_STORAGE, + BPF_MAP_TYPE_BLOOM_FILTER, }; /* Note that tracing related programs such as @@ -1274,6 +1275,13 @@ union bpf_attr { * struct stored as the * map value */ + /* Any per-map-type extra fields + * + * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the + * number of hash functions (if 0, the bloom filter will default + * to using 5 hash functions). + */ + __u64 map_extra; }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -5638,6 +5646,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u64 map_extra; } __attribute__((aligned(8))); struct bpf_btf_info { -- cgit v1.2.3 From d6aef08a872b9e23eecc92d0e92393473b13c497 Mon Sep 17 00:00:00 2001 From: Kumar Kartikeya Dwivedi Date: Thu, 28 Oct 2021 12:04:54 +0530 Subject: bpf: Add bpf_kallsyms_lookup_name helper This helper allows us to get the address of a kernel symbol from inside a BPF_PROG_TYPE_SYSCALL prog (used by gen_loader), so that we can relocate typeless ksym vars. Signed-off-by: Kumar Kartikeya Dwivedi Signed-off-by: Alexei Starovoitov Acked-by: Song Liu Link: https://lore.kernel.org/bpf/20211028063501.2239335-2-memxor@gmail.com --- include/linux/bpf.h | 1 + include/uapi/linux/bpf.h | 16 ++++++++++++++++ kernel/bpf/syscall.c | 27 +++++++++++++++++++++++++++ tools/include/uapi/linux/bpf.h | 16 ++++++++++++++++ 4 files changed, 60 insertions(+) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 50105e0b8fcc..6deebf8bf78f 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2110,6 +2110,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto; extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto; extern const struct bpf_func_proto bpf_sk_setsockopt_proto; extern const struct bpf_func_proto bpf_sk_getsockopt_proto; +extern const struct bpf_func_proto bpf_kallsyms_lookup_name_proto; const struct bpf_func_proto *tracing_prog_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f7c2c6354add..e12a217ead34 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -4781,6 +4781,31 @@ static const struct bpf_func_proto bpf_sys_close_proto = { .arg1_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res) +{ + if (flags) + return -EINVAL; + + if (name_sz <= 1 || name[name_sz - 1]) + return -EINVAL; + + if (!bpf_dump_raw_ok(current_cred())) + return -EPERM; + + *res = kallsyms_lookup_name(name); + return *res ? 0 : -ENOENT; +} + +const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = { + .func = bpf_kallsyms_lookup_name, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_MEM, + .arg2_type = ARG_CONST_SIZE, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_LONG, +}; + static const struct bpf_func_proto * syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -4791,6 +4816,8 @@ syscall_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_btf_find_by_name_kind_proto; case BPF_FUNC_sys_close: return &bpf_sys_close_proto; + case BPF_FUNC_kallsyms_lookup_name: + return &bpf_kallsyms_lookup_name_proto; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 8bead4aa3ad0..bd0c9f0487f6 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -4923,6 +4923,21 @@ union bpf_attr { * Dynamically cast a *sk* pointer to a *unix_sock* pointer. * Return * *sk* if casting is valid, or **NULL** otherwise. + * + * long bpf_kallsyms_lookup_name(const char *name, int name_sz, int flags, u64 *res) + * Description + * Get the address of a kernel symbol, returned in *res*. *res* is + * set to 0 if the symbol is not found. + * Return + * On success, zero. On error, a negative value. + * + * **-EINVAL** if *flags* is not zero. + * + * **-EINVAL** if string *name* is not the same size as *name_sz*. + * + * **-ENOENT** if symbol is not found. + * + * **-EPERM** if caller does not have permission to obtain kernel address. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -5104,6 +5119,7 @@ union bpf_attr { FN(get_branch_snapshot), \ FN(trace_vprintk), \ FN(skc_to_unix_sock), \ + FN(kallsyms_lookup_name), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper -- cgit v1.2.3 From e77fbf990316d47968a793d8aa920fd62385aec9 Mon Sep 17 00:00:00 2001 From: David Sterba Date: Fri, 22 Oct 2021 16:53:36 +0200 Subject: btrfs: send: prepare for v2 protocol This is preparatory work for send protocol update to version 2 and higher. We have many pending protocol update requests but still don't have the basic protocol rev in place, the first thing that must happen is to do the actual versioning support. The protocol version is u32 and is a new member in the send ioctl struct. Validity of the version field is backed by a new flag bit. Old kernels would fail when a higher version is requested. Version protocol 0 will pick the highest supported version, BTRFS_SEND_STREAM_VERSION, that's also exported in sysfs. The version is still unchanged and will be increased once we have new incompatible commands or stream updates. Reviewed-by: Nikolay Borisov Signed-off-by: David Sterba --- fs/btrfs/ioctl.c | 3 ++- fs/btrfs/send.c | 23 +++++++++++++++++++++++ fs/btrfs/send.h | 7 +++++++ include/uapi/linux/btrfs.h | 11 +++++++++-- 4 files changed, 41 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index c474f7e24163..92424a22d8d6 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -82,7 +82,8 @@ struct btrfs_ioctl_send_args_32 { compat_uptr_t clone_sources; /* in */ __u64 parent_root; /* in */ __u64 flags; /* in */ - __u64 reserved[4]; /* in */ + __u32 version; /* in */ + __u8 reserved[28]; /* in */ } __attribute__ ((__packed__)); #define BTRFS_IOC_SEND_32 _IOW(BTRFS_IOCTL_MAGIC, 38, \ diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c index afdcbe7844e0..040324d71118 100644 --- a/fs/btrfs/send.c +++ b/fs/btrfs/send.c @@ -84,6 +84,8 @@ struct send_ctx { u64 total_send_size; u64 cmd_send_size[BTRFS_SEND_C_MAX + 1]; u64 flags; /* 'flags' member of btrfs_ioctl_send_args is u64 */ + /* Protocol version compatibility requested */ + u32 proto; struct btrfs_root *send_root; struct btrfs_root *parent_root; @@ -312,6 +314,16 @@ static void inconsistent_snapshot_error(struct send_ctx *sctx, sctx->parent_root->root_key.objectid : 0)); } +__maybe_unused +static bool proto_cmd_ok(const struct send_ctx *sctx, int cmd) +{ + switch (sctx->proto) { + case 1: return cmd < __BTRFS_SEND_C_MAX_V1; + case 2: return cmd < __BTRFS_SEND_C_MAX_V2; + default: return false; + } +} + static int is_waiting_for_move(struct send_ctx *sctx, u64 ino); static struct waiting_dir_move * @@ -7269,6 +7281,17 @@ long btrfs_ioctl_send(struct file *mnt_file, struct btrfs_ioctl_send_args *arg) sctx->flags = arg->flags; + if (arg->flags & BTRFS_SEND_FLAG_VERSION) { + if (arg->version > BTRFS_SEND_STREAM_VERSION) { + ret = -EPROTO; + goto out; + } + /* Zero means "use the highest version" */ + sctx->proto = arg->version ?: BTRFS_SEND_STREAM_VERSION; + } else { + sctx->proto = 1; + } + sctx->send_filp = fget(arg->send_fd); if (!sctx->send_filp) { ret = -EBADF; diff --git a/fs/btrfs/send.h b/fs/btrfs/send.h index de91488b7cd0..23bcefc84e49 100644 --- a/fs/btrfs/send.h +++ b/fs/btrfs/send.h @@ -48,6 +48,7 @@ struct btrfs_tlv_header { enum btrfs_send_cmd { BTRFS_SEND_C_UNSPEC, + /* Version 1 */ BTRFS_SEND_C_SUBVOL, BTRFS_SEND_C_SNAPSHOT, @@ -76,6 +77,12 @@ enum btrfs_send_cmd { BTRFS_SEND_C_END, BTRFS_SEND_C_UPDATE_EXTENT, + __BTRFS_SEND_C_MAX_V1, + + /* Version 2 */ + __BTRFS_SEND_C_MAX_V2, + + /* End */ __BTRFS_SEND_C_MAX, }; #define BTRFS_SEND_C_MAX (__BTRFS_SEND_C_MAX - 1) diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h index d7d3cfead056..738619994e26 100644 --- a/include/uapi/linux/btrfs.h +++ b/include/uapi/linux/btrfs.h @@ -771,10 +771,16 @@ struct btrfs_ioctl_received_subvol_args { */ #define BTRFS_SEND_FLAG_OMIT_END_CMD 0x4 +/* + * Read the protocol version in the structure + */ +#define BTRFS_SEND_FLAG_VERSION 0x8 + #define BTRFS_SEND_FLAG_MASK \ (BTRFS_SEND_FLAG_NO_FILE_DATA | \ BTRFS_SEND_FLAG_OMIT_STREAM_HEADER | \ - BTRFS_SEND_FLAG_OMIT_END_CMD) + BTRFS_SEND_FLAG_OMIT_END_CMD | \ + BTRFS_SEND_FLAG_VERSION) struct btrfs_ioctl_send_args { __s64 send_fd; /* in */ @@ -782,7 +788,8 @@ struct btrfs_ioctl_send_args { __u64 __user *clone_sources; /* in */ __u64 parent_root; /* in */ __u64 flags; /* in */ - __u64 reserved[4]; /* in */ + __u32 version; /* in */ + __u8 reserved[28]; /* in */ }; /* -- cgit v1.2.3 From cf2197ca4b8c199d188593ca6800ea1827c42171 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Fri, 29 Oct 2021 14:09:29 +0800 Subject: bcache: move uapi header bcache.h to bcache code directory The header file include/uapi/linux/bcache.h is not really a user space API heaer. This file defines the ondisk format of bcache internal meta data but no one includes it from user space, bcache-tools has its own copy of this header with minor modification. Therefore, this patch moves include/uapi/linux/bcache.h to bcache code directory as drivers/md/bcache/bcache_ondisk.h. Suggested-by: Arnd Bergmann Suggested-by: Christoph Hellwig Signed-off-by: Coly Li Link: https://lore.kernel.org/r/20211029060930.119923-2-colyli@suse.de Signed-off-by: Jens Axboe --- drivers/md/bcache/bcache.h | 2 +- drivers/md/bcache/bcache_ondisk.h | 445 ++++++++++++++++++++++++++++++++++++++ drivers/md/bcache/bset.h | 2 +- drivers/md/bcache/features.c | 2 +- drivers/md/bcache/features.h | 3 +- include/uapi/linux/bcache.h | 445 -------------------------------------- 6 files changed, 450 insertions(+), 449 deletions(-) create mode 100644 drivers/md/bcache/bcache_ondisk.h delete mode 100644 include/uapi/linux/bcache.h (limited to 'include/uapi/linux') diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 941685409c68..9ed9c955add7 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -178,7 +178,6 @@ #define pr_fmt(fmt) "bcache: %s() " fmt, __func__ -#include #include #include #include @@ -190,6 +189,7 @@ #include #include +#include "bcache_ondisk.h" #include "bset.h" #include "util.h" #include "closure.h" diff --git a/drivers/md/bcache/bcache_ondisk.h b/drivers/md/bcache/bcache_ondisk.h new file mode 100644 index 000000000000..97413586195b --- /dev/null +++ b/drivers/md/bcache/bcache_ondisk.h @@ -0,0 +1,445 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef _LINUX_BCACHE_H +#define _LINUX_BCACHE_H + +/* + * Bcache on disk data structures + */ + +#include + +#define BITMASK(name, type, field, offset, size) \ +static inline __u64 name(const type *k) \ +{ return (k->field >> offset) & ~(~0ULL << size); } \ + \ +static inline void SET_##name(type *k, __u64 v) \ +{ \ + k->field &= ~(~(~0ULL << size) << offset); \ + k->field |= (v & ~(~0ULL << size)) << offset; \ +} + +/* Btree keys - all units are in sectors */ + +struct bkey { + __u64 high; + __u64 low; + __u64 ptr[]; +}; + +#define KEY_FIELD(name, field, offset, size) \ + BITMASK(name, struct bkey, field, offset, size) + +#define PTR_FIELD(name, offset, size) \ +static inline __u64 name(const struct bkey *k, unsigned int i) \ +{ return (k->ptr[i] >> offset) & ~(~0ULL << size); } \ + \ +static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ +{ \ + k->ptr[i] &= ~(~(~0ULL << size) << offset); \ + k->ptr[i] |= (v & ~(~0ULL << size)) << offset; \ +} + +#define KEY_SIZE_BITS 16 +#define KEY_MAX_U64S 8 + +KEY_FIELD(KEY_PTRS, high, 60, 3) +KEY_FIELD(__PAD0, high, 58, 2) +KEY_FIELD(KEY_CSUM, high, 56, 2) +KEY_FIELD(__PAD1, high, 55, 1) +KEY_FIELD(KEY_DIRTY, high, 36, 1) + +KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) +KEY_FIELD(KEY_INODE, high, 0, 20) + +/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */ + +static inline __u64 KEY_OFFSET(const struct bkey *k) +{ + return k->low; +} + +static inline void SET_KEY_OFFSET(struct bkey *k, __u64 v) +{ + k->low = v; +} + +/* + * The high bit being set is a relic from when we used it to do binary + * searches - it told you where a key started. It's not used anymore, + * and can probably be safely dropped. + */ +#define KEY(inode, offset, size) \ +((struct bkey) { \ + .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \ + .low = (offset) \ +}) + +#define ZERO_KEY KEY(0, 0, 0) + +#define MAX_KEY_INODE (~(~0 << 20)) +#define MAX_KEY_OFFSET (~0ULL >> 1) +#define MAX_KEY KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0) + +#define KEY_START(k) (KEY_OFFSET(k) - KEY_SIZE(k)) +#define START_KEY(k) KEY(KEY_INODE(k), KEY_START(k), 0) + +#define PTR_DEV_BITS 12 + +PTR_FIELD(PTR_DEV, 51, PTR_DEV_BITS) +PTR_FIELD(PTR_OFFSET, 8, 43) +PTR_FIELD(PTR_GEN, 0, 8) + +#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1) + +#define MAKE_PTR(gen, offset, dev) \ + ((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen) + +/* Bkey utility code */ + +static inline unsigned long bkey_u64s(const struct bkey *k) +{ + return (sizeof(struct bkey) / sizeof(__u64)) + KEY_PTRS(k); +} + +static inline unsigned long bkey_bytes(const struct bkey *k) +{ + return bkey_u64s(k) * sizeof(__u64); +} + +#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src)) + +static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) +{ + SET_KEY_INODE(dest, KEY_INODE(src)); + SET_KEY_OFFSET(dest, KEY_OFFSET(src)); +} + +static inline struct bkey *bkey_next(const struct bkey *k) +{ + __u64 *d = (void *) k; + + return (struct bkey *) (d + bkey_u64s(k)); +} + +static inline struct bkey *bkey_idx(const struct bkey *k, unsigned int nr_keys) +{ + __u64 *d = (void *) k; + + return (struct bkey *) (d + nr_keys); +} +/* Enough for a key with 6 pointers */ +#define BKEY_PAD 8 + +#define BKEY_PADDED(key) \ + union { struct bkey key; __u64 key ## _pad[BKEY_PAD]; } + +/* Superblock */ + +/* Version 0: Cache device + * Version 1: Backing device + * Version 2: Seed pointer into btree node checksum + * Version 3: Cache device with new UUID format + * Version 4: Backing device with data offset + */ +#define BCACHE_SB_VERSION_CDEV 0 +#define BCACHE_SB_VERSION_BDEV 1 +#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 +#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 +#define BCACHE_SB_VERSION_CDEV_WITH_FEATURES 5 +#define BCACHE_SB_VERSION_BDEV_WITH_FEATURES 6 +#define BCACHE_SB_MAX_VERSION 6 + +#define SB_SECTOR 8 +#define SB_OFFSET (SB_SECTOR << SECTOR_SHIFT) +#define SB_SIZE 4096 +#define SB_LABEL_SIZE 32 +#define SB_JOURNAL_BUCKETS 256U +/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */ +#define MAX_CACHES_PER_SET 8 + +#define BDEV_DATA_START_DEFAULT 16 /* sectors */ + +struct cache_sb_disk { + __le64 csum; + __le64 offset; /* sector where this sb was written */ + __le64 version; + + __u8 magic[16]; + + __u8 uuid[16]; + union { + __u8 set_uuid[16]; + __le64 set_magic; + }; + __u8 label[SB_LABEL_SIZE]; + + __le64 flags; + __le64 seq; + + __le64 feature_compat; + __le64 feature_incompat; + __le64 feature_ro_compat; + + __le64 pad[5]; + + union { + struct { + /* Cache devices */ + __le64 nbuckets; /* device size */ + + __le16 block_size; /* sectors */ + __le16 bucket_size; /* sectors */ + + __le16 nr_in_set; + __le16 nr_this_dev; + }; + struct { + /* Backing devices */ + __le64 data_offset; + + /* + * block_size from the cache device section is still used by + * backing devices, so don't add anything here until we fix + * things to not need it for backing devices anymore + */ + }; + }; + + __le32 last_mount; /* time overflow in y2106 */ + + __le16 first_bucket; + union { + __le16 njournal_buckets; + __le16 keys; + }; + __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ + __le16 obso_bucket_size_hi; /* obsoleted */ +}; + +/* + * This is for in-memory bcache super block. + * NOTE: cache_sb is NOT exactly mapping to cache_sb_disk, the member + * size, ordering and even whole struct size may be different + * from cache_sb_disk. + */ +struct cache_sb { + __u64 offset; /* sector where this sb was written */ + __u64 version; + + __u8 magic[16]; + + __u8 uuid[16]; + union { + __u8 set_uuid[16]; + __u64 set_magic; + }; + __u8 label[SB_LABEL_SIZE]; + + __u64 flags; + __u64 seq; + + __u64 feature_compat; + __u64 feature_incompat; + __u64 feature_ro_compat; + + union { + struct { + /* Cache devices */ + __u64 nbuckets; /* device size */ + + __u16 block_size; /* sectors */ + __u16 nr_in_set; + __u16 nr_this_dev; + __u32 bucket_size; /* sectors */ + }; + struct { + /* Backing devices */ + __u64 data_offset; + + /* + * block_size from the cache device section is still used by + * backing devices, so don't add anything here until we fix + * things to not need it for backing devices anymore + */ + }; + }; + + __u32 last_mount; /* time overflow in y2106 */ + + __u16 first_bucket; + union { + __u16 njournal_buckets; + __u16 keys; + }; + __u64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ +}; + +static inline _Bool SB_IS_BDEV(const struct cache_sb *sb) +{ + return sb->version == BCACHE_SB_VERSION_BDEV + || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET + || sb->version == BCACHE_SB_VERSION_BDEV_WITH_FEATURES; +} + +BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1); +BITMASK(CACHE_DISCARD, struct cache_sb, flags, 1, 1); +BITMASK(CACHE_REPLACEMENT, struct cache_sb, flags, 2, 3); +#define CACHE_REPLACEMENT_LRU 0U +#define CACHE_REPLACEMENT_FIFO 1U +#define CACHE_REPLACEMENT_RANDOM 2U + +BITMASK(BDEV_CACHE_MODE, struct cache_sb, flags, 0, 4); +#define CACHE_MODE_WRITETHROUGH 0U +#define CACHE_MODE_WRITEBACK 1U +#define CACHE_MODE_WRITEAROUND 2U +#define CACHE_MODE_NONE 3U +BITMASK(BDEV_STATE, struct cache_sb, flags, 61, 2); +#define BDEV_STATE_NONE 0U +#define BDEV_STATE_CLEAN 1U +#define BDEV_STATE_DIRTY 2U +#define BDEV_STATE_STALE 3U + +/* + * Magic numbers + * + * The various other data structures have their own magic numbers, which are + * xored with the first part of the cache set's UUID + */ + +#define JSET_MAGIC 0x245235c1a3625032ULL +#define PSET_MAGIC 0x6750e15f87337f91ULL +#define BSET_MAGIC 0x90135c78b99e07f5ULL + +static inline __u64 jset_magic(struct cache_sb *sb) +{ + return sb->set_magic ^ JSET_MAGIC; +} + +static inline __u64 pset_magic(struct cache_sb *sb) +{ + return sb->set_magic ^ PSET_MAGIC; +} + +static inline __u64 bset_magic(struct cache_sb *sb) +{ + return sb->set_magic ^ BSET_MAGIC; +} + +/* + * Journal + * + * On disk format for a journal entry: + * seq is monotonically increasing; every journal entry has its own unique + * sequence number. + * + * last_seq is the oldest journal entry that still has keys the btree hasn't + * flushed to disk yet. + * + * version is for on disk format changes. + */ + +#define BCACHE_JSET_VERSION_UUIDv1 1 +#define BCACHE_JSET_VERSION_UUID 1 /* Always latest UUID format */ +#define BCACHE_JSET_VERSION 1 + +struct jset { + __u64 csum; + __u64 magic; + __u64 seq; + __u32 version; + __u32 keys; + + __u64 last_seq; + + BKEY_PADDED(uuid_bucket); + BKEY_PADDED(btree_root); + __u16 btree_level; + __u16 pad[3]; + + __u64 prio_bucket[MAX_CACHES_PER_SET]; + + union { + struct bkey start[0]; + __u64 d[0]; + }; +}; + +/* Bucket prios/gens */ + +struct prio_set { + __u64 csum; + __u64 magic; + __u64 seq; + __u32 version; + __u32 pad; + + __u64 next_bucket; + + struct bucket_disk { + __u16 prio; + __u8 gen; + } __attribute((packed)) data[]; +}; + +/* UUIDS - per backing device/flash only volume metadata */ + +struct uuid_entry { + union { + struct { + __u8 uuid[16]; + __u8 label[32]; + __u32 first_reg; /* time overflow in y2106 */ + __u32 last_reg; + __u32 invalidated; + + __u32 flags; + /* Size of flash only volumes */ + __u64 sectors; + }; + + __u8 pad[128]; + }; +}; + +BITMASK(UUID_FLASH_ONLY, struct uuid_entry, flags, 0, 1); + +/* Btree nodes */ + +/* Version 1: Seed pointer into btree node checksum + */ +#define BCACHE_BSET_CSUM 1 +#define BCACHE_BSET_VERSION 1 + +/* + * Btree nodes + * + * On disk a btree node is a list/log of these; within each set the keys are + * sorted + */ +struct bset { + __u64 csum; + __u64 magic; + __u64 seq; + __u32 version; + __u32 keys; + + union { + struct bkey start[0]; + __u64 d[0]; + }; +}; + +/* OBSOLETE */ + +/* UUIDS - per backing device/flash only volume metadata */ + +struct uuid_entry_v0 { + __u8 uuid[16]; + __u8 label[32]; + __u32 first_reg; + __u32 last_reg; + __u32 invalidated; + __u32 pad; +}; + +#endif /* _LINUX_BCACHE_H */ diff --git a/drivers/md/bcache/bset.h b/drivers/md/bcache/bset.h index a50dcfda656f..d795c84246b0 100644 --- a/drivers/md/bcache/bset.h +++ b/drivers/md/bcache/bset.h @@ -2,10 +2,10 @@ #ifndef _BCACHE_BSET_H #define _BCACHE_BSET_H -#include #include #include +#include "bcache_ondisk.h" #include "util.h" /* for time_stats */ /* diff --git a/drivers/md/bcache/features.c b/drivers/md/bcache/features.c index 6d2b7b84a7b7..634922c5601d 100644 --- a/drivers/md/bcache/features.c +++ b/drivers/md/bcache/features.c @@ -6,7 +6,7 @@ * Copyright 2020 Coly Li * */ -#include +#include "bcache_ondisk.h" #include "bcache.h" #include "features.h" diff --git a/drivers/md/bcache/features.h b/drivers/md/bcache/features.h index d1c8fd3977fc..09161b89c63e 100644 --- a/drivers/md/bcache/features.h +++ b/drivers/md/bcache/features.h @@ -2,10 +2,11 @@ #ifndef _BCACHE_FEATURES_H #define _BCACHE_FEATURES_H -#include #include #include +#include "bcache_ondisk.h" + #define BCH_FEATURE_COMPAT 0 #define BCH_FEATURE_RO_COMPAT 1 #define BCH_FEATURE_INCOMPAT 2 diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h deleted file mode 100644 index 97413586195b..000000000000 --- a/include/uapi/linux/bcache.h +++ /dev/null @@ -1,445 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ -#ifndef _LINUX_BCACHE_H -#define _LINUX_BCACHE_H - -/* - * Bcache on disk data structures - */ - -#include - -#define BITMASK(name, type, field, offset, size) \ -static inline __u64 name(const type *k) \ -{ return (k->field >> offset) & ~(~0ULL << size); } \ - \ -static inline void SET_##name(type *k, __u64 v) \ -{ \ - k->field &= ~(~(~0ULL << size) << offset); \ - k->field |= (v & ~(~0ULL << size)) << offset; \ -} - -/* Btree keys - all units are in sectors */ - -struct bkey { - __u64 high; - __u64 low; - __u64 ptr[]; -}; - -#define KEY_FIELD(name, field, offset, size) \ - BITMASK(name, struct bkey, field, offset, size) - -#define PTR_FIELD(name, offset, size) \ -static inline __u64 name(const struct bkey *k, unsigned int i) \ -{ return (k->ptr[i] >> offset) & ~(~0ULL << size); } \ - \ -static inline void SET_##name(struct bkey *k, unsigned int i, __u64 v) \ -{ \ - k->ptr[i] &= ~(~(~0ULL << size) << offset); \ - k->ptr[i] |= (v & ~(~0ULL << size)) << offset; \ -} - -#define KEY_SIZE_BITS 16 -#define KEY_MAX_U64S 8 - -KEY_FIELD(KEY_PTRS, high, 60, 3) -KEY_FIELD(__PAD0, high, 58, 2) -KEY_FIELD(KEY_CSUM, high, 56, 2) -KEY_FIELD(__PAD1, high, 55, 1) -KEY_FIELD(KEY_DIRTY, high, 36, 1) - -KEY_FIELD(KEY_SIZE, high, 20, KEY_SIZE_BITS) -KEY_FIELD(KEY_INODE, high, 0, 20) - -/* Next time I change the on disk format, KEY_OFFSET() won't be 64 bits */ - -static inline __u64 KEY_OFFSET(const struct bkey *k) -{ - return k->low; -} - -static inline void SET_KEY_OFFSET(struct bkey *k, __u64 v) -{ - k->low = v; -} - -/* - * The high bit being set is a relic from when we used it to do binary - * searches - it told you where a key started. It's not used anymore, - * and can probably be safely dropped. - */ -#define KEY(inode, offset, size) \ -((struct bkey) { \ - .high = (1ULL << 63) | ((__u64) (size) << 20) | (inode), \ - .low = (offset) \ -}) - -#define ZERO_KEY KEY(0, 0, 0) - -#define MAX_KEY_INODE (~(~0 << 20)) -#define MAX_KEY_OFFSET (~0ULL >> 1) -#define MAX_KEY KEY(MAX_KEY_INODE, MAX_KEY_OFFSET, 0) - -#define KEY_START(k) (KEY_OFFSET(k) - KEY_SIZE(k)) -#define START_KEY(k) KEY(KEY_INODE(k), KEY_START(k), 0) - -#define PTR_DEV_BITS 12 - -PTR_FIELD(PTR_DEV, 51, PTR_DEV_BITS) -PTR_FIELD(PTR_OFFSET, 8, 43) -PTR_FIELD(PTR_GEN, 0, 8) - -#define PTR_CHECK_DEV ((1 << PTR_DEV_BITS) - 1) - -#define MAKE_PTR(gen, offset, dev) \ - ((((__u64) dev) << 51) | ((__u64) offset) << 8 | gen) - -/* Bkey utility code */ - -static inline unsigned long bkey_u64s(const struct bkey *k) -{ - return (sizeof(struct bkey) / sizeof(__u64)) + KEY_PTRS(k); -} - -static inline unsigned long bkey_bytes(const struct bkey *k) -{ - return bkey_u64s(k) * sizeof(__u64); -} - -#define bkey_copy(_dest, _src) memcpy(_dest, _src, bkey_bytes(_src)) - -static inline void bkey_copy_key(struct bkey *dest, const struct bkey *src) -{ - SET_KEY_INODE(dest, KEY_INODE(src)); - SET_KEY_OFFSET(dest, KEY_OFFSET(src)); -} - -static inline struct bkey *bkey_next(const struct bkey *k) -{ - __u64 *d = (void *) k; - - return (struct bkey *) (d + bkey_u64s(k)); -} - -static inline struct bkey *bkey_idx(const struct bkey *k, unsigned int nr_keys) -{ - __u64 *d = (void *) k; - - return (struct bkey *) (d + nr_keys); -} -/* Enough for a key with 6 pointers */ -#define BKEY_PAD 8 - -#define BKEY_PADDED(key) \ - union { struct bkey key; __u64 key ## _pad[BKEY_PAD]; } - -/* Superblock */ - -/* Version 0: Cache device - * Version 1: Backing device - * Version 2: Seed pointer into btree node checksum - * Version 3: Cache device with new UUID format - * Version 4: Backing device with data offset - */ -#define BCACHE_SB_VERSION_CDEV 0 -#define BCACHE_SB_VERSION_BDEV 1 -#define BCACHE_SB_VERSION_CDEV_WITH_UUID 3 -#define BCACHE_SB_VERSION_BDEV_WITH_OFFSET 4 -#define BCACHE_SB_VERSION_CDEV_WITH_FEATURES 5 -#define BCACHE_SB_VERSION_BDEV_WITH_FEATURES 6 -#define BCACHE_SB_MAX_VERSION 6 - -#define SB_SECTOR 8 -#define SB_OFFSET (SB_SECTOR << SECTOR_SHIFT) -#define SB_SIZE 4096 -#define SB_LABEL_SIZE 32 -#define SB_JOURNAL_BUCKETS 256U -/* SB_JOURNAL_BUCKETS must be divisible by BITS_PER_LONG */ -#define MAX_CACHES_PER_SET 8 - -#define BDEV_DATA_START_DEFAULT 16 /* sectors */ - -struct cache_sb_disk { - __le64 csum; - __le64 offset; /* sector where this sb was written */ - __le64 version; - - __u8 magic[16]; - - __u8 uuid[16]; - union { - __u8 set_uuid[16]; - __le64 set_magic; - }; - __u8 label[SB_LABEL_SIZE]; - - __le64 flags; - __le64 seq; - - __le64 feature_compat; - __le64 feature_incompat; - __le64 feature_ro_compat; - - __le64 pad[5]; - - union { - struct { - /* Cache devices */ - __le64 nbuckets; /* device size */ - - __le16 block_size; /* sectors */ - __le16 bucket_size; /* sectors */ - - __le16 nr_in_set; - __le16 nr_this_dev; - }; - struct { - /* Backing devices */ - __le64 data_offset; - - /* - * block_size from the cache device section is still used by - * backing devices, so don't add anything here until we fix - * things to not need it for backing devices anymore - */ - }; - }; - - __le32 last_mount; /* time overflow in y2106 */ - - __le16 first_bucket; - union { - __le16 njournal_buckets; - __le16 keys; - }; - __le64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ - __le16 obso_bucket_size_hi; /* obsoleted */ -}; - -/* - * This is for in-memory bcache super block. - * NOTE: cache_sb is NOT exactly mapping to cache_sb_disk, the member - * size, ordering and even whole struct size may be different - * from cache_sb_disk. - */ -struct cache_sb { - __u64 offset; /* sector where this sb was written */ - __u64 version; - - __u8 magic[16]; - - __u8 uuid[16]; - union { - __u8 set_uuid[16]; - __u64 set_magic; - }; - __u8 label[SB_LABEL_SIZE]; - - __u64 flags; - __u64 seq; - - __u64 feature_compat; - __u64 feature_incompat; - __u64 feature_ro_compat; - - union { - struct { - /* Cache devices */ - __u64 nbuckets; /* device size */ - - __u16 block_size; /* sectors */ - __u16 nr_in_set; - __u16 nr_this_dev; - __u32 bucket_size; /* sectors */ - }; - struct { - /* Backing devices */ - __u64 data_offset; - - /* - * block_size from the cache device section is still used by - * backing devices, so don't add anything here until we fix - * things to not need it for backing devices anymore - */ - }; - }; - - __u32 last_mount; /* time overflow in y2106 */ - - __u16 first_bucket; - union { - __u16 njournal_buckets; - __u16 keys; - }; - __u64 d[SB_JOURNAL_BUCKETS]; /* journal buckets */ -}; - -static inline _Bool SB_IS_BDEV(const struct cache_sb *sb) -{ - return sb->version == BCACHE_SB_VERSION_BDEV - || sb->version == BCACHE_SB_VERSION_BDEV_WITH_OFFSET - || sb->version == BCACHE_SB_VERSION_BDEV_WITH_FEATURES; -} - -BITMASK(CACHE_SYNC, struct cache_sb, flags, 0, 1); -BITMASK(CACHE_DISCARD, struct cache_sb, flags, 1, 1); -BITMASK(CACHE_REPLACEMENT, struct cache_sb, flags, 2, 3); -#define CACHE_REPLACEMENT_LRU 0U -#define CACHE_REPLACEMENT_FIFO 1U -#define CACHE_REPLACEMENT_RANDOM 2U - -BITMASK(BDEV_CACHE_MODE, struct cache_sb, flags, 0, 4); -#define CACHE_MODE_WRITETHROUGH 0U -#define CACHE_MODE_WRITEBACK 1U -#define CACHE_MODE_WRITEAROUND 2U -#define CACHE_MODE_NONE 3U -BITMASK(BDEV_STATE, struct cache_sb, flags, 61, 2); -#define BDEV_STATE_NONE 0U -#define BDEV_STATE_CLEAN 1U -#define BDEV_STATE_DIRTY 2U -#define BDEV_STATE_STALE 3U - -/* - * Magic numbers - * - * The various other data structures have their own magic numbers, which are - * xored with the first part of the cache set's UUID - */ - -#define JSET_MAGIC 0x245235c1a3625032ULL -#define PSET_MAGIC 0x6750e15f87337f91ULL -#define BSET_MAGIC 0x90135c78b99e07f5ULL - -static inline __u64 jset_magic(struct cache_sb *sb) -{ - return sb->set_magic ^ JSET_MAGIC; -} - -static inline __u64 pset_magic(struct cache_sb *sb) -{ - return sb->set_magic ^ PSET_MAGIC; -} - -static inline __u64 bset_magic(struct cache_sb *sb) -{ - return sb->set_magic ^ BSET_MAGIC; -} - -/* - * Journal - * - * On disk format for a journal entry: - * seq is monotonically increasing; every journal entry has its own unique - * sequence number. - * - * last_seq is the oldest journal entry that still has keys the btree hasn't - * flushed to disk yet. - * - * version is for on disk format changes. - */ - -#define BCACHE_JSET_VERSION_UUIDv1 1 -#define BCACHE_JSET_VERSION_UUID 1 /* Always latest UUID format */ -#define BCACHE_JSET_VERSION 1 - -struct jset { - __u64 csum; - __u64 magic; - __u64 seq; - __u32 version; - __u32 keys; - - __u64 last_seq; - - BKEY_PADDED(uuid_bucket); - BKEY_PADDED(btree_root); - __u16 btree_level; - __u16 pad[3]; - - __u64 prio_bucket[MAX_CACHES_PER_SET]; - - union { - struct bkey start[0]; - __u64 d[0]; - }; -}; - -/* Bucket prios/gens */ - -struct prio_set { - __u64 csum; - __u64 magic; - __u64 seq; - __u32 version; - __u32 pad; - - __u64 next_bucket; - - struct bucket_disk { - __u16 prio; - __u8 gen; - } __attribute((packed)) data[]; -}; - -/* UUIDS - per backing device/flash only volume metadata */ - -struct uuid_entry { - union { - struct { - __u8 uuid[16]; - __u8 label[32]; - __u32 first_reg; /* time overflow in y2106 */ - __u32 last_reg; - __u32 invalidated; - - __u32 flags; - /* Size of flash only volumes */ - __u64 sectors; - }; - - __u8 pad[128]; - }; -}; - -BITMASK(UUID_FLASH_ONLY, struct uuid_entry, flags, 0, 1); - -/* Btree nodes */ - -/* Version 1: Seed pointer into btree node checksum - */ -#define BCACHE_BSET_CSUM 1 -#define BCACHE_BSET_VERSION 1 - -/* - * Btree nodes - * - * On disk a btree node is a list/log of these; within each set the keys are - * sorted - */ -struct bset { - __u64 csum; - __u64 magic; - __u64 seq; - __u32 version; - __u32 keys; - - union { - struct bkey start[0]; - __u64 d[0]; - }; -}; - -/* OBSOLETE */ - -/* UUIDS - per backing device/flash only volume metadata */ - -struct uuid_entry_v0 { - __u8 uuid[16]; - __u8 label[32]; - __u32 first_reg; - __u32 last_reg; - __u32 invalidated; - __u32 pad; -}; - -#endif /* _LINUX_BCACHE_H */ -- cgit v1.2.3 From 56fa95014a0447f798444e626091cbeb3176af24 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 25 Oct 2021 15:43:29 +0200 Subject: netfilter: nft_meta: add NFT_META_IFTYPE Generalize NFT_META_IIFTYPE to NFT_META_IFTYPE which allows you to match on the interface type of the skb->dev field. This field is used by the netdev family to add an implicit dependency to skip non-ethernet packets when matching on layer 3 and 4 TCP/IP header fields. For backward compatibility, add the NFT_META_IIFTYPE alias to NFT_META_IFTYPE. Add __NFT_META_IIFTYPE, to be used by userspace in the future to match specifically on the iiftype. Signed-off-by: Pablo Neira Ayuso --- include/uapi/linux/netfilter/nf_tables.h | 4 +++- net/netfilter/nft_meta.c | 6 +++++- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index e94d1fa554cb..08db4ee06ab6 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -896,7 +896,8 @@ enum nft_meta_keys { NFT_META_OIF, NFT_META_IIFNAME, NFT_META_OIFNAME, - NFT_META_IIFTYPE, + NFT_META_IFTYPE, +#define NFT_META_IIFTYPE NFT_META_IFTYPE NFT_META_OIFTYPE, NFT_META_SKUID, NFT_META_SKGID, @@ -923,6 +924,7 @@ enum nft_meta_keys { NFT_META_TIME_HOUR, NFT_META_SDIF, NFT_META_SDIFNAME, + __NFT_META_IIFTYPE, }; /** diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index a7e01e9952f1..516e74635bae 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -244,7 +244,11 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest, case NFT_META_OIF: nft_meta_store_ifindex(dest, nft_out(pkt)); break; - case NFT_META_IIFTYPE: + case NFT_META_IFTYPE: + if (!nft_meta_store_iftype(dest, pkt->skb->dev)) + return false; + break; + case __NFT_META_IIFTYPE: if (!nft_meta_store_iftype(dest, nft_in(pkt))) return false; break; -- cgit v1.2.3 From e47be840e87ea15677bca2043ee7b696ccacf56a Mon Sep 17 00:00:00 2001 From: Wu Zongyong Date: Fri, 29 Oct 2021 17:14:48 +0800 Subject: vdpa: add new attribute VDPA_ATTR_DEV_MIN_VQ_SIZE This attribute advertises the min value of virtqueue size. The value is 1 by default. Signed-off-by: Wu Zongyong Link: https://lore.kernel.org/r/2bbc417355c4d22298050b1ba887cecfbde3e85d.1635493219.git.wuzongyong@linux.alibaba.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 5 +++++ include/uapi/linux/vdpa.h | 1 + 2 files changed, 6 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index d783a943647d..fcf02a364878 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -500,6 +500,7 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq int flags, struct netlink_ext_ack *extack) { u16 max_vq_size; + u16 min_vq_size = 1; u32 device_id; u32 vendor_id; void *hdr; @@ -516,6 +517,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq device_id = vdev->config->get_device_id(vdev); vendor_id = vdev->config->get_vendor_id(vdev); max_vq_size = vdev->config->get_vq_num_max(vdev); + if (vdev->config->get_vq_num_min) + min_vq_size = vdev->config->get_vq_num_min(vdev); err = -EMSGSIZE; if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) @@ -528,6 +531,8 @@ vdpa_dev_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq goto msg_err; if (nla_put_u16(msg, VDPA_ATTR_DEV_MAX_VQ_SIZE, max_vq_size)) goto msg_err; + if (nla_put_u16(msg, VDPA_ATTR_DEV_MIN_VQ_SIZE, min_vq_size)) + goto msg_err; genlmsg_end(msg, hdr); return 0; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index 66a41e4ec163..e3b87879514c 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -32,6 +32,7 @@ enum vdpa_attr { VDPA_ATTR_DEV_VENDOR_ID, /* u32 */ VDPA_ATTR_DEV_MAX_VQS, /* u32 */ VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ + VDPA_ATTR_DEV_MIN_VQ_SIZE, /* u16 */ /* new attributes must be added above here */ VDPA_ATTR_MAX, -- cgit v1.2.3 From c46b38dc8743535e686b911d253a844f0bd50ead Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Thu, 28 Oct 2021 22:15:00 +0200 Subject: netfilter: nft_payload: support for inner header matching / mangling Allow to match and mangle on inner headers / payload data after the transport header. There is a new field in the pktinfo structure that stores the inner header offset which is calculated only when requested. Only TCP and UDP supported at this stage. Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 ++ include/uapi/linux/netfilter/nf_tables.h | 2 ++ net/netfilter/nft_payload.c | 56 ++++++++++++++++++++++++++++++-- 3 files changed, 58 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 7e3188cf4a7d..a0d9e0b47ab8 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -23,6 +23,7 @@ struct module; enum { NFT_PKTINFO_L4PROTO = (1 << 0), + NFT_PKTINFO_INNER = (1 << 1), }; struct nft_pktinfo { @@ -32,6 +33,7 @@ struct nft_pktinfo { u8 tprot; u16 fragoff; unsigned int thoff; + unsigned int inneroff; }; static inline struct sock *nft_sk(const struct nft_pktinfo *pkt) diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 08db4ee06ab6..466fd3f4447c 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -753,11 +753,13 @@ enum nft_dynset_attributes { * @NFT_PAYLOAD_LL_HEADER: link layer header * @NFT_PAYLOAD_NETWORK_HEADER: network header * @NFT_PAYLOAD_TRANSPORT_HEADER: transport header + * @NFT_PAYLOAD_INNER_HEADER: inner header / payload */ enum nft_payload_bases { NFT_PAYLOAD_LL_HEADER, NFT_PAYLOAD_NETWORK_HEADER, NFT_PAYLOAD_TRANSPORT_HEADER, + NFT_PAYLOAD_INNER_HEADER, }; /** diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index d1cd6583ee00..cbfe4e4a4ad7 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -22,6 +22,7 @@ #include #include #include +#include #include static bool nft_payload_rebuild_vlan_hdr(const struct sk_buff *skb, int mac_off, @@ -79,6 +80,45 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; } +static int __nft_payload_inner_offset(struct nft_pktinfo *pkt) +{ + unsigned int thoff = nft_thoff(pkt); + + if (!(pkt->flags & NFT_PKTINFO_L4PROTO)) + return -1; + + switch (pkt->tprot) { + case IPPROTO_UDP: + pkt->inneroff = thoff + sizeof(struct udphdr); + break; + case IPPROTO_TCP: { + struct tcphdr *th, _tcph; + + th = skb_header_pointer(pkt->skb, thoff, sizeof(_tcph), &_tcph); + if (!th) + return -1; + + pkt->inneroff = thoff + __tcp_hdrlen(th); + } + break; + default: + return -1; + } + + pkt->flags |= NFT_PKTINFO_INNER; + + return 0; +} + +static 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) + return -1; + + return pkt->inneroff; +} + void nft_payload_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) @@ -112,6 +152,11 @@ void nft_payload_eval(const struct nft_expr *expr, goto err; offset = nft_thoff(pkt); break; + case NFT_PAYLOAD_INNER_HEADER: + offset = nft_payload_inner_offset(pkt); + if (offset < 0) + goto err; + break; default: BUG(); } @@ -614,6 +659,11 @@ static void nft_payload_set_eval(const struct nft_expr *expr, goto err; offset = nft_thoff(pkt); break; + case NFT_PAYLOAD_INNER_HEADER: + offset = nft_payload_inner_offset(pkt); + if (offset < 0) + goto err; + break; default: BUG(); } @@ -622,7 +672,8 @@ static void nft_payload_set_eval(const struct nft_expr *expr, offset += priv->offset; if ((priv->csum_type == NFT_PAYLOAD_CSUM_INET || priv->csum_flags) && - (priv->base != NFT_PAYLOAD_TRANSPORT_HEADER || + ((priv->base != NFT_PAYLOAD_TRANSPORT_HEADER && + priv->base != NFT_PAYLOAD_INNER_HEADER) || skb->ip_summed != CHECKSUM_PARTIAL)) { fsum = skb_checksum(skb, offset, priv->len, 0); tsum = csum_partial(src, priv->len, 0); @@ -741,6 +792,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, case NFT_PAYLOAD_LL_HEADER: case NFT_PAYLOAD_NETWORK_HEADER: case NFT_PAYLOAD_TRANSPORT_HEADER: + case NFT_PAYLOAD_INNER_HEADER: break; default: return ERR_PTR(-EOPNOTSUPP); @@ -759,7 +811,7 @@ nft_payload_select_ops(const struct nft_ctx *ctx, len = ntohl(nla_get_be32(tb[NFTA_PAYLOAD_LEN])); if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && - base != NFT_PAYLOAD_LL_HEADER) + base != NFT_PAYLOAD_LL_HEADER && base != NFT_PAYLOAD_INNER_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; -- cgit v1.2.3 From dcce162559ee1ce5f64992c4c65197f9270e3d4f Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Oct 2021 15:17:49 +0530 Subject: i2c: virtio: Add support for zero-length requests The virtio specification received a new mandatory feature (VIRTIO_I2C_F_ZERO_LENGTH_REQUEST) for zero length requests. Fail if the feature isn't offered by the device. For each read-request, set the VIRTIO_I2C_FLAGS_M_RD flag, as required by the VIRTIO_I2C_F_ZERO_LENGTH_REQUEST feature. This allows us to support zero length requests, like SMBUS Quick, where the buffer need not be sent anymore. Signed-off-by: Viresh Kumar Link: https://lore.kernel.org/r/7c58868cd26d2fc4bd82d0d8b0dfb55636380110.1634808714.git.viresh.kumar@linaro.org Signed-off-by: Michael S. Tsirkin Acked-by: Jie Deng # once the spec is merged --- drivers/i2c/busses/i2c-virtio.c | 56 ++++++++++++++++++++++------------------- include/uapi/linux/virtio_i2c.h | 6 +++++ 2 files changed, 36 insertions(+), 26 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/i2c/busses/i2c-virtio.c b/drivers/i2c/busses/i2c-virtio.c index f10a603b13fb..1ed4daa918a0 100644 --- a/drivers/i2c/busses/i2c-virtio.c +++ b/drivers/i2c/busses/i2c-virtio.c @@ -62,35 +62,33 @@ static int virtio_i2c_prepare_reqs(struct virtqueue *vq, for (i = 0; i < num; i++) { int outcnt = 0, incnt = 0; - /* - * We don't support 0 length messages and so filter out - * 0 length transfers by using i2c_adapter_quirks. - */ - if (!msgs[i].len) - break; - /* * Only 7-bit mode supported for this moment. For the address * format, Please check the Virtio I2C Specification. */ reqs[i].out_hdr.addr = cpu_to_le16(msgs[i].addr << 1); + if (msgs[i].flags & I2C_M_RD) + reqs[i].out_hdr.flags |= cpu_to_le32(VIRTIO_I2C_FLAGS_M_RD); + if (i != num - 1) - reqs[i].out_hdr.flags = cpu_to_le32(VIRTIO_I2C_FLAGS_FAIL_NEXT); + reqs[i].out_hdr.flags |= cpu_to_le32(VIRTIO_I2C_FLAGS_FAIL_NEXT); sg_init_one(&out_hdr, &reqs[i].out_hdr, sizeof(reqs[i].out_hdr)); sgs[outcnt++] = &out_hdr; - reqs[i].buf = i2c_get_dma_safe_msg_buf(&msgs[i], 1); - if (!reqs[i].buf) - break; + if (msgs[i].len) { + reqs[i].buf = i2c_get_dma_safe_msg_buf(&msgs[i], 1); + if (!reqs[i].buf) + break; - sg_init_one(&msg_buf, reqs[i].buf, msgs[i].len); + sg_init_one(&msg_buf, reqs[i].buf, msgs[i].len); - if (msgs[i].flags & I2C_M_RD) - sgs[outcnt + incnt++] = &msg_buf; - else - sgs[outcnt++] = &msg_buf; + if (msgs[i].flags & I2C_M_RD) + sgs[outcnt + incnt++] = &msg_buf; + else + sgs[outcnt++] = &msg_buf; + } sg_init_one(&in_hdr, &reqs[i].in_hdr, sizeof(reqs[i].in_hdr)); sgs[outcnt + incnt++] = &in_hdr; @@ -191,7 +189,7 @@ static int virtio_i2c_setup_vqs(struct virtio_i2c *vi) static u32 virtio_i2c_func(struct i2c_adapter *adap) { - return I2C_FUNC_I2C | (I2C_FUNC_SMBUS_EMUL & ~I2C_FUNC_SMBUS_QUICK); + return I2C_FUNC_I2C | I2C_FUNC_SMBUS_EMUL; } static struct i2c_algorithm virtio_algorithm = { @@ -199,15 +197,16 @@ static struct i2c_algorithm virtio_algorithm = { .functionality = virtio_i2c_func, }; -static const struct i2c_adapter_quirks virtio_i2c_quirks = { - .flags = I2C_AQ_NO_ZERO_LEN, -}; - static int virtio_i2c_probe(struct virtio_device *vdev) { struct virtio_i2c *vi; int ret; + if (!virtio_has_feature(vdev, VIRTIO_I2C_F_ZERO_LENGTH_REQUEST)) { + dev_err(&vdev->dev, "Zero-length request feature is mandatory\n"); + return -EINVAL; + } + vi = devm_kzalloc(&vdev->dev, sizeof(*vi), GFP_KERNEL); if (!vi) return -ENOMEM; @@ -225,7 +224,6 @@ static int virtio_i2c_probe(struct virtio_device *vdev) snprintf(vi->adap.name, sizeof(vi->adap.name), "i2c_virtio at virtio bus %d", vdev->index); vi->adap.algo = &virtio_algorithm; - vi->adap.quirks = &virtio_i2c_quirks; vi->adap.dev.parent = &vdev->dev; vi->adap.dev.of_node = vdev->dev.of_node; i2c_set_adapdata(&vi->adap, vi); @@ -270,11 +268,17 @@ static int virtio_i2c_restore(struct virtio_device *vdev) } #endif +static const unsigned int features[] = { + VIRTIO_I2C_F_ZERO_LENGTH_REQUEST, +}; + static struct virtio_driver virtio_i2c_driver = { - .id_table = id_table, - .probe = virtio_i2c_probe, - .remove = virtio_i2c_remove, - .driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), + .id_table = id_table, + .probe = virtio_i2c_probe, + .remove = virtio_i2c_remove, + .driver = { .name = "i2c_virtio", }, #ifdef CONFIG_PM_SLEEP diff --git a/include/uapi/linux/virtio_i2c.h b/include/uapi/linux/virtio_i2c.h index 7c6a6fc01ad6..acf3b6069136 100644 --- a/include/uapi/linux/virtio_i2c.h +++ b/include/uapi/linux/virtio_i2c.h @@ -11,9 +11,15 @@ #include #include +/* Virtio I2C Feature bits */ +#define VIRTIO_I2C_F_ZERO_LENGTH_REQUEST 0 + /* The bit 0 of the @virtio_i2c_out_hdr.@flags, used to group the requests */ #define VIRTIO_I2C_FLAGS_FAIL_NEXT _BITUL(0) +/* The bit 1 of the @virtio_i2c_out_hdr.@flags, used to mark a buffer as read */ +#define VIRTIO_I2C_FLAGS_M_RD _BITUL(1) + /** * struct virtio_i2c_out_hdr - the virtio I2C message OUT header * @addr: the controlled device address -- cgit v1.2.3 From ad69dd0bf26b88ec6ab26f8bbe5cd74fbed7672a Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 26 Oct 2021 20:55:13 +0300 Subject: vdpa: Introduce query of device config layout Introduce a command to query a device config layout. An example query of network vdpa device: $ vdpa dev add name bar mgmtdev vdpasim_net $ vdpa dev config show bar: mac 00:35:09:19:48:05 link up link_announce false mtu 1500 $ vdpa dev config show -jp { "config": { "bar": { "mac": "00:35:09:19:48:05", "link ": "up", "link_announce ": false, "mtu": 1500, } } } Signed-off-by: Parav Pandit Signed-off-by: Eli Cohen Acked-by: Jason Wang Link: https://lore.kernel.org/r/20211026175519.87795-3-parav@nvidia.com Signed-off-by: Michael S. Tsirkin --- drivers/vdpa/vdpa.c | 176 ++++++++++++++++++++++++++++++++++++++++++++++ include/linux/vdpa.h | 2 + include/uapi/linux/vdpa.h | 6 ++ 3 files changed, 184 insertions(+) (limited to 'include/uapi/linux') diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index cbc8fc69cf9b..8fcbdda8590c 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -14,6 +14,8 @@ #include #include #include +#include +#include static LIST_HEAD(mdev_head); /* A global mutex that protects vdpa management device and device level operations. */ @@ -66,6 +68,7 @@ static void vdpa_release_dev(struct device *d) ops->free(vdev); ida_simple_remove(&vdpa_index_ida, vdev->index); + mutex_destroy(&vdev->cf_mutex); kfree(vdev); } @@ -127,6 +130,7 @@ struct vdpa_device *__vdpa_alloc_device(struct device *parent, if (err) goto err_name; + mutex_init(&vdev->cf_mutex); device_initialize(&vdev->dev); return vdev; @@ -309,6 +313,7 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, { const struct vdpa_config_ops *ops = vdev->config; + mutex_lock(&vdev->cf_mutex); /* * Config accesses aren't supposed to trigger before features are set. * If it does happen we assume a legacy guest. @@ -316,6 +321,7 @@ void vdpa_get_config(struct vdpa_device *vdev, unsigned int offset, if (!vdev->features_valid) vdpa_set_features(vdev, 0); ops->get_config(vdev, offset, buf, len); + mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_get_config); @@ -329,7 +335,9 @@ EXPORT_SYMBOL_GPL(vdpa_get_config); void vdpa_set_config(struct vdpa_device *vdev, unsigned int offset, const void *buf, unsigned int length) { + mutex_lock(&vdev->cf_mutex); vdev->config->set_config(vdev, offset, buf, length); + mutex_unlock(&vdev->cf_mutex); } EXPORT_SYMBOL_GPL(vdpa_set_config); @@ -661,6 +669,168 @@ static int vdpa_nl_cmd_dev_get_dumpit(struct sk_buff *msg, struct netlink_callba return msg->len; } +static int vdpa_dev_net_mq_config_fill(struct vdpa_device *vdev, + struct sk_buff *msg, u64 features, + const struct virtio_net_config *config) +{ + u16 val_u16; + + if ((features & (1ULL << VIRTIO_NET_F_MQ)) == 0) + return 0; + + val_u16 = le16_to_cpu(config->max_virtqueue_pairs); + return nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MAX_VQP, val_u16); +} + +static int vdpa_dev_net_config_fill(struct vdpa_device *vdev, struct sk_buff *msg) +{ + struct virtio_net_config config = {}; + u64 features; + u16 val_u16; + + vdpa_get_config(vdev, 0, &config, sizeof(config)); + + if (nla_put(msg, VDPA_ATTR_DEV_NET_CFG_MACADDR, sizeof(config.mac), + config.mac)) + return -EMSGSIZE; + + val_u16 = le16_to_cpu(config.status); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_STATUS, val_u16)) + return -EMSGSIZE; + + val_u16 = le16_to_cpu(config.mtu); + if (nla_put_u16(msg, VDPA_ATTR_DEV_NET_CFG_MTU, val_u16)) + return -EMSGSIZE; + + features = vdev->config->get_features(vdev); + + return vdpa_dev_net_mq_config_fill(vdev, msg, features, &config); +} + +static int +vdpa_dev_config_fill(struct vdpa_device *vdev, struct sk_buff *msg, u32 portid, u32 seq, + int flags, struct netlink_ext_ack *extack) +{ + u32 device_id; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &vdpa_nl_family, flags, + VDPA_CMD_DEV_CONFIG_GET); + if (!hdr) + return -EMSGSIZE; + + if (nla_put_string(msg, VDPA_ATTR_DEV_NAME, dev_name(&vdev->dev))) { + err = -EMSGSIZE; + goto msg_err; + } + + device_id = vdev->config->get_device_id(vdev); + if (nla_put_u32(msg, VDPA_ATTR_DEV_ID, device_id)) { + err = -EMSGSIZE; + goto msg_err; + } + + switch (device_id) { + case VIRTIO_ID_NET: + err = vdpa_dev_net_config_fill(vdev, msg); + break; + default: + err = -EOPNOTSUPP; + break; + } + if (err) + goto msg_err; + + genlmsg_end(msg, hdr); + return 0; + +msg_err: + genlmsg_cancel(msg, hdr); + return err; +} + +static int vdpa_nl_cmd_dev_config_get_doit(struct sk_buff *skb, struct genl_info *info) +{ + struct vdpa_device *vdev; + struct sk_buff *msg; + const char *devname; + struct device *dev; + int err; + + if (!info->attrs[VDPA_ATTR_DEV_NAME]) + return -EINVAL; + devname = nla_data(info->attrs[VDPA_ATTR_DEV_NAME]); + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + mutex_lock(&vdpa_dev_mutex); + dev = bus_find_device(&vdpa_bus, NULL, devname, vdpa_name_match); + if (!dev) { + NL_SET_ERR_MSG_MOD(info->extack, "device not found"); + err = -ENODEV; + goto dev_err; + } + vdev = container_of(dev, struct vdpa_device, dev); + if (!vdev->mdev) { + NL_SET_ERR_MSG_MOD(info->extack, "unmanaged vdpa device"); + err = -EINVAL; + goto mdev_err; + } + err = vdpa_dev_config_fill(vdev, msg, info->snd_portid, info->snd_seq, + 0, info->extack); + if (!err) + err = genlmsg_reply(msg, info); + +mdev_err: + put_device(dev); +dev_err: + mutex_unlock(&vdpa_dev_mutex); + if (err) + nlmsg_free(msg); + return err; +} + +static int vdpa_dev_config_dump(struct device *dev, void *data) +{ + struct vdpa_device *vdev = container_of(dev, struct vdpa_device, dev); + struct vdpa_dev_dump_info *info = data; + int err; + + if (!vdev->mdev) + return 0; + if (info->idx < info->start_idx) { + info->idx++; + return 0; + } + err = vdpa_dev_config_fill(vdev, info->msg, NETLINK_CB(info->cb->skb).portid, + info->cb->nlh->nlmsg_seq, NLM_F_MULTI, + info->cb->extack); + if (err) + return err; + + info->idx++; + return 0; +} + +static int +vdpa_nl_cmd_dev_config_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) +{ + struct vdpa_dev_dump_info info; + + info.msg = msg; + info.cb = cb; + info.start_idx = cb->args[0]; + info.idx = 0; + + mutex_lock(&vdpa_dev_mutex); + bus_for_each_dev(&vdpa_bus, NULL, &info, vdpa_dev_config_dump); + mutex_unlock(&vdpa_dev_mutex); + cb->args[0] = info.idx; + return msg->len; +} + static const struct nla_policy vdpa_nl_policy[VDPA_ATTR_MAX + 1] = { [VDPA_ATTR_MGMTDEV_BUS_NAME] = { .type = NLA_NUL_STRING }, [VDPA_ATTR_MGMTDEV_DEV_NAME] = { .type = NLA_STRING }, @@ -692,6 +862,12 @@ static const struct genl_ops vdpa_nl_ops[] = { .doit = vdpa_nl_cmd_dev_get_doit, .dumpit = vdpa_nl_cmd_dev_get_dumpit, }, + { + .cmd = VDPA_CMD_DEV_CONFIG_GET, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = vdpa_nl_cmd_dev_config_get_doit, + .dumpit = vdpa_nl_cmd_dev_config_get_dumpit, + }, }; static struct genl_family vdpa_nl_family __ro_after_init = { diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h index 267236aab34c..5cc5e501397f 100644 --- a/include/linux/vdpa.h +++ b/include/linux/vdpa.h @@ -63,6 +63,7 @@ struct vdpa_mgmt_dev; * @dev: underlying device * @dma_dev: the actual device that is performing DMA * @config: the configuration ops for this device. + * @cf_mutex: Protects get and set access to configuration layout. * @index: device index * @features_valid: were features initialized? for legacy guests * @use_va: indicate whether virtual address must be used by this device @@ -74,6 +75,7 @@ struct vdpa_device { struct device dev; struct device *dma_dev; const struct vdpa_config_ops *config; + struct mutex cf_mutex; /* Protects get/set config */ unsigned int index; bool features_valid; bool use_va; diff --git a/include/uapi/linux/vdpa.h b/include/uapi/linux/vdpa.h index e3b87879514c..a252f06f9dfd 100644 --- a/include/uapi/linux/vdpa.h +++ b/include/uapi/linux/vdpa.h @@ -17,6 +17,7 @@ enum vdpa_command { VDPA_CMD_DEV_NEW, VDPA_CMD_DEV_DEL, VDPA_CMD_DEV_GET, /* can dump */ + VDPA_CMD_DEV_CONFIG_GET, /* can dump */ }; enum vdpa_attr { @@ -34,6 +35,11 @@ enum vdpa_attr { VDPA_ATTR_DEV_MAX_VQ_SIZE, /* u16 */ VDPA_ATTR_DEV_MIN_VQ_SIZE, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MACADDR, /* binary */ + VDPA_ATTR_DEV_NET_STATUS, /* u8 */ + VDPA_ATTR_DEV_NET_CFG_MAX_VQP, /* u16 */ + VDPA_ATTR_DEV_NET_CFG_MTU, /* u16 */ + /* new attributes must be added above here */ VDPA_ATTR_MAX, }; -- cgit v1.2.3 From b9022b53adad88fd6cf2b9718c9e498504f3e1dd Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Sun, 31 Oct 2021 16:00:02 +0000 Subject: amt: add control plane of amt interface It adds definitions and control plane code for AMT. this is very similar to udp tunneling interfaces such as gtp, vxlan, etc. In the next patch, data plane code will be added. Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- MAINTAINERS | 8 + drivers/net/Kconfig | 16 ++ drivers/net/Makefile | 1 + drivers/net/amt.c | 493 +++++++++++++++++++++++++++++++++++++++++++++++ include/net/amt.h | 235 ++++++++++++++++++++++ include/uapi/linux/amt.h | 62 ++++++ 6 files changed, 815 insertions(+) create mode 100644 drivers/net/amt.c create mode 100644 include/net/amt.h create mode 100644 include/uapi/linux/amt.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 3b85f039fbf9..917f360b3ece 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1020,6 +1020,14 @@ S: Maintained F: Documentation/devicetree/bindings/iio/light/ams,as73211.yaml F: drivers/iio/light/as73211.c +AMT (Automatic Multicast Tunneling) +M: Taehee Yoo +L: netdev@vger.kernel.org +S: Maintained +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git +F: drivers/net/amt.c + ANALOG DEVICES INC AD7192 DRIVER M: Alexandru Tachici L: linux-iio@vger.kernel.org diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index dd335ae1122b..034dbd487c33 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -291,6 +291,22 @@ config GTP To compile this drivers as a module, choose M here: the module will be called gtp. +config AMT + tristate "Automatic Multicast Tunneling (AMT)" + depends on INET && IP_MULTICAST + select NET_UDP_TUNNEL + help + This allows one to create AMT(Automatic Multicast Tunneling) + virtual interfaces that provide multicast tunneling. + There are two roles, Gateway, and Relay. + Gateway Encapsulates IGMP/MLD traffic from listeners to the Relay. + Gateway Decapsulates multicast traffic from the Relay to Listeners. + Relay Encapsulates multicast traffic from Sources to Gateway. + Relay Decapsulates IGMP/MLD traffic from Gateway. + + To compile this drivers as a module, choose M here: the module + will be called amt. + config MACSEC tristate "IEEE 802.1AE MAC-level encryption (MACsec)" select CRYPTO diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 739838623cf6..50b23e71065f 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -14,6 +14,7 @@ obj-$(CONFIG_WIREGUARD) += wireguard/ obj-$(CONFIG_EQUALIZER) += eql.o obj-$(CONFIG_IFB) += ifb.o obj-$(CONFIG_MACSEC) += macsec.o +obj-$(CONFIG_AMT) += amt.o obj-$(CONFIG_MACVLAN) += macvlan.o obj-$(CONFIG_MACVTAP) += macvtap.o obj-$(CONFIG_MII) += mii.o diff --git a/drivers/net/amt.c b/drivers/net/amt.c new file mode 100644 index 000000000000..addab3b1de0a --- /dev/null +++ b/drivers/net/amt.c @@ -0,0 +1,493 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* Copyright (c) 2021 Taehee Yoo */ + +#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 +#include +#include +#include + +static struct workqueue_struct *amt_wq; + +static struct socket *amt_create_sock(struct net *net, __be16 port) +{ + struct udp_port_cfg udp_conf; + struct socket *sock; + int err; + + memset(&udp_conf, 0, sizeof(udp_conf)); + udp_conf.family = AF_INET; + udp_conf.local_ip.s_addr = htonl(INADDR_ANY); + + udp_conf.local_udp_port = port; + + err = udp_sock_create(net, &udp_conf, &sock); + if (err < 0) + return ERR_PTR(err); + + return sock; +} + +static int amt_socket_create(struct amt_dev *amt) +{ + struct udp_tunnel_sock_cfg tunnel_cfg; + struct socket *sock; + + sock = amt_create_sock(amt->net, amt->relay_port); + if (IS_ERR(sock)) + return PTR_ERR(sock); + + /* Mark socket as an encapsulation socket */ + memset(&tunnel_cfg, 0, sizeof(tunnel_cfg)); + tunnel_cfg.sk_user_data = amt; + tunnel_cfg.encap_type = 1; + tunnel_cfg.encap_destroy = NULL; + setup_udp_tunnel_sock(amt->net, sock, &tunnel_cfg); + + rcu_assign_pointer(amt->sock, sock); + return 0; +} + +static int amt_dev_open(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + int err; + + amt->ready4 = false; + amt->ready6 = false; + + err = amt_socket_create(amt); + if (err) + return err; + + amt->req_cnt = 0; + amt->remote_ip = 0; + get_random_bytes(&amt->key, sizeof(siphash_key_t)); + + amt->status = AMT_STATUS_INIT; + return err; +} + +static int amt_dev_stop(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + struct socket *sock; + + /* shutdown */ + sock = rtnl_dereference(amt->sock); + RCU_INIT_POINTER(amt->sock, NULL); + synchronize_net(); + if (sock) + udp_tunnel_sock_release(sock); + + amt->ready4 = false; + amt->ready6 = false; + amt->req_cnt = 0; + amt->remote_ip = 0; + + return 0; +} + +static const struct device_type amt_type = { + .name = "amt", +}; + +static int amt_dev_init(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + int err; + + amt->dev = dev; + dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); + if (!dev->tstats) + return -ENOMEM; + + err = gro_cells_init(&amt->gro_cells, dev); + if (err) { + free_percpu(dev->tstats); + return err; + } + + return 0; +} + +static void amt_dev_uninit(struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + + gro_cells_destroy(&amt->gro_cells); + free_percpu(dev->tstats); +} + +static const struct net_device_ops amt_netdev_ops = { + .ndo_init = amt_dev_init, + .ndo_uninit = amt_dev_uninit, + .ndo_open = amt_dev_open, + .ndo_stop = amt_dev_stop, + .ndo_get_stats64 = dev_get_tstats64, +}; + +static void amt_link_setup(struct net_device *dev) +{ + dev->netdev_ops = &amt_netdev_ops; + dev->needs_free_netdev = true; + SET_NETDEV_DEVTYPE(dev, &amt_type); + dev->min_mtu = ETH_MIN_MTU; + dev->max_mtu = ETH_MAX_MTU; + dev->type = ARPHRD_NONE; + dev->flags = IFF_POINTOPOINT | IFF_NOARP | IFF_MULTICAST; + dev->hard_header_len = 0; + dev->addr_len = 0; + dev->priv_flags |= IFF_NO_QUEUE; + dev->features |= NETIF_F_LLTX; + dev->features |= NETIF_F_GSO_SOFTWARE; + dev->features |= NETIF_F_NETNS_LOCAL; + dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM; + dev->hw_features |= NETIF_F_FRAGLIST | NETIF_F_RXCSUM; + dev->hw_features |= NETIF_F_GSO_SOFTWARE; + eth_hw_addr_random(dev); + eth_zero_addr(dev->broadcast); + ether_setup(dev); +} + +static const struct nla_policy amt_policy[IFLA_AMT_MAX + 1] = { + [IFLA_AMT_MODE] = { .type = NLA_U32 }, + [IFLA_AMT_RELAY_PORT] = { .type = NLA_U16 }, + [IFLA_AMT_GATEWAY_PORT] = { .type = NLA_U16 }, + [IFLA_AMT_LINK] = { .type = NLA_U32 }, + [IFLA_AMT_LOCAL_IP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_AMT_REMOTE_IP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_AMT_DISCOVERY_IP] = { .len = sizeof_field(struct iphdr, daddr) }, + [IFLA_AMT_MAX_TUNNELS] = { .type = NLA_U32 }, +}; + +static int amt_validate(struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + if (!data) + return -EINVAL; + + if (!data[IFLA_AMT_LINK]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_LINK], + "Link attribute is required"); + return -EINVAL; + } + + if (!data[IFLA_AMT_MODE]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_MODE], + "Mode attribute is required"); + return -EINVAL; + } + + if (nla_get_u32(data[IFLA_AMT_MODE]) > AMT_MODE_MAX) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_MODE], + "Mode attribute is not valid"); + return -EINVAL; + } + + if (!data[IFLA_AMT_LOCAL_IP]) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_DISCOVERY_IP], + "Local attribute is required"); + return -EINVAL; + } + + if (!data[IFLA_AMT_DISCOVERY_IP] && + nla_get_u32(data[IFLA_AMT_MODE]) == AMT_MODE_GATEWAY) { + NL_SET_ERR_MSG_ATTR(extack, data[IFLA_AMT_LOCAL_IP], + "Discovery attribute is required"); + return -EINVAL; + } + + return 0; +} + +static int amt_newlink(struct net *net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct amt_dev *amt = netdev_priv(dev); + int err = -EINVAL; + + amt->net = net; + amt->mode = nla_get_u32(data[IFLA_AMT_MODE]); + + if (data[IFLA_AMT_MAX_TUNNELS]) + amt->max_tunnels = nla_get_u32(data[IFLA_AMT_MAX_TUNNELS]); + else + amt->max_tunnels = AMT_MAX_TUNNELS; + + spin_lock_init(&amt->lock); + amt->max_groups = AMT_MAX_GROUP; + amt->max_sources = AMT_MAX_SOURCE; + amt->hash_buckets = AMT_HSIZE; + amt->nr_tunnels = 0; + get_random_bytes(&amt->hash_seed, sizeof(amt->hash_seed)); + amt->stream_dev = dev_get_by_index(net, + nla_get_u32(data[IFLA_AMT_LINK])); + if (!amt->stream_dev) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK], + "Can't find stream device"); + return -ENODEV; + } + + if (amt->stream_dev->type != ARPHRD_ETHER) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK], + "Invalid stream device type"); + goto err; + } + + amt->local_ip = nla_get_in_addr(data[IFLA_AMT_LOCAL_IP]); + if (ipv4_is_loopback(amt->local_ip) || + ipv4_is_zeronet(amt->local_ip) || + ipv4_is_multicast(amt->local_ip)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LOCAL_IP], + "Invalid Local address"); + goto err; + } + + if (data[IFLA_AMT_RELAY_PORT]) + amt->relay_port = nla_get_be16(data[IFLA_AMT_RELAY_PORT]); + else + amt->relay_port = htons(IANA_AMT_UDP_PORT); + + if (data[IFLA_AMT_GATEWAY_PORT]) + amt->gw_port = nla_get_be16(data[IFLA_AMT_GATEWAY_PORT]); + else + amt->gw_port = htons(IANA_AMT_UDP_PORT); + + if (!amt->relay_port) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "relay port must not be 0"); + goto err; + } + if (amt->mode == AMT_MODE_RELAY) { + amt->qrv = amt->net->ipv4.sysctl_igmp_qrv; + amt->qri = 10; + dev->needed_headroom = amt->stream_dev->needed_headroom + + AMT_RELAY_HLEN; + dev->mtu = amt->stream_dev->mtu - AMT_RELAY_HLEN; + dev->max_mtu = dev->mtu; + dev->min_mtu = ETH_MIN_MTU + AMT_RELAY_HLEN; + } else { + if (!data[IFLA_AMT_DISCOVERY_IP]) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "discovery must be set in gateway mode"); + goto err; + } + if (!amt->gw_port) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "gateway port must not be 0"); + goto err; + } + amt->remote_ip = 0; + amt->discovery_ip = nla_get_in_addr(data[IFLA_AMT_DISCOVERY_IP]); + if (ipv4_is_loopback(amt->discovery_ip) || + ipv4_is_zeronet(amt->discovery_ip) || + ipv4_is_multicast(amt->discovery_ip)) { + NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_DISCOVERY_IP], + "discovery must be unicast"); + goto err; + } + + dev->needed_headroom = amt->stream_dev->needed_headroom + + AMT_GW_HLEN; + dev->mtu = amt->stream_dev->mtu - AMT_GW_HLEN; + dev->max_mtu = dev->mtu; + dev->min_mtu = ETH_MIN_MTU + AMT_GW_HLEN; + } + amt->qi = AMT_INIT_QUERY_INTERVAL; + + err = register_netdevice(dev); + if (err < 0) { + netdev_dbg(dev, "failed to register new netdev %d\n", err); + goto err; + } + + err = netdev_upper_dev_link(amt->stream_dev, dev, extack); + if (err < 0) { + unregister_netdevice(dev); + goto err; + } + + return 0; +err: + dev_put(amt->stream_dev); + return err; +} + +static void amt_dellink(struct net_device *dev, struct list_head *head) +{ + struct amt_dev *amt = netdev_priv(dev); + + unregister_netdevice_queue(dev, head); + netdev_upper_dev_unlink(amt->stream_dev, dev); + dev_put(amt->stream_dev); +} + +static size_t amt_get_size(const struct net_device *dev) +{ + return nla_total_size(sizeof(__u32)) + /* IFLA_AMT_MODE */ + nla_total_size(sizeof(__u16)) + /* IFLA_AMT_RELAY_PORT */ + nla_total_size(sizeof(__u16)) + /* IFLA_AMT_GATEWAY_PORT */ + nla_total_size(sizeof(__u32)) + /* IFLA_AMT_LINK */ + nla_total_size(sizeof(__u32)) + /* IFLA_MAX_TUNNELS */ + nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_DISCOVERY_IP */ + nla_total_size(sizeof(struct iphdr)) + /* IFLA_AMT_REMOTE_IP */ + nla_total_size(sizeof(struct iphdr)); /* IFLA_AMT_LOCAL_IP */ +} + +static int amt_fill_info(struct sk_buff *skb, const struct net_device *dev) +{ + struct amt_dev *amt = netdev_priv(dev); + + if (nla_put_u32(skb, IFLA_AMT_MODE, amt->mode)) + goto nla_put_failure; + if (nla_put_be16(skb, IFLA_AMT_RELAY_PORT, amt->relay_port)) + goto nla_put_failure; + if (nla_put_be16(skb, IFLA_AMT_GATEWAY_PORT, amt->gw_port)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_AMT_LINK, amt->stream_dev->ifindex)) + goto nla_put_failure; + if (nla_put_in_addr(skb, IFLA_AMT_LOCAL_IP, amt->local_ip)) + goto nla_put_failure; + if (nla_put_in_addr(skb, IFLA_AMT_DISCOVERY_IP, amt->discovery_ip)) + goto nla_put_failure; + if (amt->remote_ip) + if (nla_put_in_addr(skb, IFLA_AMT_REMOTE_IP, amt->remote_ip)) + goto nla_put_failure; + if (nla_put_u32(skb, IFLA_AMT_MAX_TUNNELS, amt->max_tunnels)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static struct rtnl_link_ops amt_link_ops __read_mostly = { + .kind = "amt", + .maxtype = IFLA_AMT_MAX, + .policy = amt_policy, + .priv_size = sizeof(struct amt_dev), + .setup = amt_link_setup, + .validate = amt_validate, + .newlink = amt_newlink, + .dellink = amt_dellink, + .get_size = amt_get_size, + .fill_info = amt_fill_info, +}; + +static struct net_device *amt_lookup_upper_dev(struct net_device *dev) +{ + struct net_device *upper_dev; + struct amt_dev *amt; + + for_each_netdev(dev_net(dev), upper_dev) { + if (netif_is_amt(upper_dev)) { + amt = netdev_priv(upper_dev); + if (amt->stream_dev == dev) + return upper_dev; + } + } + + return NULL; +} + +static int amt_device_event(struct notifier_block *unused, + unsigned long event, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net_device *upper_dev; + struct amt_dev *amt; + LIST_HEAD(list); + int new_mtu; + + upper_dev = amt_lookup_upper_dev(dev); + if (!upper_dev) + return NOTIFY_DONE; + amt = netdev_priv(upper_dev); + + switch (event) { + case NETDEV_UNREGISTER: + amt_dellink(amt->dev, &list); + unregister_netdevice_many(&list); + break; + case NETDEV_CHANGEMTU: + if (amt->mode == AMT_MODE_RELAY) + new_mtu = dev->mtu - AMT_RELAY_HLEN; + else + new_mtu = dev->mtu - AMT_GW_HLEN; + + dev_set_mtu(amt->dev, new_mtu); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block amt_notifier_block __read_mostly = { + .notifier_call = amt_device_event, +}; + +static int __init amt_init(void) +{ + int err; + + err = register_netdevice_notifier(&amt_notifier_block); + if (err < 0) + goto err; + + err = rtnl_link_register(&amt_link_ops); + if (err < 0) + goto unregister_notifier; + + amt_wq = alloc_workqueue("amt", WQ_UNBOUND, 1); + if (!amt_wq) + goto rtnl_unregister; + + return 0; + +rtnl_unregister: + rtnl_link_unregister(&amt_link_ops); +unregister_notifier: + unregister_netdevice_notifier(&amt_notifier_block); +err: + pr_err("error loading AMT module loaded\n"); + return err; +} +late_initcall(amt_init); + +static void __exit amt_fini(void) +{ + rtnl_link_unregister(&amt_link_ops); + unregister_netdevice_notifier(&amt_notifier_block); + destroy_workqueue(amt_wq); +} +module_exit(amt_fini); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Taehee Yoo "); +MODULE_ALIAS_RTNL_LINK("amt"); diff --git a/include/net/amt.h b/include/net/amt.h new file mode 100644 index 000000000000..ce24ff823555 --- /dev/null +++ b/include/net/amt.h @@ -0,0 +1,235 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Copyright (c) 2021 Taehee Yoo + */ +#ifndef _NET_AMT_H_ +#define _NET_AMT_H_ + +#include +#include + +enum amt_msg_type { + AMT_MSG_DISCOVERY = 1, + AMT_MSG_ADVERTISEMENT, + AMT_MSG_REQUEST, + AMT_MSG_MEMBERSHIP_QUERY, + AMT_MSG_MEMBERSHIP_UPDATE, + AMT_MSG_MULTICAST_DATA, + AMT_MSG_TEARDOWM, + __AMT_MSG_MAX, +}; + +#define AMT_MSG_MAX (__AMT_MSG_MAX - 1) + +enum amt_status { + AMT_STATUS_INIT, + AMT_STATUS_SENT_DISCOVERY, + AMT_STATUS_RECEIVED_DISCOVERY, + AMT_STATUS_SENT_ADVERTISEMENT, + AMT_STATUS_RECEIVED_ADVERTISEMENT, + AMT_STATUS_SENT_REQUEST, + AMT_STATUS_RECEIVED_REQUEST, + AMT_STATUS_SENT_QUERY, + AMT_STATUS_RECEIVED_QUERY, + AMT_STATUS_SENT_UPDATE, + AMT_STATUS_RECEIVED_UPDATE, + __AMT_STATUS_MAX, +}; + +#define AMT_STATUS_MAX (__AMT_STATUS_MAX - 1) + +struct amt_header_discovery { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + reserved:24; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_advertisement { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved:24; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + reserved:24; +#else +#error "Please fix " +#endif + __be32 nonce; + __be32 ip4; +} __packed; + +struct amt_header_request { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u32 type:4, + version:4, + reserved1:7, + p:1, + reserved2:16; +#elif defined(__BIG_ENDIAN_BITFIELD) + u32 version:4, + type:4, + p:1, + reserved1:7, + reserved2:16; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_membership_query { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u64 type:4, + version:4, + reserved:6, + l:1, + g:1, + response_mac:48; +#elif defined(__BIG_ENDIAN_BITFIELD) + u64 version:4, + type:4, + g:1, + l:1, + reserved:6, + response_mac:48; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_membership_update { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u64 type:4, + version:4, + reserved:8, + response_mac:48; +#elif defined(__BIG_ENDIAN_BITFIELD) + u64 version:4, + type:4, + reserved:8, + response_mac:48; +#else +#error "Please fix " +#endif + __be32 nonce; +} __packed; + +struct amt_header_mcast_data { +#if defined(__LITTLE_ENDIAN_BITFIELD) + u16 type:4, + version:4, + reserved:8; +#elif defined(__BIG_ENDIAN_BITFIELD) + u16 version:4, + type:4, + reserved:8; +#else +#error "Please fix " +#endif +} __packed; + +struct amt_gw_headers { + union { + struct amt_header_discovery discovery; + struct amt_header_request request; + struct amt_header_membership_update update; + }; +} __packed; + +struct amt_relay_headers { + union { + struct amt_header_advertisement advertisement; + struct amt_header_membership_query query; + struct amt_header_mcast_data data; + }; +} __packed; + +struct amt_dev { + struct net_device *dev; + struct net_device *stream_dev; + struct net *net; + /* Global lock for amt device */ + spinlock_t lock; + /* Used only in relay mode */ + struct list_head tunnel_list; + struct gro_cells gro_cells; + + /* Protected by RTNL */ + struct delayed_work discovery_wq; + /* Protected by RTNL */ + struct delayed_work req_wq; + /* Protected by RTNL */ + struct delayed_work secret_wq; + /* AMT status */ + enum amt_status status; + /* Generated key */ + siphash_key_t key; + struct socket __rcu *sock; + u32 max_groups; + u32 max_sources; + u32 hash_buckets; + u32 hash_seed; + /* Default 128 */ + u32 max_tunnels; + /* Default 128 */ + u32 nr_tunnels; + /* Gateway or Relay mode */ + u32 mode; + /* Default 2268 */ + __be16 relay_port; + /* Default 2268 */ + __be16 gw_port; + /* Outer local ip */ + __be32 local_ip; + /* Outer remote ip */ + __be32 remote_ip; + /* Outer discovery ip */ + __be32 discovery_ip; + /* Only used in gateway mode */ + __be32 nonce; + /* Gateway sent request and received query */ + bool ready4; + bool ready6; + u8 req_cnt; + u8 qi; + u64 qrv; + u64 qri; + /* Used only in gateway mode */ + u64 mac:48, + reserved:16; +}; + +#define AMT_MAX_GROUP 32 +#define AMT_MAX_SOURCE 128 +#define AMT_HSIZE_SHIFT 8 +#define AMT_HSIZE (1 << AMT_HSIZE_SHIFT) + +#define AMT_INIT_QUERY_INTERVAL 125 +#define IANA_AMT_UDP_PORT 2268 +#define AMT_MAX_TUNNELS 128 +#define AMT_MAX_REQS 128 +#define AMT_GW_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + sizeof(struct amt_gw_headers)) +#define AMT_RELAY_HLEN (sizeof(struct iphdr) + \ + sizeof(struct udphdr) + \ + sizeof(struct amt_relay_headers)) + +static inline bool netif_is_amt(const struct net_device *dev) +{ + return dev->rtnl_link_ops && !strcmp(dev->rtnl_link_ops->kind, "amt"); +} + +#endif /* _NET_AMT_H_ */ diff --git a/include/uapi/linux/amt.h b/include/uapi/linux/amt.h new file mode 100644 index 000000000000..2dccff417195 --- /dev/null +++ b/include/uapi/linux/amt.h @@ -0,0 +1,62 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (c) 2021 Taehee Yoo + */ +#ifndef _UAPI_AMT_H_ +#define _UAPI_AMT_H_ + +enum ifla_amt_mode { + /* AMT interface works as Gateway mode. + * The Gateway mode encapsulates IGMP/MLD traffic and decapsulates + * multicast traffic. + */ + AMT_MODE_GATEWAY = 0, + /* AMT interface works as Relay mode. + * The Relay mode encapsulates multicast traffic and decapsulates + * IGMP/MLD traffic. + */ + AMT_MODE_RELAY, + __AMT_MODE_MAX, +}; + +#define AMT_MODE_MAX (__AMT_MODE_MAX - 1) + +enum { + IFLA_AMT_UNSPEC, + /* This attribute specify mode etier Gateway or Relay. */ + IFLA_AMT_MODE, + /* This attribute specify Relay port. + * AMT interface is created as Gateway mode, this attribute is used + * to specify relay(remote) port. + * AMT interface is created as Relay mode, this attribute is used + * as local port. + */ + IFLA_AMT_RELAY_PORT, + /* This attribute specify Gateway port. + * AMT interface is created as Gateway mode, this attribute is used + * as local port. + * AMT interface is created as Relay mode, this attribute is not used. + */ + IFLA_AMT_GATEWAY_PORT, + /* This attribute specify physical device */ + IFLA_AMT_LINK, + /* This attribute specify local ip address */ + IFLA_AMT_LOCAL_IP, + /* This attribute specify Relay ip address. + * So, this is not used by Relay. + */ + IFLA_AMT_REMOTE_IP, + /* This attribute specify Discovery ip address. + * When Gateway get started, it send discovery message to find the + * Relay's ip address. + * So, this is not used by Relay. + */ + IFLA_AMT_DISCOVERY_IP, + /* This attribute specify number of maximum tunnel. */ + IFLA_AMT_MAX_TUNNELS, + __IFLA_AMT_MAX, +}; + +#define IFLA_AMT_MAX (__IFLA_AMT_MAX - 1) + +#endif /* _UAPI_AMT_H_ */ -- cgit v1.2.3 From 8845b4681bf44b9d2d2badf2c67cf476e42a86bd Mon Sep 17 00:00:00 2001 From: Joanne Koong Date: Fri, 29 Oct 2021 15:49:08 -0700 Subject: bpf: Add alignment padding for "map_extra" + consolidate holes This patch makes 2 changes regarding alignment padding for the "map_extra" field. 1) In the kernel header, "map_extra" and "btf_value_type_id" are rearranged to consolidate the hole. Before: struct bpf_map { ... u32 max_entries; /* 36 4 */ u32 map_flags; /* 40 4 */ /* XXX 4 bytes hole, try to pack */ u64 map_extra; /* 48 8 */ int spin_lock_off; /* 56 4 */ int timer_off; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ u32 id; /* 64 4 */ int numa_node; /* 68 4 */ ... bool frozen; /* 117 1 */ /* XXX 10 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 2, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 10 */ } __attribute__((__aligned__(64))); After: struct bpf_map { ... u32 max_entries; /* 36 4 */ u64 map_extra; /* 40 8 */ u32 map_flags; /* 48 4 */ int spin_lock_off; /* 52 4 */ int timer_off; /* 56 4 */ u32 id; /* 60 4 */ /* --- cacheline 1 boundary (64 bytes) --- */ int numa_node; /* 64 4 */ ... bool frozen /* 113 1 */ /* XXX 14 bytes hole, try to pack */ /* --- cacheline 2 boundary (128 bytes) --- */ ... struct work_struct work; /* 144 72 */ /* --- cacheline 3 boundary (192 bytes) was 24 bytes ago --- */ struct mutex freeze_mutex; /* 216 144 */ /* --- cacheline 5 boundary (320 bytes) was 40 bytes ago --- */ u64 writecnt; /* 360 8 */ /* size: 384, cachelines: 6, members: 26 */ /* sum members: 354, holes: 1, sum holes: 14 */ /* padding: 16 */ /* forced alignments: 2, forced holes: 1, sum forced holes: 14 */ } __attribute__((__aligned__(64))); 2) Add alignment padding to the bpf_map_info struct More details can be found in commit 36f9814a494a ("bpf: fix uapi hole for 32 bit compat applications") Signed-off-by: Joanne Koong Signed-off-by: Alexei Starovoitov Acked-by: Yonghong Song Link: https://lore.kernel.org/bpf/20211029224909.1721024-3-joannekoong@fb.com --- include/linux/bpf.h | 6 +++--- include/uapi/linux/bpf.h | 1 + tools/include/uapi/linux/bpf.h | 1 + 3 files changed, 5 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/bpf.h b/include/linux/bpf.h index c098089c1b54..f6743d4bb531 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -168,23 +168,23 @@ struct bpf_map { u32 key_size; u32 value_size; u32 max_entries; - u32 map_flags; u64 map_extra; /* any per-map-type extra fields */ + u32 map_flags; int spin_lock_off; /* >=0 valid offset, <0 error */ int timer_off; /* >=0 valid offset, <0 error */ u32 id; int numa_node; u32 btf_key_type_id; u32 btf_value_type_id; + u32 btf_vmlinux_value_type_id; struct btf *btf; #ifdef CONFIG_MEMCG_KMEM struct mem_cgroup *memcg; #endif char name[BPF_OBJ_NAME_LEN]; - u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; bool frozen; /* write-once; write-protected by freeze_mutex */ - /* 22 bytes hole */ + /* 14 bytes hole */ /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bd0c9f0487f6..ba5af15e25f5 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -5662,6 +5662,7 @@ struct bpf_map_info { __u32 btf_id; __u32 btf_key_type_id; __u32 btf_value_type_id; + __u32 :32; /* alignment pad */ __u64 map_extra; } __attribute__((aligned(8))); -- cgit v1.2.3 From fcdb44d08a95003c3d040aecdee286156ec6f34e Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 1 Nov 2021 10:36:28 -0700 Subject: net: arp: introduce arp_evict_nocarrier sysctl parameter This change introduces a new sysctl parameter, arp_evict_nocarrier. When set (default) the ARP cache will be cleared on a NOCARRIER event. This new option has been defaulted to '1' which maintains existing behavior. Clearing the ARP cache on NOCARRIER is relatively new, introduced by: commit 859bd2ef1fc1110a8031b967ee656c53a6260a76 Author: David Ahern Date: Thu Oct 11 20:33:49 2018 -0700 net: Evict neighbor entries on carrier down The reason for this changes is to prevent the ARP cache from being cleared when a wireless device roams. Specifically for wireless roams the ARP cache should not be cleared because the underlying network has not changed. Clearing the ARP cache in this case can introduce significant delays sending out packets after a roam. A user reported such a situation here: https://lore.kernel.org/linux-wireless/CACsRnHWa47zpx3D1oDq9JYnZWniS8yBwW1h0WAVZ6vrbwL_S0w@mail.gmail.com/ After some investigation it was found that the kernel was holding onto packets until ARP finished which resulted in this 1 second delay. It was also found that the first ARP who-has was never responded to, which is actually what caues the delay. This change is more or less working around this behavior, but again, there is no reason to clear the cache on a roam anyways. As for the unanswered who-has, we know the packet made it OTA since it was seen while monitoring. Why it never received a response is unknown. In any case, since this is a problem on the AP side of things all that can be done is to work around it until it is solved. Some background on testing/reproducing the packet delay: Hardware: - 2 access points configured for Fast BSS Transition (Though I don't see why regular reassociation wouldn't have the same behavior) - Wireless station running IWD as supplicant - A device on network able to respond to pings (I used one of the APs) Procedure: - Connect to first AP - Ping once to establish an ARP entry - Start a tcpdump - Roam to second AP - Wait for operstate UP event, and note the timestamp - Start pinging Results: Below is the tcpdump after UP. It was recorded the interface went UP at 10:42:01.432875. 10:42:01.461871 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.497976 ARP, Request who-has 192.168.254.1 tell 192.168.254.71, length 28 10:42:02.507162 ARP, Reply 192.168.254.1 is-at ac:86:74:55:b0:20, length 46 10:42:02.507185 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 1, length 64 10:42:02.507205 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 2, length 64 10:42:02.507212 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 3, length 64 10:42:02.507219 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 4, length 64 10:42:02.507225 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 5, length 64 10:42:02.507232 IP 192.168.254.71 > 192.168.254.1: ICMP echo request, id 52792, seq 6, length 64 10:42:02.515373 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 1, length 64 10:42:02.521399 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 2, length 64 10:42:02.521612 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 3, length 64 10:42:02.521941 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 4, length 64 10:42:02.522419 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 5, length 64 10:42:02.523085 IP 192.168.254.1 > 192.168.254.71: ICMP echo reply, id 52792, seq 6, length 64 You can see the first ARP who-has went out very quickly after UP, but was never responded to. Nearly a second later the kernel retries and gets a response. Only then do the ping packets go out. If an ARP entry is manually added prior to UP (after the cache is cleared) it is seen that the first ping is never responded to, so its not only an issue with ARP but with data packets in general. As mentioned prior, the wireless interface was also monitored to verify the ping/ARP packet made it OTA which was observed to be true. Signed-off-by: James Prestwood Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 9 +++++++++ include/linux/inetdevice.h | 2 ++ include/uapi/linux/ip.h | 1 + include/uapi/linux/sysctl.h | 1 + net/ipv4/arp.c | 11 ++++++++++- net/ipv4/devinet.c | 4 ++++ 6 files changed, 27 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 16b8bf72feaf..18fde4ed7a5e 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -1611,6 +1611,15 @@ arp_accept - BOOLEAN gratuitous arp frame, the arp table will be updated regardless if this setting is on or off. +arp_evict_nocarrier - BOOLEAN + Clears the ARP cache on NOCARRIER events. This option is important for + wireless devices where the ARP cache should not be cleared when roaming + between access points on the same network. In most cases this should + remain as the default (1). + + - 1 - (default): Clear the ARP cache on NOCARRIER events + - 0 - Do not clear ARP cache on NOCARRIER events + mcast_solicit - INTEGER The maximum number of multicast probes in INCOMPLETE state, when the associated hardware address is unknown. Defaults diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h index a038feb63f23..518b484a7f07 100644 --- a/include/linux/inetdevice.h +++ b/include/linux/inetdevice.h @@ -133,6 +133,8 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev) #define IN_DEV_ARP_ANNOUNCE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_ANNOUNCE) #define IN_DEV_ARP_IGNORE(in_dev) IN_DEV_MAXCONF((in_dev), ARP_IGNORE) #define IN_DEV_ARP_NOTIFY(in_dev) IN_DEV_MAXCONF((in_dev), ARP_NOTIFY) +#define IN_DEV_ARP_EVICT_NOCARRIER(in_dev) IN_DEV_ANDCONF((in_dev), \ + ARP_EVICT_NOCARRIER) struct in_ifaddr { struct hlist_node hash; diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h index e42d13b55cf3..e00bbb9c47bb 100644 --- a/include/uapi/linux/ip.h +++ b/include/uapi/linux/ip.h @@ -169,6 +169,7 @@ enum IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST, IPV4_DEVCONF_DROP_GRATUITOUS_ARP, IPV4_DEVCONF_BC_FORWARDING, + IPV4_DEVCONF_ARP_EVICT_NOCARRIER, __IPV4_DEVCONF_MAX }; diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h index 1e05d3caa712..6a3b194c50fe 100644 --- a/include/uapi/linux/sysctl.h +++ b/include/uapi/linux/sysctl.h @@ -482,6 +482,7 @@ enum NET_IPV4_CONF_PROMOTE_SECONDARIES=20, NET_IPV4_CONF_ARP_ACCEPT=21, NET_IPV4_CONF_ARP_NOTIFY=22, + NET_IPV4_CONF_ARP_EVICT_NOCARRIER=23, }; /* /proc/sys/net/ipv4/netfilter */ diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 922dd73e5740..857a144b1ea9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1247,6 +1247,8 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct netdev_notifier_change_info *change_info; + struct in_device *in_dev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: @@ -1257,7 +1259,14 @@ static int arp_netdev_event(struct notifier_block *this, unsigned long event, change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&arp_tbl, dev); - if (!netif_carrier_ok(dev)) + + in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) + evict_nocarrier = true; + else + evict_nocarrier = IN_DEV_ARP_EVICT_NOCARRIER(in_dev); + + if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&arp_tbl, dev); break; default: diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index f4468980b675..ec73a0d52d3e 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -75,6 +75,7 @@ static struct ipv4_devconf ipv4_devconf = { [IPV4_DEVCONF_SHARED_MEDIA - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -87,6 +88,7 @@ static struct ipv4_devconf ipv4_devconf_dflt = { [IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1, [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/, [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/, + [IPV4_DEVCONF_ARP_EVICT_NOCARRIER - 1] = 1, }, }; @@ -2532,6 +2534,8 @@ static struct devinet_sysctl_table { DEVINET_SYSCTL_RW_ENTRY(ARP_IGNORE, "arp_ignore"), DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"), DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"), + DEVINET_SYSCTL_RW_ENTRY(ARP_EVICT_NOCARRIER, + "arp_evict_nocarrier"), DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"), DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION, "force_igmp_version"), -- cgit v1.2.3 From 18ac597af25e9760b76471524096f5b29eb820e6 Mon Sep 17 00:00:00 2001 From: James Prestwood Date: Mon, 1 Nov 2021 10:36:29 -0700 Subject: net: ndisc: introduce ndisc_evict_nocarrier sysctl parameter In most situations the neighbor discovery cache should be cleared on a NOCARRIER event which is currently done unconditionally. But for wireless roams the neighbor discovery cache can and should remain intact since the underlying network has not changed. This patch introduces a sysctl option ndisc_evict_nocarrier which can be disabled by a wireless supplicant during a roam. This allows packets to be sent after a roam immediately without having to wait for neighbor discovery. A user reported roughly a 1 second delay after a roam before packets could be sent out (note, on IPv4). This delay was due to the ARP cache being cleared. During testing of this same scenario using IPv6 no delay was noticed, but regardless there is no reason to clear the ndisc cache for wireless roams. Signed-off-by: James Prestwood Reviewed-by: David Ahern Signed-off-by: Jakub Kicinski --- Documentation/networking/ip-sysctl.rst | 9 +++++++++ include/linux/ipv6.h | 1 + include/uapi/linux/ipv6.h | 1 + net/ipv6/addrconf.c | 12 ++++++++++++ net/ipv6/ndisc.c | 12 +++++++++++- 5 files changed, 34 insertions(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst index 18fde4ed7a5e..c61cc0219f4c 100644 --- a/Documentation/networking/ip-sysctl.rst +++ b/Documentation/networking/ip-sysctl.rst @@ -2350,6 +2350,15 @@ ndisc_tclass - INTEGER * 0 - (default) +ndisc_evict_nocarrier - BOOLEAN + Clears the neighbor discovery table on NOCARRIER events. This option is + important for wireless devices where the neighbor discovery cache should + not be cleared when roaming between access points on the same network. + In most cases this should remain as the default (1). + + - 1 - (default): Clear neighbor discover cache on NOCARRIER events. + - 0 - Do not clear neighbor discovery cache on NOCARRIER events. + mldv1_unsolicited_report_interval - INTEGER The interval in milliseconds in which the next unsolicited MLDv1 report retransmit will take place. diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index c383630d3f06..20c1f968da7c 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -79,6 +79,7 @@ struct ipv6_devconf { __u32 ioam6_id; __u32 ioam6_id_wide; __u8 ioam6_enabled; + __u8 ndisc_evict_nocarrier; struct ctl_table_header *sysctl_header; }; diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h index b243a53fa985..d4178dace0bf 100644 --- a/include/uapi/linux/ipv6.h +++ b/include/uapi/linux/ipv6.h @@ -193,6 +193,7 @@ enum { DEVCONF_IOAM6_ENABLED, DEVCONF_IOAM6_ID, DEVCONF_IOAM6_ID_WIDE, + DEVCONF_NDISC_EVICT_NOCARRIER, DEVCONF_MAX }; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 9e1463a2acae..3445f8017430 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -241,6 +241,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = { .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, + .ndisc_evict_nocarrier = 1, }; static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { @@ -300,6 +301,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = { .ioam6_enabled = 0, .ioam6_id = IOAM6_DEFAULT_IF_ID, .ioam6_id_wide = IOAM6_DEFAULT_IF_ID_WIDE, + .ndisc_evict_nocarrier = 1, }; /* Check if link is ready: is it up and is a valid qdisc available */ @@ -5545,6 +5547,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, array[DEVCONF_IOAM6_ENABLED] = cnf->ioam6_enabled; array[DEVCONF_IOAM6_ID] = cnf->ioam6_id; array[DEVCONF_IOAM6_ID_WIDE] = cnf->ioam6_id_wide; + array[DEVCONF_NDISC_EVICT_NOCARRIER] = cnf->ndisc_evict_nocarrier; } static inline size_t inet6_ifla6_size(void) @@ -6986,6 +6989,15 @@ static const struct ctl_table addrconf_sysctl[] = { .mode = 0644, .proc_handler = proc_douintvec, }, + { + .procname = "ndisc_evict_nocarrier", + .data = &ipv6_devconf.ndisc_evict_nocarrier, + .maxlen = sizeof(u8), + .mode = 0644, + .proc_handler = proc_dou8vec_minmax, + .extra1 = (void *)SYSCTL_ZERO, + .extra2 = (void *)SYSCTL_ONE, + }, { /* sentinel */ } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 184190b9ea25..f03b597e4121 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1794,6 +1794,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, struct netdev_notifier_change_info *change_info; struct net *net = dev_net(dev); struct inet6_dev *idev; + bool evict_nocarrier; switch (event) { case NETDEV_CHANGEADDR: @@ -1810,10 +1811,19 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, in6_dev_put(idev); break; case NETDEV_CHANGE: + idev = in6_dev_get(dev); + if (!idev) + evict_nocarrier = true; + else { + evict_nocarrier = idev->cnf.ndisc_evict_nocarrier && + net->ipv6.devconf_all->ndisc_evict_nocarrier; + in6_dev_put(idev); + } + change_info = ptr; if (change_info->flags_changed & IFF_NOARP) neigh_changeaddr(&nd_tbl, dev); - if (!netif_carrier_ok(dev)) + if (evict_nocarrier && !netif_carrier_ok(dev)) neigh_carrier_down(&nd_tbl, dev); break; case NETDEV_DOWN: -- cgit v1.2.3 From 1aabe578dd86e9f2867c4db4fba9a15f4ba1825d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Tue, 2 Nov 2021 15:02:36 -0700 Subject: ethtool: fix ethtool msg len calculation for pause stats ETHTOOL_A_PAUSE_STAT_MAX is the MAX attribute id, so we need to subtract non-stats and add one to get a count (IOW -2+1 == -1). Otherwise we'll see: ethnl cmd 21: calculated reply length 40, but consumed 52 Fixes: 9a27a33027f2 ("ethtool: add standard pause stats") Signed-off-by: Jakub Kicinski Reviewed-by: Saeed Mahameed Signed-off-by: David S. Miller --- include/linux/ethtool_netlink.h | 3 +++ include/uapi/linux/ethtool_netlink.h | 4 +++- net/ethtool/pause.c | 3 +-- 3 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h index 1e7bf78cb382..aba348d58ff6 100644 --- a/include/linux/ethtool_netlink.h +++ b/include/linux/ethtool_netlink.h @@ -10,6 +10,9 @@ #define __ETHTOOL_LINK_MODE_MASK_NWORDS \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) +#define ETHTOOL_PAUSE_STAT_CNT (__ETHTOOL_A_PAUSE_STAT_CNT - \ + ETHTOOL_A_PAUSE_STAT_TX_FRAMES) + enum ethtool_multicast_groups { ETHNL_MCGRP_MONITOR, }; diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h index ca5fbb59fa42..999777d32dcf 100644 --- a/include/uapi/linux/ethtool_netlink.h +++ b/include/uapi/linux/ethtool_netlink.h @@ -411,7 +411,9 @@ enum { ETHTOOL_A_PAUSE_STAT_TX_FRAMES, ETHTOOL_A_PAUSE_STAT_RX_FRAMES, - /* add new constants above here */ + /* add new constants above here + * adjust ETHTOOL_PAUSE_STAT_CNT if adding non-stats! + */ __ETHTOOL_A_PAUSE_STAT_CNT, ETHTOOL_A_PAUSE_STAT_MAX = (__ETHTOOL_A_PAUSE_STAT_CNT - 1) }; diff --git a/net/ethtool/pause.c b/net/ethtool/pause.c index 9009f412151e..ee1e5806bc93 100644 --- a/net/ethtool/pause.c +++ b/net/ethtool/pause.c @@ -56,8 +56,7 @@ static int pause_reply_size(const struct ethnl_req_info *req_base, if (req_base->flags & ETHTOOL_FLAG_STATS) n += nla_total_size(0) + /* _PAUSE_STATS */ - nla_total_size_64bit(sizeof(u64)) * - (ETHTOOL_A_PAUSE_STAT_MAX - 2); + nla_total_size_64bit(sizeof(u64)) * ETHTOOL_PAUSE_STAT_CNT; return n; } -- cgit v1.2.3 From eff5cdd745a68863a73095b0b4d62d15e0d9d902 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Thu, 21 Oct 2021 16:34:19 +0530 Subject: gpio: virtio: Add IRQ support This patch adds IRQ support for the virtio GPIO driver. Note that this uses the irq_bus_lock/unlock() callbacks, since those operations over virtio may sleep. Reviewed-by: Linus Walleij Signed-off-by: Viresh Kumar Acked-by: Michael S. Tsirkin Signed-off-by: Bartosz Golaszewski --- drivers/gpio/Kconfig | 1 + drivers/gpio/gpio-virtio.c | 302 ++++++++++++++++++++++++++++++++++++++- include/uapi/linux/virtio_gpio.h | 25 ++++ 3 files changed, 324 insertions(+), 4 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig index 02eb9f647926..072ed610f9c6 100644 --- a/drivers/gpio/Kconfig +++ b/drivers/gpio/Kconfig @@ -1686,6 +1686,7 @@ config GPIO_MOCKUP config GPIO_VIRTIO tristate "VirtIO GPIO support" depends on VIRTIO + select GPIOLIB_IRQCHIP help Say Y here to enable guest support for virtio-based GPIO controllers. diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c index d24f1c9264bc..aeec4bf0b625 100644 --- a/drivers/gpio/gpio-virtio.c +++ b/drivers/gpio/gpio-virtio.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -28,12 +29,30 @@ struct virtio_gpio_line { unsigned int rxlen; }; +struct vgpio_irq_line { + u8 type; + bool disabled; + bool masked; + bool queued; + bool update_pending; + bool queue_pending; + + struct virtio_gpio_irq_request ireq ____cacheline_aligned; + struct virtio_gpio_irq_response ires ____cacheline_aligned; +}; + struct virtio_gpio { struct virtio_device *vdev; struct mutex lock; /* Protects virtqueue operation */ struct gpio_chip gc; struct virtio_gpio_line *lines; struct virtqueue *request_vq; + + /* irq support */ + struct virtqueue *event_vq; + struct mutex irq_lock; /* Protects irq operation */ + raw_spinlock_t eventq_lock; /* Protects queuing of the buffer */ + struct vgpio_irq_line *irq_lines; }; static int _virtio_gpio_req(struct virtio_gpio *vgpio, u16 type, u16 gpio, @@ -186,6 +205,238 @@ static void virtio_gpio_set(struct gpio_chip *gc, unsigned int gpio, int value) virtio_gpio_req(vgpio, VIRTIO_GPIO_MSG_SET_VALUE, gpio, value, NULL); } +/* Interrupt handling */ +static void virtio_gpio_irq_prepare(struct virtio_gpio *vgpio, u16 gpio) +{ + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[gpio]; + struct virtio_gpio_irq_request *ireq = &irq_line->ireq; + struct virtio_gpio_irq_response *ires = &irq_line->ires; + struct scatterlist *sgs[2], req_sg, res_sg; + int ret; + + if (WARN_ON(irq_line->queued || irq_line->masked || irq_line->disabled)) + return; + + ireq->gpio = cpu_to_le16(gpio); + sg_init_one(&req_sg, ireq, sizeof(*ireq)); + sg_init_one(&res_sg, ires, sizeof(*ires)); + sgs[0] = &req_sg; + sgs[1] = &res_sg; + + ret = virtqueue_add_sgs(vgpio->event_vq, sgs, 1, 1, irq_line, GFP_ATOMIC); + if (ret) { + dev_err(&vgpio->vdev->dev, "failed to add request to eventq\n"); + return; + } + + irq_line->queued = true; + virtqueue_kick(vgpio->event_vq); +} + +static void virtio_gpio_irq_enable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->disabled = false; + irq_line->masked = false; + irq_line->queue_pending = true; + raw_spin_unlock(&vgpio->eventq_lock); + + irq_line->update_pending = true; +} + +static void virtio_gpio_irq_disable(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->disabled = true; + irq_line->masked = true; + irq_line->queue_pending = false; + raw_spin_unlock(&vgpio->eventq_lock); + + irq_line->update_pending = true; +} + +static void virtio_gpio_irq_mask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->masked = true; + raw_spin_unlock(&vgpio->eventq_lock); +} + +static void virtio_gpio_irq_unmask(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->masked = false; + + /* Queue the buffer unconditionally on unmask */ + virtio_gpio_irq_prepare(vgpio, d->hwirq); + raw_spin_unlock(&vgpio->eventq_lock); +} + +static int virtio_gpio_irq_set_type(struct irq_data *d, unsigned int type) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + + switch (type) { + case IRQ_TYPE_EDGE_RISING: + type = VIRTIO_GPIO_IRQ_TYPE_EDGE_RISING; + break; + case IRQ_TYPE_EDGE_FALLING: + type = VIRTIO_GPIO_IRQ_TYPE_EDGE_FALLING; + break; + case IRQ_TYPE_EDGE_BOTH: + type = VIRTIO_GPIO_IRQ_TYPE_EDGE_BOTH; + break; + case IRQ_TYPE_LEVEL_LOW: + type = VIRTIO_GPIO_IRQ_TYPE_LEVEL_LOW; + break; + case IRQ_TYPE_LEVEL_HIGH: + type = VIRTIO_GPIO_IRQ_TYPE_LEVEL_HIGH; + break; + default: + dev_err(&vgpio->vdev->dev, "unsupported irq type: %u\n", type); + return -EINVAL; + } + + irq_line->type = type; + irq_line->update_pending = true; + + return 0; +} + +static void virtio_gpio_irq_bus_lock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + + mutex_lock(&vgpio->irq_lock); +} + +static void virtio_gpio_irq_bus_sync_unlock(struct irq_data *d) +{ + struct gpio_chip *gc = irq_data_get_irq_chip_data(d); + struct virtio_gpio *vgpio = gpiochip_get_data(gc); + struct vgpio_irq_line *irq_line = &vgpio->irq_lines[d->hwirq]; + u8 type = irq_line->disabled ? VIRTIO_GPIO_IRQ_TYPE_NONE : irq_line->type; + unsigned long flags; + + if (irq_line->update_pending) { + irq_line->update_pending = false; + virtio_gpio_req(vgpio, VIRTIO_GPIO_MSG_IRQ_TYPE, d->hwirq, type, + NULL); + + /* Queue the buffer only after interrupt is enabled */ + raw_spin_lock_irqsave(&vgpio->eventq_lock, flags); + if (irq_line->queue_pending) { + irq_line->queue_pending = false; + virtio_gpio_irq_prepare(vgpio, d->hwirq); + } + raw_spin_unlock_irqrestore(&vgpio->eventq_lock, flags); + } + + mutex_unlock(&vgpio->irq_lock); +} + +static struct irq_chip vgpio_irq_chip = { + .name = "virtio-gpio", + .irq_enable = virtio_gpio_irq_enable, + .irq_disable = virtio_gpio_irq_disable, + .irq_mask = virtio_gpio_irq_mask, + .irq_unmask = virtio_gpio_irq_unmask, + .irq_set_type = virtio_gpio_irq_set_type, + + /* These are required to implement irqchip for slow busses */ + .irq_bus_lock = virtio_gpio_irq_bus_lock, + .irq_bus_sync_unlock = virtio_gpio_irq_bus_sync_unlock, +}; + +static bool ignore_irq(struct virtio_gpio *vgpio, int gpio, + struct vgpio_irq_line *irq_line) +{ + bool ignore = false; + + raw_spin_lock(&vgpio->eventq_lock); + irq_line->queued = false; + + /* Interrupt is disabled currently */ + if (irq_line->masked || irq_line->disabled) { + ignore = true; + goto unlock; + } + + /* + * Buffer is returned as the interrupt was disabled earlier, but is + * enabled again now. Requeue the buffers. + */ + if (irq_line->ires.status == VIRTIO_GPIO_IRQ_STATUS_INVALID) { + virtio_gpio_irq_prepare(vgpio, gpio); + ignore = true; + goto unlock; + } + + if (WARN_ON(irq_line->ires.status != VIRTIO_GPIO_IRQ_STATUS_VALID)) + ignore = true; + +unlock: + raw_spin_unlock(&vgpio->eventq_lock); + + return ignore; +} + +static void virtio_gpio_event_vq(struct virtqueue *vq) +{ + struct virtio_gpio *vgpio = vq->vdev->priv; + struct device *dev = &vgpio->vdev->dev; + struct vgpio_irq_line *irq_line; + int gpio, ret; + unsigned int len; + + while (true) { + irq_line = virtqueue_get_buf(vgpio->event_vq, &len); + if (!irq_line) + break; + + if (len != sizeof(irq_line->ires)) { + dev_err(dev, "irq with incorrect length (%u : %u)\n", + len, (unsigned int)sizeof(irq_line->ires)); + continue; + } + + /* + * Find GPIO line number from the offset of irq_line within the + * irq_lines block. We can also get GPIO number from + * irq-request, but better not to rely on a buffer returned by + * remote. + */ + gpio = irq_line - vgpio->irq_lines; + WARN_ON(gpio >= vgpio->gc.ngpio); + + if (unlikely(ignore_irq(vgpio, gpio, irq_line))) + continue; + + ret = generic_handle_domain_irq(vgpio->gc.irq.domain, gpio); + if (ret) + dev_err(dev, "failed to handle interrupt: %d\n", ret); + }; +} + static void virtio_gpio_request_vq(struct virtqueue *vq) { struct virtio_gpio_line *line; @@ -210,14 +461,15 @@ static void virtio_gpio_free_vqs(struct virtio_device *vdev) static int virtio_gpio_alloc_vqs(struct virtio_gpio *vgpio, struct virtio_device *vdev) { - const char * const names[] = { "requestq" }; + const char * const names[] = { "requestq", "eventq" }; vq_callback_t *cbs[] = { virtio_gpio_request_vq, + virtio_gpio_event_vq, }; - struct virtqueue *vqs[1] = { NULL }; + struct virtqueue *vqs[2] = { NULL, NULL }; int ret; - ret = virtio_find_vqs(vdev, 1, vqs, cbs, names, NULL); + ret = virtio_find_vqs(vdev, vgpio->irq_lines ? 2 : 1, vqs, cbs, names, NULL); if (ret) { dev_err(&vdev->dev, "failed to find vqs: %d\n", ret); return ret; @@ -225,11 +477,23 @@ static int virtio_gpio_alloc_vqs(struct virtio_gpio *vgpio, if (!vqs[0]) { dev_err(&vdev->dev, "failed to find requestq vq\n"); - return -ENODEV; + goto out; } vgpio->request_vq = vqs[0]; + if (vgpio->irq_lines && !vqs[1]) { + dev_err(&vdev->dev, "failed to find eventq vq\n"); + goto out; + } + vgpio->event_vq = vqs[1]; + return 0; + +out: + if (vqs[0] || vqs[1]) + virtio_gpio_free_vqs(vdev); + + return -ENODEV; } static const char **virtio_gpio_get_names(struct virtio_gpio *vgpio, @@ -325,6 +589,30 @@ static int virtio_gpio_probe(struct virtio_device *vdev) vgpio->gc.owner = THIS_MODULE; vgpio->gc.can_sleep = true; + /* Interrupt support */ + if (virtio_has_feature(vdev, VIRTIO_GPIO_F_IRQ)) { + vgpio->irq_lines = devm_kcalloc(dev, ngpio, sizeof(*vgpio->irq_lines), GFP_KERNEL); + if (!vgpio->irq_lines) + return -ENOMEM; + + /* The event comes from the outside so no parent handler */ + vgpio->gc.irq.parent_handler = NULL; + vgpio->gc.irq.num_parents = 0; + vgpio->gc.irq.parents = NULL; + vgpio->gc.irq.default_type = IRQ_TYPE_NONE; + vgpio->gc.irq.handler = handle_level_irq; + vgpio->gc.irq.chip = &vgpio_irq_chip; + + for (i = 0; i < ngpio; i++) { + vgpio->irq_lines[i].type = VIRTIO_GPIO_IRQ_TYPE_NONE; + vgpio->irq_lines[i].disabled = true; + vgpio->irq_lines[i].masked = true; + } + + mutex_init(&vgpio->irq_lock); + raw_spin_lock_init(&vgpio->eventq_lock); + } + ret = virtio_gpio_alloc_vqs(vgpio, vdev); if (ret) return ret; @@ -357,7 +645,13 @@ static const struct virtio_device_id id_table[] = { }; MODULE_DEVICE_TABLE(virtio, id_table); +static const unsigned int features[] = { + VIRTIO_GPIO_F_IRQ, +}; + static struct virtio_driver virtio_gpio_driver = { + .feature_table = features, + .feature_table_size = ARRAY_SIZE(features), .id_table = id_table, .probe = virtio_gpio_probe, .remove = virtio_gpio_remove, diff --git a/include/uapi/linux/virtio_gpio.h b/include/uapi/linux/virtio_gpio.h index 0445f905d8cc..d04af9c5f0de 100644 --- a/include/uapi/linux/virtio_gpio.h +++ b/include/uapi/linux/virtio_gpio.h @@ -5,12 +5,16 @@ #include +/* Virtio GPIO Feature bits */ +#define VIRTIO_GPIO_F_IRQ 0 + /* Virtio GPIO request types */ #define VIRTIO_GPIO_MSG_GET_NAMES 0x0001 #define VIRTIO_GPIO_MSG_GET_DIRECTION 0x0002 #define VIRTIO_GPIO_MSG_SET_DIRECTION 0x0003 #define VIRTIO_GPIO_MSG_GET_VALUE 0x0004 #define VIRTIO_GPIO_MSG_SET_VALUE 0x0005 +#define VIRTIO_GPIO_MSG_IRQ_TYPE 0x0006 /* Possible values of the status field */ #define VIRTIO_GPIO_STATUS_OK 0x0 @@ -21,6 +25,14 @@ #define VIRTIO_GPIO_DIRECTION_OUT 0x01 #define VIRTIO_GPIO_DIRECTION_IN 0x02 +/* Virtio GPIO IRQ types */ +#define VIRTIO_GPIO_IRQ_TYPE_NONE 0x00 +#define VIRTIO_GPIO_IRQ_TYPE_EDGE_RISING 0x01 +#define VIRTIO_GPIO_IRQ_TYPE_EDGE_FALLING 0x02 +#define VIRTIO_GPIO_IRQ_TYPE_EDGE_BOTH 0x03 +#define VIRTIO_GPIO_IRQ_TYPE_LEVEL_HIGH 0x04 +#define VIRTIO_GPIO_IRQ_TYPE_LEVEL_LOW 0x08 + struct virtio_gpio_config { __le16 ngpio; __u8 padding[2]; @@ -44,4 +56,17 @@ struct virtio_gpio_response_get_names { __u8 value[]; }; +/* Virtio GPIO IRQ Request / Response */ +struct virtio_gpio_irq_request { + __le16 gpio; +}; + +struct virtio_gpio_irq_response { + __u8 status; +}; + +/* Possible values of the interrupt status field */ +#define VIRTIO_GPIO_IRQ_STATUS_INVALID 0x0 +#define VIRTIO_GPIO_IRQ_STATUS_VALID 0x1 + #endif /* _LINUX_VIRTIO_GPIO_H */ -- cgit v1.2.3 From 7d0003da6297eb128f3490e396e6fc6df71557cd Mon Sep 17 00:00:00 2001 From: "Michael S. Tsirkin" Date: Mon, 1 Nov 2021 05:11:25 -0400 Subject: virtio_gpio: drop packed attribute Declaring the struct packed here is mostly harmless, but gives a bad example for people to copy. As the struct is packed and aligned manually, let's just drop the attribute. Signed-off-by: Michael S. Tsirkin Acked-by: Viresh Kumar Signed-off-by: Bartosz Golaszewski --- include/uapi/linux/virtio_gpio.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/virtio_gpio.h b/include/uapi/linux/virtio_gpio.h index d04af9c5f0de..d4b29d9a39dd 100644 --- a/include/uapi/linux/virtio_gpio.h +++ b/include/uapi/linux/virtio_gpio.h @@ -37,7 +37,7 @@ struct virtio_gpio_config { __le16 ngpio; __u8 padding[2]; __le32 gpio_names_size; -} __packed; +}; /* Virtio GPIO Request / Response */ struct virtio_gpio_request { -- cgit v1.2.3 From aedad3e1c6ddec234b63cfb57ac231da0f680e50 Mon Sep 17 00:00:00 2001 From: Peter Collingbourne Date: Fri, 5 Nov 2021 16:08:29 -0700 Subject: arm64: mte: change PR_MTE_TCF_NONE back into an unsigned long This constant was previously an unsigned long, but was changed into an int in commit 433c38f40f6a ("arm64: mte: change ASYNC and SYNC TCF settings into bitfields"). This ended up causing spurious unsigned-signed comparison warnings in expressions such as: (x & PR_MTE_TCF_MASK) != PR_MTE_TCF_NONE Therefore, change it back into an unsigned long to silence these warnings. Link: https://linux-review.googlesource.com/id/I07a72310db30227a5b7d789d0b817d78b657c639 Signed-off-by: Peter Collingbourne Link: https://lore.kernel.org/r/20211105230829.2254790-1-pcc@google.com Signed-off-by: Will Deacon --- include/uapi/linux/prctl.h | 2 +- tools/include/uapi/linux/prctl.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 43bd7f713c39..de45fcd2dcbe 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index 43bd7f713c39..de45fcd2dcbe 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -235,7 +235,7 @@ struct prctl_mm_map { #define PR_GET_TAGGED_ADDR_CTRL 56 # define PR_TAGGED_ADDR_ENABLE (1UL << 0) /* MTE tag check fault modes */ -# define PR_MTE_TCF_NONE 0 +# define PR_MTE_TCF_NONE 0UL # define PR_MTE_TCF_SYNC (1UL << 1) # define PR_MTE_TCF_ASYNC (1UL << 2) # define PR_MTE_TCF_MASK (PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC) -- cgit v1.2.3 From 61082ad6a6e1f999eef7e7e90046486c87933b1e Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Mon, 15 Mar 2021 16:57:13 +0100 Subject: virtio-mem: support VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE The initial virtio-mem spec states that while unplugged memory should not be read, the device still has to allow for reading unplugged memory inside the usable region. The primary motivation for this default handling was to simplify bringup of virtio-mem, because there were corner cases where Linux might have accidentially read unplugged memory inside added Linux memory blocks. In the meantime, we: 1. Removed /dev/kmem in commit bbcd53c96071 ("drivers/char: remove /dev/kmem for good") 2. Disallowed access to virtio-mem device memory via /dev/mem in commit 2128f4e21aa2 ("virtio-mem: disallow mapping virtio-mem memory via /dev/mem") 3. Sanitized access to virtio-mem device memory via /proc/kcore in commit 0daa322b8ff9 ("fs/proc/kcore: don't read offline sections, logically offline pages and hwpoisoned pages") 4. Sanitized access to virtio-mem device memory via /proc/vmcore in commit ce2814622e84 ("virtio-mem: kdump mode to sanitize /proc/vmcore access") "Accidential" access to unplugged memory is no longer possible; we can support the new VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE feature that will be required by some hypervisors implementing virtio-mem in the near future. Acked-by: Michael S. Tsirkin Cc: "Michael S. Tsirkin" Cc: Jason Wang Cc: Marek Kedzierski Cc: Hui Zhu Cc: Sebastien Boeuf Cc: Pankaj Gupta Cc: Wei Yang Signed-off-by: David Hildenbrand --- drivers/virtio/virtio_mem.c | 1 + include/uapi/linux/virtio_mem.h | 9 ++++++--- 2 files changed, 7 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c index 0da0af251c73..96e5a8782769 100644 --- a/drivers/virtio/virtio_mem.c +++ b/drivers/virtio/virtio_mem.c @@ -2889,6 +2889,7 @@ static unsigned int virtio_mem_features[] = { #if defined(CONFIG_NUMA) && defined(CONFIG_ACPI_NUMA) VIRTIO_MEM_F_ACPI_PXM, #endif + VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, }; static const struct virtio_device_id virtio_mem_id_table[] = { diff --git a/include/uapi/linux/virtio_mem.h b/include/uapi/linux/virtio_mem.h index 70e01c687d5e..e9122f1d0e0c 100644 --- a/include/uapi/linux/virtio_mem.h +++ b/include/uapi/linux/virtio_mem.h @@ -68,9 +68,10 @@ * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG). * * There are no guarantees what will happen if unplugged memory is - * read/written. Such memory should, in general, not be touched. E.g., - * even writing might succeed, but the values will simply be discarded at - * random points in time. + * read/written. In general, unplugged memory should not be touched, because + * the resulting action is undefined. There is one exception: without + * VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE, unplugged memory inside the usable + * region can be read, to simplify creation of memory dumps. * * It can happen that the device cannot process a request, because it is * busy. The device driver has to retry later. @@ -87,6 +88,8 @@ /* node_id is an ACPI PXM and is valid */ #define VIRTIO_MEM_F_ACPI_PXM 0 +/* unplugged memory must not be accessed */ +#define VIRTIO_MEM_F_UNPLUGGED_INACCESSIBLE 1 /* --- virtio-mem: guest -> host requests --- */ -- cgit v1.2.3 From b56639318bb2be66aceba92836279714488709b4 Mon Sep 17 00:00:00 2001 From: Peter Gonda Date: Thu, 21 Oct 2021 10:43:00 -0700 Subject: KVM: SEV: Add support for SEV intra host migration For SEV to work with intra host migration, contents of the SEV info struct such as the ASID (used to index the encryption key in the AMD SP) and the list of memory regions need to be transferred to the target VM. This change adds a commands for a target VMM to get a source SEV VM's sev info. Signed-off-by: Peter Gonda Suggested-by: Sean Christopherson Reviewed-by: Marc Orr Cc: Marc Orr Cc: Paolo Bonzini Cc: Sean Christopherson Cc: David Rientjes Cc: Dr. David Alan Gilbert Cc: Brijesh Singh Cc: Tom Lendacky Cc: Vitaly Kuznetsov Cc: Wanpeng Li Cc: Jim Mattson Cc: Joerg Roedel Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Borislav Petkov Cc: "H. Peter Anvin" Cc: kvm@vger.kernel.org Cc: linux-kernel@vger.kernel.org Message-Id: <20211021174303.385706-3-pgonda@google.com> Signed-off-by: Paolo Bonzini --- Documentation/virt/kvm/api.rst | 14 ++++ arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm/sev.c | 152 ++++++++++++++++++++++++++++++++++++++++ arch/x86/kvm/svm/svm.c | 1 + arch/x86/kvm/svm/svm.h | 2 + arch/x86/kvm/x86.c | 6 ++ include/uapi/linux/kvm.h | 1 + 7 files changed, 177 insertions(+) (limited to 'include/uapi/linux') diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 3b093d6dbe22..aeeb071c7688 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -6911,6 +6911,20 @@ MAP_SHARED mmap will result in an -EINVAL return. When enabled the VMM may make use of the ``KVM_ARM_MTE_COPY_TAGS`` ioctl to perform a bulk copy of tags to/from the guest. +7.29 KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM +------------------------------------- + +Architectures: x86 SEV enabled +Type: vm +Parameters: args[0] is the fd of the source vm +Returns: 0 on success + +This capability enables userspace to migrate the encryption context from the VM +indicated by the fd to the VM this is called on. + +This is intended to support intra-host migration of VMs between userspace VMMs, +upgrading the VMM process without interrupting the guest. + 8. Other capabilities. ====================== diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 88fce6ab4bbd..0e9d1786c865 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1476,6 +1476,7 @@ struct kvm_x86_ops { int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + int (*vm_move_enc_context_from)(struct kvm *kvm, unsigned int source_fd); int (*get_msr_feature)(struct kvm_msr_entry *entry); diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 227becd93cb6..8b529022f0cf 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -1532,6 +1532,158 @@ static bool cmd_allowed_from_miror(u32 cmd_id) return false; } +static int sev_lock_for_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + /* + * Bail if this VM is already involved in a migration to avoid deadlock + * between two VMs trying to migrate to/from each other. + */ + if (atomic_cmpxchg_acquire(&sev->migration_in_progress, 0, 1)) + return -EBUSY; + + mutex_lock(&kvm->lock); + + return 0; +} + +static void sev_unlock_after_migration(struct kvm *kvm) +{ + struct kvm_sev_info *sev = &to_kvm_svm(kvm)->sev_info; + + mutex_unlock(&kvm->lock); + atomic_set_release(&sev->migration_in_progress, 0); +} + + +static int sev_lock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i, j; + + kvm_for_each_vcpu(i, vcpu, kvm) { + if (mutex_lock_killable(&vcpu->mutex)) + goto out_unlock; + } + + return 0; + +out_unlock: + kvm_for_each_vcpu(j, vcpu, kvm) { + if (i == j) + break; + + mutex_unlock(&vcpu->mutex); + } + return -EINTR; +} + +static void sev_unlock_vcpus_for_migration(struct kvm *kvm) +{ + struct kvm_vcpu *vcpu; + int i; + + kvm_for_each_vcpu(i, vcpu, kvm) { + mutex_unlock(&vcpu->mutex); + } +} + +static void sev_migrate_from(struct kvm_sev_info *dst, + struct kvm_sev_info *src) +{ + dst->active = true; + dst->asid = src->asid; + dst->handle = src->handle; + dst->pages_locked = src->pages_locked; + + src->asid = 0; + src->active = false; + src->handle = 0; + src->pages_locked = 0; + + if (dst->misc_cg != src->misc_cg) + sev_misc_cg_uncharge(src); + + put_misc_cg(src->misc_cg); + src->misc_cg = NULL; + + INIT_LIST_HEAD(&dst->regions_list); + list_replace_init(&src->regions_list, &dst->regions_list); +} + +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd) +{ + struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info; + struct kvm_sev_info *src_sev; + struct file *source_kvm_file; + struct kvm *source_kvm; + int ret; + + ret = sev_lock_for_migration(kvm); + if (ret) + return ret; + + if (sev_guest(kvm)) { + ret = -EINVAL; + goto out_unlock; + } + + source_kvm_file = fget(source_fd); + if (!file_is_kvm(source_kvm_file)) { + ret = -EBADF; + goto out_fput; + } + + source_kvm = source_kvm_file->private_data; + ret = sev_lock_for_migration(source_kvm); + if (ret) + goto out_fput; + + if (!sev_guest(source_kvm) || sev_es_guest(source_kvm)) { + ret = -EINVAL; + goto out_source; + } + + src_sev = &to_kvm_svm(source_kvm)->sev_info; + dst_sev->misc_cg = get_current_misc_cg(); + if (dst_sev->misc_cg != src_sev->misc_cg) { + ret = sev_misc_cg_try_charge(dst_sev); + if (ret) + goto out_dst_put_cgroup; + } + + ret = sev_lock_vcpus_for_migration(kvm); + if (ret) + goto out_dst_cgroup; + ret = sev_lock_vcpus_for_migration(source_kvm); + if (ret) + goto out_dst_vcpu; + + sev_migrate_from(dst_sev, src_sev); + kvm_vm_dead(source_kvm); + ret = 0; + + sev_unlock_vcpus_for_migration(source_kvm); +out_dst_vcpu: + sev_unlock_vcpus_for_migration(kvm); +out_dst_cgroup: + if (ret < 0) { + sev_misc_cg_uncharge(dst_sev); +out_dst_put_cgroup: + put_misc_cg(dst_sev->misc_cg); + dst_sev->misc_cg = NULL; + } +out_source: + sev_unlock_after_migration(source_kvm); +out_fput: + if (source_kvm_file) + fput(source_kvm_file); +out_unlock: + sev_unlock_after_migration(kvm); + return ret; +} + int svm_mem_enc_op(struct kvm *kvm, void __user *argp) { struct kvm_sev_cmd sev_cmd; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 1143b4ac900d..b4f2d1d55bd2 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4699,6 +4699,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_unreg_region = svm_unregister_enc_region, .vm_copy_enc_context_from = svm_vm_copy_asid_from, + .vm_move_enc_context_from = svm_vm_migrate_from, .can_emulate_instruction = svm_can_emulate_instruction, diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 80048841cad9..d4eae06b0695 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -80,6 +80,7 @@ struct kvm_sev_info { u64 ap_jump_table; /* SEV-ES AP Jump Table address */ struct kvm *enc_context_owner; /* Owner of copied encryption context */ struct misc_cg *misc_cg; /* For misc cgroup accounting */ + atomic_t migration_in_progress; }; struct kvm_svm { @@ -562,6 +563,7 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd); +int svm_vm_migrate_from(struct kvm *kvm, unsigned int source_fd); void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 622cb75f5e75..4417f375da77 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -5845,6 +5845,12 @@ split_irqchip_unlock: if (kvm_x86_ops.vm_copy_enc_context_from) r = kvm_x86_ops.vm_copy_enc_context_from(kvm, cap->args[0]); return r; + case KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM: + r = -EINVAL; + if (kvm_x86_ops.vm_move_enc_context_from) + r = kvm_x86_ops.vm_move_enc_context_from( + kvm, cap->args[0]); + return r; case KVM_CAP_EXIT_HYPERCALL: if (cap->args[0] & ~KVM_EXIT_HYPERCALL_VALID_MASK) { r = -EINVAL; diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 78f0719cc2a3..1daa45268de2 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1130,6 +1130,7 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_BINARY_STATS_FD 203 #define KVM_CAP_EXIT_ON_EMULATION_FAILURE 204 #define KVM_CAP_ARM_MTE 205 +#define KVM_CAP_VM_MOVE_ENC_CONTEXT_FROM 206 #ifdef KVM_CAP_IRQ_ROUTING -- cgit v1.2.3 From b5f57384805a34f497edb8b04d694a8a1b3d81d4 Mon Sep 17 00:00:00 2001 From: Felix Kuehling Date: Fri, 10 Sep 2021 15:18:20 -0400 Subject: drm/amdkfd: Add sysfs bitfields and enums to uAPI These bits are de-facto part of the uAPI, so declare them in a uAPI header. The corresponding bit-fields and enums in user mode are defined in https://github.com/RadeonOpenCompute/ROCT-Thunk-Interface/blob/master/include/hsakmttypes.h HSA_CAP_... -> HSA_CAPABILITY HSA_MEM_HEAP_TYPE_... -> HSA_HEAPTYPE HSA_MEM_FLAGS_... -> HSA_MEMORYPROPERTY HSA_CACHE_TYPE_... -> HsaCacheType HSA_IOLINK_TYPE_... -> HSA_IOLINKTYPE HSA_IOLINK_FLAGS_... -> HSA_LINKPROPERTY Signed-off-by: Felix Kuehling Reviewed-by: Jonathan Kim Signed-off-by: Alex Deucher --- MAINTAINERS | 1 + drivers/gpu/drm/amd/amdkfd/kfd_topology.h | 46 +------------ include/uapi/linux/kfd_sysfs.h | 108 ++++++++++++++++++++++++++++++ 3 files changed, 110 insertions(+), 45 deletions(-) create mode 100644 include/uapi/linux/kfd_sysfs.h (limited to 'include/uapi/linux') diff --git a/MAINTAINERS b/MAINTAINERS index 7a2345ce8521..f05a19b22505 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -966,6 +966,7 @@ F: drivers/gpu/drm/amd/include/kgd_kfd_interface.h F: drivers/gpu/drm/amd/include/v9_structs.h F: drivers/gpu/drm/amd/include/vi_structs.h F: include/uapi/linux/kfd_ioctl.h +F: include/uapi/linux/kfd_sysfs.h AMD SPI DRIVER M: Sanjay R Mehta diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h index a8db017c9b8e..f0cc59d2fd5d 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h +++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h @@ -25,38 +25,11 @@ #include #include +#include #include "kfd_crat.h" #define KFD_TOPOLOGY_PUBLIC_NAME_SIZE 32 -#define HSA_CAP_HOT_PLUGGABLE 0x00000001 -#define HSA_CAP_ATS_PRESENT 0x00000002 -#define HSA_CAP_SHARED_WITH_GRAPHICS 0x00000004 -#define HSA_CAP_QUEUE_SIZE_POW2 0x00000008 -#define HSA_CAP_QUEUE_SIZE_32BIT 0x00000010 -#define HSA_CAP_QUEUE_IDLE_EVENT 0x00000020 -#define HSA_CAP_VA_LIMIT 0x00000040 -#define HSA_CAP_WATCH_POINTS_SUPPORTED 0x00000080 -#define HSA_CAP_WATCH_POINTS_TOTALBITS_MASK 0x00000f00 -#define HSA_CAP_WATCH_POINTS_TOTALBITS_SHIFT 8 -#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK 0x00003000 -#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT 12 - -#define HSA_CAP_DOORBELL_TYPE_PRE_1_0 0x0 -#define HSA_CAP_DOORBELL_TYPE_1_0 0x1 -#define HSA_CAP_DOORBELL_TYPE_2_0 0x2 -#define HSA_CAP_AQL_QUEUE_DOUBLE_MAP 0x00004000 - -#define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 /* Old buggy user mode depends on this being 0 */ -#define HSA_CAP_MEM_EDCSUPPORTED 0x00100000 -#define HSA_CAP_RASEVENTNOTIFY 0x00200000 -#define HSA_CAP_ASIC_REVISION_MASK 0x03c00000 -#define HSA_CAP_ASIC_REVISION_SHIFT 22 -#define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 -#define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 -#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 -#define HSA_CAP_RESERVED 0xe00f8000 - struct kfd_node_properties { uint64_t hive_id; uint32_t cpu_cores_count; @@ -93,17 +66,6 @@ struct kfd_node_properties { char name[KFD_TOPOLOGY_PUBLIC_NAME_SIZE]; }; -#define HSA_MEM_HEAP_TYPE_SYSTEM 0 -#define HSA_MEM_HEAP_TYPE_FB_PUBLIC 1 -#define HSA_MEM_HEAP_TYPE_FB_PRIVATE 2 -#define HSA_MEM_HEAP_TYPE_GPU_GDS 3 -#define HSA_MEM_HEAP_TYPE_GPU_LDS 4 -#define HSA_MEM_HEAP_TYPE_GPU_SCRATCH 5 - -#define HSA_MEM_FLAGS_HOT_PLUGGABLE 0x00000001 -#define HSA_MEM_FLAGS_NON_VOLATILE 0x00000002 -#define HSA_MEM_FLAGS_RESERVED 0xfffffffc - struct kfd_mem_properties { struct list_head list; uint32_t heap_type; @@ -116,12 +78,6 @@ struct kfd_mem_properties { struct attribute attr; }; -#define HSA_CACHE_TYPE_DATA 0x00000001 -#define HSA_CACHE_TYPE_INSTRUCTION 0x00000002 -#define HSA_CACHE_TYPE_CPU 0x00000004 -#define HSA_CACHE_TYPE_HSACU 0x00000008 -#define HSA_CACHE_TYPE_RESERVED 0xfffffff0 - struct kfd_cache_properties { struct list_head list; uint32_t processor_id_low; diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h new file mode 100644 index 000000000000..e1fb78b4bf09 --- /dev/null +++ b/include/uapi/linux/kfd_sysfs.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT WITH Linux-syscall-note */ +/* + * Copyright 2021 Advanced Micro Devices, Inc. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + */ + +#ifndef KFD_SYSFS_H_INCLUDED +#define KFD_SYSFS_H_INCLUDED + +/* Capability bits in node properties */ +#define HSA_CAP_HOT_PLUGGABLE 0x00000001 +#define HSA_CAP_ATS_PRESENT 0x00000002 +#define HSA_CAP_SHARED_WITH_GRAPHICS 0x00000004 +#define HSA_CAP_QUEUE_SIZE_POW2 0x00000008 +#define HSA_CAP_QUEUE_SIZE_32BIT 0x00000010 +#define HSA_CAP_QUEUE_IDLE_EVENT 0x00000020 +#define HSA_CAP_VA_LIMIT 0x00000040 +#define HSA_CAP_WATCH_POINTS_SUPPORTED 0x00000080 +#define HSA_CAP_WATCH_POINTS_TOTALBITS_MASK 0x00000f00 +#define HSA_CAP_WATCH_POINTS_TOTALBITS_SHIFT 8 +#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_MASK 0x00003000 +#define HSA_CAP_DOORBELL_TYPE_TOTALBITS_SHIFT 12 + +#define HSA_CAP_DOORBELL_TYPE_PRE_1_0 0x0 +#define HSA_CAP_DOORBELL_TYPE_1_0 0x1 +#define HSA_CAP_DOORBELL_TYPE_2_0 0x2 +#define HSA_CAP_AQL_QUEUE_DOUBLE_MAP 0x00004000 + +/* Old buggy user mode depends on this being 0 */ +#define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED 0x00080000 + +#define HSA_CAP_MEM_EDCSUPPORTED 0x00100000 +#define HSA_CAP_RASEVENTNOTIFY 0x00200000 +#define HSA_CAP_ASIC_REVISION_MASK 0x03c00000 +#define HSA_CAP_ASIC_REVISION_SHIFT 22 +#define HSA_CAP_SRAM_EDCSUPPORTED 0x04000000 +#define HSA_CAP_SVMAPI_SUPPORTED 0x08000000 +#define HSA_CAP_FLAGS_COHERENTHOSTACCESS 0x10000000 +#define HSA_CAP_RESERVED 0xe00f8000 + +/* Heap types in memory properties */ +#define HSA_MEM_HEAP_TYPE_SYSTEM 0 +#define HSA_MEM_HEAP_TYPE_FB_PUBLIC 1 +#define HSA_MEM_HEAP_TYPE_FB_PRIVATE 2 +#define HSA_MEM_HEAP_TYPE_GPU_GDS 3 +#define HSA_MEM_HEAP_TYPE_GPU_LDS 4 +#define HSA_MEM_HEAP_TYPE_GPU_SCRATCH 5 + +/* Flag bits in memory properties */ +#define HSA_MEM_FLAGS_HOT_PLUGGABLE 0x00000001 +#define HSA_MEM_FLAGS_NON_VOLATILE 0x00000002 +#define HSA_MEM_FLAGS_RESERVED 0xfffffffc + +/* Cache types in cache properties */ +#define HSA_CACHE_TYPE_DATA 0x00000001 +#define HSA_CACHE_TYPE_INSTRUCTION 0x00000002 +#define HSA_CACHE_TYPE_CPU 0x00000004 +#define HSA_CACHE_TYPE_HSACU 0x00000008 +#define HSA_CACHE_TYPE_RESERVED 0xfffffff0 + +/* Link types in IO link properties (matches CRAT link types) */ +#define HSA_IOLINK_TYPE_UNDEFINED 0 +#define HSA_IOLINK_TYPE_HYPERTRANSPORT 1 +#define HSA_IOLINK_TYPE_PCIEXPRESS 2 +#define HSA_IOLINK_TYPE_AMBA 3 +#define HSA_IOLINK_TYPE_MIPI 4 +#define HSA_IOLINK_TYPE_QPI_1_1 5 +#define HSA_IOLINK_TYPE_RESERVED1 6 +#define HSA_IOLINK_TYPE_RESERVED2 7 +#define HSA_IOLINK_TYPE_RAPID_IO 8 +#define HSA_IOLINK_TYPE_INFINIBAND 9 +#define HSA_IOLINK_TYPE_RESERVED3 10 +#define HSA_IOLINK_TYPE_XGMI 11 +#define HSA_IOLINK_TYPE_XGOP 12 +#define HSA_IOLINK_TYPE_GZ 13 +#define HSA_IOLINK_TYPE_ETHERNET_RDMA 14 +#define HSA_IOLINK_TYPE_RDMA_OTHER 15 +#define HSA_IOLINK_TYPE_OTHER 16 + +/* Flag bits in IO link properties (matches CRAT flags, excluding the + * bi-directional flag, which is not offially part of the CRAT spec, and + * only used internally in KFD) + */ +#define HSA_IOLINK_FLAGS_ENABLED (1 << 0) +#define HSA_IOLINK_FLAGS_NON_COHERENT (1 << 1) +#define HSA_IOLINK_FLAGS_NO_ATOMICS_32_BIT (1 << 2) +#define HSA_IOLINK_FLAGS_NO_ATOMICS_64_BIT (1 << 3) +#define HSA_IOLINK_FLAGS_NO_PEER_TO_PEER_DMA (1 << 4) +#define HSA_IOLINK_FLAGS_RESERVED 0xffffffe0 + +#endif -- cgit v1.2.3 From 72f6a45202f20f0e1a46b0acb7803369cc53d0b8 Mon Sep 17 00:00:00 2001 From: Xiayu Zhang Date: Wed, 1 Dec 2021 10:57:13 +0800 Subject: Fix Comment of ETH_P_802_3_MIN The description of ETH_P_802_3_MIN is misleading. The value of EthernetType in Ethernet II frame is more than 0x0600, the value of Length in 802.3 frame is less than 0x0600. Signed-off-by: Xiayu Zhang Signed-off-by: David S. Miller --- include/uapi/linux/if_ether.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/if_ether.h b/include/uapi/linux/if_ether.h index 5da4ee234e0b..c0c2f3ed5729 100644 --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@ -117,7 +117,7 @@ #define ETH_P_IFE 0xED3E /* ForCES inter-FE LFB type */ #define ETH_P_AF_IUCV 0xFBFB /* IBM af_iucv [ NOT AN OFFICIALLY REGISTERED ID ] */ -#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is less than this value +#define ETH_P_802_3_MIN 0x0600 /* If the value in the ethernet type is more than this value * then the frame is Ethernet II. Else it is 802.3 */ /* -- cgit v1.2.3 From 9dcc38e2813e0cd3b195940c98b181ce6ede8f20 Mon Sep 17 00:00:00 2001 From: Drew DeVault Date: Fri, 10 Dec 2021 14:46:09 -0800 Subject: Increase default MLOCK_LIMIT to 8 MiB This limit has not been updated since 2008, when it was increased to 64 KiB at the request of GnuPG. Until recently, the main use-cases for this feature were (1) preventing sensitive memory from being swapped, as in GnuPG's use-case; and (2) real-time use-cases. In the first case, little memory is called for, and in the second case, the user is generally in a position to increase it if they need more. The introduction of IOURING_REGISTER_BUFFERS adds a third use-case: preparing fixed buffers for high-performance I/O. This use-case will take as much of this memory as it can get, but is still limited to 64 KiB by default, which is very little. This increases the limit to 8 MB, which was chosen fairly arbitrarily as a more generous, but still conservative, default value. It is also possible to raise this limit in userspace. This is easily done, for example, in the use-case of a network daemon: systemd, for instance, provides for this via LimitMEMLOCK in the service file; OpenRC via the rc_ulimit variables. However, there is no established userspace facility for configuring this outside of daemons: end-user applications do not presently have access to a convenient means of raising their limits. The buck, as it were, stops with the kernel. It's much easier to address it here than it is to bring it to hundreds of distributions, and it can only realistically be relied upon to be high-enough by end-user software if it is more-or-less ubiquitous. Most distros don't change this particular rlimit from the kernel-supplied default value, so a change here will easily provide that ubiquity. Link: https://lkml.kernel.org/r/20211028080813.15966-1-sir@cmpwn.com Signed-off-by: Drew DeVault Acked-by: Jens Axboe Acked-by: Cyril Hrubis Acked-by: Johannes Weiner Cc: Pavel Begunkov Cc: David Hildenbrand Cc: Jason Gunthorpe Cc: Andrew Dona-Couch Cc: Ammar Faizi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/uapi/linux/resource.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/resource.h b/include/uapi/linux/resource.h index 74ef57b38f9f..ac5d6a3031db 100644 --- a/include/uapi/linux/resource.h +++ b/include/uapi/linux/resource.h @@ -66,10 +66,17 @@ struct rlimit64 { #define _STK_LIM (8*1024*1024) /* - * GPG2 wants 64kB of mlocked memory, to make sure pass phrases - * and other sensitive information are never written to disk. + * Limit the amount of locked memory by some sane default: + * root can always increase this limit if needed. + * + * The main use-cases are (1) preventing sensitive memory + * from being swapped; (2) real-time operations; (3) via + * IOURING_REGISTER_BUFFERS. + * + * The first two don't need much. The latter will take as + * much as it can get. 8MB is a reasonably sane default. */ -#define MLOCK_LIMIT ((PAGE_SIZE > 64*1024) ? PAGE_SIZE : 64*1024) +#define MLOCK_LIMIT (8*1024*1024) /* * Due to binary compatibility, the actual resource numbers -- cgit v1.2.3