From 4fe6a946823a9bc8619fd16b7ea7d15914a30f22 Mon Sep 17 00:00:00 2001 From: David Howells Date: Thu, 2 Sep 2021 21:51:01 +0100 Subject: afs: Try to avoid taking RCU read lock when checking vnode validity Try to avoid taking the RCU read lock when checking the validity of a vnode's callback state. The only thing it's needed for is to pin the parent volume's server list whilst we search it to find the record of the server we're currently using to see if it has been reinitialised (ie. it sent us a CB.InitCallBackState* RPC). Do this by the following means: (1) Keep an additional per-cell counter (fs_s_break) that's incremented each time any of the fileservers in the cell reinitialises. Since the new counter can be accessed without RCU from the vnode, we can check that first - and only if it differs, get the RCU read lock and check the volume's server list. (2) Replace afs_get_s_break_rcu() with afs_check_server_good() which now indicates whether the callback promise is still expected to be present on the server. This does the checks as described in (1). (3) Restructure afs_check_validity() to take account of the change in (2). We can also get rid of the valid variable and just use the need_clear variable with the addition of the afs_cb_break_no_promise reason. (4) afs_check_validity() probably shouldn't be altering vnode->cb_v_break and vnode->cb_s_break when it doesn't have cb_lock exclusively locked. Move the change to vnode->cb_v_break to __afs_break_callback(). Delegate the change to vnode->cb_s_break to afs_select_fileserver() and set vnode->cb_fs_s_break there also. (5) afs_validate() no longer needs to get the RCU read lock around its call to afs_check_validity() - and can skip the call entirely if we don't have a promise. Signed-off-by: David Howells Tested-by: Markus Suvanto cc: linux-afs@lists.infradead.org Link: https://lore.kernel.org/r/163111669583.283156.1397603105683094563.stgit@warthog.procyon.org.uk/ --- include/trace/events/afs.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include') diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h index 9f73ed2cf061..bca73e8c8cde 100644 --- a/include/trace/events/afs.h +++ b/include/trace/events/afs.h @@ -306,11 +306,13 @@ enum afs_flock_operation { enum afs_cb_break_reason { afs_cb_break_no_break, + afs_cb_break_no_promise, afs_cb_break_for_callback, afs_cb_break_for_deleted, afs_cb_break_for_lapsed, + afs_cb_break_for_s_reinit, afs_cb_break_for_unlink, - afs_cb_break_for_vsbreak, + afs_cb_break_for_v_break, afs_cb_break_for_volume_callback, afs_cb_break_for_zap, }; @@ -602,11 +604,13 @@ enum afs_cb_break_reason { #define afs_cb_break_reasons \ EM(afs_cb_break_no_break, "no-break") \ + EM(afs_cb_break_no_promise, "no-promise") \ EM(afs_cb_break_for_callback, "break-cb") \ EM(afs_cb_break_for_deleted, "break-del") \ EM(afs_cb_break_for_lapsed, "break-lapsed") \ + EM(afs_cb_break_for_s_reinit, "s-reinit") \ EM(afs_cb_break_for_unlink, "break-unlink") \ - EM(afs_cb_break_for_vsbreak, "break-vs") \ + EM(afs_cb_break_for_v_break, "break-v") \ EM(afs_cb_break_for_volume_callback, "break-v-cb") \ E_(afs_cb_break_for_zap, "break-zap") -- 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') 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 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') 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 81065b35e2486c024c7aa86caed452e1f01a59d4 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Mon, 13 Sep 2021 14:52:39 -0700 Subject: x86/mce: Avoid infinite loop for copy from user recovery There are two cases for machine check recovery: 1) The machine check was triggered by ring3 (application) code. This is the simpler case. The machine check handler simply queues work to be executed on return to user. That code unmaps the page from all users and arranges to send a SIGBUS to the task that triggered the poison. 2) The machine check was triggered in kernel code that is covered by an exception table entry. In this case the machine check handler still queues a work entry to unmap the page, etc. but this will not be called right away because the #MC handler returns to the fix up code address in the exception table entry. Problems occur if the kernel triggers another machine check before the return to user processes the first queued work item. Specifically, the work is queued using the ->mce_kill_me callback structure in the task struct for the current thread. Attempting to queue a second work item using this same callback results in a loop in the linked list of work functions to call. So when the kernel does return to user, it enters an infinite loop processing the same entry for ever. There are some legitimate scenarios where the kernel may take a second machine check before returning to the user. 1) Some code (e.g. futex) first tries a get_user() with page faults disabled. If this fails, the code retries with page faults enabled expecting that this will resolve the page fault. 2) Copy from user code retries a copy in byte-at-time mode to check whether any additional bytes can be copied. On the other side of the fence are some bad drivers that do not check the return value from individual get_user() calls and may access multiple user addresses without noticing that some/all calls have failed. Fix by adding a counter (current->mce_count) to keep track of repeated machine checks before task_work() is called. First machine check saves the address information and calls task_work_add(). Subsequent machine checks before that task_work call back is executed check that the address is in the same page as the first machine check (since the callback will offline exactly one page). Expected worst case is four machine checks before moving on (e.g. one user access with page faults disabled, then a repeat to the same address with page faults enabled ... repeat in copy tail bytes). Just in case there is some code that loops forever enforce a limit of 10. [ bp: Massage commit message, drop noinstr, fix typo, extend panic messages. ] Fixes: 5567d11c21a1 ("x86/mce: Send #MC singal from task work") Signed-off-by: Tony Luck Signed-off-by: Borislav Petkov Cc: Link: https://lkml.kernel.org/r/YT/IJ9ziLqmtqEPu@agluck-desk2.amr.corp.intel.com --- arch/x86/kernel/cpu/mce/core.c | 43 +++++++++++++++++++++++++++++++----------- include/linux/sched.h | 1 + 2 files changed, 33 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index 8cb7816d03b4..193204aee880 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -1253,6 +1253,9 @@ static void __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *fin static void kill_me_now(struct callback_head *ch) { + struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me); + + p->mce_count = 0; force_sig(SIGBUS); } @@ -1262,6 +1265,7 @@ static void kill_me_maybe(struct callback_head *cb) int flags = MF_ACTION_REQUIRED; int ret; + p->mce_count = 0; pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); if (!p->mce_ripv) @@ -1290,17 +1294,34 @@ static void kill_me_maybe(struct callback_head *cb) } } -static void queue_task_work(struct mce *m, int kill_current_task) +static void queue_task_work(struct mce *m, char *msg, int kill_current_task) { - current->mce_addr = m->addr; - current->mce_kflags = m->kflags; - current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); - current->mce_whole_page = whole_page(m); + int count = ++current->mce_count; - if (kill_current_task) - current->mce_kill_me.func = kill_me_now; - else - current->mce_kill_me.func = kill_me_maybe; + /* First call, save all the details */ + if (count == 1) { + current->mce_addr = m->addr; + current->mce_kflags = m->kflags; + current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(m); + + if (kill_current_task) + current->mce_kill_me.func = kill_me_now; + else + current->mce_kill_me.func = kill_me_maybe; + } + + /* Ten is likely overkill. Don't expect more than two faults before task_work() */ + if (count > 10) + mce_panic("Too many consecutive machine checks while accessing user data", m, msg); + + /* Second or later call, make sure page address matches the one from first call */ + if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT)) + mce_panic("Consecutive machine checks to different user pages", m, msg); + + /* Do not call task_work_add() more than once */ + if (count > 1) + return; task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); } @@ -1438,7 +1459,7 @@ noinstr void do_machine_check(struct pt_regs *regs) /* If this triggers there is no way to recover. Die hard. */ BUG_ON(!on_thread_stack() || !user_mode(regs)); - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } else { /* @@ -1456,7 +1477,7 @@ noinstr void do_machine_check(struct pt_regs *regs) } if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, kill_current_task); + queue_task_work(&m, msg, kill_current_task); } out: mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); diff --git a/include/linux/sched.h b/include/linux/sched.h index 1780260f237b..361c7bc72cbb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1468,6 +1468,7 @@ struct task_struct { mce_whole_page : 1, __mce_reserved : 62; struct callback_head mce_kill_me; + int mce_count; #endif #ifdef CONFIG_KRETPROBES -- cgit v1.2.3 From 8fb0f47a9d7acf620d0fd97831b69da9bc5e22ed Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:18:36 -0600 Subject: iov_iter: add helper to save iov_iter state In an ideal world, when someone is passed an iov_iter and returns X bytes, then X bytes would have been consumed/advanced from the iov_iter. But we have use cases that always consume the entire iterator, a few examples of that are iomap and bdev O_DIRECT. This means we cannot rely on the state of the iov_iter once we've called ->read_iter() or ->write_iter(). This would be easier if we didn't always have to deal with truncate of the iov_iter, as rewinding would be trivial without that. We recently added a commit to track the truncate state, but that grew the iov_iter by 8 bytes and wasn't the best solution. Implement a helper to save enough of the iov_iter state to sanely restore it after we've called the read/write iterator helpers. This currently only works for IOVEC/BVEC/KVEC as that's all we need, support for other iterator types are left as an exercise for the reader. Link: https://lore.kernel.org/linux-fsdevel/CAHk-=wiacKV4Gh-MYjteU0LwNBSGpWrK-Ov25HdqB1ewinrFPg@mail.gmail.com/ Signed-off-by: Jens Axboe --- include/linux/uio.h | 15 +++++++++++++++ lib/iov_iter.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 51 insertions(+) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 5265024e8b90..984c4ab74859 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -27,6 +27,12 @@ enum iter_type { ITER_DISCARD, }; +struct iov_iter_state { + size_t iov_offset; + size_t count; + unsigned long nr_segs; +}; + struct iov_iter { u8 iter_type; bool data_source; @@ -55,6 +61,14 @@ static inline enum iter_type iov_iter_type(const struct iov_iter *i) return i->iter_type; } +static inline void iov_iter_save_state(struct iov_iter *iter, + struct iov_iter_state *state) +{ + state->iov_offset = iter->iov_offset; + state->count = iter->count; + state->nr_segs = iter->nr_segs; +} + static inline bool iter_is_iovec(const struct iov_iter *i) { return iov_iter_type(i) == ITER_IOVEC; @@ -233,6 +247,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, struct page ***pages, size_t maxsize, size_t *start); int iov_iter_npages(const struct iov_iter *i, int maxpages); +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index f2d50d69a6c3..755c10c5138c 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1972,3 +1972,39 @@ int import_single_range(int rw, void __user *buf, size_t len, return 0; } EXPORT_SYMBOL(import_single_range); + +/** + * iov_iter_restore() - Restore a &struct iov_iter to the same state as when + * iov_iter_save_state() was called. + * + * @i: &struct iov_iter to restore + * @state: state to restore from + * + * Used after iov_iter_save_state() to bring restore @i, if operations may + * have advanced it. + * + * Note: only works on ITER_IOVEC, ITER_BVEC, and ITER_KVEC + */ +void iov_iter_restore(struct iov_iter *i, struct iov_iter_state *state) +{ + if (WARN_ON_ONCE(!iov_iter_is_bvec(i) && !iter_is_iovec(i)) && + !iov_iter_is_kvec(i)) + return; + i->iov_offset = state->iov_offset; + i->count = state->count; + /* + * For the *vec iters, nr_segs + iov is constant - if we increment + * the vec, then we also decrement the nr_segs count. Hence we don't + * need to track both of these, just one is enough and we can deduct + * the other from that. ITER_KVEC and ITER_IOVEC are the same struct + * size, so we can just increment the iov pointer as they are unionzed. + * ITER_BVEC _may_ be the same size on some archs, but on others it is + * not. Be safe and handle it separately. + */ + BUILD_BUG_ON(sizeof(struct iovec) != sizeof(struct kvec)); + if (iov_iter_is_bvec(i)) + i->bvec -= state->nr_segs - i->nr_segs; + else + i->iov -= state->nr_segs - i->nr_segs; + i->nr_segs = state->nr_segs; +} -- cgit v1.2.3 From 7dedd3e18077f996a10c47250ac85d080e5f474e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 10 Sep 2021 11:19:58 -0600 Subject: Revert "iov_iter: track truncated size" This reverts commit 2112ff5ce0c1128fe7b4d19cfe7f2b8ce5b595fa. We no longer need to track the truncation count, the one user that did need it has been converted to using iov_iter_restore() instead. Signed-off-by: Jens Axboe --- include/linux/uio.h | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/uio.h b/include/linux/uio.h index 984c4ab74859..207101a9c5c3 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -53,7 +53,6 @@ struct iov_iter { }; loff_t xarray_start; }; - size_t truncated; }; static inline enum iter_type iov_iter_type(const struct iov_iter *i) @@ -270,10 +269,8 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) * conversion in assignement is by definition greater than all * values of size_t, including old i->count. */ - if (i->count > count) { - i->truncated += i->count - count; + if (i->count > count) i->count = count; - } } /* @@ -282,7 +279,6 @@ static inline void iov_iter_truncate(struct iov_iter *i, u64 count) */ static inline void iov_iter_reexpand(struct iov_iter *i, size_t count) { - i->truncated -= count - i->count; i->count = count; } -- cgit v1.2.3 From 3c9cfb5269f76d447dbadb67835368f3111a91d7 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 14:17:35 +0300 Subject: net: update NXP copyright text NXP Legal insists that the following are not fine: - Saying "NXP Semiconductors" instead of "NXP", since the company's registered name is "NXP" - Putting a "(c)" sign in the copyright string - Putting a comma in the copyright string The only accepted copyright string format is "Copyright NXP". This patch changes the copyright headers in the networking files that were sent by me, or derived from code sent by me. Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/ocelot/felix.c | 2 +- drivers/net/dsa/ocelot/felix.h | 2 +- drivers/net/dsa/ocelot/felix_vsc9959.c | 2 +- drivers/net/dsa/sja1105/sja1105_clocking.c | 2 +- drivers/net/dsa/sja1105/sja1105_devlink.c | 2 +- drivers/net/dsa/sja1105/sja1105_flower.c | 2 +- drivers/net/dsa/sja1105/sja1105_mdio.c | 2 +- drivers/net/dsa/sja1105/sja1105_spi.c | 2 +- drivers/net/dsa/sja1105/sja1105_static_config.c | 2 +- drivers/net/dsa/sja1105/sja1105_static_config.h | 2 +- drivers/net/dsa/sja1105/sja1105_vl.c | 2 +- drivers/net/dsa/sja1105/sja1105_vl.h | 2 +- drivers/net/ethernet/freescale/enetc/enetc_ierb.c | 2 +- drivers/net/ethernet/freescale/enetc/enetc_ierb.h | 2 +- drivers/net/ethernet/mscc/ocelot_devlink.c | 2 +- drivers/net/ethernet/mscc/ocelot_mrp.c | 2 +- drivers/net/ethernet/mscc/ocelot_net.c | 2 +- drivers/net/pcs/pcs-xpcs-nxp.c | 2 +- include/linux/dsa/ocelot.h | 2 +- include/linux/packing.h | 2 +- lib/packing.c | 2 +- net/dsa/tag_ocelot.c | 2 +- net/dsa/tag_ocelot_8021q.c | 2 +- tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh | 2 +- 24 files changed, 24 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c index 3656e67af789..a3a9636430d6 100644 --- a/drivers/net/dsa/ocelot/felix.c +++ b/drivers/net/dsa/ocelot/felix.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019-2021 NXP Semiconductors +/* Copyright 2019-2021 NXP * * This is an umbrella module for all network switches that are * register-compatible with Ocelot and that perform I/O to their host CPU diff --git a/drivers/net/dsa/ocelot/felix.h b/drivers/net/dsa/ocelot/felix.h index 5854bab43327..54024b6f9498 100644 --- a/drivers/net/dsa/ocelot/felix.h +++ b/drivers/net/dsa/ocelot/felix.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019 NXP */ #ifndef _MSCC_FELIX_H #define _MSCC_FELIX_H diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index f966a253d1c7..9e2ac8e46619 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) /* Copyright 2017 Microsemi Corporation - * Copyright 2018-2019 NXP Semiconductors + * Copyright 2018-2019 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_clocking.c b/drivers/net/dsa/sja1105/sja1105_clocking.c index 387a1f2f161c..5bbf1707f2af 100644 --- a/drivers/net/dsa/sja1105/sja1105_clocking.c +++ b/drivers/net/dsa/sja1105/sja1105_clocking.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include diff --git a/drivers/net/dsa/sja1105/sja1105_devlink.c b/drivers/net/dsa/sja1105/sja1105_devlink.c index 05c7f4ca3b1a..0569ff066634 100644 --- a/drivers/net/dsa/sja1105/sja1105_devlink.c +++ b/drivers/net/dsa/sja1105/sja1105_devlink.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2018-2019, Vladimir Oltean - * Copyright 2020 NXP Semiconductors + * Copyright 2020 NXP */ #include "sja1105.h" diff --git a/drivers/net/dsa/sja1105/sja1105_flower.c b/drivers/net/dsa/sja1105/sja1105_flower.c index 6c10ffa968ce..72b9b39b0989 100644 --- a/drivers/net/dsa/sja1105/sja1105_flower.c +++ b/drivers/net/dsa/sja1105/sja1105_flower.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #include "sja1105.h" #include "sja1105_vl.h" diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c index 705d3900e43a..215dd17ca790 100644 --- a/drivers/net/dsa/sja1105/sja1105_mdio.c +++ b/drivers/net/dsa/sja1105/sja1105_mdio.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2021, NXP Semiconductors +/* Copyright 2021 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_spi.c b/drivers/net/dsa/sja1105/sja1105_spi.c index d60a530d0272..d3c9ad6d39d4 100644 --- a/drivers/net/dsa/sja1105/sja1105_spi.c +++ b/drivers/net/dsa/sja1105/sja1105_spi.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018, Sensor-Technik Wiedemann GmbH * Copyright (c) 2018-2019, Vladimir Oltean */ diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c index 7a422ef4deb6..baba204ad62f 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.c +++ b/drivers/net/dsa/sja1105/sja1105_static_config.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include "sja1105_static_config.h" diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.h b/drivers/net/dsa/sja1105/sja1105_static_config.h index bce0f5c03d0b..6a372d5f22ae 100644 --- a/drivers/net/dsa/sja1105/sja1105_static_config.h +++ b/drivers/net/dsa/sja1105/sja1105_static_config.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: BSD-3-Clause */ -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #ifndef _SJA1105_STATIC_CONFIG_H diff --git a/drivers/net/dsa/sja1105/sja1105_vl.c b/drivers/net/dsa/sja1105/sja1105_vl.c index ec7b65daec20..6802f4057cc0 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.c +++ b/drivers/net/dsa/sja1105/sja1105_vl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #include #include diff --git a/drivers/net/dsa/sja1105/sja1105_vl.h b/drivers/net/dsa/sja1105/sja1105_vl.h index 173d78963fed..51fba0dce91a 100644 --- a/drivers/net/dsa/sja1105/sja1105_vl.h +++ b/drivers/net/dsa/sja1105/sja1105_vl.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright 2020, NXP Semiconductors +/* Copyright 2020 NXP */ #ifndef _SJA1105_VL_H #define _SJA1105_VL_H diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c index ee1468e3eaa3..91f02c505028 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) -/* Copyright 2021 NXP Semiconductors +/* Copyright 2021 NXP * * The Integrated Endpoint Register Block (IERB) is configured by pre-boot * software and is supposed to be to ENETC what a NVRAM is to a 'real' PCIe diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ierb.h b/drivers/net/ethernet/freescale/enetc/enetc_ierb.h index b3b774e0998a..c2ce47c4be9f 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_ierb.h +++ b/drivers/net/ethernet/freescale/enetc/enetc_ierb.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ -/* Copyright 2021 NXP Semiconductors */ +/* Copyright 2021 NXP */ #include #include diff --git a/drivers/net/ethernet/mscc/ocelot_devlink.c b/drivers/net/ethernet/mscc/ocelot_devlink.c index edafbd37d12c..b8737efd2a85 100644 --- a/drivers/net/ethernet/mscc/ocelot_devlink.c +++ b/drivers/net/ethernet/mscc/ocelot_devlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: (GPL-2.0 OR MIT) -/* Copyright 2020-2021 NXP Semiconductors +/* Copyright 2020-2021 NXP */ #include #include "ocelot.h" diff --git a/drivers/net/ethernet/mscc/ocelot_mrp.c b/drivers/net/ethernet/mscc/ocelot_mrp.c index 08b481a93460..4b0941f09f71 100644 --- a/drivers/net/ethernet/mscc/ocelot_mrp.c +++ b/drivers/net/ethernet/mscc/ocelot_mrp.c @@ -2,7 +2,7 @@ /* Microsemi Ocelot Switch driver * * Copyright (c) 2017, 2019 Microsemi Corporation - * Copyright 2020-2021 NXP Semiconductors + * Copyright 2020-2021 NXP */ #include diff --git a/drivers/net/ethernet/mscc/ocelot_net.c b/drivers/net/ethernet/mscc/ocelot_net.c index c0c465a4a981..e54b9fb2a97a 100644 --- a/drivers/net/ethernet/mscc/ocelot_net.c +++ b/drivers/net/ethernet/mscc/ocelot_net.c @@ -5,7 +5,7 @@ * mscc_ocelot_switch_lib. * * Copyright (c) 2017, 2019 Microsemi Corporation - * Copyright 2020-2021 NXP Semiconductors + * Copyright 2020-2021 NXP */ #include diff --git a/drivers/net/pcs/pcs-xpcs-nxp.c b/drivers/net/pcs/pcs-xpcs-nxp.c index 984c9f7f16a8..d16fc58cd48d 100644 --- a/drivers/net/pcs/pcs-xpcs-nxp.c +++ b/drivers/net/pcs/pcs-xpcs-nxp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2021 NXP Semiconductors +/* Copyright 2021 NXP */ #include #include "pcs-xpcs.h" diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h index c6bc45ae5e03..435777a0073c 100644 --- a/include/linux/dsa/ocelot.h +++ b/include/linux/dsa/ocelot.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 - * Copyright 2019-2021 NXP Semiconductors + * Copyright 2019-2021 NXP */ #ifndef _NET_DSA_TAG_OCELOT_H diff --git a/include/linux/packing.h b/include/linux/packing.h index 54667735cc67..8d6571feb95d 100644 --- a/include/linux/packing.h +++ b/include/linux/packing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: BSD-3-Clause - * Copyright (c) 2016-2018, NXP Semiconductors + * Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #ifndef _LINUX_PACKING_H diff --git a/lib/packing.c b/lib/packing.c index 6ed72dccfdb5..9a72f4bbf0e2 100644 --- a/lib/packing.c +++ b/lib/packing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 -/* Copyright (c) 2016-2018, NXP Semiconductors +/* Copyright 2016-2018 NXP * Copyright (c) 2018-2019, Vladimir Oltean */ #include diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c index d37ab98e7fe1..8025ed778d33 100644 --- a/net/dsa/tag_ocelot.c +++ b/net/dsa/tag_ocelot.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2019 NXP Semiconductors +/* Copyright 2019 NXP */ #include #include diff --git a/net/dsa/tag_ocelot_8021q.c b/net/dsa/tag_ocelot_8021q.c index 3038a257ba05..59072930cb02 100644 --- a/net/dsa/tag_ocelot_8021q.c +++ b/net/dsa/tag_ocelot_8021q.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright 2020-2021 NXP Semiconductors +/* Copyright 2020-2021 NXP * * An implementation of the software-defined tag_8021q.c tagger format, which * also preserves full functionality under a vlan_filtering bridge. It does diff --git a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh index beee0d5646a6..f7d84549cc3e 100755 --- a/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh +++ b/tools/testing/selftests/drivers/net/ocelot/tc_flower_chains.sh @@ -1,6 +1,6 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 -# Copyright 2020 NXP Semiconductors +# Copyright 2020 NXP WAIT_TIME=1 NUM_NETIFS=4 -- cgit v1.2.3 From cf9579976f724ad517cc15b7caadea728c7e245c Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:32 +0300 Subject: net: mdio: introduce a shutdown method to mdio device drivers MDIO-attached devices might have interrupts and other things that might need quiesced when we kexec into a new kernel. Things are even more creepy when those interrupt lines are shared, and in that case it is absolutely mandatory to disable all interrupt sources. Moreover, MDIO devices might be DSA switches, and DSA needs its own shutdown method to unlink from the DSA master, which is a new requirement that appeared after commit 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings"). So introduce a ->shutdown method in the MDIO device driver structure. Signed-off-by: Vladimir Oltean Reviewed-by: Andrew Lunn Reviewed-by: Florian Fainelli Signed-off-by: David S. Miller --- drivers/net/phy/mdio_device.c | 11 +++++++++++ include/linux/mdio.h | 3 +++ 2 files changed, 14 insertions(+) (limited to 'include') diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c index c94cb5382dc9..250742ffdfd9 100644 --- a/drivers/net/phy/mdio_device.c +++ b/drivers/net/phy/mdio_device.c @@ -179,6 +179,16 @@ static int mdio_remove(struct device *dev) return 0; } +static void mdio_shutdown(struct device *dev) +{ + struct mdio_device *mdiodev = to_mdio_device(dev); + struct device_driver *drv = mdiodev->dev.driver; + struct mdio_driver *mdiodrv = to_mdio_driver(drv); + + if (mdiodrv->shutdown) + mdiodrv->shutdown(mdiodev); +} + /** * mdio_driver_register - register an mdio_driver with the MDIO layer * @drv: new mdio_driver to register @@ -193,6 +203,7 @@ int mdio_driver_register(struct mdio_driver *drv) mdiodrv->driver.bus = &mdio_bus_type; mdiodrv->driver.probe = mdio_probe; mdiodrv->driver.remove = mdio_remove; + mdiodrv->driver.shutdown = mdio_shutdown; retval = driver_register(&mdiodrv->driver); if (retval) { diff --git a/include/linux/mdio.h b/include/linux/mdio.h index ffb787d5ebde..5e6dc38f418e 100644 --- a/include/linux/mdio.h +++ b/include/linux/mdio.h @@ -80,6 +80,9 @@ struct mdio_driver { /* Clears up any memory if needed */ void (*remove)(struct mdio_device *mdiodev); + + /* Quiesces the device on system shutdown, turns off interrupts etc */ + void (*shutdown)(struct mdio_device *mdiodev); }; static inline struct mdio_driver * -- cgit v1.2.3 From 0650bf52b31ff35dc6430fc2e37969c36baba724 Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 16:34:33 +0300 Subject: net: dsa: be compatible with masters which unregister on shutdown Lino reports that on his system with bcmgenet as DSA master and KSZ9897 as a switch, rebooting or shutting down never works properly. What does the bcmgenet driver have special to trigger this, that other DSA masters do not? It has an implementation of ->shutdown which simply calls its ->remove implementation. Otherwise said, it unregisters its network interface on shutdown. This message can be seen in a loop, and it hangs the reboot process there: unregister_netdevice: waiting for eth0 to become free. Usage count = 3 So why 3? A usage count of 1 is normal for a registered network interface, and any virtual interface which links itself as an upper of that will increment it via dev_hold. In the case of DSA, this is the call path: dsa_slave_create -> netdev_upper_dev_link -> __netdev_upper_dev_link -> __netdev_adjacent_dev_insert -> dev_hold So a DSA switch with 3 interfaces will result in a usage count elevated by two, and netdev_wait_allrefs will wait until they have gone away. Other stacked interfaces, like VLAN, watch NETDEV_UNREGISTER events and delete themselves, but DSA cannot just vanish and go poof, at most it can unbind itself from the switch devices, but that must happen strictly earlier compared to when the DSA master unregisters its net_device, so reacting on the NETDEV_UNREGISTER event is way too late. It seems that it is a pretty established pattern to have a driver's ->shutdown hook redirect to its ->remove hook, so the same code is executed regardless of whether the driver is unbound from the device, or the system is just shutting down. As Florian puts it, it is quite a big hammer for bcmgenet to unregister its net_device during shutdown, but having a common code path with the driver unbind helps ensure it is well tested. So DSA, for better or for worse, has to live with that and engage in an arms race of implementing the ->shutdown hook too, from all individual drivers, and do something sane when paired with masters that unregister their net_device there. The only sane thing to do, of course, is to unlink from the master. However, complications arise really quickly. The pattern of redirecting ->shutdown to ->remove is not unique to bcmgenet or even to net_device drivers. In fact, SPI controllers do it too (see dspi_shutdown -> dspi_remove), and presumably, I2C controllers and MDIO controllers do it too (this is something I have not researched too deeply, but even if this is not the case today, it is certainly plausible to happen in the future, and must be taken into consideration). Since DSA switches might be SPI devices, I2C devices, MDIO devices, the insane implication is that for the exact same DSA switch device, we might have both ->shutdown and ->remove getting called. So we need to do something with that insane environment. The pattern I've come up with is "if this, then not that", so if either ->shutdown or ->remove gets called, we set the device's drvdata to NULL, and in the other hook, we check whether the drvdata is NULL and just do nothing. This is probably not necessary for platform devices, just for devices on buses, but I would really insist for consistency among drivers, because when code is copy-pasted, it is not always copy-pasted from the best sources. So depending on whether the DSA switch's ->remove or ->shutdown will get called first, we cannot really guarantee even for the same driver if rebooting will result in the same code path on all platforms. But nonetheless, we need to do something minimally reasonable on ->shutdown too to fix the bug. Of course, the ->remove will do more (a full teardown of the tree, with all data structures freed, and this is why the bug was not caught for so long). The new ->shutdown method is kept separate from dsa_unregister_switch not because we couldn't have unregistered the switch, but simply in the interest of doing something quick and to the point. The big question is: does the DSA switch's ->shutdown get called earlier than the DSA master's ->shutdown? If not, there is still a risk that we might still trigger the WARN_ON in unregister_netdevice that says we are attempting to unregister a net_device which has uppers. That's no good. Although the reference to the master net_device won't physically go away even if DSA's ->shutdown comes afterwards, remember we have a dev_hold on it. The answer to that question lies in this comment above device_link_add: * A side effect of the link creation is re-ordering of dpm_list and the * devices_kset list by moving the consumer device and all devices depending * on it to the ends of these lists (that does not happen to devices that have * not been registered when this function is called). so the fact that DSA uses device_link_add towards its master is not exactly for nothing. device_shutdown() walks devices_kset from the back, so this is our guarantee that DSA's shutdown happens before the master's shutdown. Fixes: 2f1e8ea726e9 ("net: dsa: link interfaces with the DSA master to get rid of lockdep warnings") Link: https://lore.kernel.org/netdev/20210909095324.12978-1-LinoSanfilippo@gmx.de/ Reported-by: Lino Sanfilippo Signed-off-by: Vladimir Oltean Tested-by: Andrew Lunn Signed-off-by: David S. Miller --- drivers/net/dsa/b53/b53_mdio.c | 21 +++++++++++-- drivers/net/dsa/b53/b53_mmap.c | 13 ++++++++ drivers/net/dsa/b53/b53_priv.h | 5 +++ drivers/net/dsa/b53/b53_spi.c | 13 ++++++++ drivers/net/dsa/b53/b53_srab.c | 21 +++++++++++-- drivers/net/dsa/bcm_sf2.c | 12 +++++++ drivers/net/dsa/dsa_loop.c | 22 ++++++++++++- drivers/net/dsa/lan9303-core.c | 6 ++++ drivers/net/dsa/lan9303.h | 1 + drivers/net/dsa/lan9303_i2c.c | 24 +++++++++++--- drivers/net/dsa/lan9303_mdio.c | 15 +++++++++ drivers/net/dsa/lantiq_gswip.c | 18 +++++++++++ drivers/net/dsa/microchip/ksz8795_spi.c | 11 ++++++- drivers/net/dsa/microchip/ksz9477_i2c.c | 14 +++++++-- drivers/net/dsa/microchip/ksz9477_spi.c | 8 +++-- drivers/net/dsa/mt7530.c | 18 +++++++++++ drivers/net/dsa/mv88e6060.c | 18 +++++++++++ drivers/net/dsa/mv88e6xxx/chip.c | 22 ++++++++++++- drivers/net/dsa/ocelot/felix_vsc9959.c | 20 ++++++++++-- drivers/net/dsa/ocelot/seville_vsc9953.c | 20 ++++++++++-- drivers/net/dsa/qca/ar9331.c | 18 +++++++++++ drivers/net/dsa/qca8k.c | 18 +++++++++++ drivers/net/dsa/realtek-smi-core.c | 20 +++++++++++- drivers/net/dsa/sja1105/sja1105_main.c | 21 +++++++++++-- drivers/net/dsa/vitesse-vsc73xx-core.c | 6 ++++ drivers/net/dsa/vitesse-vsc73xx-platform.c | 22 ++++++++++++- drivers/net/dsa/vitesse-vsc73xx-spi.c | 22 ++++++++++++- drivers/net/dsa/vitesse-vsc73xx.h | 1 + include/net/dsa.h | 1 + net/dsa/dsa2.c | 50 ++++++++++++++++++++++++++++++ 30 files changed, 457 insertions(+), 24 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c index a533a90e3904..a7aeb3c132c9 100644 --- a/drivers/net/dsa/b53/b53_mdio.c +++ b/drivers/net/dsa/b53/b53_mdio.c @@ -351,9 +351,25 @@ static int b53_mdio_probe(struct mdio_device *mdiodev) static void b53_mdio_remove(struct mdio_device *mdiodev) { struct b53_device *dev = dev_get_drvdata(&mdiodev->dev); - struct dsa_switch *ds = dev->ds; - dsa_unregister_switch(ds); + if (!dev) + return; + + b53_switch_remove(dev); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void b53_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct b53_device *dev = dev_get_drvdata(&mdiodev->dev); + + if (!dev) + return; + + b53_switch_shutdown(dev); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id b53_of_match[] = { @@ -373,6 +389,7 @@ MODULE_DEVICE_TABLE(of, b53_of_match); static struct mdio_driver b53_mdio_driver = { .probe = b53_mdio_probe, .remove = b53_mdio_remove, + .shutdown = b53_mdio_shutdown, .mdiodrv.driver = { .name = "bcm53xx", .of_match_table = b53_of_match, diff --git a/drivers/net/dsa/b53/b53_mmap.c b/drivers/net/dsa/b53/b53_mmap.c index 82680e083cc2..ae4c79d39bc0 100644 --- a/drivers/net/dsa/b53/b53_mmap.c +++ b/drivers/net/dsa/b53/b53_mmap.c @@ -316,9 +316,21 @@ static int b53_mmap_remove(struct platform_device *pdev) if (dev) b53_switch_remove(dev); + platform_set_drvdata(pdev, NULL); + return 0; } +static void b53_mmap_shutdown(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + + if (dev) + b53_switch_shutdown(dev); + + platform_set_drvdata(pdev, NULL); +} + static const struct of_device_id b53_mmap_of_table[] = { { .compatible = "brcm,bcm3384-switch" }, { .compatible = "brcm,bcm6328-switch" }, @@ -331,6 +343,7 @@ MODULE_DEVICE_TABLE(of, b53_mmap_of_table); static struct platform_driver b53_mmap_driver = { .probe = b53_mmap_probe, .remove = b53_mmap_remove, + .shutdown = b53_mmap_shutdown, .driver = { .name = "b53-switch", .of_match_table = b53_mmap_of_table, diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 5d068acf7cf8..959a52d41f0a 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -228,6 +228,11 @@ static inline void b53_switch_remove(struct b53_device *dev) dsa_unregister_switch(dev->ds); } +static inline void b53_switch_shutdown(struct b53_device *dev) +{ + dsa_switch_shutdown(dev->ds); +} + #define b53_build_op(type_op_size, val_type) \ static inline int b53_##type_op_size(struct b53_device *dev, u8 page, \ u8 reg, val_type val) \ diff --git a/drivers/net/dsa/b53/b53_spi.c b/drivers/net/dsa/b53/b53_spi.c index ecb9f7f6b335..01e37b75471e 100644 --- a/drivers/net/dsa/b53/b53_spi.c +++ b/drivers/net/dsa/b53/b53_spi.c @@ -321,9 +321,21 @@ static int b53_spi_remove(struct spi_device *spi) if (dev) b53_switch_remove(dev); + spi_set_drvdata(spi, NULL); + return 0; } +static void b53_spi_shutdown(struct spi_device *spi) +{ + struct b53_device *dev = spi_get_drvdata(spi); + + if (dev) + b53_switch_shutdown(dev); + + spi_set_drvdata(spi, NULL); +} + static const struct of_device_id b53_spi_of_match[] = { { .compatible = "brcm,bcm5325" }, { .compatible = "brcm,bcm5365" }, @@ -344,6 +356,7 @@ static struct spi_driver b53_spi_driver = { }, .probe = b53_spi_probe, .remove = b53_spi_remove, + .shutdown = b53_spi_shutdown, }; module_spi_driver(b53_spi_driver); diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c index 3f4249de70c5..4591bb1c05d2 100644 --- a/drivers/net/dsa/b53/b53_srab.c +++ b/drivers/net/dsa/b53/b53_srab.c @@ -629,17 +629,34 @@ static int b53_srab_probe(struct platform_device *pdev) static int b53_srab_remove(struct platform_device *pdev) { struct b53_device *dev = platform_get_drvdata(pdev); - struct b53_srab_priv *priv = dev->priv; - b53_srab_intr_set(priv, false); + if (!dev) + return 0; + + b53_srab_intr_set(dev->priv, false); b53_switch_remove(dev); + platform_set_drvdata(pdev, NULL); + return 0; } +static void b53_srab_shutdown(struct platform_device *pdev) +{ + struct b53_device *dev = platform_get_drvdata(pdev); + + if (!dev) + return; + + b53_switch_shutdown(dev); + + platform_set_drvdata(pdev, NULL); +} + static struct platform_driver b53_srab_driver = { .probe = b53_srab_probe, .remove = b53_srab_remove, + .shutdown = b53_srab_shutdown, .driver = { .name = "b53-srab-switch", .of_match_table = b53_srab_of_match, diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index b6c4b3adb171..7578a5c38df5 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -1512,6 +1512,9 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) { struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); + if (!priv) + return 0; + priv->wol_ports_mask = 0; /* Disable interrupts */ bcm_sf2_intr_disable(priv); @@ -1523,6 +1526,8 @@ static int bcm_sf2_sw_remove(struct platform_device *pdev) if (priv->type == BCM7278_DEVICE_ID) reset_control_assert(priv->rcdev); + platform_set_drvdata(pdev, NULL); + return 0; } @@ -1530,6 +1535,9 @@ static void bcm_sf2_sw_shutdown(struct platform_device *pdev) { struct bcm_sf2_priv *priv = platform_get_drvdata(pdev); + if (!priv) + return; + /* For a kernel about to be kexec'd we want to keep the GPHY on for a * successful MDIO bus scan to occur. If we did turn off the GPHY * before (e.g: port_disable), this will also power it back on. @@ -1538,6 +1546,10 @@ static void bcm_sf2_sw_shutdown(struct platform_device *pdev) */ if (priv->hw_params.num_gphy == 1) bcm_sf2_gphy_enable_set(priv->dev->ds, true); + + dsa_switch_shutdown(priv->dev->ds); + + platform_set_drvdata(pdev, NULL); } #ifdef CONFIG_PM_SLEEP diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index bfdf3324aac3..e638e3eea911 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -340,10 +340,29 @@ static int dsa_loop_drv_probe(struct mdio_device *mdiodev) static void dsa_loop_drv_remove(struct mdio_device *mdiodev) { struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); - struct dsa_loop_priv *ps = ds->priv; + struct dsa_loop_priv *ps; + + if (!ds) + return; + + ps = ds->priv; dsa_unregister_switch(ds); dev_put(ps->netdev); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void dsa_loop_drv_shutdown(struct mdio_device *mdiodev) +{ + struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + + if (!ds) + return; + + dsa_switch_shutdown(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static struct mdio_driver dsa_loop_drv = { @@ -352,6 +371,7 @@ static struct mdio_driver dsa_loop_drv = { }, .probe = dsa_loop_drv_probe, .remove = dsa_loop_drv_remove, + .shutdown = dsa_loop_drv_shutdown, }; #define NUM_FIXED_PHYS (DSA_LOOP_NUM_PORTS - 2) diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index d7ce281570b5..89f920289ae2 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -1379,6 +1379,12 @@ int lan9303_remove(struct lan9303 *chip) } EXPORT_SYMBOL(lan9303_remove); +void lan9303_shutdown(struct lan9303 *chip) +{ + dsa_switch_shutdown(chip->ds); +} +EXPORT_SYMBOL(lan9303_shutdown); + MODULE_AUTHOR("Juergen Borleis "); MODULE_DESCRIPTION("Core driver for SMSC/Microchip LAN9303 three port ethernet switch"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/lan9303.h b/drivers/net/dsa/lan9303.h index 11f590b64701..c7f73efa50f0 100644 --- a/drivers/net/dsa/lan9303.h +++ b/drivers/net/dsa/lan9303.h @@ -10,3 +10,4 @@ extern const struct lan9303_phy_ops lan9303_indirect_phy_ops; int lan9303_probe(struct lan9303 *chip, struct device_node *np); int lan9303_remove(struct lan9303 *chip); +void lan9303_shutdown(struct lan9303 *chip); diff --git a/drivers/net/dsa/lan9303_i2c.c b/drivers/net/dsa/lan9303_i2c.c index 9bffaef65a04..8ca4713310fa 100644 --- a/drivers/net/dsa/lan9303_i2c.c +++ b/drivers/net/dsa/lan9303_i2c.c @@ -67,13 +67,28 @@ static int lan9303_i2c_probe(struct i2c_client *client, static int lan9303_i2c_remove(struct i2c_client *client) { - struct lan9303_i2c *sw_dev; + struct lan9303_i2c *sw_dev = i2c_get_clientdata(client); - sw_dev = i2c_get_clientdata(client); if (!sw_dev) - return -ENODEV; + return 0; + + lan9303_remove(&sw_dev->chip); + + i2c_set_clientdata(client, NULL); + + return 0; +} + +static void lan9303_i2c_shutdown(struct i2c_client *client) +{ + struct lan9303_i2c *sw_dev = i2c_get_clientdata(client); + + if (!sw_dev) + return; + + lan9303_shutdown(&sw_dev->chip); - return lan9303_remove(&sw_dev->chip); + i2c_set_clientdata(client, NULL); } /*-------------------------------------------------------------------------*/ @@ -97,6 +112,7 @@ static struct i2c_driver lan9303_i2c_driver = { }, .probe = lan9303_i2c_probe, .remove = lan9303_i2c_remove, + .shutdown = lan9303_i2c_shutdown, .id_table = lan9303_i2c_id, }; module_i2c_driver(lan9303_i2c_driver); diff --git a/drivers/net/dsa/lan9303_mdio.c b/drivers/net/dsa/lan9303_mdio.c index 9cbe80460b53..bbb7032409ba 100644 --- a/drivers/net/dsa/lan9303_mdio.c +++ b/drivers/net/dsa/lan9303_mdio.c @@ -138,6 +138,20 @@ static void lan9303_mdio_remove(struct mdio_device *mdiodev) return; lan9303_remove(&sw_dev->chip); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void lan9303_mdio_shutdown(struct mdio_device *mdiodev) +{ + struct lan9303_mdio *sw_dev = dev_get_drvdata(&mdiodev->dev); + + if (!sw_dev) + return; + + lan9303_shutdown(&sw_dev->chip); + + dev_set_drvdata(&mdiodev->dev, NULL); } /*-------------------------------------------------------------------------*/ @@ -155,6 +169,7 @@ static struct mdio_driver lan9303_mdio_driver = { }, .probe = lan9303_mdio_probe, .remove = lan9303_mdio_remove, + .shutdown = lan9303_mdio_shutdown, }; mdio_module_driver(lan9303_mdio_driver); diff --git a/drivers/net/dsa/lantiq_gswip.c b/drivers/net/dsa/lantiq_gswip.c index 267324889dd6..3ff4b7e177f3 100644 --- a/drivers/net/dsa/lantiq_gswip.c +++ b/drivers/net/dsa/lantiq_gswip.c @@ -2184,6 +2184,9 @@ static int gswip_remove(struct platform_device *pdev) struct gswip_priv *priv = platform_get_drvdata(pdev); int i; + if (!priv) + return 0; + /* disable the switch */ gswip_mdio_mask(priv, GSWIP_MDIO_GLOB_ENABLE, 0, GSWIP_MDIO_GLOB); @@ -2197,9 +2200,23 @@ static int gswip_remove(struct platform_device *pdev) for (i = 0; i < priv->num_gphy_fw; i++) gswip_gphy_fw_remove(priv, &priv->gphy_fw[i]); + platform_set_drvdata(pdev, NULL); + return 0; } +static void gswip_shutdown(struct platform_device *pdev) +{ + struct gswip_priv *priv = platform_get_drvdata(pdev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct gswip_hw_info gswip_xrx200 = { .max_ports = 7, .cpu_port = 6, @@ -2223,6 +2240,7 @@ MODULE_DEVICE_TABLE(of, gswip_of_match); static struct platform_driver gswip_driver = { .probe = gswip_probe, .remove = gswip_remove, + .shutdown = gswip_shutdown, .driver = { .name = "gswip", .of_match_table = gswip_of_match, diff --git a/drivers/net/dsa/microchip/ksz8795_spi.c b/drivers/net/dsa/microchip/ksz8795_spi.c index ea7550d1b634..866767b70d65 100644 --- a/drivers/net/dsa/microchip/ksz8795_spi.c +++ b/drivers/net/dsa/microchip/ksz8795_spi.c @@ -94,6 +94,8 @@ static int ksz8795_spi_remove(struct spi_device *spi) if (dev) ksz_switch_remove(dev); + spi_set_drvdata(spi, NULL); + return 0; } @@ -101,8 +103,15 @@ static void ksz8795_spi_shutdown(struct spi_device *spi) { struct ksz_device *dev = spi_get_drvdata(spi); - if (dev && dev->dev_ops->shutdown) + if (!dev) + return; + + if (dev->dev_ops->shutdown) dev->dev_ops->shutdown(dev); + + dsa_switch_shutdown(dev->ds); + + spi_set_drvdata(spi, NULL); } static const struct of_device_id ksz8795_dt_ids[] = { diff --git a/drivers/net/dsa/microchip/ksz9477_i2c.c b/drivers/net/dsa/microchip/ksz9477_i2c.c index 4e053a25d077..f3afb8b8c4cc 100644 --- a/drivers/net/dsa/microchip/ksz9477_i2c.c +++ b/drivers/net/dsa/microchip/ksz9477_i2c.c @@ -56,7 +56,10 @@ static int ksz9477_i2c_remove(struct i2c_client *i2c) { struct ksz_device *dev = i2c_get_clientdata(i2c); - ksz_switch_remove(dev); + if (dev) + ksz_switch_remove(dev); + + i2c_set_clientdata(i2c, NULL); return 0; } @@ -65,8 +68,15 @@ static void ksz9477_i2c_shutdown(struct i2c_client *i2c) { struct ksz_device *dev = i2c_get_clientdata(i2c); - if (dev && dev->dev_ops->shutdown) + if (!dev) + return; + + if (dev->dev_ops->shutdown) dev->dev_ops->shutdown(dev); + + dsa_switch_shutdown(dev->ds); + + i2c_set_clientdata(i2c, NULL); } static const struct i2c_device_id ksz9477_i2c_id[] = { diff --git a/drivers/net/dsa/microchip/ksz9477_spi.c b/drivers/net/dsa/microchip/ksz9477_spi.c index 15bc11b3cda4..e3cb0e6c9f6f 100644 --- a/drivers/net/dsa/microchip/ksz9477_spi.c +++ b/drivers/net/dsa/microchip/ksz9477_spi.c @@ -72,6 +72,8 @@ static int ksz9477_spi_remove(struct spi_device *spi) if (dev) ksz_switch_remove(dev); + spi_set_drvdata(spi, NULL); + return 0; } @@ -79,8 +81,10 @@ static void ksz9477_spi_shutdown(struct spi_device *spi) { struct ksz_device *dev = spi_get_drvdata(spi); - if (dev && dev->dev_ops->shutdown) - dev->dev_ops->shutdown(dev); + if (dev) + dsa_switch_shutdown(dev->ds); + + spi_set_drvdata(spi, NULL); } static const struct of_device_id ksz9477_dt_ids[] = { diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index d0cba2d1cd68..094737e5084a 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -3286,6 +3286,9 @@ mt7530_remove(struct mdio_device *mdiodev) struct mt7530_priv *priv = dev_get_drvdata(&mdiodev->dev); int ret = 0; + if (!priv) + return; + ret = regulator_disable(priv->core_pwr); if (ret < 0) dev_err(priv->dev, @@ -3301,11 +3304,26 @@ mt7530_remove(struct mdio_device *mdiodev) dsa_unregister_switch(priv->ds); mutex_destroy(&priv->reg_mutex); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void mt7530_shutdown(struct mdio_device *mdiodev) +{ + struct mt7530_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static struct mdio_driver mt7530_mdio_driver = { .probe = mt7530_probe, .remove = mt7530_remove, + .shutdown = mt7530_shutdown, .mdiodrv.driver = { .name = "mt7530", .of_match_table = mt7530_of_match, diff --git a/drivers/net/dsa/mv88e6060.c b/drivers/net/dsa/mv88e6060.c index 24b8219fd607..a4c6eb9a52d0 100644 --- a/drivers/net/dsa/mv88e6060.c +++ b/drivers/net/dsa/mv88e6060.c @@ -290,7 +290,24 @@ static void mv88e6060_remove(struct mdio_device *mdiodev) { struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + if (!ds) + return; + dsa_unregister_switch(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void mv88e6060_shutdown(struct mdio_device *mdiodev) +{ + struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + + if (!ds) + return; + + dsa_switch_shutdown(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id mv88e6060_of_match[] = { @@ -303,6 +320,7 @@ static const struct of_device_id mv88e6060_of_match[] = { static struct mdio_driver mv88e6060_driver = { .probe = mv88e6060_probe, .remove = mv88e6060_remove, + .shutdown = mv88e6060_shutdown, .mdiodrv.driver = { .name = "mv88e6060", .of_match_table = mv88e6060_of_match, diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index c45ca2473743..fb10422d2c33 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -6389,7 +6389,12 @@ out: static void mv88e6xxx_remove(struct mdio_device *mdiodev) { struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); - struct mv88e6xxx_chip *chip = ds->priv; + struct mv88e6xxx_chip *chip; + + if (!ds) + return; + + chip = ds->priv; if (chip->info->ptp_support) { mv88e6xxx_hwtstamp_free(chip); @@ -6410,6 +6415,20 @@ static void mv88e6xxx_remove(struct mdio_device *mdiodev) mv88e6xxx_g1_irq_free(chip); else mv88e6xxx_irq_poll_free(chip); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void mv88e6xxx_shutdown(struct mdio_device *mdiodev) +{ + struct dsa_switch *ds = dev_get_drvdata(&mdiodev->dev); + + if (!ds) + return; + + dsa_switch_shutdown(ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id mv88e6xxx_of_match[] = { @@ -6433,6 +6452,7 @@ MODULE_DEVICE_TABLE(of, mv88e6xxx_of_match); static struct mdio_driver mv88e6xxx_driver = { .probe = mv88e6xxx_probe, .remove = mv88e6xxx_remove, + .shutdown = mv88e6xxx_shutdown, .mdiodrv.driver = { .name = "mv88e6085", .of_match_table = mv88e6xxx_of_match, diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c index 9e2ac8e46619..11b42fd812e4 100644 --- a/drivers/net/dsa/ocelot/felix_vsc9959.c +++ b/drivers/net/dsa/ocelot/felix_vsc9959.c @@ -1472,9 +1472,10 @@ err_pci_enable: static void felix_pci_remove(struct pci_dev *pdev) { - struct felix *felix; + struct felix *felix = pci_get_drvdata(pdev); - felix = pci_get_drvdata(pdev); + if (!felix) + return; dsa_unregister_switch(felix->ds); @@ -1482,6 +1483,20 @@ static void felix_pci_remove(struct pci_dev *pdev) kfree(felix); pci_disable_device(pdev); + + pci_set_drvdata(pdev, NULL); +} + +static void felix_pci_shutdown(struct pci_dev *pdev) +{ + struct felix *felix = pci_get_drvdata(pdev); + + if (!felix) + return; + + dsa_switch_shutdown(felix->ds); + + pci_set_drvdata(pdev, NULL); } static struct pci_device_id felix_ids[] = { @@ -1498,6 +1513,7 @@ static struct pci_driver felix_vsc9959_pci_driver = { .id_table = felix_ids, .probe = felix_pci_probe, .remove = felix_pci_remove, + .shutdown = felix_pci_shutdown, }; module_pci_driver(felix_vsc9959_pci_driver); diff --git a/drivers/net/dsa/ocelot/seville_vsc9953.c b/drivers/net/dsa/ocelot/seville_vsc9953.c index deae923c8b7a..de1d34a1f1e4 100644 --- a/drivers/net/dsa/ocelot/seville_vsc9953.c +++ b/drivers/net/dsa/ocelot/seville_vsc9953.c @@ -1245,18 +1245,33 @@ err_alloc_felix: static int seville_remove(struct platform_device *pdev) { - struct felix *felix; + struct felix *felix = platform_get_drvdata(pdev); - felix = platform_get_drvdata(pdev); + if (!felix) + return 0; dsa_unregister_switch(felix->ds); kfree(felix->ds); kfree(felix); + platform_set_drvdata(pdev, NULL); + return 0; } +static void seville_shutdown(struct platform_device *pdev) +{ + struct felix *felix = platform_get_drvdata(pdev); + + if (!felix) + return; + + dsa_switch_shutdown(felix->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct of_device_id seville_of_match[] = { { .compatible = "mscc,vsc9953-switch" }, { }, @@ -1266,6 +1281,7 @@ MODULE_DEVICE_TABLE(of, seville_of_match); static struct platform_driver seville_vsc9953_driver = { .probe = seville_probe, .remove = seville_remove, + .shutdown = seville_shutdown, .driver = { .name = "mscc_seville", .of_match_table = of_match_ptr(seville_of_match), diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index 563d8a279030..a6bfb6abc51a 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -1083,6 +1083,9 @@ static void ar9331_sw_remove(struct mdio_device *mdiodev) struct ar9331_sw_priv *priv = dev_get_drvdata(&mdiodev->dev); unsigned int i; + if (!priv) + return; + for (i = 0; i < ARRAY_SIZE(priv->port); i++) { struct ar9331_sw_port *port = &priv->port[i]; @@ -1094,6 +1097,20 @@ static void ar9331_sw_remove(struct mdio_device *mdiodev) dsa_unregister_switch(&priv->ds); reset_control_assert(priv->sw_reset); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void ar9331_sw_shutdown(struct mdio_device *mdiodev) +{ + struct ar9331_sw_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(&priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } static const struct of_device_id ar9331_sw_of_match[] = { @@ -1104,6 +1121,7 @@ static const struct of_device_id ar9331_sw_of_match[] = { static struct mdio_driver ar9331_sw_mdio_driver = { .probe = ar9331_sw_probe, .remove = ar9331_sw_remove, + .shutdown = ar9331_sw_shutdown, .mdiodrv.driver = { .name = AR9331_SW_NAME, .of_match_table = ar9331_sw_of_match, diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index bda5a9bf4f52..a984f06f6f04 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -1880,10 +1880,27 @@ qca8k_sw_remove(struct mdio_device *mdiodev) struct qca8k_priv *priv = dev_get_drvdata(&mdiodev->dev); int i; + if (!priv) + return; + for (i = 0; i < QCA8K_NUM_PORTS; i++) qca8k_port_set_status(priv, i, 0); dsa_unregister_switch(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); +} + +static void qca8k_sw_shutdown(struct mdio_device *mdiodev) +{ + struct qca8k_priv *priv = dev_get_drvdata(&mdiodev->dev); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + dev_set_drvdata(&mdiodev->dev, NULL); } #ifdef CONFIG_PM_SLEEP @@ -1940,6 +1957,7 @@ static const struct of_device_id qca8k_of_match[] = { static struct mdio_driver qca8kmdio_driver = { .probe = qca8k_sw_probe, .remove = qca8k_sw_remove, + .shutdown = qca8k_sw_shutdown, .mdiodrv.driver = { .name = "qca8k", .of_match_table = qca8k_of_match, diff --git a/drivers/net/dsa/realtek-smi-core.c b/drivers/net/dsa/realtek-smi-core.c index 8e49d4f85d48..dd2f0d6208b3 100644 --- a/drivers/net/dsa/realtek-smi-core.c +++ b/drivers/net/dsa/realtek-smi-core.c @@ -464,16 +464,33 @@ static int realtek_smi_probe(struct platform_device *pdev) static int realtek_smi_remove(struct platform_device *pdev) { - struct realtek_smi *smi = dev_get_drvdata(&pdev->dev); + struct realtek_smi *smi = platform_get_drvdata(pdev); + + if (!smi) + return 0; dsa_unregister_switch(smi->ds); if (smi->slave_mii_bus) of_node_put(smi->slave_mii_bus->dev.of_node); gpiod_set_value(smi->reset, 1); + platform_set_drvdata(pdev, NULL); + return 0; } +static void realtek_smi_shutdown(struct platform_device *pdev) +{ + struct realtek_smi *smi = platform_get_drvdata(pdev); + + if (!smi) + return; + + dsa_switch_shutdown(smi->ds); + + platform_set_drvdata(pdev, NULL); +} + static const struct of_device_id realtek_smi_of_match[] = { { .compatible = "realtek,rtl8366rb", @@ -495,6 +512,7 @@ static struct platform_driver realtek_smi_driver = { }, .probe = realtek_smi_probe, .remove = realtek_smi_remove, + .shutdown = realtek_smi_shutdown, }; module_platform_driver(realtek_smi_driver); diff --git a/drivers/net/dsa/sja1105/sja1105_main.c b/drivers/net/dsa/sja1105/sja1105_main.c index 2f8cc6686c38..7c0db80eff00 100644 --- a/drivers/net/dsa/sja1105/sja1105_main.c +++ b/drivers/net/dsa/sja1105/sja1105_main.c @@ -3335,13 +3335,29 @@ static int sja1105_probe(struct spi_device *spi) static int sja1105_remove(struct spi_device *spi) { struct sja1105_private *priv = spi_get_drvdata(spi); - struct dsa_switch *ds = priv->ds; - dsa_unregister_switch(ds); + if (!priv) + return 0; + + dsa_unregister_switch(priv->ds); + + spi_set_drvdata(spi, NULL); return 0; } +static void sja1105_shutdown(struct spi_device *spi) +{ + struct sja1105_private *priv = spi_get_drvdata(spi); + + if (!priv) + return; + + dsa_switch_shutdown(priv->ds); + + spi_set_drvdata(spi, NULL); +} + static const struct of_device_id sja1105_dt_ids[] = { { .compatible = "nxp,sja1105e", .data = &sja1105e_info }, { .compatible = "nxp,sja1105t", .data = &sja1105t_info }, @@ -3365,6 +3381,7 @@ static struct spi_driver sja1105_driver = { }, .probe = sja1105_probe, .remove = sja1105_remove, + .shutdown = sja1105_shutdown, }; module_spi_driver(sja1105_driver); diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c index 19ce4aa0973b..a4b1447ff055 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-core.c +++ b/drivers/net/dsa/vitesse-vsc73xx-core.c @@ -1225,6 +1225,12 @@ int vsc73xx_remove(struct vsc73xx *vsc) } EXPORT_SYMBOL(vsc73xx_remove); +void vsc73xx_shutdown(struct vsc73xx *vsc) +{ + dsa_switch_shutdown(vsc->ds); +} +EXPORT_SYMBOL(vsc73xx_shutdown); + MODULE_AUTHOR("Linus Walleij "); MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 driver"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/dsa/vitesse-vsc73xx-platform.c b/drivers/net/dsa/vitesse-vsc73xx-platform.c index 2a57f337b2a2..fe4b154a0a57 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-platform.c +++ b/drivers/net/dsa/vitesse-vsc73xx-platform.c @@ -116,7 +116,26 @@ static int vsc73xx_platform_remove(struct platform_device *pdev) { struct vsc73xx_platform *vsc_platform = platform_get_drvdata(pdev); - return vsc73xx_remove(&vsc_platform->vsc); + if (!vsc_platform) + return 0; + + vsc73xx_remove(&vsc_platform->vsc); + + platform_set_drvdata(pdev, NULL); + + return 0; +} + +static void vsc73xx_platform_shutdown(struct platform_device *pdev) +{ + struct vsc73xx_platform *vsc_platform = platform_get_drvdata(pdev); + + if (!vsc_platform) + return; + + vsc73xx_shutdown(&vsc_platform->vsc); + + platform_set_drvdata(pdev, NULL); } static const struct vsc73xx_ops vsc73xx_platform_ops = { @@ -144,6 +163,7 @@ MODULE_DEVICE_TABLE(of, vsc73xx_of_match); static struct platform_driver vsc73xx_platform_driver = { .probe = vsc73xx_platform_probe, .remove = vsc73xx_platform_remove, + .shutdown = vsc73xx_platform_shutdown, .driver = { .name = "vsc73xx-platform", .of_match_table = vsc73xx_of_match, diff --git a/drivers/net/dsa/vitesse-vsc73xx-spi.c b/drivers/net/dsa/vitesse-vsc73xx-spi.c index 81eca4a5781d..645398901e05 100644 --- a/drivers/net/dsa/vitesse-vsc73xx-spi.c +++ b/drivers/net/dsa/vitesse-vsc73xx-spi.c @@ -163,7 +163,26 @@ static int vsc73xx_spi_remove(struct spi_device *spi) { struct vsc73xx_spi *vsc_spi = spi_get_drvdata(spi); - return vsc73xx_remove(&vsc_spi->vsc); + if (!vsc_spi) + return 0; + + vsc73xx_remove(&vsc_spi->vsc); + + spi_set_drvdata(spi, NULL); + + return 0; +} + +static void vsc73xx_spi_shutdown(struct spi_device *spi) +{ + struct vsc73xx_spi *vsc_spi = spi_get_drvdata(spi); + + if (!vsc_spi) + return; + + vsc73xx_shutdown(&vsc_spi->vsc); + + spi_set_drvdata(spi, NULL); } static const struct vsc73xx_ops vsc73xx_spi_ops = { @@ -191,6 +210,7 @@ MODULE_DEVICE_TABLE(of, vsc73xx_of_match); static struct spi_driver vsc73xx_spi_driver = { .probe = vsc73xx_spi_probe, .remove = vsc73xx_spi_remove, + .shutdown = vsc73xx_spi_shutdown, .driver = { .name = "vsc73xx-spi", .of_match_table = vsc73xx_of_match, diff --git a/drivers/net/dsa/vitesse-vsc73xx.h b/drivers/net/dsa/vitesse-vsc73xx.h index 7478f8d4e0a9..30b951504e65 100644 --- a/drivers/net/dsa/vitesse-vsc73xx.h +++ b/drivers/net/dsa/vitesse-vsc73xx.h @@ -27,3 +27,4 @@ struct vsc73xx_ops { int vsc73xx_is_addr_valid(u8 block, u8 subblock); int vsc73xx_probe(struct vsc73xx *vsc); int vsc73xx_remove(struct vsc73xx *vsc); +void vsc73xx_shutdown(struct vsc73xx *vsc); diff --git a/include/net/dsa.h b/include/net/dsa.h index 258867eff230..6e29c0e080f6 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -1046,6 +1046,7 @@ static inline int dsa_ndo_eth_ioctl(struct net_device *dev, struct ifreq *ifr, void dsa_unregister_switch(struct dsa_switch *ds); int dsa_register_switch(struct dsa_switch *ds); +void dsa_switch_shutdown(struct dsa_switch *ds); struct dsa_switch *dsa_switch_find(int tree_index, int sw_index); #ifdef CONFIG_PM_SLEEP int dsa_switch_suspend(struct dsa_switch *ds); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index eef13cd20f19..fa88e58705f0 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -1562,3 +1562,53 @@ void dsa_unregister_switch(struct dsa_switch *ds) mutex_unlock(&dsa2_mutex); } EXPORT_SYMBOL_GPL(dsa_unregister_switch); + +/* If the DSA master chooses to unregister its net_device on .shutdown, DSA is + * blocking that operation from completion, due to the dev_hold taken inside + * netdev_upper_dev_link. Unlink the DSA slave interfaces from being uppers of + * the DSA master, so that the system can reboot successfully. + */ +void dsa_switch_shutdown(struct dsa_switch *ds) +{ + struct net_device *master, *slave_dev; + LIST_HEAD(unregister_list); + struct dsa_port *dp; + + mutex_lock(&dsa2_mutex); + rtnl_lock(); + + list_for_each_entry(dp, &ds->dst->ports, list) { + if (dp->ds != ds) + continue; + + if (!dsa_port_is_user(dp)) + continue; + + master = dp->cpu_dp->master; + slave_dev = dp->slave; + + netdev_upper_dev_unlink(master, slave_dev); + /* Just unlinking ourselves as uppers of the master is not + * sufficient. When the master net device unregisters, that will + * also call dev_close, which we will catch as NETDEV_GOING_DOWN + * and trigger a dev_close on our own devices (dsa_slave_close). + * In turn, that will call dev_mc_unsync on the master's net + * device. If the master is also a DSA switch port, this will + * trigger dsa_slave_set_rx_mode which will call dev_mc_sync on + * its own master. Lockdep will complain about the fact that + * all cascaded masters have the same dsa_master_addr_list_lock_key, + * which it normally would not do if the cascaded masters would + * be in a proper upper/lower relationship, which we've just + * destroyed. + * To suppress the lockdep warnings, let's actually unregister + * the DSA slave interfaces too, to avoid the nonsensical + * multicast address list synchronization on shutdown. + */ + unregister_netdevice_queue(slave_dev, &unregister_list); + } + unregister_netdevice_many(&unregister_list); + + rtnl_unlock(); + mutex_unlock(&dsa2_mutex); +} +EXPORT_SYMBOL_GPL(dsa_switch_shutdown); -- cgit v1.2.3 From 2dcb96bacce36021c2f3eaae0cef607b5bb71ede Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Sat, 18 Sep 2021 14:42:35 +0200 Subject: net: core: Correct the sock::sk_lock.owned lockdep annotations lock_sock_fast() and lock_sock_nested() contain lockdep annotations for the sock::sk_lock.owned 'mutex'. sock::sk_lock.owned is not a regular mutex. It is just lockdep wise equivalent. In fact it's an open coded trivial mutex implementation with some interesting features. sock::sk_lock.slock is a regular spinlock protecting the 'mutex' representation sock::sk_lock.owned which is a plain boolean. If 'owned' is true, then some other task holds the 'mutex', otherwise it is uncontended. As this locking construct is obviously endangered by lock ordering issues as any other locking primitive it got lockdep annotated via a dedicated dependency map sock::sk_lock.dep_map which has to be updated at the lock and unlock sites. lock_sock_nested() is a straight forward 'mutex' lock operation: might_sleep(); spin_lock_bh(sock::sk_lock.slock) while (!try_lock(sock::sk_lock.owned)) { spin_unlock_bh(sock::sk_lock.slock); wait_for_release(); spin_lock_bh(sock::sk_lock.slock); } The lockdep annotation for sock::sk_lock.owned is for unknown reasons _after_ the lock has been acquired, i.e. after the code block above and after releasing sock::sk_lock.slock, but inside the bottom halves disabled region: spin_unlock(sock::sk_lock.slock); mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); The placement after the unlock is obvious because otherwise the mutex_acquire() would nest into the spin lock held region. But that's from the lockdep perspective still the wrong place: 1) The mutex_acquire() is issued _after_ the successful acquisition which is pointless because in a dead lock scenario this point is never reached which means that if the deadlock is the first instance of exposing the wrong lock order lockdep does not have a chance to detect it. 2) It only works because lockdep is rather lax on the context from which the mutex_acquire() is issued. Acquiring a mutex inside a bottom halves and therefore non-preemptible region is obviously invalid, except for a trylock which is clearly not the case here. This 'works' stops working on RT enabled kernels where the bottom halves serialization is done via a local lock, which exposes this misplacement because the 'mutex' and the local lock nest the wrong way around and lockdep complains rightfully about a lock inversion. The placement is wrong since the initial commit a5b5bb9a053a ("[PATCH] lockdep: annotate sk_locks") which introduced this. Fix it by moving the mutex_acquire() in front of the actual lock acquisition, which is what the regular mutex_lock() operation does as well. lock_sock_fast() is not that straight forward. It looks at the first glance like a convoluted trylock operation: spin_lock_bh(sock::sk_lock.slock) if (!sock::sk_lock.owned) return false; while (!try_lock(sock::sk_lock.owned)) { spin_unlock_bh(sock::sk_lock.slock); wait_for_release(); spin_lock_bh(sock::sk_lock.slock); } spin_unlock(sock::sk_lock.slock); mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); return true; But that's not the case: lock_sock_fast() is an interesting optimization for short critical sections which can run with bottom halves disabled and sock::sk_lock.slock held. This allows to shortcut the 'mutex' operation in the non contended case by preventing other lockers to acquire sock::sk_lock.owned because they are blocked on sock::sk_lock.slock, which in turn avoids the overhead of doing the heavy processing in release_sock() including waking up wait queue waiters. In the contended case, i.e. when sock::sk_lock.owned == true the behavior is the same as lock_sock_nested(). Semantically this shortcut means, that the task acquired the 'mutex' even if it does not touch the sock::sk_lock.owned field in the non-contended case. Not telling lockdep about this shortcut acquisition is hiding potential lock ordering violations in the fast path. As a consequence the same reasoning as for the above lock_sock_nested() case vs. the placement of the lockdep annotation applies. The current placement of the lockdep annotation was just copied from the original lock_sock(), now renamed to lock_sock_nested(), implementation. Fix this by moving the mutex_acquire() in front of the actual lock acquisition and adding the corresponding mutex_release() into unlock_sock_fast(). Also document the fast path return case with a comment. Reported-by: Sebastian Siewior Signed-off-by: Thomas Gleixner Cc: netdev@vger.kernel.org Cc: "David S. Miller" Cc: Jakub Kicinski Cc: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 1 + net/core/sock.c | 37 +++++++++++++++++++++++-------------- 2 files changed, 24 insertions(+), 14 deletions(-) (limited to 'include') diff --git a/include/net/sock.h b/include/net/sock.h index 66a9a90f9558..c005c3c750e8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1640,6 +1640,7 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow) release_sock(sk); __release(&sk->sk_lock.slock); } else { + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); spin_unlock_bh(&sk->sk_lock.slock); } } diff --git a/net/core/sock.c b/net/core/sock.c index 62627e868e03..512e629f9780 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3179,17 +3179,15 @@ EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); + might_sleep(); spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_lock.owned) __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); - /* - * The sk_lock has mutex_lock() semantics here: - */ - mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); - local_bh_enable(); + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(lock_sock_nested); @@ -3227,24 +3225,35 @@ EXPORT_SYMBOL(release_sock); */ bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock) { + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + might_sleep(); spin_lock_bh(&sk->sk_lock.slock); - if (!sk->sk_lock.owned) + if (!sk->sk_lock.owned) { /* - * Note : We must disable BH + * Fast path return with bottom halves disabled and + * sock::sk_lock.slock held. + * + * The 'mutex' is not contended and holding + * sock::sk_lock.slock prevents all other lockers to + * proceed so the corresponding unlock_sock_fast() can + * avoid the slow path of release_sock() completely and + * just release slock. + * + * From a semantical POV this is equivalent to 'acquiring' + * the 'mutex', hence the corresponding lockdep + * mutex_release() has to happen in the fast path of + * unlock_sock_fast(). */ return false; + } __lock_sock(sk); sk->sk_lock.owned = 1; - spin_unlock(&sk->sk_lock.slock); - /* - * The sk_lock has mutex_lock() semantics here: - */ - mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); __acquire(&sk->sk_lock.slock); - local_bh_enable(); + spin_unlock_bh(&sk->sk_lock.slock); return true; } EXPORT_SYMBOL(lock_sock_fast); -- cgit v1.2.3 From fd292c189a979838622d5e03e15fa688c81dd50b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 17 Sep 2021 17:29:16 +0300 Subject: net: dsa: tear down devlink port regions when tearing down the devlink port on error Commit 86f8b1c01a0a ("net: dsa: Do not make user port errors fatal") decided it was fine to ignore errors on certain ports that fail to probe, and go on with the ports that do probe fine. Commit fb6ec87f7229 ("net: dsa: Fix type was not set for devlink port") noticed that devlink_port_type_eth_set(dlp, dp->slave); does not get called, and devlink notices after a timeout of 3600 seconds and prints a WARN_ON. So it went ahead to unregister the devlink port. And because there exists an UNUSED port flavour, we actually re-register the devlink port as UNUSED. Commit 08156ba430b4 ("net: dsa: Add devlink port regions support to DSA") added devlink port regions, which are set up by the driver and not by DSA. When we trigger the devlink port deregistration and reregistration as unused, devlink now prints another WARN_ON, from here: devlink_port_unregister: WARN_ON(!list_empty(&devlink_port->region_list)); So the port still has regions, which makes sense, because they were set up by the driver, and the driver doesn't know we're unregistering the devlink port. Somebody needs to tear them down, and optionally (actually it would be nice, to be consistent) set them up again for the new devlink port. But DSA's layering stays in our way quite badly here. The options I've considered are: 1. Introduce a function in devlink to just change a port's type and flavour. No dice, devlink keeps a lot of state, it really wants the port to not be registered when you set its parameters, so changing anything can only be done by destroying what we currently have and recreating it. 2. Make DSA cache the parameters passed to dsa_devlink_port_region_create, and the region returned, keep those in a list, then when the devlink port unregister needs to take place, the existing devlink regions are destroyed by DSA, and we replay the creation of new regions using the cached parameters. Problem: mv88e6xxx keeps the region pointers in chip->ports[port].region, and these will remain stale after DSA frees them. There are many things DSA can do, but updating mv88e6xxx's private pointers is not one of them. 3. Just let the driver do it (i.e. introduce a very specific method called ds->ops->port_reinit_as_unused, which unregisters its devlink port devlink regions, then the old devlink port, then registers the new one, then the devlink port regions for it). While it does work, as opposed to the others, it's pretty horrible from an API perspective and we can do better. 4. Introduce a new pair of methods, ->port_setup and ->port_teardown, which in the case of mv88e6xxx must register and unregister the devlink port regions. Call these 2 methods when the port must be reinitialized as unused. Naturally, I went for the 4th approach. Fixes: 08156ba430b4 ("net: dsa: Add devlink port regions support to DSA") Signed-off-by: Vladimir Oltean Signed-off-by: David S. Miller --- drivers/net/dsa/mv88e6xxx/chip.c | 16 +++++++- drivers/net/dsa/mv88e6xxx/devlink.c | 73 +++++-------------------------------- drivers/net/dsa/mv88e6xxx/devlink.h | 6 ++- include/net/dsa.h | 8 ++++ net/dsa/dsa2.c | 51 +++++++++++++++++++++++--- 5 files changed, 81 insertions(+), 73 deletions(-) (limited to 'include') diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index fb10422d2c33..8ab0be793811 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -3071,7 +3071,7 @@ static void mv88e6xxx_teardown(struct dsa_switch *ds) { mv88e6xxx_teardown_devlink_params(ds); dsa_devlink_resources_unregister(ds); - mv88e6xxx_teardown_devlink_regions(ds); + mv88e6xxx_teardown_devlink_regions_global(ds); } static int mv88e6xxx_setup(struct dsa_switch *ds) @@ -3215,7 +3215,7 @@ unlock: if (err) goto out_resources; - err = mv88e6xxx_setup_devlink_regions(ds); + err = mv88e6xxx_setup_devlink_regions_global(ds); if (err) goto out_params; @@ -3229,6 +3229,16 @@ out_resources: return err; } +static int mv88e6xxx_port_setup(struct dsa_switch *ds, int port) +{ + return mv88e6xxx_setup_devlink_regions_port(ds, port); +} + +static void mv88e6xxx_port_teardown(struct dsa_switch *ds, int port) +{ + mv88e6xxx_teardown_devlink_regions_port(ds, port); +} + /* prod_id for switch families which do not have a PHY model number */ static const u16 family_prod_id_table[] = { [MV88E6XXX_FAMILY_6341] = MV88E6XXX_PORT_SWITCH_ID_PROD_6341, @@ -6116,6 +6126,8 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .change_tag_protocol = mv88e6xxx_change_tag_protocol, .setup = mv88e6xxx_setup, .teardown = mv88e6xxx_teardown, + .port_setup = mv88e6xxx_port_setup, + .port_teardown = mv88e6xxx_port_teardown, .phylink_validate = mv88e6xxx_validate, .phylink_mac_link_state = mv88e6xxx_serdes_pcs_get_state, .phylink_mac_config = mv88e6xxx_mac_config, diff --git a/drivers/net/dsa/mv88e6xxx/devlink.c b/drivers/net/dsa/mv88e6xxx/devlink.c index 0c0f5ea6680c..381068395c63 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.c +++ b/drivers/net/dsa/mv88e6xxx/devlink.c @@ -647,26 +647,25 @@ static struct mv88e6xxx_region mv88e6xxx_regions[] = { }, }; -static void -mv88e6xxx_teardown_devlink_regions_global(struct mv88e6xxx_chip *chip) +void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds) { + struct mv88e6xxx_chip *chip = ds->priv; int i; for (i = 0; i < ARRAY_SIZE(mv88e6xxx_regions); i++) dsa_devlink_region_destroy(chip->regions[i]); } -static void -mv88e6xxx_teardown_devlink_regions_port(struct mv88e6xxx_chip *chip, - int port) +void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port) { + struct mv88e6xxx_chip *chip = ds->priv; + dsa_devlink_region_destroy(chip->ports[port].region); } -static int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, - struct mv88e6xxx_chip *chip, - int port) +int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, int port) { + struct mv88e6xxx_chip *chip = ds->priv; struct devlink_region *region; region = dsa_devlink_port_region_create(ds, @@ -681,40 +680,10 @@ static int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, return 0; } -static void -mv88e6xxx_teardown_devlink_regions_ports(struct mv88e6xxx_chip *chip) -{ - int port; - - for (port = 0; port < mv88e6xxx_num_ports(chip); port++) - mv88e6xxx_teardown_devlink_regions_port(chip, port); -} - -static int mv88e6xxx_setup_devlink_regions_ports(struct dsa_switch *ds, - struct mv88e6xxx_chip *chip) -{ - int port; - int err; - - for (port = 0; port < mv88e6xxx_num_ports(chip); port++) { - err = mv88e6xxx_setup_devlink_regions_port(ds, chip, port); - if (err) - goto out; - } - - return 0; - -out: - while (port-- > 0) - mv88e6xxx_teardown_devlink_regions_port(chip, port); - - return err; -} - -static int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds, - struct mv88e6xxx_chip *chip) +int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds) { bool (*cond)(struct mv88e6xxx_chip *chip); + struct mv88e6xxx_chip *chip = ds->priv; struct devlink_region_ops *ops; struct devlink_region *region; u64 size; @@ -753,30 +722,6 @@ out: return PTR_ERR(region); } -int mv88e6xxx_setup_devlink_regions(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds->priv; - int err; - - err = mv88e6xxx_setup_devlink_regions_global(ds, chip); - if (err) - return err; - - err = mv88e6xxx_setup_devlink_regions_ports(ds, chip); - if (err) - mv88e6xxx_teardown_devlink_regions_global(chip); - - return err; -} - -void mv88e6xxx_teardown_devlink_regions(struct dsa_switch *ds) -{ - struct mv88e6xxx_chip *chip = ds->priv; - - mv88e6xxx_teardown_devlink_regions_ports(chip); - mv88e6xxx_teardown_devlink_regions_global(chip); -} - int mv88e6xxx_devlink_info_get(struct dsa_switch *ds, struct devlink_info_req *req, struct netlink_ext_ack *extack) diff --git a/drivers/net/dsa/mv88e6xxx/devlink.h b/drivers/net/dsa/mv88e6xxx/devlink.h index 3d72db3dcf95..65ce6a6858b9 100644 --- a/drivers/net/dsa/mv88e6xxx/devlink.h +++ b/drivers/net/dsa/mv88e6xxx/devlink.h @@ -12,8 +12,10 @@ int mv88e6xxx_devlink_param_get(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); int mv88e6xxx_devlink_param_set(struct dsa_switch *ds, u32 id, struct devlink_param_gset_ctx *ctx); -int mv88e6xxx_setup_devlink_regions(struct dsa_switch *ds); -void mv88e6xxx_teardown_devlink_regions(struct dsa_switch *ds); +int mv88e6xxx_setup_devlink_regions_global(struct dsa_switch *ds); +void mv88e6xxx_teardown_devlink_regions_global(struct dsa_switch *ds); +int mv88e6xxx_setup_devlink_regions_port(struct dsa_switch *ds, int port); +void mv88e6xxx_teardown_devlink_regions_port(struct dsa_switch *ds, int port); int mv88e6xxx_devlink_info_get(struct dsa_switch *ds, struct devlink_info_req *req, diff --git a/include/net/dsa.h b/include/net/dsa.h index 6e29c0e080f6..d784e76113b8 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -585,8 +585,16 @@ struct dsa_switch_ops { int (*change_tag_protocol)(struct dsa_switch *ds, int port, enum dsa_tag_protocol proto); + /* Optional switch-wide initialization and destruction methods */ int (*setup)(struct dsa_switch *ds); void (*teardown)(struct dsa_switch *ds); + + /* Per-port initialization and destruction methods. Mandatory if the + * driver registers devlink port regions, optional otherwise. + */ + int (*port_setup)(struct dsa_switch *ds, int port); + void (*port_teardown)(struct dsa_switch *ds, int port); + u32 (*get_phy_flags)(struct dsa_switch *ds, int port); /* diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index fa88e58705f0..f14897d9b31d 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -429,6 +429,7 @@ static int dsa_port_setup(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; bool dsa_port_link_registered = false; + struct dsa_switch *ds = dp->ds; bool dsa_port_enabled = false; int err = 0; @@ -438,6 +439,12 @@ static int dsa_port_setup(struct dsa_port *dp) INIT_LIST_HEAD(&dp->fdbs); INIT_LIST_HEAD(&dp->mdbs); + if (ds->ops->port_setup) { + err = ds->ops->port_setup(ds, dp->index); + if (err) + return err; + } + switch (dp->type) { case DSA_PORT_TYPE_UNUSED: dsa_port_disable(dp); @@ -480,8 +487,11 @@ static int dsa_port_setup(struct dsa_port *dp) dsa_port_disable(dp); if (err && dsa_port_link_registered) dsa_port_link_unregister_of(dp); - if (err) + if (err) { + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); return err; + } dp->setup = true; @@ -533,11 +543,15 @@ static int dsa_port_devlink_setup(struct dsa_port *dp) static void dsa_port_teardown(struct dsa_port *dp) { struct devlink_port *dlp = &dp->devlink_port; + struct dsa_switch *ds = dp->ds; struct dsa_mac_addr *a, *tmp; if (!dp->setup) return; + if (ds->ops->port_teardown) + ds->ops->port_teardown(ds, dp->index); + devlink_port_type_clear(dlp); switch (dp->type) { @@ -581,6 +595,36 @@ static void dsa_port_devlink_teardown(struct dsa_port *dp) dp->devlink_port_setup = false; } +/* Destroy the current devlink port, and create a new one which has the UNUSED + * flavour. At this point, any call to ds->ops->port_setup has been already + * balanced out by a call to ds->ops->port_teardown, so we know that any + * devlink port regions the driver had are now unregistered. We then call its + * ds->ops->port_setup again, in order for the driver to re-create them on the + * new devlink port. + */ +static int dsa_port_reinit_as_unused(struct dsa_port *dp) +{ + struct dsa_switch *ds = dp->ds; + int err; + + dsa_port_devlink_teardown(dp); + dp->type = DSA_PORT_TYPE_UNUSED; + err = dsa_port_devlink_setup(dp); + if (err) + return err; + + if (ds->ops->port_setup) { + /* On error, leave the devlink port registered, + * dsa_switch_teardown will clean it up later. + */ + err = ds->ops->port_setup(ds, dp->index); + if (err) + return err; + } + + return 0; +} + static int dsa_devlink_info_get(struct devlink *dl, struct devlink_info_req *req, struct netlink_ext_ack *extack) @@ -938,12 +982,9 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) list_for_each_entry(dp, &dst->ports, list) { err = dsa_port_setup(dp); if (err) { - dsa_port_devlink_teardown(dp); - dp->type = DSA_PORT_TYPE_UNUSED; - err = dsa_port_devlink_setup(dp); + err = dsa_port_reinit_as_unused(dp); if (err) goto teardown; - continue; } } -- cgit v1.2.3 From 9caea0007601d3bc6debec04f8b4cd6f4c2394be Mon Sep 17 00:00:00 2001 From: Helge Deller Date: Sun, 19 Sep 2021 10:36:09 -0700 Subject: parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled Linus noticed odd declaration rules for pci_iounmap() in iomap.h and pci_iomap.h, where it dependend on either NO_GENERIC_PCI_IOPORT_MAP or GENERIC_IOMAP when CONFIG_PCI was disabled. Testing on parisc seems to indicate that we need pci_iounmap() only when CONFIG_PCI is enabled, so the declaration of pci_iounmap() can be moved cleanly into pci_iomap.h in sync with the declarations of pci_iomap(). Link: https://lore.kernel.org/all/CAHk-=wjRrh98pZoQ+AzfWmsTZacWxTJKXZ9eKU2X_0+jM=O8nw@mail.gmail.com/ Signed-off-by: Helge Deller Suggested-by: Linus Torvalds Fixes: 97a29d59fc22 ("[PARISC] fix compile break caused by iomap: make IOPORT/PCI mapping functions conditional") Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- arch/parisc/lib/iomap.c | 4 +++- include/asm-generic/iomap.h | 10 ---------- include/asm-generic/pci_iomap.h | 3 +++ 3 files changed, 6 insertions(+), 11 deletions(-) (limited to 'include') diff --git a/arch/parisc/lib/iomap.c b/arch/parisc/lib/iomap.c index f03adb1999e7..367f6397bda7 100644 --- a/arch/parisc/lib/iomap.c +++ b/arch/parisc/lib/iomap.c @@ -513,12 +513,15 @@ void ioport_unmap(void __iomem *addr) } } +#ifdef CONFIG_PCI void pci_iounmap(struct pci_dev *dev, void __iomem * addr) { if (!INDIRECT_ADDR(addr)) { iounmap(addr); } } +EXPORT_SYMBOL(pci_iounmap); +#endif EXPORT_SYMBOL(ioread8); EXPORT_SYMBOL(ioread16); @@ -544,4 +547,3 @@ EXPORT_SYMBOL(iowrite16_rep); EXPORT_SYMBOL(iowrite32_rep); EXPORT_SYMBOL(ioport_map); EXPORT_SYMBOL(ioport_unmap); -EXPORT_SYMBOL(pci_iounmap); diff --git a/include/asm-generic/iomap.h b/include/asm-generic/iomap.h index 9b3eb6d86200..08237ae8b840 100644 --- a/include/asm-generic/iomap.h +++ b/include/asm-generic/iomap.h @@ -110,16 +110,6 @@ static inline void __iomem *ioremap_np(phys_addr_t offset, size_t size) } #endif -#ifdef CONFIG_PCI -/* Destroy a virtual mapping cookie for a PCI BAR (memory or IO) */ -struct pci_dev; -extern void pci_iounmap(struct pci_dev *dev, void __iomem *); -#elif defined(CONFIG_GENERIC_IOMAP) -struct pci_dev; -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) -{ } -#endif - #include #endif diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index df636c6d8e6c..5a2f9bf53384 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -18,6 +18,7 @@ extern void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, extern void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, unsigned long offset, unsigned long maxlen); +extern void pci_iounmap(struct pci_dev *dev, void __iomem *); /* Create a virtual mapping cookie for a port on a given PCI device. * Do not call this directly, it exists to make it easier for architectures * to override */ @@ -50,6 +51,8 @@ static inline void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, { return NULL; } +static inline void pci_iounmap(struct pci_dev *dev, void __iomem *addr) +{ } #endif #endif /* __ASM_GENERIC_PCI_IOMAP_H */ -- cgit v1.2.3 From 316e8d79a0959c302b0c462ab64b069599f10eef Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 19 Sep 2021 17:13:35 -0700 Subject: pci_iounmap'2: Electric Boogaloo: try to make sense of it all Nathan Chancellor reports that the recent change to pci_iounmap in commit 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") causes build errors on arm64. It took me about two hours to convince myself that I think I know what the logic of that mess of #ifdef's in the header file really aim to do, and rewrite it to be easier to follow. Famous last words. Anyway, the code has now been lifted from that grotty header file into lib/pci_iomap.c, and has fairly extensive comments about what the logic is. It also avoids indirecting through another confusing (and badly named) helper function that has other preprocessor config conditionals. Let's see what odd architecture did something else strange in this area to break things. But my arm64 cross build is clean. Fixes: 9caea0007601 ("parisc: Declare pci_iounmap() parisc version only when CONFIG_PCI enabled") Reported-by: Nathan Chancellor Cc: Helge Deller Cc: Arnd Bergmann Cc: Guenter Roeck Cc: Ulrich Teichert Cc: James Bottomley Signed-off-by: Linus Torvalds --- include/asm-generic/io.h | 26 +++----------------------- lib/pci_iomap.c | 43 +++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 46 insertions(+), 23 deletions(-) (limited to 'include') diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index e93375c710b9..cc7338f9e0d1 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -1023,16 +1023,7 @@ static inline void __iomem *ioport_map(unsigned long port, unsigned int nr) port &= IO_SPACE_LIMIT; return (port > MMIO_UPPER_LIMIT) ? NULL : PCI_IOBASE + port; } -#define __pci_ioport_unmap __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) -{ - uintptr_t start = (uintptr_t) PCI_IOBASE; - uintptr_t addr = (uintptr_t) p; - - if (addr >= start && addr < start + IO_SPACE_LIMIT) - return; - iounmap(p); -} +#define ARCH_HAS_GENERIC_IOPORT_MAP #endif #ifndef ioport_unmap @@ -1048,21 +1039,10 @@ extern void ioport_unmap(void __iomem *p); #endif /* CONFIG_HAS_IOPORT_MAP */ #ifndef CONFIG_GENERIC_IOMAP -struct pci_dev; -extern void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long max); - -#ifndef __pci_ioport_unmap -static inline void __pci_ioport_unmap(void __iomem *p) {} -#endif - #ifndef pci_iounmap -#define pci_iounmap pci_iounmap -static inline void pci_iounmap(struct pci_dev *dev, void __iomem *p) -{ - __pci_ioport_unmap(p); -} +#define ARCH_WANTS_GENERIC_PCI_IOUNMAP +#endif #endif -#endif /* CONFIG_GENERIC_IOMAP */ #ifndef xlate_dev_mem_ptr #define xlate_dev_mem_ptr xlate_dev_mem_ptr diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c index 2d3eb1cb73b8..ce39ce9f3526 100644 --- a/lib/pci_iomap.c +++ b/lib/pci_iomap.c @@ -134,4 +134,47 @@ void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen) return pci_iomap_wc_range(dev, bar, 0, maxlen); } EXPORT_SYMBOL_GPL(pci_iomap_wc); + +/* + * pci_iounmap() somewhat illogically comes from lib/iomap.c for the + * CONFIG_GENERIC_IOMAP case, because that's the code that knows about + * the different IOMAP ranges. + * + * But if the architecture does not use the generic iomap code, and if + * it has _not_ defined it's own private pci_iounmap function, we define + * it here. + * + * NOTE! This default implementation assumes that if the architecture + * support ioport mapping (HAS_IOPORT_MAP), the ioport mapping will + * be fixed to the range [ PCI_IOBASE, PCI_IOBASE+IO_SPACE_LIMIT [, + * and does not need unmapping with 'ioport_unmap()'. + * + * If you have different rules for your architecture, you need to + * implement your own pci_iounmap() that knows the rules for where + * and how IO vs MEM get mapped. + * + * This code is odd, and the ARCH_HAS/ARCH_WANTS #define logic comes + * from legacy header file behavior. In particular, + * it would seem to make sense to do the iounmap(p) for the non-IO-space + * case here regardless, but that's not what the old header file code + * did. Probably incorrectly, but this is meant to be bug-for-bug + * compatible. + */ +#if defined(ARCH_WANTS_GENERIC_PCI_IOUNMAP) + +void pci_iounmap(struct pci_dev *dev, void __iomem *p) +{ +#ifdef ARCH_HAS_GENERIC_IOPORT_MAP + uintptr_t start = (uintptr_t) PCI_IOBASE; + uintptr_t addr = (uintptr_t) p; + + if (addr >= start && addr < start + IO_SPACE_LIMIT) + return; + iounmap(p); +#endif +} +EXPORT_SYMBOL(pci_iounmap); + +#endif /* ARCH_WANTS_GENERIC_PCI_IOUNMAP */ + #endif /* CONFIG_PCI */ -- cgit v1.2.3