September 2023 - Linux-stable-mirror

FAILED: patch "[PATCH] btrfs: release path before inode lookup during the ino lookup" failed to apply to 4.19-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x ee34a82e890a7babb5585daf1a6dd7d4d1cf142a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023092056-manifesto-shame-79c2@gregkh' --subject-prefix 'PATCH 4.19.y' HEAD^.. Possible dependencies: ee34a82e890a ("btrfs: release path before inode lookup during the ino lookup ioctl") 0202e83fdab0 ("btrfs: simplify iget helpers") c75e839414d3 ("btrfs: kill the subvol_srcu") 5c8fd99fec9d ("btrfs: make inodes hold a ref on their roots") 7ac8b88ee668 ("btrfs: backref, only collect file extent items matching backref offset") 0024652895e3 ("btrfs: rename btrfs_put_fs_root and btrfs_grab_fs_root") bd647ce385ec ("btrfs: add a leak check for roots") 8260edba67a2 ("btrfs: make the init of static elements in fs_info separate") ae18c37ad5a1 ("btrfs: move fs_info init work into it's own helper function") 141386e1a5d6 ("btrfs: free more things in btrfs_free_fs_info") bc44d7c4b2b1 ("btrfs: push btrfs_grab_fs_root into btrfs_get_fs_root") 81f096edf047 ("btrfs: use btrfs_put_fs_root to free roots always") 0d4b0463011d ("btrfs: export and rename free_fs_info") fbb0ce40d606 ("btrfs: hold a ref on the root in btrfs_check_uuid_tree_entry") ca2037fba6af ("btrfs: hold a ref on the root in btrfs_recover_log_trees") 5119cfc36f6d ("btrfs: hold a ref on the root in create_pending_snapshot") 5168489a079a ("btrfs: hold a ref on the root in get_subvol_name_from_objectid") 6f9a3da5da9e ("btrfs: hold a ref on the root in btrfs_ioctl_send") fd79d43b347e ("btrfs: hold a ref on the root in scrub_print_warning_inode") 0b2dee5cff74 ("btrfs: hold a ref for the root in btrfs_find_orphan_roots") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee34a82e890a7babb5585daf1a6dd7d4d1cf142a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Sat, 26 Aug 2023 11:28:20 +0100 Subject: [PATCH] btrfs: release path before inode lookup during the ino lookup ioctl During the ino lookup ioctl we can end up calling btrfs_iget() to get an inode reference while we are holding on a root's btree. If btrfs_iget() needs to lookup the inode from the root's btree, because it's not currently loaded in memory, then it will need to lock another or the same path in the same root btree. This may result in a deadlock and trigger the following lockdep splat: WARNING: possible circular locking dependency detected 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Not tainted ------------------------------------------------------ syz-executor277/5012 is trying to acquire lock: ffff88802df41710 (btrfs-tree-01){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 but task is already holding lock: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (btrfs-tree-00){++++}-{3:3}: down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_search_slot+0x13a4/0x2f80 fs/btrfs/ctree.c:2302 btrfs_init_root_free_objectid+0x148/0x320 fs/btrfs/disk-io.c:4955 btrfs_init_fs_root fs/btrfs/disk-io.c:1128 [inline] btrfs_get_root_ref+0x5ae/0xae0 fs/btrfs/disk-io.c:1338 btrfs_get_fs_root fs/btrfs/disk-io.c:1390 [inline] open_ctree+0x29c8/0x3030 fs/btrfs/disk-io.c:3494 btrfs_fill_super+0x1c7/0x2f0 fs/btrfs/super.c:1154 btrfs_mount_root+0x7e0/0x910 fs/btrfs/super.c:1519 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 fc_mount fs/namespace.c:1112 [inline] vfs_kern_mount+0xbc/0x150 fs/namespace.c:1142 btrfs_mount+0x39f/0xb50 fs/btrfs/super.c:1579 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 do_new_mount+0x28f/0xae0 fs/namespace.c:3335 do_mount fs/namespace.c:3675 [inline] __do_sys_mount fs/namespace.c:3884 [inline] __se_sys_mount+0x2d9/0x3c0 fs/namespace.c:3861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #0 (btrfs-tree-01){++++}-{3:3}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- rlock(btrfs-tree-00); lock(btrfs-tree-01); lock(btrfs-tree-00); rlock(btrfs-tree-01); *** DEADLOCK *** 1 lock held by syz-executor277/5012: #0: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 stack backtrace: CPU: 1 PID: 5012 Comm: syz-executor277 Not tainted 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 check_noncircular+0x375/0x4a0 kernel/locking/lockdep.c:2195 check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f0bec94ea39 Fix this simply by releasing the path before calling btrfs_iget() as at point we don't need the path anymore. Reported-by: syzbot+bf66ad948981797d2f1d(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/00000000000045fa140603c4a969@google.com/ Fixes: 23d0b79dfaed ("btrfs: Add unprivileged version of ino_lookup ioctl") CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a895d105464b..d27b0d86b8e2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1958,6 +1958,13 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, goto out_put; } + /* + * We don't need the path anymore, so release it and + * avoid deadlocks and lockdep warnings in case + * btrfs_iget() needs to lookup the inode from its root + * btree and lock the same leaf. + */ + btrfs_release_path(path); temp_inode = btrfs_iget(sb, key2.objectid, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); @@ -1978,7 +1985,6 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, goto out_put; } - btrfs_release_path(path); key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid;

1 year, 7 months

1
0
0 0

FAILED: patch "[PATCH] btrfs: release path before inode lookup during the ino lookup" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x ee34a82e890a7babb5585daf1a6dd7d4d1cf142a # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023092054-antibody-prenatal-dc3c@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: ee34a82e890a ("btrfs: release path before inode lookup during the ino lookup ioctl") 0202e83fdab0 ("btrfs: simplify iget helpers") c75e839414d3 ("btrfs: kill the subvol_srcu") 5c8fd99fec9d ("btrfs: make inodes hold a ref on their roots") 7ac8b88ee668 ("btrfs: backref, only collect file extent items matching backref offset") 0024652895e3 ("btrfs: rename btrfs_put_fs_root and btrfs_grab_fs_root") bd647ce385ec ("btrfs: add a leak check for roots") 8260edba67a2 ("btrfs: make the init of static elements in fs_info separate") ae18c37ad5a1 ("btrfs: move fs_info init work into it's own helper function") 141386e1a5d6 ("btrfs: free more things in btrfs_free_fs_info") bc44d7c4b2b1 ("btrfs: push btrfs_grab_fs_root into btrfs_get_fs_root") 81f096edf047 ("btrfs: use btrfs_put_fs_root to free roots always") 0d4b0463011d ("btrfs: export and rename free_fs_info") fbb0ce40d606 ("btrfs: hold a ref on the root in btrfs_check_uuid_tree_entry") ca2037fba6af ("btrfs: hold a ref on the root in btrfs_recover_log_trees") 5119cfc36f6d ("btrfs: hold a ref on the root in create_pending_snapshot") 5168489a079a ("btrfs: hold a ref on the root in get_subvol_name_from_objectid") 6f9a3da5da9e ("btrfs: hold a ref on the root in btrfs_ioctl_send") fd79d43b347e ("btrfs: hold a ref on the root in scrub_print_warning_inode") 0b2dee5cff74 ("btrfs: hold a ref for the root in btrfs_find_orphan_roots") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From ee34a82e890a7babb5585daf1a6dd7d4d1cf142a Mon Sep 17 00:00:00 2001 From: Filipe Manana <fdmanana(a)suse.com> Date: Sat, 26 Aug 2023 11:28:20 +0100 Subject: [PATCH] btrfs: release path before inode lookup during the ino lookup ioctl During the ino lookup ioctl we can end up calling btrfs_iget() to get an inode reference while we are holding on a root's btree. If btrfs_iget() needs to lookup the inode from the root's btree, because it's not currently loaded in memory, then it will need to lock another or the same path in the same root btree. This may result in a deadlock and trigger the following lockdep splat: WARNING: possible circular locking dependency detected 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Not tainted ------------------------------------------------------ syz-executor277/5012 is trying to acquire lock: ffff88802df41710 (btrfs-tree-01){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 but task is already holding lock: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (btrfs-tree-00){++++}-{3:3}: down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_search_slot+0x13a4/0x2f80 fs/btrfs/ctree.c:2302 btrfs_init_root_free_objectid+0x148/0x320 fs/btrfs/disk-io.c:4955 btrfs_init_fs_root fs/btrfs/disk-io.c:1128 [inline] btrfs_get_root_ref+0x5ae/0xae0 fs/btrfs/disk-io.c:1338 btrfs_get_fs_root fs/btrfs/disk-io.c:1390 [inline] open_ctree+0x29c8/0x3030 fs/btrfs/disk-io.c:3494 btrfs_fill_super+0x1c7/0x2f0 fs/btrfs/super.c:1154 btrfs_mount_root+0x7e0/0x910 fs/btrfs/super.c:1519 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 fc_mount fs/namespace.c:1112 [inline] vfs_kern_mount+0xbc/0x150 fs/namespace.c:1142 btrfs_mount+0x39f/0xb50 fs/btrfs/super.c:1579 legacy_get_tree+0xef/0x190 fs/fs_context.c:611 vfs_get_tree+0x8c/0x270 fs/super.c:1519 do_new_mount+0x28f/0xae0 fs/namespace.c:3335 do_mount fs/namespace.c:3675 [inline] __do_sys_mount fs/namespace.c:3884 [inline] __se_sys_mount+0x2d9/0x3c0 fs/namespace.c:3861 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd -> #0 (btrfs-tree-01){++++}-{3:3}: check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- rlock(btrfs-tree-00); lock(btrfs-tree-01); lock(btrfs-tree-00); rlock(btrfs-tree-01); *** DEADLOCK *** 1 lock held by syz-executor277/5012: #0: ffff88802df418e8 (btrfs-tree-00){++++}-{3:3}, at: __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 stack backtrace: CPU: 1 PID: 5012 Comm: syz-executor277 Not tainted 6.5.0-rc7-syzkaller-00004-gf7757129e3de #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/26/2023 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0x1e7/0x2d0 lib/dump_stack.c:106 check_noncircular+0x375/0x4a0 kernel/locking/lockdep.c:2195 check_prev_add kernel/locking/lockdep.c:3142 [inline] check_prevs_add kernel/locking/lockdep.c:3261 [inline] validate_chain kernel/locking/lockdep.c:3876 [inline] __lock_acquire+0x39ff/0x7f70 kernel/locking/lockdep.c:5144 lock_acquire+0x1e3/0x520 kernel/locking/lockdep.c:5761 down_read_nested+0x49/0x2f0 kernel/locking/rwsem.c:1645 __btrfs_tree_read_lock+0x2f/0x220 fs/btrfs/locking.c:136 btrfs_tree_read_lock fs/btrfs/locking.c:142 [inline] btrfs_read_lock_root_node+0x292/0x3c0 fs/btrfs/locking.c:281 btrfs_search_slot_get_root fs/btrfs/ctree.c:1832 [inline] btrfs_search_slot+0x4ff/0x2f80 fs/btrfs/ctree.c:2154 btrfs_lookup_inode+0xdc/0x480 fs/btrfs/inode-item.c:412 btrfs_read_locked_inode fs/btrfs/inode.c:3892 [inline] btrfs_iget_path+0x2d9/0x1520 fs/btrfs/inode.c:5716 btrfs_search_path_in_tree_user fs/btrfs/ioctl.c:1961 [inline] btrfs_ioctl_ino_lookup_user+0x77a/0xf50 fs/btrfs/ioctl.c:2105 btrfs_ioctl+0xb0b/0xd40 fs/btrfs/ioctl.c:4683 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xf8/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x41/0xc0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7f0bec94ea39 Fix this simply by releasing the path before calling btrfs_iget() as at point we don't need the path anymore. Reported-by: syzbot+bf66ad948981797d2f1d(a)syzkaller.appspotmail.com Link: https://lore.kernel.org/linux-btrfs/00000000000045fa140603c4a969@google.com/ Fixes: 23d0b79dfaed ("btrfs: Add unprivileged version of ino_lookup ioctl") CC: stable(a)vger.kernel.org # 4.19+ Reviewed-by: Josef Bacik <josef(a)toxicpanda.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a895d105464b..d27b0d86b8e2 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -1958,6 +1958,13 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, goto out_put; } + /* + * We don't need the path anymore, so release it and + * avoid deadlocks and lockdep warnings in case + * btrfs_iget() needs to lookup the inode from its root + * btree and lock the same leaf. + */ + btrfs_release_path(path); temp_inode = btrfs_iget(sb, key2.objectid, root); if (IS_ERR(temp_inode)) { ret = PTR_ERR(temp_inode); @@ -1978,7 +1985,6 @@ static int btrfs_search_path_in_tree_user(struct mnt_idmap *idmap, goto out_put; } - btrfs_release_path(path); key.objectid = key.offset; key.offset = (u64)-1; dirid = key.objectid;

1 year, 7 months

1
0
0 0

FAILED: patch "[PATCH] dm: fix a race condition in retrieve_deps" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x f6007dce0cd35d634d9be91ef3515a6385dcee16 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023092039-pulmonary-map-20ae@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: f6007dce0cd3 ("dm: fix a race condition in retrieve_deps") 43e6c111824c ("dm: change from DMWARN to DMERR or DMCRIT for fatal errors") 564b5c5476cd ("dm table: audit all dm_table_get_target() callers") 2aec377a2925 ("dm table: remove dm_table_get_num_targets() wrapper") e810cb78bc4b ("dm: refactor dm_md_mempool allocation") 9571f829f30a ("dm table: fix dm_table_supports_poll to return false if no data devices") 0f14d60a023c ("dm: improve dm_io reference counting") 3b03f7c1242c ("dm: simplify dm_start_io_acct") 4857abf66434 ("dm: simplify dm_io access in dm_split_and_process_bio") 84b98f4ce4d1 ("dm: factor out dm_io_set_error and __dm_io_dec_pending") cfc97abcbe0b ("dm: conditionally enable BIOSET_PERCPU_CACHE for dm_io bioset") 7dd06a2548b2 ("dm: allow dm_accept_partial_bio() for dm_io without duplicate bios") 5291984004ed ("dm: fix bio polling to handle possibile BLK_STS_AGAIN") 4d7bca13dd9a ("dm: consolidate spinlocks in dm_io struct") bd4a6dd241ae ("dm: reduce size of dm_io and dm_target_io structs") 655f3aad7aa4 ("dm: switch dm_target_io booleans over to proper flags") 82f6cdcc3676 ("dm: switch dm_io booleans over to proper flags") e27363472f9b ("dm: factor out dm_io_complete") b7f8dff09827 ("dm: simplify dm_sumbit_bio_remap interface") a92512819b1f ("dm thin: use dm_submit_bio_remap") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f6007dce0cd35d634d9be91ef3515a6385dcee16 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka <mpatocka(a)redhat.com> Date: Wed, 9 Aug 2023 12:44:20 +0200 Subject: [PATCH] dm: fix a race condition in retrieve_deps There's a race condition in the multipath target when retrieve_deps races with multipath_message calling dm_get_device and dm_put_device. retrieve_deps walks the list of open devices without holding any lock but multipath may add or remove devices to the list while it is running. The end result may be memory corruption or use-after-free memory access. See this description of a UAF with multipath_message(): https://listman.redhat.com/archives/dm-devel/2022-October/052373.html Fix this bug by introducing a new rw semaphore "devices_lock". We grab devices_lock for read in retrieve_deps and we grab it for write in dm_get_device and dm_put_device. Reported-by: Luo Meng <luomeng12(a)huawei.com> Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Cc: stable(a)vger.kernel.org Tested-by: Li Lingfeng <lilingfeng3(a)huawei.com> Signed-off-by: Mike Snitzer <snitzer(a)kernel.org> diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 0d93661f88d3..095b9b49aa82 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -214,6 +214,7 @@ struct dm_table { /* a list of devices used by this table */ struct list_head devices; + struct rw_semaphore devices_lock; /* events get handed up using this callback */ void (*event_fn)(void *data); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index f5ed729a8e0c..21ebb6c39394 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1630,6 +1630,8 @@ static void retrieve_deps(struct dm_table *table, struct dm_dev_internal *dd; struct dm_target_deps *deps; + down_read(&table->devices_lock); + deps = get_result_buffer(param, param_size, &len); /* @@ -1644,7 +1646,7 @@ static void retrieve_deps(struct dm_table *table, needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; - return; + goto out; } /* @@ -1656,6 +1658,9 @@ static void retrieve_deps(struct dm_table *table, deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev); param->data_size = param->data_start + needed; + +out: + up_read(&table->devices_lock); } static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 7d208b2b1a19..37b48f63ae6a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -135,6 +135,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); + init_rwsem(&t->devices_lock); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -359,16 +360,20 @@ int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, if (dev == disk_devt(t->md->disk)) return -EINVAL; + down_write(&t->devices_lock); + dd = find_device(&t->devices, dev); if (!dd) { dd = kmalloc(sizeof(*dd), GFP_KERNEL); - if (!dd) - return -ENOMEM; + if (!dd) { + r = -ENOMEM; + goto unlock_ret_r; + } r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev); if (r) { kfree(dd); - return r; + goto unlock_ret_r; } refcount_set(&dd->count, 1); @@ -378,12 +383,17 @@ int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { r = upgrade_mode(dd, mode, t->md); if (r) - return r; + goto unlock_ret_r; } refcount_inc(&dd->count); out: + up_write(&t->devices_lock); *result = dd->dm_dev; return 0; + +unlock_ret_r: + up_write(&t->devices_lock); + return r; } EXPORT_SYMBOL(dm_get_device); @@ -419,9 +429,12 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, void dm_put_device(struct dm_target *ti, struct dm_dev *d) { int found = 0; - struct list_head *devices = &ti->table->devices; + struct dm_table *t = ti->table; + struct list_head *devices = &t->devices; struct dm_dev_internal *dd; + down_write(&t->devices_lock); + list_for_each_entry(dd, devices, list) { if (dd->dm_dev == d) { found = 1; @@ -430,14 +443,17 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } if (!found) { DMERR("%s: device %s not in table devices list", - dm_device_name(ti->table->md), d->name); - return; + dm_device_name(t->md), d->name); + goto unlock_ret; } if (refcount_dec_and_test(&dd->count)) { - dm_put_table_device(ti->table->md, d); + dm_put_table_device(t->md, d); list_del(&dd->list); kfree(dd); } + +unlock_ret: + up_write(&t->devices_lock); } EXPORT_SYMBOL(dm_put_device);

1 year, 7 months

1
0
0 0

FAILED: patch "[PATCH] dm: fix a race condition in retrieve_deps" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x f6007dce0cd35d634d9be91ef3515a6385dcee16 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023092038-jingle-defuse-c9fa@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: f6007dce0cd3 ("dm: fix a race condition in retrieve_deps") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f6007dce0cd35d634d9be91ef3515a6385dcee16 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka <mpatocka(a)redhat.com> Date: Wed, 9 Aug 2023 12:44:20 +0200 Subject: [PATCH] dm: fix a race condition in retrieve_deps There's a race condition in the multipath target when retrieve_deps races with multipath_message calling dm_get_device and dm_put_device. retrieve_deps walks the list of open devices without holding any lock but multipath may add or remove devices to the list while it is running. The end result may be memory corruption or use-after-free memory access. See this description of a UAF with multipath_message(): https://listman.redhat.com/archives/dm-devel/2022-October/052373.html Fix this bug by introducing a new rw semaphore "devices_lock". We grab devices_lock for read in retrieve_deps and we grab it for write in dm_get_device and dm_put_device. Reported-by: Luo Meng <luomeng12(a)huawei.com> Signed-off-by: Mikulas Patocka <mpatocka(a)redhat.com> Cc: stable(a)vger.kernel.org Tested-by: Li Lingfeng <lilingfeng3(a)huawei.com> Signed-off-by: Mike Snitzer <snitzer(a)kernel.org> diff --git a/drivers/md/dm-core.h b/drivers/md/dm-core.h index 0d93661f88d3..095b9b49aa82 100644 --- a/drivers/md/dm-core.h +++ b/drivers/md/dm-core.h @@ -214,6 +214,7 @@ struct dm_table { /* a list of devices used by this table */ struct list_head devices; + struct rw_semaphore devices_lock; /* events get handed up using this callback */ void (*event_fn)(void *data); diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c index f5ed729a8e0c..21ebb6c39394 100644 --- a/drivers/md/dm-ioctl.c +++ b/drivers/md/dm-ioctl.c @@ -1630,6 +1630,8 @@ static void retrieve_deps(struct dm_table *table, struct dm_dev_internal *dd; struct dm_target_deps *deps; + down_read(&table->devices_lock); + deps = get_result_buffer(param, param_size, &len); /* @@ -1644,7 +1646,7 @@ static void retrieve_deps(struct dm_table *table, needed = struct_size(deps, dev, count); if (len < needed) { param->flags |= DM_BUFFER_FULL_FLAG; - return; + goto out; } /* @@ -1656,6 +1658,9 @@ static void retrieve_deps(struct dm_table *table, deps->dev[count++] = huge_encode_dev(dd->dm_dev->bdev->bd_dev); param->data_size = param->data_start + needed; + +out: + up_read(&table->devices_lock); } static int table_deps(struct file *filp, struct dm_ioctl *param, size_t param_size) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 7d208b2b1a19..37b48f63ae6a 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -135,6 +135,7 @@ int dm_table_create(struct dm_table **result, blk_mode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); + init_rwsem(&t->devices_lock); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -359,16 +360,20 @@ int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, if (dev == disk_devt(t->md->disk)) return -EINVAL; + down_write(&t->devices_lock); + dd = find_device(&t->devices, dev); if (!dd) { dd = kmalloc(sizeof(*dd), GFP_KERNEL); - if (!dd) - return -ENOMEM; + if (!dd) { + r = -ENOMEM; + goto unlock_ret_r; + } r = dm_get_table_device(t->md, dev, mode, &dd->dm_dev); if (r) { kfree(dd); - return r; + goto unlock_ret_r; } refcount_set(&dd->count, 1); @@ -378,12 +383,17 @@ int __ref dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode, } else if (dd->dm_dev->mode != (mode | dd->dm_dev->mode)) { r = upgrade_mode(dd, mode, t->md); if (r) - return r; + goto unlock_ret_r; } refcount_inc(&dd->count); out: + up_write(&t->devices_lock); *result = dd->dm_dev; return 0; + +unlock_ret_r: + up_write(&t->devices_lock); + return r; } EXPORT_SYMBOL(dm_get_device); @@ -419,9 +429,12 @@ static int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev, void dm_put_device(struct dm_target *ti, struct dm_dev *d) { int found = 0; - struct list_head *devices = &ti->table->devices; + struct dm_table *t = ti->table; + struct list_head *devices = &t->devices; struct dm_dev_internal *dd; + down_write(&t->devices_lock); + list_for_each_entry(dd, devices, list) { if (dd->dm_dev == d) { found = 1; @@ -430,14 +443,17 @@ void dm_put_device(struct dm_target *ti, struct dm_dev *d) } if (!found) { DMERR("%s: device %s not in table devices list", - dm_device_name(ti->table->md), d->name); - return; + dm_device_name(t->md), d->name); + goto unlock_ret; } if (refcount_dec_and_test(&dd->count)) { - dm_put_table_device(ti->table->md, d); + dm_put_table_device(t->md, d); list_del(&dd->list); kfree(dd); } + +unlock_ret: + up_write(&t->devices_lock); } EXPORT_SYMBOL(dm_put_device);

1 year, 7 months

1
0
0 0

[PATCH 0/5] netfilter: Reinstate dropped Stable patches

by Lee Jones

Dropped in August: https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/com… https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git/com… Only re-applied and build tested against v6.1.53. If they do apply and test well against linux-5.{4,10,15}, all the better. Florian Westphal (1): netfilter: nf_tables: don't skip expired elements during walk Pablo Neira Ayuso (4): netfilter: nf_tables: GC transaction API to avoid race with control plane netfilter: nf_tables: adapt set backend to use GC transaction API netfilter: nft_set_hash: mark set element as dead when deleting from packet path netfilter: nf_tables: remove busy mark and gc batch API include/net/netfilter/nf_tables.h | 120 +++++------- net/netfilter/nf_tables_api.c | 307 ++++++++++++++++++++++++------ net/netfilter/nft_set_hash.c | 85 +++++---- net/netfilter/nft_set_pipapo.c | 66 +++++-- net/netfilter/nft_set_rbtree.c | 146 ++++++++------ 5 files changed, 476 insertions(+), 248 deletions(-) -- 2.42.0.459.ge4e396fd5e-goog

1 year, 7 months

2
8
0 0

[tip: sched/urgent] kernel/sched: Modify initial boot task idle setup

by tip-bot2 for Liam R. Howlett

The following commit has been merged into the sched/urgent branch of tip: Commit-ID: cff9b2332ab762b7e0586c793c431a8f2ea4db04 Gitweb: https://git.kernel.org/tip/cff9b2332ab762b7e0586c793c431a8f2ea4db04 Author: Liam R. Howlett <Liam.Howlett(a)oracle.com> AuthorDate: Fri, 15 Sep 2023 13:44:44 -04:00 Committer: Peter Zijlstra <peterz(a)infradead.org> CommitterDate: Tue, 19 Sep 2023 10:48:04 +02:00 kernel/sched: Modify initial boot task idle setup Initial booting is setting the task flag to idle (PF_IDLE) by the call path sched_init() -> init_idle(). Having the task idle and calling call_rcu() in kernel/rcu/tiny.c means that TIF_NEED_RESCHED will be set. Subsequent calls to any cond_resched() will enable IRQs, potentially earlier than the IRQ setup has completed. Recent changes have caused just this scenario and IRQs have been enabled early. This causes a warning later in start_kernel() as interrupts are enabled before they are fully set up. Fix this issue by setting the PF_IDLE flag later in the boot sequence. Although the boot task was marked as idle since (at least) d80e4fda576d, I am not sure that it is wrong to do so. The forced context-switch on idle task was introduced in the tiny_rcu update, so I'm going to claim this fixes 5f6130fa52ee. Fixes: 5f6130fa52ee ("tiny_rcu: Directly force QS when call_rcu_[bh|sched]() on idle_task") Signed-off-by: Liam R. Howlett <Liam.Howlett(a)oracle.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/linux-mm/CAMuHMdWpvpWoDa=Ox-do92czYRvkok6_x6pYUH+Zo… --- kernel/sched/core.c | 2 +- kernel/sched/idle.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2299a5c..802551e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -9269,7 +9269,7 @@ void __init init_idle(struct task_struct *idle, int cpu) * PF_KTHREAD should already be set at this point; regardless, make it * look like a proper per-CPU kthread. */ - idle->flags |= PF_IDLE | PF_KTHREAD | PF_NO_SETAFFINITY; + idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY; kthread_set_per_cpu(idle, cpu); #ifdef CONFIG_SMP diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 342f58a..5007b25 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -373,6 +373,7 @@ EXPORT_SYMBOL_GPL(play_idle_precise); void cpu_startup_entry(enum cpuhp_state state) { + current->flags |= PF_IDLE; arch_cpu_idle_prepare(); cpuhp_online_idle(state); while (1)

1 year, 7 months

1
0
0 0

[PATCH AUTOSEL 6.5 01/36] drm/bridge: tc358762: Instruct DSI host to generate HSE packets

by Sasha Levin

From: Marek Vasut <marex(a)denx.de> [ Upstream commit 362fa8f6e6a05089872809f4465bab9d011d05b3 ] This bridge seems to need the HSE packet, otherwise the image is shifted up and corrupted at the bottom. This makes the bridge work with Samsung DSIM on i.MX8MM and i.MX8MP. Signed-off-by: Marek Vasut <marex(a)denx.de> Reviewed-by: Sam Ravnborg <sam(a)ravnborg.org> Signed-off-by: Robert Foss <rfoss(a)kernel.org> Link: https://patchwork.freedesktop.org/patch/msgid/20230615201902.566182-3-marex… Signed-off-by: Sasha Levin <sashal(a)kernel.org> --- drivers/gpu/drm/bridge/tc358762.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/bridge/tc358762.c b/drivers/gpu/drm/bridge/tc358762.c index 5641395fd310e..11445c50956e1 100644 --- a/drivers/gpu/drm/bridge/tc358762.c +++ b/drivers/gpu/drm/bridge/tc358762.c @@ -231,7 +231,7 @@ static int tc358762_probe(struct mipi_dsi_device *dsi) dsi->lanes = 1; dsi->format = MIPI_DSI_FMT_RGB888; dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE | - MIPI_DSI_MODE_LPM; + MIPI_DSI_MODE_LPM | MIPI_DSI_MODE_VIDEO_HSE; ret = tc358762_parse_dt(ctx); if (ret < 0) -- 2.40.1

1 year, 7 months

5
47
0 0

[PATCH] i915: Limit the length of an sg list to the requested length

by Matthew Wilcox (Oracle)

The folio conversion changed the behaviour of shmem_sg_alloc_table() to put the entire length of the last folio into the sg list, even if the sg list should have been shorter. gen8_ggtt_insert_entries() relied on the list being the right langth and would overrun the end of the page tables. Other functions may also have been affected. Clamp the length of the last entry in the sg list to be the expected length. Signed-off-by: Matthew Wilcox (Oracle) <willy(a)infradead.org> Fixes: 0b62af28f249 ("i915: convert shmem_sg_free_table() to use a folio_batch") Cc: stable(a)vger.kernel.org # 6.5.x Link: https://gitlab.freedesktop.org/drm/intel/-/issues/9256 Link: https://lore.kernel.org/lkml/6287208.lOV4Wx5bFT@natalenko.name/ Reported-by: Oleksandr Natalenko <oleksandr(a)natalenko.name> Tested-by: Oleksandr Natalenko <oleksandr(a)natalenko.name> --- drivers/gpu/drm/i915/gem/i915_gem_shmem.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c index 8f1633c3fb93..73a4a4eb29e0 100644 --- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c +++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c @@ -100,6 +100,7 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, st->nents = 0; for (i = 0; i < page_count; i++) { struct folio *folio; + unsigned long nr_pages; const unsigned int shrink[] = { I915_SHRINK_BOUND | I915_SHRINK_UNBOUND, 0, @@ -150,6 +151,8 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, } } while (1); + nr_pages = min_t(unsigned long, + folio_nr_pages(folio), page_count - i); if (!i || sg->length >= max_segment || folio_pfn(folio) != next_pfn) { @@ -157,13 +160,13 @@ int shmem_sg_alloc_table(struct drm_i915_private *i915, struct sg_table *st, sg = sg_next(sg); st->nents++; - sg_set_folio(sg, folio, folio_size(folio), 0); + sg_set_folio(sg, folio, nr_pages * PAGE_SIZE, 0); } else { /* XXX: could overflow? */ - sg->length += folio_size(folio); + sg->length += nr_pages * PAGE_SIZE; } - next_pfn = folio_pfn(folio) + folio_nr_pages(folio); - i += folio_nr_pages(folio) - 1; + next_pfn = folio_pfn(folio) + nr_pages; + i += nr_pages - 1; /* Check that the i965g/gm workaround works. */ GEM_BUG_ON(gfp & __GFP_DMA32 && next_pfn >= 0x00100000UL); -- 2.40.1

1 year, 7 months

2
1
0 0

[PATCH v6.1.y] net/sched: Retire rsvp classifier

by Kyle Zeng

commit 265b4da82dbf5df04bee5a5d46b7474b1aaf326a upstream. The rsvp classifier has served us well for about a quarter of a century but has has not been getting much maintenance attention due to lack of known users. Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Acked-by: Jiri Pirko <jiri(a)nvidia.com> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> --- Please apply this patch to v6.1.y. This patch adapts the original patch to v6.1.y considering codebase change. This patch retires rsvp classifier which is what the upstream patch did. This patch has been tested against the v6.1.y stable tree. net/sched/Kconfig | 28 - net/sched/Makefile | 2 - net/sched/cls_rsvp.c | 24 - net/sched/cls_rsvp.h | 764 ------------------ net/sched/cls_rsvp6.c | 24 - .../tc-testing/tc-tests/filters/rsvp.json | 203 ----- 6 files changed, 1045 deletions(-) delete mode 100644 net/sched/cls_rsvp.c delete mode 100644 net/sched/cls_rsvp.h delete mode 100644 net/sched/cls_rsvp6.c delete mode 100644 tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bcdd6e925343..24cf0bf7c80e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -548,34 +548,6 @@ config CLS_U32_MARK help Say Y here to be able to use netfilter marks as u32 key. -config NET_CLS_RSVP - tristate "IPv4 Resource Reservation Protocol (RSVP)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp. - -config NET_CLS_RSVP6 - tristate "IPv6 Resource Reservation Protocol (RSVP6)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6 protocol. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp6. - config NET_CLS_FLOW tristate "Flow classifier" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index b7dbac5c519f..8a33a35fc50d 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -69,8 +69,6 @@ obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o -obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c deleted file mode 100644 index de1c1d4da597..000000000000 --- a/net/sched/cls_rsvp.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4. - * - * Authors: Alexey Kuznetsov, <kuznet(a)ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> - -#define RSVP_DST_LEN 1 -#define RSVP_ID "rsvp" -#define RSVP_OPS cls_rsvp_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h deleted file mode 100644 index b00a7dbd0587..000000000000 --- a/net/sched/cls_rsvp.h +++ /dev/null @@ -1,764 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers. - * - * Authors: Alexey Kuznetsov, <kuznet(a)ms2.inr.ac.ru> - */ - -/* - Comparing to general packet classification problem, - RSVP needs only several relatively simple rules: - - * (dst, protocol) are always specified, - so that we are able to hash them. - * src may be exact, or may be wildcard, so that - we can keep a hash table plus one wildcard entry. - * source port (or flow label) is important only if src is given. - - IMPLEMENTATION. - - We use a two level hash table: The top level is keyed by - destination address and protocol ID, every bucket contains a list - of "rsvp sessions", identified by destination address, protocol and - DPI(="Destination Port ID"): triple (key, mask, offset). - - Every bucket has a smaller hash table keyed by source address - (cf. RSVP flowspec) and one wildcard entry for wildcard reservations. - Every bucket is again a list of "RSVP flows", selected by - source address and SPI(="Source Port ID" here rather than - "security parameter index"): triple (key, mask, offset). - - - NOTE 1. All the packets with IPv6 extension headers (but AH and ESP) - and all fragmented packets go to the best-effort traffic class. - - - NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires - only one "Generalized Port Identifier". So that for classic - ah, esp (and udp,tcp) both *pi should coincide or one of them - should be wildcard. - - At first sight, this redundancy is just a waste of CPU - resources. But DPI and SPI add the possibility to assign different - priorities to GPIs. Look also at note 4 about tunnels below. - - - NOTE 3. One complication is the case of tunneled packets. - We implement it as following: if the first lookup - matches a special session with "tunnelhdr" value not zero, - flowid doesn't contain the true flow ID, but the tunnel ID (1...255). - In this case, we pull tunnelhdr bytes and restart lookup - with tunnel ID added to the list of keys. Simple and stupid 8)8) - It's enough for PIMREG and IPIP. - - - NOTE 4. Two GPIs make it possible to parse even GRE packets. - F.e. DPI can select ETH_P_IP (and necessary flags to make - tunnelhdr correct) in GRE protocol field and SPI matches - GRE key. Is it not nice? 8)8) - - - Well, as result, despite its simplicity, we get a pretty - powerful classification engine. */ - - -struct rsvp_head { - u32 tmap[256/32]; - u32 hgenerator; - u8 tgenerator; - struct rsvp_session __rcu *ht[256]; - struct rcu_head rcu; -}; - -struct rsvp_session { - struct rsvp_session __rcu *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; - /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter __rcu *ht[16 + 1]; - struct rcu_head rcu; -}; - - -struct rsvp_filter { - struct rsvp_filter __rcu *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; - - struct tcf_result res; - struct tcf_exts exts; - - u32 handle; - struct rsvp_session *sess; - struct rcu_work rwork; -}; - -static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) -{ - unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; - - h ^= h>>16; - h ^= h>>8; - return (h ^ protocol ^ tunnelid) & 0xFF; -} - -static inline unsigned int hash_src(__be32 *src) -{ - unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; - - h ^= h>>16; - h ^= h>>8; - h ^= h>>4; - return h & 0xF; -} - -#define RSVP_APPLY_RESULT() \ -{ \ - int r = tcf_exts_exec(skb, &f->exts, res); \ - if (r < 0) \ - continue; \ - else if (r > 0) \ - return r; \ -} - -static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct rsvp_head *head = rcu_dereference_bh(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1, h2; - __be32 *dst, *src; - u8 protocol; - u8 tunnelid = 0; - u8 *xprt; -#if RSVP_DST_LEN == 4 - struct ipv6hdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ipv6_hdr(skb); -#else - struct iphdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ip_hdr(skb); -#endif -restart: - -#if RSVP_DST_LEN == 4 - src = &nhptr->saddr.s6_addr32[0]; - dst = &nhptr->daddr.s6_addr32[0]; - protocol = nhptr->nexthdr; - xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); -#else - src = &nhptr->saddr; - dst = &nhptr->daddr; - protocol = nhptr->protocol; - xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (ip_is_fragment(nhptr)) - return -1; -#endif - - h1 = hash_dst(dst, protocol, tunnelid); - h2 = hash_src(src); - - for (s = rcu_dereference_bh(head->ht[h1]); s; - s = rcu_dereference_bh(s->next)) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && - protocol == s->protocol && - !(s->dpi.mask & - (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - tunnelid == s->tunnelid) { - - for (f = rcu_dereference_bh(s->ht[h2]); f; - f = rcu_dereference_bh(f->next)) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && - !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) -#if RSVP_DST_LEN == 4 - && - src[0] == f->src[0] && - src[1] == f->src[1] && - src[2] == f->src[2] -#endif - ) { - *res = f->res; - RSVP_APPLY_RESULT(); - -matched: - if (f->tunnelhdr == 0) - return 0; - - tunnelid = f->res.classid; - nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); - goto restart; - } - } - - /* And wildcard bucket... */ - for (f = rcu_dereference_bh(s->ht[16]); f; - f = rcu_dereference_bh(f->next)) { - *res = f->res; - RSVP_APPLY_RESULT(); - goto matched; - } - return -1; - } - } - return -1; -} - -static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter __rcu **ins; - struct rsvp_filter *pins; - unsigned int h1 = h & 0xFF; - unsigned int h2 = (h >> 8) & 0xFF; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ; - ins = &pins->next, pins = rtnl_dereference(*ins)) { - if (pins->handle == h) { - RCU_INIT_POINTER(n->next, pins->next); - rcu_assign_pointer(*ins, n); - return; - } - } - } - - /* Something went wrong if we are trying to replace a non-existent - * node. Mind as well halt instead of silently failing. - */ - BUG_ON(1); -} - -static void *rsvp_get(struct tcf_proto *tp, u32 handle) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1 = handle & 0xFF; - unsigned int h2 = (handle >> 8) & 0xFF; - - if (h2 > 16) - return NULL; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->handle == handle) - return f; - } - } - return NULL; -} - -static int rsvp_init(struct tcf_proto *tp) -{ - struct rsvp_head *data; - - data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); - if (data) { - rcu_assign_pointer(tp->root, data); - return 0; - } - return -ENOBUFS; -} - -static void __rsvp_delete_filter(struct rsvp_filter *f) -{ - tcf_exts_destroy(&f->exts); - tcf_exts_put_net(&f->exts); - kfree(f); -} - -static void rsvp_delete_filter_work(struct work_struct *work) -{ - struct rsvp_filter *f = container_of(to_rcu_work(work), - struct rsvp_filter, - rwork); - rtnl_lock(); - __rsvp_delete_filter(f); - rtnl_unlock(); -} - -static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -{ - tcf_unbind_filter(tp, &f->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (tcf_exts_get_net(&f->exts)) - tcf_queue_work(&f->rwork, rsvp_delete_filter_work); - else - __rsvp_delete_filter(f); -} - -static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int h1, h2; - - if (data == NULL) - return; - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - - while ((s = rtnl_dereference(data->ht[h1])) != NULL) { - RCU_INIT_POINTER(data->ht[h1], s->next); - - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - while ((f = rtnl_dereference(s->ht[h2])) != NULL) { - rcu_assign_pointer(s->ht[h2], f->next); - rsvp_delete_filter(tp, f); - } - } - kfree_rcu(s, rcu); - } - } - kfree_rcu(data, rcu); -} - -static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = arg; - struct rsvp_filter __rcu **fp; - unsigned int h = f->handle; - struct rsvp_session __rcu **sp; - struct rsvp_session *nsp, *s = f->sess; - int i, h1; - - fp = &s->ht[(h >> 8) & 0xFF]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - if (nfp == f) { - RCU_INIT_POINTER(*fp, f->next); - rsvp_delete_filter(tp, f); - - /* Strip tree */ - - for (i = 0; i <= 16; i++) - if (s->ht[i]) - goto out; - - /* OK, session has no flows */ - sp = &head->ht[h & 0xFF]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if (nsp == s) { - RCU_INIT_POINTER(*sp, s->next); - kfree_rcu(s, rcu); - goto out; - } - } - - break; - } - } - -out: - *last = true; - for (h1 = 0; h1 < 256; h1++) { - if (rcu_access_pointer(head->ht[h1])) { - *last = false; - break; - } - } - - return 0; -} - -static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int i = 0xFFFF; - - while (i-- > 0) { - u32 h; - - if ((data->hgenerator += 0x10000) == 0) - data->hgenerator = 0x10000; - h = data->hgenerator|salt; - if (!rsvp_get(tp, h)) - return h; - } - return 0; -} - -static int tunnel_bts(struct rsvp_head *data) -{ - int n = data->tgenerator >> 5; - u32 b = 1 << (data->tgenerator & 0x1F); - - if (data->tmap[n] & b) - return 0; - data->tmap[n] |= b; - return 1; -} - -static void tunnel_recycle(struct rsvp_head *data) -{ - struct rsvp_session __rcu **sht = data->ht; - u32 tmap[256/32]; - int h1, h2; - - memset(tmap, 0, sizeof(tmap)); - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - for (s = rtnl_dereference(sht[h1]); s; - s = rtnl_dereference(s->next)) { - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->tunnelhdr == 0) - continue; - data->tgenerator = f->res.classid; - tunnel_bts(data); - } - } - } - } - - memcpy(data->tmap, tmap, sizeof(tmap)); -} - -static u32 gen_tunnel(struct rsvp_head *data) -{ - int i, k; - - for (k = 0; k < 2; k++) { - for (i = 255; i > 0; i--) { - if (++data->tgenerator == 0) - data->tgenerator = 1; - if (tunnel_bts(data)) - return data->tgenerator; - } - tunnel_recycle(data); - } - return 0; -} - -static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { - [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, -}; - -static int rsvp_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, struct nlattr **tca, - void **arg, u32 flags, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - struct rsvp_filter *f, *nfp; - struct rsvp_filter __rcu **fp; - struct rsvp_session *nsp, *s; - struct rsvp_session __rcu **sp; - struct tc_rsvp_pinfo *pinfo = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_RSVP_MAX + 1]; - struct tcf_exts e; - unsigned int h1, h2; - __be32 *dst; - int err; - - if (opt == NULL) - return handle ? -EINVAL : 0; - - err = nla_parse_nested_deprecated(tb, TCA_RSVP_MAX, opt, rsvp_policy, - NULL); - if (err < 0) - return err; - - err = tcf_exts_init(&e, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, flags, - extack); - if (err < 0) - goto errout2; - - f = *arg; - if (f) { - /* Node exists: adjust only classid */ - struct rsvp_filter *n; - - if (f->handle != handle && handle) - goto errout2; - - n = kmemdup(f, sizeof(*f), GFP_KERNEL); - if (!n) { - err = -ENOMEM; - goto errout2; - } - - err = tcf_exts_init(&n->exts, net, TCA_RSVP_ACT, - TCA_RSVP_POLICE); - if (err < 0) { - kfree(n); - goto errout2; - } - - if (tb[TCA_RSVP_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } - - tcf_exts_change(&n->exts, &e); - rsvp_replace(tp, n, handle); - return 0; - } - - /* Now more serious part... */ - err = -EINVAL; - if (handle) - goto errout2; - if (tb[TCA_RSVP_DST] == NULL) - goto errout2; - - err = -ENOBUFS; - f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL); - if (f == NULL) - goto errout2; - - err = tcf_exts_init(&f->exts, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - goto errout; - h2 = 16; - if (tb[TCA_RSVP_SRC]) { - memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); - h2 = hash_src(f->src); - } - if (tb[TCA_RSVP_PINFO]) { - pinfo = nla_data(tb[TCA_RSVP_PINFO]); - f->spi = pinfo->spi; - f->tunnelhdr = pinfo->tunnelhdr; - } - if (tb[TCA_RSVP_CLASSID]) - f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - - dst = nla_data(tb[TCA_RSVP_DST]); - h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0); - - err = -ENOMEM; - if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0) - goto errout; - - if (f->tunnelhdr) { - err = -EINVAL; - if (f->res.classid > 255) - goto errout; - - err = -ENOMEM; - if (f->res.classid == 0 && - (f->res.classid = gen_tunnel(data)) == 0) - goto errout; - } - - for (sp = &data->ht[h1]; - (s = rtnl_dereference(*sp)) != NULL; - sp = &s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && - pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - pinfo->tunnelid == s->tunnelid) { - -insert: - /* OK, we found appropriate session */ - - fp = &s->ht[h2]; - - f->sess = s; - if (f->tunnelhdr == 0) - tcf_bind_filter(tp, &f->res, base); - - tcf_exts_change(&f->exts, &e); - - fp = &s->ht[h2]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - __u32 mask = nfp->spi.mask & f->spi.mask; - - if (mask != f->spi.mask) - break; - } - RCU_INIT_POINTER(f->next, nfp); - rcu_assign_pointer(*fp, f); - - *arg = f; - return 0; - } - } - - /* No session found. Create new one. */ - - err = -ENOBUFS; - s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL); - if (s == NULL) - goto errout; - memcpy(s->dst, dst, sizeof(s->dst)); - - if (pinfo) { - s->dpi = pinfo->dpi; - s->protocol = pinfo->protocol; - s->tunnelid = pinfo->tunnelid; - } - sp = &data->ht[h1]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) - break; - } - RCU_INIT_POINTER(s->next, nsp); - rcu_assign_pointer(*sp, s); - - goto insert; - -errout: - tcf_exts_destroy(&f->exts); - kfree(f); -errout2: - tcf_exts_destroy(&e); - return err; -} - -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg, - bool rtnl_held) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - unsigned int h, h1; - - if (arg->stop) - return; - - for (h = 0; h < 256; h++) { - struct rsvp_session *s; - - for (s = rtnl_dereference(head->ht[h]); s; - s = rtnl_dereference(s->next)) { - for (h1 = 0; h1 <= 16; h1++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h1]); f; - f = rtnl_dereference(f->next)) { - if (!tc_cls_stats_dump(tp, arg, f)) - return; - } - } - } - } -} - -static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) -{ - struct rsvp_filter *f = fh; - struct rsvp_session *s; - struct nlattr *nest; - struct tc_rsvp_pinfo pinfo; - - if (f == NULL) - return skb->len; - s = f->sess; - - t->tcm_handle = f->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) - goto nla_put_failure; - pinfo.dpi = s->dpi; - pinfo.spi = f->spi; - pinfo.protocol = s->protocol; - pinfo.tunnelid = s->tunnelid; - pinfo.tunnelhdr = f->tunnelhdr; - pinfo.pad = 0; - if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) - goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) - goto nla_put_failure; - if (((f->handle >> 8) & 0xFF) != 16 && - nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &f->exts) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &f->exts) < 0) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, - unsigned long base) -{ - struct rsvp_filter *f = fh; - - tc_cls_bind_class(classid, cl, q, &f->res, base); -} - -static struct tcf_proto_ops RSVP_OPS __read_mostly = { - .kind = RSVP_ID, - .classify = rsvp_classify, - .init = rsvp_init, - .destroy = rsvp_destroy, - .get = rsvp_get, - .change = rsvp_change, - .delete = rsvp_delete, - .walk = rsvp_walk, - .dump = rsvp_dump, - .bind_class = rsvp_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_rsvp(void) -{ - return register_tcf_proto_ops(&RSVP_OPS); -} - -static void __exit exit_rsvp(void) -{ - unregister_tcf_proto_ops(&RSVP_OPS); -} - -module_init(init_rsvp) -module_exit(exit_rsvp) diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c deleted file mode 100644 index 64078846000e..000000000000 --- a/net/sched/cls_rsvp6.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6. - * - * Authors: Alexey Kuznetsov, <kuznet(a)ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/ipv6.h> -#include <linux/skbuff.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> -#include <net/netlink.h> - -#define RSVP_DST_LEN 4 -#define RSVP_ID "rsvp6" -#define RSVP_OPS cls_rsvp6_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json b/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json deleted file mode 100644 index bdcbaa4c5663..000000000000 --- a/tools/testing/selftests/tc-testing/tc-tests/filters/rsvp.json +++ /dev/null @@ -1,203 +0,0 @@ -[ - { - "id": "2141", - "name": "Add rsvp filter with tcp proto and specific IP address", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto tcp session 198.168.10.64", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*session 198.168.10.64 ipproto tcp", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "5267", - "name": "Add rsvp filter with udp proto and specific IP address", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*session 1.1.1.1 ipproto udp", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2819", - "name": "Add rsvp filter with src ip and src port", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 sender 2.2.2.2/5021 classid 1:1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp sender 2.2.2.2/5021", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "c967", - "name": "Add rsvp filter with tunnelid and continue action", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnelid 2 classid 1:1 action continue", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp tunnelid 2.*action order [0-9]+: gact action continue", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "5463", - "name": "Add rsvp filter with tunnel and pipe action", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnel 2 skip 1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*tunnel 2 skip 1 session 1.1.1.1 ipproto udp.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "2332", - "name": "Add rsvp filter with miltiple actions", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 7 rsvp ipproto udp session 1.1.1.1 classid 1:1 action skbedit mark 7 pipe action gact drop", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 1:1 session 1.1.1.1 ipproto udp.*action order [0-9]+: skbedit mark 7 pipe.*action order [0-9]+: gact action drop", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8879", - "name": "Add rsvp filter with tunnel and skp flag", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress" - ], - "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1 tunnel 2 skip 1 action pipe", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*tunnel 2 skip 1 session 1.1.1.1 ipproto udp.*action order [0-9]+: gact action pipe", - "matchCount": "1", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8261", - "name": "List rsvp filters", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 classid 1:1", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto tcp session 2.2.2.2/1234 classid 2:1" - ], - "cmdUnderTest": "$TC filter show dev $DEV1 parent ffff:", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "^filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh", - "matchCount": "2", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - }, - { - "id": "8989", - "name": "Delete rsvp filter", - "category": [ - "filter", - "rsvp" - ], - "plugins": { - "requires": "nsPlugin" - }, - "setup": [ - "$TC qdisc add dev $DEV1 ingress", - "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 tunnelid 9 classid 2:1" - ], - "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol ip prio 1 rsvp ipproto udp session 1.1.1.1/1234 tunnelid 9 classid 2:1", - "expExitCode": "0", - "verifyCmd": "$TC filter show dev $DEV1 parent ffff:", - "matchPattern": "filter protocol ip pref [0-9]+ rsvp chain [0-9]+ fh 0x.*flowid 2:1 session 1.1.1.1/1234 ipproto udp tunnelid 9", - "matchCount": "0", - "teardown": [ - "$TC qdisc del dev $DEV1 ingress" - ] - } -] -- 2.34.1

1 year, 7 months

1
0
0 0

[PATCH v5.15.y] net/sched: Retire rsvp classifier

by Kyle Zeng

commit 265b4da82dbf5df04bee5a5d46b7474b1aaf326a upstream. The rsvp classifier has served us well for about a quarter of a century but has has not been getting much maintenance attention due to lack of known users. Signed-off-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Acked-by: Jiri Pirko <jiri(a)nvidia.com> Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Kyle Zeng <zengyhkyle(a)gmail.com> --- Please apply this patch to v5.15.y. This patch adapts the original patch to v5.15.y considering codebase change. This patch retires rsvp classifier which is what the upstream patch did. This patch has been tested against the v5.15.y stable tree. net/sched/Kconfig | 28 -- net/sched/Makefile | 2 - net/sched/cls_rsvp.c | 24 -- net/sched/cls_rsvp.h | 776 ------------------------------------------ net/sched/cls_rsvp6.c | 24 -- 5 files changed, 854 deletions(-) delete mode 100644 net/sched/cls_rsvp.c delete mode 100644 net/sched/cls_rsvp.h delete mode 100644 net/sched/cls_rsvp6.c diff --git a/net/sched/Kconfig b/net/sched/Kconfig index bcdd6e925343..24cf0bf7c80e 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -548,34 +548,6 @@ config CLS_U32_MARK help Say Y here to be able to use netfilter marks as u32 key. -config NET_CLS_RSVP - tristate "IPv4 Resource Reservation Protocol (RSVP)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp. - -config NET_CLS_RSVP6 - tristate "IPv6 Resource Reservation Protocol (RSVP6)" - select NET_CLS - help - The Resource Reservation Protocol (RSVP) permits end systems to - request a minimum and maximum data flow rate for a connection; this - is important for real time data such as streaming sound or video. - - Say Y here if you want to be able to classify outgoing packets based - on their RSVP requests and you are using the IPv6 protocol. - - To compile this code as a module, choose M here: the - module will be called cls_rsvp6. - config NET_CLS_FLOW tristate "Flow classifier" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index b7dbac5c519f..8a33a35fc50d 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -69,8 +69,6 @@ obj-$(CONFIG_NET_SCH_TAPRIO) += sch_taprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o -obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o obj-$(CONFIG_NET_CLS_CGROUP) += cls_cgroup.o diff --git a/net/sched/cls_rsvp.c b/net/sched/cls_rsvp.c deleted file mode 100644 index de1c1d4da597..000000000000 --- a/net/sched/cls_rsvp.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp.c Special RSVP packet classifier for IPv4. - * - * Authors: Alexey Kuznetsov, <kuznet(a)ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/ip.h> -#include <net/netlink.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> - -#define RSVP_DST_LEN 1 -#define RSVP_ID "rsvp" -#define RSVP_OPS cls_rsvp_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h deleted file mode 100644 index 5cd9d6b143c4..000000000000 --- a/net/sched/cls_rsvp.h +++ /dev/null @@ -1,776 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-or-later */ -/* - * net/sched/cls_rsvp.h Template file for RSVPv[46] classifiers. - * - * Authors: Alexey Kuznetsov, <kuznet(a)ms2.inr.ac.ru> - */ - -/* - Comparing to general packet classification problem, - RSVP needs only several relatively simple rules: - - * (dst, protocol) are always specified, - so that we are able to hash them. - * src may be exact, or may be wildcard, so that - we can keep a hash table plus one wildcard entry. - * source port (or flow label) is important only if src is given. - - IMPLEMENTATION. - - We use a two level hash table: The top level is keyed by - destination address and protocol ID, every bucket contains a list - of "rsvp sessions", identified by destination address, protocol and - DPI(="Destination Port ID"): triple (key, mask, offset). - - Every bucket has a smaller hash table keyed by source address - (cf. RSVP flowspec) and one wildcard entry for wildcard reservations. - Every bucket is again a list of "RSVP flows", selected by - source address and SPI(="Source Port ID" here rather than - "security parameter index"): triple (key, mask, offset). - - - NOTE 1. All the packets with IPv6 extension headers (but AH and ESP) - and all fragmented packets go to the best-effort traffic class. - - - NOTE 2. Two "port id"'s seems to be redundant, rfc2207 requires - only one "Generalized Port Identifier". So that for classic - ah, esp (and udp,tcp) both *pi should coincide or one of them - should be wildcard. - - At first sight, this redundancy is just a waste of CPU - resources. But DPI and SPI add the possibility to assign different - priorities to GPIs. Look also at note 4 about tunnels below. - - - NOTE 3. One complication is the case of tunneled packets. - We implement it as following: if the first lookup - matches a special session with "tunnelhdr" value not zero, - flowid doesn't contain the true flow ID, but the tunnel ID (1...255). - In this case, we pull tunnelhdr bytes and restart lookup - with tunnel ID added to the list of keys. Simple and stupid 8)8) - It's enough for PIMREG and IPIP. - - - NOTE 4. Two GPIs make it possible to parse even GRE packets. - F.e. DPI can select ETH_P_IP (and necessary flags to make - tunnelhdr correct) in GRE protocol field and SPI matches - GRE key. Is it not nice? 8)8) - - - Well, as result, despite its simplicity, we get a pretty - powerful classification engine. */ - - -struct rsvp_head { - u32 tmap[256/32]; - u32 hgenerator; - u8 tgenerator; - struct rsvp_session __rcu *ht[256]; - struct rcu_head rcu; -}; - -struct rsvp_session { - struct rsvp_session __rcu *next; - __be32 dst[RSVP_DST_LEN]; - struct tc_rsvp_gpi dpi; - u8 protocol; - u8 tunnelid; - /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter __rcu *ht[16 + 1]; - struct rcu_head rcu; -}; - - -struct rsvp_filter { - struct rsvp_filter __rcu *next; - __be32 src[RSVP_DST_LEN]; - struct tc_rsvp_gpi spi; - u8 tunnelhdr; - - struct tcf_result res; - struct tcf_exts exts; - - u32 handle; - struct rsvp_session *sess; - struct rcu_work rwork; -}; - -static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) -{ - unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; - - h ^= h>>16; - h ^= h>>8; - return (h ^ protocol ^ tunnelid) & 0xFF; -} - -static inline unsigned int hash_src(__be32 *src) -{ - unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; - - h ^= h>>16; - h ^= h>>8; - h ^= h>>4; - return h & 0xF; -} - -#define RSVP_APPLY_RESULT() \ -{ \ - int r = tcf_exts_exec(skb, &f->exts, res); \ - if (r < 0) \ - continue; \ - else if (r > 0) \ - return r; \ -} - -static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct rsvp_head *head = rcu_dereference_bh(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1, h2; - __be32 *dst, *src; - u8 protocol; - u8 tunnelid = 0; - u8 *xprt; -#if RSVP_DST_LEN == 4 - struct ipv6hdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ipv6_hdr(skb); -#else - struct iphdr *nhptr; - - if (!pskb_network_may_pull(skb, sizeof(*nhptr))) - return -1; - nhptr = ip_hdr(skb); -#endif -restart: - -#if RSVP_DST_LEN == 4 - src = &nhptr->saddr.s6_addr32[0]; - dst = &nhptr->daddr.s6_addr32[0]; - protocol = nhptr->nexthdr; - xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); -#else - src = &nhptr->saddr; - dst = &nhptr->daddr; - protocol = nhptr->protocol; - xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (ip_is_fragment(nhptr)) - return -1; -#endif - - h1 = hash_dst(dst, protocol, tunnelid); - h2 = hash_src(src); - - for (s = rcu_dereference_bh(head->ht[h1]); s; - s = rcu_dereference_bh(s->next)) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && - protocol == s->protocol && - !(s->dpi.mask & - (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - tunnelid == s->tunnelid) { - - for (f = rcu_dereference_bh(s->ht[h2]); f; - f = rcu_dereference_bh(f->next)) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && - !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) -#if RSVP_DST_LEN == 4 - && - src[0] == f->src[0] && - src[1] == f->src[1] && - src[2] == f->src[2] -#endif - ) { - *res = f->res; - RSVP_APPLY_RESULT(); - -matched: - if (f->tunnelhdr == 0) - return 0; - - tunnelid = f->res.classid; - nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); - goto restart; - } - } - - /* And wildcard bucket... */ - for (f = rcu_dereference_bh(s->ht[16]); f; - f = rcu_dereference_bh(f->next)) { - *res = f->res; - RSVP_APPLY_RESULT(); - goto matched; - } - return -1; - } - } - return -1; -} - -static void rsvp_replace(struct tcf_proto *tp, struct rsvp_filter *n, u32 h) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter __rcu **ins; - struct rsvp_filter *pins; - unsigned int h1 = h & 0xFF; - unsigned int h2 = (h >> 8) & 0xFF; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (ins = &s->ht[h2], pins = rtnl_dereference(*ins); ; - ins = &pins->next, pins = rtnl_dereference(*ins)) { - if (pins->handle == h) { - RCU_INIT_POINTER(n->next, pins->next); - rcu_assign_pointer(*ins, n); - return; - } - } - } - - /* Something went wrong if we are trying to replace a non-existent - * node. Mind as well halt instead of silently failing. - */ - BUG_ON(1); -} - -static void *rsvp_get(struct tcf_proto *tp, u32 handle) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_session *s; - struct rsvp_filter *f; - unsigned int h1 = handle & 0xFF; - unsigned int h2 = (handle >> 8) & 0xFF; - - if (h2 > 16) - return NULL; - - for (s = rtnl_dereference(head->ht[h1]); s; - s = rtnl_dereference(s->next)) { - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->handle == handle) - return f; - } - } - return NULL; -} - -static int rsvp_init(struct tcf_proto *tp) -{ - struct rsvp_head *data; - - data = kzalloc(sizeof(struct rsvp_head), GFP_KERNEL); - if (data) { - rcu_assign_pointer(tp->root, data); - return 0; - } - return -ENOBUFS; -} - -static void __rsvp_delete_filter(struct rsvp_filter *f) -{ - tcf_exts_destroy(&f->exts); - tcf_exts_put_net(&f->exts); - kfree(f); -} - -static void rsvp_delete_filter_work(struct work_struct *work) -{ - struct rsvp_filter *f = container_of(to_rcu_work(work), - struct rsvp_filter, - rwork); - rtnl_lock(); - __rsvp_delete_filter(f); - rtnl_unlock(); -} - -static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) -{ - tcf_unbind_filter(tp, &f->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (tcf_exts_get_net(&f->exts)) - tcf_queue_work(&f->rwork, rsvp_delete_filter_work); - else - __rsvp_delete_filter(f); -} - -static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int h1, h2; - - if (data == NULL) - return; - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - - while ((s = rtnl_dereference(data->ht[h1])) != NULL) { - RCU_INIT_POINTER(data->ht[h1], s->next); - - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - while ((f = rtnl_dereference(s->ht[h2])) != NULL) { - rcu_assign_pointer(s->ht[h2], f->next); - rsvp_delete_filter(tp, f); - } - } - kfree_rcu(s, rcu); - } - } - kfree_rcu(data, rcu); -} - -static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - bool rtnl_held, struct netlink_ext_ack *extack) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - struct rsvp_filter *nfp, *f = arg; - struct rsvp_filter __rcu **fp; - unsigned int h = f->handle; - struct rsvp_session __rcu **sp; - struct rsvp_session *nsp, *s = f->sess; - int i, h1; - - fp = &s->ht[(h >> 8) & 0xFF]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - if (nfp == f) { - RCU_INIT_POINTER(*fp, f->next); - rsvp_delete_filter(tp, f); - - /* Strip tree */ - - for (i = 0; i <= 16; i++) - if (s->ht[i]) - goto out; - - /* OK, session has no flows */ - sp = &head->ht[h & 0xFF]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if (nsp == s) { - RCU_INIT_POINTER(*sp, s->next); - kfree_rcu(s, rcu); - goto out; - } - } - - break; - } - } - -out: - *last = true; - for (h1 = 0; h1 < 256; h1++) { - if (rcu_access_pointer(head->ht[h1])) { - *last = false; - break; - } - } - - return 0; -} - -static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - int i = 0xFFFF; - - while (i-- > 0) { - u32 h; - - if ((data->hgenerator += 0x10000) == 0) - data->hgenerator = 0x10000; - h = data->hgenerator|salt; - if (!rsvp_get(tp, h)) - return h; - } - return 0; -} - -static int tunnel_bts(struct rsvp_head *data) -{ - int n = data->tgenerator >> 5; - u32 b = 1 << (data->tgenerator & 0x1F); - - if (data->tmap[n] & b) - return 0; - data->tmap[n] |= b; - return 1; -} - -static void tunnel_recycle(struct rsvp_head *data) -{ - struct rsvp_session __rcu **sht = data->ht; - u32 tmap[256/32]; - int h1, h2; - - memset(tmap, 0, sizeof(tmap)); - - for (h1 = 0; h1 < 256; h1++) { - struct rsvp_session *s; - for (s = rtnl_dereference(sht[h1]); s; - s = rtnl_dereference(s->next)) { - for (h2 = 0; h2 <= 16; h2++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h2]); f; - f = rtnl_dereference(f->next)) { - if (f->tunnelhdr == 0) - continue; - data->tgenerator = f->res.classid; - tunnel_bts(data); - } - } - } - } - - memcpy(data->tmap, tmap, sizeof(tmap)); -} - -static u32 gen_tunnel(struct rsvp_head *data) -{ - int i, k; - - for (k = 0; k < 2; k++) { - for (i = 255; i > 0; i--) { - if (++data->tgenerator == 0) - data->tgenerator = 1; - if (tunnel_bts(data)) - return data->tgenerator; - } - tunnel_recycle(data); - } - return 0; -} - -static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { - [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, -}; - -static int rsvp_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, - u32 handle, struct nlattr **tca, - void **arg, u32 flags, - struct netlink_ext_ack *extack) -{ - struct rsvp_head *data = rtnl_dereference(tp->root); - struct rsvp_filter *f, *nfp; - struct rsvp_filter __rcu **fp; - struct rsvp_session *nsp, *s; - struct rsvp_session __rcu **sp; - struct tc_rsvp_pinfo *pinfo = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_RSVP_MAX + 1]; - struct tcf_exts e; - unsigned int h1, h2; - __be32 *dst; - int err; - - if (opt == NULL) - return handle ? -EINVAL : 0; - - err = nla_parse_nested_deprecated(tb, TCA_RSVP_MAX, opt, rsvp_policy, - NULL); - if (err < 0) - return err; - - err = tcf_exts_init(&e, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, flags, - extack); - if (err < 0) - goto errout2; - - f = *arg; - if (f) { - /* Node exists: adjust only classid */ - struct rsvp_filter *n; - - if (f->handle != handle && handle) - goto errout2; - - n = kmemdup(f, sizeof(*f), GFP_KERNEL); - if (!n) { - err = -ENOMEM; - goto errout2; - } - - err = tcf_exts_init(&n->exts, net, TCA_RSVP_ACT, - TCA_RSVP_POLICE); - if (err < 0) { - kfree(n); - goto errout2; - } - - if (tb[TCA_RSVP_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } - - tcf_exts_change(&n->exts, &e); - rsvp_replace(tp, n, handle); - return 0; - } - - /* Now more serious part... */ - err = -EINVAL; - if (handle) - goto errout2; - if (tb[TCA_RSVP_DST] == NULL) - goto errout2; - - err = -ENOBUFS; - f = kzalloc(sizeof(struct rsvp_filter), GFP_KERNEL); - if (f == NULL) - goto errout2; - - err = tcf_exts_init(&f->exts, net, TCA_RSVP_ACT, TCA_RSVP_POLICE); - if (err < 0) - goto errout; - h2 = 16; - if (tb[TCA_RSVP_SRC]) { - memcpy(f->src, nla_data(tb[TCA_RSVP_SRC]), sizeof(f->src)); - h2 = hash_src(f->src); - } - if (tb[TCA_RSVP_PINFO]) { - pinfo = nla_data(tb[TCA_RSVP_PINFO]); - f->spi = pinfo->spi; - f->tunnelhdr = pinfo->tunnelhdr; - } - if (tb[TCA_RSVP_CLASSID]) - f->res.classid = nla_get_u32(tb[TCA_RSVP_CLASSID]); - - dst = nla_data(tb[TCA_RSVP_DST]); - h1 = hash_dst(dst, pinfo ? pinfo->protocol : 0, pinfo ? pinfo->tunnelid : 0); - - err = -ENOMEM; - if ((f->handle = gen_handle(tp, h1 | (h2<<8))) == 0) - goto errout; - - if (f->tunnelhdr) { - err = -EINVAL; - if (f->res.classid > 255) - goto errout; - - err = -ENOMEM; - if (f->res.classid == 0 && - (f->res.classid = gen_tunnel(data)) == 0) - goto errout; - } - - for (sp = &data->ht[h1]; - (s = rtnl_dereference(*sp)) != NULL; - sp = &s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && - pinfo && pinfo->protocol == s->protocol && - memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && -#if RSVP_DST_LEN == 4 - dst[0] == s->dst[0] && - dst[1] == s->dst[1] && - dst[2] == s->dst[2] && -#endif - pinfo->tunnelid == s->tunnelid) { - -insert: - /* OK, we found appropriate session */ - - fp = &s->ht[h2]; - - f->sess = s; - if (f->tunnelhdr == 0) - tcf_bind_filter(tp, &f->res, base); - - tcf_exts_change(&f->exts, &e); - - fp = &s->ht[h2]; - for (nfp = rtnl_dereference(*fp); nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) { - __u32 mask = nfp->spi.mask & f->spi.mask; - - if (mask != f->spi.mask) - break; - } - RCU_INIT_POINTER(f->next, nfp); - rcu_assign_pointer(*fp, f); - - *arg = f; - return 0; - } - } - - /* No session found. Create new one. */ - - err = -ENOBUFS; - s = kzalloc(sizeof(struct rsvp_session), GFP_KERNEL); - if (s == NULL) - goto errout; - memcpy(s->dst, dst, sizeof(s->dst)); - - if (pinfo) { - s->dpi = pinfo->dpi; - s->protocol = pinfo->protocol; - s->tunnelid = pinfo->tunnelid; - } - sp = &data->ht[h1]; - for (nsp = rtnl_dereference(*sp); nsp; - sp = &nsp->next, nsp = rtnl_dereference(*sp)) { - if ((nsp->dpi.mask & s->dpi.mask) != s->dpi.mask) - break; - } - RCU_INIT_POINTER(s->next, nsp); - rcu_assign_pointer(*sp, s); - - goto insert; - -errout: - tcf_exts_destroy(&f->exts); - kfree(f); -errout2: - tcf_exts_destroy(&e); - return err; -} - -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg, - bool rtnl_held) -{ - struct rsvp_head *head = rtnl_dereference(tp->root); - unsigned int h, h1; - - if (arg->stop) - return; - - for (h = 0; h < 256; h++) { - struct rsvp_session *s; - - for (s = rtnl_dereference(head->ht[h]); s; - s = rtnl_dereference(s->next)) { - for (h1 = 0; h1 <= 16; h1++) { - struct rsvp_filter *f; - - for (f = rtnl_dereference(s->ht[h1]); f; - f = rtnl_dereference(f->next)) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(tp, f, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } - } - } -} - -static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) -{ - struct rsvp_filter *f = fh; - struct rsvp_session *s; - struct nlattr *nest; - struct tc_rsvp_pinfo pinfo; - - if (f == NULL) - return skb->len; - s = f->sess; - - t->tcm_handle = f->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_RSVP_DST, sizeof(s->dst), &s->dst)) - goto nla_put_failure; - pinfo.dpi = s->dpi; - pinfo.spi = f->spi; - pinfo.protocol = s->protocol; - pinfo.tunnelid = s->tunnelid; - pinfo.tunnelhdr = f->tunnelhdr; - pinfo.pad = 0; - if (nla_put(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo)) - goto nla_put_failure; - if (f->res.classid && - nla_put_u32(skb, TCA_RSVP_CLASSID, f->res.classid)) - goto nla_put_failure; - if (((f->handle >> 8) & 0xFF) != 16 && - nla_put(skb, TCA_RSVP_SRC, sizeof(f->src), f->src)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &f->exts) < 0) - goto nla_put_failure; - - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &f->exts) < 0) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, - unsigned long base) -{ - struct rsvp_filter *f = fh; - - if (f && f->res.classid == classid) { - if (cl) - __tcf_bind_filter(q, &f->res, base); - else - __tcf_unbind_filter(q, &f->res); - } -} - -static struct tcf_proto_ops RSVP_OPS __read_mostly = { - .kind = RSVP_ID, - .classify = rsvp_classify, - .init = rsvp_init, - .destroy = rsvp_destroy, - .get = rsvp_get, - .change = rsvp_change, - .delete = rsvp_delete, - .walk = rsvp_walk, - .dump = rsvp_dump, - .bind_class = rsvp_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_rsvp(void) -{ - return register_tcf_proto_ops(&RSVP_OPS); -} - -static void __exit exit_rsvp(void) -{ - unregister_tcf_proto_ops(&RSVP_OPS); -} - -module_init(init_rsvp) -module_exit(exit_rsvp) diff --git a/net/sched/cls_rsvp6.c b/net/sched/cls_rsvp6.c deleted file mode 100644 index 64078846000e..000000000000 --- a/net/sched/cls_rsvp6.c +++ /dev/null @@ -1,24 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/cls_rsvp6.c Special RSVP packet classifier for IPv6. - * - * Authors: Alexey Kuznetsov, <kuznet(a)ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/ipv6.h> -#include <linux/skbuff.h> -#include <net/act_api.h> -#include <net/pkt_cls.h> -#include <net/netlink.h> - -#define RSVP_DST_LEN 4 -#define RSVP_ID "rsvp6" -#define RSVP_OPS cls_rsvp6_ops - -#include "cls_rsvp.h" -MODULE_LICENSE("GPL"); -- 2.34.1

1 year, 7 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2023