From: Greg Kroah-Hartman Date: Mon, 3 Apr 2023 13:41:41 +0000 (+0200) Subject: 5.4-stable patches X-Git-Tag: v4.14.312~11 X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=13480680c56372fa884f02b9451a9b690ef4badb;p=thirdparty%2Fkernel%2Fstable-queue.git 5.4-stable patches added patches: ext4-fix-kernel-bug-in-ext4_write_inline_data_end.patch firmware-arm_scmi-fix-device-node-validation-for-mailbox-transport.patch gfs2-always-check-inode-size-of-inline-inodes.patch net-sched-fix-race-condition-in-qdisc_graft.patch net_sched-add-__rcu-annotation-to-netdev-qdisc.patch --- diff --git a/queue-5.4/ext4-fix-kernel-bug-in-ext4_write_inline_data_end.patch b/queue-5.4/ext4-fix-kernel-bug-in-ext4_write_inline_data_end.patch new file mode 100644 index 00000000000..724aa940ad0 --- /dev/null +++ b/queue-5.4/ext4-fix-kernel-bug-in-ext4_write_inline_data_end.patch @@ -0,0 +1,110 @@ +From 5c099c4fdc438014d5893629e70a8ba934433ee8 Mon Sep 17 00:00:00 2001 +From: Ye Bin +Date: Tue, 6 Dec 2022 22:41:34 +0800 +Subject: ext4: fix kernel BUG in 'ext4_write_inline_data_end()' + +From: Ye Bin + +commit 5c099c4fdc438014d5893629e70a8ba934433ee8 upstream. + +Syzbot report follow issue: +------------[ cut here ]------------ +kernel BUG at fs/ext4/inline.c:227! +invalid opcode: 0000 [#1] PREEMPT SMP KASAN +CPU: 1 PID: 3629 Comm: syz-executor212 Not tainted 6.1.0-rc5-syzkaller-00018-g59d0d52c30d4 #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 +RIP: 0010:ext4_write_inline_data+0x344/0x3e0 fs/ext4/inline.c:227 +RSP: 0018:ffffc90003b3f368 EFLAGS: 00010293 +RAX: 0000000000000000 RBX: ffff8880704e16c0 RCX: 0000000000000000 +RDX: ffff888021763a80 RSI: ffffffff821e31a4 RDI: 0000000000000006 +RBP: 000000000006818e R08: 0000000000000006 R09: 0000000000068199 +R10: 0000000000000079 R11: 0000000000000000 R12: 000000000000000b +R13: 0000000000068199 R14: ffffc90003b3f408 R15: ffff8880704e1c82 +FS: 000055555723e3c0(0000) GS:ffff8880b9b00000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 +CR2: 00007fffe8ac9080 CR3: 0000000079f81000 CR4: 0000000000350ee0 +Call Trace: + + ext4_write_inline_data_end+0x2a3/0x12f0 fs/ext4/inline.c:768 + ext4_write_end+0x242/0xdd0 fs/ext4/inode.c:1313 + ext4_da_write_end+0x3ed/0xa30 fs/ext4/inode.c:3063 + generic_perform_write+0x316/0x570 mm/filemap.c:3764 + ext4_buffered_write_iter+0x15b/0x460 fs/ext4/file.c:285 + ext4_file_write_iter+0x8bc/0x16e0 fs/ext4/file.c:700 + call_write_iter include/linux/fs.h:2191 [inline] + do_iter_readv_writev+0x20b/0x3b0 fs/read_write.c:735 + do_iter_write+0x182/0x700 fs/read_write.c:861 + vfs_iter_write+0x74/0xa0 fs/read_write.c:902 + iter_file_splice_write+0x745/0xc90 fs/splice.c:686 + do_splice_from fs/splice.c:764 [inline] + direct_splice_actor+0x114/0x180 fs/splice.c:931 + splice_direct_to_actor+0x335/0x8a0 fs/splice.c:886 + do_splice_direct+0x1ab/0x280 fs/splice.c:974 + do_sendfile+0xb19/0x1270 fs/read_write.c:1255 + __do_sys_sendfile64 fs/read_write.c:1323 [inline] + __se_sys_sendfile64 fs/read_write.c:1309 [inline] + __x64_sys_sendfile64+0x1d0/0x210 fs/read_write.c:1309 + do_syscall_x64 arch/x86/entry/common.c:50 [inline] + do_syscall_64+0x39/0xb0 arch/x86/entry/common.c:80 + entry_SYSCALL_64_after_hwframe+0x63/0xcd +---[ end trace 0000000000000000 ]--- + +Above issue may happens as follows: +ext4_da_write_begin + ext4_da_write_inline_data_begin + ext4_da_convert_inline_data_to_extent + ext4_clear_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA); +ext4_da_write_end + +ext4_run_li_request + ext4_mb_prefetch + ext4_read_block_bitmap_nowait + ext4_validate_block_bitmap + ext4_mark_group_bitmap_corrupted(sb, block_group, EXT4_GROUP_INFO_BBITMAP_CORRUPT) + percpu_counter_sub(&sbi->s_freeclusters_counter,grp->bb_free); + -> sbi->s_freeclusters_counter become zero +ext4_da_write_begin + if (ext4_nonda_switch(inode->i_sb)) -> As freeclusters_counter is zero will return true + *fsdata = (void *)FALL_BACK_TO_NONDELALLOC; + ext4_write_begin +ext4_da_write_end + if (write_mode == FALL_BACK_TO_NONDELALLOC) + ext4_write_end + if (inline_data) + ext4_write_inline_data_end + ext4_write_inline_data + BUG_ON(pos + len > EXT4_I(inode)->i_inline_size); + -> As inode is already convert to extent, so 'pos + len' > inline_size + -> then trigger BUG. + +To solve this issue, instead of checking ext4_has_inline_data() which +is only cleared after data has been written back, check the +EXT4_STATE_MAY_INLINE_DATA flag in ext4_write_end(). + +Fixes: f19d5870cbf7 ("ext4: add normal write support for inline data") +Reported-by: syzbot+4faa160fa96bfba639f8@syzkaller.appspotmail.com +Reported-by: Jun Nie +Signed-off-by: Ye Bin +Link: https://lore.kernel.org/r/20221206144134.1919987-1-yebin@huaweicloud.com +Signed-off-by: Theodore Ts'o +Cc: stable@kernel.org +[ta: Fix conflict in if expression and use the local variable inline_data +as it is initialized with ext4_has_inline_data(inode) anyway.] +Signed-off-by: Tudor Ambarus +Signed-off-by: Greg Kroah-Hartman +--- + fs/ext4/inode.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/fs/ext4/inode.c ++++ b/fs/ext4/inode.c +@@ -1439,7 +1439,8 @@ static int ext4_write_end(struct file *f + bool verity = ext4_verity_in_progress(inode); + + trace_ext4_write_end(inode, pos, len, copied); +- if (inline_data) { ++ if (inline_data && ++ ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) { + ret = ext4_write_inline_data_end(inode, pos, len, + copied, page); + if (ret < 0) { diff --git a/queue-5.4/firmware-arm_scmi-fix-device-node-validation-for-mailbox-transport.patch b/queue-5.4/firmware-arm_scmi-fix-device-node-validation-for-mailbox-transport.patch new file mode 100644 index 00000000000..c0fd648bb31 --- /dev/null +++ b/queue-5.4/firmware-arm_scmi-fix-device-node-validation-for-mailbox-transport.patch @@ -0,0 +1,81 @@ +From 2ab4f4018cb6b8010ca5002c3bdc37783b5d28c2 Mon Sep 17 00:00:00 2001 +From: Cristian Marussi +Date: Tue, 7 Mar 2023 16:23:24 +0000 +Subject: firmware: arm_scmi: Fix device node validation for mailbox transport + +From: Cristian Marussi + +commit 2ab4f4018cb6b8010ca5002c3bdc37783b5d28c2 upstream. + +When mailboxes are used as a transport it is possible to setup the SCMI +transport layer, depending on the underlying channels configuration, to use +one or two mailboxes, associated, respectively, to one or two, distinct, +shared memory areas: any other combination should be treated as invalid. + +Add more strict checking of SCMI mailbox transport device node descriptors. + +Fixes: 5c8a47a5a91d ("firmware: arm_scmi: Make scmi core independent of the transport type") +Cc: # 4.19 +Signed-off-by: Cristian Marussi +Link: https://lore.kernel.org/r/20230307162324.891866-1-cristian.marussi@arm.com +Signed-off-by: Sudeep Holla +[Cristian: backported to v5.4] +Signed-off-by: Cristian Marussi +Signed-off-by: Greg Kroah-Hartman +--- + drivers/firmware/arm_scmi/driver.c | 37 +++++++++++++++++++++++++++++++++++++ + 1 file changed, 37 insertions(+) + +--- a/drivers/firmware/arm_scmi/driver.c ++++ b/drivers/firmware/arm_scmi/driver.c +@@ -737,6 +737,39 @@ static int scmi_mailbox_check(struct dev + idx, NULL); + } + ++static int scmi_mailbox_chan_validate(struct device *cdev) ++{ ++ int num_mb, num_sh, ret = 0; ++ struct device_node *np = cdev->of_node; ++ ++ num_mb = of_count_phandle_with_args(np, "mboxes", "#mbox-cells"); ++ num_sh = of_count_phandle_with_args(np, "shmem", NULL); ++ /* Bail out if mboxes and shmem descriptors are inconsistent */ ++ if (num_mb <= 0 || num_sh > 2 || num_mb != num_sh) { ++ dev_warn(cdev, "Invalid channel descriptor for '%s'\n", ++ of_node_full_name(np)); ++ return -EINVAL; ++ } ++ ++ if (num_sh > 1) { ++ struct device_node *np_tx, *np_rx; ++ ++ np_tx = of_parse_phandle(np, "shmem", 0); ++ np_rx = of_parse_phandle(np, "shmem", 1); ++ /* SCMI Tx and Rx shared mem areas have to be distinct */ ++ if (!np_tx || !np_rx || np_tx == np_rx) { ++ dev_warn(cdev, "Invalid shmem descriptor for '%s'\n", ++ of_node_full_name(np)); ++ ret = -EINVAL; ++ } ++ ++ of_node_put(np_tx); ++ of_node_put(np_rx); ++ } ++ ++ return ret; ++} ++ + static int scmi_mbox_chan_setup(struct scmi_info *info, struct device *dev, + int prot_id, bool tx) + { +@@ -760,6 +793,10 @@ static int scmi_mbox_chan_setup(struct s + goto idr_alloc; + } + ++ ret = scmi_mailbox_chan_validate(dev); ++ if (ret) ++ return ret; ++ + cinfo = devm_kzalloc(info->dev, sizeof(*cinfo), GFP_KERNEL); + if (!cinfo) + return -ENOMEM; diff --git a/queue-5.4/gfs2-always-check-inode-size-of-inline-inodes.patch b/queue-5.4/gfs2-always-check-inode-size-of-inline-inodes.patch new file mode 100644 index 00000000000..ae2e114dddb --- /dev/null +++ b/queue-5.4/gfs2-always-check-inode-size-of-inline-inodes.patch @@ -0,0 +1,65 @@ +From 70376c7ff31221f1d21db5611d8209e677781d3a Mon Sep 17 00:00:00 2001 +From: Andreas Gruenbacher +Date: Sun, 4 Dec 2022 17:00:04 +0100 +Subject: gfs2: Always check inode size of inline inodes + +From: Andreas Gruenbacher + +commit 70376c7ff31221f1d21db5611d8209e677781d3a upstream. + +Check if the inode size of stuffed (inline) inodes is within the allowed +range when reading inodes from disk (gfs2_dinode_in()). This prevents +us from on-disk corruption. + +The two checks in stuffed_readpage() and gfs2_unstuffer_page() that just +truncate inline data to the maximum allowed size don't actually make +sense, and they can be removed now as well. + +Reported-by: syzbot+7bb81dfa9cda07d9cd9d@syzkaller.appspotmail.com +Signed-off-by: Andreas Gruenbacher +[pchelkin@ispras.ru: adjust the inode variable inside gfs2_dinode_in with +the format used before upstream commit 7db354444ad8 ("gfs2: Cosmetic +gfs2_dinode_{in,out} cleanup")] +Signed-off-by: Fedor Pchelkin +Signed-off-by: Greg Kroah-Hartman +--- + fs/gfs2/aops.c | 2 -- + fs/gfs2/bmap.c | 3 --- + fs/gfs2/glops.c | 3 +++ + 3 files changed, 3 insertions(+), 5 deletions(-) + +--- a/fs/gfs2/aops.c ++++ b/fs/gfs2/aops.c +@@ -456,8 +456,6 @@ static int stuffed_readpage(struct gfs2_ + return error; + + kaddr = kmap_atomic(page); +- if (dsize > gfs2_max_stuffed_size(ip)) +- dsize = gfs2_max_stuffed_size(ip); + memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); + memset(kaddr + dsize, 0, PAGE_SIZE - dsize); + kunmap_atomic(kaddr); +--- a/fs/gfs2/bmap.c ++++ b/fs/gfs2/bmap.c +@@ -70,9 +70,6 @@ static int gfs2_unstuffer_page(struct gf + void *kaddr = kmap(page); + u64 dsize = i_size_read(inode); + +- if (dsize > gfs2_max_stuffed_size(ip)) +- dsize = gfs2_max_stuffed_size(ip); +- + memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize); + memset(kaddr + dsize, 0, PAGE_SIZE - dsize); + kunmap(page); +--- a/fs/gfs2/glops.c ++++ b/fs/gfs2/glops.c +@@ -411,6 +411,9 @@ static int gfs2_dinode_in(struct gfs2_in + ip->i_depth = (u8)depth; + ip->i_entries = be32_to_cpu(str->di_entries); + ++ if (gfs2_is_stuffed(ip) && ip->i_inode.i_size > gfs2_max_stuffed_size(ip)) ++ goto corrupt; ++ + if (S_ISREG(ip->i_inode.i_mode)) + gfs2_set_aops(&ip->i_inode); + diff --git a/queue-5.4/net-sched-fix-race-condition-in-qdisc_graft.patch b/queue-5.4/net-sched-fix-race-condition-in-qdisc_graft.patch new file mode 100644 index 00000000000..29f255f31aa --- /dev/null +++ b/queue-5.4/net-sched-fix-race-condition-in-qdisc_graft.patch @@ -0,0 +1,261 @@ +From ebda44da44f6f309d302522b049f43d6f829f7aa Mon Sep 17 00:00:00 2001 +From: Eric Dumazet +Date: Tue, 18 Oct 2022 20:32:58 +0000 +Subject: net: sched: fix race condition in qdisc_graft() + +From: Eric Dumazet + +commit ebda44da44f6f309d302522b049f43d6f829f7aa upstream. + +We had one syzbot report [1] in syzbot queue for a while. +I was waiting for more occurrences and/or a repro but +Dmitry Vyukov spotted the issue right away. + + +qdisc_graft() drops reference to qdisc in notify_and_destroy +while it's still assigned to dev->qdisc + + +Indeed, RCU rules are clear when replacing a data structure. +The visible pointer (dev->qdisc in this case) must be updated +to the new object _before_ RCU grace period is started +(qdisc_put(old) in this case). + +[1] +BUG: KASAN: use-after-free in __tcf_qdisc_find.part.0+0xa3a/0xac0 net/sched/cls_api.c:1066 +Read of size 4 at addr ffff88802065e038 by task syz-executor.4/21027 + +CPU: 0 PID: 21027 Comm: syz-executor.4 Not tainted 6.0.0-rc3-syzkaller-00363-g7726d4c3e60b #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/26/2022 +Call Trace: + +__dump_stack lib/dump_stack.c:88 [inline] +dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 +print_address_description mm/kasan/report.c:317 [inline] +print_report.cold+0x2ba/0x719 mm/kasan/report.c:433 +kasan_report+0xb1/0x1e0 mm/kasan/report.c:495 +__tcf_qdisc_find.part.0+0xa3a/0xac0 net/sched/cls_api.c:1066 +__tcf_qdisc_find net/sched/cls_api.c:1051 [inline] +tc_new_tfilter+0x34f/0x2200 net/sched/cls_api.c:2018 +rtnetlink_rcv_msg+0x955/0xca0 net/core/rtnetlink.c:6081 +netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 +netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] +netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 +netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 +sock_sendmsg_nosec net/socket.c:714 [inline] +sock_sendmsg+0xcf/0x120 net/socket.c:734 +____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 +___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 +__sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 +do_syscall_x64 arch/x86/entry/common.c:50 [inline] +do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 +entry_SYSCALL_64_after_hwframe+0x63/0xcd +RIP: 0033:0x7f5efaa89279 +Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 +RSP: 002b:00007f5efbc31168 EFLAGS: 00000246 ORIG_RAX: 000000000000002e +RAX: ffffffffffffffda RBX: 00007f5efab9bf80 RCX: 00007f5efaa89279 +RDX: 0000000000000000 RSI: 0000000020000140 RDI: 0000000000000005 +RBP: 00007f5efaae32e9 R08: 0000000000000000 R09: 0000000000000000 +R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 +R13: 00007f5efb0cfb1f R14: 00007f5efbc31300 R15: 0000000000022000 + + +Allocated by task 21027: +kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 +kasan_set_track mm/kasan/common.c:45 [inline] +set_alloc_info mm/kasan/common.c:437 [inline] +____kasan_kmalloc mm/kasan/common.c:516 [inline] +____kasan_kmalloc mm/kasan/common.c:475 [inline] +__kasan_kmalloc+0xa9/0xd0 mm/kasan/common.c:525 +kmalloc_node include/linux/slab.h:623 [inline] +kzalloc_node include/linux/slab.h:744 [inline] +qdisc_alloc+0xb0/0xc50 net/sched/sch_generic.c:938 +qdisc_create_dflt+0x71/0x4a0 net/sched/sch_generic.c:997 +attach_one_default_qdisc net/sched/sch_generic.c:1152 [inline] +netdev_for_each_tx_queue include/linux/netdevice.h:2437 [inline] +attach_default_qdiscs net/sched/sch_generic.c:1170 [inline] +dev_activate+0x760/0xcd0 net/sched/sch_generic.c:1229 +__dev_open+0x393/0x4d0 net/core/dev.c:1441 +__dev_change_flags+0x583/0x750 net/core/dev.c:8556 +rtnl_configure_link+0xee/0x240 net/core/rtnetlink.c:3189 +rtnl_newlink_create net/core/rtnetlink.c:3371 [inline] +__rtnl_newlink+0x10b8/0x17e0 net/core/rtnetlink.c:3580 +rtnl_newlink+0x64/0xa0 net/core/rtnetlink.c:3593 +rtnetlink_rcv_msg+0x43a/0xca0 net/core/rtnetlink.c:6090 +netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 +netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] +netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 +netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 +sock_sendmsg_nosec net/socket.c:714 [inline] +sock_sendmsg+0xcf/0x120 net/socket.c:734 +____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 +___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 +__sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 +do_syscall_x64 arch/x86/entry/common.c:50 [inline] +do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 +entry_SYSCALL_64_after_hwframe+0x63/0xcd + +Freed by task 21020: +kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 +kasan_set_track+0x21/0x30 mm/kasan/common.c:45 +kasan_set_free_info+0x20/0x30 mm/kasan/generic.c:370 +____kasan_slab_free mm/kasan/common.c:367 [inline] +____kasan_slab_free+0x166/0x1c0 mm/kasan/common.c:329 +kasan_slab_free include/linux/kasan.h:200 [inline] +slab_free_hook mm/slub.c:1754 [inline] +slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1780 +slab_free mm/slub.c:3534 [inline] +kfree+0xe2/0x580 mm/slub.c:4562 +rcu_do_batch kernel/rcu/tree.c:2245 [inline] +rcu_core+0x7b5/0x1890 kernel/rcu/tree.c:2505 +__do_softirq+0x1d3/0x9c6 kernel/softirq.c:571 + +Last potentially related work creation: +kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 +__kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 +call_rcu+0x99/0x790 kernel/rcu/tree.c:2793 +qdisc_put+0xcd/0xe0 net/sched/sch_generic.c:1083 +notify_and_destroy net/sched/sch_api.c:1012 [inline] +qdisc_graft+0xeb1/0x1270 net/sched/sch_api.c:1084 +tc_modify_qdisc+0xbb7/0x1a00 net/sched/sch_api.c:1671 +rtnetlink_rcv_msg+0x43a/0xca0 net/core/rtnetlink.c:6090 +netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2501 +netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] +netlink_unicast+0x543/0x7f0 net/netlink/af_netlink.c:1345 +netlink_sendmsg+0x917/0xe10 net/netlink/af_netlink.c:1921 +sock_sendmsg_nosec net/socket.c:714 [inline] +sock_sendmsg+0xcf/0x120 net/socket.c:734 +____sys_sendmsg+0x6eb/0x810 net/socket.c:2482 +___sys_sendmsg+0x110/0x1b0 net/socket.c:2536 +__sys_sendmsg+0xf3/0x1c0 net/socket.c:2565 +do_syscall_x64 arch/x86/entry/common.c:50 [inline] +do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 +entry_SYSCALL_64_after_hwframe+0x63/0xcd + +Second to last potentially related work creation: +kasan_save_stack+0x1e/0x40 mm/kasan/common.c:38 +__kasan_record_aux_stack+0xbe/0xd0 mm/kasan/generic.c:348 +kvfree_call_rcu+0x74/0x940 kernel/rcu/tree.c:3322 +neigh_destroy+0x431/0x630 net/core/neighbour.c:912 +neigh_release include/net/neighbour.h:454 [inline] +neigh_cleanup_and_release+0x1f8/0x330 net/core/neighbour.c:103 +neigh_del net/core/neighbour.c:225 [inline] +neigh_remove_one+0x37d/0x460 net/core/neighbour.c:246 +neigh_forced_gc net/core/neighbour.c:276 [inline] +neigh_alloc net/core/neighbour.c:447 [inline] +___neigh_create+0x18b5/0x29a0 net/core/neighbour.c:642 +ip6_finish_output2+0xfb8/0x1520 net/ipv6/ip6_output.c:125 +__ip6_finish_output net/ipv6/ip6_output.c:195 [inline] +ip6_finish_output+0x690/0x1160 net/ipv6/ip6_output.c:206 +NF_HOOK_COND include/linux/netfilter.h:296 [inline] +ip6_output+0x1ed/0x540 net/ipv6/ip6_output.c:227 +dst_output include/net/dst.h:451 [inline] +NF_HOOK include/linux/netfilter.h:307 [inline] +NF_HOOK include/linux/netfilter.h:301 [inline] +mld_sendpack+0xa09/0xe70 net/ipv6/mcast.c:1820 +mld_send_cr net/ipv6/mcast.c:2121 [inline] +mld_ifc_work+0x71c/0xdc0 net/ipv6/mcast.c:2653 +process_one_work+0x991/0x1610 kernel/workqueue.c:2289 +worker_thread+0x665/0x1080 kernel/workqueue.c:2436 +kthread+0x2e4/0x3a0 kernel/kthread.c:376 +ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 + +The buggy address belongs to the object at ffff88802065e000 +which belongs to the cache kmalloc-1k of size 1024 +The buggy address is located 56 bytes inside of +1024-byte region [ffff88802065e000, ffff88802065e400) + +The buggy address belongs to the physical page: +page:ffffea0000819600 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x20658 +head:ffffea0000819600 order:3 compound_mapcount:0 compound_pincount:0 +flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) +raw: 00fff00000010200 0000000000000000 dead000000000001 ffff888011841dc0 +raw: 0000000000000000 0000000000100010 00000001ffffffff 0000000000000000 +page dumped because: kasan: bad access detected +page_owner tracks the page as allocated +page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd20c0(__GFP_IO|__GFP_FS|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 3523, tgid 3523 (sshd), ts 41495190986, free_ts 41417713212 +prep_new_page mm/page_alloc.c:2532 [inline] +get_page_from_freelist+0x109b/0x2ce0 mm/page_alloc.c:4283 +__alloc_pages+0x1c7/0x510 mm/page_alloc.c:5515 +alloc_pages+0x1a6/0x270 mm/mempolicy.c:2270 +alloc_slab_page mm/slub.c:1824 [inline] +allocate_slab+0x27e/0x3d0 mm/slub.c:1969 +new_slab mm/slub.c:2029 [inline] +___slab_alloc+0x7f1/0xe10 mm/slub.c:3031 +__slab_alloc.constprop.0+0x4d/0xa0 mm/slub.c:3118 +slab_alloc_node mm/slub.c:3209 [inline] +__kmalloc_node_track_caller+0x2f2/0x380 mm/slub.c:4955 +kmalloc_reserve net/core/skbuff.c:358 [inline] +__alloc_skb+0xd9/0x2f0 net/core/skbuff.c:430 +alloc_skb_fclone include/linux/skbuff.h:1307 [inline] +tcp_stream_alloc_skb+0x38/0x580 net/ipv4/tcp.c:861 +tcp_sendmsg_locked+0xc36/0x2f80 net/ipv4/tcp.c:1325 +tcp_sendmsg+0x2b/0x40 net/ipv4/tcp.c:1483 +inet_sendmsg+0x99/0xe0 net/ipv4/af_inet.c:819 +sock_sendmsg_nosec net/socket.c:714 [inline] +sock_sendmsg+0xcf/0x120 net/socket.c:734 +sock_write_iter+0x291/0x3d0 net/socket.c:1108 +call_write_iter include/linux/fs.h:2187 [inline] +new_sync_write fs/read_write.c:491 [inline] +vfs_write+0x9e9/0xdd0 fs/read_write.c:578 +ksys_write+0x1e8/0x250 fs/read_write.c:631 +page last free stack trace: +reset_page_owner include/linux/page_owner.h:24 [inline] +free_pages_prepare mm/page_alloc.c:1449 [inline] +free_pcp_prepare+0x5e4/0xd20 mm/page_alloc.c:1499 +free_unref_page_prepare mm/page_alloc.c:3380 [inline] +free_unref_page+0x19/0x4d0 mm/page_alloc.c:3476 +__unfreeze_partials+0x17c/0x1a0 mm/slub.c:2548 +qlink_free mm/kasan/quarantine.c:168 [inline] +qlist_free_all+0x6a/0x170 mm/kasan/quarantine.c:187 +kasan_quarantine_reduce+0x180/0x200 mm/kasan/quarantine.c:294 +__kasan_slab_alloc+0xa2/0xc0 mm/kasan/common.c:447 +kasan_slab_alloc include/linux/kasan.h:224 [inline] +slab_post_alloc_hook mm/slab.h:727 [inline] +slab_alloc_node mm/slub.c:3243 [inline] +slab_alloc mm/slub.c:3251 [inline] +__kmem_cache_alloc_lru mm/slub.c:3258 [inline] +kmem_cache_alloc+0x267/0x3b0 mm/slub.c:3268 +kmem_cache_zalloc include/linux/slab.h:723 [inline] +alloc_buffer_head+0x20/0x140 fs/buffer.c:2974 +alloc_page_buffers+0x280/0x790 fs/buffer.c:829 +create_empty_buffers+0x2c/0xee0 fs/buffer.c:1558 +ext4_block_write_begin+0x1004/0x1530 fs/ext4/inode.c:1074 +ext4_da_write_begin+0x422/0xae0 fs/ext4/inode.c:2996 +generic_perform_write+0x246/0x560 mm/filemap.c:3738 +ext4_buffered_write_iter+0x15b/0x460 fs/ext4/file.c:270 +ext4_file_write_iter+0x44a/0x1660 fs/ext4/file.c:679 +call_write_iter include/linux/fs.h:2187 [inline] +new_sync_write fs/read_write.c:491 [inline] +vfs_write+0x9e9/0xdd0 fs/read_write.c:578 + +Fixes: af356afa010f ("net_sched: reintroduce dev->qdisc for use by sch_api") +Reported-by: syzbot +Diagnosed-by: Dmitry Vyukov +Signed-off-by: Eric Dumazet +Link: https://lore.kernel.org/r/20221018203258.2793282-1-edumazet@google.com +Signed-off-by: Jakub Kicinski +Signed-off-by: Zubin Mithra +Signed-off-by: Greg Kroah-Hartman +--- + net/sched/sch_api.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/net/sched/sch_api.c ++++ b/net/sched/sch_api.c +@@ -1071,12 +1071,13 @@ static int qdisc_graft(struct net_device + + skip: + if (!ingress) { +- notify_and_destroy(net, skb, n, classid, +- rtnl_dereference(dev->qdisc), new); ++ old = rtnl_dereference(dev->qdisc); + if (new && !new->ops->attach) + qdisc_refcount_inc(new); + rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + ++ notify_and_destroy(net, skb, n, classid, old, new); ++ + if (new && new->ops->attach) + new->ops->attach(new); + } else { diff --git a/queue-5.4/net_sched-add-__rcu-annotation-to-netdev-qdisc.patch b/queue-5.4/net_sched-add-__rcu-annotation-to-netdev-qdisc.patch new file mode 100644 index 00000000000..bc8f10dad3f --- /dev/null +++ b/queue-5.4/net_sched-add-__rcu-annotation-to-netdev-qdisc.patch @@ -0,0 +1,312 @@ +From 5891cd5ec46c2c2eb6427cb54d214b149635dd0e Mon Sep 17 00:00:00 2001 +From: Eric Dumazet +Date: Fri, 11 Feb 2022 12:06:23 -0800 +Subject: net_sched: add __rcu annotation to netdev->qdisc + +From: Eric Dumazet + +commit 5891cd5ec46c2c2eb6427cb54d214b149635dd0e upstream. + +syzbot found a data-race [1] which lead me to add __rcu +annotations to netdev->qdisc, and proper accessors +to get LOCKDEP support. + +[1] +BUG: KCSAN: data-race in dev_activate / qdisc_lookup_rcu + +write to 0xffff888168ad6410 of 8 bytes by task 13559 on cpu 1: + attach_default_qdiscs net/sched/sch_generic.c:1167 [inline] + dev_activate+0x2ed/0x8f0 net/sched/sch_generic.c:1221 + __dev_open+0x2e9/0x3a0 net/core/dev.c:1416 + __dev_change_flags+0x167/0x3f0 net/core/dev.c:8139 + rtnl_configure_link+0xc2/0x150 net/core/rtnetlink.c:3150 + __rtnl_newlink net/core/rtnetlink.c:3489 [inline] + rtnl_newlink+0xf4d/0x13e0 net/core/rtnetlink.c:3529 + rtnetlink_rcv_msg+0x745/0x7e0 net/core/rtnetlink.c:5594 + netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 + rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 + netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] + netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 + netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 + sock_sendmsg_nosec net/socket.c:705 [inline] + sock_sendmsg net/socket.c:725 [inline] + ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 + ___sys_sendmsg net/socket.c:2467 [inline] + __sys_sendmsg+0x195/0x230 net/socket.c:2496 + __do_sys_sendmsg net/socket.c:2505 [inline] + __se_sys_sendmsg net/socket.c:2503 [inline] + __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 + do_syscall_x64 arch/x86/entry/common.c:50 [inline] + do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + +read to 0xffff888168ad6410 of 8 bytes by task 13560 on cpu 0: + qdisc_lookup_rcu+0x30/0x2e0 net/sched/sch_api.c:323 + __tcf_qdisc_find+0x74/0x3a0 net/sched/cls_api.c:1050 + tc_del_tfilter+0x1c7/0x1350 net/sched/cls_api.c:2211 + rtnetlink_rcv_msg+0x5ba/0x7e0 net/core/rtnetlink.c:5585 + netlink_rcv_skb+0x14e/0x250 net/netlink/af_netlink.c:2494 + rtnetlink_rcv+0x18/0x20 net/core/rtnetlink.c:5612 + netlink_unicast_kernel net/netlink/af_netlink.c:1317 [inline] + netlink_unicast+0x602/0x6d0 net/netlink/af_netlink.c:1343 + netlink_sendmsg+0x728/0x850 net/netlink/af_netlink.c:1919 + sock_sendmsg_nosec net/socket.c:705 [inline] + sock_sendmsg net/socket.c:725 [inline] + ____sys_sendmsg+0x39a/0x510 net/socket.c:2413 + ___sys_sendmsg net/socket.c:2467 [inline] + __sys_sendmsg+0x195/0x230 net/socket.c:2496 + __do_sys_sendmsg net/socket.c:2505 [inline] + __se_sys_sendmsg net/socket.c:2503 [inline] + __x64_sys_sendmsg+0x42/0x50 net/socket.c:2503 + do_syscall_x64 arch/x86/entry/common.c:50 [inline] + do_syscall_64+0x44/0xd0 arch/x86/entry/common.c:80 + entry_SYSCALL_64_after_hwframe+0x44/0xae + +value changed: 0xffffffff85dee080 -> 0xffff88815d96ec00 + +Reported by Kernel Concurrency Sanitizer on: +CPU: 0 PID: 13560 Comm: syz-executor.2 Not tainted 5.17.0-rc3-syzkaller-00116-gf1baf68e1383-dirty #0 +Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 + +Fixes: 470502de5bdb ("net: sched: unlock rules update API") +Signed-off-by: Eric Dumazet +Cc: Vlad Buslov +Reported-by: syzbot +Cc: Jamal Hadi Salim +Cc: Cong Wang +Cc: Jiri Pirko +Signed-off-by: David S. Miller +Signed-off-by: Zubin Mithra +Signed-off-by: Greg Kroah-Hartman +--- + include/linux/netdevice.h | 2 +- + net/core/rtnetlink.c | 6 ++++-- + net/sched/cls_api.c | 6 +++--- + net/sched/sch_api.c | 22 ++++++++++++---------- + net/sched/sch_generic.c | 22 ++++++++++++---------- + 5 files changed, 32 insertions(+), 26 deletions(-) + +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -1986,7 +1986,7 @@ struct net_device { + struct netdev_queue *_tx ____cacheline_aligned_in_smp; + unsigned int num_tx_queues; + unsigned int real_num_tx_queues; +- struct Qdisc *qdisc; ++ struct Qdisc __rcu *qdisc; + #ifdef CONFIG_NET_SCHED + DECLARE_HASHTABLE (qdisc_hash, 4); + #endif +--- a/net/core/rtnetlink.c ++++ b/net/core/rtnetlink.c +@@ -1593,6 +1593,7 @@ static int rtnl_fill_ifinfo(struct sk_bu + { + struct ifinfomsg *ifm; + struct nlmsghdr *nlh; ++ struct Qdisc *qdisc; + + ASSERT_RTNL(); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); +@@ -1610,6 +1611,7 @@ static int rtnl_fill_ifinfo(struct sk_bu + if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid)) + goto nla_put_failure; + ++ qdisc = rtnl_dereference(dev->qdisc); + if (nla_put_string(skb, IFLA_IFNAME, dev->name) || + nla_put_u32(skb, IFLA_TXQLEN, dev->tx_queue_len) || + nla_put_u8(skb, IFLA_OPERSTATE, +@@ -1628,8 +1630,8 @@ static int rtnl_fill_ifinfo(struct sk_bu + #endif + put_master_ifindex(skb, dev) || + nla_put_u8(skb, IFLA_CARRIER, netif_carrier_ok(dev)) || +- (dev->qdisc && +- nla_put_string(skb, IFLA_QDISC, dev->qdisc->ops->id)) || ++ (qdisc && ++ nla_put_string(skb, IFLA_QDISC, qdisc->ops->id)) || + nla_put_ifalias(skb, dev) || + nla_put_u32(skb, IFLA_CARRIER_CHANGES, + atomic_read(&dev->carrier_up_count) + +--- a/net/sched/cls_api.c ++++ b/net/sched/cls_api.c +@@ -1079,7 +1079,7 @@ static int __tcf_qdisc_find(struct net * + + /* Find qdisc */ + if (!*parent) { +- *q = dev->qdisc; ++ *q = rcu_dereference(dev->qdisc); + *parent = (*q)->handle; + } else { + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); +@@ -2552,7 +2552,7 @@ static int tc_dump_tfilter(struct sk_buf + + parent = tcm->tcm_parent; + if (!parent) +- q = dev->qdisc; ++ q = rtnl_dereference(dev->qdisc); + else + q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); + if (!q) +@@ -2938,7 +2938,7 @@ static int tc_dump_chain(struct sk_buff + + parent = tcm->tcm_parent; + if (!parent) { +- q = dev->qdisc; ++ q = rtnl_dereference(dev->qdisc); + parent = q->handle; + } else { + q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); +--- a/net/sched/sch_api.c ++++ b/net/sched/sch_api.c +@@ -298,7 +298,7 @@ struct Qdisc *qdisc_lookup(struct net_de + + if (!handle) + return NULL; +- q = qdisc_match_from_root(dev->qdisc, handle); ++ q = qdisc_match_from_root(rtnl_dereference(dev->qdisc), handle); + if (q) + goto out; + +@@ -317,7 +317,7 @@ struct Qdisc *qdisc_lookup_rcu(struct ne + + if (!handle) + return NULL; +- q = qdisc_match_from_root(dev->qdisc, handle); ++ q = qdisc_match_from_root(rcu_dereference(dev->qdisc), handle); + if (q) + goto out; + +@@ -1072,10 +1072,10 @@ static int qdisc_graft(struct net_device + skip: + if (!ingress) { + notify_and_destroy(net, skb, n, classid, +- dev->qdisc, new); ++ rtnl_dereference(dev->qdisc), new); + if (new && !new->ops->attach) + qdisc_refcount_inc(new); +- dev->qdisc = new ? : &noop_qdisc; ++ rcu_assign_pointer(dev->qdisc, new ? : &noop_qdisc); + + if (new && new->ops->attach) + new->ops->attach(new); +@@ -1455,7 +1455,7 @@ static int tc_get_qdisc(struct sk_buff * + q = dev_ingress_queue(dev)->qdisc_sleeping; + } + } else { +- q = dev->qdisc; ++ q = rtnl_dereference(dev->qdisc); + } + if (!q) { + NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); +@@ -1544,7 +1544,7 @@ replay: + q = dev_ingress_queue(dev)->qdisc_sleeping; + } + } else { +- q = dev->qdisc; ++ q = rtnl_dereference(dev->qdisc); + } + + /* It may be default qdisc, ignore it */ +@@ -1766,7 +1766,8 @@ static int tc_dump_qdisc(struct sk_buff + s_q_idx = 0; + q_idx = 0; + +- if (tc_dump_qdisc_root(dev->qdisc, skb, cb, &q_idx, s_q_idx, ++ if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc), ++ skb, cb, &q_idx, s_q_idx, + true, tca[TCA_DUMP_INVISIBLE]) < 0) + goto done; + +@@ -2042,7 +2043,7 @@ static int tc_ctl_tclass(struct sk_buff + } else if (qid1) { + qid = qid1; + } else if (qid == 0) +- qid = dev->qdisc->handle; ++ qid = rtnl_dereference(dev->qdisc)->handle; + + /* Now qid is genuine qdisc handle consistent + * both with parent and child. +@@ -2053,7 +2054,7 @@ static int tc_ctl_tclass(struct sk_buff + portid = TC_H_MAKE(qid, portid); + } else { + if (qid == 0) +- qid = dev->qdisc->handle; ++ qid = rtnl_dereference(dev->qdisc)->handle; + } + + /* OK. Locate qdisc */ +@@ -2214,7 +2215,8 @@ static int tc_dump_tclass(struct sk_buff + s_t = cb->args[0]; + t = 0; + +- if (tc_dump_tclass_root(dev->qdisc, skb, tcm, cb, &t, s_t, true) < 0) ++ if (tc_dump_tclass_root(rtnl_dereference(dev->qdisc), ++ skb, tcm, cb, &t, s_t, true) < 0) + goto done; + + dev_queue = dev_ingress_queue(dev); +--- a/net/sched/sch_generic.c ++++ b/net/sched/sch_generic.c +@@ -1106,18 +1106,20 @@ static void attach_default_qdiscs(struct + if (!netif_is_multiqueue(dev) || + dev->priv_flags & IFF_NO_QUEUE) { + netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); +- dev->qdisc = txq->qdisc_sleeping; +- qdisc_refcount_inc(dev->qdisc); ++ qdisc = txq->qdisc_sleeping; ++ rcu_assign_pointer(dev->qdisc, qdisc); ++ qdisc_refcount_inc(qdisc); + } else { + qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); + if (qdisc) { +- dev->qdisc = qdisc; ++ rcu_assign_pointer(dev->qdisc, qdisc); + qdisc->ops->attach(qdisc); + } + } ++ + #ifdef CONFIG_NET_SCHED +- if (dev->qdisc != &noop_qdisc) +- qdisc_hash_add(dev->qdisc, false); ++ if (qdisc != &noop_qdisc) ++ qdisc_hash_add(qdisc, false); + #endif + } + +@@ -1147,7 +1149,7 @@ void dev_activate(struct net_device *dev + * and noqueue_qdisc for virtual interfaces + */ + +- if (dev->qdisc == &noop_qdisc) ++ if (rtnl_dereference(dev->qdisc) == &noop_qdisc) + attach_default_qdiscs(dev); + + if (!netif_carrier_ok(dev)) +@@ -1316,7 +1318,7 @@ static int qdisc_change_tx_queue_len(str + void dev_qdisc_change_real_num_tx(struct net_device *dev, + unsigned int new_real_tx) + { +- struct Qdisc *qdisc = dev->qdisc; ++ struct Qdisc *qdisc = rtnl_dereference(dev->qdisc); + + if (qdisc->ops->change_real_num_tx) + qdisc->ops->change_real_num_tx(qdisc, new_real_tx); +@@ -1356,7 +1358,7 @@ static void dev_init_scheduler_queue(str + + void dev_init_scheduler(struct net_device *dev) + { +- dev->qdisc = &noop_qdisc; ++ rcu_assign_pointer(dev->qdisc, &noop_qdisc); + netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); +@@ -1384,8 +1386,8 @@ void dev_shutdown(struct net_device *dev + netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); + if (dev_ingress_queue(dev)) + shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); +- qdisc_put(dev->qdisc); +- dev->qdisc = &noop_qdisc; ++ qdisc_put(rtnl_dereference(dev->qdisc)); ++ rcu_assign_pointer(dev->qdisc, &noop_qdisc); + + WARN_ON(timer_pending(&dev->watchdog_timer)); + } diff --git a/queue-5.4/series b/queue-5.4/series index a7d303f2fe6..b7b5e36647e 100644 --- a/queue-5.4/series +++ b/queue-5.4/series @@ -97,3 +97,8 @@ alsa-usb-audio-fix-regression-on-detection-of-roland-vs-100.patch drm-etnaviv-fix-reference-leak-when-mmaping-imported-buffer.patch s390-uaccess-add-missing-earlyclobber-annotations-to-__clear_user.patch btrfs-scan-device-in-non-exclusive-mode.patch +ext4-fix-kernel-bug-in-ext4_write_inline_data_end.patch +net_sched-add-__rcu-annotation-to-netdev-qdisc.patch +net-sched-fix-race-condition-in-qdisc_graft.patch +firmware-arm_scmi-fix-device-node-validation-for-mailbox-transport.patch +gfs2-always-check-inode-size-of-inline-inodes.patch