From: wenxu <wenxu@ucloud.cn> mainline inclusion from mainline-v5.11-rc1 commit fa6d639930ee5cd3f932cc314f3407f07a06582d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I64END CVE: CVE-2022-4269 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h... -------------------------------- This one is prepare for the next patch. Signed-off-by: wenxu <wenxu@ucloud.cn> Signed-off-by: Jakub Kicinski <kuba@kernel.org> Conflicts: include/net/sch_generic.h Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com> Reviewed-by: Liu Jian <liujian56@huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- include/net/sch_generic.h | 5 ----- net/sched/act_mirred.c | 21 +++++++++++++++------ 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 73c699355470..8271b10bc30e 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -1329,11 +1329,6 @@ void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block); -static inline int skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res) -{ - return res->ingress ? netif_receive_skb(skb) : dev_queue_xmit(skb); -} - /* Make sure qdisc is no longer in SCHED state. */ static inline void qdisc_synchronize(const struct Qdisc *q) { diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 24d561d8d9c9..53594b0466eb 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -206,6 +206,18 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return err; } +static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) +{ + int err; + + if (!want_ingress) + err = dev_queue_xmit(skb); + else + err = netif_receive_skb(skb); + + return err; +} + static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { @@ -295,18 +307,15 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; - if (skb_tc_reinsert(skb, res)) + err = tcf_mirred_forward(res->ingress, skb); + if (err) tcf_action_inc_overlimit_qstats(&m->common); __this_cpu_dec(mirred_rec_level); return TC_ACT_CONSUMED; } } - if (!want_ingress) - err = dev_queue_xmit(skb2); - else - err = netif_receive_skb(skb2); - + err = tcf_mirred_forward(want_ingress, skb2); if (err) { out: tcf_action_inc_overlimit_qstats(&m->common); -- 2.25.1

From: Davide Caratti <dcaratti@redhat.com> mainline inclusion from mainline-v6.3-rc1 commit ca22da2fbd693b54dc8e3b7b54ccc9f7e9ba3640 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I64END CVE: CVE-2022-4269 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?h... -------------------------------- William reports kernel soft-lockups on some OVS topologies when TC mirred egress->ingress action is hit by local TCP traffic [1]. The same can also be reproduced with SCTP (thanks Xin for verifying), when client and server reach themselves through mirred egress to ingress, and one of the two peers sends a "heartbeat" packet (from within a timer). Enqueueing to backlog proved to fix this soft lockup; however, as Cong noticed [2], we should preserve - when possible - the current mirred behavior that counts as "overlimits" any eventual packet drop subsequent to the mirred forwarding action [3]. A compromise solution might use the backlog only when tcf_mirred_act() has a nest level greater than one: change tcf_mirred_forward() accordingly. Also, add a kselftest that can reproduce the lockup and verifies TC mirred ability to account for further packet drops after TC mirred egress->ingress (when the nest level is 1). [1] https://lore.kernel.org/netdev/33dc43f587ec1388ba456b4915c75f02a8aae226.1663... [2] https://lore.kernel.org/netdev/Y0w%2FWWY60gqrtGLp@pop-os.localdomain/ [3] such behavior is not guaranteed: for example, if RPS or skb RX timestamping is enabled on the mirred target device, the kernel can defer receiving the skb and return NET_RX_SUCCESS inside tcf_mirred_forward(). Reported-by: William Zhao <wizhao@redhat.com> CC: Xin Long <lucien.xin@gmail.com> Signed-off-by: Davide Caratti <dcaratti@redhat.com> Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Acked-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Paolo Abeni <pabeni@redhat.com> Conflicts: net/sched/act_mirred.c tools/testing/selftests/net/forwarding/tc_actions.sh Signed-off-by: Ziyang Xuan <william.xuanziyang@huawei.com> Reviewed-by: Liu Jian <liujian56@huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- net/sched/act_mirred.c | 7 +++ .../selftests/net/forwarding/tc_actions.sh | 49 ++++++++++++++++++- 2 files changed, 55 insertions(+), 1 deletion(-) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 01a44c3e8d6d..296af520817d 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -206,12 +206,19 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, return err; } +static bool is_mirred_nested(void) +{ + return unlikely(__this_cpu_read(mirred_nest_level) > 1); +} + static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = dev_queue_xmit(skb); + else if (is_mirred_nested()) + err = netif_rx(skb); else err = netif_receive_skb(skb); diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index d9eca227136b..e396e24d30e0 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -3,7 +3,8 @@ ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ - gact_trap_test" + gact_trap_test \ + mirred_egress_to_ingress_tcp_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -153,6 +154,52 @@ gact_trap_test() log_test "trap ($tcflags)" } +mirred_egress_to_ingress_tcp_test() +{ + local tmpfile=$(mktemp) tmpfile1=$(mktemp) + + RET=0 + dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile + tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ + $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ + action ct commit nat src addr 192.0.2.2 pipe \ + action ct clear pipe \ + action ct commit nat dst addr 192.0.2.1 pipe \ + action ct clear pipe \ + action skbedit ptype host pipe \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 101 handle 101 egress flower \ + $tcflags ip_proto icmp \ + action mirred ingress redirect dev $h1 + tc filter add dev $h1 protocol ip pref 102 handle 102 ingress flower \ + ip_proto icmp \ + action drop + + ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1 & + local rpid=$! + ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile + wait -n $rpid + cmp -s $tmpfile $tmpfile1 + check_err $? "server output check failed" + + $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ + -t icmp "ping,id=42,seq=5" -q + tc_check_packets "dev $h1 egress" 101 10 + check_err $? "didn't mirred redirect ICMP" + tc_check_packets "dev $h1 ingress" 102 10 + check_err $? "didn't drop mirred ICMP" + local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) + test ${overlimits} = 10 + check_err $? "wrong overlimits, expected 10 got ${overlimits}" + + tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower + tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower + tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower + + rm -f $tmpfile $tmpfile1 + log_test "mirred_egress_to_ingress_tcp ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} -- 2.25.1

From: Brian Foster <bfoster@redhat.com> mainline inclusion from mainline-v5.13-rc1 commit fd43cf600cf61c66ae0a1021aca2f636115c7fcb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4KIAO CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- The blocks used for allocation btrees (bnobt and countbt) are technically considered free space. This is because as free space is used, allocbt blocks are removed and naturally become available for traditional allocation. However, this means that a significant portion of free space may consist of in-use btree blocks if free space is severely fragmented. On large filesystems with large perag reservations, this can lead to a rare but nasty condition where a significant amount of physical free space is available, but the majority of actual usable blocks consist of in-use allocbt blocks. We have a record of a (~12TB, 32 AG) filesystem with multiple AGs in a state with ~2.5GB or so free blocks tracked across ~300 total allocbt blocks, but effectively at 100% full because the the free space is entirely consumed by refcountbt perag reservation. Such a large perag reservation is by design on large filesystems. The problem is that because the free space is so fragmented, this AG contributes the 300 or so allocbt blocks to the global counters as free space. If this pattern repeats across enough AGs, the filesystem lands in a state where global block reservation can outrun physical block availability. For example, a streaming buffered write on the affected filesystem continues to allow delayed allocation beyond the point where writeback starts to fail due to physical block allocation failures. The expected behavior is for the delalloc block reservation to fail gracefully with -ENOSPC before physical block allocation failure is a possibility. To address this problem, set aside in-use allocbt blocks at reservation time and thus ensure they cannot be reserved until truly available for physical allocation. This allows alloc btree metadata to continue to reside in free space, but dynamically adjusts reservation availability based on internal state. Note that the logic requires that the allocbt counter is fully populated at reservation time before it is fully effective. We currently rely on the mount time AGF scan in the perag reservation initialization code for this dependency on filesystems where it's most important (i.e. with active perag reservations). Signed-off-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Chandan Babu R <chandanrlinux@gmail.com> Reviewed-by: Allison Henderson <allison.henderson@oracle.com> Reviewed-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Darrick J. Wong <djwong@kernel.org> Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- fs/xfs/xfs_mount.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c index 6504503f07b3..adc49fe31bdd 100644 --- a/fs/xfs/xfs_mount.c +++ b/fs/xfs/xfs_mount.c @@ -1244,6 +1244,7 @@ xfs_mod_fdblocks( int64_t lcounter; long long res_used; s32 batch; + uint64_t set_aside; if (delta > 0) { /* @@ -1283,8 +1284,20 @@ xfs_mod_fdblocks( else batch = XFS_FDBLOCKS_BATCH; + /* + * Set aside allocbt blocks because these blocks are tracked as free + * space but not available for allocation. Technically this means that a + * single reservation cannot consume all remaining free space, but the + * ratio of allocbt blocks to usable free blocks should be rather small. + * The tradeoff without this is that filesystems that maintain high + * perag block reservations can over reserve physical block availability + * and fail physical allocation, which leads to much more serious + * problems (i.e. transaction abort, pagecache discards, etc.) than + * slightly premature -ENOSPC. + */ + set_aside = mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks); percpu_counter_add_batch(&mp->m_fdblocks, delta, batch); - if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside, + if (__percpu_counter_compare(&mp->m_fdblocks, set_aside, XFS_FDBLOCKS_BATCH) >= 0) { /* we had space! */ return 0; -- 2.25.1

From: "Darrick J. Wong" <djwong@kernel.org> mainline inclusion from mainline-v5.18-rc1 commit 85bcfa26f9a3782be37d4feafd49668b98b8bdbe category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4KIAO CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- On a modern filesystem, we don't allow userspace to allocate blocks for data storage from the per-AG space reservations, the user-controlled reservation pool that prevents ENOSPC in the middle of internal operations, or the internal per-AG set-aside that prevents unwanted filesystem shutdowns due to ENOSPC during a bmap btree split. Since we now consider freespace btree blocks as unavailable for allocation for data storage, we shouldn't report those blocks via statfs either. This makes the numbers that we return via the statfs f_bavail and f_bfree fields a more conservative estimate of actual free space. Signed-off-by: Darrick J. Wong <djwong@kernel.org> Reviewed-by: Brian Foster <bfoster@redhat.com> Reviewed-by: Dave Chinner <dchinner@redhat.com> Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- fs/xfs/xfs_fsops.c | 2 +- fs/xfs/xfs_super.c | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c index 81cb2b3b20f2..0e899eafbc16 100644 --- a/fs/xfs/xfs_fsops.c +++ b/fs/xfs/xfs_fsops.c @@ -291,7 +291,7 @@ xfs_fs_counts( cnt->allocino = percpu_counter_read_positive(&mp->m_icount); cnt->freeino = percpu_counter_read_positive(&mp->m_ifree); cnt->freedata = percpu_counter_read_positive(&mp->m_fdblocks) - - mp->m_alloc_set_aside; + xfs_fdblocks_unavailable(mp); spin_lock(&mp->m_sb_lock); cnt->freertx = mp->m_sb.sb_frextents; diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c index bc4ea6f13dad..9b4ff8247de2 100644 --- a/fs/xfs/xfs_super.c +++ b/fs/xfs/xfs_super.c @@ -809,7 +809,8 @@ xfs_fs_statfs( spin_unlock(&mp->m_sb_lock); /* make sure statp->f_bfree does not underflow */ - statp->f_bfree = max_t(int64_t, fdblocks - mp->m_alloc_set_aside, 0); + statp->f_bfree = max_t(int64_t, 0, + fdblocks - xfs_fdblocks_unavailable(mp)); statp->f_bavail = statp->f_bfree; fakeinos = XFS_FSB_TO_INO(mp, statp->f_bfree); -- 2.25.1

From: Greg Kroah-Hartman <gregkh@linuxfoundation.org> stable inclusion from stable-v5.10.169 commit 6416c2108ba54d569e4c98d3b62ac78cb12e7107 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6OOP3 CVE: CVE-2023-1513 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- commit 2c10b61421a28e95a46ab489fd56c0f442ff6952 upstream. When calling the KVM_GET_DEBUGREGS ioctl, on some configurations, there might be some unitialized portions of the kvm_debugregs structure that could be copied to userspace. Prevent this as is done in the other kvm ioctls, by setting the whole structure to 0 before copying anything into it. Bonus is that this reduces the lines of code as the explicit flag setting and reserved space zeroing out can be removed. Cc: Sean Christopherson <seanjc@google.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: <x86@kernel.org> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: stable <stable@kernel.org> Reported-by: Xingyuan Mo <hdthky0@gmail.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Message-Id: <20230214103304.3689213-1-gregkh@linuxfoundation.org> Tested-by: Xingyuan Mo <hdthky0@gmail.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Guo Mengqi <guomengqi3@huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2@huawei.com> Reviewed-by: Weilong Chen <chenweilong@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- arch/x86/kvm/x86.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 409af5ee8f2d..d5c04a7ab45c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4517,12 +4517,11 @@ static void kvm_vcpu_ioctl_x86_get_debugregs(struct kvm_vcpu *vcpu, { unsigned long val; + memset(dbgregs, 0, sizeof(*dbgregs)); memcpy(dbgregs->db, vcpu->arch.db, sizeof(vcpu->arch.db)); kvm_get_dr(vcpu, 6, &val); dbgregs->dr6 = val; dbgregs->dr7 = vcpu->arch.dr7; - dbgregs->flags = 0; - memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved)); } static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu, -- 2.25.1

From: Baokun Li <libaokun1@huawei.com> hulk inclusion category: bugfix bugzilla: 188500, https://gitee.com/openeuler/kernel/issues/I6RJ0V CVE: NA -------------------------------- We got a WARNING in ext4_add_complete_io: ================================================================== WARNING: at fs/ext4/page-io.c:231 ext4_put_io_end_defer+0x182/0x250 CPU: 10 PID: 77 Comm: ksoftirqd/10 Tainted: 6.3.0-rc2 #85 RIP: 0010:ext4_put_io_end_defer+0x182/0x250 [ext4] [...] Call Trace: <TASK> ext4_end_bio+0xa8/0x240 [ext4] bio_endio+0x195/0x310 blk_update_request+0x184/0x770 scsi_end_request+0x2f/0x240 scsi_io_completion+0x75/0x450 scsi_finish_command+0xef/0x160 scsi_complete+0xa3/0x180 blk_complete_reqs+0x60/0x80 blk_done_softirq+0x25/0x40 __do_softirq+0x119/0x4c8 run_ksoftirqd+0x42/0x70 smpboot_thread_fn+0x136/0x3c0 kthread+0x140/0x1a0 ret_from_fork+0x2c/0x50 ================================================================== Above issue may happen as follows: cpu1 cpu2 ----------------------------|---------------------------- mount -o dioread_lock ext4_writepages ext4_do_writepages *if (ext4_should_dioread_nolock(inode))* // rsv_blocks is not assigned here mount -o remount,dioread_nolock ext4_journal_start_with_reserve __ext4_journal_start __ext4_journal_start_sb jbd2__journal_start *if (rsv_blocks)* // h_rsv_handle is not initialized here mpage_map_and_submit_extent mpage_map_one_extent dioread_nolock = ext4_should_dioread_nolock(inode) if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) mpd->io_submit.io_end->handle = handle->h_rsv_handle ext4_set_io_unwritten_flag io_end->flag |= EXT4_IO_END_UNWRITTEN // now io_end->handle is NULL but has EXT4_IO_END_UNWRITTEN flag scsi_finish_command scsi_io_completion scsi_io_completion_action scsi_end_request blk_update_request req_bio_endio bio_endio bio->bi_end_io > ext4_end_bio ext4_put_io_end_defer ext4_add_complete_io // trigger WARN_ON(!io_end->handle && sbi->s_journal); The immediate cause of this problem is that ext4_should_dioread_nolock() function returns inconsistent values in the ext4_do_writepages() and mpage_map_one_extent(). There are four conditions in this function that can be changed at mount time to cause this problem. These four conditions can be divided into two categories: (1) journal_data and EXT4_EXTENTS_FL, which can be changed by ioctl (2) DELALLOC and DIOREAD_NOLOCK, which can be changed by remount The two in the first category have been fixed by commit c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") and commit cb85f4d23f79 ("ext4: fix race between writepages and enabling EXT4_EXTENTS_FL") respectively. Two cases in the other category have not yet been fixed, and the above issue is caused by this situation. We refer to the fix for the first category, when applying options during remount, we grab s_writepages_rwsem to avoid racing with writepages ops to trigger this problem. Fixes: 6b523df4fb5a ("ext4: use transaction reservation for extent conversion in ext4_end_io") Cc: stable@vger.kernel.org Signed-off-by: Baokun Li <libaokun1@huawei.com> Reviewed-by: Zhang Yi <yi.zhang@huawei.com> Reviewed-by: Yang Erkun <yangerkun@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- fs/ext4/ext4.h | 3 ++- fs/ext4/super.c | 13 +++++++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 7e5abaa31fea..60a8fcdd9d27 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1615,7 +1615,8 @@ struct ext4_sb_info { /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA - * or EXTENTS flag. + * or EXTENTS flag or between writepages ops and changing DELALLOC or + * DIOREAD_NOLOCK mount options on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index ffac35e66bd9..ac0b90b5dbbf 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5983,10 +5983,20 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) vfs_flags = SB_LAZYTIME | SB_I_VERSION; sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + /* + * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause + * two calls to ext4_should_dioread_nolock() to return inconsistent + * values, triggering WARN_ON in ext4_add_complete_io(). we grab + * here s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + percpu_down_write(&sbi->s_writepages_rwsem); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; + percpu_up_write(&sbi->s_writepages_rwsem); goto restore_opts; } + percpu_up_write(&sbi->s_writepages_rwsem); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -6204,6 +6214,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: + percpu_down_write(&sbi->s_writepages_rwsem); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -6212,6 +6223,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + percpu_up_write(&sbi->s_writepages_rwsem); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->s_system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA -- 2.25.1

From: "Gustavo A. R. Silva" <gustavoars@kernel.org> mainline inclusion from mainline-v5.16-rc1 commit 69508d43334e3b09c344f662272bcf24a5b508ed category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6SFHJ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Make use of the struct_size() and flex_array_size() helpers instead of an open-coded version, in order to avoid any potential type mistakes or integer overflows that, in the worse scenario, could lead to heap overflows. Link: https://github.com/KSPP/linux/issues/160 Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org> Link: https://lore.kernel.org/r/20210928193107.GA262595@embeddedor Signed-off-by: Jakub Kicinski <kuba@kernel.org> Conflicts: net/sched/sch_api.c Signed-off-by: Zhengchao Shao <shaozhengchao@huawei.com> Reviewed-by: Liu Jian <liujian56@huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> --- net/sched/sch_api.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 54e2309315eb..b12a3502fca5 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -507,7 +507,8 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, list_for_each_entry(stab, &qdisc_stab_list, list) { if (memcmp(&stab->szopts, s, sizeof(*s))) continue; - if (tsize > 0 && memcmp(stab->data, tab, tsize * sizeof(u16))) + if (tsize > 0 && + memcmp(stab->data, tab, flex_array_size(stab, data, tsize))) continue; stab->refcnt++; return stab; @@ -519,14 +520,14 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt, return ERR_PTR(-EINVAL); } - stab = kmalloc(sizeof(*stab) + tsize * sizeof(u16), GFP_KERNEL); + stab = kmalloc(struct_size(stab, data, tsize), GFP_KERNEL); if (!stab) return ERR_PTR(-ENOMEM); stab->refcnt = 1; stab->szopts = *s; if (tsize > 0) - memcpy(stab->data, tab, tsize * sizeof(u16)); + memcpy(stab->data, tab, flex_array_size(stab, data, tsize)); list_add_tail(&stab->list, &qdisc_stab_list); -- 2.25.1