From: Ido Schimmel idosch@nvidia.com

mainline inclusion from mainline-v6.8-rc2 commit 32f2a0afa95fae0d1ceec2ff06e0e816939964b8 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9DNKF CVE: CVE-2024-26669

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...

--------------------------------

When a qdisc is deleted from a net device the stack instructs the underlying driver to remove its flow offload callback from the associated filter block using the 'FLOW_BLOCK_UNBIND' command. The stack then continues to replay the removal of the filters in the block for this driver by iterating over the chains in the block and invoking the 'reoffload' operation of the classifier being used. In turn, the classifier in its 'reoffload' operation prepares and emits a 'FLOW_CLS_DESTROY' command for each filter.

However, the stack does not do the same for chain templates and the underlying driver never receives a 'FLOW_CLS_TMPLT_DESTROY' command when a qdisc is deleted. This results in a memory leak [1] which can be reproduced using [2].

Fix by introducing a 'tmplt_reoffload' operation and have the stack invoke it with the appropriate arguments as part of the replay. Implement the operation in the sole classifier that supports chain templates (flower) by emitting the 'FLOW_CLS_TMPLT_{CREATE,DESTROY}' command based on whether a flow offload callback is being bound to a filter block or being unbound from one.

As far as I can tell, the issue happens since cited commit which reordered tcf_block_offload_unbind() before tcf_block_flush_all_chains() in __tcf_block_put(). The order cannot be reversed as the filter block is expected to be freed after flushing all the chains.

[1] unreferenced object 0xffff888107e28800 (size 2048): comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s) hex dump (first 32 bytes): b1 a6 7c 11 81 88 ff ff e0 5b b3 10 81 88 ff ff ..|......[...... 01 00 00 00 00 00 00 00 e0 aa b0 84 ff ff ff ff ................ backtrace: [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320 [<ffffffff81ab374e>] __kmalloc+0x4e/0x90 [<ffffffff832aec6d>] mlxsw_sp_acl_ruleset_get+0x34d/0x7a0 [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180 [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280 [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340 [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0 [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170 [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0 [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440 [<ffffffff83ac6270>] netlink_unicast+0x540/0x820 [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0 [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80 [<ffffffff8379d29a>] ___sys_sendmsg+0x13a/0x1e0 [<ffffffff8379d50c>] __sys_sendmsg+0x11c/0x1f0 [<ffffffff843b9ce0>] do_syscall_64+0x40/0xe0 unreferenced object 0xffff88816d2c0400 (size 1024): comm "tc", pid 1079, jiffies 4294958525 (age 3074.287s) hex dump (first 32 bytes): 40 00 00 00 00 00 00 00 57 f6 38 be 00 00 00 00 @.......W.8..... 10 04 2c 6d 81 88 ff ff 10 04 2c 6d 81 88 ff ff ..,m......,m.... backtrace: [<ffffffff81c06a68>] __kmem_cache_alloc_node+0x1e8/0x320 [<ffffffff81ab36c1>] __kmalloc_node+0x51/0x90 [<ffffffff81a8ed96>] kvmalloc_node+0xa6/0x1f0 [<ffffffff82827d03>] bucket_table_alloc.isra.0+0x83/0x460 [<ffffffff82828d2b>] rhashtable_init+0x43b/0x7c0 [<ffffffff832aed48>] mlxsw_sp_acl_ruleset_get+0x428/0x7a0 [<ffffffff832bc195>] mlxsw_sp_flower_tmplt_create+0x145/0x180 [<ffffffff832b2e1a>] mlxsw_sp_flow_block_cb+0x1ea/0x280 [<ffffffff83a10613>] tc_setup_cb_call+0x183/0x340 [<ffffffff83a9f85a>] fl_tmplt_create+0x3da/0x4c0 [<ffffffff83a22435>] tc_ctl_chain+0xa15/0x1170 [<ffffffff838a863c>] rtnetlink_rcv_msg+0x3cc/0xed0 [<ffffffff83ac87f0>] netlink_rcv_skb+0x170/0x440 [<ffffffff83ac6270>] netlink_unicast+0x540/0x820 [<ffffffff83ac6e28>] netlink_sendmsg+0x8d8/0xda0 [<ffffffff83793def>] ____sys_sendmsg+0x30f/0xa80

[2] # tc qdisc add dev swp1 clsact # tc chain add dev swp1 ingress proto ip chain 1 flower dst_ip 0.0.0.0/32 # tc qdisc del dev swp1 clsact # devlink dev reload pci/0000:06:00.0

Fixes: bbf73830cd48 ("net: sched: traverse chains in block with tcf_get_next_chain()") Signed-off-by: Ido Schimmel idosch@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net

Conflicts: include/net/sch_generic.h net/sched/cls_flower.c

Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- include/net/sch_generic.h | 5 ++++- net/sched/cls_api.c | 9 ++++++++- net/sched/cls_flower.c | 23 +++++++++++++++++++++++ 3 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index fad29c9961cc..13f6609644df 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -369,7 +369,10 @@ struct tcf_proto_ops { struct nlattr **tca, struct netlink_ext_ack *extack); void (*tmplt_destroy)(void *tmplt_priv); - + void (*tmplt_reoffload)(struct tcf_chain *chain, + bool add, + flow_setup_cb_t *cb, + void *cb_priv); /* rtnetlink specific */ int (*dump)(struct net*, struct tcf_proto*, void *, struct sk_buff *skb, struct tcmsg*, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index beedd0d2b509..521fd4d6eb31 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1413,6 +1413,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, chain_prev = chain, chain = __tcf_get_next_chain(block, chain), tcf_chain_put(chain_prev)) { + if (chain->tmplt_ops && add) + chain->tmplt_ops->tmplt_reoffload(chain, true, cb, + cb_priv); for (tp = __tcf_get_next_proto(chain, NULL); tp; tp_prev = tp, tp = __tcf_get_next_proto(chain, tp), @@ -1428,6 +1431,9 @@ tcf_block_playback_offloads(struct tcf_block *block, flow_setup_cb_t *cb, goto err_playback_remove; } } + if (chain->tmplt_ops && !add) + chain->tmplt_ops->tmplt_reoffload(chain, false, cb, + cb_priv); }

return 0; @@ -2772,7 +2778,8 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); - if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { + if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump || + !ops->tmplt_reoffload) { NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier"); module_put(ops->owner); return -EOPNOTSUPP; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 275122cc0b6d..6d2467c772d9 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2396,6 +2396,28 @@ static void fl_tmplt_destroy(void *tmplt_priv) kfree(tmplt); }

+static void fl_tmplt_reoffload(struct tcf_chain *chain, bool add, + flow_setup_cb_t *cb, void *cb_priv) +{ + struct fl_flow_tmplt *tmplt = chain->tmplt_priv; + struct flow_cls_offload cls_flower = {}; + + cls_flower.rule = flow_rule_alloc(0); + if (!cls_flower.rule) + return; + + cls_flower.common.chain_index = chain->index; + cls_flower.command = add ? FLOW_CLS_TMPLT_CREATE : + FLOW_CLS_TMPLT_DESTROY; + cls_flower.cookie = (unsigned long) tmplt; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; + + cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); +} + static int fl_dump_key_val(struct sk_buff *skb, void *val, int val_type, void *mask, int mask_type, int len) @@ -3201,6 +3223,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = { .bind_class = fl_bind_class, .tmplt_create = fl_tmplt_create, .tmplt_destroy = fl_tmplt_destroy, + .tmplt_reoffload = fl_tmplt_reoffload, .tmplt_dump = fl_tmplt_dump, .owner = THIS_MODULE, .flags = TCF_PROTO_OPS_DOIT_UNLOCKED,

From: Zhengchao Shao shaozhengchao@huawei.com

Offering: HULK hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I9DNKF

--------------------------------

The tmplt_reoffload function pointer is of the const type, and the value is assigned to the constant in fl_init. As a result, the following issue occurs. BUG: unable to handle page fault for address: ffffffff98715da0 PF: supervisor write access in kernel mode PF: error_code(0x0003) - permissions violation PGD ec0d067 P4D ec0d067 PUD ec0e063 PMD 800000000e0001e1 Oops: 0003 [#1] SMP PTI CPU: 20 PID: 7533 Comm: tc Kdump: loaded Not tainted 5.10.0+ #40 Hardware name: Red Hat KVM, BIOS 0.5.1 01/01/2011 RIP: 0010:fl_init+0xcf/0x100 RSP: 0018:ffffb6e7c0fe7978 EFLAGS: 00010202 RAX: 0000000000000049 RBX: ffff99c6b3580480 RCX: 0000000000000027 RDX: 0000000000000000 RSI: ffffffff98718740 RDI: ffff99c6a359f800 RBP: ffff99c6a359f800 R08: ffff99cfdce1fe50 R09: ffffb6e7c0fe77a0 R10: ffffb6e7c0fe7798 R11: ffffffff9967d5a8 R12: ffff99c6b3580480 R13: ffffb6e7c0fe7b80 R14: 0000000000000001 R15: ffffb6e7c0fe7ab0 FS: 00007fbaef7b1800(0000) GS:ffff99cfdce00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffff98715da0 CR3: 000000011299c000 CR4: 00000000000006e0 Call Trace: tcf_proto_create.cold+0x66/0x9e tc_new_tfilter+0x611/0xa70 rtnetlink_rcv_msg+0x406/0x560 netlink_rcv_skb+0x64/0x180 rtnetlink_rcv+0x19/0x30 netlink_unicast_kernel+0x7b/0x180 netlink_unicast+0x13d/0x230 netlink_sendmsg+0x432/0x610 __sock_sendmsg+0xc6/0xd0 ____sys_sendmsg+0x1f5/0x380 ___sys_sendmsg+0x82/0xe

Fixes: beb4e9f0ea13 ("net/sched: flower: Fix kabi change") Signed-off-by: Zhengchao Shao shaozhengchao@huawei.com --- net/sched/cls_api.c | 4 ++-- net/sched/cls_flower.c | 5 +---- 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 7801d8c552c9..b6dd697a3d5f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -1397,8 +1397,8 @@ void tcf_block_put(struct tcf_block *block)

EXPORT_SYMBOL(tcf_block_put);

-void (* const tmplt_reoffload)(struct tcf_chain *chain, bool add, - flow_setup_cb_t *cb, void *cb_priv); +void (*tmplt_reoffload)(struct tcf_chain *chain, bool add, + flow_setup_cb_t *cb, void *cb_priv); EXPORT_SYMBOL(tmplt_reoffload);

static void cls_tmplt_reoffload(struct tcf_chain *chain, bool add, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 1c273b8abf4d..7ddc58059ead 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -356,8 +356,6 @@ static int fl_init(struct tcf_proto *tp) rcu_assign_pointer(tp->root, head); idr_init(&head->handle_idr);

- tmplt_reoffload = &fl_tmplt_reoffload; - return rhashtable_init(&head->ht, &mask_ht_params); }

@@ -596,8 +594,6 @@ static void fl_destroy(struct tcf_proto *tp, bool rtnl_held,

__module_get(THIS_MODULE); tcf_queue_work(&head->rwork, fl_destroy_sleepable); - - tmplt_reoffload = NULL; }

static void fl_put(struct tcf_proto *tp, void *arg) @@ -3240,6 +3236,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {

static int __init cls_fl_init(void) { + tmplt_reoffload = &fl_tmplt_reoffload; return register_tcf_proto_ops(&cls_fl_ops); }