From: Herbert Xu <herbert@gondor.apana.org.au> stable inclusion from stable-v4.19.268 commit 0c76cb8dcaf2561c7acef006af29ab9709fe001c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69KBO CVE: NA -------------------------------- [ Upstream commit 7f57f8165cb6d2c206e2b9ada53b9e2d6d8af42f ] The function pfkey_send_acquire may race with pfkey_register (which could even be in a different name space). This may result in a buffer overrun. Allocating the maximum amount of memory that could be used prevents this. Reported-by: syzbot+1e9af9185d8850e2c2fa@syzkaller.appspotmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Reviewed-by: Sabrina Dubroca <sd@queasysnail.net> Reviewed-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- net/key/af_key.c | 32 ++++++++++++++++++++++---------- 1 file changed, 22 insertions(+), 10 deletions(-) diff --git a/net/key/af_key.c b/net/key/af_key.c index 23470b0d84aa..6a170a37d9e2 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2911,7 +2911,7 @@ static int count_ah_combs(const struct xfrm_tmpl *t) break; if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } return sz + sizeof(struct sadb_prop); @@ -2929,7 +2929,7 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!ealg->pfkey_supported) continue; - if (!(ealg_tmpl_set(t, ealg) && ealg->available)) + if (!(ealg_tmpl_set(t, ealg))) continue; for (k = 1; ; k++) { @@ -2940,16 +2940,17 @@ static int count_esp_combs(const struct xfrm_tmpl *t) if (!aalg->pfkey_supported) continue; - if (aalg_tmpl_set(t, aalg) && aalg->available) + if (aalg_tmpl_set(t, aalg)) sz += sizeof(struct sadb_comb); } } return sz + sizeof(struct sadb_prop); } -static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -2977,13 +2978,17 @@ static void dump_ah_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } -static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) +static int dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) { struct sadb_prop *p; + int sz = 0; int i, k; p = skb_put(skb, sizeof(struct sadb_prop)); @@ -3025,8 +3030,11 @@ static void dump_esp_combs(struct sk_buff *skb, const struct xfrm_tmpl *t) c->sadb_comb_soft_addtime = 20*60*60; c->sadb_comb_hard_usetime = 8*60*60; c->sadb_comb_soft_usetime = 7*60*60; + sz += sizeof(*c); } } + + return sz + sizeof(*p); } static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) @@ -3156,6 +3164,7 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct struct sadb_x_sec_ctx *sec_ctx; struct xfrm_sec_ctx *xfrm_ctx; int ctx_size = 0; + int alg_size = 0; sockaddr_size = pfkey_sockaddr_size(x->props.family); if (!sockaddr_size) @@ -3167,16 +3176,16 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct sizeof(struct sadb_x_policy); if (x->id.proto == IPPROTO_AH) - size += count_ah_combs(t); + alg_size = count_ah_combs(t); else if (x->id.proto == IPPROTO_ESP) - size += count_esp_combs(t); + alg_size = count_esp_combs(t); if ((xfrm_ctx = x->security)) { ctx_size = PFKEY_ALIGN8(xfrm_ctx->ctx_len); size += sizeof(struct sadb_x_sec_ctx) + ctx_size; } - skb = alloc_skb(size + 16, GFP_ATOMIC); + skb = alloc_skb(size + alg_size + 16, GFP_ATOMIC); if (skb == NULL) return -ENOMEM; @@ -3230,10 +3239,13 @@ static int pfkey_send_acquire(struct xfrm_state *x, struct xfrm_tmpl *t, struct pol->sadb_x_policy_priority = xp->priority; /* Set sadb_comb's. */ + alg_size = 0; if (x->id.proto == IPPROTO_AH) - dump_ah_combs(skb, t); + alg_size = dump_ah_combs(skb, t); else if (x->id.proto == IPPROTO_ESP) - dump_esp_combs(skb, t); + alg_size = dump_esp_combs(skb, t); + + hdr->sadb_msg_len += alg_size / 8; /* security context */ if (xfrm_ctx) { -- 2.25.1

From: Shigeru Yoshida <syoshida@redhat.com> stable inclusion from stable-v4.19.268 commit 1f23f1890d91812c35d32eab1b49621b6d32dc7b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69KBO CVE: NA -------------------------------- [ Upstream commit 5daadc86f27ea4d691e2131c04310d0418c6cd12 ] syzbot reported use-after-free in tun_detach() [1]. This causes call trace like below: ================================================================== BUG: KASAN: use-after-free in notifier_call_chain+0x1ee/0x200 kernel/notifier.c:75 Read of size 8 at addr ffff88807324e2a8 by task syz-executor.0/3673 CPU: 0 PID: 3673 Comm: syz-executor.0 Not tainted 6.1.0-rc5-syzkaller-00044-gcc675d22e422 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:284 [inline] print_report+0x15e/0x461 mm/kasan/report.c:395 kasan_report+0xbf/0x1f0 mm/kasan/report.c:495 notifier_call_chain+0x1ee/0x200 kernel/notifier.c:75 call_netdevice_notifiers_info+0x86/0x130 net/core/dev.c:1942 call_netdevice_notifiers_extack net/core/dev.c:1983 [inline] call_netdevice_notifiers net/core/dev.c:1997 [inline] netdev_wait_allrefs_any net/core/dev.c:10237 [inline] netdev_run_todo+0xbc6/0x1100 net/core/dev.c:10351 tun_detach drivers/net/tun.c:704 [inline] tun_chr_close+0xe4/0x190 drivers/net/tun.c:3467 __fput+0x27c/0xa90 fs/file_table.c:320 task_work_run+0x16f/0x270 kernel/task_work.c:179 exit_task_work include/linux/task_work.h:38 [inline] do_exit+0xb3d/0x2a30 kernel/exit.c:820 do_group_exit+0xd4/0x2a0 kernel/exit.c:950 get_signal+0x21b1/0x2440 kernel/signal.c:2858 arch_do_signal_or_restart+0x86/0x2300 arch/x86/kernel/signal.c:869 exit_to_user_mode_loop kernel/entry/common.c:168 [inline] exit_to_user_mode_prepare+0x15f/0x250 kernel/entry/common.c:203 __syscall_exit_to_user_mode_work kernel/entry/common.c:285 [inline] syscall_exit_to_user_mode+0x1d/0x50 kernel/entry/common.c:296 do_syscall_64+0x46/0xb0 arch/x86/entry/common.c:86 entry_SYSCALL_64_after_hwframe+0x63/0xcd The cause of the issue is that sock_put() from __tun_detach() drops last reference count for struct net, and then notifier_call_chain() from netdev_state_change() accesses that struct net. This patch fixes the issue by calling sock_put() from tun_detach() after all necessary accesses for the struct net has done. Fixes: 83c1f36f9880 ("tun: send netlink notification when the device is modified") Reported-by: syzbot+106f9b687cd64ee70cd1@syzkaller.appspotmail.com Link: https://syzkaller.appspot.com/bug?id=96eb7f1ce75ef933697f24eeab928c4a716edef... [1] Signed-off-by: Shigeru Yoshida <syoshida@redhat.com> Link: https://lore.kernel.org/r/20221124175134.1589053-1-syoshida@redhat.com Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- drivers/net/tun.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 01de856c9774..240dd4523a7d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -748,7 +748,6 @@ static void __tun_detach(struct tun_file *tfile, bool clean) if (tun) xdp_rxq_info_unreg(&tfile->xdp_rxq); ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free); - sock_put(&tfile->sk); } } @@ -764,6 +763,9 @@ static void tun_detach(struct tun_file *tfile, bool clean) if (dev) netdev_state_change(dev); rtnl_unlock(); + + if (clean) + sock_put(&tfile->sk); } static void tun_detach_all(struct net_device *dev) -- 2.25.1

From: James Morse <james.morse@arm.com> stable inclusion from stable-v4.19.268 commit 70133fb6e3cebb7c7b295d848f3ab76ee22ab4dd category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69KBO CVE: NA -------------------------------- Sami reports that linux panic()s when resuming from suspend to RAM. This is because when CPUs are brought back online, they re-enable any necessary mitigations. The Spectre-v2 and Spectre-BHB mitigations interact as both need to done by KVM when exiting a guest. Slots KVM can use as vectors are allocated, and templates for the mitigation are patched into the vector. This fails if a new slot needs to be allocated once the kernel has finished booting as it is no-longer possible to modify KVM's vectors: | root@adam:/sys/devices/system/cpu/cpu1# echo 1 > online | Unable to handle kernel write to read-only memory at virtual add> | Mem abort info: | ESR = 0x9600004e | Exception class = DABT (current EL), IL = 32 bits | SET = 0, FnV = 0 | EA = 0, S1PTW = 0 | Data abort info: | ISV = 0, ISS = 0x0000004e | CM = 0, WnR = 1 | swapper pgtable: 4k pages, 48-bit VAs, pgdp = 000000000f07a71c | [ffff800000b4b800] pgd=00000009ffff8803, pud=00000009ffff7803, p> | Internal error: Oops: 9600004e [#1] PREEMPT SMP | Modules linked in: | Process swapper/1 (pid: 0, stack limit = 0x0000000063153c53) | CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.19.252-dirty #14 | Hardware name: ARM LTD ARM Juno Development Platform/ARM Juno De> | pstate: 000001c5 (nzcv dAIF -PAN -UAO) | pc : __memcpy+0x48/0x180 | lr : __copy_hyp_vect_bpi+0x64/0x90 | Call trace: | __memcpy+0x48/0x180 | kvm_setup_bhb_slot+0x204/0x2a8 | spectre_bhb_enable_mitigation+0x1b8/0x1d0 | __verify_local_cpu_caps+0x54/0xf0 | check_local_cpu_capabilities+0xc4/0x184 | secondary_start_kernel+0xb0/0x170 | Code: b8404423 b80044c3 36180064 f8408423 (f80084c3) | ---[ end trace 859bcacb09555348 ]--- | Kernel panic - not syncing: Attempted to kill the idle task! | SMP: stopping secondary CPUs | Kernel Offset: disabled | CPU features: 0x10,25806086 | Memory Limit: none | ---[ end Kernel panic - not syncing: Attempted to kill the idle ] This is only a problem on platforms where there is only one CPU that is vulnerable to both Spectre-v2 and Spectre-BHB. The Spectre-v2 mitigation identifies the slot it can re-use by the CPU's 'fn'. It unconditionally writes the slot number and 'template_start' pointer. The Spectre-BHB mitigation identifies slots it can re-use by the CPU's template_start pointer, which was previously clobbered by the Spectre-v2 mitigation. When there is only one CPU that is vulnerable to both issues, this causes Spectre-v2 to try to allocate a new slot, which fails. Change both mitigations to check whether they are changing the slot this CPU uses before writing the percpu variables again. This issue only exists in the stable backports for Spectre-BHB which have to use totally different infrastructure to mainline. Reported-by: Sami Lee <sami.lee@mediatek.com> Fixes: c20d55174479 ("arm64: Mitigate spectre style branch history side channels") Signed-off-by: James Morse <james.morse@arm.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- arch/arm64/kernel/cpu_errata.c | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index fdff9c6d8969..d7b4ed1f37f5 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -192,9 +192,12 @@ static void install_bp_hardening_cb(bp_hardening_cb_t fn, __copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end); } - __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot); - __this_cpu_write(bp_hardening_data.fn, fn); - __this_cpu_write(bp_hardening_data.template_start, hyp_vecs_start); + if (fn != __this_cpu_read(bp_hardening_data.fn)) { + __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot); + __this_cpu_write(bp_hardening_data.fn, fn); + __this_cpu_write(bp_hardening_data.template_start, + hyp_vecs_start); + } spin_unlock(&bp_lock); } #else @@ -1263,8 +1266,11 @@ static void kvm_setup_bhb_slot(const char *hyp_vecs_start) __copy_hyp_vect_bpi(slot, hyp_vecs_start, hyp_vecs_end); } - __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot); - __this_cpu_write(bp_hardening_data.template_start, hyp_vecs_start); + if (hyp_vecs_start != __this_cpu_read(bp_hardening_data.template_start)) { + __this_cpu_write(bp_hardening_data.hyp_vectors_slot, slot); + __this_cpu_write(bp_hardening_data.template_start, + hyp_vecs_start); + } spin_unlock(&bp_lock); } #else -- 2.25.1

From: Keith Busch <kbusch@kernel.org> stable inclusion from stable-v4.19.268 commit 4722ac3b7809747cc116dc4355757d26e2e6e1fb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69KBO CVE: NA -------------------------------- commit 23e085b2dead13b51fe86d27069895b740f749c0 upstream. The passthrough commands already have this restriction, but the other operations do not. Require the same capabilities for all users as all of these operations, which include resets and rescans, can be disruptive. Signed-off-by: Keith Busch <kbusch@kernel.org> Signed-off-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ovidiu Panait <ovidiu.panait@windriver.com> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- drivers/nvme/host/core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index ccfdd4222697..b6e312187b51 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -2838,11 +2838,17 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd, case NVME_IOCTL_IO_CMD: return nvme_dev_user_cmd(ctrl, argp); case NVME_IOCTL_RESET: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; dev_warn(ctrl->device, "resetting controller\n"); return nvme_reset_ctrl_sync(ctrl); case NVME_IOCTL_SUBSYS_RESET: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; return nvme_reset_subsystem(ctrl); case NVME_IOCTL_RESCAN: + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; nvme_queue_scan(ctrl); return 0; default: -- 2.25.1

From: Tejun Heo <tj@kernel.org> stable inclusion from stable-v4.19.269 commit e1ae97624ecf400ea56c238bff23e5cd139df0b8 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69KBO CVE: NA -------------------------------- commit 4a7ba45b1a435e7097ca0f79a847d0949d0eb088 upstream. memcg_write_event_control() accesses the dentry->d_name of the specified control fd to route the write call. As a cgroup interface file can't be renamed, it's safe to access d_name as long as the specified file is a regular cgroup file. Also, as these cgroup interface files can't be removed before the directory, it's safe to access the parent too. Prior to 347c4a874710 ("memcg: remove cgroup_event->cft"), there was a call to __file_cft() which verified that the specified file is a regular cgroupfs file before further accesses. The cftype pointer returned from __file_cft() was no longer necessary and the commit inadvertently dropped the file type check with it allowing any file to slip through. With the invarients broken, the d_name and parent accesses can now race against renames and removals of arbitrary files and cause use-after-free's. Fix the bug by resurrecting the file type check in __file_cft(). Now that cgroupfs is implemented through kernfs, checking the file operations needs to go through a layer of indirection. Instead, let's check the superblock and dentry type. Link: https://lkml.kernel.org/r/Y5FRm/cfcKPGzWwl@slm.duckdns.org Fixes: 347c4a874710 ("memcg: remove cgroup_event->cft") Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Jann Horn <jannh@google.com> Acked-by: Roman Gushchin <roman.gushchin@linux.dev> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Shakeel Butt <shakeelb@google.com> Cc: <stable@vger.kernel.org> [3.14+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- include/linux/cgroup.h | 1 + kernel/cgroup/cgroup-internal.h | 1 - mm/memcontrol.c | 15 +++++++++++++-- 3 files changed, 14 insertions(+), 3 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index f2273649c31b..17a7718d000f 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -69,6 +69,7 @@ struct css_task_iter { struct list_head iters_node; /* css_set->task_iters */ }; +extern struct file_system_type cgroup_fs_type; extern struct cgroup_root cgrp_dfl_root; extern struct css_set init_css_set; diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index c52883e5cb8a..2e65e4c4d6e7 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -144,7 +144,6 @@ extern struct mutex cgroup_mutex; extern spinlock_t css_set_lock; extern struct cgroup_subsys *cgroup_subsys[]; extern struct list_head cgroup_roots; -extern struct file_system_type cgroup_fs_type; /* iterate across the hierarchies */ #define for_each_root(root) \ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 345a9d159ad8..63b91a030b02 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4520,6 +4520,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, unsigned int efd, cfd; struct fd efile; struct fd cfile; + struct dentry *cdentry; const char *name; char *endp; int ret; @@ -4570,6 +4571,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, if (ret < 0) goto out_put_cfile; + /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + /* * Determine the event callbacks and set them in @event. This used * to be done via struct cftype but cgroup core no longer knows @@ -4578,7 +4589,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_path.dentry->d_name.name; + name = cdentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4602,7 +4613,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) -- 2.25.1

From: Eric Dumazet <edumazet@google.com> stable inclusion from stable-v4.19.269 commit 7e0dcd5f3ade221a6126278aca60c8ab4cc3bce9 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I69KBO CVE: NA -------------------------------- [ Upstream commit 803e84867de59a1e5d126666d25eb4860cfd2ebe ] Blamed commit claimed rcu_read_lock() was held by ip6_fragment() callers. It seems to not be always true, at least for UDP stack. syzbot reported: BUG: KASAN: use-after-free in ip6_dst_idev include/net/ip6_fib.h:245 [inline] BUG: KASAN: use-after-free in ip6_fragment+0x2724/0x2770 net/ipv6/ip6_output.c:951 Read of size 8 at addr ffff88801d403e80 by task syz-executor.3/7618 CPU: 1 PID: 7618 Comm: syz-executor.3 Not tainted 6.1.0-rc6-syzkaller-00012-g4312098baf37 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 10/26/2022 Call Trace: <TASK> __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xd1/0x138 lib/dump_stack.c:106 print_address_description mm/kasan/report.c:284 [inline] print_report+0x15e/0x45d mm/kasan/report.c:395 kasan_report+0xbf/0x1f0 mm/kasan/report.c:495 ip6_dst_idev include/net/ip6_fib.h:245 [inline] ip6_fragment+0x2724/0x2770 net/ipv6/ip6_output.c:951 __ip6_finish_output net/ipv6/ip6_output.c:193 [inline] ip6_finish_output+0x9a3/0x1170 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0x1f1/0x540 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:445 [inline] ip6_local_out+0xb3/0x1a0 net/ipv6/output_core.c:161 ip6_send_skb+0xbb/0x340 net/ipv6/ip6_output.c:1966 udp_v6_send_skb+0x82a/0x18a0 net/ipv6/udp.c:1286 udp_v6_push_pending_frames+0x140/0x200 net/ipv6/udp.c:1313 udpv6_sendmsg+0x18da/0x2c80 net/ipv6/udp.c:1606 inet6_sendmsg+0x9d/0xe0 net/ipv6/af_inet6.c:665 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 sock_write_iter+0x295/0x3d0 net/socket.c:1108 call_write_iter include/linux/fs.h:2191 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9ed/0xdd0 fs/read_write.c:584 ksys_write+0x1ec/0x250 fs/read_write.c:637 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 RIP: 0033:0x7fde3588c0d9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 f1 19 00 00 90 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:00007fde365b6168 EFLAGS: 00000246 ORIG_RAX: 0000000000000001 RAX: ffffffffffffffda RBX: 00007fde359ac050 RCX: 00007fde3588c0d9 RDX: 000000000000ffdc RSI: 00000000200000c0 RDI: 000000000000000a RBP: 00007fde358e7ae9 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007fde35acfb1f R14: 00007fde365b6300 R15: 0000000000022000 </TASK> Allocated by task 7618: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 __kasan_slab_alloc+0x82/0x90 mm/kasan/common.c:325 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slab.h:737 [inline] slab_alloc_node mm/slub.c:3398 [inline] slab_alloc mm/slub.c:3406 [inline] __kmem_cache_alloc_lru mm/slub.c:3413 [inline] kmem_cache_alloc+0x2b4/0x3d0 mm/slub.c:3422 dst_alloc+0x14a/0x1f0 net/core/dst.c:92 ip6_dst_alloc+0x32/0xa0 net/ipv6/route.c:344 ip6_rt_pcpu_alloc net/ipv6/route.c:1369 [inline] rt6_make_pcpu_route net/ipv6/route.c:1417 [inline] ip6_pol_route+0x901/0x1190 net/ipv6/route.c:2254 pol_lookup_func include/net/ip6_fib.h:582 [inline] fib6_rule_lookup+0x52e/0x6f0 net/ipv6/fib6_rules.c:121 ip6_route_output_flags_noref+0x2e6/0x380 net/ipv6/route.c:2625 ip6_route_output_flags+0x76/0x320 net/ipv6/route.c:2638 ip6_route_output include/net/ip6_route.h:98 [inline] ip6_dst_lookup_tail+0x5ab/0x1620 net/ipv6/ip6_output.c:1092 ip6_dst_lookup_flow+0x90/0x1d0 net/ipv6/ip6_output.c:1222 ip6_sk_dst_lookup_flow+0x553/0x980 net/ipv6/ip6_output.c:1260 udpv6_sendmsg+0x151d/0x2c80 net/ipv6/udp.c:1554 inet6_sendmsg+0x9d/0xe0 net/ipv6/af_inet6.c:665 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 __sys_sendto+0x23a/0x340 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xe1/0x1b0 net/socket.c:2125 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 Freed by task 7599: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 kasan_set_track+0x25/0x30 mm/kasan/common.c:52 kasan_save_free_info+0x2e/0x40 mm/kasan/generic.c:511 ____kasan_slab_free mm/kasan/common.c:236 [inline] ____kasan_slab_free+0x160/0x1c0 mm/kasan/common.c:200 kasan_slab_free include/linux/kasan.h:177 [inline] slab_free_hook mm/slub.c:1724 [inline] slab_free_freelist_hook+0x8b/0x1c0 mm/slub.c:1750 slab_free mm/slub.c:3661 [inline] kmem_cache_free+0xee/0x5c0 mm/slub.c:3683 dst_destroy+0x2ea/0x400 net/core/dst.c:127 rcu_do_batch kernel/rcu/tree.c:2250 [inline] rcu_core+0x81f/0x1980 kernel/rcu/tree.c:2510 __do_softirq+0x1fb/0xadc kernel/softirq.c:571 Last potentially related work creation: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 __kasan_record_aux_stack+0xbc/0xd0 mm/kasan/generic.c:481 call_rcu+0x9d/0x820 kernel/rcu/tree.c:2798 dst_release net/core/dst.c:177 [inline] dst_release+0x7d/0xe0 net/core/dst.c:167 refdst_drop include/net/dst.h:256 [inline] skb_dst_drop include/net/dst.h:268 [inline] skb_release_head_state+0x250/0x2a0 net/core/skbuff.c:838 skb_release_all net/core/skbuff.c:852 [inline] __kfree_skb net/core/skbuff.c:868 [inline] kfree_skb_reason+0x151/0x4b0 net/core/skbuff.c:891 kfree_skb_list_reason+0x4b/0x70 net/core/skbuff.c:901 kfree_skb_list include/linux/skbuff.h:1227 [inline] ip6_fragment+0x2026/0x2770 net/ipv6/ip6_output.c:949 __ip6_finish_output net/ipv6/ip6_output.c:193 [inline] ip6_finish_output+0x9a3/0x1170 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0x1f1/0x540 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:445 [inline] ip6_local_out+0xb3/0x1a0 net/ipv6/output_core.c:161 ip6_send_skb+0xbb/0x340 net/ipv6/ip6_output.c:1966 udp_v6_send_skb+0x82a/0x18a0 net/ipv6/udp.c:1286 udp_v6_push_pending_frames+0x140/0x200 net/ipv6/udp.c:1313 udpv6_sendmsg+0x18da/0x2c80 net/ipv6/udp.c:1606 inet6_sendmsg+0x9d/0xe0 net/ipv6/af_inet6.c:665 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 sock_write_iter+0x295/0x3d0 net/socket.c:1108 call_write_iter include/linux/fs.h:2191 [inline] new_sync_write fs/read_write.c:491 [inline] vfs_write+0x9ed/0xdd0 fs/read_write.c:584 ksys_write+0x1ec/0x250 fs/read_write.c:637 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 Second to last potentially related work creation: kasan_save_stack+0x22/0x40 mm/kasan/common.c:45 __kasan_record_aux_stack+0xbc/0xd0 mm/kasan/generic.c:481 call_rcu+0x9d/0x820 kernel/rcu/tree.c:2798 dst_release net/core/dst.c:177 [inline] dst_release+0x7d/0xe0 net/core/dst.c:167 refdst_drop include/net/dst.h:256 [inline] skb_dst_drop include/net/dst.h:268 [inline] __dev_queue_xmit+0x1b9d/0x3ba0 net/core/dev.c:4211 dev_queue_xmit include/linux/netdevice.h:3008 [inline] neigh_resolve_output net/core/neighbour.c:1552 [inline] neigh_resolve_output+0x51b/0x840 net/core/neighbour.c:1532 neigh_output include/net/neighbour.h:546 [inline] ip6_finish_output2+0x56c/0x1530 net/ipv6/ip6_output.c:134 __ip6_finish_output net/ipv6/ip6_output.c:195 [inline] ip6_finish_output+0x694/0x1170 net/ipv6/ip6_output.c:206 NF_HOOK_COND include/linux/netfilter.h:291 [inline] ip6_output+0x1f1/0x540 net/ipv6/ip6_output.c:227 dst_output include/net/dst.h:445 [inline] NF_HOOK include/linux/netfilter.h:302 [inline] NF_HOOK include/linux/netfilter.h:296 [inline] mld_sendpack+0xa09/0xe70 net/ipv6/mcast.c:1820 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x720/0xdc0 net/ipv6/mcast.c:2653 process_one_work+0x9bf/0x1710 kernel/workqueue.c:2289 worker_thread+0x669/0x1090 kernel/workqueue.c:2436 kthread+0x2e8/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 The buggy address belongs to the object at ffff88801d403dc0 which belongs to the cache ip6_dst_cache of size 240 The buggy address is located 192 bytes inside of 240-byte region [ffff88801d403dc0, ffff88801d403eb0) The buggy address belongs to the physical page: page:ffffea00007500c0 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1d403 memcg:ffff888022f49c81 flags: 0xfff00000000200(slab|node=0|zone=1|lastcpupid=0x7ff) raw: 00fff00000000200 ffffea0001ef6580 dead000000000002 ffff88814addf640 raw: 0000000000000000 00000000800c000c 00000001ffffffff ffff888022f49c81 page dumped because: kasan: bad access detected page_owner tracks the page as allocated page last allocated via order 0, migratetype Unmovable, gfp_mask 0x112a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_HARDWALL), pid 3719, tgid 3719 (kworker/0:6), ts 136223432244, free_ts 136222971441 prep_new_page mm/page_alloc.c:2539 [inline] get_page_from_freelist+0x10b5/0x2d50 mm/page_alloc.c:4288 __alloc_pages+0x1cb/0x5b0 mm/page_alloc.c:5555 alloc_pages+0x1aa/0x270 mm/mempolicy.c:2285 alloc_slab_page mm/slub.c:1794 [inline] allocate_slab+0x213/0x300 mm/slub.c:1939 new_slab mm/slub.c:1992 [inline] ___slab_alloc+0xa91/0x1400 mm/slub.c:3180 __slab_alloc.constprop.0+0x56/0xa0 mm/slub.c:3279 slab_alloc_node mm/slub.c:3364 [inline] slab_alloc mm/slub.c:3406 [inline] __kmem_cache_alloc_lru mm/slub.c:3413 [inline] kmem_cache_alloc+0x31a/0x3d0 mm/slub.c:3422 dst_alloc+0x14a/0x1f0 net/core/dst.c:92 ip6_dst_alloc+0x32/0xa0 net/ipv6/route.c:344 icmp6_dst_alloc+0x71/0x680 net/ipv6/route.c:3261 mld_sendpack+0x5de/0xe70 net/ipv6/mcast.c:1809 mld_send_cr net/ipv6/mcast.c:2121 [inline] mld_ifc_work+0x720/0xdc0 net/ipv6/mcast.c:2653 process_one_work+0x9bf/0x1710 kernel/workqueue.c:2289 worker_thread+0x669/0x1090 kernel/workqueue.c:2436 kthread+0x2e8/0x3a0 kernel/kthread.c:376 ret_from_fork+0x1f/0x30 arch/x86/entry/entry_64.S:306 page last free stack trace: reset_page_owner include/linux/page_owner.h:24 [inline] free_pages_prepare mm/page_alloc.c:1459 [inline] free_pcp_prepare+0x65c/0xd90 mm/page_alloc.c:1509 free_unref_page_prepare mm/page_alloc.c:3387 [inline] free_unref_page+0x1d/0x4d0 mm/page_alloc.c:3483 __unfreeze_partials+0x17c/0x1a0 mm/slub.c:2586 qlink_free mm/kasan/quarantine.c:168 [inline] qlist_free_all+0x6a/0x170 mm/kasan/quarantine.c:187 kasan_quarantine_reduce+0x184/0x210 mm/kasan/quarantine.c:294 __kasan_slab_alloc+0x66/0x90 mm/kasan/common.c:302 kasan_slab_alloc include/linux/kasan.h:201 [inline] slab_post_alloc_hook mm/slab.h:737 [inline] slab_alloc_node mm/slub.c:3398 [inline] kmem_cache_alloc_node+0x304/0x410 mm/slub.c:3443 __alloc_skb+0x214/0x300 net/core/skbuff.c:497 alloc_skb include/linux/skbuff.h:1267 [inline] netlink_alloc_large_skb net/netlink/af_netlink.c:1191 [inline] netlink_sendmsg+0x9a6/0xe10 net/netlink/af_netlink.c:1896 sock_sendmsg_nosec net/socket.c:714 [inline] sock_sendmsg+0xd3/0x120 net/socket.c:734 __sys_sendto+0x23a/0x340 net/socket.c:2117 __do_sys_sendto net/socket.c:2129 [inline] __se_sys_sendto net/socket.c:2125 [inline] __x64_sys_sendto+0xe1/0x1b0 net/socket.c:2125 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 Fixes: 1758fd4688eb ("ipv6: remove unnecessary dst_hold() in ip6_fragment()") Reported-by: syzbot+8c0ac31aa9681abb9e2d@syzkaller.appspotmail.com Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Wei Wang <weiwan@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Link: https://lore.kernel.org/r/20221206101351.2037285-1-edumazet@google.com Signed-off-by: Jakub Kicinski <kuba@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Yongqiang Liu <liuyongqiang13@huawei.com> --- net/ipv6/ip6_output.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 6fd1a4b61747..70820d049b92 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -734,6 +734,9 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); + /* We prevent @rt from being freed. */ + rcu_read_lock(); + for (;;) { /* Prepare header of the next frame, * before previous one went down. */ @@ -776,6 +779,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, if (err == 0) { IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGOKS); + rcu_read_unlock(); return 0; } @@ -783,6 +787,7 @@ int ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, IP6_INC_STATS(net, ip6_dst_idev(&rt->dst), IPSTATS_MIB_FRAGFAILS); + rcu_read_unlock(); return err; slow_path_clean: -- 2.25.1