[PATCH OLK-6.6 v2 0/2] CVE-2026-90313
Pu Lehui (1): bpf, cgroup: Fix invalid storage access after __cgroup_bpf_attach failed Yonghong Song (1): bpf: Allow pre-ordering for bpf cgroup progs include/linux/bpf-cgroup.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 41 +++++++++++++++++++++++++++------- kernel/bpf/syscall.c | 3 ++- tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 38 insertions(+), 9 deletions(-) -- 2.34.1
From: Yonghong Song <yonghong.song@linux.dev> stable inclusion from stable-v6.6.93 commit bc8023ef3b11410682e5d4990e05e5bc2d3e1c94 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICGTHF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- [ Upstream commit 4b82b181a26cff8bf7adc3a85a88d121d92edeaf ] Currently for bpf progs in a cgroup hierarchy, the effective prog array is computed from bottom cgroup to upper cgroups (post-ordering). For example, the following cgroup hierarchy root cgroup: p1, p2 subcgroup: p3, p4 have BPF_F_ALLOW_MULTI for both cgroup levels. The effective cgroup array ordering looks like p3 p4 p1 p2 and at run time, progs will execute based on that order. But in some cases, it is desirable to have root prog executes earlier than children progs (pre-ordering). For example, - prog p1 intends to collect original pkt dest addresses. - prog p3 will modify original pkt dest addresses to a proxy address for security reason. The end result is that prog p1 gets proxy address which is not what it wants. Putting p1 to every child cgroup is not desirable either as it will duplicate itself in many child cgroups. And this is exactly a use case we are encountering in Meta. To fix this issue, let us introduce a flag BPF_F_PREORDER. If the flag is specified at attachment time, the prog has higher priority and the ordering with that flag will be from top to bottom (pre-ordering). For example, in the above example, root cgroup: p1, p2 subcgroup: p3, p4 Let us say p2 and p4 are marked with BPF_F_PREORDER. The final effective array ordering will be p2 p4 p3 p1 Suggested-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Yonghong Song <yonghong.song@linux.dev> Link: https://lore.kernel.org/r/20250224230116.283071-1-yonghong.song@linux.dev Signed-off-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Sasha Levin <sashal@kernel.org> Conflicts: kernel/bpf/cgroup.c [ctx conflicts] Signed-off-by: Pu Lehui <pulehui@huawei.com> --- include/linux/bpf-cgroup.h | 1 + include/uapi/linux/bpf.h | 1 + kernel/bpf/cgroup.c | 33 +++++++++++++++++++++++++-------- kernel/bpf/syscall.c | 3 ++- tools/include/uapi/linux/bpf.h | 1 + 5 files changed, 30 insertions(+), 9 deletions(-) diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index bd9e3d5c7835..37f860ab9efa 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -106,6 +106,7 @@ struct bpf_prog_list { struct bpf_prog *prog; struct bpf_cgroup_link *link; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE]; + u32 flags; }; int cgroup_bpf_inherit(struct cgroup *cgrp); diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 4c6a06ba878d..9b48463575c9 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -1156,6 +1156,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index d72413d9b9bc..4813008b49ea 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -390,7 +390,7 @@ static struct bpf_prog *prog_list_prog(struct bpf_prog_list *pl) /* count number of elements in the list. * it's slow but the list cannot be long */ -static u32 prog_list_length(struct hlist_head *head) +static u32 prog_list_length(struct hlist_head *head, int *preorder_cnt) { struct bpf_prog_list *pl; u32 cnt = 0; @@ -398,6 +398,8 @@ static u32 prog_list_length(struct hlist_head *head) hlist_for_each_entry(pl, head, node) { if (!prog_list_prog(pl)) continue; + if (preorder_cnt && (pl->flags & BPF_F_PREORDER)) + (*preorder_cnt)++; cnt++; } return cnt; @@ -421,7 +423,7 @@ static bool hierarchy_allows_attach(struct cgroup *cgrp, if (flags & BPF_F_ALLOW_MULTI) return true; - cnt = prog_list_length(&p->bpf.progs[atype]); + cnt = prog_list_length(&p->bpf.progs[atype], NULL); WARN_ON_ONCE(cnt > 1); if (cnt == 1) return !!(flags & BPF_F_ALLOW_OVERRIDE); @@ -444,12 +446,12 @@ static int compute_effective_progs(struct cgroup *cgrp, struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; - int cnt = 0; + int i, j, cnt = 0, preorder_cnt = 0, fstart, bstart, init_bstart; /* count number of effective programs by walking parents */ do { if (cnt == 0 || (p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) - cnt += prog_list_length(&p->bpf.progs[atype]); + cnt += prog_list_length(&p->bpf.progs[atype], &preorder_cnt); p = cgroup_parent(p); } while (p); @@ -460,20 +462,34 @@ static int compute_effective_progs(struct cgroup *cgrp, /* populate the array with effective progs */ cnt = 0; p = cgrp; + fstart = preorder_cnt; + bstart = preorder_cnt - 1; do { if (cnt > 0 && !(p->bpf.flags[atype] & BPF_F_ALLOW_MULTI)) continue; + init_bstart = bstart; hlist_for_each_entry(pl, &p->bpf.progs[atype], node) { if (!prog_list_prog(pl)) continue; - item = &progs->items[cnt]; + if (pl->flags & BPF_F_PREORDER) { + item = &progs->items[bstart]; + bstart--; + } else { + item = &progs->items[fstart]; + fstart++; + } item->prog = prog_list_prog(pl); bpf_cgroup_storages_assign(item->cgroup_storage, pl->storage); cnt++; } + + /* reverse pre-ordering progs at this cgroup level */ + for (i = bstart + 1, j = init_bstart; i < j; i++, j--) + swap(progs->items[i], progs->items[j]); + } while ((p = cgroup_parent(p))); *array = progs; @@ -690,7 +706,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, return -EEXIST; #endif - if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS) + if (prog_list_length(progs, NULL) >= BPF_CGROUP_MAX_PROGS) return -E2BIG; pl = find_attach_entry(progs, prog, link, replace_prog, @@ -725,6 +741,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, pl->prog = prog; pl->link = link; + pl->flags = flags; bpf_cgroup_storages_assign(pl->storage, storage); cgrp->bpf.flags[atype] = saved_flags; @@ -1117,7 +1134,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, lockdep_is_held(&cgroup_mutex)); total_cnt += bpf_prog_array_length(effective); } else { - total_cnt += prog_list_length(&cgrp->bpf.progs[atype]); + total_cnt += prog_list_length(&cgrp->bpf.progs[atype], NULL); } } @@ -1149,7 +1166,7 @@ static int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr, u32 id; progs = &cgrp->bpf.progs[atype]; - cnt = min_t(int, prog_list_length(progs), total_cnt); + cnt = min_t(int, prog_list_length(progs, NULL), total_cnt); i = 0; hlist_for_each_entry(pl, progs, node) { prog = prog_list_prog(pl); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index c98dbecb618d..3a8e29431e63 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -3956,7 +3956,8 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, #define BPF_F_ATTACH_MASK_BASE \ (BPF_F_ALLOW_OVERRIDE | \ BPF_F_ALLOW_MULTI | \ - BPF_F_REPLACE) + BPF_F_REPLACE | \ + BPF_F_PREORDER) #define BPF_F_ATTACH_MASK_MPROG \ (BPF_F_REPLACE | \ diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index bdc686df3faa..2691740425ee 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -1152,6 +1152,7 @@ enum bpf_perf_event_type { #define BPF_F_BEFORE (1U << 3) #define BPF_F_AFTER (1U << 4) #define BPF_F_ID (1U << 5) +#define BPF_F_PREORDER (1U << 6) #define BPF_F_LINK BPF_F_LINK /* 1 << 13 */ /* If BPF_F_STRICT_ALIGNMENT is used in BPF_PROG_LOAD command, the -- 2.34.1
stable inclusion from stable-6.6.157 commit e26db0d636e4c24a6b16683ea95cf5077c64d74b category: bugfix bugzilla: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... ------------------------------ [ Upstream commit 6655c409707ec8ce9ce0850ffe4fe02331fd4d9c ] A potential invalid storage access issue can occur after replacing a cgroup bpf prog. This occurs in the following scenario: 1. prog1 with storage is attached to a cgroup in multi-attach mode. 2. prog1 is replaced with prog2 using BPF_F_REPLACE in multi-attach mode, but fails midway (e.g. in bpf_trampoline_link_cgroup_shim or update_effective_progs). 3. A new prog3 is attached to the cgroup in multi-attach mode. The reason is that __cgroup_bpf_attach overwrites pl->storage with the new storage prior to attachment completion. When attachment fails midway, the cleanup path calls bpf_cgroup_storages_free(new_storage) to free the newly allocated storage, but fails to restore pl->storage back to old_storage. Consequently, the still-active prog1 holds invalid or dangling storage pointers, leading to an invalid memory access when prog1 executes and calls bpf_get_local_storage. Additionally, original pl->flags and cgrp->bpf.flags[atype] are left unrestored. Fix this by saving old_pl_flags, old_storage, and old_flags prior to the update, and properly restoring all of them in the cleanup path on error. Fixes: 7d9c3427894f ("bpf: Make cgroup storages shared between programs on the same cgroup") Reported-by: Sashiko <sashiko-bot@kernel.org> Signed-off-by: Pu Lehui <pulehui@huawei.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com> Link: https://lore.kernel.org/bpf/20260803013934.4036646-1-pulehui@huaweicloud.com Signed-off-by: Sasha Levin <sashal@kernel.org> Signed-off-by: Pu Lehui <pulehui@huawei.com> --- kernel/bpf/cgroup.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 4813008b49ea..c0cee61518e1 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -667,8 +667,10 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *old_prog = NULL; struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_cgroup_storage *new_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; + struct bpf_cgroup_storage *old_storage[MAX_BPF_CGROUP_STORAGE_TYPE] = {}; struct bpf_prog *new_prog = prog ? : link->link.prog; enum cgroup_bpf_attach_type atype; + u32 old_flags, old_pl_flags; struct bpf_prog_list *pl; struct hlist_head *progs; int err; @@ -720,6 +722,8 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, if (pl) { old_prog = pl->prog; + old_pl_flags = pl->flags; + bpf_cgroup_storages_assign(old_storage, pl->storage); } else { struct hlist_node *last = NULL; @@ -743,6 +747,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, pl->link = link; pl->flags = flags; bpf_cgroup_storages_assign(pl->storage, storage); + old_flags = cgrp->bpf.flags[atype]; cgrp->bpf.flags[atype] = saved_flags; if (type == BPF_LSM_CGROUP) { @@ -773,12 +778,15 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp, if (old_prog) { pl->prog = old_prog; pl->link = NULL; + pl->flags = old_pl_flags; + bpf_cgroup_storages_assign(pl->storage, old_storage); } bpf_cgroup_storages_free(new_storage); if (!old_prog) { hlist_del(&pl->node); kfree(pl); } + cgrp->bpf.flags[atype] = old_flags; return err; } -- 2.34.1
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://atomgit.com/openeuler/kernel/merge_requests/28409 邮件列表地址：https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/HDU... FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://atomgit.com/openeuler/kernel/merge_requests/28409 Mailing list address: https://mailweb.openeuler.org/archives/list/kernel@openeuler.org/message/HDU...
participants (2)
-
patchwork bot -
Pu Lehui