From 6da88306811b40a207c94c9da9faf07bdb20776e Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:39 +0800 Subject: [PATCH 1/8] cgroup: Prepare for using css_task_iter_*() in BPF This patch makes some preparations for using css_task_iter_*() in BPF Program. 1. Flags CSS_TASK_ITER_* are #define-s and it's not easy for bpf prog to use them. Convert them to enum so bpf prog can take them from vmlinux.h. 2. In the next patch we will add css_task_iter_*() in common kfuncs which is not safe. Since css_task_iter_*() does spin_unlock_irq() which might screw up irq flags depending on the context where bpf prog is running. So we should use irqsave/irqrestore here and the switching is harmless. Suggested-by: Alexei Starovoitov Signed-off-by: Chuyi Zhou Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20231018061746.111364-2-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/cgroup.h | 12 +++++------- kernel/cgroup/cgroup.c | 18 ++++++++++++------ 2 files changed, 17 insertions(+), 13 deletions(-) diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b307013b9c6c..0ef0af66080e 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -40,13 +40,11 @@ struct kernel_clone_args; #define CGROUP_WEIGHT_DFL 100 #define CGROUP_WEIGHT_MAX 10000 -/* walk only threadgroup leaders */ -#define CSS_TASK_ITER_PROCS (1U << 0) -/* walk all threaded css_sets in the domain */ -#define CSS_TASK_ITER_THREADED (1U << 1) - -/* internal flags */ -#define CSS_TASK_ITER_SKIPPED (1U << 16) +enum { + CSS_TASK_ITER_PROCS = (1U << 0), /* walk only threadgroup leaders */ + CSS_TASK_ITER_THREADED = (1U << 1), /* walk all threaded css_sets in the domain */ + CSS_TASK_ITER_SKIPPED = (1U << 16), /* internal flags */ +}; /* a css_task_iter should be treated as an opaque object */ struct css_task_iter { diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 1fb7f562289d..b6d64f3b8888 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -4917,9 +4917,11 @@ repeat: void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, struct css_task_iter *it) { + unsigned long irqflags; + memset(it, 0, sizeof(*it)); - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); it->ss = css->ss; it->flags = flags; @@ -4933,7 +4935,7 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, css_task_iter_advance(it); - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); } /** @@ -4946,12 +4948,14 @@ void css_task_iter_start(struct cgroup_subsys_state *css, unsigned int flags, */ struct task_struct *css_task_iter_next(struct css_task_iter *it) { + unsigned long irqflags; + if (it->cur_task) { put_task_struct(it->cur_task); it->cur_task = NULL; } - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); /* @it may be half-advanced by skips, finish advancing */ if (it->flags & CSS_TASK_ITER_SKIPPED) @@ -4964,7 +4968,7 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) css_task_iter_advance(it); } - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); return it->cur_task; } @@ -4977,11 +4981,13 @@ struct task_struct *css_task_iter_next(struct css_task_iter *it) */ void css_task_iter_end(struct css_task_iter *it) { + unsigned long irqflags; + if (it->cur_cset) { - spin_lock_irq(&css_set_lock); + spin_lock_irqsave(&css_set_lock, irqflags); list_del(&it->iters_node); put_css_set_locked(it->cur_cset); - spin_unlock_irq(&css_set_lock); + spin_unlock_irqrestore(&css_set_lock, irqflags); } if (it->cur_dcset) From 9c66dc94b62aef23300f05f63404afb8990920b4 Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:40 +0800 Subject: [PATCH 2/8] bpf: Introduce css_task open-coded iterator kfuncs This patch adds kfuncs bpf_iter_css_task_{new,next,destroy} which allow creation and manipulation of struct bpf_iter_css_task in open-coded iterator style. These kfuncs actually wrapps css_task_iter_{start,next, end}. BPF programs can use these kfuncs through bpf_for_each macro for iteration of all tasks under a css. css_task_iter_*() would try to get the global spin-lock *css_set_lock*, so the bpf side has to be careful in where it allows to use this iter. Currently we only allow it in bpf_lsm and bpf iter-s. Signed-off-by: Chuyi Zhou Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20231018061746.111364-3-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/helpers.c | 3 + kernel/bpf/task_iter.c | 58 +++++++++++++++++++ kernel/bpf/verifier.c | 23 ++++++++ .../testing/selftests/bpf/bpf_experimental.h | 8 +++ 4 files changed, 92 insertions(+) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 61f51dee8448..c01441db9fd5 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2560,6 +2560,9 @@ BTF_ID_FLAGS(func, bpf_iter_num_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_iter_task_vma_new, KF_ITER_NEW | KF_RCU) BTF_ID_FLAGS(func, bpf_iter_task_vma_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index fef17628341f..e4126698cecf 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -894,6 +894,64 @@ __bpf_kfunc void bpf_iter_task_vma_destroy(struct bpf_iter_task_vma *it) __diag_pop(); +struct bpf_iter_css_task { + __u64 __opaque[1]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_task_kern { + struct css_task_iter *css_it; +} __attribute__((aligned(8))); + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_task_kern) != sizeof(struct bpf_iter_css_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_task_kern) != + __alignof__(struct bpf_iter_css_task)); + kit->css_it = NULL; + switch (flags) { + case CSS_TASK_ITER_PROCS | CSS_TASK_ITER_THREADED: + case CSS_TASK_ITER_PROCS: + case 0: + break; + default: + return -EINVAL; + } + + kit->css_it = bpf_mem_alloc(&bpf_global_ma, sizeof(struct css_task_iter)); + if (!kit->css_it) + return -ENOMEM; + css_task_iter_start(css, flags, kit->css_it); + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return NULL; + return css_task_iter_next(kit->css_it); +} + +__bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) +{ + struct bpf_iter_css_task_kern *kit = (void *)it; + + if (!kit->css_it) + return; + css_task_iter_end(kit->css_it); + bpf_mem_free(&bpf_global_ma, kit->css_it); +} + +__diag_pop(); + DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); static void do_mmap_read_unlock(struct irq_work *entry) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bb58987e4844..974713185269 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10472,6 +10472,7 @@ enum special_kfunc_type { KF_bpf_percpu_obj_new_impl, KF_bpf_percpu_obj_drop_impl, KF_bpf_throw, + KF_bpf_iter_css_task_new, }; BTF_SET_START(special_kfunc_set) @@ -10495,6 +10496,7 @@ BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) +BTF_ID(func, bpf_iter_css_task_new) BTF_SET_END(special_kfunc_set) BTF_ID_LIST(special_kfunc_list) @@ -10520,6 +10522,7 @@ BTF_ID(func, bpf_dynptr_clone) BTF_ID(func, bpf_percpu_obj_new_impl) BTF_ID(func, bpf_percpu_obj_drop_impl) BTF_ID(func, bpf_throw) +BTF_ID(func, bpf_iter_css_task_new) static bool is_kfunc_ret_null(struct bpf_kfunc_call_arg_meta *meta) { @@ -11050,6 +11053,20 @@ static int process_kf_arg_ptr_to_rbtree_node(struct bpf_verifier_env *env, &meta->arg_rbtree_root.field); } +static bool check_css_task_iter_allowlist(struct bpf_verifier_env *env) +{ + enum bpf_prog_type prog_type = resolve_prog_type(env->prog); + + switch (prog_type) { + case BPF_PROG_TYPE_LSM: + return true; + case BPF_TRACE_ITER: + return env->prog->aux->sleepable; + default: + return false; + } +} + static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_arg_meta *meta, int insn_idx) { @@ -11300,6 +11317,12 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ break; } case KF_ARG_PTR_TO_ITER: + if (meta->func_id == special_kfunc_list[KF_bpf_iter_css_task_new]) { + if (!check_css_task_iter_allowlist(env)) { + verbose(env, "css_task_iter is only allowed in bpf_lsm and bpf iter-s\n"); + return -EINVAL; + } + } ret = process_iter_arg(env, regno, insn_idx, meta); if (ret < 0) return ret; diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 2c8cb3f61529..6792ed2b45d7 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -458,4 +458,12 @@ extern void bpf_throw(u64 cookie) __ksym; __bpf_assert_op(LHS, <=, END, value, false); \ }) +struct bpf_iter_css_task; +struct cgroup_subsys_state; +extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it, + struct cgroup_subsys_state *css, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym; +extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym; + + #endif From c68a78ffe2cb4207f64fd0f4262818c728c67be0 Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:41 +0800 Subject: [PATCH 3/8] bpf: Introduce task open coded iterator kfuncs This patch adds kfuncs bpf_iter_task_{new,next,destroy} which allow creation and manipulation of struct bpf_iter_task in open-coded iterator style. BPF programs can use these kfuncs or through bpf_for_each macro to iterate all processes in the system. The API design keep consistent with SEC("iter/task"). bpf_iter_task_new() accepts a specific task and iterating type which allows: 1. iterating all process in the system (BPF_TASK_ITER_ALL_PROCS) 2. iterating all threads in the system (BPF_TASK_ITER_ALL_THREADS) 3. iterating all threads of a specific task (BPF_TASK_ITER_PROC_THREADS) Signed-off-by: Chuyi Zhou Link: https://lore.kernel.org/r/20231018061746.111364-4-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/helpers.c | 3 + kernel/bpf/task_iter.c | 90 +++++++++++++++++++ .../testing/selftests/bpf/bpf_experimental.h | 5 ++ 3 files changed, 98 insertions(+) diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index c01441db9fd5..c25941531265 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2563,6 +2563,9 @@ BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index e4126698cecf..faa1712c1df5 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -952,6 +952,96 @@ __bpf_kfunc void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __diag_pop(); +struct bpf_iter_task { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_task_kern { + struct task_struct *task; + struct task_struct *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +enum { + /* all process in the system */ + BPF_TASK_ITER_ALL_PROCS, + /* all threads in the system */ + BPF_TASK_ITER_ALL_THREADS, + /* all threads of a specific process */ + BPF_TASK_ITER_PROC_THREADS +}; + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task, unsigned int flags) +{ + struct bpf_iter_task_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_task_kern) > sizeof(struct bpf_iter_task)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != + __alignof__(struct bpf_iter_task)); + + kit->task = kit->pos = NULL; + switch (flags) { + case BPF_TASK_ITER_ALL_THREADS: + case BPF_TASK_ITER_ALL_PROCS: + case BPF_TASK_ITER_PROC_THREADS: + break; + default: + return -EINVAL; + } + + if (flags == BPF_TASK_ITER_PROC_THREADS) + kit->task = task; + else + kit->task = &init_task; + kit->pos = kit->task; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) +{ + struct bpf_iter_task_kern *kit = (void *)it; + struct task_struct *pos; + unsigned int flags; + + flags = kit->flags; + pos = kit->pos; + + if (!pos) + return pos; + + if (flags == BPF_TASK_ITER_ALL_PROCS) + goto get_next_task; + + kit->pos = next_thread(kit->pos); + if (kit->pos == kit->task) { + if (flags == BPF_TASK_ITER_PROC_THREADS) { + kit->pos = NULL; + return pos; + } + } else + return pos; + +get_next_task: + kit->pos = next_task(kit->pos); + kit->task = kit->pos; + if (kit->pos == &init_task) + kit->pos = NULL; + + return pos; +} + +__bpf_kfunc void bpf_iter_task_destroy(struct bpf_iter_task *it) +{ +} + +__diag_pop(); + DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work); static void do_mmap_read_unlock(struct irq_work *entry) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 6792ed2b45d7..2f6c747aa874 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -465,5 +465,10 @@ extern int bpf_iter_css_task_new(struct bpf_iter_css_task *it, extern struct task_struct *bpf_iter_css_task_next(struct bpf_iter_css_task *it) __weak __ksym; extern void bpf_iter_css_task_destroy(struct bpf_iter_css_task *it) __weak __ksym; +struct bpf_iter_task; +extern int bpf_iter_task_new(struct bpf_iter_task *it, + struct task_struct *task, unsigned int flags) __weak __ksym; +extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym; +extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym; #endif From 7251d0905e7518bcb990c8e9a3615b1bb23c78f2 Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:42 +0800 Subject: [PATCH 4/8] bpf: Introduce css open-coded iterator kfuncs This Patch adds kfuncs bpf_iter_css_{new,next,destroy} which allow creation and manipulation of struct bpf_iter_css in open-coded iterator style. These kfuncs actually wrapps css_next_descendant_{pre, post}. css_iter can be used to: 1) iterating a sepcific cgroup tree with pre/post/up order 2) iterating cgroup_subsystem in BPF Prog, like for_each_mem_cgroup_tree/cpuset_for_each_descendant_pre in kernel. The API design is consistent with cgroup_iter. bpf_iter_css_new accepts parameters defining iteration order and starting css. Here we also reuse BPF_CGROUP_ITER_DESCENDANTS_PRE, BPF_CGROUP_ITER_DESCENDANTS_POST, BPF_CGROUP_ITER_ANCESTORS_UP enums. Signed-off-by: Chuyi Zhou Acked-by: Tejun Heo Link: https://lore.kernel.org/r/20231018061746.111364-5-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/cgroup_iter.c | 65 +++++++++++++++++++ kernel/bpf/helpers.c | 3 + .../testing/selftests/bpf/bpf_experimental.h | 6 ++ 3 files changed, 74 insertions(+) diff --git a/kernel/bpf/cgroup_iter.c b/kernel/bpf/cgroup_iter.c index 810378f04fbc..209e5135f9fb 100644 --- a/kernel/bpf/cgroup_iter.c +++ b/kernel/bpf/cgroup_iter.c @@ -294,3 +294,68 @@ static int __init bpf_cgroup_iter_init(void) } late_initcall(bpf_cgroup_iter_init); + +struct bpf_iter_css { + __u64 __opaque[3]; +} __attribute__((aligned(8))); + +struct bpf_iter_css_kern { + struct cgroup_subsys_state *start; + struct cgroup_subsys_state *pos; + unsigned int flags; +} __attribute__((aligned(8))); + +__diag_push(); +__diag_ignore_all("-Wmissing-prototypes", + "Global functions as their definitions will be in vmlinux BTF"); + +__bpf_kfunc int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + BUILD_BUG_ON(sizeof(struct bpf_iter_css_kern) > sizeof(struct bpf_iter_css)); + BUILD_BUG_ON(__alignof__(struct bpf_iter_css_kern) != __alignof__(struct bpf_iter_css)); + + kit->start = NULL; + switch (flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + case BPF_CGROUP_ITER_DESCENDANTS_POST: + case BPF_CGROUP_ITER_ANCESTORS_UP: + break; + default: + return -EINVAL; + } + + kit->start = start; + kit->pos = NULL; + kit->flags = flags; + return 0; +} + +__bpf_kfunc struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) +{ + struct bpf_iter_css_kern *kit = (void *)it; + + if (!kit->start) + return NULL; + + switch (kit->flags) { + case BPF_CGROUP_ITER_DESCENDANTS_PRE: + kit->pos = css_next_descendant_pre(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_DESCENDANTS_POST: + kit->pos = css_next_descendant_post(kit->pos, kit->start); + break; + case BPF_CGROUP_ITER_ANCESTORS_UP: + kit->pos = kit->pos ? kit->pos->parent : kit->start; + } + + return kit->pos; +} + +__bpf_kfunc void bpf_iter_css_destroy(struct bpf_iter_css *it) +{ +} + +__diag_pop(); \ No newline at end of file diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index c25941531265..b1d285ed4796 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2566,6 +2566,9 @@ BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY) +BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL) +BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) BTF_ID_FLAGS(func, bpf_dynptr_is_null) BTF_ID_FLAGS(func, bpf_dynptr_is_rdonly) diff --git a/tools/testing/selftests/bpf/bpf_experimental.h b/tools/testing/selftests/bpf/bpf_experimental.h index 2f6c747aa874..1386baf9ae4a 100644 --- a/tools/testing/selftests/bpf/bpf_experimental.h +++ b/tools/testing/selftests/bpf/bpf_experimental.h @@ -471,4 +471,10 @@ extern int bpf_iter_task_new(struct bpf_iter_task *it, extern struct task_struct *bpf_iter_task_next(struct bpf_iter_task *it) __weak __ksym; extern void bpf_iter_task_destroy(struct bpf_iter_task *it) __weak __ksym; +struct bpf_iter_css; +extern int bpf_iter_css_new(struct bpf_iter_css *it, + struct cgroup_subsys_state *start, unsigned int flags) __weak __ksym; +extern struct cgroup_subsys_state *bpf_iter_css_next(struct bpf_iter_css *it) __weak __ksym; +extern void bpf_iter_css_destroy(struct bpf_iter_css *it) __weak __ksym; + #endif From dfab99df147b0d364f0c199f832ff2aedfb2265a Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:43 +0800 Subject: [PATCH 5/8] bpf: teach the verifier to enforce css_iter and task_iter in RCU CS css_iter and task_iter should be used in rcu section. Specifically, in sleepable progs explicit bpf_rcu_read_lock() is needed before use these iters. In normal bpf progs that have implicit rcu_read_lock(), it's OK to use them directly. This patch adds a new a KF flag KF_RCU_PROTECTED for bpf_iter_task_new and bpf_iter_css_new. It means the kfunc should be used in RCU CS. We check whether we are in rcu cs before we want to invoke this kfunc. If the rcu protection is guaranteed, we would let st->type = PTR_TO_STACK | MEM_RCU. Once user do rcu_unlock during the iteration, state MEM_RCU of regs would be cleared. is_iter_reg_valid_init() will reject if reg->type is UNTRUSTED. It is worth noting that currently, bpf_rcu_read_unlock does not clear the state of the STACK_ITER reg, since bpf_for_each_spilled_reg only considers STACK_SPILL. This patch also let bpf_for_each_spilled_reg search STACK_ITER. Signed-off-by: Chuyi Zhou Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231018061746.111364-6-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- include/linux/bpf_verifier.h | 19 ++++++++------ include/linux/btf.h | 1 + kernel/bpf/helpers.c | 4 +-- kernel/bpf/verifier.c | 50 ++++++++++++++++++++++++++++-------- 4 files changed, 53 insertions(+), 21 deletions(-) diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 94ec766432f5..e67cd45a85be 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -386,19 +386,18 @@ struct bpf_verifier_state { u32 jmp_history_cnt; }; -#define bpf_get_spilled_reg(slot, frame) \ +#define bpf_get_spilled_reg(slot, frame, mask) \ (((slot < frame->allocated_stack / BPF_REG_SIZE) && \ - (frame->stack[slot].slot_type[0] == STACK_SPILL)) \ + ((1 << frame->stack[slot].slot_type[0]) & (mask))) \ ? &frame->stack[slot].spilled_ptr : NULL) /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */ -#define bpf_for_each_spilled_reg(iter, frame, reg) \ - for (iter = 0, reg = bpf_get_spilled_reg(iter, frame); \ +#define bpf_for_each_spilled_reg(iter, frame, reg, mask) \ + for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask); \ iter < frame->allocated_stack / BPF_REG_SIZE; \ - iter++, reg = bpf_get_spilled_reg(iter, frame)) + iter++, reg = bpf_get_spilled_reg(iter, frame, mask)) -/* Invoke __expr over regsiters in __vst, setting __state and __reg */ -#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ +#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr) \ ({ \ struct bpf_verifier_state *___vstate = __vst; \ int ___i, ___j; \ @@ -410,7 +409,7 @@ struct bpf_verifier_state { __reg = &___regs[___j]; \ (void)(__expr); \ } \ - bpf_for_each_spilled_reg(___j, __state, __reg) { \ + bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \ if (!__reg) \ continue; \ (void)(__expr); \ @@ -418,6 +417,10 @@ struct bpf_verifier_state { } \ }) +/* Invoke __expr over regsiters in __vst, setting __state and __reg */ +#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \ + bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr) + /* linked list of verifier states used to prune search */ struct bpf_verifier_state_list { struct bpf_verifier_state state; diff --git a/include/linux/btf.h b/include/linux/btf.h index 928113a80a95..c2231c64d60b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -74,6 +74,7 @@ #define KF_ITER_NEW (1 << 8) /* kfunc implements BPF iter constructor */ #define KF_ITER_NEXT (1 << 9) /* kfunc implements BPF iter next method */ #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */ +#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */ /* * Tag marking a kernel function as a kfunc. This is meant to minimize the diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index b1d285ed4796..da058aead20c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -2563,10 +2563,10 @@ BTF_ID_FLAGS(func, bpf_iter_task_vma_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_iter_css_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) BTF_ID_FLAGS(func, bpf_iter_css_task_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_css_task_destroy, KF_ITER_DESTROY) -BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_task_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) BTF_ID_FLAGS(func, bpf_iter_task_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_task_destroy, KF_ITER_DESTROY) -BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS) +BTF_ID_FLAGS(func, bpf_iter_css_new, KF_ITER_NEW | KF_TRUSTED_ARGS | KF_RCU_PROTECTED) BTF_ID_FLAGS(func, bpf_iter_css_next, KF_ITER_NEXT | KF_RET_NULL) BTF_ID_FLAGS(func, bpf_iter_css_destroy, KF_ITER_DESTROY) BTF_ID_FLAGS(func, bpf_dynptr_adjust) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 974713185269..fcdf2382153a 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1173,7 +1173,12 @@ static bool is_dynptr_type_expected(struct bpf_verifier_env *env, struct bpf_reg static void __mark_reg_known_zero(struct bpf_reg_state *reg); +static bool in_rcu_cs(struct bpf_verifier_env *env); + +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta); + static int mark_stack_slots_iter(struct bpf_verifier_env *env, + struct bpf_kfunc_call_arg_meta *meta, struct bpf_reg_state *reg, int insn_idx, struct btf *btf, u32 btf_id, int nr_slots) { @@ -1194,6 +1199,12 @@ static int mark_stack_slots_iter(struct bpf_verifier_env *env, __mark_reg_known_zero(st); st->type = PTR_TO_STACK; /* we don't have dedicated reg type */ + if (is_kfunc_rcu_protected(meta)) { + if (in_rcu_cs(env)) + st->type |= MEM_RCU; + else + st->type |= PTR_UNTRUSTED; + } st->live |= REG_LIVE_WRITTEN; st->ref_obj_id = i == 0 ? id : 0; st->iter.btf = btf; @@ -1268,7 +1279,7 @@ static bool is_iter_reg_valid_uninit(struct bpf_verifier_env *env, return true; } -static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, +static int is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg, struct btf *btf, u32 btf_id, int nr_slots) { struct bpf_func_state *state = func(env, reg); @@ -1276,26 +1287,28 @@ static bool is_iter_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_ spi = iter_get_spi(env, reg, nr_slots); if (spi < 0) - return false; + return -EINVAL; for (i = 0; i < nr_slots; i++) { struct bpf_stack_state *slot = &state->stack[spi - i]; struct bpf_reg_state *st = &slot->spilled_ptr; + if (st->type & PTR_UNTRUSTED) + return -EPROTO; /* only main (first) slot has ref_obj_id set */ if (i == 0 && !st->ref_obj_id) - return false; + return -EINVAL; if (i != 0 && st->ref_obj_id) - return false; + return -EINVAL; if (st->iter.btf != btf || st->iter.btf_id != btf_id) - return false; + return -EINVAL; for (j = 0; j < BPF_REG_SIZE; j++) if (slot->slot_type[j] != STACK_ITER) - return false; + return -EINVAL; } - return true; + return 0; } /* Check if given stack slot is "special": @@ -7640,15 +7653,24 @@ static int process_iter_arg(struct bpf_verifier_env *env, int regno, int insn_id return err; } - err = mark_stack_slots_iter(env, reg, insn_idx, meta->btf, btf_id, nr_slots); + err = mark_stack_slots_iter(env, meta, reg, insn_idx, meta->btf, btf_id, nr_slots); if (err) return err; } else { /* iter_next() or iter_destroy() expect initialized iter state*/ - if (!is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots)) { + err = is_iter_reg_valid_init(env, reg, meta->btf, btf_id, nr_slots); + switch (err) { + case 0: + break; + case -EINVAL: verbose(env, "expected an initialized iter_%s as arg #%d\n", iter_type_str(meta->btf, btf_id), regno); - return -EINVAL; + return err; + case -EPROTO: + verbose(env, "expected an RCU CS when using %s\n", meta->func_name); + return err; + default: + return err; } spi = iter_get_spi(env, reg, nr_slots); @@ -10231,6 +10253,11 @@ static bool is_kfunc_rcu(struct bpf_kfunc_call_arg_meta *meta) return meta->kfunc_flags & KF_RCU; } +static bool is_kfunc_rcu_protected(struct bpf_kfunc_call_arg_meta *meta) +{ + return meta->kfunc_flags & KF_RCU_PROTECTED; +} + static bool __kfunc_param_match_suffix(const struct btf *btf, const struct btf_param *arg, const char *suffix) @@ -11582,6 +11609,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, if (env->cur_state->active_rcu_lock) { struct bpf_func_state *state; struct bpf_reg_state *reg; + u32 clear_mask = (1 << STACK_SPILL) | (1 << STACK_ITER); if (in_rbtree_lock_required_cb(env) && (rcu_lock || rcu_unlock)) { verbose(env, "Calling bpf_rcu_read_{lock,unlock} in unnecessary rbtree callback\n"); @@ -11592,7 +11620,7 @@ static int check_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn, verbose(env, "nested rcu read lock (kernel function %s)\n", func_name); return -EINVAL; } else if (rcu_unlock) { - bpf_for_each_reg_in_vstate(env->cur_state, state, reg, ({ + bpf_for_each_reg_in_vstate_mask(env->cur_state, state, reg, clear_mask, ({ if (reg->type & MEM_RCU) { reg->type &= ~(MEM_RCU | PTR_MAYBE_NULL); reg->type |= PTR_UNTRUSTED; From cb3ecf7915a1d7ce5304402f4d8616d9fa5193f7 Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:44 +0800 Subject: [PATCH 6/8] bpf: Let bpf_iter_task_new accept null task ptr When using task_iter to iterate all threads of a specific task, we enforce that the user must pass a valid task pointer to ensure safety. However, when iterating all threads/process in the system, BPF verifier still require a valid ptr instead of "nullable" pointer, even though it's pointless, which is a kind of surprising from usability standpoint. It would be nice if we could let that kfunc accept a explicit null pointer when we are using BPF_TASK_ITER_ALL_{PROCS, THREADS} and a valid pointer when using BPF_TASK_ITER_THREAD. Given a trival kfunc: __bpf_kfunc void FN(struct TYPE_A *obj); BPF Prog would reject a nullptr for obj. The error info is: "arg#x pointer type xx xx must point to scalar, or struct with scalar" reported by get_kfunc_ptr_arg_type(). The reg->type is SCALAR_VALUE and the btf type of ref_t is not scalar or scalar_struct which leads to the rejection of get_kfunc_ptr_arg_type. This patch add "__nullable" annotation: __bpf_kfunc void FN(struct TYPE_A *obj__nullable); Here __nullable indicates obj can be optional, user can pass a explicit nullptr or a normal TYPE_A pointer. In get_kfunc_ptr_arg_type(), we will detect whether the current arg is optional and register is null, If so, return a new kfunc_ptr_arg_type KF_ARG_PTR_TO_NULL and skip to the next arg in check_kfunc_args(). Signed-off-by: Chuyi Zhou Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231018061746.111364-7-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- kernel/bpf/task_iter.c | 7 +++++-- kernel/bpf/verifier.c | 13 ++++++++++++- 2 files changed, 17 insertions(+), 3 deletions(-) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index faa1712c1df5..59e747938bdb 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -976,7 +976,7 @@ __diag_ignore_all("-Wmissing-prototypes", "Global functions as their definitions will be in vmlinux BTF"); __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, - struct task_struct *task, unsigned int flags) + struct task_struct *task__nullable, unsigned int flags) { struct bpf_iter_task_kern *kit = (void *)it; @@ -988,14 +988,17 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, switch (flags) { case BPF_TASK_ITER_ALL_THREADS: case BPF_TASK_ITER_ALL_PROCS: + break; case BPF_TASK_ITER_PROC_THREADS: + if (!task__nullable) + return -EINVAL; break; default: return -EINVAL; } if (flags == BPF_TASK_ITER_PROC_THREADS) - kit->task = task; + kit->task = task__nullable; else kit->task = &init_task; kit->pos = kit->task; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index fcdf2382153a..e9bc5d4a25a1 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -10332,6 +10332,11 @@ static bool is_kfunc_arg_refcounted_kptr(const struct btf *btf, const struct btf return __kfunc_param_match_suffix(btf, arg, "__refcounted_kptr"); } +static bool is_kfunc_arg_nullable(const struct btf *btf, const struct btf_param *arg) +{ + return __kfunc_param_match_suffix(btf, arg, "__nullable"); +} + static bool is_kfunc_arg_scalar_with_name(const struct btf *btf, const struct btf_param *arg, const char *name) @@ -10474,6 +10479,7 @@ enum kfunc_ptr_arg_type { KF_ARG_PTR_TO_CALLBACK, KF_ARG_PTR_TO_RB_ROOT, KF_ARG_PTR_TO_RB_NODE, + KF_ARG_PTR_TO_NULL, }; enum special_kfunc_type { @@ -10630,6 +10636,8 @@ get_kfunc_ptr_arg_type(struct bpf_verifier_env *env, if (is_kfunc_arg_callback(env, meta->btf, &args[argno])) return KF_ARG_PTR_TO_CALLBACK; + if (is_kfunc_arg_nullable(meta->btf, &args[argno]) && register_is_null(reg)) + return KF_ARG_PTR_TO_NULL; if (argno + 1 < nargs && (is_kfunc_arg_mem_size(meta->btf, &args[argno + 1], ®s[regno + 1]) || @@ -11180,7 +11188,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ } if ((is_kfunc_trusted_args(meta) || is_kfunc_rcu(meta)) && - (register_is_null(reg) || type_may_be_null(reg->type))) { + (register_is_null(reg) || type_may_be_null(reg->type)) && + !is_kfunc_arg_nullable(meta->btf, &args[i])) { verbose(env, "Possibly NULL pointer passed to trusted arg%d\n", i); return -EACCES; } @@ -11205,6 +11214,8 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_ return kf_arg_type; switch (kf_arg_type) { + case KF_ARG_PTR_TO_NULL: + continue; case KF_ARG_PTR_TO_ALLOC_BTF_ID: case KF_ARG_PTR_TO_BTF_ID: if (!is_kfunc_trusted_args(meta) && !is_kfunc_rcu(meta)) From ddab78cbb52f81f7f7598482602342955b2ff8b8 Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:45 +0800 Subject: [PATCH 7/8] selftests/bpf: rename bpf_iter_task.c to bpf_iter_tasks.c The newly-added struct bpf_iter_task has a name collision with a selftest for the seq_file task iter's bpf skel, so the selftests/bpf/progs file is renamed in order to avoid the collision. Signed-off-by: Chuyi Zhou Acked-by: Andrii Nakryiko Link: https://lore.kernel.org/r/20231018061746.111364-8-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- .../selftests/bpf/prog_tests/bpf_iter.c | 18 +++++++++--------- .../{bpf_iter_task.c => bpf_iter_tasks.c} | 0 2 files changed, 9 insertions(+), 9 deletions(-) rename tools/testing/selftests/bpf/progs/{bpf_iter_task.c => bpf_iter_tasks.c} (100%) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 41aba139b20b..e3498f607b49 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -7,7 +7,7 @@ #include "bpf_iter_ipv6_route.skel.h" #include "bpf_iter_netlink.skel.h" #include "bpf_iter_bpf_map.skel.h" -#include "bpf_iter_task.skel.h" +#include "bpf_iter_tasks.skel.h" #include "bpf_iter_task_stack.skel.h" #include "bpf_iter_task_file.skel.h" #include "bpf_iter_task_vmas.skel.h" @@ -215,12 +215,12 @@ static void *do_nothing_wait(void *arg) static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, int *num_unknown, int *num_known) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; pthread_t thread_id; void *ret; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; ASSERT_OK(pthread_mutex_lock(&do_nothing_mutex), "pthread_mutex_lock"); @@ -239,7 +239,7 @@ static void test_task_common_nocheck(struct bpf_iter_attach_opts *opts, ASSERT_FALSE(pthread_join(thread_id, &ret) || ret != NULL, "pthread_join"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_common(struct bpf_iter_attach_opts *opts, int num_unknown, int num_known) @@ -307,10 +307,10 @@ static void test_task_pidfd(void) static void test_task_sleepable(void) { - struct bpf_iter_task *skel; + struct bpf_iter_tasks *skel; - skel = bpf_iter_task__open_and_load(); - if (!ASSERT_OK_PTR(skel, "bpf_iter_task__open_and_load")) + skel = bpf_iter_tasks__open_and_load(); + if (!ASSERT_OK_PTR(skel, "bpf_iter_tasks__open_and_load")) return; do_dummy_read(skel->progs.dump_task_sleepable); @@ -320,7 +320,7 @@ static void test_task_sleepable(void) ASSERT_GT(skel->bss->num_success_copy_from_user_task, 0, "num_success_copy_from_user_task"); - bpf_iter_task__destroy(skel); + bpf_iter_tasks__destroy(skel); } static void test_task_stack(void) diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_task.c b/tools/testing/selftests/bpf/progs/bpf_iter_tasks.c similarity index 100% rename from tools/testing/selftests/bpf/progs/bpf_iter_task.c rename to tools/testing/selftests/bpf/progs/bpf_iter_tasks.c From 130e0f7af9fc7388b90fb016ca13ff3840c48d4a Mon Sep 17 00:00:00 2001 From: Chuyi Zhou Date: Wed, 18 Oct 2023 14:17:46 +0800 Subject: [PATCH 8/8] selftests/bpf: Add tests for open-coded task and css iter This patch adds 4 subtests to demonstrate these patterns and validating correctness. subtest1: 1) We use task_iter to iterate all process in the system and search for the current process with a given pid. 2) We create some threads in current process context, and use BPF_TASK_ITER_PROC_THREADS to iterate all threads of current process. As expected, we would find all the threads of current process. 3) We create some threads and use BPF_TASK_ITER_ALL_THREADS to iterate all threads in the system. As expected, we would find all the threads which was created. subtest2: We create a cgroup and add the current task to the cgroup. In the BPF program, we would use bpf_for_each(css_task, task, css) to iterate all tasks under the cgroup. As expected, we would find the current process. subtest3: 1) We create a cgroup tree. In the BPF program, we use bpf_for_each(css, pos, root, XXX) to iterate all descendant under the root with pre and post order. As expected, we would find all descendant and the last iterating cgroup in post-order is root cgroup, the first iterating cgroup in pre-order is root cgroup. 2) We wse BPF_CGROUP_ITER_ANCESTORS_UP to traverse the cgroup tree starting from leaf and root separately, and record the height. The diff of the hights would be the total tree-high - 1. subtest4: Add some failure testcase when using css_task, task and css iters, e.g, unlock when using task-iters to iterate tasks. Signed-off-by: Chuyi Zhou Link: https://lore.kernel.org/r/20231018061746.111364-9-zhouchuyi@bytedance.com Signed-off-by: Alexei Starovoitov --- .../testing/selftests/bpf/prog_tests/iters.c | 150 ++++++++++++++++++ tools/testing/selftests/bpf/progs/iters_css.c | 72 +++++++++ .../selftests/bpf/progs/iters_css_task.c | 47 ++++++ .../testing/selftests/bpf/progs/iters_task.c | 41 +++++ .../selftests/bpf/progs/iters_task_failure.c | 105 ++++++++++++ 5 files changed, 415 insertions(+) create mode 100644 tools/testing/selftests/bpf/progs/iters_css.c create mode 100644 tools/testing/selftests/bpf/progs/iters_css_task.c create mode 100644 tools/testing/selftests/bpf/progs/iters_task.c create mode 100644 tools/testing/selftests/bpf/progs/iters_task_failure.c diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c index b696873c5455..c2425791c923 100644 --- a/tools/testing/selftests/bpf/prog_tests/iters.c +++ b/tools/testing/selftests/bpf/prog_tests/iters.c @@ -1,7 +1,14 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */ +#include +#include +#include +#include +#include +#include #include +#include "cgroup_helpers.h" #include "iters.skel.h" #include "iters_state_safety.skel.h" @@ -9,6 +16,10 @@ #include "iters_num.skel.h" #include "iters_testmod_seq.skel.h" #include "iters_task_vma.skel.h" +#include "iters_task.skel.h" +#include "iters_css_task.skel.h" +#include "iters_css.skel.h" +#include "iters_task_failure.skel.h" static void subtest_num_iters(void) { @@ -146,6 +157,138 @@ cleanup: iters_task_vma__destroy(skel); } +static pthread_mutex_t do_nothing_mutex; + +static void *do_nothing_wait(void *arg) +{ + pthread_mutex_lock(&do_nothing_mutex); + pthread_mutex_unlock(&do_nothing_mutex); + + pthread_exit(arg); +} + +#define thread_num 2 + +static void subtest_task_iters(void) +{ + struct iters_task *skel = NULL; + pthread_t thread_ids[thread_num]; + void *ret; + int err; + + skel = iters_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + skel->bss->target_pid = getpid(); + err = iters_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + pthread_mutex_lock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_create(&thread_ids[i], NULL, &do_nothing_wait, NULL), + "pthread_create"); + + syscall(SYS_getpgid); + iters_task__detach(skel); + ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt"); + ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt"); + ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt"); + pthread_mutex_unlock(&do_nothing_mutex); + for (int i = 0; i < thread_num; i++) + ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join"); +cleanup: + iters_task__destroy(skel); +} + +extern int stack_mprotect(void); + +static void subtest_css_task_iters(void) +{ + struct iters_css_task *skel = NULL; + int err, cg_fd, cg_id; + const char *cgrp_path = "/cg1"; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + cg_fd = create_and_get_cgroup(cgrp_path); + if (!ASSERT_GE(cg_fd, 0, "create_and_get_cgroup")) + goto cleanup; + cg_id = get_cgroup_id(cgrp_path); + err = join_cgroup(cgrp_path); + if (!ASSERT_OK(err, "join_cgroup")) + goto cleanup; + + skel = iters_css_task__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->cg_id = cg_id; + err = iters_css_task__attach(skel); + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + err = stack_mprotect(); + if (!ASSERT_EQ(err, -1, "stack_mprotect") || + !ASSERT_EQ(errno, EPERM, "stack_mprotect")) + goto cleanup; + iters_css_task__detach(skel); + ASSERT_EQ(skel->bss->css_task_cnt, 1, "css_task_cnt"); + +cleanup: + cleanup_cgroup_environment(); + iters_css_task__destroy(skel); +} + +static void subtest_css_iters(void) +{ + struct iters_css *skel = NULL; + struct { + const char *path; + int fd; + } cgs[] = { + { "/cg1" }, + { "/cg1/cg2" }, + { "/cg1/cg2/cg3" }, + { "/cg1/cg2/cg3/cg4" }, + }; + int err, cg_nr = ARRAY_SIZE(cgs); + int i; + + err = setup_cgroup_environment(); + if (!ASSERT_OK(err, "setup_cgroup_environment")) + goto cleanup; + for (i = 0; i < cg_nr; i++) { + cgs[i].fd = create_and_get_cgroup(cgs[i].path); + if (!ASSERT_GE(cgs[i].fd, 0, "create_and_get_cgroup")) + goto cleanup; + } + + skel = iters_css__open_and_load(); + if (!ASSERT_OK_PTR(skel, "open_and_load")) + goto cleanup; + + skel->bss->target_pid = getpid(); + skel->bss->root_cg_id = get_cgroup_id(cgs[0].path); + skel->bss->leaf_cg_id = get_cgroup_id(cgs[cg_nr - 1].path); + err = iters_css__attach(skel); + + if (!ASSERT_OK(err, "iters_task__attach")) + goto cleanup; + + syscall(SYS_getpgid); + ASSERT_EQ(skel->bss->pre_order_cnt, cg_nr, "pre_order_cnt"); + ASSERT_EQ(skel->bss->first_cg_id, get_cgroup_id(cgs[0].path), "first_cg_id"); + + ASSERT_EQ(skel->bss->post_order_cnt, cg_nr, "post_order_cnt"); + ASSERT_EQ(skel->bss->last_cg_id, get_cgroup_id(cgs[0].path), "last_cg_id"); + ASSERT_EQ(skel->bss->tree_high, cg_nr - 1, "tree_high"); + iters_css__detach(skel); +cleanup: + cleanup_cgroup_environment(); + iters_css__destroy(skel); +} + void test_iters(void) { RUN_TESTS(iters_state_safety); @@ -161,4 +304,11 @@ void test_iters(void) subtest_testmod_seq_iters(); if (test__start_subtest("task_vma")) subtest_task_vma_iters(); + if (test__start_subtest("task")) + subtest_task_iters(); + if (test__start_subtest("css_task")) + subtest_css_task_iters(); + if (test__start_subtest("css")) + subtest_css_iters(); + RUN_TESTS(iters_task_failure); } diff --git a/tools/testing/selftests/bpf/progs/iters_css.c b/tools/testing/selftests/bpf/progs/iters_css.c new file mode 100644 index 000000000000..ec1f6c2f590b --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css.c @@ -0,0 +1,72 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +u64 root_cg_id, leaf_cg_id; +u64 first_cg_id, last_cg_id; + +int pre_order_cnt, post_order_cnt, tree_high; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_css_for_each(const void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *root_css, *leaf_css, *pos; + struct cgroup *root_cgrp, *leaf_cgrp, *cur_cgrp; + + if (cur_task->pid != target_pid) + return 0; + + root_cgrp = bpf_cgroup_from_id(root_cg_id); + + if (!root_cgrp) + return 0; + + leaf_cgrp = bpf_cgroup_from_id(leaf_cg_id); + + if (!leaf_cgrp) { + bpf_cgroup_release(root_cgrp); + return 0; + } + root_css = &root_cgrp->self; + leaf_css = &leaf_cgrp->self; + pre_order_cnt = post_order_cnt = tree_high = 0; + first_cg_id = last_cg_id = 0; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + cur_cgrp = pos->cgroup; + post_order_cnt++; + last_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_PRE) { + cur_cgrp = pos->cgroup; + pre_order_cnt++; + if (!first_cg_id) + first_cg_id = cur_cgrp->kn->id; + } + + bpf_for_each(css, pos, leaf_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high++; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_ANCESTORS_UP) + tree_high--; + bpf_rcu_read_unlock(); + bpf_cgroup_release(root_cgrp); + bpf_cgroup_release(leaf_cgrp); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_css_task.c b/tools/testing/selftests/bpf/progs/iters_css_task.c new file mode 100644 index 000000000000..5089ce384a1c --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_css_task.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; + +pid_t target_pid; +int css_task_cnt; +u64 cg_id; + +SEC("lsm/file_mprotect") +int BPF_PROG(iter_css_task_for_each, struct vm_area_struct *vma, + unsigned long reqprot, unsigned long prot, int ret) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct cgroup_subsys_state *css; + struct task_struct *task; + struct cgroup *cgrp; + + if (cur_task->pid != target_pid) + return ret; + + cgrp = bpf_cgroup_from_id(cg_id); + + if (!cgrp) + return -EPERM; + + css = &cgrp->self; + css_task_cnt = 0; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) + if (task->pid == target_pid) + css_task_cnt++; + + bpf_cgroup_release(cgrp); + + return -EPERM; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c new file mode 100644 index 000000000000..c9b4055cd410 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +pid_t target_pid; +int procs_cnt, threads_cnt, proc_threads_cnt; + +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("fentry.s/" SYS_PREFIX "sys_getpgid") +int iter_task_for_each_sleep(void *ctx) +{ + struct task_struct *cur_task = bpf_get_current_task_btf(); + struct task_struct *pos; + + if (cur_task->pid != target_pid) + return 0; + procs_cnt = threads_cnt = proc_threads_cnt = 0; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) + if (pos->pid == target_pid) + procs_cnt++; + + bpf_for_each(task, pos, cur_task, BPF_TASK_ITER_PROC_THREADS) + proc_threads_cnt++; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_THREADS) + if (pos->tgid == target_pid) + threads_cnt++; + bpf_rcu_read_unlock(); + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/iters_task_failure.c b/tools/testing/selftests/bpf/progs/iters_task_failure.c new file mode 100644 index 000000000000..c3bf96a67dba --- /dev/null +++ b/tools/testing/selftests/bpf/progs/iters_task_failure.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2023 Chuyi Zhou */ + +#include "vmlinux.h" +#include +#include +#include "bpf_misc.h" +#include "bpf_experimental.h" + +char _license[] SEC("license") = "GPL"; + +struct cgroup *bpf_cgroup_from_id(u64 cgid) __ksym; +void bpf_cgroup_release(struct cgroup *p) __ksym; +void bpf_rcu_read_lock(void) __ksym; +void bpf_rcu_read_unlock(void) __ksym; + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_without_lock) +{ + struct task_struct *pos; + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + + } + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_without_lock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + + } + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_task_next") +int BPF_PROG(iter_tasks_lock_and_unlock) +{ + struct task_struct *pos; + + bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("expected an RCU CS when using bpf_iter_css_next") +int BPF_PROG(iter_css_lock_and_unlock) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *root_css, *pos; + + if (!cgrp) + return 0; + root_css = &cgrp->self; + + bpf_rcu_read_lock(); + bpf_for_each(css, pos, root_css, BPF_CGROUP_ITER_DESCENDANTS_POST) { + bpf_rcu_read_unlock(); + + bpf_rcu_read_lock(); + } + bpf_rcu_read_unlock(); + bpf_cgroup_release(cgrp); + return 0; +} + +SEC("?fentry.s/" SYS_PREFIX "sys_getpgid") +__failure __msg("css_task_iter is only allowed in bpf_lsm and bpf iter-s") +int BPF_PROG(iter_css_task_for_each) +{ + u64 cg_id = bpf_get_current_cgroup_id(); + struct cgroup *cgrp = bpf_cgroup_from_id(cg_id); + struct cgroup_subsys_state *css; + struct task_struct *task; + + if (cgrp == NULL) + return 0; + css = &cgrp->self; + + bpf_for_each(css_task, task, css, CSS_TASK_ITER_PROCS) { + + } + bpf_cgroup_release(cgrp); + return 0; +}