Minki/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2024-11-10 22:21:40 +00:00
Code Issues Packages Projects Releases Wiki Activity
8f161ca110
linux/kernel/bpf/task_iter.c

850 lines
20 KiB
C
Raw Normal View History

bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
// SPDX-License-Identifier: GPL-2.0-only
/* Copyright (c) 2020 Facebook */
#include <linux/init.h>
#include <linux/namei.h>
#include <linux/pid_namespace.h>
#include <linux/fs.h>
#include <linux/fdtable.h>
#include <linux/filter.h>
bpf: net: Use precomputed btf_id for bpf iterators One additional field btf_id is added to struct bpf_ctx_arg_aux to store the precomputed btf_ids. The btf_id is computed at build time with BTF_ID_LIST or BTF_ID_LIST_GLOBAL macro definitions. All existing bpf iterators are changed to used pre-compute btf_ids. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200720163403.1393551-1-yhs@fb.com
2020-07-20 16:34:03 +00:00
#include <linux/btf_ids.h>
bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Tested-by: Hengqi Chen <hengqi.chen@gmail.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com
2021-11-05 23:23:29 +00:00
#include "mmap_unlock_work.h"
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
bpf: Handle show_fdinfo for the parameterized task BPF iterators Show information of iterators in the respective files under /proc/<pid>/fdinfo/. For example, for a task file iterator with 1723 as the value of tid parameter, its fdinfo would look like the following lines. pos: 0 flags: 02000000 mnt_id: 14 ino: 38 link_type: iter link_id: 51 prog_tag: a590ac96db22b825 prog_id: 299 target_name: task_file task_type: TID tid: 1723 This patch add the last three fields. task_type is the type of the task parameter. TID means the iterator visit only the thread specified by tid. The value of tid in the above example is 1723. For the case of PID task_type, it means the iterator visits only threads of a process and will show the pid value of the process instead of a tid. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-4-kuifeng@fb.com
2022-09-26 18:49:55 +00:00
static const char * const iter_task_type_names[] = {
"ALL",
"TID",
"PID",
};
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
struct bpf_iter_seq_task_common {
struct pid_namespace *ns;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
enum bpf_iter_task_type type;
u32 pid;
u32 pid_visiting;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
};
struct bpf_iter_seq_task_info {
/* The first field must be struct bpf_iter_seq_task_common.
* this is assumed by {init, fini}_seq_pidns() callback functions.
*/
struct bpf_iter_seq_task_common common;
u32 tid;
};
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
static struct task_struct *task_group_seq_get_next(struct bpf_iter_seq_task_common *common,
u32 *tid,
bool skip_if_dup_files)
{
struct task_struct *task, *next_task;
struct pid *pid;
u32 saved_tid;
if (!*tid) {
/* The first time, the iterator calls this function. */
pid = find_pid_ns(common->pid, common->ns);
if (!pid)
return NULL;
task = get_pid_task(pid, PIDTYPE_TGID);
if (!task)
return NULL;
*tid = common->pid;
common->pid_visiting = common->pid;
return task;
}
/* If the control returns to user space and comes back to the
* kernel again, *tid and common->pid_visiting should be the
* same for task_seq_start() to pick up the correct task.
*/
if (*tid == common->pid_visiting) {
pid = find_pid_ns(common->pid_visiting, common->ns);
task = get_pid_task(pid, PIDTYPE_PID);
return task;
}
pid = find_pid_ns(common->pid_visiting, common->ns);
if (!pid)
return NULL;
task = get_pid_task(pid, PIDTYPE_PID);
if (!task)
return NULL;
retry:
if (!pid_alive(task)) {
put_task_struct(task);
return NULL;
}
next_task = next_thread(task);
put_task_struct(task);
if (!next_task)
return NULL;
saved_tid = *tid;
*tid = __task_pid_nr_ns(next_task, PIDTYPE_PID, common->ns);
if (!*tid || *tid == common->pid) {
/* Run out of tasks of a process. The tasks of a
* thread_group are linked as circular linked list.
*/
*tid = saved_tid;
return NULL;
}
get_task_struct(next_task);
common->pid_visiting = *tid;
if (skip_if_dup_files && task->files == task->group_leader->files) {
task = next_task;
goto retry;
}
return next_task;
}
static struct task_struct *task_seq_get_next(struct bpf_iter_seq_task_common *common,
bpf: Avoid iterating duplicated files for task_file iterator Currently, task_file iterator iterates all files from all tasks. This may potentially visit a lot of duplicated files if there are many tasks sharing the same files, e.g., typical pthreads where these pthreads and the main thread are sharing the same files. This patch changed task_file iterator to skip a particular task if that task shares the same files as its group_leader (the task having the same tgid and also task->tgid == task->pid). This will preserve the same result, visiting all files from all tasks, and will reduce runtime cost significantl, e.g., if there are a lot of pthreads and the process has a lot of open files. Suggested-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Link: https://lore.kernel.org/bpf/20200902023112.1672792-1-yhs@fb.com
2020-09-02 02:31:12 +00:00
u32 *tid,
bool skip_if_dup_files)
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
{
struct task_struct *task = NULL;
struct pid *pid;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
if (common->type == BPF_TASK_ITER_TID) {
if (*tid && *tid != common->pid)
return NULL;
rcu_read_lock();
pid = find_pid_ns(common->pid, common->ns);
if (pid) {
task = get_pid_task(pid, PIDTYPE_TGID);
*tid = common->pid;
}
rcu_read_unlock();
return task;
}
if (common->type == BPF_TASK_ITER_TGID) {
rcu_read_lock();
task = task_group_seq_get_next(common, tid, skip_if_dup_files);
rcu_read_unlock();
return task;
}
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
rcu_read_lock();
bpf: Fix bpf_iter's task iterator logic task_seq_get_next might stop prematurely if get_pid_task() fails to get task_struct. Failure to do so doesn't mean that there are no more tasks with higher pids. Procfs's iteration algorithm (see next_tgid in fs/proc/base.c) does a retry in such case. After this fix, instead of stopping prematurely after about 300 tasks on my server, bpf_iter program now returns >4000, which sounds much closer to reality. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200514055137.1564581-1-andriin@fb.com
2020-05-14 05:51:37 +00:00
retry:
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
pid = find_ge_pid(*tid, common->ns);
bpf: Fix bpf_iter's task iterator logic task_seq_get_next might stop prematurely if get_pid_task() fails to get task_struct. Failure to do so doesn't mean that there are no more tasks with higher pids. Procfs's iteration algorithm (see next_tgid in fs/proc/base.c) does a retry in such case. After this fix, instead of stopping prematurely after about 300 tasks on my server, bpf_iter program now returns >4000, which sounds much closer to reality. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200514055137.1564581-1-andriin@fb.com
2020-05-14 05:51:37 +00:00
if (pid) {
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
*tid = pid_nr_ns(pid, common->ns);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
task = get_pid_task(pid, PIDTYPE_PID);
bpf: Fix bpf_iter's task iterator logic task_seq_get_next might stop prematurely if get_pid_task() fails to get task_struct. Failure to do so doesn't mean that there are no more tasks with higher pids. Procfs's iteration algorithm (see next_tgid in fs/proc/base.c) does a retry in such case. After this fix, instead of stopping prematurely after about 300 tasks on my server, bpf_iter program now returns >4000, which sounds much closer to reality. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200514055137.1564581-1-andriin@fb.com
2020-05-14 05:51:37 +00:00
if (!task) {
++*tid;
goto retry;
bpf: Use thread_group_leader() Instead of directly comparing task->tgid and task->pid, use the thread_group_leader() helper. This helps with readability, and there should be no functional change. Signed-off-by: Jonathan Lemon <jonathan.lemon@gmail.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20201218185032.2464558-3-jonathan.lemon@gmail.com
2020-12-18 18:50:31 +00:00
} else if (skip_if_dup_files && !thread_group_leader(task) &&
bpf: Avoid iterating duplicated files for task_file iterator Currently, task_file iterator iterates all files from all tasks. This may potentially visit a lot of duplicated files if there are many tasks sharing the same files, e.g., typical pthreads where these pthreads and the main thread are sharing the same files. This patch changed task_file iterator to skip a particular task if that task shares the same files as its group_leader (the task having the same tgid and also task->tgid == task->pid). This will preserve the same result, visiting all files from all tasks, and will reduce runtime cost significantl, e.g., if there are a lot of pthreads and the process has a lot of open files. Suggested-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Link: https://lore.kernel.org/bpf/20200902023112.1672792-1-yhs@fb.com
2020-09-02 02:31:12 +00:00
task->files == task->group_leader->files) {
put_task_struct(task);
task = NULL;
++*tid;
goto retry;
bpf: Fix bpf_iter's task iterator logic task_seq_get_next might stop prematurely if get_pid_task() fails to get task_struct. Failure to do so doesn't mean that there are no more tasks with higher pids. Procfs's iteration algorithm (see next_tgid in fs/proc/base.c) does a retry in such case. After this fix, instead of stopping prematurely after about 300 tasks on my server, bpf_iter program now returns >4000, which sounds much closer to reality. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20200514055137.1564581-1-andriin@fb.com
2020-05-14 05:51:37 +00:00
}
}
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
rcu_read_unlock();
return task;
}
static void *task_seq_start(struct seq_file *seq, loff_t *pos)
{
struct bpf_iter_seq_task_info *info = seq->private;
struct task_struct *task;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
task = task_seq_get_next(&info->common, &info->tid, false);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
if (!task)
return NULL;
bpf: Fix pos computation for bpf_iter seq_ops->start() Currently, the pos pointer in bpf iterator map/task/task_file seq_ops->start() is always incremented. This is incorrect. It should be increased only if *pos is 0 (for SEQ_START_TOKEN) since these start() function actually returns the first real object. If *pos is not 0, it merely found the object based on the state in seq->private, and not really advancing the *pos. This patch fixed this issue by only incrementing *pos if it is 0. Note that the old *pos calculation, although not correct, does not affect correctness of bpf_iter as bpf_iter seq_file->read() does not support llseek. This patch also renamed "mid" in bpf_map iterator seq_file private data to "map_id" for better clarity. Fixes: 6086d29def80 ("bpf: Add bpf_map iterator") Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200722195156.4029817-1-yhs@fb.com
2020-07-22 19:51:56 +00:00
if (*pos == 0)
++*pos;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
return task;
}
static void *task_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct bpf_iter_seq_task_info *info = seq->private;
struct task_struct *task;
++*pos;
++info->tid;
put_task_struct((struct task_struct *)v);
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
task = task_seq_get_next(&info->common, &info->tid, false);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
if (!task)
return NULL;
return task;
}
struct bpf_iter__task {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct task_struct *, task);
};
DEFINE_BPF_ITER_FUNC(task, struct bpf_iter_meta *meta, struct task_struct *task)
static int __task_seq_show(struct seq_file *seq, struct task_struct *task,
bool in_stop)
{
struct bpf_iter_meta meta;
struct bpf_iter__task ctx;
struct bpf_prog *prog;
meta.seq = seq;
prog = bpf_iter_get_info(&meta, in_stop);
if (!prog)
return 0;
ctx.meta = &meta;
ctx.task = task;
return bpf_iter_run_prog(prog, &ctx);
}
static int task_seq_show(struct seq_file *seq, void *v)
{
return __task_seq_show(seq, v, false);
}
static void task_seq_stop(struct seq_file *seq, void *v)
{
if (!v)
(void)__task_seq_show(seq, v, true);
else
put_task_struct((struct task_struct *)v);
}
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
static int bpf_iter_attach_task(struct bpf_prog *prog,
union bpf_iter_link_info *linfo,
struct bpf_iter_aux_info *aux)
{
unsigned int flags;
struct pid *pid;
pid_t tgid;
if ((!!linfo->task.tid + !!linfo->task.pid + !!linfo->task.pid_fd) > 1)
return -EINVAL;
aux->task.type = BPF_TASK_ITER_ALL;
if (linfo->task.tid != 0) {
aux->task.type = BPF_TASK_ITER_TID;
aux->task.pid = linfo->task.tid;
}
if (linfo->task.pid != 0) {
aux->task.type = BPF_TASK_ITER_TGID;
aux->task.pid = linfo->task.pid;
}
if (linfo->task.pid_fd != 0) {
aux->task.type = BPF_TASK_ITER_TGID;
pid = pidfd_get_pid(linfo->task.pid_fd, &flags);
if (IS_ERR(pid))
return PTR_ERR(pid);
tgid = pid_nr_ns(pid, task_active_pid_ns(current));
aux->task.pid = tgid;
put_pid(pid);
}
return 0;
}
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
static const struct seq_operations task_seq_ops = {
.start = task_seq_start,
.next = task_seq_next,
.stop = task_seq_stop,
.show = task_seq_show,
};
struct bpf_iter_seq_task_file_info {
/* The first field must be struct bpf_iter_seq_task_common.
* this is assumed by {init, fini}_seq_pidns() callback functions.
*/
struct bpf_iter_seq_task_common common;
struct task_struct *task;
u32 tid;
u32 fd;
};
static struct file *
bpf: Simplify task_file_seq_get_next() Simplify task_file_seq_get_next() by removing two in/out arguments: task and fstruct. Use info->task and info->files instead. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20201120002833.2481110-1-songliubraving@fb.com
2020-11-20 00:28:33 +00:00
task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info)
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
{
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
u32 saved_tid = info->tid;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
struct task_struct *curr_task;
bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu When discussing[1] exec and posix file locks it was realized that none of the callers of get_files_struct fundamentally needed to call get_files_struct, and that by switching them to helper functions instead it will both simplify their code and remove unnecessary increments of files_struct.count. Those unnecessary increments can result in exec unnecessarily unsharing files_struct which breaking posix locks, and it can result in fget_light having to fallback to fget reducing system performance. Using task_lookup_next_fd_rcu simplifies task_file_seq_get_next, by moving the checking for the maximum file descritor into the generic code, and by remvoing the need for capturing and releasing a reference on files_struct. As the reference count of files_struct no longer needs to be maintained bpf_iter_seq_task_file_info can have it's files member removed and task_file_seq_get_next no longer needs it's fstruct argument. The curr_fd local variable does need to become unsigned to be used with fnext_task. As curr_fd is assigned from and assigned a u32 making curr_fd an unsigned int won't cause problems and might prevent them. [1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com Suggested-by: Oleg Nesterov <oleg@redhat.com> v1: https://lkml.kernel.org/r/20200817220425.9389-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20201120231441.29911-16-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-11-20 23:14:33 +00:00
unsigned int curr_fd = info->fd;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
/* If this function returns a non-NULL file object,
bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu When discussing[1] exec and posix file locks it was realized that none of the callers of get_files_struct fundamentally needed to call get_files_struct, and that by switching them to helper functions instead it will both simplify their code and remove unnecessary increments of files_struct.count. Those unnecessary increments can result in exec unnecessarily unsharing files_struct which breaking posix locks, and it can result in fget_light having to fallback to fget reducing system performance. Using task_lookup_next_fd_rcu simplifies task_file_seq_get_next, by moving the checking for the maximum file descritor into the generic code, and by remvoing the need for capturing and releasing a reference on files_struct. As the reference count of files_struct no longer needs to be maintained bpf_iter_seq_task_file_info can have it's files member removed and task_file_seq_get_next no longer needs it's fstruct argument. The curr_fd local variable does need to become unsigned to be used with fnext_task. As curr_fd is assigned from and assigned a u32 making curr_fd an unsigned int won't cause problems and might prevent them. [1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com Suggested-by: Oleg Nesterov <oleg@redhat.com> v1: https://lkml.kernel.org/r/20200817220425.9389-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20201120231441.29911-16-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-11-20 23:14:33 +00:00
* it held a reference to the task/file.
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
* Otherwise, it does not hold any reference.
*/
again:
bpf: Simplify task_file_seq_get_next() Simplify task_file_seq_get_next() by removing two in/out arguments: task and fstruct. Use info->task and info->files instead. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20201120002833.2481110-1-songliubraving@fb.com
2020-11-20 00:28:33 +00:00
if (info->task) {
curr_task = info->task;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
curr_fd = info->fd;
} else {
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
curr_task = task_seq_get_next(&info->common, &info->tid, true);
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf Daniel Borkmann says: ==================== pull-request: bpf 2020-12-28 The following pull-request contains BPF updates for your *net* tree. There is a small merge conflict between bpf tree commit 69ca310f3416 ("bpf: Save correct stopping point in file seq iteration") and net tree commit 66ed594409a1 ("bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu"). The get_files_struct() does not exist anymore in net, so take the hunk in HEAD and add the `info->tid = curr_tid` to the error path: [...] curr_task = task_seq_get_next(ns, &curr_tid, true); if (!curr_task) { info->task = NULL; info->tid = curr_tid; return NULL; } /* set info->task and info->tid */ [...] We've added 10 non-merge commits during the last 9 day(s) which contain a total of 11 files changed, 75 insertions(+), 20 deletions(-). The main changes are: 1) Various AF_XDP fixes such as fill/completion ring leak on failed bind and fixing a race in skb mode's backpressure mechanism, from Magnus Karlsson. 2) Fix latency spikes on lockdep enabled kernels by adding a rescheduling point to BPF hashtab initialization, from Eric Dumazet. 3) Fix a splat in task iterator by saving the correct stopping point in the seq file iteration, from Jonathan Lemon. 4) Fix BPF maps selftest by adding retries in case hashtab returns EBUSY errors on update/deletes, from Andrii Nakryiko. 5) Fix BPF selftest error reporting to something more user friendly if the vmlinux BTF cannot be found, from Kamal Mostafa. ==================== Signed-off-by: David S. Miller <davem@davemloft.net>
2020-12-28 23:20:48 +00:00
if (!curr_task) {
info->task = NULL;
return NULL;
}
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
/* set info->task */
bpf: Fix a task_iter bug caused by a merge conflict resolution Latest bpf tree has a bug for bpf_iter selftest: $ ./test_progs -n 4/25 test_bpf_sk_storage_get:PASS:bpf_iter_bpf_sk_storage_helpers__open_and_load 0 nsec test_bpf_sk_storage_get:PASS:socket 0 nsec ... do_dummy_read:PASS:read 0 nsec test_bpf_sk_storage_get:FAIL:bpf_map_lookup_elem map value wasn't set correctly (expected 1792, got -1, err=0) #4/25 bpf_sk_storage_get:FAIL #4 bpf_iter:FAIL Summary: 0/0 PASSED, 0 SKIPPED, 2 FAILED When doing merge conflict resolution, Commit 4bfc4714849d missed to save curr_task to seq_file private data. The task pointer in seq_file private data is passed to bpf program. This caused NULL-pointer task passed to bpf program which will immediately return upon checking whether task pointer is NULL. This patch added back the assignment of curr_task to seq_file private data and fixed the issue. Fixes: 4bfc4714849d ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf") Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: John Fastabend <john.fastabend@gmail.com> Link: https://lore.kernel.org/bpf/20201231052418.577024-1-yhs@fb.com
2020-12-31 05:24:18 +00:00
info->task = curr_task;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
if (saved_tid == info->tid)
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
curr_fd = info->fd;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
else
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
curr_fd = 0;
}
rcu_read_lock();
bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu When discussing[1] exec and posix file locks it was realized that none of the callers of get_files_struct fundamentally needed to call get_files_struct, and that by switching them to helper functions instead it will both simplify their code and remove unnecessary increments of files_struct.count. Those unnecessary increments can result in exec unnecessarily unsharing files_struct which breaking posix locks, and it can result in fget_light having to fallback to fget reducing system performance. Using task_lookup_next_fd_rcu simplifies task_file_seq_get_next, by moving the checking for the maximum file descritor into the generic code, and by remvoing the need for capturing and releasing a reference on files_struct. As the reference count of files_struct no longer needs to be maintained bpf_iter_seq_task_file_info can have it's files member removed and task_file_seq_get_next no longer needs it's fstruct argument. The curr_fd local variable does need to become unsigned to be used with fnext_task. As curr_fd is assigned from and assigned a u32 making curr_fd an unsigned int won't cause problems and might prevent them. [1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com Suggested-by: Oleg Nesterov <oleg@redhat.com> v1: https://lkml.kernel.org/r/20200817220425.9389-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20201120231441.29911-16-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-11-20 23:14:33 +00:00
for (;; curr_fd++) {
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
struct file *f;
bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu When discussing[1] exec and posix file locks it was realized that none of the callers of get_files_struct fundamentally needed to call get_files_struct, and that by switching them to helper functions instead it will both simplify their code and remove unnecessary increments of files_struct.count. Those unnecessary increments can result in exec unnecessarily unsharing files_struct which breaking posix locks, and it can result in fget_light having to fallback to fget reducing system performance. Using task_lookup_next_fd_rcu simplifies task_file_seq_get_next, by moving the checking for the maximum file descritor into the generic code, and by remvoing the need for capturing and releasing a reference on files_struct. As the reference count of files_struct no longer needs to be maintained bpf_iter_seq_task_file_info can have it's files member removed and task_file_seq_get_next no longer needs it's fstruct argument. The curr_fd local variable does need to become unsigned to be used with fnext_task. As curr_fd is assigned from and assigned a u32 making curr_fd an unsigned int won't cause problems and might prevent them. [1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com Suggested-by: Oleg Nesterov <oleg@redhat.com> v1: https://lkml.kernel.org/r/20200817220425.9389-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20201120231441.29911-16-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-11-20 23:14:33 +00:00
f = task_lookup_next_fd_rcu(curr_task, &curr_fd);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
if (!f)
bpf/task_iter: In task_file_seq_get_next use task_lookup_next_fd_rcu When discussing[1] exec and posix file locks it was realized that none of the callers of get_files_struct fundamentally needed to call get_files_struct, and that by switching them to helper functions instead it will both simplify their code and remove unnecessary increments of files_struct.count. Those unnecessary increments can result in exec unnecessarily unsharing files_struct which breaking posix locks, and it can result in fget_light having to fallback to fget reducing system performance. Using task_lookup_next_fd_rcu simplifies task_file_seq_get_next, by moving the checking for the maximum file descritor into the generic code, and by remvoing the need for capturing and releasing a reference on files_struct. As the reference count of files_struct no longer needs to be maintained bpf_iter_seq_task_file_info can have it's files member removed and task_file_seq_get_next no longer needs it's fstruct argument. The curr_fd local variable does need to become unsigned to be used with fnext_task. As curr_fd is assigned from and assigned a u32 making curr_fd an unsigned int won't cause problems and might prevent them. [1] https://lkml.kernel.org/r/20180915160423.GA31461@redhat.com Suggested-by: Oleg Nesterov <oleg@redhat.com> v1: https://lkml.kernel.org/r/20200817220425.9389-11-ebiederm@xmission.com Link: https://lkml.kernel.org/r/20201120231441.29911-16-ebiederm@xmission.com Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
2020-11-20 23:14:33 +00:00
break;
bpf: Use get_file_rcu() instead of get_file() for task_file iterator With latest `bpftool prog` command, we observed the following kernel panic. BUG: kernel NULL pointer dereference, address: 0000000000000000 #PF: supervisor instruction fetch in kernel mode #PF: error_code(0x0010) - not-present page PGD dfe894067 P4D dfe894067 PUD deb663067 PMD 0 Oops: 0010 [#1] SMP CPU: 9 PID: 6023 ... RIP: 0010:0x0 Code: Bad RIP value. RSP: 0000:ffffc900002b8f18 EFLAGS: 00010286 RAX: ffff8883a405f400 RBX: ffff888e46a6bf00 RCX: 000000008020000c RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8883a405f400 RBP: ffff888e46a6bf50 R08: 0000000000000000 R09: ffffffff81129600 R10: ffff8883a405f300 R11: 0000160000000000 R12: 0000000000002710 R13: 000000e9494b690c R14: 0000000000000202 R15: 0000000000000009 FS: 00007fd9187fe700(0000) GS:ffff888e46a40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffffffffffffd6 CR3: 0000000de5d33002 CR4: 0000000000360ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <IRQ> rcu_core+0x1a4/0x440 __do_softirq+0xd3/0x2c8 irq_exit+0x9d/0xa0 smp_apic_timer_interrupt+0x68/0x120 apic_timer_interrupt+0xf/0x20 </IRQ> RIP: 0033:0x47ce80 Code: Bad RIP value. RSP: 002b:00007fd9187fba40 EFLAGS: 00000206 ORIG_RAX: ffffffffffffff13 RAX: 0000000000000002 RBX: 00007fd931789160 RCX: 000000000000010c RDX: 00007fd9308cdfb4 RSI: 00007fd9308cdfb4 RDI: 00007ffedd1ea0a8 RBP: 00007fd9187fbab0 R08: 000000000000000e R09: 000000000000002a R10: 0000000000480210 R11: 00007fd9187fc570 R12: 00007fd9316cc400 R13: 0000000000000118 R14: 00007fd9308cdfb4 R15: 00007fd9317a9380 After further analysis, the bug is triggered by Commit eaaacd23910f ("bpf: Add task and task/file iterator targets") which introduced task_file bpf iterator, which traverses all open file descriptors for all tasks in the current namespace. The latest `bpftool prog` calls a task_file bpf program to traverse all files in the system in order to associate processes with progs/maps, etc. When traversing files for a given task, rcu read_lock is taken to access all files in a file_struct. But it used get_file() to grab a file, which is not right. It is possible file->f_count is 0 and get_file() will unconditionally increase it. Later put_file() may cause all kind of issues with the above as one of sympotoms. The failure can be reproduced with the following steps in a few seconds: $ cat t.c #include <stdio.h> #include <sys/types.h> #include <sys/stat.h> #include <fcntl.h> #include <unistd.h> #define N 10000 int fd[N]; int main() { int i; for (i = 0; i < N; i++) { fd[i] = open("./note.txt", 'r'); if (fd[i] < 0) { fprintf(stderr, "failed\n"); return -1; } } for (i = 0; i < N; i++) close(fd[i]); return 0; } $ gcc -O2 t.c $ cat run.sh #/bin/bash for i in {1..100} do while true; do ./a.out; done & done $ ./run.sh $ while true; do bpftool prog >& /dev/null; done This patch used get_file_rcu() which only grabs a file if the file->f_count is not zero. This is to ensure the file pointer is always valid. The above reproducer did not fail for more than 30 minutes. Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Suggested-by: Josef Bacik <josef@toxicpanda.com> Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Reviewed-by: Josef Bacik <josef@toxicpanda.com> Link: https://lore.kernel.org/bpf/20200817174214.252601-1-yhs@fb.com
2020-08-17 17:42:14 +00:00
if (!get_file_rcu(f))
continue;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
/* set info->fd */
info->fd = curr_fd;
rcu_read_unlock();
return f;
}
/* the current task is done, go to the next task */
rcu_read_unlock();
put_task_struct(curr_task);
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
if (info->common.type == BPF_TASK_ITER_TID) {
info->task = NULL;
return NULL;
}
bpf: Simplify task_file_seq_get_next() Simplify task_file_seq_get_next() by removing two in/out arguments: task and fstruct. Use info->task and info->files instead. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20201120002833.2481110-1-songliubraving@fb.com
2020-11-20 00:28:33 +00:00
info->task = NULL;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
info->fd = 0;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
saved_tid = ++(info->tid);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
goto again;
}
static void *task_file_seq_start(struct seq_file *seq, loff_t *pos)
{
struct bpf_iter_seq_task_file_info *info = seq->private;
struct file *file;
bpf: Simplify task_file_seq_get_next() Simplify task_file_seq_get_next() by removing two in/out arguments: task and fstruct. Use info->task and info->files instead. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20201120002833.2481110-1-songliubraving@fb.com
2020-11-20 00:28:33 +00:00
info->task = NULL;
file = task_file_seq_get_next(info);
if (file && *pos == 0)
bpf: Fix pos computation for bpf_iter seq_ops->start() Currently, the pos pointer in bpf iterator map/task/task_file seq_ops->start() is always incremented. This is incorrect. It should be increased only if *pos is 0 (for SEQ_START_TOKEN) since these start() function actually returns the first real object. If *pos is not 0, it merely found the object based on the state in seq->private, and not really advancing the *pos. This patch fixed this issue by only incrementing *pos if it is 0. Note that the old *pos calculation, although not correct, does not affect correctness of bpf_iter as bpf_iter seq_file->read() does not support llseek. This patch also renamed "mid" in bpf_map iterator seq_file private data to "map_id" for better clarity. Fixes: 6086d29def80 ("bpf: Add bpf_map iterator") Fixes: eaaacd23910f ("bpf: Add task and task/file iterator targets") Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200722195156.4029817-1-yhs@fb.com
2020-07-22 19:51:56 +00:00
++*pos;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
return file;
}
static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct bpf_iter_seq_task_file_info *info = seq->private;
++*pos;
++info->fd;
fput((struct file *)v);
bpf: Simplify task_file_seq_get_next() Simplify task_file_seq_get_next() by removing two in/out arguments: task and fstruct. Use info->task and info->files instead. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20201120002833.2481110-1-songliubraving@fb.com
2020-11-20 00:28:33 +00:00
return task_file_seq_get_next(info);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
}
struct bpf_iter__task_file {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct task_struct *, task);
u32 fd __aligned(8);
__bpf_md_ptr(struct file *, file);
};
DEFINE_BPF_ITER_FUNC(task_file, struct bpf_iter_meta *meta,
struct task_struct *task, u32 fd,
struct file *file)
static int __task_file_seq_show(struct seq_file *seq, struct file *file,
bool in_stop)
{
struct bpf_iter_seq_task_file_info *info = seq->private;
struct bpf_iter__task_file ctx;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
meta.seq = seq;
prog = bpf_iter_get_info(&meta, in_stop);
if (!prog)
return 0;
ctx.meta = &meta;
ctx.task = info->task;
ctx.fd = info->fd;
ctx.file = file;
return bpf_iter_run_prog(prog, &ctx);
}
static int task_file_seq_show(struct seq_file *seq, void *v)
{
return __task_file_seq_show(seq, v, false);
}
static void task_file_seq_stop(struct seq_file *seq, void *v)
{
struct bpf_iter_seq_task_file_info *info = seq->private;
if (!v) {
(void)__task_file_seq_show(seq, v, true);
} else {
fput((struct file *)v);
put_task_struct(info->task);
info->task = NULL;
}
}
bpf: Refactor to provide aux info to bpf_iter_init_seq_priv_t This patch refactored target bpf_iter_init_seq_priv_t callback function to accept additional information. This will be needed in later patches for map element targets since a particular map should be passed to traverse elements for that particular map. In the future, other information may be passed to target as well, e.g., pid, cgroup id, etc. to customize the iterator. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184110.590156-1-yhs@fb.com
2020-07-23 18:41:10 +00:00
static int init_seq_pidns(void *priv_data, struct bpf_iter_aux_info *aux)
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
{
struct bpf_iter_seq_task_common *common = priv_data;
common->ns = get_pid_ns(task_active_pid_ns(current));
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
common->type = aux->task.type;
common->pid = aux->task.pid;
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
return 0;
}
static void fini_seq_pidns(void *priv_data)
{
struct bpf_iter_seq_task_common *common = priv_data;
put_pid_ns(common->ns);
}
static const struct seq_operations task_file_seq_ops = {
.start = task_file_seq_start,
.next = task_file_seq_next,
.stop = task_file_seq_stop,
.show = task_file_seq_show,
};
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
struct bpf_iter_seq_task_vma_info {
/* The first field must be struct bpf_iter_seq_task_common.
* this is assumed by {init, fini}_seq_pidns() callback functions.
*/
struct bpf_iter_seq_task_common common;
struct task_struct *task;
struct vm_area_struct *vma;
u32 tid;
unsigned long prev_vm_start;
unsigned long prev_vm_end;
};
enum bpf_task_vma_iter_find_op {
bpf: remove VMA linked list Use vma_next() and remove reference to the start of the linked list Link: https://lkml.kernel.org/r/20220906194824.2110408-51-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: SeongJae Park <sj@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-06 19:48:59 +00:00
task_vma_iter_first_vma, /* use find_vma() with addr 0 */
task_vma_iter_next_vma, /* use vma_next() with curr_vma */
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
task_vma_iter_find_vma, /* use find_vma() to find next vma */
};
static struct vm_area_struct *
task_vma_seq_get_next(struct bpf_iter_seq_task_vma_info *info)
{
enum bpf_task_vma_iter_find_op op;
struct vm_area_struct *curr_vma;
struct task_struct *curr_task;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
u32 saved_tid = info->tid;
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
/* If this function returns a non-NULL vma, it holds a reference to
* the task_struct, and holds read lock on vma->mm->mmap_lock.
* If this function returns NULL, it does not hold any reference or
* lock.
*/
if (info->task) {
curr_task = info->task;
curr_vma = info->vma;
/* In case of lock contention, drop mmap_lock to unblock
* the writer.
*
* After relock, call find(mm, prev_vm_end - 1) to find
* new vma to process.
*
* +------+------+-----------+
* | VMA1 | VMA2 | VMA3 |
* +------+------+-----------+
* | | | |
* 4k 8k 16k 400k
*
* For example, curr_vma == VMA2. Before unlock, we set
*
* prev_vm_start = 8k
* prev_vm_end = 16k
*
* There are a few cases:
*
* 1) VMA2 is freed, but VMA3 exists.
*
* find_vma() will return VMA3, just process VMA3.
*
* 2) VMA2 still exists.
*
* find_vma() will return VMA2, process VMA2->next.
*
* 3) no more vma in this mm.
*
* Process the next task.
*
* 4) find_vma() returns a different vma, VMA2'.
*
* 4.1) If VMA2 covers same range as VMA2', skip VMA2',
* because we already covered the range;
* 4.2) VMA2 and VMA2' covers different ranges, process
* VMA2'.
*/
if (mmap_lock_is_contended(curr_task->mm)) {
info->prev_vm_start = curr_vma->vm_start;
info->prev_vm_end = curr_vma->vm_end;
op = task_vma_iter_find_vma;
mmap_read_unlock(curr_task->mm);
if (mmap_read_lock_killable(curr_task->mm))
goto finish;
} else {
op = task_vma_iter_next_vma;
}
} else {
again:
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
curr_task = task_seq_get_next(&info->common, &info->tid, true);
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
if (!curr_task) {
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
info->tid++;
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
goto finish;
}
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
if (saved_tid != info->tid) {
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
/* new task, process the first vma */
op = task_vma_iter_first_vma;
} else {
/* Found the same tid, which means the user space
* finished data in previous buffer and read more.
* We dropped mmap_lock before returning to user
* space, so it is necessary to use find_vma() to
* find the next vma to process.
*/
op = task_vma_iter_find_vma;
}
if (!curr_task->mm)
goto next_task;
if (mmap_read_lock_killable(curr_task->mm))
goto finish;
}
switch (op) {
case task_vma_iter_first_vma:
bpf: remove VMA linked list Use vma_next() and remove reference to the start of the linked list Link: https://lkml.kernel.org/r/20220906194824.2110408-51-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: SeongJae Park <sj@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-06 19:48:59 +00:00
curr_vma = find_vma(curr_task->mm, 0);
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
break;
case task_vma_iter_next_vma:
bpf: remove VMA linked list Use vma_next() and remove reference to the start of the linked list Link: https://lkml.kernel.org/r/20220906194824.2110408-51-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: SeongJae Park <sj@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-06 19:48:59 +00:00
curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
break;
case task_vma_iter_find_vma:
/* We dropped mmap_lock so it is necessary to use find_vma
* to find the next vma. This is similar to the mechanism
* in show_smaps_rollup().
*/
curr_vma = find_vma(curr_task->mm, info->prev_vm_end - 1);
/* case 1) and 4.2) above just use curr_vma */
/* check for case 2) or case 4.1) above */
if (curr_vma &&
curr_vma->vm_start == info->prev_vm_start &&
curr_vma->vm_end == info->prev_vm_end)
bpf: remove VMA linked list Use vma_next() and remove reference to the start of the linked list Link: https://lkml.kernel.org/r/20220906194824.2110408-51-Liam.Howlett@oracle.com Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com> Tested-by: Yu Zhao <yuzhao@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Hildenbrand <david@redhat.com> Cc: David Howells <dhowells@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: SeongJae Park <sj@kernel.org> Cc: Sven Schnelle <svens@linux.ibm.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2022-09-06 19:48:59 +00:00
curr_vma = find_vma(curr_task->mm, curr_vma->vm_end);
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
break;
}
if (!curr_vma) {
/* case 3) above, or case 2) 4.1) with vma->next == NULL */
mmap_read_unlock(curr_task->mm);
goto next_task;
}
info->task = curr_task;
info->vma = curr_vma;
return curr_vma;
next_task:
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
if (info->common.type == BPF_TASK_ITER_TID)
goto finish;
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
put_task_struct(curr_task);
info->task = NULL;
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
info->tid++;
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
goto again;
finish:
if (curr_task)
put_task_struct(curr_task);
info->task = NULL;
info->vma = NULL;
return NULL;
}
static void *task_vma_seq_start(struct seq_file *seq, loff_t *pos)
{
struct bpf_iter_seq_task_vma_info *info = seq->private;
struct vm_area_struct *vma;
vma = task_vma_seq_get_next(info);
if (vma && *pos == 0)
++*pos;
return vma;
}
static void *task_vma_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct bpf_iter_seq_task_vma_info *info = seq->private;
++*pos;
return task_vma_seq_get_next(info);
}
struct bpf_iter__task_vma {
__bpf_md_ptr(struct bpf_iter_meta *, meta);
__bpf_md_ptr(struct task_struct *, task);
__bpf_md_ptr(struct vm_area_struct *, vma);
};
DEFINE_BPF_ITER_FUNC(task_vma, struct bpf_iter_meta *meta,
struct task_struct *task, struct vm_area_struct *vma)
static int __task_vma_seq_show(struct seq_file *seq, bool in_stop)
{
struct bpf_iter_seq_task_vma_info *info = seq->private;
struct bpf_iter__task_vma ctx;
struct bpf_iter_meta meta;
struct bpf_prog *prog;
meta.seq = seq;
prog = bpf_iter_get_info(&meta, in_stop);
if (!prog)
return 0;
ctx.meta = &meta;
ctx.task = info->task;
ctx.vma = info->vma;
return bpf_iter_run_prog(prog, &ctx);
}
static int task_vma_seq_show(struct seq_file *seq, void *v)
{
return __task_vma_seq_show(seq, false);
}
static void task_vma_seq_stop(struct seq_file *seq, void *v)
{
struct bpf_iter_seq_task_vma_info *info = seq->private;
if (!v) {
(void)__task_vma_seq_show(seq, true);
} else {
/* info->vma has not been seen by the BPF program. If the
* user space reads more, task_vma_seq_get_next should
* return this vma again. Set prev_vm_start to ~0UL,
* so that we don't skip the vma returned by the next
* find_vma() (case task_vma_iter_find_vma in
* task_vma_seq_get_next()).
*/
info->prev_vm_start = ~0UL;
info->prev_vm_end = info->vma->vm_end;
mmap_read_unlock(info->task->mm);
put_task_struct(info->task);
info->task = NULL;
}
}
static const struct seq_operations task_vma_seq_ops = {
.start = task_vma_seq_start,
.next = task_vma_seq_next,
.stop = task_vma_seq_stop,
.show = task_vma_seq_show,
};
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
static const struct bpf_iter_seq_info task_seq_info = {
bpf: net: Refactor bpf_iter target registration Currently bpf_iter_reg_target takes parameters from target and allocates memory to save them. This is really not necessary, esp. in the future we may grow information passed from targets to bpf_iter manager. The patch refactors the code so target reg_info becomes static and bpf_iter manager can just take a reference to it. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200513180219.2949605-1-yhs@fb.com
2020-05-13 18:02:19 +00:00
.seq_ops = &task_seq_ops,
.init_seq_private = init_seq_pidns,
.fini_seq_private = fini_seq_pidns,
.seq_priv_size = sizeof(struct bpf_iter_seq_task_info),
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
};
bpf: Handle bpf_link_info for the parameterized task BPF iterators. Add new fields to bpf_link_info that users can query it through bpf_obj_get_info_by_fd(). Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-3-kuifeng@fb.com
2022-09-26 18:49:54 +00:00
static int bpf_iter_fill_link_info(const struct bpf_iter_aux_info *aux, struct bpf_link_info *info)
{
switch (aux->task.type) {
case BPF_TASK_ITER_TID:
info->iter.task.tid = aux->task.pid;
break;
case BPF_TASK_ITER_TGID:
info->iter.task.pid = aux->task.pid;
break;
default:
break;
}
return 0;
}
bpf: Handle show_fdinfo for the parameterized task BPF iterators Show information of iterators in the respective files under /proc/<pid>/fdinfo/. For example, for a task file iterator with 1723 as the value of tid parameter, its fdinfo would look like the following lines. pos: 0 flags: 02000000 mnt_id: 14 ino: 38 link_type: iter link_id: 51 prog_tag: a590ac96db22b825 prog_id: 299 target_name: task_file task_type: TID tid: 1723 This patch add the last three fields. task_type is the type of the task parameter. TID means the iterator visit only the thread specified by tid. The value of tid in the above example is 1723. For the case of PID task_type, it means the iterator visits only threads of a process and will show the pid value of the process instead of a tid. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-4-kuifeng@fb.com
2022-09-26 18:49:55 +00:00
static void bpf_iter_task_show_fdinfo(const struct bpf_iter_aux_info *aux, struct seq_file *seq)
{
seq_printf(seq, "task_type:\t%s\n", iter_task_type_names[aux->task.type]);
if (aux->task.type == BPF_TASK_ITER_TID)
seq_printf(seq, "tid:\t%u\n", aux->task.pid);
else if (aux->task.type == BPF_TASK_ITER_TGID)
seq_printf(seq, "pid:\t%u\n", aux->task.pid);
}
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
static struct bpf_iter_reg task_reg_info = {
.target = "task",
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
.attach_target = bpf_iter_attach_task,
bpf: Permit cond_resched for some iterators Commit e679654a704e ("bpf: Fix a rcu_sched stall issue with bpf task/task_file iterator") tries to fix rcu stalls warning which is caused by bpf task_file iterator when running "bpftool prog". rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913 \x09(t=21031 jiffies g=2534773 q=179750) NMI backtrace for cpu 7 CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G W 5.8.0-00004-g68bfc7f8c1b4 #6 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019 Call Trace: <IRQ> dump_stack+0x57/0x70 nmi_cpu_backtrace.cold+0x14/0x53 ? lapic_can_unplug_cpu.cold+0x39/0x39 nmi_trigger_cpumask_backtrace+0xb7/0xc7 rcu_dump_cpu_stacks+0xa2/0xd0 rcu_sched_clock_irq.cold+0x1ff/0x3d9 ? tick_nohz_handler+0x100/0x100 update_process_times+0x5b/0x90 tick_sched_timer+0x5e/0xf0 __hrtimer_run_queues+0x12a/0x2a0 hrtimer_interrupt+0x10e/0x280 __sysvec_apic_timer_interrupt+0x51/0xe0 asm_call_on_stack+0xf/0x20 </IRQ> sysvec_apic_timer_interrupt+0x6f/0x80 ... task_file_seq_next+0x52/0xa0 bpf_seq_read+0xb9/0x320 vfs_read+0x9d/0x180 ksys_read+0x5f/0xe0 do_syscall_64+0x38/0x60 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The fix is to limit the number of bpf program runs to be one million. This fixed the program in most cases. But we also found under heavy load, which can increase the wallclock time for bpf_seq_read(), the warning may still be possible. For example, calling bpf_delay() in the "while" loop of bpf_seq_read(), which will introduce artificial delay, the warning will show up in my qemu run. static unsigned q; volatile unsigned *p = &q; volatile unsigned long long ll; static void bpf_delay(void) { int i, j; for (i = 0; i < 10000; i++) for (j = 0; j < 10000; j++) ll += *p; } There are two ways to fix this issue. One is to reduce the above one million threshold to say 100,000 and hopefully rcu warning will not show up any more. Another is to introduce a target feature which enables bpf_seq_read() calling cond_resched(). This patch took second approach as the first approach may cause more -EAGAIN failures for read() syscalls. Note that not all bpf_iter targets can permit cond_resched() in bpf_seq_read() as some, e.g., netlink seq iterator, rcu read lock critical section spans through seq_ops->next() -> seq_ops->show() -> seq_ops->next(). For the kernel code with the above hack, "bpftool p" roughly takes 38 seconds to finish on my VM with 184 bpf program runs. Using the following command, I am able to collect the number of context switches: perf stat -e context-switches -- ./bpftool p >& log Without this patch, 69 context-switches With this patch, 75 context-switches This patch added additional 6 context switches, roughly every 6 seconds to reschedule, to avoid lengthy no-rescheduling which may cause the above RCU warnings. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20201028061054.1411116-1-yhs@fb.com
2020-10-28 06:10:54 +00:00
.feature = BPF_ITER_RESCHED,
bpf: Enable bpf_iter targets registering ctx argument types Commit b121b341e598 ("bpf: Add PTR_TO_BTF_ID_OR_NULL support") adds a field btf_id_or_null_non0_off to bpf_prog->aux structure to indicate that the first ctx argument is PTR_TO_BTF_ID reg_type and all others are PTR_TO_BTF_ID_OR_NULL. This approach does not really scale if we have other different reg types in the future, e.g., a pointer to a buffer. This patch enables bpf_iter targets registering ctx argument reg types which may be different from the default one. For example, for pointers to structures, the default reg_type is PTR_TO_BTF_ID for tracing program. The target can register a particular pointer type as PTR_TO_BTF_ID_OR_NULL which can be used by the verifier to enforce accesses. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200513180221.2949882-1-yhs@fb.com
2020-05-13 18:02:21 +00:00
.ctx_arg_info_size = 1,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task, task),
PTR_TO_BTF_ID_OR_NULL },
},
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
.seq_info = &task_seq_info,
bpf: Handle bpf_link_info for the parameterized task BPF iterators. Add new fields to bpf_link_info that users can query it through bpf_obj_get_info_by_fd(). Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-3-kuifeng@fb.com
2022-09-26 18:49:54 +00:00
.fill_link_info = bpf_iter_fill_link_info,
bpf: Handle show_fdinfo for the parameterized task BPF iterators Show information of iterators in the respective files under /proc/<pid>/fdinfo/. For example, for a task file iterator with 1723 as the value of tid parameter, its fdinfo would look like the following lines. pos: 0 flags: 02000000 mnt_id: 14 ino: 38 link_type: iter link_id: 51 prog_tag: a590ac96db22b825 prog_id: 299 target_name: task_file task_type: TID tid: 1723 This patch add the last three fields. task_type is the type of the task parameter. TID means the iterator visit only the thread specified by tid. The value of tid in the above example is 1723. For the case of PID task_type, it means the iterator visits only threads of a process and will show the pid value of the process instead of a tid. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-4-kuifeng@fb.com
2022-09-26 18:49:55 +00:00
.show_fdinfo = bpf_iter_task_show_fdinfo,
bpf: net: Refactor bpf_iter target registration Currently bpf_iter_reg_target takes parameters from target and allocates memory to save them. This is really not necessary, esp. in the future we may grow information passed from targets to bpf_iter manager. The patch refactors the code so target reg_info becomes static and bpf_iter manager can just take a reference to it. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200513180219.2949605-1-yhs@fb.com
2020-05-13 18:02:19 +00:00
};
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
static const struct bpf_iter_seq_info task_file_seq_info = {
bpf: net: Refactor bpf_iter target registration Currently bpf_iter_reg_target takes parameters from target and allocates memory to save them. This is really not necessary, esp. in the future we may grow information passed from targets to bpf_iter manager. The patch refactors the code so target reg_info becomes static and bpf_iter manager can just take a reference to it. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200513180219.2949605-1-yhs@fb.com
2020-05-13 18:02:19 +00:00
.seq_ops = &task_file_seq_ops,
.init_seq_private = init_seq_pidns,
.fini_seq_private = fini_seq_pidns,
.seq_priv_size = sizeof(struct bpf_iter_seq_task_file_info),
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
};
static struct bpf_iter_reg task_file_reg_info = {
.target = "task_file",
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
.attach_target = bpf_iter_attach_task,
bpf: Permit cond_resched for some iterators Commit e679654a704e ("bpf: Fix a rcu_sched stall issue with bpf task/task_file iterator") tries to fix rcu stalls warning which is caused by bpf task_file iterator when running "bpftool prog". rcu: INFO: rcu_sched self-detected stall on CPU rcu: \x097-....: (20999 ticks this GP) idle=302/1/0x4000000000000000 softirq=1508852/1508852 fqs=4913 \x09(t=21031 jiffies g=2534773 q=179750) NMI backtrace for cpu 7 CPU: 7 PID: 184195 Comm: bpftool Kdump: loaded Tainted: G W 5.8.0-00004-g68bfc7f8c1b4 #6 Hardware name: Quanta Twin Lakes MP/Twin Lakes Passive MP, BIOS F09_3A17 05/03/2019 Call Trace: <IRQ> dump_stack+0x57/0x70 nmi_cpu_backtrace.cold+0x14/0x53 ? lapic_can_unplug_cpu.cold+0x39/0x39 nmi_trigger_cpumask_backtrace+0xb7/0xc7 rcu_dump_cpu_stacks+0xa2/0xd0 rcu_sched_clock_irq.cold+0x1ff/0x3d9 ? tick_nohz_handler+0x100/0x100 update_process_times+0x5b/0x90 tick_sched_timer+0x5e/0xf0 __hrtimer_run_queues+0x12a/0x2a0 hrtimer_interrupt+0x10e/0x280 __sysvec_apic_timer_interrupt+0x51/0xe0 asm_call_on_stack+0xf/0x20 </IRQ> sysvec_apic_timer_interrupt+0x6f/0x80 ... task_file_seq_next+0x52/0xa0 bpf_seq_read+0xb9/0x320 vfs_read+0x9d/0x180 ksys_read+0x5f/0xe0 do_syscall_64+0x38/0x60 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The fix is to limit the number of bpf program runs to be one million. This fixed the program in most cases. But we also found under heavy load, which can increase the wallclock time for bpf_seq_read(), the warning may still be possible. For example, calling bpf_delay() in the "while" loop of bpf_seq_read(), which will introduce artificial delay, the warning will show up in my qemu run. static unsigned q; volatile unsigned *p = &q; volatile unsigned long long ll; static void bpf_delay(void) { int i, j; for (i = 0; i < 10000; i++) for (j = 0; j < 10000; j++) ll += *p; } There are two ways to fix this issue. One is to reduce the above one million threshold to say 100,000 and hopefully rcu warning will not show up any more. Another is to introduce a target feature which enables bpf_seq_read() calling cond_resched(). This patch took second approach as the first approach may cause more -EAGAIN failures for read() syscalls. Note that not all bpf_iter targets can permit cond_resched() in bpf_seq_read() as some, e.g., netlink seq iterator, rcu read lock critical section spans through seq_ops->next() -> seq_ops->show() -> seq_ops->next(). For the kernel code with the above hack, "bpftool p" roughly takes 38 seconds to finish on my VM with 184 bpf program runs. Using the following command, I am able to collect the number of context switches: perf stat -e context-switches -- ./bpftool p >& log Without this patch, 69 context-switches With this patch, 75 context-switches This patch added additional 6 context switches, roughly every 6 seconds to reschedule, to avoid lengthy no-rescheduling which may cause the above RCU warnings. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/bpf/20201028061054.1411116-1-yhs@fb.com
2020-10-28 06:10:54 +00:00
.feature = BPF_ITER_RESCHED,
bpf: Enable bpf_iter targets registering ctx argument types Commit b121b341e598 ("bpf: Add PTR_TO_BTF_ID_OR_NULL support") adds a field btf_id_or_null_non0_off to bpf_prog->aux structure to indicate that the first ctx argument is PTR_TO_BTF_ID reg_type and all others are PTR_TO_BTF_ID_OR_NULL. This approach does not really scale if we have other different reg types in the future, e.g., a pointer to a buffer. This patch enables bpf_iter targets registering ctx argument reg types which may be different from the default one. For example, for pointers to structures, the default reg_type is PTR_TO_BTF_ID for tracing program. The target can register a particular pointer type as PTR_TO_BTF_ID_OR_NULL which can be used by the verifier to enforce accesses. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200513180221.2949882-1-yhs@fb.com
2020-05-13 18:02:21 +00:00
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task_file, task),
PTR_TO_BTF_ID_OR_NULL },
{ offsetof(struct bpf_iter__task_file, file),
PTR_TO_BTF_ID_OR_NULL },
},
bpf: Refactor bpf_iter_reg to have separate seq_info member There is no functionality change for this patch. Struct bpf_iter_reg is used to register a bpf_iter target, which includes information for both prog_load, link_create and seq_file creation. This patch puts fields related seq_file creation into a different structure. This will be useful for map elements iterator where one iterator covers different map types and different map types may have different seq_ops, init/fini private_data function and private_data size. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200723184109.590030-1-yhs@fb.com
2020-07-23 18:41:09 +00:00
.seq_info = &task_file_seq_info,
bpf: Handle bpf_link_info for the parameterized task BPF iterators. Add new fields to bpf_link_info that users can query it through bpf_obj_get_info_by_fd(). Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-3-kuifeng@fb.com
2022-09-26 18:49:54 +00:00
.fill_link_info = bpf_iter_fill_link_info,
bpf: Handle show_fdinfo for the parameterized task BPF iterators Show information of iterators in the respective files under /proc/<pid>/fdinfo/. For example, for a task file iterator with 1723 as the value of tid parameter, its fdinfo would look like the following lines. pos: 0 flags: 02000000 mnt_id: 14 ino: 38 link_type: iter link_id: 51 prog_tag: a590ac96db22b825 prog_id: 299 target_name: task_file task_type: TID tid: 1723 This patch add the last three fields. task_type is the type of the task parameter. TID means the iterator visit only the thread specified by tid. The value of tid in the above example is 1723. For the case of PID task_type, it means the iterator visits only threads of a process and will show the pid value of the process instead of a tid. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-4-kuifeng@fb.com
2022-09-26 18:49:55 +00:00
.show_fdinfo = bpf_iter_task_show_fdinfo,
bpf: net: Refactor bpf_iter target registration Currently bpf_iter_reg_target takes parameters from target and allocates memory to save them. This is really not necessary, esp. in the future we may grow information passed from targets to bpf_iter manager. The patch refactors the code so target reg_info becomes static and bpf_iter manager can just take a reference to it. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20200513180219.2949605-1-yhs@fb.com
2020-05-13 18:02:19 +00:00
};
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
static const struct bpf_iter_seq_info task_vma_seq_info = {
.seq_ops = &task_vma_seq_ops,
.init_seq_private = init_seq_pidns,
.fini_seq_private = fini_seq_pidns,
.seq_priv_size = sizeof(struct bpf_iter_seq_task_vma_info),
};
static struct bpf_iter_reg task_vma_reg_info = {
.target = "task_vma",
bpf: Parameterize task iterators. Allow creating an iterator that loops through resources of one thread/process. People could only create iterators to loop through all resources of files, vma, and tasks in the system, even though they were interested in only the resources of a specific task or process. Passing the additional parameters, people can now create an iterator to go through all resources or only the resources of a task. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-2-kuifeng@fb.com
2022-09-26 18:49:53 +00:00
.attach_target = bpf_iter_attach_task,
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
.feature = BPF_ITER_RESCHED,
.ctx_arg_info_size = 2,
.ctx_arg_info = {
{ offsetof(struct bpf_iter__task_vma, task),
PTR_TO_BTF_ID_OR_NULL },
{ offsetof(struct bpf_iter__task_vma, vma),
PTR_TO_BTF_ID_OR_NULL },
},
.seq_info = &task_vma_seq_info,
bpf: Handle bpf_link_info for the parameterized task BPF iterators. Add new fields to bpf_link_info that users can query it through bpf_obj_get_info_by_fd(). Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-3-kuifeng@fb.com
2022-09-26 18:49:54 +00:00
.fill_link_info = bpf_iter_fill_link_info,
bpf: Handle show_fdinfo for the parameterized task BPF iterators Show information of iterators in the respective files under /proc/<pid>/fdinfo/. For example, for a task file iterator with 1723 as the value of tid parameter, its fdinfo would look like the following lines. pos: 0 flags: 02000000 mnt_id: 14 ino: 38 link_type: iter link_id: 51 prog_tag: a590ac96db22b825 prog_id: 299 target_name: task_file task_type: TID tid: 1723 This patch add the last three fields. task_type is the type of the task parameter. TID means the iterator visit only the thread specified by tid. The value of tid in the above example is 1723. For the case of PID task_type, it means the iterator visits only threads of a process and will show the pid value of the process instead of a tid. Signed-off-by: Kui-Feng Lee <kuifeng@fb.com> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Acked-by: Martin KaFai Lau <martin.lau@kernel.org> Link: https://lore.kernel.org/bpf/20220926184957.208194-4-kuifeng@fb.com
2022-09-26 18:49:55 +00:00
.show_fdinfo = bpf_iter_task_show_fdinfo,
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
};
bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Tested-by: Hengqi Chen <hengqi.chen@gmail.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com
2021-11-05 23:23:29 +00:00
BPF_CALL_5(bpf_find_vma, struct task_struct *, task, u64, start,
bpf_callback_t, callback_fn, void *, callback_ctx, u64, flags)
{
struct mmap_unlock_irq_work *work = NULL;
struct vm_area_struct *vma;
bool irq_work_busy = false;
struct mm_struct *mm;
int ret = -ENOENT;
if (flags)
return -EINVAL;
if (!task)
return -ENOENT;
mm = task->mm;
if (!mm)
return -ENOENT;
irq_work_busy = bpf_mmap_unlock_get_irq_work(&work);
if (irq_work_busy || !mmap_read_trylock(mm))
return -EBUSY;
vma = find_vma(mm, start);
if (vma && vma->vm_start <= start && vma->vm_end > start) {
callback_fn((u64)(long)task, (u64)(long)vma,
(u64)(long)callback_ctx, 0, 0);
ret = 0;
}
bpf_mmap_unlock_mm(work, mm);
return ret;
}
const struct bpf_func_proto bpf_find_vma_proto = {
.func = bpf_find_vma,
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_BTF_ID,
bpf: Introduce btf_tracing_ids Similar to btf_sock_ids, btf_tracing_ids provides btf ID for task_struct, file, and vm_area_struct via easy to understand format like btf_tracing_ids[BTF_TRACING_TYPE_[TASK|file|VMA]]. Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211112150243.1270987-3-songliubraving@fb.com
2021-11-12 15:02:43 +00:00
.arg1_btf_id = &btf_tracing_ids[BTF_TRACING_TYPE_TASK],
bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Tested-by: Hengqi Chen <hengqi.chen@gmail.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com
2021-11-05 23:23:29 +00:00
.arg2_type = ARG_ANYTHING,
.arg3_type = ARG_PTR_TO_FUNC,
.arg4_type = ARG_PTR_TO_STACK_OR_NULL,
.arg5_type = ARG_ANYTHING,
};
DEFINE_PER_CPU(struct mmap_unlock_irq_work, mmap_unlock_work);
static void do_mmap_read_unlock(struct irq_work *entry)
{
struct mmap_unlock_irq_work *work;
if (WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_RT)))
return;
work = container_of(entry, struct mmap_unlock_irq_work, irq_work);
mmap_read_unlock_non_owner(work->mm);
}
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
static int __init task_iter_init(void)
{
bpf: Introduce helper bpf_find_vma In some profiler use cases, it is necessary to map an address to the backing file, e.g., a shared library. bpf_find_vma helper provides a flexible way to achieve this. bpf_find_vma maps an address of a task to the vma (vm_area_struct) for this address, and feed the vma to an callback BPF function. The callback function is necessary here, as we need to ensure mmap_sem is unlocked. It is necessary to lock mmap_sem for find_vma. To lock and unlock mmap_sem safely when irqs are disable, we use the same mechanism as stackmap with build_id. Specifically, when irqs are disabled, the unlocked is postponed in an irq_work. Refactor stackmap.c so that the irq_work is shared among bpf_find_vma and stackmap helpers. Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Tested-by: Hengqi Chen <hengqi.chen@gmail.com> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211105232330.1936330-2-songliubraving@fb.com
2021-11-05 23:23:29 +00:00
struct mmap_unlock_irq_work *work;
int ret, cpu;
for_each_possible_cpu(cpu) {
work = per_cpu_ptr(&mmap_unlock_work, cpu);
init_irq_work(&work->irq_work, do_mmap_read_unlock);
}
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
bpf: Introduce btf_tracing_ids Similar to btf_sock_ids, btf_tracing_ids provides btf ID for task_struct, file, and vm_area_struct via easy to understand format like btf_tracing_ids[BTF_TRACING_TYPE_[TASK|file|VMA]]. Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211112150243.1270987-3-songliubraving@fb.com
2021-11-12 15:02:43 +00:00
task_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
ret = bpf_iter_reg_target(&task_reg_info);
if (ret)
return ret;
bpf: Introduce btf_tracing_ids Similar to btf_sock_ids, btf_tracing_ids provides btf ID for task_struct, file, and vm_area_struct via easy to understand format like btf_tracing_ids[BTF_TRACING_TYPE_[TASK|file|VMA]]. Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211112150243.1270987-3-songliubraving@fb.com
2021-11-12 15:02:43 +00:00
task_file_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
task_file_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_FILE];
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
ret = bpf_iter_reg_target(&task_file_reg_info);
if (ret)
return ret;
bpf: Introduce btf_tracing_ids Similar to btf_sock_ids, btf_tracing_ids provides btf ID for task_struct, file, and vm_area_struct via easy to understand format like btf_tracing_ids[BTF_TRACING_TYPE_[TASK|file|VMA]]. Suggested-by: Alexei Starovoitov <ast@kernel.org> Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20211112150243.1270987-3-songliubraving@fb.com
2021-11-12 15:02:43 +00:00
task_vma_reg_info.ctx_arg_info[0].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_TASK];
task_vma_reg_info.ctx_arg_info[1].btf_id = btf_tracing_ids[BTF_TRACING_TYPE_VMA];
bpf: Introduce task_vma bpf_iter Introduce task_vma bpf_iter to print memory information of a process. It can be used to print customized information similar to /proc/<pid>/maps. Current /proc/<pid>/maps and /proc/<pid>/smaps provide information of vma's of a process. However, these information are not flexible enough to cover all use cases. For example, if a vma cover mixed 2MB pages and 4kB pages (x86_64), there is no easy way to tell which address ranges are backed by 2MB pages. task_vma solves the problem by enabling the user to generate customize information based on the vma (and vma->vm_mm, vma->vm_file, etc.). To access the vma safely in the BPF program, task_vma iterator holds target mmap_lock while calling the BPF program. If the mmap_lock is contended, task_vma unlocks mmap_lock between iterations to unblock the writer(s). This lock contention avoidance mechanism is similar to the one used in show_smaps_rollup(). Signed-off-by: Song Liu <songliubraving@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Yonghong Song <yhs@fb.com> Link: https://lore.kernel.org/bpf/20210212183107.50963-2-songliubraving@fb.com
2021-02-12 18:31:05 +00:00
return bpf_iter_reg_target(&task_vma_reg_info);
bpf: Add task and task/file iterator targets Only the tasks belonging to "current" pid namespace are enumerated. For task/file target, the bpf program will have access to struct task_struct *task u32 fd struct file *file where fd/file is an open file for the task. Signed-off-by: Yonghong Song <yhs@fb.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Acked-by: Andrii Nakryiko <andriin@fb.com> Link: https://lore.kernel.org/bpf/20200509175911.2476407-1-yhs@fb.com
2020-05-09 17:59:11 +00:00
}
late_initcall(task_iter_init);
Reference in New Issue Copy Permalink