From 92333baaceb399c7878c7f868a0746d7d22f9b77 Mon Sep 17 00:00:00 2001 From: Lukas Bulwahn Date: Wed, 23 Mar 2022 16:07:00 -0700 Subject: taskstats: remove unneeded dead assignment make clang-analyzer on x86_64 defconfig caught my attention with: kernel/taskstats.c:120:2: warning: Value stored to 'rc' is never read \ [clang-analyzer-deadcode.DeadStores] rc = 0; ^ Commit d94a041519f3 ("taskstats: free skb, avoid returns in send_cpu_listeners") made send_cpu_listeners() not return a value and hence, the rc variable remained only to be used within the loop where it is always assigned before read and it does not need any other initialisation. So, simply remove this unneeded dead initializing assignment. As compilers will detect this unneeded assignment and optimize this anyway, the resulting object code is identical before and after this change. No functional change. No change to object code. [akpm@linux-foundation.org: reduce scope of `rc'] Link: https://lkml.kernel.org/r/20220307093942.21310-1-lukas.bulwahn@gmail.com Signed-off-by: Lukas Bulwahn Reviewed-by: Nick Desaulniers Cc: Balbir Singh Cc: Tom Rix Cc: Nathan Chancellor Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/taskstats.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/taskstats.c') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 2b4898b4752e..bcac5a9043aa 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -113,13 +113,14 @@ static void send_cpu_listeners(struct sk_buff *skb, struct listener *s, *tmp; struct sk_buff *skb_next, *skb_cur = skb; void *reply = genlmsg_data(genlhdr); - int rc, delcount = 0; + int delcount = 0; genlmsg_end(skb, reply); - rc = 0; down_read(&listeners->sem); list_for_each_entry(s, &listeners->list, list) { + int rc; + skb_next = NULL; if (!list_is_last(&s->list, &listeners->list)) { skb_next = skb_clone(skb_cur, GFP_KERNEL); -- cgit v1.2.3 From 0e0af57e0e91b304f36b7d1dba859e3c04094273 Mon Sep 17 00:00:00 2001 From: "Dr. Thomas Orgis" Date: Fri, 29 Apr 2022 14:38:03 -0700 Subject: taskstats: version 12 with thread group and exe info The task exit struct needs some crucial information to be able to provide an enhanced version of process and thread accounting. This change provides: 1. ac_tgid in additon to ac_pid 2. thread group execution walltime in ac_tgetime 3. flag AGROUP in ac_flag to indicate the last task in a thread group / process 4. device ID and inode of task's /proc/self/exe in ac_exe_dev and ac_exe_inode 5. tools/accounting/procacct as demonstrator When a task exits, taskstats are reported to userspace including the task's pid and ppid, but without the id of the thread group this task is part of. Without the tgid, the stats of single tasks cannot be correlated to each other as a thread group (process). The taskstats documentation suggests that on process exit a data set consisting of accumulated stats for the whole group is produced. But such an additional set of stats is only produced for actually multithreaded processes, not groups that had only one thread, and also those stats only contain data about delay accounting and not the more basic information about CPU and memory resource usage. Adding the AGROUP flag to be set when the last task of a group exited enables determination of process end also for single-threaded processes. My applicaton basically does enhanced process accounting with summed cputime, biggest maxrss, tasks per process. The data is not available with the traditional BSD process accounting (which is not designed to be extensible) and the taskstats interface allows more efficient on-the-fly grouping and summing of the stats, anyway, without intermediate disk writes. Furthermore, I do carry statistics on which exact program binary is used how often with associated resources, getting a picture on how important which parts of a collection of installed scientific software in different versions are, and how well they put load on the machine. This is enabled by providing information on /proc/self/exe for each task. I assume the two 64-bit fields for device ID and inode are more appropriate than the possibly large resolved path to keep the data volume down. Add the tgid to the stats to complete task identification, the flag AGROUP to mark the last task of a group, the group wallclock time, and inode-based identification of the associated executable file. Add tools/accounting/procacct.c as a simplified fork of getdelays.c to demonstrate process and thread accounting. [thomas.orgis@uni-hamburg.de: fix version number in comment] Link: https://lkml.kernel.org/r/20220405003601.7a5f6008@plasteblaster Link: https://lkml.kernel.org/r/20220331004106.64e5616b@plasteblaster Signed-off-by: Dr. Thomas Orgis Reviewed-by: Ismael Luceno Cc: Balbir Singh Cc: Eric W. Biederman Cc: xu xin Cc: Yang Yang Signed-off-by: Andrew Morton --- kernel/taskstats.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) (limited to 'kernel/taskstats.c') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index bcac5a9043aa..72415e22342b 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include @@ -153,6 +154,23 @@ static void send_cpu_listeners(struct sk_buff *skb, up_write(&listeners->sem); } +static void exe_add_tsk(struct taskstats *stats, struct task_struct *tsk) +{ + /* No idea if I'm allowed to access that here, now. */ + struct file *exe_file = get_task_exe_file(tsk); + + if (exe_file) { + /* Following cp_new_stat64() in stat.c . */ + stats->ac_exe_dev = + huge_encode_dev(exe_file->f_inode->i_sb->s_dev); + stats->ac_exe_inode = exe_file->f_inode->i_ino; + fput(exe_file); + } else { + stats->ac_exe_dev = 0; + stats->ac_exe_inode = 0; + } +} + static void fill_stats(struct user_namespace *user_ns, struct pid_namespace *pid_ns, struct task_struct *tsk, struct taskstats *stats) @@ -175,6 +193,9 @@ static void fill_stats(struct user_namespace *user_ns, /* fill in extended acct fields */ xacct_add_tsk(stats, tsk); + + /* add executable info */ + exe_add_tsk(stats, tsk); } static int fill_stats_for_pid(pid_t pid, struct taskstats *stats) @@ -620,6 +641,8 @@ void taskstats_exit(struct task_struct *tsk, int group_dead) goto err; fill_stats(&init_user_ns, &init_pid_ns, tsk, stats); + if (group_dead) + stats->ac_flag |= AGROUP; /* * Doesn't matter if tsk is the leader or the last group member leaving -- cgit v1.2.3 From edc73c7261ca3ea79867437bb0b9dab0e232436c Mon Sep 17 00:00:00 2001 From: xu xin Date: Fri, 29 Apr 2022 14:38:03 -0700 Subject: kernel: make taskstats available from all net namespaces If getdelays runs in a non-init network namespace, it will fail in getting delayacct stats even if it has privilege of root user, which seems to be not very reasonable. We can simply reproduce this by executing commands: unshare -n getdelays -d -p I don't think net namespace should be an obstacle to the normal execution of getdelay function. So let's make it available from all net namespaces. Link: https://lkml.kernel.org/r/20220412071946.2532318-1-xu.xin16@zte.com.cn Signed-off-by: xu xin Cc: Balbir Singh Cc: Yang Yang Cc: "Dr. Thomas Orgis" Cc: Eric W. Biederman Cc: Ismael Luceno Signed-off-by: Andrew Morton --- kernel/taskstats.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/taskstats.c') diff --git a/kernel/taskstats.c b/kernel/taskstats.c index 72415e22342b..f7e246336218 100644 --- a/kernel/taskstats.c +++ b/kernel/taskstats.c @@ -688,6 +688,7 @@ static struct genl_family family __ro_after_init = { .module = THIS_MODULE, .ops = taskstats_ops, .n_ops = ARRAY_SIZE(taskstats_ops), + .netnsok = true, }; /* Needed early in initialization */ -- cgit v1.2.3