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 --- include/uapi/linux/acct.h | 3 +- include/uapi/linux/taskstats.h | 24 ++- kernel/taskstats.c | 23 +++ kernel/tsacct.c | 10 +- tools/accounting/.gitignore | 1 + tools/accounting/Makefile | 2 +- tools/accounting/procacct.c | 417 +++++++++++++++++++++++++++++++++++++++++ 7 files changed, 473 insertions(+), 7 deletions(-) create mode 100644 tools/accounting/procacct.c (limited to 'kernel/taskstats.c') diff --git a/include/uapi/linux/acct.h b/include/uapi/linux/acct.h index 985b89068591..0e591152aa8a 100644 --- a/include/uapi/linux/acct.h +++ b/include/uapi/linux/acct.h @@ -103,12 +103,13 @@ struct acct_v3 /* * accounting flags */ - /* bit set when the process ... */ + /* bit set when the process/task ... */ #define AFORK 0x01 /* ... executed fork, but did not exec */ #define ASU 0x02 /* ... used super-user privileges */ #define ACOMPAT 0x04 /* ... used compatibility mode (VAX only not used) */ #define ACORE 0x08 /* ... dumped core */ #define AXSIG 0x10 /* ... was killed by a signal */ +#define AGROUP 0x20 /* ... was the last task of the process (task group) */ #if defined(__BYTE_ORDER) ? __BYTE_ORDER == __BIG_ENDIAN : defined(__BIG_ENDIAN) #define ACCT_BYTEORDER 0x80 /* accounting file is big endian */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 12327d32378f..736154171489 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 11 +#define TASKSTATS_VERSION 12 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -48,7 +48,8 @@ struct taskstats { __u32 ac_exitcode; /* Exit status */ /* The accounting flags of a task as defined in - * Defined values are AFORK, ASU, ACOMPAT, ACORE, and AXSIG. + * Defined values are AFORK, ASU, ACOMPAT, ACORE, AXSIG, and AGROUP. + * (AGROUP since version 12). */ __u8 ac_flag; /* Record flags */ __u8 ac_nice; /* task_nice */ @@ -173,9 +174,26 @@ struct taskstats { /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ - /* Delay waiting for memory compact */ + /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; + + /* v12 begin */ + __u32 ac_tgid; /* thread group ID */ + /* Thread group walltime up to now. This is total process walltime if + * AGROUP flag is set. + */ + __u64 ac_tgetime __attribute__((aligned(8))); + /* Lightweight information to identify process binary files. + * This leaves userspace to match this to a file system path, using + * MAJOR() and MINOR() macros to identify a device and mount point, + * the inode to identify the executable file. This is /proc/self/exe + * at the end, so matching the most recent exec(). Values are zero + * for kernel threads. + */ + __u64 ac_exe_dev; /* program binary device ID */ + __u64 ac_exe_inode; /* program binary inode number */ + /* v12 end */ }; 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 diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 1d261fbe367b..4252f0645b9e 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -23,15 +23,20 @@ void bacct_add_tsk(struct user_namespace *user_ns, { const struct cred *tcred; u64 utime, stime, utimescaled, stimescaled; - u64 delta; + u64 now_ns, delta; time64_t btime; BUILD_BUG_ON(TS_COMM_LEN < TASK_COMM_LEN); /* calculate task elapsed time in nsec */ - delta = ktime_get_ns() - tsk->start_time; + now_ns = ktime_get_ns(); + /* store whole group time first */ + delta = now_ns - tsk->group_leader->start_time; /* Convert to micro seconds */ do_div(delta, NSEC_PER_USEC); + stats->ac_tgetime = delta; + delta = now_ns - tsk->start_time; + do_div(delta, NSEC_PER_USEC); stats->ac_etime = delta; /* Convert to seconds for btime (note y2106 limit) */ btime = ktime_get_real_seconds() - div_u64(delta, USEC_PER_SEC); @@ -51,6 +56,7 @@ void bacct_add_tsk(struct user_namespace *user_ns, stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; stats->ac_pid = task_pid_nr_ns(tsk, pid_ns); + stats->ac_tgid = task_tgid_nr_ns(tsk, pid_ns); rcu_read_lock(); tcred = __task_cred(tsk); stats->ac_uid = from_kuid_munged(user_ns, tcred->uid); diff --git a/tools/accounting/.gitignore b/tools/accounting/.gitignore index c45fb4ed4309..522a690aaf3d 100644 --- a/tools/accounting/.gitignore +++ b/tools/accounting/.gitignore @@ -1,2 +1,3 @@ # SPDX-License-Identifier: GPL-2.0-only getdelays +procacct diff --git a/tools/accounting/Makefile b/tools/accounting/Makefile index 03687f19cbb1..11def1ad046c 100644 --- a/tools/accounting/Makefile +++ b/tools/accounting/Makefile @@ -2,7 +2,7 @@ CC := $(CROSS_COMPILE)gcc CFLAGS := -I../../usr/include -PROGS := getdelays +PROGS := getdelays procacct all: $(PROGS) diff --git a/tools/accounting/procacct.c b/tools/accounting/procacct.c new file mode 100644 index 000000000000..8353d3237e50 --- /dev/null +++ b/tools/accounting/procacct.c @@ -0,0 +1,417 @@ +// SPDX-License-Identifier: GPL-2.0 +/* procacct.c + * + * Demonstrator of fetching resource data on task exit, as a way + * to accumulate accurate program resource usage statistics, without + * prior identification of the programs. For that, the fields for + * device and inode of the program executable binary file are also + * extracted in addition to the command string. + * + * The TGID together with the PID and the AGROUP flag allow + * identification of threads in a process and single-threaded processes. + * The ac_tgetime field gives proper whole-process walltime. + * + * Written (changed) by Thomas Orgis, University of Hamburg in 2022 + * + * This is a cheap derivation (inheriting the style) of getdelays.c: + * + * Utility to get per-pid and per-tgid delay accounting statistics + * Also illustrates usage of the taskstats interface + * + * Copyright (C) Shailabh Nagar, IBM Corp. 2005 + * Copyright (C) Balbir Singh, IBM Corp. 2006 + * Copyright (c) Jay Lan, SGI. 2006 + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include + +/* + * Generic macros for dealing with netlink sockets. Might be duplicated + * elsewhere. It is recommended that commercial grade applications use + * libnl or libnetlink and use the interfaces provided by the library + */ +#define GENLMSG_DATA(glh) ((void *)(NLMSG_DATA(glh) + GENL_HDRLEN)) +#define GENLMSG_PAYLOAD(glh) (NLMSG_PAYLOAD(glh, 0) - GENL_HDRLEN) +#define NLA_DATA(na) ((void *)((char *)(na) + NLA_HDRLEN)) +#define NLA_PAYLOAD(len) (len - NLA_HDRLEN) + +#define err(code, fmt, arg...) \ + do { \ + fprintf(stderr, fmt, ##arg); \ + exit(code); \ + } while (0) + +int rcvbufsz; +char name[100]; +int dbg; +int print_delays; +int print_io_accounting; +int print_task_context_switch_counts; + +#define PRINTF(fmt, arg...) { \ + if (dbg) { \ + printf(fmt, ##arg); \ + } \ + } + +/* Maximum size of response requested or message sent */ +#define MAX_MSG_SIZE 1024 +/* Maximum number of cpus expected to be specified in a cpumask */ +#define MAX_CPUS 32 + +struct msgtemplate { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[MAX_MSG_SIZE]; +}; + +char cpumask[100+6*MAX_CPUS]; + +static void usage(void) +{ + fprintf(stderr, "procacct [-v] [-w logfile] [-r bufsize] [-m cpumask]\n"); + fprintf(stderr, " -v: debug on\n"); +} + +/* + * Create a raw netlink socket and bind + */ +static int create_nl_socket(int protocol) +{ + int fd; + struct sockaddr_nl local; + + fd = socket(AF_NETLINK, SOCK_RAW, protocol); + if (fd < 0) + return -1; + + if (rcvbufsz) + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, + &rcvbufsz, sizeof(rcvbufsz)) < 0) { + fprintf(stderr, "Unable to set socket rcv buf size to %d\n", + rcvbufsz); + goto error; + } + + memset(&local, 0, sizeof(local)); + local.nl_family = AF_NETLINK; + + if (bind(fd, (struct sockaddr *) &local, sizeof(local)) < 0) + goto error; + + return fd; +error: + close(fd); + return -1; +} + + +static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, + __u8 genl_cmd, __u16 nla_type, + void *nla_data, int nla_len) +{ + struct nlattr *na; + struct sockaddr_nl nladdr; + int r, buflen; + char *buf; + + struct msgtemplate msg; + + msg.n.nlmsg_len = NLMSG_LENGTH(GENL_HDRLEN); + msg.n.nlmsg_type = nlmsg_type; + msg.n.nlmsg_flags = NLM_F_REQUEST; + msg.n.nlmsg_seq = 0; + msg.n.nlmsg_pid = nlmsg_pid; + msg.g.cmd = genl_cmd; + msg.g.version = 0x1; + na = (struct nlattr *) GENLMSG_DATA(&msg); + na->nla_type = nla_type; + na->nla_len = nla_len + 1 + NLA_HDRLEN; + memcpy(NLA_DATA(na), nla_data, nla_len); + msg.n.nlmsg_len += NLMSG_ALIGN(na->nla_len); + + buf = (char *) &msg; + buflen = msg.n.nlmsg_len; + memset(&nladdr, 0, sizeof(nladdr)); + nladdr.nl_family = AF_NETLINK; + while ((r = sendto(sd, buf, buflen, 0, (struct sockaddr *) &nladdr, + sizeof(nladdr))) < buflen) { + if (r > 0) { + buf += r; + buflen -= r; + } else if (errno != EAGAIN) + return -1; + } + return 0; +} + + +/* + * Probe the controller in genetlink to find the family id + * for the TASKSTATS family + */ +static int get_family_id(int sd) +{ + struct { + struct nlmsghdr n; + struct genlmsghdr g; + char buf[256]; + } ans; + + int id = 0, rc; + struct nlattr *na; + int rep_len; + + strcpy(name, TASKSTATS_GENL_NAME); + rc = send_cmd(sd, GENL_ID_CTRL, getpid(), CTRL_CMD_GETFAMILY, + CTRL_ATTR_FAMILY_NAME, (void *)name, + strlen(TASKSTATS_GENL_NAME)+1); + if (rc < 0) + return 0; /* sendto() failure? */ + + rep_len = recv(sd, &ans, sizeof(ans), 0); + if (ans.n.nlmsg_type == NLMSG_ERROR || + (rep_len < 0) || !NLMSG_OK((&ans.n), rep_len)) + return 0; + + na = (struct nlattr *) GENLMSG_DATA(&ans); + na = (struct nlattr *) ((char *) na + NLA_ALIGN(na->nla_len)); + if (na->nla_type == CTRL_ATTR_FAMILY_ID) + id = *(__u16 *) NLA_DATA(na); + + return id; +} + +#define average_ms(t, c) (t / 1000000ULL / (c ? c : 1)) + +static void print_procacct(struct taskstats *t) +{ + /* First letter: T is a mere thread, G the last in a group, U unknown. */ + printf( + "%c pid=%lu tgid=%lu uid=%lu wall=%llu gwall=%llu cpu=%llu vmpeak=%llu rsspeak=%llu dev=%lu:%lu inode=%llu comm=%s\n" + , t->version >= 12 ? (t->ac_flag & AGROUP ? 'P' : 'T') : '?' + , (unsigned long)t->ac_pid + , (unsigned long)(t->version >= 12 ? t->ac_tgid : 0) + , (unsigned long)t->ac_uid + , (unsigned long long)t->ac_etime + , (unsigned long long)(t->version >= 12 ? t->ac_tgetime : 0) + , (unsigned long long)(t->ac_utime+t->ac_stime) + , (unsigned long long)t->hiwater_vm + , (unsigned long long)t->hiwater_rss + , (unsigned long)(t->version >= 12 ? MAJOR(t->ac_exe_dev) : 0) + , (unsigned long)(t->version >= 12 ? MINOR(t->ac_exe_dev) : 0) + , (unsigned long long)(t->version >= 12 ? t->ac_exe_inode : 0) + , t->ac_comm + ); +} + +void handle_aggr(int mother, struct nlattr *na, int fd) +{ + int aggr_len = NLA_PAYLOAD(na->nla_len); + int len2 = 0; + pid_t rtid = 0; + + na = (struct nlattr *) NLA_DATA(na); + while (len2 < aggr_len) { + switch (na->nla_type) { + case TASKSTATS_TYPE_PID: + rtid = *(int *) NLA_DATA(na); + PRINTF("PID\t%d\n", rtid); + break; + case TASKSTATS_TYPE_TGID: + rtid = *(int *) NLA_DATA(na); + PRINTF("TGID\t%d\n", rtid); + break; + case TASKSTATS_TYPE_STATS: + if (mother == TASKSTATS_TYPE_AGGR_PID) + print_procacct((struct taskstats *) NLA_DATA(na)); + if (fd) { + if (write(fd, NLA_DATA(na), na->nla_len) < 0) + err(1, "write error\n"); + } + break; + case TASKSTATS_TYPE_NULL: + break; + default: + fprintf(stderr, "Unknown nested nla_type %d\n", + na->nla_type); + break; + } + len2 += NLA_ALIGN(na->nla_len); + na = (struct nlattr *)((char *)na + + NLA_ALIGN(na->nla_len)); + } +} + +int main(int argc, char *argv[]) +{ + int c, rc, rep_len, aggr_len, len2; + int cmd_type = TASKSTATS_CMD_ATTR_UNSPEC; + __u16 id; + __u32 mypid; + + struct nlattr *na; + int nl_sd = -1; + int len = 0; + pid_t tid = 0; + + int fd = 0; + int write_file = 0; + int maskset = 0; + char *logfile = NULL; + int containerset = 0; + char *containerpath = NULL; + int cfd = 0; + int forking = 0; + sigset_t sigset; + + struct msgtemplate msg; + + while (!forking) { + c = getopt(argc, argv, "m:vr:"); + if (c < 0) + break; + + switch (c) { + case 'w': + logfile = strdup(optarg); + printf("write to file %s\n", logfile); + write_file = 1; + break; + case 'r': + rcvbufsz = atoi(optarg); + printf("receive buf size %d\n", rcvbufsz); + if (rcvbufsz < 0) + err(1, "Invalid rcv buf size\n"); + break; + case 'm': + strncpy(cpumask, optarg, sizeof(cpumask)); + cpumask[sizeof(cpumask) - 1] = '\0'; + maskset = 1; + break; + case 'v': + printf("debug on\n"); + dbg = 1; + break; + default: + usage(); + exit(-1); + } + } + if (!maskset) { + maskset = 1; + strncpy(cpumask, "1", sizeof(cpumask)); + cpumask[sizeof(cpumask) - 1] = '\0'; + } + printf("cpumask %s maskset %d\n", cpumask, maskset); + + if (write_file) { + fd = open(logfile, O_WRONLY | O_CREAT | O_TRUNC, 0644); + if (fd == -1) { + perror("Cannot open output file\n"); + exit(1); + } + } + + nl_sd = create_nl_socket(NETLINK_GENERIC); + if (nl_sd < 0) + err(1, "error creating Netlink socket\n"); + + mypid = getpid(); + id = get_family_id(nl_sd); + if (!id) { + fprintf(stderr, "Error getting family id, errno %d\n", errno); + goto err; + } + PRINTF("family id %d\n", id); + + if (maskset) { + rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, + TASKSTATS_CMD_ATTR_REGISTER_CPUMASK, + &cpumask, strlen(cpumask) + 1); + PRINTF("Sent register cpumask, retval %d\n", rc); + if (rc < 0) { + fprintf(stderr, "error sending register cpumask\n"); + goto err; + } + } + + do { + rep_len = recv(nl_sd, &msg, sizeof(msg), 0); + PRINTF("received %d bytes\n", rep_len); + + if (rep_len < 0) { + fprintf(stderr, "nonfatal reply error: errno %d\n", + errno); + continue; + } + if (msg.n.nlmsg_type == NLMSG_ERROR || + !NLMSG_OK((&msg.n), rep_len)) { + struct nlmsgerr *err = NLMSG_DATA(&msg); + + fprintf(stderr, "fatal reply error, errno %d\n", + err->error); + goto done; + } + + PRINTF("nlmsghdr size=%zu, nlmsg_len=%d, rep_len=%d\n", + sizeof(struct nlmsghdr), msg.n.nlmsg_len, rep_len); + + + rep_len = GENLMSG_PAYLOAD(&msg.n); + + na = (struct nlattr *) GENLMSG_DATA(&msg); + len = 0; + while (len < rep_len) { + len += NLA_ALIGN(na->nla_len); + int mother = na->nla_type; + + PRINTF("mother=%i\n", mother); + switch (na->nla_type) { + case TASKSTATS_TYPE_AGGR_PID: + case TASKSTATS_TYPE_AGGR_TGID: + /* For nested attributes, na follows */ + handle_aggr(mother, na, fd); + break; + default: + fprintf(stderr, "Unexpected nla_type %d\n", + na->nla_type); + case TASKSTATS_TYPE_NULL: + break; + } + na = (struct nlattr *) (GENLMSG_DATA(&msg) + len); + } + } while (1); +done: + if (maskset) { + rc = send_cmd(nl_sd, id, mypid, TASKSTATS_CMD_GET, + TASKSTATS_CMD_ATTR_DEREGISTER_CPUMASK, + &cpumask, strlen(cpumask) + 1); + printf("Sent deregister mask, retval %d\n", rc); + if (rc < 0) + err(rc, "error sending deregister cpumask\n"); + } +err: + close(nl_sd); + if (fd) + close(fd); + if (cfd) + close(cfd); + return 0; +} -- 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 From 9c5d03d362519f36cd551aec596388f895c93d2d Mon Sep 17 00:00:00 2001 From: Jakub Kicinski Date: Wed, 24 Aug 2022 17:18:30 -0700 Subject: genetlink: start to validate reserved header bytes We had historically not checked that genlmsghdr.reserved is 0 on input which prevents us from using those precious bytes in the future. One use case would be to extend the cmd field, which is currently just 8 bits wide and 256 is not a lot of commands for some core families. To make sure that new families do the right thing by default put the onus of opting out of validation on existing families. Signed-off-by: Jakub Kicinski Acked-by: Paul Moore (NetLabel) Signed-off-by: David S. Miller --- drivers/block/nbd.c | 1 + drivers/net/gtp.c | 1 + drivers/net/ieee802154/mac802154_hwsim.c | 1 + drivers/net/macsec.c | 1 + drivers/net/team/team.c | 1 + drivers/net/wireguard/netlink.c | 1 + drivers/net/wireless/mac80211_hwsim.c | 1 + drivers/target/target_core_user.c | 1 + drivers/thermal/thermal_netlink.c | 1 + drivers/vdpa/vdpa.c | 1 + fs/cifs/netlink.c | 1 + fs/dlm/netlink.c | 1 + fs/ksmbd/transport_ipc.c | 1 + include/linux/genl_magic_func.h | 1 + include/net/genetlink.h | 3 +++ kernel/taskstats.c | 1 + net/batman-adv/netlink.c | 1 + net/core/devlink.c | 1 + net/core/drop_monitor.c | 1 + net/ethtool/netlink.c | 1 + net/hsr/hsr_netlink.c | 1 + net/ieee802154/netlink.c | 1 + net/ieee802154/nl802154.c | 1 + net/ipv4/fou.c | 1 + net/ipv4/tcp_metrics.c | 1 + net/ipv6/ila/ila_main.c | 1 + net/ipv6/ioam6.c | 1 + net/ipv6/seg6.c | 1 + net/l2tp/l2tp_netlink.c | 1 + net/mptcp/pm_netlink.c | 1 + net/ncsi/ncsi-netlink.c | 1 + net/netfilter/ipvs/ip_vs_ctl.c | 1 + net/netlabel/netlabel_calipso.c | 1 + net/netlabel/netlabel_cipso_v4.c | 1 + net/netlabel/netlabel_mgmt.c | 1 + net/netlabel/netlabel_unlabeled.c | 1 + net/netlink/genetlink.c | 4 ++++ net/nfc/netlink.c | 1 + net/openvswitch/conntrack.c | 1 + net/openvswitch/datapath.c | 3 +++ net/openvswitch/meter.c | 1 + net/psample/psample.c | 1 + net/smc/smc_netlink.c | 3 ++- net/smc/smc_pnet.c | 3 ++- net/tipc/netlink.c | 1 + net/tipc/netlink_compat.c | 1 + net/wireless/nl80211.c | 1 + 47 files changed, 56 insertions(+), 2 deletions(-) (limited to 'kernel/taskstats.c') diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 2a709daefbc4..6cec9ce23fd3 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -2322,6 +2322,7 @@ static struct genl_family nbd_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = nbd_connect_genl_ops, .n_small_ops = ARRAY_SIZE(nbd_connect_genl_ops), + .resv_start_op = NBD_CMD_STATUS + 1, .maxattr = NBD_ATTR_MAX, .policy = nbd_attr_policy, .mcgrps = nbd_mcast_grps, diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index a208e2b1a9af..15c7dc82107f 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1859,6 +1859,7 @@ static struct genl_family gtp_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = gtp_genl_ops, .n_small_ops = ARRAY_SIZE(gtp_genl_ops), + .resv_start_op = GTP_CMD_ECHOREQ + 1, .mcgrps = gtp_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(gtp_genl_mcgrps), }; diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c index 38c217bd7c82..2f0544dd7c2a 100644 --- a/drivers/net/ieee802154/mac802154_hwsim.c +++ b/drivers/net/ieee802154/mac802154_hwsim.c @@ -630,6 +630,7 @@ static struct genl_family hwsim_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = hwsim_nl_ops, .n_small_ops = ARRAY_SIZE(hwsim_nl_ops), + .resv_start_op = MAC802154_HWSIM_CMD_NEW_EDGE + 1, .mcgrps = hwsim_mcgrps, .n_mcgrps = ARRAY_SIZE(hwsim_mcgrps), }; diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index c6d271e5687e..adf448a8162b 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3404,6 +3404,7 @@ static struct genl_family macsec_fam __ro_after_init = { .module = THIS_MODULE, .small_ops = macsec_genl_ops, .n_small_ops = ARRAY_SIZE(macsec_genl_ops), + .resv_start_op = MACSEC_CMD_UPD_OFFLOAD + 1, }; static netdev_tx_t macsec_start_xmit(struct sk_buff *skb, diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index aac133a1e27a..b1e1239dfade 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2840,6 +2840,7 @@ static struct genl_family team_nl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = team_nl_ops, .n_small_ops = ARRAY_SIZE(team_nl_ops), + .resv_start_op = TEAM_CMD_PORT_LIST_GET + 1, .mcgrps = team_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(team_nl_mcgrps), }; diff --git a/drivers/net/wireguard/netlink.c b/drivers/net/wireguard/netlink.c index d0f3b6d7f408..0c0644e762e5 100644 --- a/drivers/net/wireguard/netlink.c +++ b/drivers/net/wireguard/netlink.c @@ -621,6 +621,7 @@ static const struct genl_ops genl_ops[] = { static struct genl_family genl_family __ro_after_init = { .ops = genl_ops, .n_ops = ARRAY_SIZE(genl_ops), + .resv_start_op = WG_CMD_SET_DEVICE + 1, .name = WG_GENL_NAME, .version = WG_GENL_VERSION, .maxattr = WGDEVICE_A_MAX, diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 4fb8f68e5c3b..d9054104725e 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -5288,6 +5288,7 @@ static struct genl_family hwsim_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = hwsim_ops, .n_small_ops = ARRAY_SIZE(hwsim_ops), + .resv_start_op = HWSIM_CMD_DEL_MAC_ADDR + 1, .mcgrps = hwsim_mcgrps, .n_mcgrps = ARRAY_SIZE(hwsim_mcgrps), }; diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c index 3deaeecb712e..2940559c3086 100644 --- a/drivers/target/target_core_user.c +++ b/drivers/target/target_core_user.c @@ -486,6 +486,7 @@ static struct genl_family tcmu_genl_family __ro_after_init = { .netnsok = true, .small_ops = tcmu_genl_ops, .n_small_ops = ARRAY_SIZE(tcmu_genl_ops), + .resv_start_op = TCMU_CMD_SET_FEATURES + 1, }; #define tcmu_cmd_set_dbi_cur(cmd, index) ((cmd)->dbi_cur = (index)) diff --git a/drivers/thermal/thermal_netlink.c b/drivers/thermal/thermal_netlink.c index 050d243a5fa1..e2d78a996b5f 100644 --- a/drivers/thermal/thermal_netlink.c +++ b/drivers/thermal/thermal_netlink.c @@ -693,6 +693,7 @@ static struct genl_family thermal_gnl_family __ro_after_init = { .policy = thermal_genl_policy, .small_ops = thermal_genl_ops, .n_small_ops = ARRAY_SIZE(thermal_genl_ops), + .resv_start_op = THERMAL_GENL_CMD_CDEV_GET + 1, .mcgrps = thermal_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(thermal_genl_mcgrps), }; diff --git a/drivers/vdpa/vdpa.c b/drivers/vdpa/vdpa.c index c06c02704461..7badf5777597 100644 --- a/drivers/vdpa/vdpa.c +++ b/drivers/vdpa/vdpa.c @@ -1183,6 +1183,7 @@ static struct genl_family vdpa_nl_family __ro_after_init = { .module = THIS_MODULE, .ops = vdpa_nl_ops, .n_ops = ARRAY_SIZE(vdpa_nl_ops), + .resv_start_op = VDPA_CMD_DEV_VSTATS_GET + 1, }; static int vdpa_init(void) diff --git a/fs/cifs/netlink.c b/fs/cifs/netlink.c index 291cb606f149..147d9409252c 100644 --- a/fs/cifs/netlink.c +++ b/fs/cifs/netlink.c @@ -51,6 +51,7 @@ struct genl_family cifs_genl_family = { .policy = cifs_genl_policy, .ops = cifs_genl_ops, .n_ops = ARRAY_SIZE(cifs_genl_ops), + .resv_start_op = CIFS_GENL_CMD_SWN_NOTIFY + 1, .mcgrps = cifs_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(cifs_genl_mcgrps), }; diff --git a/fs/dlm/netlink.c b/fs/dlm/netlink.c index 67f68d48d60c..4de4b8651c6c 100644 --- a/fs/dlm/netlink.c +++ b/fs/dlm/netlink.c @@ -75,6 +75,7 @@ static struct genl_family family __ro_after_init = { .version = DLM_GENL_VERSION, .small_ops = dlm_nl_ops, .n_small_ops = ARRAY_SIZE(dlm_nl_ops), + .resv_start_op = DLM_CMD_HELLO + 1, .module = THIS_MODULE, }; diff --git a/fs/ksmbd/transport_ipc.c b/fs/ksmbd/transport_ipc.c index 7cb0eeb07c80..c9aca21637d5 100644 --- a/fs/ksmbd/transport_ipc.c +++ b/fs/ksmbd/transport_ipc.c @@ -197,6 +197,7 @@ static struct genl_family ksmbd_genl_family = { .module = THIS_MODULE, .ops = ksmbd_genl_ops, .n_ops = ARRAY_SIZE(ksmbd_genl_ops), + .resv_start_op = KSMBD_EVENT_SPNEGO_AUTHEN_RESPONSE + 1, }; static void ksmbd_nl_init_fixup(void) diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h index 939b1a8f571b..4a4b387181ad 100644 --- a/include/linux/genl_magic_func.h +++ b/include/linux/genl_magic_func.h @@ -294,6 +294,7 @@ static struct genl_family ZZZ_genl_family __ro_after_init = { .ops = ZZZ_genl_ops, .n_ops = ARRAY_SIZE(ZZZ_genl_ops), .mcgrps = ZZZ_genl_mcgrps, + .resv_start_op = 42, /* drbd is currently the only user */ .n_mcgrps = ARRAY_SIZE(ZZZ_genl_mcgrps), .module = THIS_MODULE, }; diff --git a/include/net/genetlink.h b/include/net/genetlink.h index 56a50e1c51b9..a4827b5e1e07 100644 --- a/include/net/genetlink.h +++ b/include/net/genetlink.h @@ -39,6 +39,8 @@ struct genl_info; * undo operations done by pre_doit, for example release locks * @mcgrps: multicast groups used by this family * @n_mcgrps: number of multicast groups + * @resv_start_op: first operation for which reserved fields of the header + * can be validated, new families should leave this field at zero * @mcgrp_offset: starting number of multicast group IDs in this family * (private) * @ops: the operations supported by this family @@ -58,6 +60,7 @@ struct genl_family { u8 n_ops; u8 n_small_ops; u8 n_mcgrps; + u8 resv_start_op; const struct nla_policy *policy; int (*pre_doit)(const struct genl_ops *ops, struct sk_buff *skb, diff --git a/kernel/taskstats.c b/kernel/taskstats.c index f7e246336218..8ce3fa0c19e2 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), + .resv_start_op = CGROUPSTATS_CMD_GET + 1, .netnsok = true, }; diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 00875e1d8c44..a5e4a4e976cf 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1493,6 +1493,7 @@ struct genl_family batadv_netlink_family __ro_after_init = { .module = THIS_MODULE, .small_ops = batadv_netlink_ops, .n_small_ops = ARRAY_SIZE(batadv_netlink_ops), + .resv_start_op = BATADV_CMD_SET_VLAN + 1, .mcgrps = batadv_netlink_mcgrps, .n_mcgrps = ARRAY_SIZE(batadv_netlink_mcgrps), }; diff --git a/net/core/devlink.c b/net/core/devlink.c index 2afbeb6eca67..3396fdf802b6 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -9610,6 +9610,7 @@ static struct genl_family devlink_nl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = devlink_nl_ops, .n_small_ops = ARRAY_SIZE(devlink_nl_ops), + .resv_start_op = DEVLINK_CMD_SELFTESTS_RUN + 1, .mcgrps = devlink_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), }; diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 876664fc605e..f084a4a6b7ab 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -1645,6 +1645,7 @@ static struct genl_family net_drop_monitor_family __ro_after_init = { .module = THIS_MODULE, .small_ops = dropmon_ops, .n_small_ops = ARRAY_SIZE(dropmon_ops), + .resv_start_op = NET_DM_CMD_STATS_GET + 1, .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index e26079e11835..d5e77f1cbbfa 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -1033,6 +1033,7 @@ static struct genl_family ethtool_genl_family __ro_after_init = { .parallel_ops = true, .ops = ethtool_genl_ops, .n_ops = ARRAY_SIZE(ethtool_genl_ops), + .resv_start_op = ETHTOOL_MSG_MODULE_GET + 1, .mcgrps = ethtool_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(ethtool_nl_mcgrps), }; diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 1405c037cf7a..7174a9092900 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -522,6 +522,7 @@ static struct genl_family hsr_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = hsr_ops, .n_small_ops = ARRAY_SIZE(hsr_ops), + .resv_start_op = HSR_C_SET_NODE_LIST + 1, .mcgrps = hsr_mcgrps, .n_mcgrps = ARRAY_SIZE(hsr_mcgrps), }; diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c index b07abc38b4b3..7d2de4ee6992 100644 --- a/net/ieee802154/netlink.c +++ b/net/ieee802154/netlink.c @@ -132,6 +132,7 @@ struct genl_family nl802154_family __ro_after_init = { .module = THIS_MODULE, .small_ops = ieee802154_ops, .n_small_ops = ARRAY_SIZE(ieee802154_ops), + .resv_start_op = IEEE802154_LLSEC_DEL_SECLEVEL + 1, .mcgrps = ieee802154_mcgrps, .n_mcgrps = ARRAY_SIZE(ieee802154_mcgrps), }; diff --git a/net/ieee802154/nl802154.c b/net/ieee802154/nl802154.c index e0b072aecf0f..38c4f3cb010e 100644 --- a/net/ieee802154/nl802154.c +++ b/net/ieee802154/nl802154.c @@ -2500,6 +2500,7 @@ static struct genl_family nl802154_fam __ro_after_init = { .module = THIS_MODULE, .ops = nl802154_ops, .n_ops = ARRAY_SIZE(nl802154_ops), + .resv_start_op = NL802154_CMD_DEL_SEC_LEVEL + 1, .mcgrps = nl802154_mcgrps, .n_mcgrps = ARRAY_SIZE(nl802154_mcgrps), }; diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index cb5bfb77944c..0c3c6d0cee29 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -928,6 +928,7 @@ static struct genl_family fou_nl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = fou_nl_ops, .n_small_ops = ARRAY_SIZE(fou_nl_ops), + .resv_start_op = FOU_CMD_GET + 1, }; size_t fou_encap_hlen(struct ip_tunnel_encap *e) diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index d58e672be31c..82f4575f9cd9 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -969,6 +969,7 @@ static struct genl_family tcp_metrics_nl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = tcp_metrics_nl_ops, .n_small_ops = ARRAY_SIZE(tcp_metrics_nl_ops), + .resv_start_op = TCP_METRICS_CMD_DEL + 1, }; static unsigned int tcpmhash_entries; diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c index 36c58aa257e8..3faf62530d6a 100644 --- a/net/ipv6/ila/ila_main.c +++ b/net/ipv6/ila/ila_main.c @@ -55,6 +55,7 @@ struct genl_family ila_nl_family __ro_after_init = { .module = THIS_MODULE, .ops = ila_nl_ops, .n_ops = ARRAY_SIZE(ila_nl_ops), + .resv_start_op = ILA_CMD_FLUSH + 1, }; static __net_init int ila_init_net(struct net *net) diff --git a/net/ipv6/ioam6.c b/net/ipv6/ioam6.c index 1098131ed90c..571f0e4d9cf3 100644 --- a/net/ipv6/ioam6.c +++ b/net/ipv6/ioam6.c @@ -619,6 +619,7 @@ static struct genl_family ioam6_genl_family __ro_after_init = { .parallel_ops = true, .ops = ioam6_genl_ops, .n_ops = ARRAY_SIZE(ioam6_genl_ops), + .resv_start_op = IOAM6_CMD_NS_SET_SCHEMA + 1, .module = THIS_MODULE, }; diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 73aaabf0e966..5421cc7c935f 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -499,6 +499,7 @@ static struct genl_family seg6_genl_family __ro_after_init = { .parallel_ops = true, .ops = seg6_genl_ops, .n_ops = ARRAY_SIZE(seg6_genl_ops), + .resv_start_op = SEG6_CMD_GET_TUNSRC + 1, .module = THIS_MODULE, }; diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index 96eb91be9238..a901fd14fe3b 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -989,6 +989,7 @@ static struct genl_family l2tp_nl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = l2tp_nl_ops, .n_small_ops = ARRAY_SIZE(l2tp_nl_ops), + .resv_start_op = L2TP_CMD_SESSION_GET + 1, .mcgrps = l2tp_multicast_group, .n_mcgrps = ARRAY_SIZE(l2tp_multicast_group), }; diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 291b5da42fdb..a3e4ee7af0ee 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -2280,6 +2280,7 @@ static struct genl_family mptcp_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = mptcp_pm_ops, .n_small_ops = ARRAY_SIZE(mptcp_pm_ops), + .resv_start_op = MPTCP_PM_CMD_SUBFLOW_DESTROY + 1, .mcgrps = mptcp_pm_mcgrps, .n_mcgrps = ARRAY_SIZE(mptcp_pm_mcgrps), }; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index c189b4c8a182..d27f4eccce6d 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -768,6 +768,7 @@ static struct genl_family ncsi_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = ncsi_ops, .n_small_ops = ARRAY_SIZE(ncsi_ops), + .resv_start_op = NCSI_CMD_SET_CHANNEL_MASK + 1, }; static int __init ncsi_init_netlink(void) diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index efab2b06d373..818b0b058b10 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -4005,6 +4005,7 @@ static struct genl_family ip_vs_genl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = ip_vs_genl_ops, .n_small_ops = ARRAY_SIZE(ip_vs_genl_ops), + .resv_start_op = IPVS_CMD_FLUSH + 1, }; static int __init ip_vs_genl_register(void) diff --git a/net/netlabel/netlabel_calipso.c b/net/netlabel/netlabel_calipso.c index 91a19c3ea1a3..f1d5b8465217 100644 --- a/net/netlabel/netlabel_calipso.c +++ b/net/netlabel/netlabel_calipso.c @@ -344,6 +344,7 @@ static struct genl_family netlbl_calipso_gnl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = netlbl_calipso_ops, .n_small_ops = ARRAY_SIZE(netlbl_calipso_ops), + .resv_start_op = NLBL_CALIPSO_C_LISTALL + 1, }; /* NetLabel Generic NETLINK Protocol Functions diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index 894e6b8f1a86..fa08ee75ac06 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -767,6 +767,7 @@ static struct genl_family netlbl_cipsov4_gnl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = netlbl_cipsov4_ops, .n_small_ops = ARRAY_SIZE(netlbl_cipsov4_ops), + .resv_start_op = NLBL_CIPSOV4_C_LISTALL + 1, }; /* diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 032b7d7b32c7..689eaa2afbec 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -826,6 +826,7 @@ static struct genl_family netlbl_mgmt_gnl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = netlbl_mgmt_genl_ops, .n_small_ops = ARRAY_SIZE(netlbl_mgmt_genl_ops), + .resv_start_op = NLBL_MGMT_C_VERSION + 1, }; /* diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 0555dffd80e0..9996883bf2b7 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1374,6 +1374,7 @@ static struct genl_family netlbl_unlabel_gnl_family __ro_after_init = { .module = THIS_MODULE, .small_ops = netlbl_unlabel_genl_ops, .n_small_ops = ARRAY_SIZE(netlbl_unlabel_genl_ops), + .resv_start_op = NLBL_UNLABEL_C_STATICLISTDEF + 1, }; /* diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 76aed0571e3a..7c136de117eb 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -757,6 +757,9 @@ static int genl_family_rcv_msg(const struct genl_family *family, if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; + if (hdr->cmd >= family->resv_start_op && hdr->reserved) + return -EINVAL; + if (genl_get_cmd(hdr->cmd, family, &op)) return -EOPNOTSUPP; @@ -1348,6 +1351,7 @@ static struct genl_family genl_ctrl __ro_after_init = { .module = THIS_MODULE, .ops = genl_ctrl_ops, .n_ops = ARRAY_SIZE(genl_ctrl_ops), + .resv_start_op = CTRL_CMD_GETPOLICY + 1, .mcgrps = genl_ctrl_groups, .n_mcgrps = ARRAY_SIZE(genl_ctrl_groups), .id = GENL_ID_CTRL, diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 7c62417ccfd7..9d91087b9399 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -1783,6 +1783,7 @@ static struct genl_family nfc_genl_family __ro_after_init = { .module = THIS_MODULE, .ops = nfc_genl_ops, .n_ops = ARRAY_SIZE(nfc_genl_ops), + .resv_start_op = NFC_CMD_DEACTIVATE_TARGET + 1, .mcgrps = nfc_genl_mcgrps, .n_mcgrps = ARRAY_SIZE(nfc_genl_mcgrps), }; diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 4e70df91d0f2..48e8f5c29b67 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -2283,6 +2283,7 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = ct_limit_genl_ops, .n_small_ops = ARRAY_SIZE(ct_limit_genl_ops), + .resv_start_op = OVS_CT_LIMIT_CMD_GET + 1, .mcgrps = &ovs_ct_limit_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index e4667700336b..8f49e2359a1b 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -692,6 +692,7 @@ static struct genl_family dp_packet_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = dp_packet_genl_ops, .n_small_ops = ARRAY_SIZE(dp_packet_genl_ops), + .resv_start_op = OVS_PACKET_CMD_EXECUTE + 1, .module = THIS_MODULE, }; @@ -1509,6 +1510,7 @@ static struct genl_family dp_flow_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = dp_flow_genl_ops, .n_small_ops = ARRAY_SIZE(dp_flow_genl_ops), + .resv_start_op = OVS_FLOW_CMD_SET + 1, .mcgrps = &ovs_dp_flow_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, @@ -2051,6 +2053,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = dp_datapath_genl_ops, .n_small_ops = ARRAY_SIZE(dp_datapath_genl_ops), + .resv_start_op = OVS_DP_CMD_SET + 1, .mcgrps = &ovs_dp_datapath_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index 04a060ac7fdf..51111a9009bd 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -720,6 +720,7 @@ struct genl_family dp_meter_genl_family __ro_after_init = { .parallel_ops = true, .small_ops = dp_meter_genl_ops, .n_small_ops = ARRAY_SIZE(dp_meter_genl_ops), + .resv_start_op = OVS_METER_CMD_GET + 1, .mcgrps = &ovs_meter_multicast_group, .n_mcgrps = 1, .module = THIS_MODULE, diff --git a/net/psample/psample.c b/net/psample/psample.c index 118d5d2a81a0..81a794e36f53 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -115,6 +115,7 @@ static struct genl_family psample_nl_family __ro_after_init = { .mcgrps = psample_nl_mcgrps, .small_ops = psample_nl_ops, .n_small_ops = ARRAY_SIZE(psample_nl_ops), + .resv_start_op = PSAMPLE_CMD_GET_GROUP + 1, .n_mcgrps = ARRAY_SIZE(psample_nl_mcgrps), }; diff --git a/net/smc/smc_netlink.c b/net/smc/smc_netlink.c index c5a62f6f52ba..621c46c70073 100644 --- a/net/smc/smc_netlink.c +++ b/net/smc/smc_netlink.c @@ -142,7 +142,8 @@ struct genl_family smc_gen_nl_family __ro_after_init = { .netnsok = true, .module = THIS_MODULE, .ops = smc_gen_nl_ops, - .n_ops = ARRAY_SIZE(smc_gen_nl_ops) + .n_ops = ARRAY_SIZE(smc_gen_nl_ops), + .resv_start_op = SMC_NETLINK_DISABLE_HS_LIMITATION + 1, }; int __init smc_nl_init(void) diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 4c3bf6db7038..25fb2fd186e2 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -715,7 +715,8 @@ static struct genl_family smc_pnet_nl_family __ro_after_init = { .netnsok = true, .module = THIS_MODULE, .ops = smc_pnet_ops, - .n_ops = ARRAY_SIZE(smc_pnet_ops) + .n_ops = ARRAY_SIZE(smc_pnet_ops), + .resv_start_op = SMC_PNETID_FLUSH + 1, }; bool smc_pnet_is_ndev_pnetid(struct net *net, u8 *pnetid) diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index c447cb5f879e..e8fd257c0e68 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -294,6 +294,7 @@ struct genl_family tipc_genl_family __ro_after_init = { .module = THIS_MODULE, .ops = tipc_genl_v2_ops, .n_ops = ARRAY_SIZE(tipc_genl_v2_ops), + .resv_start_op = TIPC_NL_ADDR_LEGACY_GET + 1, }; int __init tipc_netlink_start(void) diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 0749df80454d..fc68733673ba 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -1357,6 +1357,7 @@ static struct genl_family tipc_genl_compat_family __ro_after_init = { .module = THIS_MODULE, .small_ops = tipc_genl_compat_ops, .n_small_ops = ARRAY_SIZE(tipc_genl_compat_ops), + .resv_start_op = TIPC_GENL_CMD + 1, }; int __init tipc_netlink_compat_start(void) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index dad88d231d56..e0087176796c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -17237,6 +17237,7 @@ static struct genl_family nl80211_fam __ro_after_init = { .n_ops = ARRAY_SIZE(nl80211_ops), .small_ops = nl80211_small_ops, .n_small_ops = ARRAY_SIZE(nl80211_small_ops), + .resv_start_op = NL80211_CMD_REMOVE_LINK_STA + 1, .mcgrps = nl80211_mcgrps, .n_mcgrps = ARRAY_SIZE(nl80211_mcgrps), .parallel_ops = true, -- cgit v1.2.3