From cc82b3dcc6a8fa259fbda12ab00d6fc00908a49e Mon Sep 17 00:00:00 2001 From: Yiyang Chen Date: Mon, 30 Mar 2026 03:00:41 +0800 Subject: [PATCH] tools/accounting: handle truncated taskstats netlink messages procacct and getdelays use a fixed receive buffer for taskstats generic netlink messages. A multi-threaded process exit can emit a single PID+TGID notification large enough to exceed that buffer on newer kernels. Switch to recvmsg() so MSG_TRUNC is detected explicitly, increase the message buffer size, and report truncated datagrams clearly instead of misparsing them as fatal netlink errors. Also print the taskstats version in debug output to make version mismatches easier to diagnose while inspecting taskstats traffic. Link: https://lkml.kernel.org/r/520308bb4cbbaf8dc2c7296b5f60f11e12fb30a5.1774810498.git.cyyzero16@gmail.com Signed-off-by: Yiyang Chen Cc: Balbir Singh Cc: Dr. Thomas Orgis Cc: Fan Yu Cc: Wang Yaxin Cc: Signed-off-by: Andrew Morton --- tools/accounting/getdelays.c | 41 ++++++++++++++++++++++++++++++++---- tools/accounting/procacct.c | 40 +++++++++++++++++++++++++++++++---- 2 files changed, 73 insertions(+), 8 deletions(-) diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 50792df277077..368a622ca0273 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -60,7 +60,7 @@ int print_task_context_switch_counts; } /* Maximum size of response requested or message sent */ -#define MAX_MSG_SIZE 1024 +#define MAX_MSG_SIZE 2048 /* Maximum number of cpus expected to be specified in a cpumask */ #define MAX_CPUS 32 @@ -115,6 +115,32 @@ error: return -1; } +static int recv_taskstats_msg(int sd, struct msgtemplate *msg) +{ + struct sockaddr_nl nladdr; + struct iovec iov = { + .iov_base = msg, + .iov_len = sizeof(*msg), + }; + struct msghdr hdr = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1, + }; + int ret; + + ret = recvmsg(sd, &hdr, 0); + if (ret < 0) + return -1; + if (hdr.msg_flags & MSG_TRUNC) { + errno = EMSGSIZE; + return -1; + } + + return ret; +} + static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, __u8 genl_cmd, __u16 nla_type, @@ -633,12 +659,16 @@ int main(int argc, char *argv[]) } do { - rep_len = recv(nl_sd, &msg, sizeof(msg), 0); + rep_len = recv_taskstats_msg(nl_sd, &msg); PRINTF("received %d bytes\n", rep_len); if (rep_len < 0) { - fprintf(stderr, "nonfatal reply error: errno %d\n", - errno); + if (errno == EMSGSIZE) + fprintf(stderr, + "dropped truncated taskstats netlink message, please increase MAX_MSG_SIZE\n"); + else + fprintf(stderr, "nonfatal reply error: errno %d\n", + errno); continue; } if (msg.n.nlmsg_type == NLMSG_ERROR || @@ -680,6 +710,9 @@ int main(int argc, char *argv[]) printf("TGID\t%d\n", rtid); break; case TASKSTATS_TYPE_STATS: + PRINTF("version %u\n", + ((struct taskstats *) + NLA_DATA(na))->version); if (print_delays) print_delayacct((struct taskstats *) NLA_DATA(na)); if (print_io_accounting) diff --git a/tools/accounting/procacct.c b/tools/accounting/procacct.c index e8dee05a62646..46e5986ad9277 100644 --- a/tools/accounting/procacct.c +++ b/tools/accounting/procacct.c @@ -71,7 +71,7 @@ int print_task_context_switch_counts; } /* Maximum size of response requested or message sent */ -#define MAX_MSG_SIZE 1024 +#define MAX_MSG_SIZE 2048 /* Maximum number of cpus expected to be specified in a cpumask */ #define MAX_CPUS 32 @@ -121,6 +121,32 @@ error: return -1; } +static int recv_taskstats_msg(int sd, struct msgtemplate *msg) +{ + struct sockaddr_nl nladdr; + struct iovec iov = { + .iov_base = msg, + .iov_len = sizeof(*msg), + }; + struct msghdr hdr = { + .msg_name = &nladdr, + .msg_namelen = sizeof(nladdr), + .msg_iov = &iov, + .msg_iovlen = 1, + }; + int ret; + + ret = recvmsg(sd, &hdr, 0); + if (ret < 0) + return -1; + if (hdr.msg_flags & MSG_TRUNC) { + errno = EMSGSIZE; + return -1; + } + + return ret; +} + static int send_cmd(int sd, __u16 nlmsg_type, __u32 nlmsg_pid, __u8 genl_cmd, __u16 nla_type, @@ -239,6 +265,8 @@ void handle_aggr(int mother, struct nlattr *na, int fd) PRINTF("TGID\t%d\n", rtid); break; case TASKSTATS_TYPE_STATS: + PRINTF("version %u\n", + ((struct taskstats *)NLA_DATA(na))->version); if (mother == TASKSTATS_TYPE_AGGR_PID) print_procacct((struct taskstats *) NLA_DATA(na)); if (fd) { @@ -347,12 +375,16 @@ int main(int argc, char *argv[]) } do { - rep_len = recv(nl_sd, &msg, sizeof(msg), 0); + rep_len = recv_taskstats_msg(nl_sd, &msg); PRINTF("received %d bytes\n", rep_len); if (rep_len < 0) { - fprintf(stderr, "nonfatal reply error: errno %d\n", - errno); + if (errno == EMSGSIZE) + fprintf(stderr, + "dropped truncated taskstats netlink message, please increase MAX_MSG_SIZE\n"); + else + fprintf(stderr, "nonfatal reply error: errno %d\n", + errno); continue; } if (msg.n.nlmsg_type == NLMSG_ERROR || -- 2.47.3