On Thu, 27 Feb 2020 16:19:49 +0200
"Tzvetomir Stoyanov (VMware)" <tz.stoyanov@xxxxxxxxx> wrote:
> From: Tzvetomir Stoyanov <tstoyanov@xxxxxxxxxx>
>
> In order to match host and guest events, a mapping between guest VCPU
> and the host task, running this VCPU is needed. Extended existing
> struct guest to hold such mapping and added logic in read_qemu_guests()
> function to initialize it. Implemented a new internal API,
> get_guest_vcpu_pid(), to retrieve VCPU-task mapping for given VM.
>
> Signed-off-by: Tzvetomir Stoyanov <tstoyanov@xxxxxxxxxx>
> ---
> tracecmd/include/trace-local.h | 2 +
> tracecmd/trace-record.c | 77 ++++++++++++++++++++++++++++++++++
> 2 files changed, 79 insertions(+)
>
> diff --git a/tracecmd/include/trace-local.h b/tracecmd/include/trace-local.h
> index 29f27793..a5cf0640 100644
> --- a/tracecmd/include/trace-local.h
> +++ b/tracecmd/include/trace-local.h
> @@ -247,6 +247,8 @@ void update_first_instance(struct buffer_instance *instance, int topt);
>
> void show_instance_file(struct buffer_instance *instance, const char *name);
>
> +int get_guest_vcpu_pid(unsigned int guest_cid, unsigned int guest_vcpu);
> +
> /* moved from trace-cmd.h */
> void tracecmd_create_top_instance(char *name);
> void tracecmd_remove_instances(void);
> diff --git a/tracecmd/trace-record.c b/tracecmd/trace-record.c
> index 28fe31b7..4370c964 100644
> --- a/tracecmd/trace-record.c
> +++ b/tracecmd/trace-record.c
> @@ -3035,11 +3035,30 @@ struct guest {
> char *name;
> int cid;
> int pid;
> + int cpu_max;
> + int *cpu_pid;
> };
>
> static struct guest *guests;
> static size_t guests_len;
>
> +static int set_vcpu_pid_mapping(struct guest *guest, int cpu, int pid)
> +{
> + int *cpu_pid;
> +
> + if (cpu < 0 || pid < 0)
> + return -1;
This check makes the check before its call not needed (see below).
> + if (cpu >= guest->cpu_max) {
> + cpu_pid = realloc(guest->cpu_pid, (cpu + 1) * sizeof(int));
It is possible that the cpu numbers may be sparse, which means we should we
should probably initialize the new numbers as...
> + if (!cpu_pid)
> + return -1;
/* Handle sparse CPU numbers */
for (i = guest->cpu_max; i < cpu; i++)
guest->cpu_pid[i] = -1;
Note, the above wont loop at all if there's no sparse CPUs (missing
numbers).
> + guest->cpu_max = cpu + 1;
> + guest->cpu_pid = cpu_pid;
> + }
> + guest->cpu_pid[cpu] = pid;
> + return 0;
> +}
> +
> static char *get_qemu_guest_name(char *arg)
> {
> char *tok, *end = arg;
> @@ -3052,6 +3071,46 @@ static char *get_qemu_guest_name(char *arg)
> return arg;
> }
>
> +static void read_qemu_guests_pids(char *guest_task, struct guest *guest)
Probably should return a status.
> +{
> + struct dirent *entry;
> + char path[PATH_MAX];
> + char *buf = NULL;
> + size_t n = 0;
> + long int vcpu;
> + long int pid;
"int" is not needed. Just "long" is good enough.
long vcpu;
long pid;
Although, I doubt there will be more than 4 billion of either of these, so
they should probably be just "int". Which means you don't need the INT_MAX
checks.
> + DIR *dir;
> + FILE *f;
> +
> + snprintf(path, sizeof(path), "/proc/%s/task", guest_task);
> + dir = opendir(path);
> + if (!dir)
> + return;
> +
> + while ((entry = readdir(dir))) {
> + if (!(entry->d_type == DT_DIR && is_digits(entry->d_name)))
> + continue;
> +
> + snprintf(path, sizeof(path), "/proc/%s/task/%s/comm",
> + guest_task, entry->d_name);
> + f = fopen(path, "r");
> + if (!f)
> + continue;
> +
> + if (getline(&buf, &n, f) >= 0 &&
> + strncmp(buf, "CPU ", 4) == 0) {
> + vcpu = strtol(buf + 4, NULL, 10);
> + pid = strtol(entry->d_name, NULL, 10);
> + if (vcpu < INT_MAX && pid < INT_MAX &&
> + vcpu >= 0 && pid >= 0)
The vcpu >= 0 && pid >= 0 are not needed due to the check in the function.
> + set_vcpu_pid_mapping(guest, vcpu, pid);
Probably should check the return status of this function, and report a
warning if it fails.
> + }
> +
> + fclose(f);
> + }
> + free(buf);
> +}
> +
> static void read_qemu_guests(void)
> {
> static bool initialized;
> @@ -3115,6 +3174,8 @@ static void read_qemu_guests(void)
> if (!is_qemu)
> goto next;
>
> + read_qemu_guests_pids(entry->d_name, &guest);
Should probably check the status of the above function. Die on error?
> +
> guests = realloc(guests, (guests_len + 1) * sizeof(*guests));
> if (!guests)
> die("Can not allocate guest buffer");
> @@ -3160,6 +3221,22 @@ static char *parse_guest_name(char *guest, int *cid, int *port)
> return guest;
> }
>
> +int get_guest_vcpu_pid(unsigned int guest_cid, unsigned int guest_vcpu)
> +{
> + int i;
> +
> + if (!guests)
> + return -1;
> +
> + for (i = 0; i < guests_len; i++) {
> + if (!guests[i].cpu_pid || guest_vcpu >= guests[i].cpu_max)
As a cpu_pid may be zero (unlikely), and the code I showed above
initialized sparse cpus as -1, then this should be guests[i].cpu_pid < 0.
-- Steve
> + continue;
> + if (guest_cid == guests[i].cid)
> + return guests[i].cpu_pid[guest_vcpu];
> + }
> + return -1;
> +}
> +
> static void set_prio(int prio)
> {
> struct sched_param sp;
|