After some experimenting it will fault all the mapped pages, causing the VM subsystem to try to back them. In Linux 4.4+ there is an a flag to `mlockall(2)` called "MCL_ONFAULT" which does not do that and instead locks the pages as they become backed.

    $ cat wheres-the-ram.c
    #! /home/rkeene/bin/c
    #include <sys/mman.h>
    #include <stdlib.h>
    #include <stdio.h>
    
    int main(int argc, char **argv) {
            unsigned char *buffer;
            int mla_ret;
    
            mla_ret = mlockall(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT);
            if (mla_ret != 0) {
                    perror("mlockall");
    
                    return(1);
            }
    
            buffer = malloc(1024LLU * 1024LLU * 1024LLU * 32LLU);
            if (!buffer) {
                    perror("malloc");
    
                    return(1);
            }
    
            buffer[0] = 1;
            buffer[1] = buffer[0];
            buffer[2] = buffer[3];
    
            puts("Success !");
    
            return(0);
    }
    $ sudo ./wheres-the-ram.c
    Success !
    $ free -g
                  total        used        free      shared  buff/cache   available
    Mem:             14           1           5           0           7          13
    Swap:             0           0           0
    $