Re: [RFC PATCH QEMU 2/3] plugins: Add cache miss reporting over a socket.

["Alex Bennée" <alex.bennee@linaro.org>]

Jonathan Cameron <Jonathan.Cameron@huawei.com> writes:

> This allows an external program to act as a hotness tracker.
>
> Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
> ---
>  contrib/plugins/cache.c | 75 +++++++++++++++++++++++++++++++++++++----
>  1 file changed, 68 insertions(+), 7 deletions(-)
>
> diff --git a/contrib/plugins/cache.c b/contrib/plugins/cache.c
> index 7baff86860..5af1e6559c 100644
> --- a/contrib/plugins/cache.c
> +++ b/contrib/plugins/cache.c
> @@ -7,10 +7,17 @@
>  
>  #include <inttypes.h>
>  #include <stdio.h>
> +#include <unistd.h>
>  #include <glib.h>
> +#include <sys/socket.h>
> +#include <arpa/inet.h>
>  
>  #include <qemu-plugin.h>
>  
> +static int client_socket = -1;
> +static uint64_t missfilterbase;
> +static uint64_t missfiltersize;
> +
>  #define STRTOLL(x) g_ascii_strtoll(x, NULL, 10)
>  
>  QEMU_PLUGIN_EXPORT int qemu_plugin_version = QEMU_PLUGIN_VERSION;
> @@ -104,6 +111,7 @@ static Cache **l2_ucaches;
>  static GMutex *l1_dcache_locks;
>  static GMutex *l1_icache_locks;
>  static GMutex *l2_ucache_locks;
> +static GMutex *socket_lock;
>  
>  static uint64_t l1_dmem_accesses;
>  static uint64_t l1_imem_accesses;
> @@ -385,6 +393,21 @@ static bool access_cache(Cache *cache, uint64_t addr)
>      return false;
>  }
>  
> +static void miss(uint64_t paddr)
> +{
> +    if (client_socket < 0) {
> +        return;
> +    }
> +
> +    if (paddr < missfilterbase || paddr >= missfilterbase + missfiltersize) {
> +        return;
> +    }
> +
> +    g_mutex_lock(socket_lock);
> +    send(client_socket, &paddr, sizeof(paddr), 0);
> +    g_mutex_unlock(socket_lock);
> +}
> +
>  static void vcpu_mem_access(unsigned int vcpu_index, qemu_plugin_meminfo_t info,
>                              uint64_t vaddr, void *userdata)
>  {
> @@ -395,9 +418,6 @@ static void vcpu_mem_access(unsigned int vcpu_index, qemu_plugin_meminfo_t info,
>      bool hit_in_l1;
>  
>      hwaddr = qemu_plugin_get_hwaddr(info, vaddr);
> -    if (hwaddr && qemu_plugin_hwaddr_is_io(hwaddr)) {
> -        return;
> -    }
>  
>      effective_addr = hwaddr ? qemu_plugin_hwaddr_phys_addr(hwaddr) : vaddr;
>      cache_idx = vcpu_index % cores;
> @@ -412,7 +432,11 @@ static void vcpu_mem_access(unsigned int vcpu_index, qemu_plugin_meminfo_t info,
>      l1_dcaches[cache_idx]->accesses++;
>      g_mutex_unlock(&l1_dcache_locks[cache_idx]);
>  
> -    if (hit_in_l1 || !use_l2) {
> +    if (hit_in_l1) {
> +        return;
> +    }
> +    if (!use_l2) {
> +        miss(effective_addr);
>          /* No need to access L2 */
>          return;
>      }
> @@ -422,6 +446,7 @@ static void vcpu_mem_access(unsigned int vcpu_index, qemu_plugin_meminfo_t info,
>          insn = userdata;
>          __atomic_fetch_add(&insn->l2_misses, 1, __ATOMIC_SEQ_CST);
>          l2_ucaches[cache_idx]->misses++;
> +        miss(effective_addr);
>      }
>      l2_ucaches[cache_idx]->accesses++;
>      g_mutex_unlock(&l2_ucache_locks[cache_idx]);
> @@ -447,8 +472,12 @@ static void vcpu_insn_exec(unsigned int vcpu_index, void *userdata)
>      l1_icaches[cache_idx]->accesses++;
>      g_mutex_unlock(&l1_icache_locks[cache_idx]);
>  
> -    if (hit_in_l1 || !use_l2) {
> -        /* No need to access L2 */
> +    if (hit_in_l1) {
> +        return;
> +    }
> +
> +    if (!use_l2) {
> +        miss(insn_addr);
>          return;
>      }
>  
> @@ -739,14 +768,16 @@ QEMU_PLUGIN_EXPORT
>  int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
>                          int argc, char **argv)
>  {
> -    int i;
> +    int i, port;
>      int l1_iassoc, l1_iblksize, l1_icachesize;
>      int l1_dassoc, l1_dblksize, l1_dcachesize;
>      int l2_assoc, l2_blksize, l2_cachesize;
> +    struct sockaddr_in server_addr;
>  
>      limit = 32;
>      sys = info->system_emulation;
>  
> +    port = -1;
>      l1_dassoc = 8;
>      l1_dblksize = 64;
>      l1_dcachesize = l1_dblksize * l1_dassoc * 32;
> @@ -808,11 +839,39 @@ int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
>                  fprintf(stderr, "invalid eviction policy: %s\n", opt);
>                  return -1;
>              }
> +        } else if (g_strcmp0(tokens[0], "port") == 0) {
> +            port = STRTOLL(tokens[1]);
> +        } else if (g_strcmp0(tokens[0], "missfilterbase") == 0) {
> +            missfilterbase = STRTOLL(tokens[1]);
> +        } else if (g_strcmp0(tokens[0], "missfiltersize") == 0) {
> +            missfiltersize = STRTOLL(tokens[1]);
>          } else {
>              fprintf(stderr, "option parsing failed: %s\n", opt);
>              return -1;
>          }
>      }
> +    if (port >= -1) {
> +        uint64_t paddr = 42; /* hello, I'm a provider */
> +        client_socket = socket(AF_INET, SOCK_STREAM, IPPROTO_TCP);
> +        if (client_socket < 0) {
> +            printf("failed to create a socket\n");
> +            return -1;
> +        }
> +        printf("Cache miss reported on on %lx size %lx\n",
> +               missfilterbase, missfiltersize);
> +        memset((char *)&server_addr, 0, sizeof(server_addr));
> +        server_addr.sin_family = AF_INET;
> +        server_addr.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
> +        server_addr.sin_port = htons(port);
> +
> +        if (connect(client_socket, (struct sockaddr *)&server_addr,
> +                    sizeof(server_addr)) < 0) {
> +            close(client_socket);
> +            return -1;
> +        }
> +        /* Let it know we are a data provider */
> +        send(client_socket, &paddr, sizeof(paddr), 0);
> +    }

No particular objections to the patch as is. I do wonder if it would be
worth exposing a chardev pipe to plugins so we could take advantage of
QEMU's flexible redirection handling.

But not a blocker for this.

>  
>      policy_init();
>  
> @@ -840,6 +899,8 @@ int qemu_plugin_install(qemu_plugin_id_t id, const qemu_info_t *info,
>          return -1;
>      }
>  
> +    socket_lock = g_new0(GMutex, 1);
> +
>      l1_dcache_locks = g_new0(GMutex, cores);
>      l1_icache_locks = g_new0(GMutex, cores);
>      l2_ucache_locks = use_l2 ? g_new0(GMutex, cores) : NULL;

-- 
Alex Bennée
Virtualisation Tech Lead @ Linaro