libxc: maintain a small, per-handle, cache of hypercall buffer memory

Constantly m(un)locking memory can have significant overhead on
systems with large numbers of CPUs. This was previously fixed by
20841:fbe8f32fa257 but this was dropped during the transition to
hypercall buffers.

Introduce a small cache of single page hypercall buffer allocations
which can be resused to avoid this overhead.

Add some statistics tracking to the hypercall buffer allocations.

The cache size of 4 was chosen based on these statistics since they
indicated that 2 pages was sufficient to satisfy all concurrent single
page hypercall buffer allocations seen during "xl create", "xl
shutdown" and "xl destroy" of both a PV and HVM guest therefore 4
pages should cover the majority of important cases.

This fixes http://bugzilla.xensource.com/bugzilla/show_bug.cgi?id=1719.

Signed-off-by: Ian Campbell <ian.campbell@citrix.com>
Reported-by: Zheng, Shaohui <shaohui.zheng@intel.com>
Tested-by: Haitao Shan <maillists.shan@gmail.com>
Committed-by: Ian Jackson <ian.jackson@eu.citrix.com>

3 files changed, 162 insertions, 19 deletions

diff --git a/tools/libxc/xc_hcall_buf.c b/tools/libxc/xc_hcall_buf.c
index 032997f125..d817d90ca1 100644
--- a/tools/libxc/xc_hcall_buf.c
+++ b/tools/libxc/xc_hcall_buf.c
@@ -18,6 +18,7 @@
 
 #include <stdlib.h>
 #include <malloc.h>
+#include <pthread.h>
 
 #include "xc_private.h"
 #include "xg_private.h"
@@ -28,31 +29,137 @@ xc_hypercall_buffer_t XC__HYPERCALL_BUFFER_NAME(HYPERCALL_BUFFER_NULL) = {
     HYPERCALL_BUFFER_INIT_NO_BOUNCE
 };
 
+pthread_mutex_t hypercall_buffer_cache_mutex = PTHREAD_MUTEX_INITIALIZER;
+
+static void hypercall_buffer_cache_lock(xc_interface *xch)
+{
+    if ( xch->flags & XC_OPENFLAG_NON_REENTRANT )
+        return;
+    pthread_mutex_lock(&hypercall_buffer_cache_mutex);
+}
+
+static void hypercall_buffer_cache_unlock(xc_interface *xch)
+{
+    if ( xch->flags & XC_OPENFLAG_NON_REENTRANT )
+        return;
+    pthread_mutex_unlock(&hypercall_buffer_cache_mutex);
+}
+
+static void *hypercall_buffer_cache_alloc(xc_interface *xch, int nr_pages)
+{
+    void *p = NULL;
+
+    hypercall_buffer_cache_lock(xch);
+
+    xch->hypercall_buffer_total_allocations++;
+    xch->hypercall_buffer_current_allocations++;
+    if ( xch->hypercall_buffer_current_allocations > xch->hypercall_buffer_maximum_allocations )
+        xch->hypercall_buffer_maximum_allocations = xch->hypercall_buffer_current_allocations;
+
+    if ( nr_pages > 1 )
+    {
+        xch->hypercall_buffer_cache_toobig++;
+    }
+    else if ( xch->hypercall_buffer_cache_nr > 0 )
+    {
+        p = xch->hypercall_buffer_cache[--xch->hypercall_buffer_cache_nr];
+        xch->hypercall_buffer_cache_hits++;
+    }
+    else
+    {
+        xch->hypercall_buffer_cache_misses++;
+    }
+
+    hypercall_buffer_cache_unlock(xch);
+
+    return p;
+}
+
+static int hypercall_buffer_cache_free(xc_interface *xch, void *p, int nr_pages)
+{
+    int rc = 0;
+
+    hypercall_buffer_cache_lock(xch);
+
+    xch->hypercall_buffer_total_releases++;
+    xch->hypercall_buffer_current_allocations--;
+
+    if ( nr_pages == 1 && xch->hypercall_buffer_cache_nr < HYPERCALL_BUFFER_CACHE_SIZE )
+    {
+        xch->hypercall_buffer_cache[xch->hypercall_buffer_cache_nr++] = p;
+        rc = 1;
+    }
+
+    hypercall_buffer_cache_unlock(xch);
+
+    return rc;
+}
+
+static void do_hypercall_buffer_free_pages(void *ptr, int nr_pages)
+{
+#ifndef __sun__
+    (void) munlock(ptr, nr_pages * PAGE_SIZE);
+#endif
+
+    free(ptr);
+}
+
+void xc__hypercall_buffer_cache_release(xc_interface *xch)
+{
+    void *p;
+
+    hypercall_buffer_cache_lock(xch);
+
+    DBGPRINTF("hypercall buffer: total allocations:%d total releases:%d",
+              xch->hypercall_buffer_total_allocations,
+              xch->hypercall_buffer_total_releases);
+    DBGPRINTF("hypercall buffer: current allocations:%d maximum allocations:%d",
+              xch->hypercall_buffer_current_allocations,
+              xch->hypercall_buffer_maximum_allocations);
+    DBGPRINTF("hypercall buffer: cache current size:%d",
+              xch->hypercall_buffer_cache_nr);
+    DBGPRINTF("hypercall buffer: cache hits:%d misses:%d toobig:%d",
+              xch->hypercall_buffer_cache_hits,
+              xch->hypercall_buffer_cache_misses,
+              xch->hypercall_buffer_cache_toobig);
+
+    while ( xch->hypercall_buffer_cache_nr > 0 )
+    {
+        p = xch->hypercall_buffer_cache[--xch->hypercall_buffer_cache_nr];
+        do_hypercall_buffer_free_pages(p, 1);
+    }
+
+    hypercall_buffer_cache_unlock(xch);
+}
+
 void *xc__hypercall_buffer_alloc_pages(xc_interface *xch, xc_hypercall_buffer_t *b, int nr_pages)
 {
     size_t size = nr_pages * PAGE_SIZE;
-    void *p;
+    void *p = hypercall_buffer_cache_alloc(xch, nr_pages);
+
+    if ( !p ) {
 #if defined(_POSIX_C_SOURCE) && !defined(__sun__)
-    int ret;
-    ret = posix_memalign(&p, PAGE_SIZE, size);
-    if (ret != 0)
-        return NULL;
+        int ret;
+        ret = posix_memalign(&p, PAGE_SIZE, size);
+        if (ret != 0)
+            return NULL;
 #elif defined(__NetBSD__) || defined(__OpenBSD__)
-    p = valloc(size);
+        p = valloc(size);
 #else
-    p = memalign(PAGE_SIZE, size);
+        p = memalign(PAGE_SIZE, size);
 #endif
 
-    if (!p)
-        return NULL;
+        if (!p)
+            return NULL;
 
 #ifndef __sun__
-    if ( mlock(p, size) < 0 )
-    {
-        free(p);
-        return NULL;
-    }
+        if ( mlock(p, size) < 0 )
+        {
+            free(p);
+            return NULL;
+        }
 #endif
+    }
 
     b->hbuf = p;
 
@@ -65,11 +172,8 @@ void xc__hypercall_buffer_free_pages(xc_interface *xch, xc_hypercall_buffer_t *b
     if ( b->hbuf == NULL )
         return;
 
-#ifndef __sun__
-    (void) munlock(b->hbuf, nr_pages * PAGE_SIZE);
-#endif
-
-    free(b->hbuf);
+    if ( !hypercall_buffer_cache_free(xch, b->hbuf, nr_pages) )
+        do_hypercall_buffer_free_pages(b->hbuf, nr_pages);
 }
 
 struct allocation_header {
diff --git a/tools/libxc/xc_private.c b/tools/libxc/xc_private.c
index 72ee07fd34..09c8f23ca5 100644
--- a/tools/libxc/xc_private.c
+++ b/tools/libxc/xc_private.c
@@ -126,6 +126,16 @@ static struct xc_interface_core *xc_interface_open_common(xentoollog_logger *log
     xch->error_handler   = logger;           xch->error_handler_tofree   = 0;
     xch->dombuild_logger = dombuild_logger;  xch->dombuild_logger_tofree = 0;
 
+    xch->hypercall_buffer_cache_nr = 0;
+
+    xch->hypercall_buffer_total_allocations = 0;
+    xch->hypercall_buffer_total_releases = 0;
+    xch->hypercall_buffer_current_allocations = 0;
+    xch->hypercall_buffer_maximum_allocations = 0;
+    xch->hypercall_buffer_cache_hits = 0;
+    xch->hypercall_buffer_cache_misses = 0;
+    xch->hypercall_buffer_cache_toobig = 0;
+
     xch->ops_handle = XC_OSDEP_OPEN_ERROR;
     xch->ops = NULL;
 
@@ -172,6 +182,8 @@ static int xc_interface_close_common(xc_interface *xch)
 {
     int rc = 0;
 
+    xc__hypercall_buffer_cache_release(xch);
+
     xtl_logger_destroy(xch->dombuild_logger_tofree);
     xtl_logger_destroy(xch->error_handler_tofree);
 
diff --git a/tools/libxc/xc_private.h b/tools/libxc/xc_private.h
index b01ca2419d..3687561df0 100644
--- a/tools/libxc/xc_private.h
+++ b/tools/libxc/xc_private.h
@@ -75,6 +75,28 @@ struct xc_interface_core {
     FILE *dombuild_logger_file;
     const char *currently_progress_reporting;
 
+    /*
+     * A simple cache of unused, single page, hypercall buffers
+     *
+     * Protected by a global lock.
+     */
+#define HYPERCALL_BUFFER_CACHE_SIZE 4
+    int hypercall_buffer_cache_nr;
+    void *hypercall_buffer_cache[HYPERCALL_BUFFER_CACHE_SIZE];
+
+    /*
+     * Hypercall buffer statistics. All protected by the global
+     * hypercall_buffer_cache lock.
+     */
+    int hypercall_buffer_total_allocations;
+    int hypercall_buffer_total_releases;
+    int hypercall_buffer_current_allocations;
+    int hypercall_buffer_maximum_allocations;
+    int hypercall_buffer_cache_hits;
+    int hypercall_buffer_cache_misses;
+    int hypercall_buffer_cache_toobig;
+
+    /* Low lovel OS interface */
     xc_osdep_info_t  osdep;
     xc_osdep_ops    *ops; /* backend operations */
     xc_osdep_handle  ops_handle; /* opaque data for xc_osdep_ops */
@@ -158,6 +180,11 @@ void xc__hypercall_bounce_post(xc_interface *xch, xc_hypercall_buffer_t *bounce)
 #define xc_hypercall_bounce_post(_xch, _name) xc__hypercall_bounce_post(_xch, HYPERCALL_BUFFER(_name))
 
 /*
+ * Release hypercall buffer cache
+ */
+void xc__hypercall_buffer_cache_release(xc_interface *xch);
+
+/*
  * Hypercall interfaces.
  */