[PATCH v1 2/2] tools/lib/call: cache up to 4 pages in hypercall bounce buffers

[Edwin Török <edwin.torok@xxxxxxxxxx>]

During migration there are a lot of mmap/munmap calls,
because `xc_get_pfn_type_batch` exceeds the default hypercall bounce
buffer cache size, and needs to allocate every time it is called.

`munmap` is slow, especially in a PV Dom0 (takes an emulation fault),
so is best avoided.

Eventually it'd be good if the memory pool from  xmalloc_tlsf.c
was reused here, but for now make it handle the commonly encountered
sizes (so far up to 4 pages).

Signed-off-by: Edwin Török <edwin.torok@xxxxxxxxxx>
---
 tools/libs/call/buffer.c  | 28 ++++++++++++++++------------
 tools/libs/call/core.c    |  3 ++-
 tools/libs/call/private.h |  8 +++++---
 3 files changed, 23 insertions(+), 16 deletions(-)

diff --git a/tools/libs/call/buffer.c b/tools/libs/call/buffer.c
index 2579b8c719..5601ee83ba 100644
--- a/tools/libs/call/buffer.c
+++ b/tools/libs/call/buffer.c
@@ -56,13 +56,13 @@ static void *cache_alloc(xencall_handle *xcall, size_t 
nr_pages)
     if ( xcall->buffer_current_allocations > xcall->buffer_maximum_allocations 
)
         xcall->buffer_maximum_allocations = xcall->buffer_current_allocations;
 
-    if ( nr_pages > 1 )
+    if ( nr_pages > ARRAY_SIZE(xcall->buffer_cache) )
     {
         xcall->buffer_cache_toobig++;
     }
-    else if ( xcall->buffer_cache_nr > 0 )
+    else if ( xcall->buffer_cache_nr[nr_pages-1] > 0 )
     {
-        p = xcall->buffer_cache[--xcall->buffer_cache_nr];
+        p = 
xcall->buffer_cache[nr_pages-1][--xcall->buffer_cache_nr[nr_pages-1]];
         xcall->buffer_cache_hits++;
     }
     else
@@ -84,10 +84,10 @@ static int cache_free(xencall_handle *xcall, void *p, 
size_t nr_pages)
     xcall->buffer_total_releases++;
     xcall->buffer_current_allocations--;
 
-    if ( nr_pages == 1 &&
-         xcall->buffer_cache_nr < BUFFER_CACHE_SIZE )
+    if ( nr_pages && nr_pages < ARRAY_SIZE(xcall->buffer_cache) &&
+         xcall->buffer_cache_nr[nr_pages-1] < BUFFER_CACHE_SIZE )
     {
-        xcall->buffer_cache[xcall->buffer_cache_nr++] = p;
+        xcall->buffer_cache[nr_pages-1][xcall->buffer_cache_nr[nr_pages-1]++] 
= p;
         rc = 1;
     }
 
@@ -108,17 +108,21 @@ void buffer_release_cache(xencall_handle *xcall)
     DBGPRINTF("current allocations:%d maximum allocations:%d",
               xcall->buffer_current_allocations,
               xcall->buffer_maximum_allocations);
-    DBGPRINTF("cache current size:%d",
-              xcall->buffer_cache_nr);
+    for ( unsigned i = 0; i < ARRAY_SIZE(xcall->buffer_cache_nr); ++i) {
+        DBGPRINTF("cache current size[%u pages]:%d", i+1,
+                xcall->buffer_cache_nr[i]);
+    }
     DBGPRINTF("cache hits:%d misses:%d toobig:%d",
               xcall->buffer_cache_hits,
               xcall->buffer_cache_misses,
               xcall->buffer_cache_toobig);
 
-    while ( xcall->buffer_cache_nr > 0 )
-    {
-        p = xcall->buffer_cache[--xcall->buffer_cache_nr];
-        osdep_free_pages(xcall, p, 1);
+    for ( unsigned i = 0; i < ARRAY_SIZE(xcall->buffer_cache_nr); ++i) {
+        while ( xcall->buffer_cache_nr[i] > 0 )
+        {
+            p = xcall->buffer_cache[i][--xcall->buffer_cache_nr[i]];
+            osdep_free_pages(xcall, p, 1);
+        }
     }
 
     cache_unlock(xcall);
diff --git a/tools/libs/call/core.c b/tools/libs/call/core.c
index 02c4f8e1ae..dd8877c1a0 100644
--- a/tools/libs/call/core.c
+++ b/tools/libs/call/core.c
@@ -14,6 +14,7 @@
  */
 
 #include <stdlib.h>
+#include <string.h>
 
 #include "private.h"
 
@@ -44,7 +45,7 @@ xencall_handle *xencall_open(xentoollog_logger *logger, 
unsigned open_flags)
     xentoolcore__register_active_handle(&xcall->tc_ah);
 
     xcall->flags = open_flags;
-    xcall->buffer_cache_nr = 0;
+    memset(xcall->buffer_cache_nr, 0, sizeof(xcall->buffer_cache_nr));
 
     xcall->buffer_total_allocations = 0;
     xcall->buffer_total_releases = 0;
diff --git a/tools/libs/call/private.h b/tools/libs/call/private.h
index 9c3aa432ef..7aca526abe 100644
--- a/tools/libs/call/private.h
+++ b/tools/libs/call/private.h
@@ -31,13 +31,15 @@ struct xencall_handle {
     Xentoolcore__Active_Handle tc_ah;
 
     /*
-     * A simple cache of unused, single page, hypercall buffers
+     * A simple cache of unused, small, hypercall buffers
+     * buffer_cache[i]'s size is (i-1) pages
      *
      * Protected by a global lock.
      */
 #define BUFFER_CACHE_SIZE 4
-    int buffer_cache_nr;
-    void *buffer_cache[BUFFER_CACHE_SIZE];
+#define BUFFER_CACHE_NRPAGES 4
+    int buffer_cache_nr[BUFFER_CACHE_NRPAGES];
+    void *buffer_cache[BUFFER_CACHE_NRPAGES][BUFFER_CACHE_SIZE];
 
     /*
      * Hypercall buffer statistics. All protected by the global
-- 
2.47.3