[PATCH v4 10/15] util/mmap-alloc: Prepare for resizeable mmaps

[David Hildenbrand <david@redhat.com>]

When shrinking a mmap we want to re-reserve the already activated area.
When growing a memory region, we want to activate starting with a given
fd_offset. Prepare by allowing to pass these parameters.

Also, let's make sure we always process full pages, to avoid
unmapping/remapping pages that are already in use when
growing/shrinking. Add some asserts.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Igor Kotrasinski <i.kotrasinsk@partner.samsung.com>
Cc: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Greg Kurz <groug@kaod.org>
Cc: Murilo Opsfelder Araujo <muriloo@linux.ibm.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Cc: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 util/mmap-alloc.c | 34 +++++++++++++++++++++++-----------
 1 file changed, 23 insertions(+), 11 deletions(-)

diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c
index 8f40ef4fed..2767caa33b 100644
--- a/util/mmap-alloc.c
+++ b/util/mmap-alloc.c
@@ -83,12 +83,12 @@ size_t qemu_mempath_getpagesize(const char *mem_path)
 }
 
 /*
- * Reserve a new memory region of the requested size to be used for mapping
- * from the given fd (if any).
+ * Reserve a new memory region of the requested size or re-reserve parts
+ * of an activated region to be used for mapping from the given fd (if any).
  */
-static void *mmap_reserve(size_t size, int fd)
+static void *mmap_reserve(void *ptr, size_t size, int fd)
 {
-    int flags = MAP_PRIVATE;
+    int flags = MAP_PRIVATE | (ptr ? MAP_FIXED : 0);
 
 #if defined(__powerpc64__) && defined(__linux__)
     /*
@@ -111,20 +111,24 @@ static void *mmap_reserve(size_t size, int fd)
     flags |= MAP_ANONYMOUS;
 #endif
 
-    return mmap(0, size, PROT_NONE, flags, fd, 0);
+    return mmap(ptr, size, PROT_NONE, flags, fd, 0);
 }
 
 /*
  * Activate memory in a reserved region from the given fd (if any), to make
  * it accessible.
  */
-static void *mmap_activate(void *ptr, size_t size, int fd, bool shared,
-                           bool is_pmem)
+static void *mmap_activate(void *ptr, size_t size, int fd, size_t fd_offset,
+                           bool shared, bool is_pmem)
 {
     int map_sync_flags = 0;
     int flags = MAP_FIXED;
     void *activated_ptr;
 
+    if (fd == -1) {
+        fd_offset = 0;
+    }
+
     flags |= fd == -1 ? MAP_ANONYMOUS : 0;
     flags |= shared ? MAP_SHARED : MAP_PRIVATE;
     if (shared && is_pmem) {
@@ -132,7 +136,7 @@ static void *mmap_activate(void *ptr, size_t size, int fd, bool shared,
     }
 
     activated_ptr = mmap(ptr, size, PROT_READ | PROT_WRITE,
-                         flags | map_sync_flags, fd, 0);
+                         flags | map_sync_flags, fd, fd_offset);
     if (activated_ptr == MAP_FAILED && map_sync_flags) {
         if (errno == ENOTSUP) {
             char *proc_link = g_strdup_printf("/proc/self/fd/%d", fd);
@@ -154,7 +158,8 @@ static void *mmap_activate(void *ptr, size_t size, int fd, bool shared,
          * If mmap failed with MAP_SHARED_VALIDATE | MAP_SYNC, we will try
          * again without these flags to handle backwards compatibility.
          */
-        activated_ptr = mmap(ptr, size, PROT_READ | PROT_WRITE, flags, fd, 0);
+        activated_ptr = mmap(ptr, size, PROT_READ | PROT_WRITE, flags, fd,
+                             fd_offset);
     }
     return activated_ptr;
 }
@@ -176,16 +181,19 @@ void *qemu_ram_mmap(int fd,
                     bool is_pmem)
 {
     const size_t guard_pagesize = mmap_guard_pagesize(fd);
+    const size_t pagesize = qemu_fd_getpagesize(fd);
     size_t offset, total;
     void *ptr, *guardptr;
 
+    g_assert(QEMU_IS_ALIGNED(size, pagesize));
+
     /*
      * Note: this always allocates at least one extra page of virtual address
      * space, even if size is already aligned.
      */
     total = size + align;
 
-    guardptr = mmap_reserve(total, fd);
+    guardptr = mmap_reserve(NULL, total, fd);
     if (guardptr == MAP_FAILED) {
         return MAP_FAILED;
     }
@@ -196,7 +204,7 @@ void *qemu_ram_mmap(int fd,
 
     offset = QEMU_ALIGN_UP((uintptr_t)guardptr, align) - (uintptr_t)guardptr;
 
-    ptr = mmap_activate(guardptr + offset, size, fd, shared, is_pmem);
+    ptr = mmap_activate(guardptr + offset, size, fd, 0, shared, is_pmem);
     if (ptr == MAP_FAILED) {
         munmap(guardptr, total);
         return MAP_FAILED;
@@ -220,6 +228,10 @@ void *qemu_ram_mmap(int fd,
 
 void qemu_ram_munmap(int fd, void *ptr, size_t size)
 {
+    const size_t pagesize = qemu_fd_getpagesize(fd);
+
+    g_assert(QEMU_IS_ALIGNED(size, pagesize));
+
     if (ptr) {
         /* Unmap both the RAM block and the guard page */
         munmap(ptr, size + mmap_guard_pagesize(fd));
-- 
2.24.1