[PATCH v3] linux-user: Fix brk() to release pages

[Helge Deller <deller@gmx.de>]

The current brk() implementation does not de-allocate pages if a lower
address is given compared to earlier brk() calls.
But according to the manpage, brk() shall deallocate memory in this case
and currently it breaks a real-world application, specifically building
the debian gcl package in qemu-user.

Fix this issue by reworking the qemu brk() implementation.

Tested with the C-code testcase included in qemu commit 4d1de87c750, and
by building debian package of gcl in a hppa-linux guest on a x86-64
host.

Signed-off-by: Helge Deller <deller@gmx.de>

---
v3:
- Fixed one bug where page aligned address was returned instead
  of requested address.
- Dropped debug info which is partly outdated now
- Reduced number of changed lines in diff compared to v2 to make
  diff easier readable
- Fixed changelog of v2
v2:
- Fixed return value of brk(). The v1 version wrongly page-aligned
  the provided address, while userspace expects an unmodified
  address returned.


diff --git a/linux-user/syscall.c b/linux-user/syscall.c
index 4fee882cd7..7d28802aa6 100644
--- a/linux-user/syscall.c
+++ b/linux-user/syscall.c
@@ -838,49 +838,52 @@ static inline int host_to_target_sock_type(int host_type)
 }

 static abi_ulong target_brk;
-static abi_ulong target_original_brk;
 static abi_ulong brk_page;

 void target_set_brk(abi_ulong new_brk)
 {
-    target_original_brk = target_brk = HOST_PAGE_ALIGN(new_brk);
+    target_brk = new_brk;
     brk_page = HOST_PAGE_ALIGN(target_brk);
 }

-//#define DEBUGF_BRK(message, args...) do { fprintf(stderr, (message), ## args); } while (0)
-#define DEBUGF_BRK(message, args...)
-
 /* do_brk() must return target values and target errnos. */
-abi_long do_brk(abi_ulong new_brk)
+abi_long do_brk(abi_ulong brk_val)
 {
     abi_long mapped_addr;
     abi_ulong new_alloc_size;
+    abi_ulong new_brk, new_host_brk_page;

     /* brk pointers are always untagged */

-    DEBUGF_BRK("do_brk(" TARGET_ABI_FMT_lx ") -> ", new_brk);
-
-    if (!new_brk) {
-        DEBUGF_BRK(TARGET_ABI_FMT_lx " (!new_brk)\n", target_brk);
+    /* return old brk value if brk_val unchanged or zero */
+    if (!brk_val || brk_val == target_brk) {
         return target_brk;
     }
-    if (new_brk < target_original_brk) {
-        DEBUGF_BRK(TARGET_ABI_FMT_lx " (new_brk < target_original_brk)\n",
-                   target_brk);
+
+    new_brk = TARGET_PAGE_ALIGN(brk_val);
+    new_host_brk_page = HOST_PAGE_ALIGN(brk_val);
+
+    /* brk_val and old target_brk might be on the same page */
+    if (new_brk == TARGET_PAGE_ALIGN(target_brk)) {
+        if (brk_val > target_brk) {
+            /* empty remaining bytes in (possibly larger) host page */
+            memset(g2h_untagged(target_brk), 0, new_host_brk_page - target_brk);
+        }
+        target_brk = brk_val;
         return target_brk;
     }

-    /* If the new brk is less than the highest page reserved to the
-     * target heap allocation, set it and we're almost done...  */
-    if (new_brk <= brk_page) {
-        /* Heap contents are initialized to zero, as for anonymous
-         * mapped pages.  */
-        if (new_brk > target_brk) {
-            memset(g2h_untagged(target_brk), 0, new_brk - target_brk);
-        }
-	target_brk = new_brk;
-        DEBUGF_BRK(TARGET_ABI_FMT_lx " (new_brk <= brk_page)\n", target_brk);
-	return target_brk;
+    /* Release heap if necesary */
+    if (new_brk < target_brk) {
+        /* empty remaining bytes in (possibly larger) host page */
+        memset(g2h_untagged(brk_val), 0, new_host_brk_page - brk_val);
+
+        /* free unused host pages and set new brk_page */
+        target_munmap(new_host_brk_page, brk_page - new_host_brk_page);
+        brk_page = new_host_brk_page;
+
+        target_brk = brk_val;
+        return target_brk;
     }

     /* We need to allocate more memory after the brk... Note that
@@ -889,10 +892,14 @@ abi_long do_brk(abi_ulong new_brk)
      * itself); instead we treat "mapped but at wrong address" as
      * a failure and unmap again.
      */
-    new_alloc_size = HOST_PAGE_ALIGN(new_brk - brk_page);
-    mapped_addr = get_errno(target_mmap(brk_page, new_alloc_size,
+    new_alloc_size = new_host_brk_page - brk_page;
+    if (new_alloc_size) {
+        mapped_addr = get_errno(target_mmap(brk_page, new_alloc_size,
                                         PROT_READ|PROT_WRITE,
                                         MAP_ANON|MAP_PRIVATE, 0, 0));
+    } else {
+        mapped_addr = brk_page;
+    }

     if (mapped_addr == brk_page) {
         /* Heap contents are initialized to zero, as for anonymous
@@ -904,10 +911,8 @@ abi_long do_brk(abi_ulong new_brk)
          * then shrunken).  */
         memset(g2h_untagged(target_brk), 0, brk_page - target_brk);

-        target_brk = new_brk;
-        brk_page = HOST_PAGE_ALIGN(target_brk);
-        DEBUGF_BRK(TARGET_ABI_FMT_lx " (mapped_addr == brk_page)\n",
-            target_brk);
+        target_brk = brk_val;
+        brk_page = new_host_brk_page;
         return target_brk;
     } else if (mapped_addr != -1) {
         /* Mapped but at wrong address, meaning there wasn't actually
@@ -915,10 +920,6 @@ abi_long do_brk(abi_ulong new_brk)
          */
         target_munmap(mapped_addr, new_alloc_size);
         mapped_addr = -1;
-        DEBUGF_BRK(TARGET_ABI_FMT_lx " (mapped_addr != -1)\n", target_brk);
-    }
-    else {
-        DEBUGF_BRK(TARGET_ABI_FMT_lx " (otherwise)\n", target_brk);
     }

 #if defined(TARGET_ALPHA)