oslib-posix: add helpers for stack alloc and free

the allocated stack will be adjusted to the minimum supported stack size
by the OS and rounded up to be a multiple of the system pagesize.
Additionally an architecture dependent guard page is added to the stack
to catch stack overflows.

Signed-off-by: Peter Lieven <pl@kamp.de>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>

2 files changed, 69 insertions, 0 deletions

diff --git a/include/sysemu/os-posix.h b/include/sysemu/os-posix.h
index 9c7dfdf..3cfedbc 100644
--- a/include/sysemu/os-posix.h
+++ b/include/sysemu/os-posix.h
@@ -60,4 +60,31 @@ int qemu_utimens(const char *path, const qemu_timespec *times);
 
 bool is_daemonized(void);
 
+/**
+ * qemu_alloc_stack:
+ * @sz: pointer to a size_t holding the requested usable stack size
+ *
+ * Allocate memory that can be used as a stack, for instance for
+ * coroutines. If the memory cannot be allocated, this function
+ * will abort (like g_malloc()). This function also inserts an
+ * additional guard page to catch a potential stack overflow.
+ * Note that the memory required for the guard page and alignment
+ * and minimal stack size restrictions will increase the value of sz.
+ *
+ * The allocated stack must be freed with qemu_free_stack().
+ *
+ * Returns: pointer to (the lowest address of) the stack memory.
+ */
+void *qemu_alloc_stack(size_t *sz);
+
+/**
+ * qemu_free_stack:
+ * @stack: stack to free
+ * @sz: size of stack in bytes
+ *
+ * Free a stack allocated via qemu_alloc_stack(). Note that sz must
+ * be exactly the adjusted stack size returned by qemu_alloc_stack.
+ */
+void qemu_free_stack(void *stack, size_t sz);
+
 #endif
diff --git a/util/oslib-posix.c b/util/oslib-posix.c
index f2d4e9e..d950c34 100644
--- a/util/oslib-posix.c
+++ b/util/oslib-posix.c
@@ -499,3 +499,45 @@ pid_t qemu_fork(Error **errp)
     }
     return pid;
 }
+
+void *qemu_alloc_stack(size_t *sz)
+{
+    void *ptr, *guardpage;
+    size_t pagesz = getpagesize();
+#ifdef _SC_THREAD_STACK_MIN
+    /* avoid stacks smaller than _SC_THREAD_STACK_MIN */
+    long min_stack_sz = sysconf(_SC_THREAD_STACK_MIN);
+    *sz = MAX(MAX(min_stack_sz, 0), *sz);
+#endif
+    /* adjust stack size to a multiple of the page size */
+    *sz = ROUND_UP(*sz, pagesz);
+    /* allocate one extra page for the guard page */
+    *sz += pagesz;
+
+    ptr = mmap(NULL, *sz, PROT_READ | PROT_WRITE,
+               MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+    if (ptr == MAP_FAILED) {
+        abort();
+    }
+
+#if defined(HOST_IA64)
+    /* separate register stack */
+    guardpage = ptr + (((*sz - pagesz) / 2) & ~pagesz);
+#elif defined(HOST_HPPA)
+    /* stack grows up */
+    guardpage = ptr + *sz - pagesz;
+#else
+    /* stack grows down */
+    guardpage = ptr;
+#endif
+    if (mprotect(guardpage, pagesz, PROT_NONE) != 0) {
+        abort();
+    }
+
+    return ptr;
+}
+
+void qemu_free_stack(void *stack, size_t sz)
+{
+    munmap(stack, sz);
+}