accel/tcg: Use interval tree for user-only page tracking

Finish weaning user-only away from PageDesc.

Using an interval tree to track page permissions means that
we can represent very large regions efficiently.

Resolves: https://gitlab.com/qemu-project/qemu/-/issues/290
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/967
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1214
Reviewed-by: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

accel/tcg/internal.h

@@ -24,9 +24,7 @@
 #endif
 
 typedef struct PageDesc {
-#ifdef CONFIG_USER_ONLY
-    unsigned long flags;
-#else
+#ifndef CONFIG_USER_ONLY
     QemuSpin lock;
     /* list of TBs intersecting this ram page */
     uintptr_t first_tb;

accel/tcg/tb-maint.c

@@ -68,15 +68,23 @@ static void tb_remove_all(void)
 /* Call with mmap_lock held. */
 static void tb_record(TranslationBlock *tb, PageDesc *p1, PageDesc *p2)
 {
-    /* translator_loop() must have made all TB pages non-writable */
-    assert(!(p1->flags & PAGE_WRITE));
-    if (p2) {
-        assert(!(p2->flags & PAGE_WRITE));
-    }
+    target_ulong addr;
+    int flags;
 
     assert_memory_lock();
-
     tb->itree.last = tb->itree.start + tb->size - 1;
+
+    /* translator_loop() must have made all TB pages non-writable */
+    addr = tb_page_addr0(tb);
+    flags = page_get_flags(addr);
+    assert(!(flags & PAGE_WRITE));
+
+    addr = tb_page_addr1(tb);
+    if (addr != -1) {
+        flags = page_get_flags(addr);
+        assert(!(flags & PAGE_WRITE));
+    }
+
     interval_tree_insert(&tb->itree, &tb_root);
 }
 

tests/tcg/multiarch/test-vma.c

@@ -0,0 +1,22 @@
+/*
+ * Test very large vma allocations.
+ * The qemu out-of-memory condition was within the mmap syscall itself.
+ * If the syscall actually returns with MAP_FAILED, the test succeeded.
+ */
+#include <sys/mman.h>
+
+int main()
+{
+    int n = sizeof(size_t) == 4 ? 32 : 45;
+
+    for (int i = 28; i < n; i++) {
+        size_t l = (size_t)1 << i;
+        void *p = mmap(0, l, PROT_NONE,
+                       MAP_PRIVATE | MAP_ANONYMOUS | MAP_NORESERVE, -1, 0);
+        if (p == MAP_FAILED) {
+            break;
+        }
+        munmap(p, l);
+    }
+    return 0;
+}