[Qemu-devel] [PATCH 3/4] libqos: add a simple first-fit memory allocator

[John Snow <jsnow@redhat.com>]

Implement a simple first-fit memory allocator that
attempts to keep track of leased blocks of memory
in order to be able to re-use blocks.

Additionally, allow the user to specify when
initializing the device that upon cleanup,
we would like to assert that there are no
blocks in use. This may be useful for identifying
problems in qtests that use more complicated
set-up and tear-down routines.

This functionality is used in my upcoming ahci-test v2
patch set, but I didn't see fit to enable it for any
existing tests, which will continue to operate the
same as they have prior.

Signed-off-by: John Snow <jsnow@redhat.com>
---
 tests/libqos/malloc-pc.c | 296 +++++++++++++++++++++++++++++++++++++++++++++--
 tests/libqos/malloc-pc.h |   9 ++
 2 files changed, 295 insertions(+), 10 deletions(-)

diff --git a/tests/libqos/malloc-pc.c b/tests/libqos/malloc-pc.c
index 2efd095..641162d 100644
--- a/tests/libqos/malloc-pc.c
+++ b/tests/libqos/malloc-pc.c
@@ -17,45 +17,312 @@
 #include "hw/nvram/fw_cfg.h"
 
 #include "qemu-common.h"
+#include "qemu/queue.h"
 #include <glib.h>
 
 #define PAGE_SIZE (4096)
+#define bitany(X, MASK) ((X) & (MASK))
+#define bitset(X, MASK) (bitany((X), (MASK)) == (MASK))
+
+#define MLIST_ENTNAME entries
+#define MLIST_FOREACH(node, head) QTAILQ_FOREACH((node), (head), MLIST_ENTNAME)
+#define MLIST_PREV(node) QTAILQ_PREV((node), MemList, MLIST_ENTNAME);
+#define MLIST_NEXT(node) QTAILQ_NEXT((node), MLIST_ENTNAME);
+typedef QTAILQ_HEAD(MemList, MemBlock) MemList;
+typedef struct MemBlock {
+    QTAILQ_ENTRY(MemBlock) MLIST_ENTNAME;
+    uint64_t size;
+    uint64_t addr;
+} MemBlock;
 
 typedef struct PCAlloc
 {
     QGuestAllocator alloc;
-
+    PCAllocOpts opts;
     uint64_t start;
     uint64_t end;
+
+    MemList used;
+    MemList free;
 } PCAlloc;
 
-static uint64_t pc_alloc(QGuestAllocator *allocator, size_t size)
+static inline void mlist_insert(MemList *head, MemBlock *insr)
 {
-    PCAlloc *s = container_of(allocator, PCAlloc, alloc);
-    uint64_t addr;
+    QTAILQ_INSERT_HEAD(head, insr, MLIST_ENTNAME);
+}
+
+static inline void mlist_append(MemList *head, MemBlock *node)
+{
+    QTAILQ_INSERT_TAIL(head, node, MLIST_ENTNAME);
+}
+
+static inline void mlist_unlink(MemList *head, MemBlock *rem)
+{
+    QTAILQ_REMOVE(head, rem, MLIST_ENTNAME);
+}
+
+static MemBlock *mlist_new(uint64_t addr, uint64_t size)
+{
+    MemBlock *block;
+
+    if (!size) {
+        return NULL;
+    }
+    block = g_malloc0(sizeof(MemBlock));
+
+    block->addr = addr;
+    block->size = size;
+
+    return block;
+}
+
+static void mlist_delete(MemList *list, MemBlock *node)
+{
+    g_assert(list && node);
+    mlist_unlink(list, node);
+    g_free(node);
+}
+
+static MemBlock *mlist_find_key(MemList *head, uint64_t addr)
+{
+    MemBlock *node;
+    MLIST_FOREACH(node, head) {
+        if (node->addr == addr) {
+            return node;
+        }
+    }
+    return NULL;
+}
+
+static MemBlock *mlist_find_space(MemList *head, uint64_t size)
+{
+    MemBlock *node;
+    MLIST_FOREACH(node, head) {
+        if (node->size >= size) {
+            return node;
+        }
+    }
+    return NULL;
+}
+
+static MemBlock *mlist_sort_insert(MemList *head, MemBlock *insr)
+{
+    MemBlock *node;
+    g_assert(head && insr);
+
+    MLIST_FOREACH(node, head) {
+        if (insr->addr < node->addr) {
+            QTAILQ_INSERT_BEFORE(node, insr, entries);
+            return insr;
+        }
+    }
+
+    mlist_append(head, insr);
+    return insr;
+}
+
+static inline uint64_t mlist_boundary(MemBlock *node)
+{
+    return node->size + node->addr;
+}
+
+static MemBlock *mlist_join(MemList *head, MemBlock *left, MemBlock *right)
+{
+    g_assert(head && left && right);
+
+    left->size += right->size;
+    mlist_delete(head, right);
+    return left;
+}
+
+static void mlist_coalesce(MemList *head, MemBlock *node)
+{
+    g_assert(node);
+    MemBlock *left;
+    MemBlock *right;
+    char merge;
+
+    do {
+        merge = 0;
+        left = MLIST_PREV(node);
+        right = MLIST_NEXT(node);
 
+        /* clowns to the left of me */
+        if (left && mlist_boundary(left) == node->addr) {
+            node = mlist_join(head, left, node);
+            merge = 1;
+        }
 
-    size += (PAGE_SIZE - 1);
-    size &= -PAGE_SIZE;
+        /* jokers to the right */
+        if (right && mlist_boundary(node) == right->addr) {
+            node = mlist_join(head, node, right);
+            merge = 1;
+        }
 
-    g_assert_cmpint((s->start + size), <=, s->end);
+    } while (merge);
+}
+
+static uint64_t pc_mlist_fulfill(PCAlloc *s, MemBlock *freenode, uint64_t size)
+{
+    uint64_t addr;
+    MemBlock *usednode;
+
+    g_assert(freenode);
+    g_assert_cmpint(freenode->size, >=, size);
 
-    addr = s->start;
-    s->start += size;
+    addr = freenode->addr;
+    if (freenode->size == size) {
+        /* re-use this freenode as our used node */
+        mlist_unlink(&s->free, freenode);
+        usednode = freenode;
+    } else {
+        /* adjust the free node and create a new used node */
+        freenode->addr += size;
+        freenode->size -= size;
+        usednode = mlist_new(addr, size);
+    }
 
+    mlist_sort_insert(&s->used, usednode);
     return addr;
 }
 
+/* To assert the correctness of the list.
+ * Used only if PC_ALLOC_PARANOID is set. */
+static void pc_mlist_check(PCAlloc *s)
+{
+    MemBlock *node;
+    uint64_t addr = s->start > 0 ? s->start - 1 : 0;
+    uint64_t next = s->start;
+
+    MLIST_FOREACH(node, &s->free) {
+        g_assert_cmpint(node->addr, >, addr);
+        g_assert_cmpint(node->addr, >=, next);
+        addr = node->addr;
+        next = node->addr + node->size;
+    }
+
+    addr = s->start > 0 ? s->start - 1 : 0;
+    next = s->start;
+    MLIST_FOREACH(node, &s->used) {
+        g_assert_cmpint(node->addr, >, addr);
+        g_assert_cmpint(node->addr, >=, next);
+        addr = node->addr;
+        next = node->addr + node->size;
+    }
+}
+
+static uint64_t pc_mlist_alloc(PCAlloc *s, uint64_t size)
+{
+    MemBlock *node;
+
+    node = mlist_find_space(&s->free, size);
+    if (!node) {
+        fprintf(stderr, "Out of guest memory.\n");
+        g_assert_not_reached();
+    }
+    return pc_mlist_fulfill(s, node, size);
+}
+
+static void pc_mlist_free(PCAlloc *s, uint64_t addr)
+{
+    MemBlock *node;
+
+    if (addr == 0) {
+        return;
+    }
+
+    node = mlist_find_key(&s->used, addr);
+    if (!node) {
+        fprintf(stderr, "Error: no record found for an allocation at "
+                "0x%016" PRIx64 ".\n",
+                addr);
+        g_assert_not_reached();
+    }
+
+    /* Rip it out of the used list and re-insert back into the free list. */
+    mlist_unlink(&s->used, node);
+    mlist_sort_insert(&s->free, node);
+    mlist_coalesce(&s->free, node);
+}
+
+static uint64_t pc_alloc(QGuestAllocator *allocator, size_t size)
+{
+    PCAlloc *s = container_of(allocator, PCAlloc, alloc);
+    uint64_t rsize = size;
+    uint64_t naddr;
+
+    rsize += (PAGE_SIZE - 1);
+    rsize &= -PAGE_SIZE;
+    g_assert_cmpint((s->start + rsize), <=, s->end);
+    g_assert_cmpint(rsize, >=, size);
+
+    naddr = pc_mlist_alloc(s, rsize);
+    if (s->opts & PC_ALLOC_PARANOID) {
+        pc_mlist_check(s);
+    }
+
+    return naddr;
+}
+
 static void pc_free(QGuestAllocator *allocator, uint64_t addr)
 {
+    PCAlloc *s = container_of(allocator, PCAlloc, alloc);
+
+    pc_mlist_free(s, addr);
+    if (s->opts & PC_ALLOC_PARANOID) {
+        pc_mlist_check(s);
+    }
+}
+
+/*
+ * Mostly for valgrind happiness, but it does offer
+ * a chokepoint for debugging guest memory leaks, too.
+ */
+void pc_alloc_uninit(QGuestAllocator *allocator)
+{
+    PCAlloc *s = container_of(allocator, PCAlloc, alloc);
+    MemBlock *node;
+    MemBlock *tmp;
+
+    /* Check for guest leaks, and destroy the list. */
+    QTAILQ_FOREACH_SAFE(node, &s->used, entries, tmp) {
+        if (s->opts & (PC_ALLOC_LEAK_WARN | PC_ALLOC_LEAK_ASSERT)) {
+            fprintf(stderr, "guest malloc leak @ 0x%016" PRIx64 "; "
+                    "size 0x%016" PRIx64 ".\n",
+                    node->addr, node->size);
+        }
+        if (s->opts & PC_ALLOC_LEAK_ASSERT) {
+            g_assert_not_reached();
+        }
+        g_free(node);
+    }
+
+    /* If there are no leaks, there should be only one node
+     * here with a specific address and size. */
+    QTAILQ_FOREACH_SAFE(node, &s->free, entries, tmp) {
+        if (bitset(s->opts, PC_ALLOC_PARANOID | PC_ALLOC_LEAK_ASSERT)) {
+            if ((node->addr != s->start) ||
+                (node->size != s->end - s->start)) {
+                fprintf(stderr, "Free list is corrupted.\n");
+                if (bitset(s->opts, PC_ALLOC_LEAK_ASSERT)) {
+                    g_assert_not_reached();
+                }
+            }
+        }
+
+        g_free(node);
+    }
+
+    g_free(s);
 }
 
-QGuestAllocator *pc_alloc_init(void)
+QGuestAllocator *pc_alloc_init_flags(PCAllocOpts flags)
 {
     PCAlloc *s = g_malloc0(sizeof(*s));
     uint64_t ram_size;
     QFWCFG *fw_cfg = pc_fw_cfg_init();
 
+    s->opts = flags;
     s->alloc.alloc = pc_alloc;
     s->alloc.free = pc_free;
 
@@ -67,5 +334,14 @@ QGuestAllocator *pc_alloc_init(void)
     /* Respect PCI hole */
     s->end = MIN(ram_size, 0xE0000000);
 
+    QTAILQ_INIT(&s->used);
+    QTAILQ_INIT(&s->free);
+    mlist_insert(&s->free, mlist_new(s->start, s->end - s->start));
+
     return &s->alloc;
 }
+
+inline QGuestAllocator *pc_alloc_init(void)
+{
+    return pc_alloc_init_flags(PC_ALLOC_NO_FLAGS);
+}
diff --git a/tests/libqos/malloc-pc.h b/tests/libqos/malloc-pc.h
index ff964ab..9f525e3 100644
--- a/tests/libqos/malloc-pc.h
+++ b/tests/libqos/malloc-pc.h
@@ -15,6 +15,15 @@
 
 #include "libqos/malloc.h"
 
+typedef enum {
+    PC_ALLOC_NO_FLAGS    = 0x00,
+    PC_ALLOC_LEAK_WARN   = 0x01,
+    PC_ALLOC_LEAK_ASSERT = 0x02,
+    PC_ALLOC_PARANOID    = 0x04
+} PCAllocOpts;
+
 QGuestAllocator *pc_alloc_init(void);
+QGuestAllocator *pc_alloc_init_flags(PCAllocOpts flags);
+void             pc_alloc_uninit(QGuestAllocator *allocator);
 
 #endif
-- 
1.9.3