[Qemu-devel] [PATCH v3 4/7] cpu: Support a target CPU having a variable page size

[Peter Maydell]

Support target CPUs having a page size which isn't knownn
at compile time. To use this, the CPU implementation should:
 * define TARGET_PAGE_BITS_VARY
 * not define TARGET_PAGE_BITS
 * define TARGET_PAGE_BITS_MIN to the smallest value it
   might possibly want for TARGET_PAGE_BITS
 * call set_preferred_target_page_bits() in its realize
   function to indicate the actual preferred target page
   size for the CPU (and report any error from it)

In CONFIG_USER_ONLY, the CPU implementation should continue
to define TARGET_PAGE_BITS appropriately for the guest
OS page size.

Machines which want to take advantage of having the page
size something larger than TARGET_PAGE_BITS_MIN must
set the MachineClass minimum_page_bits field to a value
which they guarantee will be no greater than the preferred
page size for any CPU they create.

Note that changing the target page size by setting
minimum_page_bits is a migration compatibility break
for that machine.

For debugging purposes, attempts to use TARGET_PAGE_SIZE
before it has been finally confirmed will assert.

Signed-off-by: Peter Maydell <address@hidden>
---
 exec.c                 | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/exec/cpu-all.h |  9 +++++++++
 include/hw/boards.h    |  7 +++++++
 include/qemu-common.h  | 12 ++++++++++++
 vl.c                   | 10 ++++++++++
 5 files changed, 80 insertions(+)

diff --git a/exec.c b/exec.c
index 86b09ac..25d972f 100644
--- a/exec.c
+++ b/exec.c
@@ -93,6 +93,11 @@ static MemoryRegion io_mem_unassigned;
 
 #endif
 
+#ifdef TARGET_PAGE_BITS_VARY
+int target_page_bits;
+bool target_page_bits_decided;
+#endif
+
 struct CPUTailQ cpus = QTAILQ_HEAD_INITIALIZER(cpus);
 /* current CPU in the current thread. It is only valid inside
    cpu_exec() */
@@ -102,8 +107,37 @@ __thread CPUState *current_cpu;
    2 = Adaptive rate instruction counting.  */
 int use_icount;
 
+bool set_preferred_target_page_bits(int bits)
+{
+    /* The target page size is the lowest common denominator for all
+     * the CPUs in the system, so we can only make it smaller, never
+     * larger. And we can't make it smaller once we've committed to
+     * a particular size.
+     */
+#ifdef TARGET_PAGE_BITS_VARY
+    assert(bits >= TARGET_PAGE_BITS_MIN);
+    if (target_page_bits == 0 || target_page_bits > bits) {
+        if (target_page_bits_decided) {
+            return false;
+        }
+        target_page_bits = bits;
+    }
+#endif
+    return true;
+}
+
 #if !defined(CONFIG_USER_ONLY)
 
+static void finalize_target_page_bits(void)
+{
+#ifdef TARGET_PAGE_BITS_VARY
+    if (target_page_bits == 0) {
+        target_page_bits = TARGET_PAGE_BITS_MIN;
+    }
+    target_page_bits_decided = true;
+#endif
+}
+
 typedef struct PhysPageEntry PhysPageEntry;
 
 struct PhysPageEntry {
@@ -2797,6 +2831,14 @@ void cpu_register_map_client(QEMUBH *bh)
 void cpu_exec_init_all(void)
 {
     qemu_mutex_init(&ram_list.mutex);
+    /* The data structures we set up here depend on knowing the page size,
+     * so no more changes can be made after this point.
+     * In an ideal world, nothing we did before we had finished the
+     * machine setup would care about the target page size, and we could
+     * do this much later, rather than requiring board models to state
+     * up front what their requirements are.
+     */
+    finalize_target_page_bits();
     io_mem_init();
     memory_map_init();
     qemu_mutex_init(&map_client_list_lock);
diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h
index b6a7059..861260d 100644
--- a/include/exec/cpu-all.h
+++ b/include/exec/cpu-all.h
@@ -189,6 +189,15 @@ void address_space_stq(AddressSpace *as, hwaddr addr, 
uint64_t val,
 
 /* page related stuff */
 
+#ifdef TARGET_PAGE_BITS_VARY
+extern bool target_page_bits_decided;
+extern int target_page_bits;
+#define TARGET_PAGE_BITS ({ assert(target_page_bits_decided); \
+                            target_page_bits; })
+#else
+#define TARGET_PAGE_BITS_MIN TARGET_PAGE_BITS
+#endif
+
 #define TARGET_PAGE_SIZE (1 << TARGET_PAGE_BITS)
 #define TARGET_PAGE_MASK ~(TARGET_PAGE_SIZE - 1)
 #define TARGET_PAGE_ALIGN(addr) (((addr) + TARGET_PAGE_SIZE - 1) & 
TARGET_PAGE_MASK)
diff --git a/include/hw/boards.h b/include/hw/boards.h
index e46a744..a51da9c 100644
--- a/include/hw/boards.h
+++ b/include/hw/boards.h
@@ -86,6 +86,12 @@ typedef struct {
  *    Returns a @HotpluggableCPUList, which describes CPUs objects which
  *    could be added with -device/device_add.
  *    Caller is responsible for freeing returned list.
+ * @minimum_page_bits:
+ *    If non-zero, the board promises never to create a CPU with a page size
+ *    smaller than this, so QEMU can use a more efficient larger page
+ *    size than the target architecture's minimum. (Attempting to create
+ *    such a CPU will fail.) Note that changing this is a migration
+ *    compatibility break for the machine.
  */
 struct MachineClass {
     /*< private >*/
@@ -124,6 +130,7 @@ struct MachineClass {
     ram_addr_t default_ram_size;
     bool option_rom_has_mr;
     bool rom_file_has_mr;
+    int minimum_page_bits;
 
     HotplugHandler *(*get_hotplug_handler)(MachineState *machine,
                                            DeviceState *dev);
diff --git a/include/qemu-common.h b/include/qemu-common.h
index 9e8b0bd..7e6e4fe 100644
--- a/include/qemu-common.h
+++ b/include/qemu-common.h
@@ -82,6 +82,18 @@ bool tcg_enabled(void);
 void cpu_exec_init_all(void);
 
 /**
+ * set_preferred_target_page_bits:
+ * @bits: number of bits needed to represent an address within the page
+ *
+ * Set the preferred target page size (the actual target page
+ * size may be smaller than any given CPU's preference).
+ * Returns true on success, false on failure (which can only happen
+ * if this is called after the system has already finalized its
+ * choice of page size and the requested page size is smaller than that).
+ */
+bool set_preferred_target_page_bits(int bits);
+
+/**
  * Sends a (part of) iovec down a socket, yielding when the socket is full, or
  * Receives data into a (part of) iovec from a socket,
  * yielding when there is no data in the socket.
diff --git a/vl.c b/vl.c
index eb3c5ee..5feaae9 100644
--- a/vl.c
+++ b/vl.c
@@ -4088,6 +4088,16 @@ int main(int argc, char **argv, char **envp)
     }
     object_property_add_child(object_get_root(), "machine",
                               OBJECT(current_machine), &error_abort);
+
+    if (machine_class->minimum_page_bits) {
+        if (!set_preferred_target_page_bits(machine_class->minimum_page_bits)) 
{
+            /* This would be a board error: specifying a minimum smaller than
+             * a target's compile-time fixed setting.
+             */
+            g_assert_not_reached();
+        }
+    }
+
     cpu_exec_init_all();
 
     if (machine_class->hw_version) {
-- 
2.7.4