device.h: reorganize struct device

struct device is big, around 760 bytes on x86_64.  It's not a critical
structure, but it is embedded everywhere, so making it smaller is always
a good thing.

With a recent patch that moved a field from struct device to the private
structure, some benchmarks showed a very odd regression, despite this
structure having nothing to do with those benchmarks.  That caused me to
look into the layout of the structure.  Using 'pahole', it showed a
number of holes and ways that the structure could be reordered in order
to align some cachelines better, as well as reduce the size of the
overall structure.

Move 'struct kobj' to the start of the structure, to keep that access
in the first cacheline, and try to organize things a bit more compactly
where possible

By doing these few moves, the result removes at least 8 bytes from
'struct device' on a 64bit system.  Given we know there are systems with
at least 30k devices in memory at once, every little byte counts, and
this change could be a savings of 240k of kernel memory for them.  On
"normal" systems the overall memory savings would be much less.

Cc: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Cc: Johan Hovold <johan@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/device.h b/include/linux/device.h
index 4e6987e11f688bc12001cc4d030e8a3a99faa514..4457e560bc2b09cf3f10e943aa1fcfe40a0ebd49 100644 (file)
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -976,18 +976,14 @@ struct dev_links_info {
  * a higher-level representation of the device.
  */
 struct device {
+       struct kobject kobj;
        struct device           *parent;
 
        struct device_private   *p;
 
-       struct kobject kobj;
        const char              *init_name; /* initial name of the device */
        const struct device_type *type;
 
-       struct mutex            mutex;  /* mutex to synchronize calls to
-                                        * its driver.
-                                        */
-
        struct bus_type *bus;           /* type of bus device is on */
        struct device_driver *driver;   /* which driver has allocated this
                                           device */
@@ -995,6 +991,10 @@ struct device {
                                           core doesn't touch it */
        void            *driver_data;   /* Driver data, set and get with
                                           dev_set_drvdata/dev_get_drvdata */
+       struct mutex            mutex;  /* mutex to synchronize calls to
+                                        * its driver.
+                                        */
+
        struct dev_links_info   links;
        struct dev_pm_info      power;
        struct dev_pm_domain    *pm_domain;
@@ -1009,9 +1009,6 @@ struct device {
        struct list_head        msi_list;
 #endif
 
-#ifdef CONFIG_NUMA
-       int             numa_node;      /* NUMA node this device is close to */
-#endif
        const struct dma_map_ops *dma_ops;
        u64             *dma_mask;      /* dma mask (if dma'able device) */
        u64             coherent_dma_mask;/* Like dma_mask, but for
@@ -1040,6 +1037,9 @@ struct device {
        struct device_node      *of_node; /* associated device tree node */
        struct fwnode_handle    *fwnode; /* firmware device node */
 
+#ifdef CONFIG_NUMA
+       int             numa_node;      /* NUMA node this device is close to */
+#endif
        dev_t                   devt;   /* dev_t, creates the sysfs "dev" */
        u32                     id;     /* device instance */