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. This patch removes 16 bytes from 'struct device' on a 64bit system, just by moving things around. 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 480k of kernel memory for them. On "normal" systems the overall memory savings would be much less. Cc: "Rafael J. Wysocki" <[email protected]> Signed-off-by: Greg Kroah-Hartman <[email protected]> --- include/linux/device.h | 22 +++++++++++----------- 1 file changed, 11 insertions(+), 11 deletions(-) diff --git a/include/linux/device.h b/include/linux/device.h index b63165276a09..4e6b9a2ab8d0 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -967,18 +967,14 @@ 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 */ @@ -986,7 +982,14 @@ struct device { core doesn't touch it */ void *driver_data; /* Driver data, set and get with dev_set/get_drvdata */ + struct mutex mutex; /* mutex to synchronize calls to + * its driver. + */ + struct dev_links_info links; + spinlock_t devres_lock; + struct list_head devres_head; + struct dev_pm_info power; struct dev_pm_domain *pm_domain; @@ -1000,9 +1003,6 @@ 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 @@ -1032,9 +1032,6 @@ struct device { dev_t devt; /* dev_t, creates the sysfs "dev" */ u32 id; /* device instance */ - spinlock_t devres_lock; - struct list_head devres_head; - struct klist_node knode_class; struct class *class; const struct attribute_group **groups; /* optional groups */ @@ -1043,6 +1040,9 @@ struct device { struct iommu_group *iommu_group; struct iommu_fwspec *iommu_fwspec; +#ifdef CONFIG_NUMA + int numa_node; /* NUMA node this device is close to */ +#endif bool offline_disabled:1; bool offline:1; bool of_node_reused:1; -- 2.21.0
