The kmalloc was taking up about 1.5% of the CPU on an ioctl-heavy workload
(x11perf -aa10text on 965). Initial results look like they have a
corresponding improvement in performance for aa10text, but more numbers might
not hurt.
Thanks to ajax for pointing out this performance regression I'd introduced
back in 2007.
---
drivers/gpu/drm/drm_drv.c | 15 ++++++++++-----
1 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 14c7a23..822d092 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -458,6 +458,7 @@ int drm_ioctl(struct inode *inode, struct file *filp,
drm_ioctl_t *func;
unsigned int nr = DRM_IOCTL_NR(cmd);
int retcode = -EINVAL;
+ char stack_kdata[128];
char *kdata = NULL;
atomic_inc(&dev->ioctl_count);
@@ -496,10 +497,14 @@ int drm_ioctl(struct inode *inode, struct file *filp,
retcode = -EACCES;
} else {
if (cmd & (IOC_IN | IOC_OUT)) {
- kdata = kmalloc(_IOC_SIZE(cmd), GFP_KERNEL);
- if (!kdata) {
- retcode = -ENOMEM;
- goto err_i1;
+ if (_IOC_SIZE(cmd) <= sizeof(stack_kdata)) {
+ kdata = stack_kdata;
+ } else {
+ kdata = kmalloc(_IOC_SIZE(cmd), GFP_KERNEL);
+ if (!kdata) {
+ retcode = -ENOMEM;
+ goto err_i1;
+ }
}
}
@@ -520,7 +525,7 @@ int drm_ioctl(struct inode *inode, struct file *filp,
}
err_i1:
- if (kdata)
+ if (kdata != stack_kdata)
kfree(kdata);
atomic_dec(&dev->ioctl_count);
if (retcode)
--
1.6.2.1
------------------------------------------------------------------------------
Apps built with the Adobe(R) Flex(R) framework and Flex Builder(TM) are
powering Web 2.0 with engaging, cross-platform capabilities. Quickly and
easily build your RIAs with Flex Builder, the Eclipse(TM)based development
software that enables intelligent coding and step-through debugging.
Download the free 60 day trial. http://p.sf.net/sfu/www-adobe-com
--
_______________________________________________
Dri-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/dri-devel
