| Message ID | 20181011231810.1363-1-robdclark@gmail.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | [libdrm] xf86drmHash: remove redundant zero init | expand |
On Thursday, 2018-10-11 19:18:10 -0400, mesa-dev-bounces@lists.freedesktop.org wrote: > From: Rob Clark <robclark@freedesktop.org> > > drmMalloc() is already calloc() Sounds very much like an implementation detail, but everything relies on it already, so... Reviewed-by: Eric Engestrom <eric.engestrom@intel.com> > > Signed-off-by: Rob Clark <robclark@freedesktop.org> > --- > Small micro-optimization that I noticed while doing some perf work.. > I should probably look at promoting amdgpu's handle_table to core > libdrm and replacing a couple of libdrm_freedreno's xf86drmHash > tables over to that. There is still at least one hashtable (in > some libdrm_freedreno patches I'm working on finalizing) where > handle_table would not be appropriate (ie. key is a ptr).. but the > answer there might be importing a better hashtable implementation > into libdrm. > > Related note, once I land a libdrm_freedreno patchset (hopefully > tomorrow or over the weekend), I'll have interest in making a > libdrm release so I can start landing mesa patches that will > depend on that.. so if anyone else wants me to wait a few days > so they can push something before the next libdrm release, please > let me know. > > xf86drmHash.c | 5 ----- > 1 file changed, 5 deletions(-) > > diff --git a/xf86drmHash.c b/xf86drmHash.c > index b2fa414e..39900e7e 100644 > --- a/xf86drmHash.c > +++ b/xf86drmHash.c > @@ -109,12 +109,7 @@ void *drmHashCreate(void) > table = drmMalloc(sizeof(*table)); > if (!table) return NULL; > table->magic = HASH_MAGIC; > - table->entries = 0; > - table->hits = 0; > - table->partials = 0; > - table->misses = 0; > > - for (i = 0; i < HASH_SIZE; i++) table->buckets[i] = NULL; > return table; > } > > -- > 2.17.1 > > _______________________________________________ > mesa-dev mailing list > mesa-dev@lists.freedesktop.org > https://lists.freedesktop.org/mailman/listinfo/mesa-dev
On Fri, 12 Oct 2018 at 00:18, Rob Clark <robdclark@gmail.com> wrote: > > From: Rob Clark <robclark@freedesktop.org> > > drmMalloc() is already calloc() > > Signed-off-by: Rob Clark <robclark@freedesktop.org> For the patch Reviewed-by: Emil Velikov <emil.velikov@collabora.com> > --- > Small micro-optimization that I noticed while doing some perf work.. > I should probably look at promoting amdgpu's handle_table to core > libdrm and replacing a couple of libdrm_freedreno's xf86drmHash > tables over to that. There is still at least one hashtable (in > some libdrm_freedreno patches I'm working on finalizing) where > handle_table would not be appropriate (ie. key is a ptr).. but the > answer there might be importing a better hashtable implementation > into libdrm. > Please remember to nuke some of the existing hash implementations, if you want to add new one. The more (nuked) the better. > Related note, once I land a libdrm_freedreno patchset (hopefully > tomorrow or over the weekend), I'll have interest in making a > libdrm release so I can start landing mesa patches that will > depend on that.. so if anyone else wants me to wait a few days > so they can push something before the next libdrm release, please > let me know. > There's nothing urgent on my end. Thanks Emil
diff --git a/xf86drmHash.c b/xf86drmHash.c index b2fa414e..39900e7e 100644 --- a/xf86drmHash.c +++ b/xf86drmHash.c @@ -109,12 +109,7 @@ void *drmHashCreate(void) table = drmMalloc(sizeof(*table)); if (!table) return NULL; table->magic = HASH_MAGIC; - table->entries = 0; - table->hits = 0; - table->partials = 0; - table->misses = 0; - for (i = 0; i < HASH_SIZE; i++) table->buckets[i] = NULL; return table; }