intel: add missing drm_public exports
PATCH 1/3 intel: add missing drm_public exports
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
intel/intel_bufmgr_fake.c +3 -3
@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,
@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),
@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,
Signature · 7 lines
Cheers, Eric _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
PATCH 2/3 nouveau: add missing drm_public exports
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
--- nouveau/nouveau.c | 2 +- nouveau/pushbuf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
nouveau/nouveau.c +1 -1
@@ -856,7 +856,7 @@ nouveau_bo_wait(struct nouveau_bo *bo, uint32_t access,return ret; } -int +drm_public intnouveau_bo_map (struct nouveau_bo *bo,uint32_t access,struct nouveau_client *client) {
nouveau/pushbuf.c +1 -1
@@ -728,7 +728,7 @@ nouveau_pushbuf_data(struct nouveau_pushbuf *push, struct nouveau_bo *bo, } } -int +drm_public intnouveau_pushbuf_refn (struct nouveau_pushbuf *push,struct nouveau_pushbuf_refn *refs,int nr) {
Signature · 7 lines
Cheers, Eric _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH libdrm 2/3] nouveau: add missing drm_public exports
Quoting Eric Engestrom (2018-09-20 08:58:33)
Quoted 40 lines
Fixes d7320bfcddc596f23fa2 "nouveau: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- nouveau/nouveau.c | 2 +- nouveau/pushbuf.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)nouveau/nouveau.c +1
-1@@ -856,7 +856,7 @@ nouveau_bo_wait(struct nouveau_bo *bo, uint32_t access,return ret; } -int +drm_public intnouveau_bo_map (struct nouveau_bo *bo,uint32_t access,struct nouveau_client *client) {nouveau/pushbuf.c +1
-1@@ -728,7 +728,7 @@ nouveau_pushbuf_data(struct nouveau_pushbuf *push, struct nouveau_bo *bo, } } -int +drm_public intnouveau_pushbuf_refn (struct nouveau_pushbuf *push,struct nouveau_pushbuf_refn *refs,int nr) {Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
PATCH 3/3 radeon: add missing drm_public exports
In reply to Eric EngestromBugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
--- radeon/radeon_bo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
radeon/radeon_bo.c +2 -2
@@ -67,13 +67,13 @@ drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo)return boi->bom->funcs->bo_unref (boi); } -int radeon_bo_map (struct radeon_bo *bo,int write) +drm_public int radeon_bo_map(struct radeon_bo *bo, int write) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_map (boi, write); } -int radeon_bo_unmap (struct radeon_bo *bo) +drm_public int radeon_bo_unmap(struct radeon_bo *bo) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_unmap (boi);
Signature · 7 lines
Cheers, Eric _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH libdrm 3/3] radeon: add missing drm_public exports
Quoted 20 lines · Eric Engestrom
Fixes 9f45264815eff6ebeba3 "radeon: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- radeon/radeon_bo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)radeon/radeon_bo.c +1
-1@@ -67,13 +67,13 @@ drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo)return boi->bom->funcs->bo_unref (boi); } -int radeon_bo_map (struct radeon_bo *bo,int write) +drm_public int radeon_bo_map(struct radeon_bo *bo, int write)
radeon/radeon_bo.c drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo) · line 79
Quoted 10 lines
radeon/radeon_bo.c +1
-1{struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_map (boi, write); } -int radeon_bo_unmap (struct radeon_bo *bo) +drm_public int radeon_bo_unmap(struct radeon_bo *bo) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_unmap (boi);
Thanks Eric!
Signature · 6 lines
Earthling Michel Dänzer | http://www.amd.com Libre software enthusiast | Mesa and X developer _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH libdrm 3/3] radeon: add missing drm_public exports
Quoted 25 lines · Michel Dänzer
Quoted 24 lines · Eric Engestrom
Fixes 9f45264815eff6ebeba3 "radeon: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- radeon/radeon_bo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)radeon/radeon_bo.c +1
-1@@ -67,13 +67,13 @@ drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo)return boi->bom->funcs->bo_unref (boi); } -int radeon_bo_map (struct radeon_bo *bo,int write) +drm_public int radeon_bo_map(struct radeon_bo *bo, int write) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_map (boi, write); }
Quoted 9 lines
radeon/radeon_bo.c drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo) · line 79
Quoted 6 lines
radeon/radeon_bo.c +1
-1-int radeon_bo_unmap (struct radeon_bo *bo) +drm_public int radeon_bo_unmap(struct radeon_bo *bo) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_unmap (boi);Reviewed-by Michel Dänzer <[email protected]>Tested-by Michel Dänzer <[email protected]>
Thanks!
radeon_cs_space_check was also missing, but my grep didn't catch it because radeon_cs_space_check_with_bo matched my weak grep skills...
I added drm_public to it too, can I still apply your tags, or do you want a v2?
----8<----
radeon/radeon_cs_space.c +1 -1
@@ -227,7 +227,7 @@ radeon_cs_space_check_with_bo(struct radeon_cs *cs, struct radeon_bo *bo,return ret; } -int radeon_cs_space_check (struct radeon_cs *cs) +drm_public int radeon_cs_space_check(struct radeon_cs *cs) {struct radeon_cs_int *csi = (struct radeon_cs_int *)cs;return radeon_cs_check_space_internal (csi,NULL );
---->8----
Quoted 7 lines
Thanks Eric!
Signature · 2 lines
Earthling Michel Dänzer | http://www.amd.com Libre software enthusiast | Mesa and X developer
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH libdrm 3/3] radeon: add missing drm_public exports
Quoted 36 lines · Eric Engestrom
Quoted 25 lines · Michel Dänzer
Quoted 24 lines · Eric Engestrom
Fixes 9f45264815eff6ebeba3 "radeon: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- radeon/radeon_bo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)radeon/radeon_bo.c +1
-1@@ -67,13 +67,13 @@ drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo)return boi->bom->funcs->bo_unref (boi); } -int radeon_bo_map (struct radeon_bo *bo,int write) +drm_public int radeon_bo_map(struct radeon_bo *bo, int write) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_map (boi, write); }Quoted 9 lines
radeon/radeon_bo.c drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo) · line 79
Quoted 6 lines
radeon/radeon_bo.c +1
-1-int radeon_bo_unmap (struct radeon_bo *bo) +drm_public int radeon_bo_unmap(struct radeon_bo *bo) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_unmap (boi);Reviewed-by Michel Dänzer <[email protected]>Tested-by Michel Dänzer <[email protected]>
Quoted 7 lines
Thanks!
radeon_cs_space_checkwas also missing, but my grep didn't catch it becauseradeon_cs_space_check_with_bomatched my weak grep skills...I added
drm_publicto it too, can I still apply your tags, or do you want a v2?
I ended up pushing it with your r-b and t-b, because I'm going home and would rather not have left it like that too long :)
Thanks again!
Quoted 18 lines
----8<----
radeon/radeon_cs_space.c +1
-2@@ -227,7 +227,7 @@ radeon_cs_space_check_with_bo(struct radeon_cs *cs, struct radeon_bo *bo,return ret; } -int radeon_cs_space_check (struct radeon_cs *cs) +drm_public int radeon_cs_space_check(struct radeon_cs *cs) {struct radeon_cs_int *csi = (struct radeon_cs_int *)cs;return radeon_cs_check_space_internal (csi,NULL ); ---->8----Quoted 2 lines
Quoted 6 lines
Quoted 6 lines
Thanks Eric!
Signature · 2 lines
Earthling Michel Dänzer | http://www.amd.com Libre software enthusiast | Mesa and X developer
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH libdrm 3/3] radeon: add missing drm_public exports
Quoted 39 lines · Eric Engestrom
Quoted 38 lines · Eric Engestrom
Quoted 25 lines · Michel Dänzer
Quoted 24 lines · Eric Engestrom
Fixes 9f45264815eff6ebeba3 "radeon: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- radeon/radeon_bo.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)radeon/radeon_bo.c +1
-1@@ -67,13 +67,13 @@ drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo)return boi->bom->funcs->bo_unref (boi); } -int radeon_bo_map (struct radeon_bo *bo,int write) +drm_public int radeon_bo_map(struct radeon_bo *bo, int write) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_map (boi, write); }Quoted 9 lines
radeon/radeon_bo.c drm_public struct radeon_bo *radeon_bo_unref(struct radeon_bo *bo) · line 79
Quoted 6 lines
radeon/radeon_bo.c +1
-1-int radeon_bo_unmap (struct radeon_bo *bo) +drm_public int radeon_bo_unmap(struct radeon_bo *bo) {struct radeon_bo_int *boi = (struct radeon_bo_int *)bo;return boi->bom->funcs->bo_unmap (boi);Reviewed-by Michel Dänzer <[email protected]>Tested-by Michel Dänzer <[email protected]>Thanks!
Quoted 8 lines
Quoted 5 lines
radeon_cs_space_checkwas also missing, but my grep didn't catch it becauseradeon_cs_space_check_with_bomatched my weak grep skills...I added
drm_publicto it too, can I still apply your tags, or do you want a v2?I ended up pushing it with your r-b and t-b, because I'm going home and would rather not have left it like that too long :)
Good catch and good call, thanks again.
Signature · 6 lines
Earthling Michel Dänzer | http://www.amd.com Libre software enthusiast | Mesa and X developer _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 5 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>
But for the series, I went to check what went wrong. It seems my script missed the cases in which we had more than one symbol with the same name (yes, we do have some static functions that have the same name of an exported symbol) and cases in which for some reason cscope didn't return the location of the symbold definition.
So... I decided to double check if we are now exporting all symbols that we were previously. My check is with:
$ git checkout 473e2d2
$ flags="-D amdgpu=true -D cairo-tests=true -D etnaviv=true -D exynos=true
-D freedreno=true -D freedreno-kgsl=true -D intel=true -D libkms=true
-D man-pages=true -D nouveau=true -D omap=true -D radeon=true
-D tegra=true -D udev=true -D valgrind=true -D vc4=true -D vmwgfx=true"
$ meson _buildold
$ ninja -C _buildold
$ git checkout master
$ ls /tmp/patches/
0001-intel-add-missing-drm-public-exports.patch 0003-radeon-add-missing-drm-public-exports.patch
0002-nouveau-add-missing-drm-public-exports.patch
$ git am /tmp/patches/*
$ meson _buildnew
$ ninja -C _buildnew
$ find _buildnew/ -name '*.so' | while read f; do
fold=${f/_buildnew/_buildold}
nm --dynamic --defined-only $f | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/new.txt
nm --dynamic --defined-only $fold | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/old.txt
git diff /tmp/old.txt /tmp/new.txt
doneSo.. we still have the following symbols missing.
tmp/new.txt renamed from tmp/old.txt +0 -1
@@ -29,7 +29,6 @@ radeon_cs_need_flush radeon_cs_print radeon_cs_set_limit radeon_cs_space_add_persistent_bo -radeon_cs_space_check radeon_cs_space_check_with_bo radeon_cs_space_reset_bos radeon_cs_space_set_flush
tmp/new.txt renamed from tmp/old.txt +0 -4
@@ -4,13 +4,9 @@ omap_bo_cpu_fini omap_bo_cpu_prep omap_bo_del omap_bo_dmabuf -omap_bo_from_dmabuf -omap_bo_from_name omap_bo_get_name omap_bo_handle omap_bo_map -omap_bo_new -omap_bo_new_tiled omap_bo_ref omap_bo_size omap_device_del
tmp/new.txt renamed from tmp/old.txt +0 -1
@@ -3,7 +3,6 @@ fd_bo_cpu_prep fd_bo_del fd_bo_dmabuf fd_bo_from_dmabuf -fd_bo_from_fbdev fd_bo_from_handle fd_bo_from_name fd_bo_get_iova
I hope I'm covering everything now.
Thanks
Lucas De Marchi
Quoted 39 lines
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +3
-3@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 46 lines · Lucas De Marchi
Quoted 5 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>Reviewed-by Lucas De Marchi <[email protected]>But for the series, I went to check what went wrong. It seems my script missed the cases in which we had more than one symbol with the same name (yes, we do have some static functions that have the same name of an exported symbol) and cases in which for some reason cscope didn't return the location of the symbold definition.
So... I decided to double check if we are now exporting all symbols that we were previously. My check is with:
$ git checkout 473e2d2 $ flags="-D amdgpu=true -D cairo-tests=true -D etnaviv=true -D exynos=true -D freedreno=true -D freedreno-kgsl=true -D intel=true -D libkms=true -D man-pages=true -D nouveau=true -D omap=true -D radeon=true -D tegra=true -D udev=true -D valgrind=true -D vc4=true -D vmwgfx=true" $ meson _buildold $ ninja -C _buildold $ git checkout master $ ls /tmp/patches/ 0001-intel-add-missing-drm-public-exports.patch 0003-radeon-add-missing-drm-public-exports.patch 0002-nouveau-add-missing-drm-public-exports.patch $ git am /tmp/patches/* $ meson _buildnew $ ninja -C _buildnew $ find _buildnew/ -name '*.so' | while read f; do fold=${f/_buildnew/_buildold} nm --dynamic --defined-only $f | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/new.txt nm --dynamic --defined-only $fold | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/old.txt git diff /tmp/old.txt /tmp/new.txt doneSo.. we still have the following symbols missing.
tmp/new.txt renamed from tmp/old.txt +0
-0
tmp/new.txt radeon_cs_need_flush · line 32
Quoted 4 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -29,7 +29,6 @@ radeon_cs_need_flush radeon_cs_print radeon_cs_set_limit radeon_cs_space_add_persistent_bo -radeon_cs_space_check
Ha, I missed that one because my grep found the one with the _with_bo suffix which was properly exported... :eyeroll:
I'll send a v2 in a bit with that added.
Quoted 11 lines
tmp/new.txt renamed from tmp/old.txt +0
-0radeon_cs_space_check_with_bo radeon_cs_space_reset_bos radeon_cs_space_set_flushtmp/new.txt renamed from tmp/old.txt +0
-0@@ -4,13 +4,9 @@ omap_bo_cpu_fini omap_bo_cpu_prep omap_bo_del omap_bo_dmabuf
tmp/new.txt omap_bo_cpu_fini · line 12
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-4-omap_bo_from_dmabuf -omap_bo_from_name omap_bo_get_name omap_bo_handle omap_bo_map -omap_bo_new -omap_bo_new_tiled omap_bo_ref omap_bo_size omap_device_del
These ones actually do have the drm_public annotation, although it was not written the "normal way", which might be why it's not working?
For example:
struct omap_bo *
drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name)
{
...I guess from your script above that they are actually not exported? Could you double-check, and send a patch for these omap ones? Thanks :)
tmp/new.txt fd_bo_cpu_prep · line 6
Quoted 9 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -3,7 +3,6 @@ fd_bo_cpu_prep fd_bo_del fd_bo_dmabuf fd_bo_from_dmabuf -fd_bo_from_fbdev
This one is actually all good:
drm_public struct fd_bo * fd_bo_from_fbdev(struct fd_pipe *pipe, int fbfd, uint32_t size)
It is hidden behind !HAVE_FREEDRENO_KGSL which is itself controlled by -D freedreno-kgsl=false on meson; make sure you're using the same config for your before/after comparison :)
Quoted 39 lines
tmp/new.txt renamed from tmp/old.txt +0
-0fd_bo_from_handle fd_bo_from_name fd_bo_get_iovaI hope I'm covering everything now.
Thanks
Lucas De MarchiQuoted 30 lines
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +2
-2@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; }
Quoted 9 lines
Quoted 9 lines
intel/intel_bufmgr_fake.c +1
-1-void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 83 lines · Eric Engestrom
Quoted 46 lines · Lucas De Marchi
Quoted 5 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>Reviewed-by Lucas De Marchi <[email protected]>But for the series, I went to check what went wrong. It seems my script missed the cases in which we had more than one symbol with the same name (yes, we do have some static functions that have the same name of an exported symbol) and cases in which for some reason cscope didn't return the location of the symbold definition.
So... I decided to double check if we are now exporting all symbols that we were previously. My check is with:
$ git checkout 473e2d2 $ flags="-D amdgpu=true -D cairo-tests=true -D etnaviv=true -D exynos=true -D freedreno=true -D freedreno-kgsl=true -D intel=true -D libkms=true -D man-pages=true -D nouveau=true -D omap=true -D radeon=true -D tegra=true -D udev=true -D valgrind=true -D vc4=true -D vmwgfx=true" $ meson _buildold $ ninja -C _buildold $ git checkout master $ ls /tmp/patches/ 0001-intel-add-missing-drm-public-exports.patch 0003-radeon-add-missing-drm-public-exports.patch 0002-nouveau-add-missing-drm-public-exports.patch $ git am /tmp/patches/* $ meson _buildnew $ ninja -C _buildnew $ find _buildnew/ -name '*.so' | while read f; do fold=${f/_buildnew/_buildold} nm --dynamic --defined-only $f | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/new.txt nm --dynamic --defined-only $fold | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/old.txt git diff /tmp/old.txt /tmp/new.txt doneSo.. we still have the following symbols missing.
tmp/new.txt renamed from tmp/old.txt +0
-0tmp/new.txt radeon_cs_need_flush · line 32
Quoted 4 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -29,7 +29,6 @@ radeon_cs_need_flush radeon_cs_print radeon_cs_set_limit radeon_cs_space_add_persistent_bo -radeon_cs_space_checkHa, I missed that one because my grep found the one with the
_with_bosuffix which was properly exported... :eyeroll:
I'll send a v2 in a bit with that added.Quoted 11 lines
tmp/new.txt renamed from tmp/old.txt +0
-0radeon_cs_space_check_with_bo radeon_cs_space_reset_bos radeon_cs_space_set_flushtmp/new.txt renamed from tmp/old.txt +0
-0@@ -4,13 +4,9 @@ omap_bo_cpu_fini omap_bo_cpu_prep omap_bo_del omap_bo_dmabuftmp/new.txt omap_bo_cpu_fini · line 12
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-4-omap_bo_from_dmabuf -omap_bo_from_name omap_bo_get_name omap_bo_handle omap_bo_map -omap_bo_new -omap_bo_new_tiled omap_bo_ref omap_bo_size omap_device_delThese ones actually do have the
drm_publicannotation, although it was not written the "normal way", which might be why it's not working?For example:
Quoted 7 lines
struct omap_bo * drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name) { ...I guess from your script above that they are actually not exported? Could you double-check, and send a patch for these omap ones? Thanks :)
Actually, I went ahead and did that patch anyway, sending it in a minute.
Quoted 58 lines
tmp/new.txt fd_bo_cpu_prep · line 6
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -3,7 +3,6 @@ fd_bo_cpu_prep fd_bo_del fd_bo_dmabuf fd_bo_from_dmabuf -fd_bo_from_fbdevThis one is actually all good:
drm_publicstructfd_bo*fd_bo_from_fbdev(struct fd_pipe *pipe, int fbfd, uint32_t size)It is hidden behind
!HAVE_FREEDRENO_KGSLwhich is itself controlled by-D freedreno-kgsl=falseon meson; make sure you're using the same config for your before/after comparison :)Quoted 39 lines
tmp/new.txt renamed from tmp/old.txt +0
-0fd_bo_from_handle fd_bo_from_name fd_bo_get_iovaI hope I'm covering everything now.
Thanks
Lucas De MarchiQuoted 30 lines
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +2
-2@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; }
Quoted 9 lines
Quoted 9 lines
Quoted 9 lines
intel/intel_bufmgr_fake.c +1
-1-void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
PATCH 1/1 omap: fix symbol annotations
--- omap/omap_drm.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)
omap/omap_drm.c +12 -12
@@ -128,8 +128,8 @@ drm_public void omap_device_del(struct omap_device *dev)free (dev); } -int -drm_public omap_get_param(struct omap_device *dev, uint64_t param, uint64_t *value) +drm_public int +omap_get_param (struct omap_device *dev,uint64_t param,uint64_t *value) {struct drm_omap_param req = { .param = param,
@@ -146,8 +146,8 @@ drm_public omap_get_param(struct omap_device *dev, uint64_t param, uint64_t *valreturn 0 ; } -int -drm_public omap_set_param(struct omap_device *dev, uint64_t param, uint64_t value) +drm_public int +omap_set_param (struct omap_device *dev,uint64_t param,uint64_t value) {struct drm_omap_param req = { .param = param,
@@ -226,8 +226,8 @@ static struct omap_bo * omap_bo_new_impl(struct omap_device *dev,/* allocate a new (un-tiled) buffer object */ -struct omap_bo * -drm_public omap_bo_new(struct omap_device *dev, uint32_t size, uint32_t flags) +drm_public struct omap_bo * +omap_bo_new (struct omap_device *dev,uint32_t size,uint32_t flags) {union omap_gem_size gsize = { .bytes = size,
@@ -239,8 +239,8 @@ drm_public omap_bo_new(struct omap_device *dev, uint32_t size, uint32_t flags) }/* allocate a new buffer object */ -struct omap_bo * -drm_public omap_bo_new_tiled(struct omap_device *dev, uint32_t width, +drm_public struct omap_bo * +omap_bo_new_tiled (struct omap_device *dev,uint32_t width,uint32_t height,uint32_t flags) {union omap_gem_size gsize = {
@@ -281,8 +281,8 @@ static int get_buffer_info(struct omap_bo *bo) }/* import a buffer object from DRI2 name */ -struct omap_bo * -drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name) +drm_public struct omap_bo * +omap_bo_from_name (struct omap_device *dev,uint32_t name) {struct omap_bo *bo =NULL ;struct drm_gem_open req = {
@@ -315,8 +315,8 @@ drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name)* fd so caller should close() the fd when it is otherwise done * with it (even if it is still using the 'struct omap_bo *') */ -struct omap_bo * -drm_public omap_bo_from_dmabuf(struct omap_device *dev, int fd) +drm_public struct omap_bo * +omap_bo_from_dmabuf (struct omap_device *dev,int fd) {struct omap_bo *bo =NULL ;struct drm_prime_handle req = {
Signature · 7 lines
Cheers, Eric _______________________________________________ dri-devel mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/dri-devel
Re: [PATCH libdrm] omap: fix symbol annotations
Quoted 3 lines · Eric Engestrom
Fixes f3f7266d94e0354bfd97 "omap: annotate public functions"Cc Lucas De Marchi <[email protected]>Signed-off-by Eric Engestrom <[email protected]>
Lucas De Marchi
Quoted 78 lines
--- omap/omap_drm.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-)omap/omap_drm.c +12
-12@@ -128,8 +128,8 @@ drm_public void omap_device_del(struct omap_device *dev)free (dev); } -int -drm_public omap_get_param(struct omap_device *dev, uint64_t param, uint64_t *value) +drm_public int +omap_get_param (struct omap_device *dev,uint64_t param,uint64_t *value) {struct drm_omap_param req = { .param = param,@@ -146,8 +146,8 @@ drm_public omap_get_param(struct omap_device *dev, uint64_t param, uint64_t *valreturn 0 ; } -int -drm_public omap_set_param(struct omap_device *dev, uint64_t param, uint64_t value) +drm_public int +omap_set_param (struct omap_device *dev,uint64_t param,uint64_t value) {struct drm_omap_param req = { .param = param,@@ -226,8 +226,8 @@ static struct omap_bo * omap_bo_new_impl(struct omap_device *dev,/* allocate a new (un-tiled) buffer object */ -struct omap_bo * -drm_public omap_bo_new(struct omap_device *dev, uint32_t size, uint32_t flags) +drm_public struct omap_bo * +omap_bo_new (struct omap_device *dev,uint32_t size,uint32_t flags) {union omap_gem_size gsize = { .bytes = size,@@ -239,8 +239,8 @@ drm_public omap_bo_new(struct omap_device *dev, uint32_t size, uint32_t flags) }/* allocate a new buffer object */ -struct omap_bo * -drm_public omap_bo_new_tiled(struct omap_device *dev, uint32_t width, +drm_public struct omap_bo * +omap_bo_new_tiled (struct omap_device *dev,uint32_t width,uint32_t height,uint32_t flags) {union omap_gem_size gsize = {@@ -281,8 +281,8 @@ static int get_buffer_info(struct omap_bo *bo) }/* import a buffer object from DRI2 name */ -struct omap_bo * -drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name) +drm_public struct omap_bo * +omap_bo_from_name (struct omap_device *dev,uint32_t name) {struct omap_bo *bo =NULL ;struct drm_gem_open req = {@@ -315,8 +315,8 @@ drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name)* fd so caller should close() the fd when it is otherwise done * with it (even if it is still using the 'struct omap_bo *') */ -struct omap_bo * -drm_public omap_bo_from_dmabuf(struct omap_device *dev, int fd) +drm_public struct omap_bo * +omap_bo_from_dmabuf (struct omap_device *dev,int fd) {struct omap_bo *bo =NULL ;struct drm_prime_handle req = {Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 103 lines · Eric Engestrom
Quoted 46 lines · Lucas De Marchi
Quoted 5 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>Reviewed-by Lucas De Marchi <[email protected]>But for the series, I went to check what went wrong. It seems my script missed the cases in which we had more than one symbol with the same name (yes, we do have some static functions that have the same name of an exported symbol) and cases in which for some reason cscope didn't return the location of the symbold definition.
So... I decided to double check if we are now exporting all symbols that we were previously. My check is with:
$ git checkout 473e2d2 $ flags="-D amdgpu=true -D cairo-tests=true -D etnaviv=true -D exynos=true -D freedreno=true -D freedreno-kgsl=true -D intel=true -D libkms=true -D man-pages=true -D nouveau=true -D omap=true -D radeon=true -D tegra=true -D udev=true -D valgrind=true -D vc4=true -D vmwgfx=true" $ meson _buildold $ ninja -C _buildold $ git checkout master $ ls /tmp/patches/ 0001-intel-add-missing-drm-public-exports.patch 0003-radeon-add-missing-drm-public-exports.patch 0002-nouveau-add-missing-drm-public-exports.patch $ git am /tmp/patches/* $ meson _buildnew $ ninja -C _buildnew $ find _buildnew/ -name '*.so' | while read f; do fold=${f/_buildnew/_buildold} nm --dynamic --defined-only $f | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/new.txt nm --dynamic --defined-only $fold | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/old.txt git diff /tmp/old.txt /tmp/new.txt doneSo.. we still have the following symbols missing.
tmp/new.txt renamed from tmp/old.txt +0
-0tmp/new.txt radeon_cs_need_flush · line 32
Quoted 4 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -29,7 +29,6 @@ radeon_cs_need_flush radeon_cs_print radeon_cs_set_limit radeon_cs_space_add_persistent_bo -radeon_cs_space_checkHa, I missed that one because my grep found the one with the
_with_bosuffix which was properly exported... :eyeroll:
I'll send a v2 in a bit with that added.Quoted 11 lines
tmp/new.txt renamed from tmp/old.txt +0
-0radeon_cs_space_check_with_bo radeon_cs_space_reset_bos radeon_cs_space_set_flushtmp/new.txt renamed from tmp/old.txt +0
-0@@ -4,13 +4,9 @@ omap_bo_cpu_fini omap_bo_cpu_prep omap_bo_del omap_bo_dmabuftmp/new.txt omap_bo_cpu_fini · line 12
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-4-omap_bo_from_dmabuf -omap_bo_from_name omap_bo_get_name omap_bo_handle omap_bo_map -omap_bo_new -omap_bo_new_tiled omap_bo_ref omap_bo_size omap_device_delThese ones actually do have the
drm_publicannotation, although it was not written the "normal way", which might be why it's not working?For example:
struct omap_bo * drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name) { ...I guess from your script above that they are actually not exported? Could you double-check, and send a patch for these omap ones? Thanks :)
tmp/new.txt fd_bo_cpu_prep · line 6
Quoted 9 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -3,7 +3,6 @@ fd_bo_cpu_prep fd_bo_del fd_bo_dmabuf fd_bo_from_dmabuf -fd_bo_from_fbdevThis one is actually all good:
Quoted 5 lines
drm_publicstructfd_bo*fd_bo_from_fbdev(struct fd_pipe *pipe, int fbfd, uint32_t size)It is hidden behind
!HAVE_FREEDRENO_KGSLwhich is itself controlled by-D freedreno-kgsl=falseon meson; make sure you're using the same config for your before/after comparison :)
that's why I used a flags variable... to pass the same configuration flags before and after.
it's drm_public in the !HAVE_FREEDRENO_KGSL case, but is should also be drm_public when this configure flag is true. In this case the function is defined in kgsl_bo.c rather than freedreno_bo.c.
Lucas De Marchi
Quoted 40 lines
Quoted 40 lines
tmp/new.txt renamed from tmp/old.txt +0
-0fd_bo_from_handle fd_bo_from_name fd_bo_get_iovaI hope I'm covering everything now.
Thanks
Lucas De MarchiQuoted 30 lines
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +2
-2@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; }
Quoted 9 lines
Quoted 9 lines
Quoted 9 lines
intel/intel_bufmgr_fake.c +1
-1-void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 83 lines · Eric Engestrom
Quoted 46 lines · Lucas De Marchi
Quoted 5 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>Reviewed-by Lucas De Marchi <[email protected]>But for the series, I went to check what went wrong. It seems my script missed the cases in which we had more than one symbol with the same name (yes, we do have some static functions that have the same name of an exported symbol) and cases in which for some reason cscope didn't return the location of the symbold definition.
So... I decided to double check if we are now exporting all symbols that we were previously. My check is with:
$ git checkout 473e2d2 $ flags="-D amdgpu=true -D cairo-tests=true -D etnaviv=true -D exynos=true -D freedreno=true -D freedreno-kgsl=true -D intel=true -D libkms=true -D man-pages=true -D nouveau=true -D omap=true -D radeon=true -D tegra=true -D udev=true -D valgrind=true -D vc4=true -D vmwgfx=true" $ meson _buildold $ ninja -C _buildold $ git checkout master $ ls /tmp/patches/ 0001-intel-add-missing-drm-public-exports.patch 0003-radeon-add-missing-drm-public-exports.patch 0002-nouveau-add-missing-drm-public-exports.patch $ git am /tmp/patches/* $ meson _buildnew $ ninja -C _buildnew $ find _buildnew/ -name '*.so' | while read f; do fold=${f/_buildnew/_buildold} nm --dynamic --defined-only $f | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/new.txt nm --dynamic --defined-only $fold | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/old.txt git diff /tmp/old.txt /tmp/new.txt doneSo.. we still have the following symbols missing.
tmp/new.txt renamed from tmp/old.txt +0
-0tmp/new.txt radeon_cs_need_flush · line 32
Quoted 4 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -29,7 +29,6 @@ radeon_cs_need_flush radeon_cs_print radeon_cs_set_limit radeon_cs_space_add_persistent_bo -radeon_cs_space_checkHa, I missed that one because my grep found the one with the
_with_bosuffix which was properly exported... :eyeroll:
I'll send a v2 in a bit with that added.Quoted 11 lines
tmp/new.txt renamed from tmp/old.txt +0
-0radeon_cs_space_check_with_bo radeon_cs_space_reset_bos radeon_cs_space_set_flushtmp/new.txt renamed from tmp/old.txt +0
-0@@ -4,13 +4,9 @@ omap_bo_cpu_fini omap_bo_cpu_prep omap_bo_del omap_bo_dmabuftmp/new.txt omap_bo_cpu_fini · line 12
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-4-omap_bo_from_dmabuf -omap_bo_from_name omap_bo_get_name omap_bo_handle omap_bo_map -omap_bo_new -omap_bo_new_tiled omap_bo_ref omap_bo_size omap_device_delThese ones actually do have the
drm_publicannotation, although it was not written the "normal way", which might be why it's not working?For example:
Quoted 7 lines
struct omap_bo * drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name) { ...I guess from your script above that they are actually not exported? Could you double-check, and send a patch for these omap ones? Thanks :)
I double checked everything. With your patches applied (including the omap one and the radeon_cs_space_check) and the additional drm_public in fd_bo_from_fbdev, then it passes the symbol check I did with before vs after.
thanks for fixing my breakage.
Lucas De Marchi
Quoted 58 lines
tmp/new.txt fd_bo_cpu_prep · line 6
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -3,7 +3,6 @@ fd_bo_cpu_prep fd_bo_del fd_bo_dmabuf fd_bo_from_dmabuf -fd_bo_from_fbdevThis one is actually all good:
drm_publicstructfd_bo*fd_bo_from_fbdev(struct fd_pipe *pipe, int fbfd, uint32_t size)It is hidden behind
!HAVE_FREEDRENO_KGSLwhich is itself controlled by-D freedreno-kgsl=falseon meson; make sure you're using the same config for your before/after comparison :)Quoted 39 lines
tmp/new.txt renamed from tmp/old.txt +0
-0fd_bo_from_handle fd_bo_from_name fd_bo_get_iovaI hope I'm covering everything now.
Thanks
Lucas De MarchiQuoted 30 lines
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +2
-2@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; }
Quoted 9 lines
Quoted 9 lines
Quoted 9 lines
intel/intel_bufmgr_fake.c +1
-1-void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 89 lines · Lucas De Marchi
Quoted 88 lines · Eric Engestrom
Quoted 46 lines · Lucas De Marchi
Quoted 5 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>Reviewed-by Lucas De Marchi <[email protected]>But for the series, I went to check what went wrong. It seems my script missed the cases in which we had more than one symbol with the same name (yes, we do have some static functions that have the same name of an exported symbol) and cases in which for some reason cscope didn't return the location of the symbold definition.
So... I decided to double check if we are now exporting all symbols that we were previously. My check is with:
$ git checkout 473e2d2 $ flags="-D amdgpu=true -D cairo-tests=true -D etnaviv=true -D exynos=true -D freedreno=true -D freedreno-kgsl=true -D intel=true -D libkms=true -D man-pages=true -D nouveau=true -D omap=true -D radeon=true -D tegra=true -D udev=true -D valgrind=true -D vc4=true -D vmwgfx=true" $ meson _buildold $ ninja -C _buildold $ git checkout master $ ls /tmp/patches/ 0001-intel-add-missing-drm-public-exports.patch 0003-radeon-add-missing-drm-public-exports.patch 0002-nouveau-add-missing-drm-public-exports.patch $ git am /tmp/patches/* $ meson _buildnew $ ninja -C _buildnew $ find _buildnew/ -name '*.so' | while read f; do fold=${f/_buildnew/_buildold} nm --dynamic --defined-only $f | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/new.txt nm --dynamic --defined-only $fold | grep -i " T " | cut -d' ' -f3 | sort -u > /tmp/old.txt git diff /tmp/old.txt /tmp/new.txt doneSo.. we still have the following symbols missing.
tmp/new.txt renamed from tmp/old.txt +0
-0tmp/new.txt radeon_cs_need_flush · line 32
Quoted 4 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -29,7 +29,6 @@ radeon_cs_need_flush radeon_cs_print radeon_cs_set_limit radeon_cs_space_add_persistent_bo -radeon_cs_space_checkHa, I missed that one because my grep found the one with the
_with_bosuffix which was properly exported... :eyeroll:
I'll send a v2 in a bit with that added.Quoted 11 lines
tmp/new.txt renamed from tmp/old.txt +0
-0radeon_cs_space_check_with_bo radeon_cs_space_reset_bos radeon_cs_space_set_flushtmp/new.txt renamed from tmp/old.txt +0
-0@@ -4,13 +4,9 @@ omap_bo_cpu_fini omap_bo_cpu_prep omap_bo_del omap_bo_dmabuftmp/new.txt omap_bo_cpu_fini · line 12
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-4-omap_bo_from_dmabuf -omap_bo_from_name omap_bo_get_name omap_bo_handle omap_bo_map -omap_bo_new -omap_bo_new_tiled omap_bo_ref omap_bo_size omap_device_delThese ones actually do have the
drm_publicannotation, although it was not written the "normal way", which might be why it's not working?For example:
struct omap_bo * drm_public omap_bo_from_name(struct omap_device *dev, uint32_t name) { ...
Quoted 6 lines
Quoted 2 lines
I guess from your script above that they are actually not exported? Could you double-check, and send a patch for these omap ones? Thanks :)
I double checked everything. With your patches applied (including the omap one and the
radeon_cs_space_check) and the additionaldrm_publicinfd_bo_from_fbdev, then it passes the symbol check I did with before vs after.
OK, I pushed everything (including the freedreno one, which was technically not reviewed, but I'm going home and I'd rather not leave it like that).
Quoted 2 lines
thanks for fixing my breakage.
Sure, and thanks for helping me :)
Quoted 61 lines
Lucas De Marchi
Quoted 58 lines
tmp/new.txt fd_bo_cpu_prep · line 6
Quoted 10 lines
tmp/new.txt renamed from tmp/old.txt +0
-1@@ -3,7 +3,6 @@ fd_bo_cpu_prep fd_bo_del fd_bo_dmabuf fd_bo_from_dmabuf -fd_bo_from_fbdevThis one is actually all good:
drm_publicstructfd_bo*fd_bo_from_fbdev(struct fd_pipe *pipe, int fbfd, uint32_t size)It is hidden behind
!HAVE_FREEDRENO_KGSLwhich is itself controlled by-D freedreno-kgsl=falseon meson; make sure you're using the same config for your before/after comparison :)Quoted 39 lines
tmp/new.txt renamed from tmp/old.txt +0
-0fd_bo_from_handle fd_bo_from_name fd_bo_get_iovaI hope I'm covering everything now.
Thanks
Lucas De MarchiQuoted 30 lines
--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +2
-2@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; }
Quoted 9 lines
Quoted 9 lines
Quoted 9 lines
Quoted 9 lines
intel/intel_bufmgr_fake.c +1
-1-void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoting Eric Engestrom (2018-09-20 08:58:32)
Quoted 44 lines
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)intel/intel_bufmgr_fake.c +3
-3@@ -241,7 +241,7 @@ FENCE_LTE(unsigned a, unsigned b)return 0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_fence_callback(drm_intel_bufmgr *bufmgr, unsigned int (*emit) (void *priv), void (*wait) (unsigned int fence,@@ -955,7 +955,7 @@ drm_intel_fake_bo_unreference(drm_intel_bo *bo)* Set the buffer as not requiring backing store, and instead get the callback * invoked whenever it would be set dirty. */ -void +drm_public void drm_intel_bo_fake_disable_backing_store(drm_intel_bo *bo, void (*invalidate_cb) (drm_intel_bo *bo, void *ptr),@@ -1409,7 +1409,7 @@ drm_intel_bo_fake_post_submit(drm_intel_bo *bo) bo_fake->write_domain =0 ; } -void +drm_public void drm_intel_bufmgr_fake_set_exec_callback(drm_intel_bufmgr *bufmgr, int (*exec) (drm_intel_bo *bo, unsigned int used,Signature · 2 lines
Cheers, Eric
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 9 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
This indicated my earlier concern it's not an issue of drm_public vs drm_private - people simply forget to run make check.
As said earlier - if you want this in Intel sure, but don't push it onto others.
Thanks
Emil
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 10 lines · Emil Velikov
Quoted 9 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
Quoted 2 lines
This indicated my earlier concern it's not an issue of
drm_publicvsdrm_private- people simply forget to run make check.
Actually, this is a limitation of the current symbol check system: it only checks that nothing is exported when it shouldn't be, but it doesn't check that what should be exported actually is.
My symbols check series fixes that and would've caught these; I really need to find the time to finish it :/
Quoted 1 line
As said earlier - if you want this in Intel sure, but don't push it onto others.
Intel or not isn't the issue here, but I understand your concern. If someone using one of those broken compilers raises a bug, we might have to reconsider and revert it, but for now let's just try to fix it :)
Quoted 3 lines
Thanks
Emil
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel
Quoted 10 lines · Emil Velikov
Quoted 9 lines · Eric Engestrom
Fixes 36bb0ea47b71d220b31e "intel: annotate public functions"Cc Lucas De Marchi <[email protected]>Cc Mark Janes <[email protected]>Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108006
Signed-off-by Eric Engestrom <[email protected]>--- intel/intel_bufmgr_fake.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
Quoted 2 lines
This indicated my earlier concern it's not an issue of
drm_publicvsdrm_private- people simply forget to run make check.
make check with all build systems was passing, this was not the problem
Quoted 1 line
As said earlier - if you want this in Intel sure, but don't push it onto others.
I will respond to this in the other thread.
Lucas De Marchi
Quoted 3 lines
Thanks
Emil
_______________________________________________
dri-devel mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/dri-devel