search for: perfmon

Hi folks, This set of patches is just for clearing the way before introducing the infrastructure for performance counters in perfmon. I'll try to publish a new version of my kernel interface based on nvif in a couple of days. See you.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com> --- nvkm/engine/perfmon/base.c | 20 -------------------- nvkm/engine/perfmon/priv.h | 3 --- 2 files changed, 23 deletions(-) diff --git a/nvkm/engine/perfmon/base.c b/nvkm/engine/perfmon/base.c index 5fa45e1..b74734e 100644 --- a/nvkm/engine/perfmon/base.c +++ b/nvkm/engine/perfmon/base.c @@ -80,26 +80,6 @@ nouveau_pe...

This fixes a crash when we reload Nouveau DRM. Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com> --- nvkm/engine/perfmon/base.c | 1 + 1 file changed, 1 insertion(+) diff --git a/nvkm/engine/perfmon/base.c b/nvkm/engine/perfmon/base.c index e9c5e51..7481003 100644 --- a/nvkm/engine/perfmon/base.c +++ b/nvkm/engine/perfmon/base.c @@ -303,6 +303,7 @@ nouveau_perfctx_dtor(struct nouveau_object *object) { struct nouv...

On 8 June 2015 at 06:40, Samuel Pitoiset <samuel.pitoiset at gmail.com> wrote: > This commit introduces the NVIF_IOCTL_NEW_V0_PERFMON class which will be > used in order to query domains, signals and sources. This separates the > querying and the counting interface. Hey Samuel, I've merged patches 1-4 already, I've got some comments on this one, but after they're solved I'm happy to merge up to (and includi...

...h > +++ b/drm/nouveau/include/nvkm/subdev/clk.h > @@ -91,7 +91,7 @@ struct nvkm_clk { > > struct nvkm_notify pwrsrc_ntfy; > int pwrsrc; > - int pstate; /* current */ > + struct nvkm_pstate *pstate; /* current */ > int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ > int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ > int astate; /* perfmon adjustment (base) */ > diff --git a/drm/nouveau/nvkm/engine/device/ctrl.c b/drm/nouveau/nvkm/engine/device/ctrl.c > index 039e8a4..cb85266 100644 > --- a/drm/nouveau/nvkm/engine/device/...

...s only exposes performance counters on NV50, but this is going to be pretty similar for other families. My plan is to submit more patches for Fermi and Kepler after this series will be reviewed. The code of this series can be found here: http://cgit.freedesktop.org/~hakzsam/nouveau/log/?h=nouveau_perfmon And the corresponding libdrm branch can be found here: http://cgit.freedesktop.org/~hakzsam/drm/log/?h=nouveau_perfmon A full example which exposes both compute and graphics hardware events on NV50 can be found here: http://cgit.freedesktop.org/~hakzsam/perfevent Most of the code will be imple...

...ph/nve4.o +nouveau-$(CONFIG_DRM_NOUVEAU_NVC0) += core/engine/graph/nvf0.o +nouveau-$(CONFIG_DRM_NOUVEAU_NVC0) += core/engine/graph/nv108.o nouveau-y += core/engine/mpeg/nv31.o nouveau-y += core/engine/mpeg/nv40.o nouveau-y += core/engine/mpeg/nv44.o @@ -279,19 +279,19 @@ nouveau-y += core/engine/perfmon/nv40.o nouveau-y += core/engine/perfmon/nv50.o nouveau-y += core/engine/perfmon/nv84.o nouveau-y += core/engine/perfmon/nva3.o -nouveau-y += core/engine/perfmon/nvc0.o -nouveau-y += core/engine/perfmon/nve0.o -nouveau-y += core/engine/perfmon/nvf0.o +nouveau-$(CONFIG_DRM_NOUVEAU_NVC0) += core/en...

I''m not a windows person, so I am hoping someone can help me with this... I''ve just installed a Windows 2003 Server VM and I would like to make sure that the average disk IO wait is acceptable. In Linux and other *nixes I would normally use sar or iostat for this. I have found perfmon in windows. Will this give me the numbers I need? Thanks, Matt. _______________________________________________ Xen-users mailing list Xen-users@lists.xensource.com http://lists.xensource.com/xen-users

...IG_DRM_NOUVEAU_NVC0) += core/engine/graph/nvf0.o > +nouveau-$(CONFIG_DRM_NOUVEAU_NVC0) += core/engine/graph/nv108.o > nouveau-y += core/engine/mpeg/nv31.o > nouveau-y += core/engine/mpeg/nv40.o > nouveau-y += core/engine/mpeg/nv44.o > @@ -279,19 +279,19 @@ nouveau-y += core/engine/perfmon/nv40.o > nouveau-y += core/engine/perfmon/nv50.o > nouveau-y += core/engine/perfmon/nv84.o > nouveau-y += core/engine/perfmon/nva3.o > -nouveau-y += core/engine/perfmon/nvc0.o > -nouveau-y += core/engine/perfmon/nve0.o > -nouveau-y += core/engine/perfmon/nvf0.o > +nouveau-$(...

gcc-8 reports drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c: In function 'nvkm_perfmon_mthd': include/linux/string.h:265:9: error: '__builtin_strncpy' specified bound 64 equals destination size [-Werror=stringop-truncation] We need one less byte or call strlcpy() to make it a nul-terminated string. Signed-off-by: Arnd Bergmann <arnd at arndb.de> --- drivers/gpu/d...

...diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index b2c94cd5..69942b14 100644 --- a/drm/nouveau/include/nvkm/subdev/clk.h +++ b/drm/nouveau/include/nvkm/subdev/clk.h @@ -99,7 +99,6 @@ struct nvkm_clk { int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ int astate; /* perfmon adjustment (base) */ - int dstate; /* display adjustment (min+) */ u8 temp; bool allow_reclock; @@ -121,7 +120,6 @@ struct nvkm_clk { int nvkm_clk_read(struct nvkm_clk *, enum nv_clk_src); int nvkm...

...diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index ce3bbcfe..1340f5b8 100644 --- a/drm/nouveau/include/nvkm/subdev/clk.h +++ b/drm/nouveau/include/nvkm/subdev/clk.h @@ -99,7 +99,6 @@ struct nvkm_clk { int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ int astate; /* perfmon adjustment (base) */ - int dstate; /* display adjustment (min+) */ u8 temp; bool allow_reclock; @@ -121,7 +120,6 @@ struct nvkm_clk { int nvkm_clk_read(struct nvkm_clk *, enum nv_clk_src); int nvkm...

...re/engine/mpeg/nv31.o +nouveau-$(CONFIG_DRM_NOUVEAU_NV04) += core/engine/mpeg/nv40.o +nouveau-$(CONFIG_DRM_NOUVEAU_NV04) += core/engine/mpeg/nv44.o +nouveau-$(CONFIG_DRM_NOUVEAU_NV50) += core/engine/mpeg/nv50.o +nouveau-$(CONFIG_DRM_NOUVEAU_NV50) += core/engine/mpeg/nv84.o nouveau-y += core/engine/perfmon/base.o nouveau-y += core/engine/perfmon/daemon.o -nouveau-y += core/engine/perfmon/nv40.o -nouveau-y += core/engine/perfmon/nv50.o -nouveau-y += core/engine/perfmon/nv84.o -nouveau-y += core/engine/perfmon/nva3.o -nouveau-y += core/engine/perfmon/nvc0.o -nouveau-y += core/engine/perfmon/nve0.o -no...

...c { > nv_clk_src_crystal, > nv_clk_src_href, > @@ -95,7 +97,7 @@ struct nvkm_clk { > > struct nvkm_notify pwrsrc_ntfy; > int pwrsrc; > - int pstate; /* current */ > + struct nvkm_pstate *pstate; /* current */ > int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ > int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ > int astate; /* perfmon adjustment (base) */ > diff --git a/drm/nouveau/nvkm/engine/device/ctrl.c b/drm/nouveau/nvkm/engine/device/ctrl.c > index b0ece71a..da70626c 100644 > --- a/drm/nouveau/nvkm/engine/device/...

...) diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index 77d94c1..db52e65 100644 --- a/drm/nouveau/include/nvkm/subdev/clk.h +++ b/drm/nouveau/include/nvkm/subdev/clk.h @@ -95,8 +95,6 @@ struct nvkm_clk { int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ int astate; /* perfmon adjustment (base) */ - int tstate; /* thermal adjustment (max-) */ - int dstate; /* display adjustment (min+) */ bool allow_reclock; #define NVKM_CLK_BOOST_NONE 0x0 @@ -118,8 +116,6 @@ struct nvkm_clk...

...u/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h > index 77d94c1..db52e65 100644 > --- a/drm/nouveau/include/nvkm/subdev/clk.h > +++ b/drm/nouveau/include/nvkm/subdev/clk.h > @@ -95,8 +95,6 @@ struct nvkm_clk { > int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ > int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ > int astate; /* perfmon adjustment (base) */ > - int tstate; /* thermal adjustment (max-) */ > - int dstate; /* display adjustment (min+) */ > > bool allow_reclock; > #define NVKM_CLK_BOOST_NONE...

This series addresses various issues inside the reclocking code: 1. after resume the set clocks are reset 2. reclocking not possible while GPU is suspended Some of the patches were part of the bigger reclocking series I sent months ago, some things have changed though. This is also preparation work of changing the clock state due to temperature changes and dynamic reclocking. v2: remove commits

...diff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index 4fb2c1b..6deda96 100644 --- a/drm/nouveau/include/nvkm/subdev/clk.h +++ b/drm/nouveau/include/nvkm/subdev/clk.h @@ -95,6 +95,11 @@ struct nvkm_clk { int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ int astate; /* perfmon adjustment (base) */ + struct nvkm_cstate *set_cstate; +#define NVKM_CLK_CSTATE_DEFAULT -1 +#define NVKM_CLK_CSTATE_BASE -2 +#define NVKM_CLK_CSTATE_HIGHEST -3 + int exp_cstate; bool allow_reclock;...

This series addresses various issues inside the reclocking code: 1. after resume the set clocks are reset 2. reclocking not possible while GPU is suspended 3. racy reclocking while GPU is suspending and leading to hangs Some of the patches were part of the bigger reclocking series I sent months ago, some things have changed though. This is also preparation work of changing the clock state due to

...iff --git a/drm/nouveau/include/nvkm/subdev/clk.h b/drm/nouveau/include/nvkm/subdev/clk.h index ec537e08..f35518c3 100644 --- a/drm/nouveau/include/nvkm/subdev/clk.h +++ b/drm/nouveau/include/nvkm/subdev/clk.h @@ -101,6 +101,8 @@ struct nvkm_clk { int ustate_ac; /* user-requested (-1 disabled, -2 perfmon) */ int ustate_dc; /* user-requested (-1 disabled, -2 perfmon) */ int astate; /* perfmon adjustment (base) */ + struct nvkm_cstate *cstate; + int exp_cstateid; u8 temp; bool allow_reclock; diff --git a/drm/nouveau/nvkm/subdev/clk/base.c b/drm/nouveau/nvkm/subdev/clk/base.c index 0d4d9fdf...