| Message ID | 20230727101352.1899466-6-tvrtko.ursulin@linux.intel.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | fdinfo memory stats | expand |
On 27-07-2023 15:43, Tvrtko Ursulin wrote: > From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> > > Use the newly added drm_print_memory_stats helper to show memory > utilisation of our objects in drm/driver specific fdinfo output. > > To collect the stats we walk the per memory regions object lists > and accumulate object size into the respective drm_memory_stats > categories. > > Objects with multiple possible placements are reported in multiple > regions for total and shared sizes, while other categories are > counted only for the currently active region. > > Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> > Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com> > Cc: Rob Clark <robdclark@gmail.com>> --- > drivers/gpu/drm/i915/i915_drm_client.c | 85 ++++++++++++++++++++++++++ > 1 file changed, 85 insertions(+) > > diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c > index a61356012df8..9e7a6075ee25 100644 > --- a/drivers/gpu/drm/i915/i915_drm_client.c > +++ b/drivers/gpu/drm/i915/i915_drm_client.c > @@ -45,6 +45,89 @@ void __i915_drm_client_free(struct kref *kref) > } > > #ifdef CONFIG_PROC_FS > +static void > +obj_meminfo(struct drm_i915_gem_object *obj, > + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN]) > +{ > + struct intel_memory_region *mr; > + u64 sz = obj->base.size; > + enum intel_region_id id; > + unsigned int i; > + > + /* Attribute size and shared to all possible memory regions. */ > + for (i = 0; i < obj->mm.n_placements; i++) { > + mr = obj->mm.placements[i]; > + id = mr->id; > + > + if (obj->base.handle_count > 1) > + stats[id].shared += sz; > + else > + stats[id].private += sz; > + } > + > + /* Attribute other categories to only the current region. */ > + mr = obj->mm.region; > + if (mr) > + id = mr->id; > + else > + id = INTEL_REGION_SMEM; > + > + if (!obj->mm.n_placements) { I guess we do not expect to have n_placements set to public objects, is that right? Thanks, Aravind. > + if (obj->base.handle_count > 1) > + stats[id].shared += sz; > + else > + stats[id].private += sz; > + } > + > + if (i915_gem_object_has_pages(obj)) { > + stats[id].resident += sz; > + > + if (!dma_resv_test_signaled(obj->base.resv, > + dma_resv_usage_rw(true))) > + stats[id].active += sz; > + else if (i915_gem_object_is_shrinkable(obj) && > + obj->mm.madv == I915_MADV_DONTNEED) > + stats[id].purgeable += sz; > + } > +} > + > +static void show_meminfo(struct drm_printer *p, struct drm_file *file) > +{ > + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN] = {}; > + struct drm_i915_file_private *fpriv = file->driver_priv; > + struct i915_drm_client *client = fpriv->client; > + struct drm_i915_private *i915 = fpriv->i915; > + struct drm_i915_gem_object *obj; > + struct intel_memory_region *mr; > + struct list_head *pos; > + unsigned int id; > + > + /* Public objects. */ > + spin_lock(&file->table_lock); > + idr_for_each_entry(&file->object_idr, obj, id) > + obj_meminfo(obj, stats); > + spin_unlock(&file->table_lock); > + > + /* Internal objects. */ > + rcu_read_lock(); > + list_for_each_rcu(pos, &client->objects_list) { > + obj = i915_gem_object_get_rcu(list_entry(pos, typeof(*obj), > + client_link)); > + if (!obj) > + continue; > + obj_meminfo(obj, stats); > + i915_gem_object_put(obj); > + } > + rcu_read_unlock(); > + > + for_each_memory_region(mr, i915, id) > + drm_print_memory_stats(p, > + &stats[id], > + DRM_GEM_OBJECT_RESIDENT | > + DRM_GEM_OBJECT_PURGEABLE, > + mr->name); > +} > + > static const char * const uabi_class_names[] = { > [I915_ENGINE_CLASS_RENDER] = "render", > [I915_ENGINE_CLASS_COPY] = "copy", > @@ -106,6 +189,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file) > * ****************************************************************** > */ > > + show_meminfo(p, file); > + > if (GRAPHICS_VER(i915) < 8) > return; >
On 03/08/2023 06:15, Iddamsetty, Aravind wrote: > On 27-07-2023 15:43, Tvrtko Ursulin wrote: >> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> >> >> Use the newly added drm_print_memory_stats helper to show memory >> utilisation of our objects in drm/driver specific fdinfo output. >> >> To collect the stats we walk the per memory regions object lists >> and accumulate object size into the respective drm_memory_stats >> categories. >> >> Objects with multiple possible placements are reported in multiple >> regions for total and shared sizes, while other categories are >> counted only for the currently active region. >> >> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> >> Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com> >> Cc: Rob Clark <robdclark@gmail.com>> --- >> drivers/gpu/drm/i915/i915_drm_client.c | 85 ++++++++++++++++++++++++++ >> 1 file changed, 85 insertions(+) >> >> diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c >> index a61356012df8..9e7a6075ee25 100644 >> --- a/drivers/gpu/drm/i915/i915_drm_client.c >> +++ b/drivers/gpu/drm/i915/i915_drm_client.c >> @@ -45,6 +45,89 @@ void __i915_drm_client_free(struct kref *kref) >> } >> >> #ifdef CONFIG_PROC_FS >> +static void >> +obj_meminfo(struct drm_i915_gem_object *obj, >> + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN]) >> +{ >> + struct intel_memory_region *mr; >> + u64 sz = obj->base.size; >> + enum intel_region_id id; >> + unsigned int i; >> + >> + /* Attribute size and shared to all possible memory regions. */ >> + for (i = 0; i < obj->mm.n_placements; i++) { >> + mr = obj->mm.placements[i]; >> + id = mr->id; >> + >> + if (obj->base.handle_count > 1) >> + stats[id].shared += sz; >> + else >> + stats[id].private += sz; >> + } >> + >> + /* Attribute other categories to only the current region. */ >> + mr = obj->mm.region; >> + if (mr) >> + id = mr->id; >> + else >> + id = INTEL_REGION_SMEM; >> + >> + if (!obj->mm.n_placements) { > > I guess we do not expect to have n_placements set to public objects, is > that right? I think they are the only ones which can have placements. It is via I915_GEM_CREATE_EXT_MEMORY_REGIONS userspace is able to create them. My main conundrum in this patch is a few lines above, the loop which adds shared and private. Question is, if an object can be either smem or lmem, how do we want to report it? This patch adds the size for all possible regions and resident and active only to the currently active. But perhaps that is wrong. Maybe I should change it is only against the active region and multiple regions are just ignored. Then if object is migrated do access patterns or memory pressure, the total size would migrate too. I think I was trying to achieve something here (have more visibility on what kind of backing store clients are allocating) which maybe does not work to well with the current categories. Namely if userspace allocates say one 1MiB object with placement in either smem or lmem, and it is currently resident in lmem, I wanted it to show as: total-smem: 1 MiB resident-smem: 0 total-lmem: 1 MiB resident-lmem: 1 MiB To constantly show how in theory client could be using memory from either region. Maybe that is misleading and should instead be: total-smem: 0 resident-smem: 0 total-lmem: 1 MiB resident-lmem: 1 MiB ? And then if/when the same object gets migrated to smem it changes to (lets assume it is also not resident any more but got swapped out): total-smem: 1 MiB resident-smem: 0 total-lmem: 0 resident-lmem: 0 Regards, Tvrtko >> + if (obj->base.handle_count > 1) >> + stats[id].shared += sz; >> + else >> + stats[id].private += sz; >> + } >> + >> + if (i915_gem_object_has_pages(obj)) { >> + stats[id].resident += sz; >> + >> + if (!dma_resv_test_signaled(obj->base.resv, >> + dma_resv_usage_rw(true))) >> + stats[id].active += sz; >> + else if (i915_gem_object_is_shrinkable(obj) && >> + obj->mm.madv == I915_MADV_DONTNEED) >> + stats[id].purgeable += sz; >> + } >> +} >> + >> +static void show_meminfo(struct drm_printer *p, struct drm_file *file) >> +{ >> + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN] = {}; >> + struct drm_i915_file_private *fpriv = file->driver_priv; >> + struct i915_drm_client *client = fpriv->client; >> + struct drm_i915_private *i915 = fpriv->i915; >> + struct drm_i915_gem_object *obj; >> + struct intel_memory_region *mr; >> + struct list_head *pos; >> + unsigned int id; >> + >> + /* Public objects. */ >> + spin_lock(&file->table_lock); >> + idr_for_each_entry(&file->object_idr, obj, id) >> + obj_meminfo(obj, stats); >> + spin_unlock(&file->table_lock); >> + >> + /* Internal objects. */ >> + rcu_read_lock(); >> + list_for_each_rcu(pos, &client->objects_list) { >> + obj = i915_gem_object_get_rcu(list_entry(pos, typeof(*obj), >> + client_link)); >> + if (!obj) >> + continue; >> + obj_meminfo(obj, stats); >> + i915_gem_object_put(obj); >> + } >> + rcu_read_unlock(); >> + >> + for_each_memory_region(mr, i915, id) >> + drm_print_memory_stats(p, >> + &stats[id], >> + DRM_GEM_OBJECT_RESIDENT | >> + DRM_GEM_OBJECT_PURGEABLE, >> + mr->name); >> +} >> + >> static const char * const uabi_class_names[] = { >> [I915_ENGINE_CLASS_RENDER] = "render", >> [I915_ENGINE_CLASS_COPY] = "copy", >> @@ -106,6 +189,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file) >> * ****************************************************************** >> */ >> >> + show_meminfo(p, file); >> + >> if (GRAPHICS_VER(i915) < 8) >> return; >> > > >
On 03-08-2023 14:19, Tvrtko Ursulin wrote: > > On 03/08/2023 06:15, Iddamsetty, Aravind wrote: >> On 27-07-2023 15:43, Tvrtko Ursulin wrote: >>> From: Tvrtko Ursulin <tvrtko.ursulin@intel.com> >>> >>> Use the newly added drm_print_memory_stats helper to show memory >>> utilisation of our objects in drm/driver specific fdinfo output. >>> >>> To collect the stats we walk the per memory regions object lists >>> and accumulate object size into the respective drm_memory_stats >>> categories. >>> >>> Objects with multiple possible placements are reported in multiple >>> regions for total and shared sizes, while other categories are >>> counted only for the currently active region. >>> >>> Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> >>> Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com> >>> Cc: Rob Clark <robdclark@gmail.com>> --- >>> drivers/gpu/drm/i915/i915_drm_client.c | 85 ++++++++++++++++++++++++++ >>> 1 file changed, 85 insertions(+) >>> >>> diff --git a/drivers/gpu/drm/i915/i915_drm_client.c >>> b/drivers/gpu/drm/i915/i915_drm_client.c >>> index a61356012df8..9e7a6075ee25 100644 >>> --- a/drivers/gpu/drm/i915/i915_drm_client.c >>> +++ b/drivers/gpu/drm/i915/i915_drm_client.c >>> @@ -45,6 +45,89 @@ void __i915_drm_client_free(struct kref *kref) >>> } >>> #ifdef CONFIG_PROC_FS >>> +static void >>> +obj_meminfo(struct drm_i915_gem_object *obj, >>> + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN]) >>> +{ >>> + struct intel_memory_region *mr; >>> + u64 sz = obj->base.size; >>> + enum intel_region_id id; >>> + unsigned int i; >>> + >>> + /* Attribute size and shared to all possible memory regions. */ >>> + for (i = 0; i < obj->mm.n_placements; i++) { >>> + mr = obj->mm.placements[i]; >>> + id = mr->id; >>> + >>> + if (obj->base.handle_count > 1) >>> + stats[id].shared += sz; >>> + else >>> + stats[id].private += sz; >>> + } >>> + >>> + /* Attribute other categories to only the current region. */ >>> + mr = obj->mm.region; >>> + if (mr) >>> + id = mr->id; >>> + else >>> + id = INTEL_REGION_SMEM; >>> + >>> + if (!obj->mm.n_placements) { >> >> I guess we do not expect to have n_placements set to public objects, is >> that right? > > I think they are the only ones which can have placements. It is via > I915_GEM_CREATE_EXT_MEMORY_REGIONS userspace is able to create them. > > My main conundrum in this patch is a few lines above, the loop which > adds shared and private. > > Question is, if an object can be either smem or lmem, how do we want to > report it? This patch adds the size for all possible regions and > resident and active only to the currently active. But perhaps that is > wrong. Maybe I should change it is only against the active region and > multiple regions are just ignored. Then if object is migrated do access > patterns or memory pressure, the total size would migrate too. > > I think I was trying to achieve something here (have more visibility on > what kind of backing store clients are allocating) which maybe does not > work to well with the current categories. > > Namely if userspace allocates say one 1MiB object with placement in > either smem or lmem, and it is currently resident in lmem, I wanted it > to show as: > > total-smem: 1 MiB > resident-smem: 0 > total-lmem: 1 MiB > resident-lmem: 1 MiB > > To constantly show how in theory client could be using memory from > either region. Maybe that is misleading and should instead be: > > total-smem: 0 > resident-smem: 0 > total-lmem: 1 MiB > resident-lmem: 1 MiB > > ? I think the current implementation will not match with the memregion info in query ioctl as well. While what you say is true I'm not sure if there can be a client who is tracking the allocation say for an obj who has 2 placements LMEM and SMEM, and might assume since I had made a reservation in SMEM it shall not fail when i try to migrate there later. Thanks, Aravind. > > And then if/when the same object gets migrated to smem it changes to > (lets assume it is also not resident any more but got swapped out): > > total-smem: 1 MiB > resident-smem: 0 > total-lmem: 0 > resident-lmem: 0 > > Regards, > > Tvrtko > >>> + if (obj->base.handle_count > 1) >>> + stats[id].shared += sz; >>> + else >>> + stats[id].private += sz; >>> + } >>> + >>> + if (i915_gem_object_has_pages(obj)) { >>> + stats[id].resident += sz; >>> + >>> + if (!dma_resv_test_signaled(obj->base.resv, >>> + dma_resv_usage_rw(true))) >>> + stats[id].active += sz; >>> + else if (i915_gem_object_is_shrinkable(obj) && >>> + obj->mm.madv == I915_MADV_DONTNEED) >>> + stats[id].purgeable += sz; >>> + } >>> +} >>> + >>> +static void show_meminfo(struct drm_printer *p, struct drm_file *file) >>> +{ >>> + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN] = {}; >>> + struct drm_i915_file_private *fpriv = file->driver_priv; >>> + struct i915_drm_client *client = fpriv->client; >>> + struct drm_i915_private *i915 = fpriv->i915; >>> + struct drm_i915_gem_object *obj; >>> + struct intel_memory_region *mr; >>> + struct list_head *pos; >>> + unsigned int id; >>> + >>> + /* Public objects. */ >>> + spin_lock(&file->table_lock); >>> + idr_for_each_entry(&file->object_idr, obj, id) >>> + obj_meminfo(obj, stats); >>> + spin_unlock(&file->table_lock); >>> + >>> + /* Internal objects. */ >>> + rcu_read_lock(); >>> + list_for_each_rcu(pos, &client->objects_list) { >>> + obj = i915_gem_object_get_rcu(list_entry(pos, typeof(*obj), >>> + client_link)); >>> + if (!obj) >>> + continue; >>> + obj_meminfo(obj, stats); >>> + i915_gem_object_put(obj); >>> + } >>> + rcu_read_unlock(); >>> + >>> + for_each_memory_region(mr, i915, id) >>> + drm_print_memory_stats(p, >>> + &stats[id], >>> + DRM_GEM_OBJECT_RESIDENT | >>> + DRM_GEM_OBJECT_PURGEABLE, >>> + mr->name); >>> +} >>> + >>> static const char * const uabi_class_names[] = { >>> [I915_ENGINE_CLASS_RENDER] = "render", >>> [I915_ENGINE_CLASS_COPY] = "copy", >>> @@ -106,6 +189,8 @@ void i915_drm_client_fdinfo(struct drm_printer >>> *p, struct drm_file *file) >>> * >>> ****************************************************************** >>> */ >>> + show_meminfo(p, file); >>> + >>> if (GRAPHICS_VER(i915) < 8) >>> return; >>> >> >> >>
diff --git a/drivers/gpu/drm/i915/i915_drm_client.c b/drivers/gpu/drm/i915/i915_drm_client.c index a61356012df8..9e7a6075ee25 100644 --- a/drivers/gpu/drm/i915/i915_drm_client.c +++ b/drivers/gpu/drm/i915/i915_drm_client.c @@ -45,6 +45,89 @@ void __i915_drm_client_free(struct kref *kref) } #ifdef CONFIG_PROC_FS +static void +obj_meminfo(struct drm_i915_gem_object *obj, + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN]) +{ + struct intel_memory_region *mr; + u64 sz = obj->base.size; + enum intel_region_id id; + unsigned int i; + + /* Attribute size and shared to all possible memory regions. */ + for (i = 0; i < obj->mm.n_placements; i++) { + mr = obj->mm.placements[i]; + id = mr->id; + + if (obj->base.handle_count > 1) + stats[id].shared += sz; + else + stats[id].private += sz; + } + + /* Attribute other categories to only the current region. */ + mr = obj->mm.region; + if (mr) + id = mr->id; + else + id = INTEL_REGION_SMEM; + + if (!obj->mm.n_placements) { + if (obj->base.handle_count > 1) + stats[id].shared += sz; + else + stats[id].private += sz; + } + + if (i915_gem_object_has_pages(obj)) { + stats[id].resident += sz; + + if (!dma_resv_test_signaled(obj->base.resv, + dma_resv_usage_rw(true))) + stats[id].active += sz; + else if (i915_gem_object_is_shrinkable(obj) && + obj->mm.madv == I915_MADV_DONTNEED) + stats[id].purgeable += sz; + } +} + +static void show_meminfo(struct drm_printer *p, struct drm_file *file) +{ + struct drm_memory_stats stats[INTEL_REGION_UNKNOWN] = {}; + struct drm_i915_file_private *fpriv = file->driver_priv; + struct i915_drm_client *client = fpriv->client; + struct drm_i915_private *i915 = fpriv->i915; + struct drm_i915_gem_object *obj; + struct intel_memory_region *mr; + struct list_head *pos; + unsigned int id; + + /* Public objects. */ + spin_lock(&file->table_lock); + idr_for_each_entry(&file->object_idr, obj, id) + obj_meminfo(obj, stats); + spin_unlock(&file->table_lock); + + /* Internal objects. */ + rcu_read_lock(); + list_for_each_rcu(pos, &client->objects_list) { + obj = i915_gem_object_get_rcu(list_entry(pos, typeof(*obj), + client_link)); + if (!obj) + continue; + obj_meminfo(obj, stats); + i915_gem_object_put(obj); + } + rcu_read_unlock(); + + for_each_memory_region(mr, i915, id) + drm_print_memory_stats(p, + &stats[id], + DRM_GEM_OBJECT_RESIDENT | + DRM_GEM_OBJECT_PURGEABLE, + mr->name); +} + static const char * const uabi_class_names[] = { [I915_ENGINE_CLASS_RENDER] = "render", [I915_ENGINE_CLASS_COPY] = "copy", @@ -106,6 +189,8 @@ void i915_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file) * ****************************************************************** */ + show_meminfo(p, file); + if (GRAPHICS_VER(i915) < 8) return;