Re: [RFC PATCH v3 11/11] drm, cgroup: Allow more aggressive memory reclaim
On Wed, Jun 26, 2019 at 06:52:50PM -0400, Kenny Ho wrote: > Ok. I am not too familiar with shrinker but I will dig into it. Just > so that I am looking into the right things, you are referring to > things like struct shrinker and struct shrink_control? Yeah. Reason I'm asking for this is this is how system memory is shrunk right now, so at least having some conceptual similarities might be useful here. And a lot of people have thought quite hard about system memory shrinking and all that, so hopefully that gives us good design inspiration. -Daniel > > Regards, > Kenny > > On Wed, Jun 26, 2019 at 12:44 PM Daniel Vetter wrote: > > > > On Wed, Jun 26, 2019 at 11:05:22AM -0400, Kenny Ho wrote: > > > Allow DRM TTM memory manager to register a work_struct, such that, when > > > a drmcgrp is under memory pressure, memory reclaiming can be triggered > > > immediately. > > > > > > Change-Id: I25ac04e2db9c19ff12652b88ebff18b44b2706d8 > > > Signed-off-by: Kenny Ho > > > --- > > > drivers/gpu/drm/ttm/ttm_bo.c| 47 + > > > include/drm/drm_cgroup.h| 14 ++ > > > include/drm/ttm/ttm_bo_driver.h | 2 ++ > > > kernel/cgroup/drm.c | 33 +++ > > > 4 files changed, 96 insertions(+) > > > > > > diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c > > > index 79c530f4a198..5fc3bc5bd4c5 100644 > > > --- a/drivers/gpu/drm/ttm/ttm_bo.c > > > +++ b/drivers/gpu/drm/ttm/ttm_bo.c > > > @@ -1509,6 +1509,44 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, > > > unsigned mem_type) > > > } > > > EXPORT_SYMBOL(ttm_bo_evict_mm); > > > > > > +static void ttm_bo_reclaim_wq(struct work_struct *work) > > > +{ > > > > I think a design a bit more inspired by memcg aware core shrinkers would > > be nice, i.e. explicitly passing: > > - which drm_cgroup needs to be shrunk > > - which ttm_mem_reg (well the fancy new abstracted out stuff for tracking > > special gpu memory resources like tt or vram or whatever) > > - how much it needs to be shrunk > > > > I think with that a lot more the book-keeping could be pushed into the > > drm_cgroup code, and the callback just needs to actually shrink enough as > > requested. > > -Daniel > > > > > + struct ttm_operation_ctx ctx = { > > > + .interruptible = false, > > > + .no_wait_gpu = false, > > > + .flags = TTM_OPT_FLAG_FORCE_ALLOC > > > + }; > > > + struct ttm_mem_type_manager *man = > > > + container_of(work, struct ttm_mem_type_manager, reclaim_wq); > > > + struct ttm_bo_device *bdev = man->bdev; > > > + struct dma_fence *fence; > > > + int mem_type; > > > + int ret; > > > + > > > + for (mem_type = 0; mem_type < TTM_NUM_MEM_TYPES; mem_type++) > > > + if (>man[mem_type] == man) > > > + break; > > > + > > > + BUG_ON(mem_type >= TTM_NUM_MEM_TYPES); > > > + > > > + if (!drmcgrp_mem_pressure_scan(bdev, mem_type)) > > > + return; > > > + > > > + ret = ttm_mem_evict_first(bdev, mem_type, NULL, ); > > > + if (ret) > > > + return; > > > + > > > + spin_lock(>move_lock); > > > + fence = dma_fence_get(man->move); > > > + spin_unlock(>move_lock); > > > + > > > + if (fence) { > > > + ret = dma_fence_wait(fence, false); > > > + dma_fence_put(fence); > > > + } > > > + > > > +} > > > + > > > int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type, > > > unsigned long p_size) > > > { > > > @@ -1543,6 +1581,13 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, > > > unsigned type, > > > INIT_LIST_HEAD(>lru[i]); > > > man->move = NULL; > > > > > > + pr_err("drmcgrp %p type %d\n", bdev->ddev, type); > > > + > > > + if (type <= TTM_PL_VRAM) { > > > + INIT_WORK(>reclaim_wq, ttm_bo_reclaim_wq); > > > + drmcgrp_register_device_mm(bdev->ddev, type, > > > >reclaim_wq); > > > + } > > > + > > > return 0; > > > } > > > EXPORT_SYMBOL(ttm_bo_init_mm); > > > @@ -1620,6 +1665,8 @@ int ttm_bo_device_release(struct ttm_bo_device > > > *bdev) > > > man = >man[i]; > > > if (man->has_type) { > > > man->use_type = false; > > > + drmcgrp_unregister_device_mm(bdev->ddev, i); > > > + cancel_work_sync(>reclaim_wq); > > > if ((i != TTM_PL_SYSTEM) && ttm_bo_clean_mm(bdev, > > > i)) { > > > ret = -EBUSY; > > > pr_err("DRM memory manager type %d is not > > > clean\n", > > > diff --git a/include/drm/drm_cgroup.h b/include/drm/drm_cgroup.h > > > index 360c1e6c809f..134d6e5475f3 100644 > > > --- a/include/drm/drm_cgroup.h > > > +++ b/include/drm/drm_cgroup.h > > > @@ -5,6 +5,7 @@ > > > #define __DRM_CGROUP_H__ > > > > > > #include > > > +#include > > > #include > > > #include
Re: [RFC PATCH v3 11/11] drm, cgroup: Allow more aggressive memory reclaim
Ok. I am not too familiar with shrinker but I will dig into it. Just so that I am looking into the right things, you are referring to things like struct shrinker and struct shrink_control? Regards, Kenny On Wed, Jun 26, 2019 at 12:44 PM Daniel Vetter wrote: > > On Wed, Jun 26, 2019 at 11:05:22AM -0400, Kenny Ho wrote: > > Allow DRM TTM memory manager to register a work_struct, such that, when > > a drmcgrp is under memory pressure, memory reclaiming can be triggered > > immediately. > > > > Change-Id: I25ac04e2db9c19ff12652b88ebff18b44b2706d8 > > Signed-off-by: Kenny Ho > > --- > > drivers/gpu/drm/ttm/ttm_bo.c| 47 + > > include/drm/drm_cgroup.h| 14 ++ > > include/drm/ttm/ttm_bo_driver.h | 2 ++ > > kernel/cgroup/drm.c | 33 +++ > > 4 files changed, 96 insertions(+) > > > > diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c > > index 79c530f4a198..5fc3bc5bd4c5 100644 > > --- a/drivers/gpu/drm/ttm/ttm_bo.c > > +++ b/drivers/gpu/drm/ttm/ttm_bo.c > > @@ -1509,6 +1509,44 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, > > unsigned mem_type) > > } > > EXPORT_SYMBOL(ttm_bo_evict_mm); > > > > +static void ttm_bo_reclaim_wq(struct work_struct *work) > > +{ > > I think a design a bit more inspired by memcg aware core shrinkers would > be nice, i.e. explicitly passing: > - which drm_cgroup needs to be shrunk > - which ttm_mem_reg (well the fancy new abstracted out stuff for tracking > special gpu memory resources like tt or vram or whatever) > - how much it needs to be shrunk > > I think with that a lot more the book-keeping could be pushed into the > drm_cgroup code, and the callback just needs to actually shrink enough as > requested. > -Daniel > > > + struct ttm_operation_ctx ctx = { > > + .interruptible = false, > > + .no_wait_gpu = false, > > + .flags = TTM_OPT_FLAG_FORCE_ALLOC > > + }; > > + struct ttm_mem_type_manager *man = > > + container_of(work, struct ttm_mem_type_manager, reclaim_wq); > > + struct ttm_bo_device *bdev = man->bdev; > > + struct dma_fence *fence; > > + int mem_type; > > + int ret; > > + > > + for (mem_type = 0; mem_type < TTM_NUM_MEM_TYPES; mem_type++) > > + if (>man[mem_type] == man) > > + break; > > + > > + BUG_ON(mem_type >= TTM_NUM_MEM_TYPES); > > + > > + if (!drmcgrp_mem_pressure_scan(bdev, mem_type)) > > + return; > > + > > + ret = ttm_mem_evict_first(bdev, mem_type, NULL, ); > > + if (ret) > > + return; > > + > > + spin_lock(>move_lock); > > + fence = dma_fence_get(man->move); > > + spin_unlock(>move_lock); > > + > > + if (fence) { > > + ret = dma_fence_wait(fence, false); > > + dma_fence_put(fence); > > + } > > + > > +} > > + > > int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type, > > unsigned long p_size) > > { > > @@ -1543,6 +1581,13 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, > > unsigned type, > > INIT_LIST_HEAD(>lru[i]); > > man->move = NULL; > > > > + pr_err("drmcgrp %p type %d\n", bdev->ddev, type); > > + > > + if (type <= TTM_PL_VRAM) { > > + INIT_WORK(>reclaim_wq, ttm_bo_reclaim_wq); > > + drmcgrp_register_device_mm(bdev->ddev, type, > > >reclaim_wq); > > + } > > + > > return 0; > > } > > EXPORT_SYMBOL(ttm_bo_init_mm); > > @@ -1620,6 +1665,8 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev) > > man = >man[i]; > > if (man->has_type) { > > man->use_type = false; > > + drmcgrp_unregister_device_mm(bdev->ddev, i); > > + cancel_work_sync(>reclaim_wq); > > if ((i != TTM_PL_SYSTEM) && ttm_bo_clean_mm(bdev, i)) > > { > > ret = -EBUSY; > > pr_err("DRM memory manager type %d is not > > clean\n", > > diff --git a/include/drm/drm_cgroup.h b/include/drm/drm_cgroup.h > > index 360c1e6c809f..134d6e5475f3 100644 > > --- a/include/drm/drm_cgroup.h > > +++ b/include/drm/drm_cgroup.h > > @@ -5,6 +5,7 @@ > > #define __DRM_CGROUP_H__ > > > > #include > > +#include > > #include > > #include > > > > @@ -12,6 +13,9 @@ > > > > int drmcgrp_register_device(struct drm_device *device); > > int drmcgrp_unregister_device(struct drm_device *device); > > +void drmcgrp_register_device_mm(struct drm_device *dev, unsigned type, > > + struct work_struct *wq); > > +void drmcgrp_unregister_device_mm(struct drm_device *dev, unsigned type); > > bool drmcgrp_is_self_or_ancestor(struct drmcgrp *self, > > struct drmcgrp *relative); > > void drmcgrp_chg_bo_alloc(struct drmcgrp *drmcgrp, struct drm_device *dev, > > @@ -40,6 +44,16 @@ static inline int drmcgrp_unregister_device(struct > >
Re: [RFC PATCH v3 11/11] drm, cgroup: Allow more aggressive memory reclaim
On Wed, Jun 26, 2019 at 11:05:22AM -0400, Kenny Ho wrote: > Allow DRM TTM memory manager to register a work_struct, such that, when > a drmcgrp is under memory pressure, memory reclaiming can be triggered > immediately. > > Change-Id: I25ac04e2db9c19ff12652b88ebff18b44b2706d8 > Signed-off-by: Kenny Ho > --- > drivers/gpu/drm/ttm/ttm_bo.c| 47 + > include/drm/drm_cgroup.h| 14 ++ > include/drm/ttm/ttm_bo_driver.h | 2 ++ > kernel/cgroup/drm.c | 33 +++ > 4 files changed, 96 insertions(+) > > diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c > index 79c530f4a198..5fc3bc5bd4c5 100644 > --- a/drivers/gpu/drm/ttm/ttm_bo.c > +++ b/drivers/gpu/drm/ttm/ttm_bo.c > @@ -1509,6 +1509,44 @@ int ttm_bo_evict_mm(struct ttm_bo_device *bdev, > unsigned mem_type) > } > EXPORT_SYMBOL(ttm_bo_evict_mm); > > +static void ttm_bo_reclaim_wq(struct work_struct *work) > +{ I think a design a bit more inspired by memcg aware core shrinkers would be nice, i.e. explicitly passing: - which drm_cgroup needs to be shrunk - which ttm_mem_reg (well the fancy new abstracted out stuff for tracking special gpu memory resources like tt or vram or whatever) - how much it needs to be shrunk I think with that a lot more the book-keeping could be pushed into the drm_cgroup code, and the callback just needs to actually shrink enough as requested. -Daniel > + struct ttm_operation_ctx ctx = { > + .interruptible = false, > + .no_wait_gpu = false, > + .flags = TTM_OPT_FLAG_FORCE_ALLOC > + }; > + struct ttm_mem_type_manager *man = > + container_of(work, struct ttm_mem_type_manager, reclaim_wq); > + struct ttm_bo_device *bdev = man->bdev; > + struct dma_fence *fence; > + int mem_type; > + int ret; > + > + for (mem_type = 0; mem_type < TTM_NUM_MEM_TYPES; mem_type++) > + if (>man[mem_type] == man) > + break; > + > + BUG_ON(mem_type >= TTM_NUM_MEM_TYPES); > + > + if (!drmcgrp_mem_pressure_scan(bdev, mem_type)) > + return; > + > + ret = ttm_mem_evict_first(bdev, mem_type, NULL, ); > + if (ret) > + return; > + > + spin_lock(>move_lock); > + fence = dma_fence_get(man->move); > + spin_unlock(>move_lock); > + > + if (fence) { > + ret = dma_fence_wait(fence, false); > + dma_fence_put(fence); > + } > + > +} > + > int ttm_bo_init_mm(struct ttm_bo_device *bdev, unsigned type, > unsigned long p_size) > { > @@ -1543,6 +1581,13 @@ int ttm_bo_init_mm(struct ttm_bo_device *bdev, > unsigned type, > INIT_LIST_HEAD(>lru[i]); > man->move = NULL; > > + pr_err("drmcgrp %p type %d\n", bdev->ddev, type); > + > + if (type <= TTM_PL_VRAM) { > + INIT_WORK(>reclaim_wq, ttm_bo_reclaim_wq); > + drmcgrp_register_device_mm(bdev->ddev, type, >reclaim_wq); > + } > + > return 0; > } > EXPORT_SYMBOL(ttm_bo_init_mm); > @@ -1620,6 +1665,8 @@ int ttm_bo_device_release(struct ttm_bo_device *bdev) > man = >man[i]; > if (man->has_type) { > man->use_type = false; > + drmcgrp_unregister_device_mm(bdev->ddev, i); > + cancel_work_sync(>reclaim_wq); > if ((i != TTM_PL_SYSTEM) && ttm_bo_clean_mm(bdev, i)) { > ret = -EBUSY; > pr_err("DRM memory manager type %d is not > clean\n", > diff --git a/include/drm/drm_cgroup.h b/include/drm/drm_cgroup.h > index 360c1e6c809f..134d6e5475f3 100644 > --- a/include/drm/drm_cgroup.h > +++ b/include/drm/drm_cgroup.h > @@ -5,6 +5,7 @@ > #define __DRM_CGROUP_H__ > > #include > +#include > #include > #include > > @@ -12,6 +13,9 @@ > > int drmcgrp_register_device(struct drm_device *device); > int drmcgrp_unregister_device(struct drm_device *device); > +void drmcgrp_register_device_mm(struct drm_device *dev, unsigned type, > + struct work_struct *wq); > +void drmcgrp_unregister_device_mm(struct drm_device *dev, unsigned type); > bool drmcgrp_is_self_or_ancestor(struct drmcgrp *self, > struct drmcgrp *relative); > void drmcgrp_chg_bo_alloc(struct drmcgrp *drmcgrp, struct drm_device *dev, > @@ -40,6 +44,16 @@ static inline int drmcgrp_unregister_device(struct > drm_device *device) > return 0; > } > > +static inline void drmcgrp_register_device_mm(struct drm_device *dev, > + unsigned type, struct work_struct *wq) > +{ > +} > + > +static inline void drmcgrp_unregister_device_mm(struct drm_device *dev, > + unsigned type) > +{ > +} > + > static inline bool drmcgrp_is_self_or_ancestor(struct drmcgrp *self, > struct drmcgrp *relative) > { > diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h >