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 <kenny...@amd.com>
> ---
> 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 (&bdev->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, &ctx);
> + if (ret)
> + return;
> +
> + spin_lock(&man->move_lock);
> + fence = dma_fence_get(man->move);
> + spin_unlock(&man->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(&man->lru[i]);
> man->move = NULL;
>
> + pr_err("drmcgrp %p type %d\n", bdev->ddev, type);
> +
> + if (type <= TTM_PL_VRAM) {
> + INIT_WORK(&man->reclaim_wq, ttm_bo_reclaim_wq);
> + drmcgrp_register_device_mm(bdev->ddev, type, &man->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 = &bdev->man[i];
> if (man->has_type) {
> man->use_type = false;
> + drmcgrp_unregister_device_mm(bdev->ddev, i);
> + cancel_work_sync(&man->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 <linux/cgroup_drm.h>
> +#include <linux/workqueue.h>
> #include <drm/ttm/ttm_bo_api.h>
> #include <drm/ttm/ttm_bo_driver.h>
>
> @@ -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
> index 4cbcb41e5aa9..0956ca7888fc 100644
> --- a/include/drm/ttm/ttm_bo_driver.h
> +++ b/include/drm/ttm/ttm_bo_driver.h
> @@ -205,6 +205,8 @@ struct ttm_mem_type_manager {
> * Protected by @move_lock.
> */
> struct dma_fence *move;
> +
> + struct work_struct reclaim_wq;
> };
>
> /**
> diff --git a/kernel/cgroup/drm.c b/kernel/cgroup/drm.c
> index 1ce13db36ce9..985a89e849d3 100644
> --- a/kernel/cgroup/drm.c
> +++ b/kernel/cgroup/drm.c
> @@ -31,6 +31,8 @@ struct drmcgrp_device {
> s64 mem_bw_avg_bytes_per_us_default;
>
> s64 mem_highs_default[TTM_PL_PRIV+1];
> +
> + struct work_struct *mem_reclaim_wq[TTM_PL_PRIV];
> };
>
> #define DRMCG_CTF_PRIV_SIZE 3
> @@ -793,6 +795,31 @@ int drmcgrp_unregister_device(struct drm_device *dev)
> }
> EXPORT_SYMBOL(drmcgrp_unregister_device);
>
> +void drmcgrp_register_device_mm(struct drm_device *dev, unsigned type,
> + struct work_struct *wq)
> +{
> + if (dev == NULL || dev->primary->index > max_minor
> + || type >= TTM_PL_PRIV)
> + return;
> +
> + mutex_lock(&drmcgrp_mutex);
> + known_drmcgrp_devs[dev->primary->index]->mem_reclaim_wq[type] = wq;
> + mutex_unlock(&drmcgrp_mutex);
> +}
> +EXPORT_SYMBOL(drmcgrp_register_device_mm);
> +
> +void drmcgrp_unregister_device_mm(struct drm_device *dev, unsigned type)
> +{
> + if (dev == NULL || dev->primary->index > max_minor
> + || type >= TTM_PL_PRIV)
> + return;
> +
> + mutex_lock(&drmcgrp_mutex);
> + known_drmcgrp_devs[dev->primary->index]->mem_reclaim_wq[type] = NULL;
> + mutex_unlock(&drmcgrp_mutex);
> +}
> +EXPORT_SYMBOL(drmcgrp_unregister_device_mm);
> +
> bool drmcgrp_is_self_or_ancestor(struct drmcgrp *self, struct drmcgrp
> *relative)
> {
> for (; self != NULL; self = parent_drmcgrp(self))
> @@ -1004,6 +1031,12 @@ void drmcgrp_mem_track_move(struct ttm_buffer_object
> *old_bo, bool evict,
>
> ddr->mem_bw_stats[DRMCGRP_MEM_BW_ATTR_BYTE_CREDIT]
> -= move_in_bytes;
> +
> + if (known_dev->mem_reclaim_wq[new_mem_type] != NULL &&
> + ddr->mem_stats[new_mem_type] >
> + ddr->mem_highs[new_mem_type])
> + schedule_work(
> + known_dev->mem_reclaim_wq[new_mem_type]);
> }
> mutex_unlock(&known_dev->mutex);
> }
> --
> 2.21.0
>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
