search for: chunk_full

...struct nouveau_dmem_chunk are allocated and put on the dmem->chunk_empty list. Then in nouveau_dmem_pages_alloc(), a nouveau_dmem_chunk is removed from the list and GPU memory is allocated. However, the nouveau_dmem_chunk is never removed from the chunk_empty list nor placed on the chunk_free or chunk_full lists. This results in only one chunk ever being actually used (2MB) and quickly leads to migration to device private memory failures. Fix this by having just one list of free device private pages and if no pages are free, allocate a chunk of device private pages and GPU memory. Signed-off-by: Ra...

...eau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -593,6 +593,11 @@ nouveau_dmem_init(struct nouveau_drm *drm) unsigned long i, size; int ret; + mutex_init(&drm->dmem->mutex); + INIT_LIST_HEAD(&drm->dmem->chunk_free); + INIT_LIST_HEAD(&drm->dmem->chunk_full); + INIT_LIST_HEAD(&drm->dmem->chunk_empty); + /* This only make sense on PASCAL or newer */ if (drm->client.device.info.family < NV_DEVICE_INFO_V0_PASCAL) return; @@ -600,11 +605,6 @@ nouveau_dmem_init(struct nouveau_drm *drm) if (!(drm->dmem = kzalloc(sizeof(*drm->d...

...pty, list) { - ret = nouveau_bo_pin(chunk->bo, TTM_PL_FLAG_VRAM, false); - /* FIXME handle pin failure */ - WARN_ON(ret); - } mutex_unlock(&drm->dmem->mutex); } @@ -479,9 +474,6 @@ nouveau_dmem_suspend(struct nouveau_drm *drm) list_for_each_entry (chunk, &drm->dmem->chunk_full, list) { nouveau_bo_unpin(chunk->bo); } - list_for_each_entry (chunk, &drm->dmem->chunk_empty, list) { - nouveau_bo_unpin(chunk->bo); - } mutex_unlock(&drm->dmem->mutex); } -- 2.17.1

...chunk are allocated > and put on the dmem->chunk_empty list. Then in nouveau_dmem_pages_alloc(), > a nouveau_dmem_chunk is removed from the list and GPU memory is allocated. > However, the nouveau_dmem_chunk is never removed from the chunk_empty > list nor placed on the chunk_free or chunk_full lists. This results > in only one chunk ever being actually used (2MB) and quickly leads to > migration to device private memory failures. > > Fix this by having just one list of free device private pages and if no > pages are free, allocate a chunk of device private pages and GPU m...

Hi, just for your information and maybe for some help: with 5.1rc1 and SVM enabled i see the following backtrace [1] when the nouveau card (reverse prime) goes to sleep, for now i have papered over with [2] which leaves me with userspace hangs. Any pointers where to look for the actual culprit? PS: Card is: nouveau 0000:01:00.0: NVIDIA GP106 (136000a1) Greetings, Tobias [1]: BUG: unable

Hi Dan, Jérôme and Jason, below is a series that cleans up the dev_pagemap interface so that it is more easily usable, which removes the need to wrap it in hmm and thus allowing to kill a lot of code Note: this series is on top of the rdma/hmm branch + the dev_pagemap releas fix series from Dan that went into 5.2-rc5. Git tree: git://git.infradead.org/users/hch/misc.git

Hi Dan, Jérôme and Jason, below is a series that cleans up the dev_pagemap interface so that it is more easily usable, which removes the need to wrap it in hmm and thus allowing to kill a lot of code Diffstat: 22 files changed, 245 insertions(+), 802 deletions(-) Git tree: git://git.infradead.org/users/hch/misc.git hmm-devmem-cleanup Gitweb:

Hi Dan, Jérôme and Jason, below is a series that cleans up the dev_pagemap interface so that it is more easily usable, which removes the need to wrap it in hmm and thus allowing to kill a lot of code Note: this series is on top of Linux 5.2-rc5 and has some minor conflicts with the hmm tree that are easy to resolve. Diffstat summary: 32 files changed, 361 insertions(+), 1012 deletions(-) Git