<!DOCTYPE html><html><head> <meta http-equiv="Content-Type" content="text/html; charset=utf-8"> </head> <body> On 2025-05-08 10:50, Christian König wrote: <blockquote type="cite" cite="mid:e741c57a-651e-4acf-9ae6-4268c6540e0e@amd.com"> <pre class="moz-quote-pre" wrap="">On 5/8/25 16:46, James Zhu wrote: </pre> <blockquote type="cite"> <pre class="moz-quote-pre" wrap="">When XNACK on, hang or low performance is observed with some test cases. The restoring page process has unexpected stuck during evicting/restoring if some bo's flag has KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED setting: 1. when xnack on, retry pagefault will invoke restoring pages process 2. A. if there is enough VRAM space, simply migrating pages from ram to vram B. if there is no enough VRAM space left, searching resource LRU list, and scheduling a new eviction work queue to evict LRU bo from vram to ram first, then resume restoring pages process, or waiting for eviction timeout and try to schedule evicting next LRU bo 3. for case 2B, if bo has KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED setting, queue eviction will be triggered.So restoring work queue will be scheduled. 4. step 1, restoring pages process will hold one mm->mmap_lock's read until restoring pages is completed step 2B, evictiion work queue process will hold one mm->mmap_lock's read until evicting bo is completed step 3, restoring work queue process is trying to acquire one mm->mmap_lock's write after the above two mm->mmap_lock's read are released, and in the meantime which will block all following mm->mmap_lock's read request. 5. in step 2, if the first eviction bo's size is big enough for step 1 restoring pages request, everything is fine. if not, which means that the mm->mmap_lock's read step 1 won't be release right the way. In step 3, first eviction bo's restoring work queue will compete for mm->mmap_lock's write, the second and following LRU bo's evictiion work queue will be blocked by tring to acquire mm->mmap_lock's read until timeout. All restoring pages process will be stuck here. Using down_write_trylock to replace mmap_write_lock will help not block the second and following evictiion work queue process. Signed-off-by: James Zhu <a class="moz-txt-link-rfc2396E" href="mailto:James.Zhu@amd.com"><James.Zhu@amd.com></a> --- drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c index 72be6e152e88..5f6ed70559b7 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c @@ -1794,7 +1794,11 @@ svm_range_list_lock_and_flush_work(struct svm_range_list *svms, { retry_flush_work: flush_work(&svms->deferred_list_work); - mmap_write_lock(mm); + while (true) { + if (down_write_trylock(&(mm->mmap_lock))) + break; + schedule(); + } </pre> </blockquote> <pre class="moz-quote-pre" wrap="">Oh, stuff like that is usually an absolutely clear NAK from upstream. As far as I know that is not something we can do so easily. Would it be possible to wait for progress instead of calling schedule() here?</pre> </blockquote> I could think of a few other higher level mitigations to avoid getting into this situation in the first place. <ol> <li>Give BOs allocated with KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED a higher LRU priority, to make them less likely to be evicted</li> <li>If that doesn't help, set bp.no_wait_gpu in svm_range_vram_node_new. This should avoid causing evictions when trying to migrate data to VRAM in the page fault handler. In this case, migration should fail and the page fault should map data in system memory </li> </ol> Regards, Felix <blockquote type="cite" cite="mid:e741c57a-651e-4acf-9ae6-4268c6540e0e@amd.com"> <pre class="moz-quote-pre" wrap=""> Regards, Christian. </pre> <blockquote type="cite"> <pre class="moz-quote-pre" wrap=""> if (list_empty(&svms->deferred_range_list)) return; </pre> </blockquote> </blockquote> </body> </html>