Blob Blame History Raw
From 1d79b24e15bbb8755f875fed9c91e10c6c85b3fb Mon Sep 17 00:00:00 2001
From: Lang Yu <Lang.Yu@amd.com>
Date: Fri, 15 Apr 2022 15:35:44 +0800
Subject: drm/amdkfd: only allow heavy-weight TLB flush on some ASICs for SVM
 too
Git-commit: 36bf93216ecbe399c40c5e0486f0f0e3a4afa69e
Patch-mainline: v5.19-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

The idea is from
commit a50fe7078035 ("drm/amdkfd: Only apply heavy-weight TLB flush on Aldebaran")
and
commit f61c40c0757a ("drm/amdkfd: enable heavy-weight TLB flush on Arcturus").

At the moment, heavy-weight TLB could cause problems on ASICs except
Aldebaran and Arcturus.

A simple hipMallocManaged/hipFree program could trigger this issue.

[   97.787657] amdgpu 0000:01:00.0: amdgpu: wait for kiq fence error: 0.
[  106.868758] amdgpu: qcm fence wait loop timeout expired
[  106.868966] amdgpu: The cp might be in an unrecoverable state due to an unsuccessful queues preemption
[  106.869203] amdgpu: Failed to evict process queues
[  106.869261] amdgpu: Failed to quiesce KFD

Signed-off-by: Lang Yu <Lang.Yu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/amd/amdkfd/kfd_svm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
index 11b395b90a3d..0df3a4cd6ce7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
@@ -1229,7 +1229,9 @@ svm_range_unmap_from_gpus(struct svm_range *prange, unsigned long start,
 			if (r)
 				break;
 		}
-		kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
+
+		if (kfd_flush_tlb_after_unmap(pdd->dev))
+			kfd_flush_tlb(pdd, TLB_FLUSH_HEAVYWEIGHT);
 	}
 
 	return r;
-- 
2.38.1