[PATCH AUTOSEL 5.17 10/49] drm/amdkfd: Fix Incorrect VMIDs passed to HWS

From: Sasha Levin
Date: Mon Apr 11 2022 - 20:45:56 EST


From: Tushar Patel <tushar.patel@xxxxxxx>

[ Upstream commit b7dfbd2e601f3fee545bc158feceba4f340fe7cf ]

Compute-only GPUs have more than 8 VMIDs allocated to KFD. Fix
this by passing correct number of VMIDs to HWS

v2: squash in warning fix (Alex)

Signed-off-by: Tushar Patel <tushar.patel@xxxxxxx>
Reviewed-by: Felix Kuehling <felix.kuehling@xxxxxxx>
Signed-off-by: Alex Deucher <alexander.deucher@xxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +-
drivers/gpu/drm/amd/amdkfd/kfd_device.c | 11 +++--------
2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 0ead08ba58c2..7672790d8b6b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -686,7 +686,7 @@ MODULE_PARM_DESC(sched_policy,
* Maximum number of processes that HWS can schedule concurrently. The maximum is the
* number of VMIDs assigned to the HWS, which is also the default.
*/
-int hws_max_conc_proc = 8;
+int hws_max_conc_proc = -1;
module_param(hws_max_conc_proc, int, 0444);
MODULE_PARM_DESC(hws_max_conc_proc,
"Max # processes HWS can execute concurrently when sched_policy=0 (0 = no concurrency, #VMIDs for KFD = Maximum(default))");
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 2b65d0acae2c..2fdbe2f475e4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -480,15 +480,10 @@ bool kgd2kfd_device_init(struct kfd_dev *kfd,
}

/* Verify module parameters regarding mapped process number*/
- if ((hws_max_conc_proc < 0)
- || (hws_max_conc_proc > kfd->vm_info.vmid_num_kfd)) {
- dev_err(kfd_device,
- "hws_max_conc_proc %d must be between 0 and %d, use %d instead\n",
- hws_max_conc_proc, kfd->vm_info.vmid_num_kfd,
- kfd->vm_info.vmid_num_kfd);
+ if (hws_max_conc_proc >= 0)
+ kfd->max_proc_per_quantum = min((u32)hws_max_conc_proc, kfd->vm_info.vmid_num_kfd);
+ else
kfd->max_proc_per_quantum = kfd->vm_info.vmid_num_kfd;
- } else
- kfd->max_proc_per_quantum = hws_max_conc_proc;

/* calculate max size of mqds needed for queues */
size = max_num_of_queues_per_device *
--
2.35.1