[PATCH 3/4] drm/amdgpu: reroute VMC and UMD to IH ring 1 for oss v5
Alex Sierra
alex.sierra at amd.com
Fri Mar 27 19:37:46 UTC 2020
[Why]
Due Page faults can easily overwhelm the interrupt handler.
So to make sure that we never lose valuable interrupts on the primary ring
we re-route page faults to IH ring 1.
It also facilitates the recovery page process, since it's already
running from a process context.
This is valid for Arcturus and future Navi generation GPUs.
[How]
Setting IH_CLIENT_CFG_DATA for VMC and UMD IH clients.
Signed-off-by: Alex Sierra <alex.sierra at amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>
---
drivers/gpu/drm/amd/amdgpu/navi10_ih.c | 19 +++++++++++++++++++
1 file changed, 19 insertions(+)
diff --git a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
index 4ce42635787a..6fca5206833d 100644
--- a/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/navi10_ih.c
@@ -205,6 +205,24 @@ static uint32_t navi10_ih_doorbell_rptr(struct amdgpu_ih_ring *ih)
return ih_doorbell_rtpr;
}
+static void navi10_ih_reroute_ih(struct amdgpu_device *adev)
+{
+ uint32_t tmp;
+
+ /* Reroute to IH ring 1 for VMC */
+ WREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_INDEX, 0x12);
+ tmp = RREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_DATA);
+ tmp = REG_SET_FIELD(tmp, IH_CLIENT_CFG_DATA, CLIENT_TYPE, 1);
+ tmp = REG_SET_FIELD(tmp, IH_CLIENT_CFG_DATA, RING_ID, 1);
+ WREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_DATA, tmp);
+
+ /* Reroute IH ring 1 for UMC */
+ WREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_INDEX, 0x1B);
+ tmp = RREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_DATA);
+ tmp = REG_SET_FIELD(tmp, IH_CLIENT_CFG_DATA, RING_ID, 1);
+ WREG32_SOC15(OSSSYS, 0, mmIH_CLIENT_CFG_DATA, tmp);
+}
+
/**
* navi10_ih_irq_init - init and enable the interrupt ring
*
@@ -243,6 +261,7 @@ static int navi10_ih_irq_init(struct amdgpu_device *adev)
} else {
WREG32_SOC15(OSSSYS, 0, mmIH_RB_CNTL, ih_rb_cntl);
}
+ navi10_ih_reroute_ih(adev);
if (unlikely(adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT)) {
if (ih->use_bus_addr) {
--
2.17.1
More information about the amd-gfx
mailing list