[PATCH 1/1] drm/amdkfd: make needs_pcie_atomics FW-version dependent

[Felix Kuehling]

On 2021-08-31 6:09 p.m., Zeng, Oak wrote:
> A nit-pick inline. Otherwise this patch is Reviewed-by: Oak Zeng <Oak.Zeng at amd.com>
>
> Regards,
> Oak
>
>   
>
> On 2021-08-31, 5:57 PM, "amd-gfx on behalf of Felix Kuehling" <amd-gfx-bounces at lists.freedesktop.org on behalf of Felix.Kuehling at amd.com> wrote:
>
>      On some GPUs the PCIe atomic requirement for KFD depends on the MEC
>      firmware version. Add a firmware version check for this. The minimum
>      firmware version that works without atomics can be updated in the
>      device_info structure for each GPU type.
>
>      Signed-off-by: Felix Kuehling <Felix.Kuehling at amd.com>
>      ---
>       drivers/gpu/drm/amd/amdkfd/kfd_device.c | 9 +++++++--
>       drivers/gpu/drm/amd/amdkfd/kfd_priv.h   | 1 +
>       2 files changed, 8 insertions(+), 2 deletions(-)
>
>      diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
>      index 16a57b70cc1a..655ee5733229 100644
>      --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
>      +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
>      @@ -688,6 +688,7 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
>       	struct kfd_dev *kfd;
>       	const struct kfd_device_info *device_info;
>       	const struct kfd2kgd_calls *f2g;
>      +	uint32_t fw_version;
>
>       	if (asic_type >= sizeof(kfd_supported_devices) / (sizeof(void *) * 2)
>       		|| asic_type >= sizeof(kfd2kgd_funcs) / sizeof(void *)) {
>      @@ -713,8 +714,12 @@ struct kfd_dev *kgd2kfd_probe(struct kgd_dev *kgd,
>       	 * supported.
>       	 */
>       	kfd->pci_atomic_requested = amdgpu_amdkfd_have_atomics_support(kgd);
>      -	if (device_info->needs_pci_atomics &&
>      -	    !kfd->pci_atomic_requested) {
>      +	fw_version = amdgpu_amdkfd_get_fw_version(kgd, KGD_ENGINE_MEC1);
>      +	if (!kfd->pci_atomic_requested &&
>      +	    device_info->needs_pci_atomics &&
>      +	    (!device_info->no_atomic_fw_version ||
>      +	      amdgpu_amdkfd_get_fw_version(kgd, KGD_ENGINE_MEC1) <
> You already get the fw_version above __

I'll fix that. I forgot to remove the local variable after I decided to 
move the function call into the condition.

Thanks,
   Felix


>      +			device_info->no_atomic_fw_version)) {
>       		dev_info(kfd_device,
>       			 "skipped device %x:%x, PCI rejects atomics\n",
>       			 pdev->vendor, pdev->device);
>      diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>      index ab83b0de6b22..6d8f9bb2d905 100644
>      --- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>      +++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
>      @@ -207,6 +207,7 @@ struct kfd_device_info {
>       	bool supports_cwsr;
>       	bool needs_iommu_device;
>       	bool needs_pci_atomics;
>      +	uint32_t no_atomic_fw_version;
>       	unsigned int num_sdma_engines;
>       	unsigned int num_xgmi_sdma_engines;
>       	unsigned int num_sdma_queues_per_engine;
>      --
>      2.32.0
>
>