<html> <head> <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1"> <style type="text/css" style="display:none;"></style> </head> <body dir="ltr"> <div id="divtagdefaultwrapper" style="font-size: 12pt; color: rgb(0, 0, 0); font-family: Calibri, Helvetica, sans-serif, "EmojiFont", "Apple Color Emoji", "Segoe UI Emoji", NotoColorEmoji, "Segoe UI Symbol", "Android Emoji", EmojiSymbols;" dir="ltr"> <p style="margin-top:0;margin-bottom:0">Reviewed-by: Alex Deucher <alexander.deucher@amd.com><br> </p> <div style="color: rgb(0, 0, 0);"> <hr style="display:inline-block;width:98%" tabindex="-1"> <div id="divRplyFwdMsg" dir="ltr"><font style="font-size:11pt" face="Calibri, sans-serif" color="#000000"><b>From:</b> amd-gfx <amd-gfx-bounces@lists.freedesktop.org> on behalf of Christian König <ckoenig.leichtzumerken@gmail.com><br> <b>Sent:</b> Monday, January 29, 2018 10:05 AM<br> <b>To:</b> amd-gfx@lists.freedesktop.org<br> <b>Subject:</b> [PATCH] drm/amdgpu: limit the VM address space with older VCE FW versions</font> <div> </div> </div> <div class="BodyFragment"><font size="2"><span style="font-size:11pt;"> <div class="PlainText">Older VCE FW versions are buggy and can't work with 48bit address<br> spaces.<br> <br> RFC: Should we limit the address space or just reject loading the older<br> VCE firmware?<br> <br> Signed-off-by: Christian König <christian.koenig@amd.com><br> ---<br> drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 5 +++++<br> drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h | 2 ++<br> 2 files changed, 7 insertions(+)<br> <br> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c<br> index 431038885778..51a4b08546f2 100644<br> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c<br> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c<br> @@ -581,6 +581,11 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file<br> <br> vm_size = adev->vm_manager.max_pfn * AMDGPU_GPU_PAGE_SIZE;<br> vm_size -= AMDGPU_VA_RESERVED_SIZE;<br> +<br> + /* Older VCE FW versions are buggy and can handle only 40bits */<br> + if (adev->vce.fw_version < AMDGPU_VCE_FW_53_45)<br> + vm_size = min(vm_size, 1ULL << 40);<br> +<br> dev_info.virtual_address_offset = AMDGPU_VA_RESERVED_SIZE;<br> dev_info.virtual_address_max =<br> min(vm_size, AMDGPU_VA_HOLE_START);<br> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h<br> index 0fd378ae92c3..71781267ee4c 100644<br> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h<br> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.h<br> @@ -30,6 +30,8 @@<br> #define AMDGPU_VCE_HARVEST_VCE0 (1 << 0)<br> #define AMDGPU_VCE_HARVEST_VCE1 (1 << 1)<br> <br> +#define AMDGPU_VCE_FW_53_45 ((53 << 24) | (45 << 16))<br> +<br> struct amdgpu_vce {<br> struct amdgpu_bo *vcpu_bo;<br> uint64_t gpu_addr;<br> -- <br> 2.14.1<br> <br> _______________________________________________<br> amd-gfx mailing list<br> amd-gfx@lists.freedesktop.org<br> <a href="https://lists.freedesktop.org/mailman/listinfo/amd-gfx" id="LPlnk441166" previewremoved="true">https://lists.freedesktop.org/mailman/listinfo/amd-gfx</a><br> </div> </span></font></div> </div> </div> </body> </html>