From c2fe93fbe0ad3d8891e672370a3585b9ca087bbb Mon Sep 17 00:00:00 2001 From: Jay Cornwall Date: Mon, 10 Oct 2016 14:02:56 -0500 Subject: [PATCH 1199/4131] drm/amdkfd: Clamp EOP queue size correctly on Gfx8 Gfx8 HW incorrectly clamps CP_HQD_EOP_CONTROL.EOP_SIZE, which can lead to scheduling deadlock due to SE EOP done counter overflow. Enforce a EOP queue size limit which prevents the CP from sending more than 0xFF events at a time. Signed-off-by: Jay Cornwall --- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c index ebb4664..579cc68 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c @@ -215,8 +215,15 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd, 3 << CP_HQD_IB_CONTROL__MIN_IB_AVAIL_SIZE__SHIFT | mtype << CP_HQD_IB_CONTROL__MTYPE__SHIFT; - m->cp_hqd_eop_control |= - ffs(q->eop_ring_buffer_size / sizeof(unsigned int)) - 1 - 1; + /* + * HW does not clamp this field correctly. Maximum EOP queue size + * is constrained by per-SE EOP done signal count, which is 8-bit. + * Limit is 0xFF EOP entries (= 0x7F8 dwords). CP will not submit + * more than (EOP entry count - 1) so a queue size of 0x800 dwords + * is safe, giving a maximum field value of 0xA. + */ + m->cp_hqd_eop_control |= min(0xA, + ffs(q->eop_ring_buffer_size / sizeof(unsigned int)) - 1 - 1); m->cp_hqd_eop_base_addr_lo = lower_32_bits(q->eop_ring_buffer_address >> 8); m->cp_hqd_eop_base_addr_hi = -- 2.7.4