diff options
Diffstat (limited to 'drivers/gpu/drm/xe/xe_bb.c')
| -rw-r--r-- | drivers/gpu/drm/xe/xe_bb.c | 44 |
1 files changed, 40 insertions, 4 deletions
diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index 541361caff3b..6d20229c11de 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -6,7 +6,7 @@ #include "xe_bb.h" #include "instructions/xe_mi_commands.h" -#include "regs/xe_gpu_commands.h" +#include "xe_assert.h" #include "xe_device.h" #include "xe_exec_queue_types.h" #include "xe_gt.h" @@ -19,7 +19,7 @@ static int bb_prefetch(struct xe_gt *gt) { struct xe_device *xe = gt_to_xe(gt); - if (GRAPHICS_VERx100(xe) >= 1250 && !xe_gt_is_media_type(gt)) + if (GRAPHICS_VERx100(xe) >= 1250 && xe_gt_is_main_type(gt)) /* * RCS and CCS require 1K, although other engines would be * okay with 512. @@ -41,7 +41,7 @@ struct xe_bb *xe_bb_new(struct xe_gt *gt, u32 dwords, bool usm) /* * We need to allocate space for the requested number of dwords, * one additional MI_BATCH_BUFFER_END dword, and additional buffer - * space to accomodate the platform-specific hardware prefetch + * space to accommodate the platform-specific hardware prefetch * requirements. */ bb->bo = xe_sa_bo_new(!usm ? tile->mem.kernel_bb_pool : gt->usm.bb_pool, @@ -60,12 +60,48 @@ err: return ERR_PTR(err); } +struct xe_bb *xe_bb_ccs_new(struct xe_gt *gt, u32 dwords, + enum xe_sriov_vf_ccs_rw_ctxs ctx_id) +{ + struct xe_bb *bb = kmalloc(sizeof(*bb), GFP_KERNEL); + struct xe_device *xe = gt_to_xe(gt); + struct xe_sa_manager *bb_pool; + int err; + + if (!bb) + return ERR_PTR(-ENOMEM); + /* + * We need to allocate space for the requested number of dwords & + * one additional MI_BATCH_BUFFER_END dword. Since the whole SA + * is submitted to HW, we need to make sure that the last instruction + * is not over written when the last chunk of SA is allocated for BB. + * So, this extra DW acts as a guard here. + */ + + bb_pool = xe->sriov.vf.ccs.contexts[ctx_id].mem.ccs_bb_pool; + bb->bo = xe_sa_bo_new(bb_pool, 4 * (dwords + 1)); + + if (IS_ERR(bb->bo)) { + err = PTR_ERR(bb->bo); + goto err; + } + + bb->cs = xe_sa_bo_cpu_addr(bb->bo); + bb->len = 0; + + return bb; +err: + kfree(bb); + return ERR_PTR(err); +} + static struct xe_sched_job * __xe_bb_create_job(struct xe_exec_queue *q, struct xe_bb *bb, u64 *addr) { u32 size = drm_suballoc_size(bb->bo); - bb->cs[bb->len++] = MI_BATCH_BUFFER_END; + if (bb->len == 0 || bb->cs[bb->len - 1] != MI_BATCH_BUFFER_END) + bb->cs[bb->len++] = MI_BATCH_BUFFER_END; xe_gt_assert(q->gt, bb->len * 4 + bb_prefetch(q->gt) <= size); |