From: Satyanarayana K V P Date: Tue, 22 Jul 2025 12:05:05 +0000 (+0530) Subject: drm/xe/vf: Attach and detach CCS copy commands with BO X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=864690cf4dd62482b6dd049d82c509886c904303;p=users%2Fjedix%2Flinux-maple.git drm/xe/vf: Attach and detach CCS copy commands with BO Attach CCS read/write copy commands to BO for old and new mem types as NULL -> tt or system -> tt. Detach the CCS read/write copy commands from BO while deleting ttm bo from xe_ttm_bo_delete_mem_notify(). Signed-off-by: Satyanarayana K V P Cc: Michal Wajdeczko Cc: Matthew Brost Cc: Matthew Auld Cc: Michał Winiarski Reviewed-by: Matthew Brost Signed-off-by: Matthew Brost Link: https://lore.kernel.org/r/20250722120506.6483-3-satyanarayana.k.v.p@intel.com --- diff --git a/drivers/gpu/drm/xe/xe_bb.c b/drivers/gpu/drm/xe/xe_bb.c index 5ce0e26822f2..feb6e013dc38 100644 --- a/drivers/gpu/drm/xe/xe_bb.c +++ b/drivers/gpu/drm/xe/xe_bb.c @@ -60,6 +60,41 @@ 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_tile *tile = gt_to_tile(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 = tile->sriov.vf.ccs[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) { diff --git a/drivers/gpu/drm/xe/xe_bb.h b/drivers/gpu/drm/xe/xe_bb.h index b5cc65506696..2a8adc9a6dee 100644 --- a/drivers/gpu/drm/xe/xe_bb.h +++ b/drivers/gpu/drm/xe/xe_bb.h @@ -13,8 +13,11 @@ struct dma_fence; struct xe_gt; struct xe_exec_queue; struct xe_sched_job; +enum xe_sriov_vf_ccs_rw_ctxs; struct xe_bb *xe_bb_new(struct xe_gt *gt, u32 dwords, bool usm); +struct xe_bb *xe_bb_ccs_new(struct xe_gt *gt, u32 dwords, + enum xe_sriov_vf_ccs_rw_ctxs ctx_id); struct xe_sched_job *xe_bb_create_job(struct xe_exec_queue *q, struct xe_bb *bb); struct xe_sched_job *xe_bb_create_migration_job(struct xe_exec_queue *q, diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 00ce067d5fd3..ffca1cea5585 100644 --- a/drivers/gpu/drm/xe/xe_bo.c +++ b/drivers/gpu/drm/xe/xe_bo.c @@ -33,6 +33,7 @@ #include "xe_pxp.h" #include "xe_res_cursor.h" #include "xe_shrinker.h" +#include "xe_sriov_vf_ccs.h" #include "xe_trace_bo.h" #include "xe_ttm_stolen_mgr.h" #include "xe_vm.h" @@ -965,6 +966,20 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict, dma_fence_put(fence); xe_pm_runtime_put(xe); + /* + * CCS meta data is migrated from TT -> SMEM. So, let us detach the + * BBs from BO as it is no longer needed. + */ + if (IS_VF_CCS_BB_VALID(xe, bo) && old_mem_type == XE_PL_TT && + new_mem->mem_type == XE_PL_SYSTEM) + xe_sriov_vf_ccs_detach_bo(bo); + + if (IS_SRIOV_VF(xe) && + ((move_lacks_source && new_mem->mem_type == XE_PL_TT) || + (old_mem_type == XE_PL_SYSTEM && new_mem->mem_type == XE_PL_TT)) && + handle_system_ccs) + ret = xe_sriov_vf_ccs_attach_bo(bo); + out: if ((!ttm_bo->resource || ttm_bo->resource->mem_type == XE_PL_SYSTEM) && ttm_bo->ttm) { @@ -975,6 +990,9 @@ out: if (timeout < 0) ret = timeout; + if (IS_VF_CCS_BB_VALID(xe, bo)) + xe_sriov_vf_ccs_detach_bo(bo); + xe_tt_unmap_sg(xe, ttm_bo->ttm); } @@ -1502,9 +1520,14 @@ static void xe_ttm_bo_release_notify(struct ttm_buffer_object *ttm_bo) static void xe_ttm_bo_delete_mem_notify(struct ttm_buffer_object *ttm_bo) { + struct xe_bo *bo = ttm_to_xe_bo(ttm_bo); + if (!xe_bo_is_xe_bo(ttm_bo)) return; + if (IS_VF_CCS_BB_VALID(ttm_to_xe_device(ttm_bo->bdev), bo)) + xe_sriov_vf_ccs_detach_bo(bo); + /* * Object is idle and about to be destroyed. Release the * dma-buf attachment. diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h index 57d34698139e..cf604adc13a3 100644 --- a/drivers/gpu/drm/xe/xe_bo_types.h +++ b/drivers/gpu/drm/xe/xe_bo_types.h @@ -77,6 +77,9 @@ struct xe_bo { /** @ccs_cleared */ bool ccs_cleared; + /** @bb_ccs_rw: BB instructions of CCS read/write. Valid only for VF */ + struct xe_bb *bb_ccs[XE_SRIOV_VF_CCS_CTX_COUNT]; + /** * @cpu_caching: CPU caching mode. Currently only used for userspace * objects. Exceptions are system memory on DGFX, which is always diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c index 6a80ae6104dd..5a108e34c554 100644 --- a/drivers/gpu/drm/xe/xe_migrate.c +++ b/drivers/gpu/drm/xe/xe_migrate.c @@ -30,6 +30,7 @@ #include "xe_mocs.h" #include "xe_pt.h" #include "xe_res_cursor.h" +#include "xe_sa.h" #include "xe_sched_job.h" #include "xe_sync.h" #include "xe_trace_bo.h" @@ -954,6 +955,153 @@ err_sync: return fence; } +/** + * xe_get_migrate_lrc() - Get the LRC from migrate context. + * @migrate: Migrate context. + * + * Return: Pointer to LRC on success, error on failure + */ +struct xe_lrc *xe_migrate_lrc(struct xe_migrate *migrate) +{ + return migrate->q->lrc[0]; +} + +static int emit_flush_invalidate(struct xe_migrate *m, u32 *dw, int i, + u32 flags) +{ + dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | MI_FLUSH_DW_OP_STOREDW | + MI_FLUSH_IMM_DW | flags; + dw[i++] = lower_32_bits(xe_lrc_start_seqno_ggtt_addr(xe_migrate_lrc(m))) | + MI_FLUSH_DW_USE_GTT; + dw[i++] = upper_32_bits(xe_lrc_start_seqno_ggtt_addr(xe_migrate_lrc(m))); + dw[i++] = MI_NOOP; + dw[i++] = MI_NOOP; + + return i; +} + +/** + * xe_migrate_ccs_rw_copy() - Copy content of TTM resources. + * @m: The migration context. + * @src_bo: The buffer object @src is currently bound to. + * @read_write : Creates BB commands for CCS read/write. + * + * Creates batch buffer instructions to copy CCS metadata from CCS pool to + * memory and vice versa. + * + * This function should only be called for IGPU. + * + * Return: 0 if successful, negative error code on failure. + */ +int xe_migrate_ccs_rw_copy(struct xe_migrate *m, + struct xe_bo *src_bo, + enum xe_sriov_vf_ccs_rw_ctxs read_write) + +{ + bool src_is_pltt = read_write == XE_SRIOV_VF_CCS_READ_CTX; + bool dst_is_pltt = read_write == XE_SRIOV_VF_CCS_WRITE_CTX; + struct ttm_resource *src = src_bo->ttm.resource; + struct xe_gt *gt = m->tile->primary_gt; + u32 batch_size, batch_size_allocated; + struct xe_device *xe = gt_to_xe(gt); + struct xe_res_cursor src_it, ccs_it; + u64 size = xe_bo_size(src_bo); + struct xe_bb *bb = NULL; + u64 src_L0, src_L0_ofs; + u32 src_L0_pt; + int err; + + xe_res_first_sg(xe_bo_sg(src_bo), 0, size, &src_it); + + xe_res_first_sg(xe_bo_sg(src_bo), xe_bo_ccs_pages_start(src_bo), + PAGE_ALIGN(xe_device_ccs_bytes(xe, size)), + &ccs_it); + + /* Calculate Batch buffer size */ + batch_size = 0; + while (size) { + batch_size += 10; /* Flush + ggtt addr + 2 NOP */ + u64 ccs_ofs, ccs_size; + u32 ccs_pt; + + u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE; + + src_L0 = min_t(u64, max_mem_transfer_per_pass(xe), size); + + batch_size += pte_update_size(m, false, src, &src_it, &src_L0, + &src_L0_ofs, &src_L0_pt, 0, 0, + avail_pts); + + ccs_size = xe_device_ccs_bytes(xe, src_L0); + batch_size += pte_update_size(m, 0, NULL, &ccs_it, &ccs_size, &ccs_ofs, + &ccs_pt, 0, avail_pts, avail_pts); + xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE)); + + /* Add copy commands size here */ + batch_size += EMIT_COPY_CCS_DW; + + size -= src_L0; + } + + bb = xe_bb_ccs_new(gt, batch_size, read_write); + if (IS_ERR(bb)) { + drm_err(&xe->drm, "BB allocation failed.\n"); + err = PTR_ERR(bb); + goto err_ret; + } + + batch_size_allocated = batch_size; + size = xe_bo_size(src_bo); + batch_size = 0; + + /* + * Emit PTE and copy commands here. + * The CCS copy command can only support limited size. If the size to be + * copied is more than the limit, divide copy into chunks. So, calculate + * sizes here again before copy command is emitted. + */ + while (size) { + batch_size += 10; /* Flush + ggtt addr + 2 NOP */ + u32 flush_flags = 0; + u64 ccs_ofs, ccs_size; + u32 ccs_pt; + + u32 avail_pts = max_mem_transfer_per_pass(xe) / LEVEL0_PAGE_TABLE_ENCODE_SIZE; + + src_L0 = xe_migrate_res_sizes(m, &src_it); + + batch_size += pte_update_size(m, false, src, &src_it, &src_L0, + &src_L0_ofs, &src_L0_pt, 0, 0, + avail_pts); + + ccs_size = xe_device_ccs_bytes(xe, src_L0); + batch_size += pte_update_size(m, 0, NULL, &ccs_it, &ccs_size, &ccs_ofs, + &ccs_pt, 0, avail_pts, avail_pts); + xe_assert(xe, IS_ALIGNED(ccs_it.start, PAGE_SIZE)); + batch_size += EMIT_COPY_CCS_DW; + + emit_pte(m, bb, src_L0_pt, false, true, &src_it, src_L0, src); + + emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src); + + bb->len = emit_flush_invalidate(m, bb->cs, bb->len, flush_flags); + flush_flags = xe_migrate_ccs_copy(m, bb, src_L0_ofs, src_is_pltt, + src_L0_ofs, dst_is_pltt, + src_L0, ccs_ofs, true); + bb->len = emit_flush_invalidate(m, bb->cs, bb->len, flush_flags); + + size -= src_L0; + } + + xe_assert(xe, (batch_size_allocated == bb->len)); + src_bo->bb_ccs[read_write] = bb; + + return 0; + +err_ret: + return err; +} + static void emit_clear_link_copy(struct xe_gt *gt, struct xe_bb *bb, u64 src_ofs, u32 size, u32 pitch) { diff --git a/drivers/gpu/drm/xe/xe_migrate.h b/drivers/gpu/drm/xe/xe_migrate.h index 74c60f55004a..cd948c7b8dea 100644 --- a/drivers/gpu/drm/xe/xe_migrate.h +++ b/drivers/gpu/drm/xe/xe_migrate.h @@ -24,6 +24,8 @@ struct xe_vm; struct xe_vm_pgtable_update; struct xe_vma; +enum xe_sriov_vf_ccs_rw_ctxs; + /** * struct xe_migrate_pt_update_ops - Callbacks for the * xe_migrate_update_pgtables() function. @@ -113,6 +115,11 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m, struct ttm_resource *dst, bool copy_only_ccs); +int xe_migrate_ccs_rw_copy(struct xe_migrate *m, + struct xe_bo *src_bo, + enum xe_sriov_vf_ccs_rw_ctxs read_write); + +struct xe_lrc *xe_migrate_lrc(struct xe_migrate *migrate); int xe_migrate_access_memory(struct xe_migrate *m, struct xe_bo *bo, unsigned long offset, void *buf, int len, int write); diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c index 697eea46659a..6ddeb016b892 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.c @@ -5,6 +5,7 @@ #include "instructions/xe_mi_commands.h" #include "instructions/xe_gpu_commands.h" +#include "xe_bb.h" #include "xe_bo.h" #include "xe_device.h" #include "xe_migrate.h" @@ -206,3 +207,69 @@ int xe_sriov_vf_ccs_init(struct xe_device *xe) err_ret: return err; } + +/** + * xe_sriov_vf_ccs_attach_bo - Insert CCS read write commands in the BO. + * @bo: the &buffer object to which batch buffer commands will be added. + * + * This function shall be called only by VF. It inserts the PTEs and copy + * command instructions in the BO by calling xe_migrate_ccs_rw_copy() + * function. + * + * Returns: 0 if successful, negative error code on failure. + */ +int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo) +{ + struct xe_device *xe = xe_bo_device(bo); + enum xe_sriov_vf_ccs_rw_ctxs ctx_id; + struct xe_migrate *migrate; + struct xe_tile *tile; + struct xe_bb *bb; + int err = 0; + + if (!IS_VF_CCS_READY(xe)) + return 0; + + tile = xe_device_get_root_tile(xe); + + for_each_ccs_rw_ctx(ctx_id) { + bb = bo->bb_ccs[ctx_id]; + /* bb should be NULL here. Assert if not NULL */ + xe_assert(xe, !bb); + + migrate = tile->sriov.vf.ccs[ctx_id].migrate; + err = xe_migrate_ccs_rw_copy(migrate, bo, ctx_id); + } + return err; +} + +/** + * xe_sriov_vf_ccs_detach_bo - Remove CCS read write commands from the BO. + * @bo: the &buffer object from which batch buffer commands will be removed. + * + * This function shall be called only by VF. It removes the PTEs and copy + * command instructions from the BO. Make sure to update the BB with MI_NOOP + * before freeing. + * + * Returns: 0 if successful. + */ +int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo) +{ + struct xe_device *xe = xe_bo_device(bo); + enum xe_sriov_vf_ccs_rw_ctxs ctx_id; + struct xe_bb *bb; + + if (!IS_VF_CCS_READY(xe)) + return 0; + + for_each_ccs_rw_ctx(ctx_id) { + bb = bo->bb_ccs[ctx_id]; + if (!bb) + continue; + + memset(bb->cs, MI_NOOP, bb->len * sizeof(u32)); + xe_bb_free(bb, NULL); + bo->bb_ccs[ctx_id] = NULL; + } + return 0; +} diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h index 5df9ba028d14..5d5e4bd25904 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs.h @@ -7,7 +7,10 @@ #define _XE_SRIOV_VF_CCS_H_ struct xe_device; +struct xe_bo; int xe_sriov_vf_ccs_init(struct xe_device *xe); +int xe_sriov_vf_ccs_attach_bo(struct xe_bo *bo); +int xe_sriov_vf_ccs_detach_bo(struct xe_bo *bo); #endif diff --git a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h index 6dc279d206ec..e240f3fd18af 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h +++ b/drivers/gpu/drm/xe/xe_sriov_vf_ccs_types.h @@ -27,6 +27,14 @@ enum xe_sriov_vf_ccs_rw_ctxs { XE_SRIOV_VF_CCS_CTX_COUNT }; +#define IS_VF_CCS_BB_VALID(xe, bo) ({ \ + struct xe_device *___xe = (xe); \ + struct xe_bo *___bo = (bo); \ + IS_SRIOV_VF(___xe) && \ + ___bo->bb_ccs[XE_SRIOV_VF_CCS_READ_CTX] && \ + ___bo->bb_ccs[XE_SRIOV_VF_CCS_WRITE_CTX]; \ + }) + struct xe_migrate; struct xe_sa_manager;