Intel-XE Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Brost <matthew.brost@intel.com>
To: intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: kenneth.w.graunke@intel.com, lionel.g.landwerlin@intel.com,
	jose.souza@intel.com, simona.vetter@ffwll.ch,
	thomas.hellstrom@linux.intel.com, boris.brezillon@collabora.com,
	airlied@gmail.com, christian.koenig@amd.com,
	mihail.atanassov@arm.com, steven.price@arm.com,
	shashank.sharma@amd.com
Subject: [RFC PATCH 07/29] drm/xe: Break indirect ring state out into its own BO
Date: Mon, 18 Nov 2024 15:37:35 -0800	[thread overview]
Message-ID: <20241118233757.2374041-8-matthew.brost@intel.com> (raw)
In-Reply-To: <20241118233757.2374041-1-matthew.brost@intel.com>

Start laying the ground work for UMD submission. This will allow mmaping
the indirect ring state to user space.

Signed-off-by: Matthew Brost <matthew.brost@intel.com>
---
 drivers/gpu/drm/xe/xe_lrc.c       | 79 ++++++++++++++++++++++---------
 drivers/gpu/drm/xe/xe_lrc_types.h |  7 ++-
 2 files changed, 63 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 758648b6a711..e3c1773191bd 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -74,10 +74,6 @@ size_t xe_gt_lrc_size(struct xe_gt *gt, enum xe_engine_class class)
 		size = 2 * SZ_4K;
 	}
 
-	/* Add indirect ring state page */
-	if (xe_gt_has_indirect_ring_state(gt))
-		size += LRC_INDIRECT_RING_STATE_SIZE;
-
 	return size;
 }
 
@@ -694,8 +690,7 @@ static u32 __xe_lrc_ctx_timestamp_offset(struct xe_lrc *lrc)
 
 static inline u32 __xe_lrc_indirect_ring_offset(struct xe_lrc *lrc)
 {
-	/* Indirect ring state page is at the very end of LRC */
-	return lrc->size - LRC_INDIRECT_RING_STATE_SIZE;
+	return 0;
 }
 
 #define DECL_MAP_ADDR_HELPERS(elem) \
@@ -726,6 +721,20 @@ static inline u32 __maybe_unused __xe_lrc_##elem##_ggtt_addr(struct xe_lrc *lrc)
 	return xe_bo_ggtt_addr(lrc->submission_ring) + __xe_lrc_##elem##_offset(lrc); \
 } \
 
+#define DECL_MAP_INDIRECT_ADDR_HELPERS(elem) \
+static inline struct iosys_map __xe_lrc_##elem##_map(struct xe_lrc *lrc) \
+{ \
+	struct iosys_map map = lrc->indirect_state->vmap; \
+\
+	xe_assert(lrc_to_xe(lrc), !iosys_map_is_null(&map));  \
+	iosys_map_incr(&map, __xe_lrc_##elem##_offset(lrc)); \
+	return map; \
+} \
+static inline u32 __maybe_unused __xe_lrc_##elem##_ggtt_addr(struct xe_lrc *lrc) \
+{ \
+	return xe_bo_ggtt_addr(lrc->indirect_state) + __xe_lrc_##elem##_offset(lrc); \
+} \
+
 DECL_MAP_RING_ADDR_HELPERS(ring)
 DECL_MAP_ADDR_HELPERS(pphwsp)
 DECL_MAP_ADDR_HELPERS(seqno)
@@ -734,8 +743,9 @@ DECL_MAP_ADDR_HELPERS(start_seqno)
 DECL_MAP_ADDR_HELPERS(ctx_job_timestamp)
 DECL_MAP_ADDR_HELPERS(ctx_timestamp)
 DECL_MAP_ADDR_HELPERS(parallel)
-DECL_MAP_ADDR_HELPERS(indirect_ring)
+DECL_MAP_INDIRECT_ADDR_HELPERS(indirect_ring)
 
+#undef DECL_INDIRECT_MAP_ADDR_HELPERS
 #undef DECL_RING_MAP_ADDR_HELPERS
 #undef DECL_MAP_ADDR_HELPERS
 
@@ -845,25 +855,27 @@ void xe_lrc_write_ctx_reg(struct xe_lrc *lrc, int reg_nr, u32 val)
 	xe_map_write32(xe, &map, val);
 }
 
-static void *empty_lrc_data(struct xe_hw_engine *hwe)
+static void *empty_lrc_data(struct xe_hw_engine *hwe, bool has_default)
 {
 	struct xe_gt *gt = hwe->gt;
 	void *data;
 	u32 *regs;
 
-	data = kzalloc(xe_gt_lrc_size(gt, hwe->class), GFP_KERNEL);
+	data = kzalloc(xe_gt_lrc_size(gt, hwe->class) +
+		       LRC_INDIRECT_RING_STATE_SIZE, GFP_KERNEL);
 	if (!data)
 		return NULL;
 
 	/* 1st page: Per-Process of HW status Page */
-	regs = data + LRC_PPHWSP_SIZE;
-	set_offsets(regs, reg_offsets(gt_to_xe(gt), hwe->class), hwe);
-	set_context_control(regs, hwe);
-	set_memory_based_intr(regs, hwe);
-	reset_stop_ring(regs, hwe);
+	if (!has_default) {
+		regs = data + LRC_PPHWSP_SIZE;
+		set_offsets(regs, reg_offsets(gt_to_xe(gt), hwe->class), hwe);
+		set_context_control(regs, hwe);
+		set_memory_based_intr(regs, hwe);
+		reset_stop_ring(regs, hwe);
+	}
 	if (xe_gt_has_indirect_ring_state(gt)) {
-		regs = data + xe_gt_lrc_size(gt, hwe->class) -
-		       LRC_INDIRECT_RING_STATE_SIZE;
+		regs = data + xe_gt_lrc_size(gt, hwe->class);
 		set_offsets(regs, xe2_indirect_ring_state_offsets, hwe);
 	}
 
@@ -883,6 +895,7 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
 	xe_hw_fence_ctx_finish(&lrc->fence_ctx);
 	xe_bo_unpin_map_no_vm(lrc->bo);
 	xe_bo_unpin_map_no_vm(lrc->submission_ring);
+	xe_bo_unpin_map_no_vm(lrc->indirect_state);
 }
 
 #define PVC_CTX_ASID		(0x2e + 1)
@@ -903,8 +916,6 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	kref_init(&lrc->refcount);
 	lrc->flags = 0;
 	lrc_size = xe_gt_lrc_size(gt, hwe->class);
-	if (xe_gt_has_indirect_ring_state(gt))
-		lrc->flags |= XE_LRC_FLAG_INDIRECT_RING_STATE;
 
 	/*
 	 * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address
@@ -929,6 +940,22 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 		goto err_lrc_finish;
 	}
 
+	if (xe_gt_has_indirect_ring_state(gt)) {
+		lrc->flags |= XE_LRC_FLAG_INDIRECT_RING_STATE;
+
+		lrc->indirect_state = xe_bo_create_pin_map(xe, tile, vm,
+							   LRC_INDIRECT_RING_STATE_SIZE,
+							   ttm_bo_type_kernel,
+							   XE_BO_FLAG_VRAM_IF_DGFX(tile) |
+							   XE_BO_FLAG_GGTT |
+							   XE_BO_FLAG_GGTT_INVALIDATE);
+		if (IS_ERR(lrc->indirect_state)) {
+			err = PTR_ERR(lrc->indirect_state);
+			lrc->indirect_state = NULL;
+			goto err_lrc_finish;
+		}
+	}
+
 	lrc->size = lrc_size;
 	lrc->tile = gt_to_tile(hwe->gt);
 	lrc->ring.size = ring_size;
@@ -938,8 +965,8 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	xe_hw_fence_ctx_init(&lrc->fence_ctx, hwe->gt,
 			     hwe->fence_irq, hwe->name);
 
-	if (!gt->default_lrc[hwe->class]) {
-		init_data = empty_lrc_data(hwe);
+	if (!gt->default_lrc[hwe->class] || xe_gt_has_indirect_ring_state(gt)) {
+		init_data = empty_lrc_data(hwe, !!gt->default_lrc[hwe->class]);
 		if (!init_data) {
 			err = -ENOMEM;
 			goto err_lrc_finish;
@@ -951,7 +978,7 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	 * values
 	 */
 	map = __xe_lrc_pphwsp_map(lrc);
-	if (!init_data) {
+	if (gt->default_lrc[hwe->class]) {
 		xe_map_memset(xe, &map, 0, 0, LRC_PPHWSP_SIZE);	/* PPHWSP */
 		xe_map_memcpy_to(xe, &map, LRC_PPHWSP_SIZE,
 				 gt->default_lrc[hwe->class] + LRC_PPHWSP_SIZE,
@@ -959,9 +986,17 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	} else {
 		xe_map_memcpy_to(xe, &map, 0, init_data,
 				 xe_gt_lrc_size(gt, hwe->class));
-		kfree(init_data);
 	}
 
+	if (xe_gt_has_indirect_ring_state(gt)) {
+		map = __xe_lrc_indirect_ring_map(lrc);
+		xe_map_memcpy_to(xe, &map, 0, init_data +
+				 xe_gt_lrc_size(gt, hwe->class),
+				 LRC_INDIRECT_RING_STATE_SIZE);
+	}
+
+	kfree(init_data);
+
 	if (vm) {
 		xe_lrc_set_ppgtt(lrc, vm);
 
diff --git a/drivers/gpu/drm/xe/xe_lrc_types.h b/drivers/gpu/drm/xe/xe_lrc_types.h
index 3ad9ac2d644f..3be708c82313 100644
--- a/drivers/gpu/drm/xe/xe_lrc_types.h
+++ b/drivers/gpu/drm/xe/xe_lrc_types.h
@@ -27,7 +27,12 @@ struct xe_lrc {
 	 */
 	struct xe_bo *submission_ring;
 
-	/** @size: size of lrc including any indirect ring state page */
+	/**
+	 * @indirect_state: buffer object (memory) for indirect state
+	 */
+	struct xe_bo *indirect_state;
+
+	/** @size: size of lrc */
 	u32 size;
 
 	/** @tile: tile which this LRC belongs to */
-- 
2.34.1


  parent reply	other threads:[~2024-11-18 23:37 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-11-18 23:37 [RFC PATCH 00/29] UMD direct submission in Xe Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 01/29] dma-fence: Add dma_fence_preempt base class Matthew Brost
2024-11-20 13:31   ` Christian König
2024-11-20 17:36     ` Matthew Brost
2024-11-21 10:04       ` Christian König
2024-11-21 18:41         ` Matthew Brost
2024-11-22 10:56           ` Christian König
2024-11-18 23:37 ` [RFC PATCH 02/29] dma-fence: Add dma_fence_user_fence Matthew Brost
2024-11-20 13:38   ` Christian König
2024-11-20 22:50     ` Matthew Brost
2024-11-21  9:31       ` Christian König
2024-11-22  2:35         ` Matthew Brost
2024-11-22 10:28           ` Christian König
2024-11-18 23:37 ` [RFC PATCH 03/29] drm/xe: Use dma_fence_preempt base class Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 04/29] drm/xe: Allocate doorbells for UMD exec queues Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 05/29] drm/xe: Add doorbell ID to snapshot capture Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 06/29] drm/xe: Break submission ring out into its own BO Matthew Brost
2024-11-18 23:37 ` Matthew Brost [this message]
2024-11-18 23:37 ` [RFC PATCH 08/29] drm/xe: Clear GGTT in xe_bo_restore_kernel Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 09/29] FIXME: drm/xe: Add pad to ring and indirect state Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 10/29] drm/xe: Enable indirect ring on media GT Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 11/29] drm/xe: Don't add pinned mappings to VM bulk move Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 12/29] drm/xe: Add exec queue post init extension processing Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 13/29] drm/xe/mmap: Add mmap support for PCI memory barrier Matthew Brost
2024-11-19 10:00   ` Christian König
2024-11-19 11:57     ` Joonas Lahtinen
2024-11-19 12:42       ` Mrozek, Michal
2024-12-18 12:59         ` Upadhyay, Tejas
2024-11-18 23:37 ` [RFC PATCH 14/29] drm/xe: Add support for mmapping doorbells to user space Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 15/29] drm/xe: Add support for mmapping submission ring and indirect ring state " Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 16/29] drm/xe/uapi: Define UMD exec queue mapping uAPI Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 17/29] drm/xe: Add usermap exec queue extension Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 18/29] drm/xe: Drop EXEC_QUEUE_FLAG_UMD_SUBMISSION flag Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 19/29] drm/xe: Do not allow usermap exec queues in exec IOCTL Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 20/29] drm/xe: Teach GuC backend to kill usermap queues Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 21/29] drm/xe: Enable preempt fences on " Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 22/29] drm/xe/uapi: Add uAPI to convert user semaphore to / from drm syncobj Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 23/29] drm/xe: Add user fence IRQ handler Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 24/29] drm/xe: Add xe_hw_fence_user_init Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 25/29] drm/xe: Add a message lock to the Xe GPU scheduler Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 26/29] drm/xe: Always wait on preempt fences in vma_check_userptr Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 27/29] drm/xe: Teach xe_sync layer about drm_xe_semaphore Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 28/29] drm/xe: Add VM convert fence IOCTL Matthew Brost
2024-11-18 23:37 ` [RFC PATCH 29/29] drm/xe: Add user fence TDR Matthew Brost
2024-11-18 23:55 ` ✓ CI.Patch_applied: success for UMD direct submission in Xe Patchwork
2024-11-18 23:56 ` ✗ CI.checkpatch: warning " Patchwork
2024-11-18 23:57 ` ✓ CI.KUnit: success " Patchwork
2024-11-19  0:15 ` ✓ CI.Build: " Patchwork
2024-11-19  0:17 ` ✗ CI.Hooks: failure " Patchwork
2024-11-19  0:19 ` ✓ CI.checksparse: success " Patchwork
2024-11-19  0:39 ` ✗ CI.BAT: failure " Patchwork
2024-11-19 11:44 ` ✗ CI.FULL: " Patchwork

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20241118233757.2374041-8-matthew.brost@intel.com \
    --to=matthew.brost@intel.com \
    --cc=airlied@gmail.com \
    --cc=boris.brezillon@collabora.com \
    --cc=christian.koenig@amd.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-xe@lists.freedesktop.org \
    --cc=jose.souza@intel.com \
    --cc=kenneth.w.graunke@intel.com \
    --cc=lionel.g.landwerlin@intel.com \
    --cc=mihail.atanassov@arm.com \
    --cc=shashank.sharma@amd.com \
    --cc=simona.vetter@ffwll.ch \
    --cc=steven.price@arm.com \
    --cc=thomas.hellstrom@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox