AMD-GFX Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Alex Deucher <alexander.deucher@amd.com>
To: <amd-gfx@lists.freedesktop.org>
Cc: "Alex Deucher" <alexander.deucher@amd.com>,
	"Jack Xiao" <Jack.Xiao@amd.com>,
	"Christian König" <christian.koenig@amd.com>,
	"Hawking Zhang" <Hawking.Zhang@amd.com>
Subject: [PATCH 03/73] drm/amdgpu: add the per-context meta data v3
Date: Fri, 29 Apr 2022 13:45:14 -0400	[thread overview]
Message-ID: <20220429174624.459475-4-alexander.deucher@amd.com> (raw)
In-Reply-To: <20220429174624.459475-1-alexander.deucher@amd.com>

From: Jack Xiao <Jack.Xiao@amd.com>

The per-context meta data is a per-context data structure associated
with a mes-managed hardware ring, which includes MCBP CSA, ring buffer
and etc.

v2: fix typo
v3: a. use structure instead of typedef
    b. move amdgpu_mes_ctx_get_offs_* to amdgpu_ring.h
    c. use __aligned to make alignement

Signed-off-by: Jack Xiao <Jack.Xiao@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h         |   1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes_ctx.h | 118 ++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h    |   9 ++
 3 files changed, 128 insertions(+)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_mes_ctx.h

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 2eed9479e854..24bce7e691a8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -91,6 +91,7 @@
 #include "amdgpu_dm.h"
 #include "amdgpu_virt.h"
 #include "amdgpu_csa.h"
+#include "amdgpu_mes_ctx.h"
 #include "amdgpu_gart.h"
 #include "amdgpu_debugfs.h"
 #include "amdgpu_job.h"
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes_ctx.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes_ctx.h
new file mode 100644
index 000000000000..f3e1ba1a889f
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes_ctx.h
@@ -0,0 +1,118 @@
+/*
+ * Copyright 2019 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef __AMDGPU_MES_CTX_H__
+#define __AMDGPU_MES_CTX_H__
+
+#include "v10_structs.h"
+
+enum {
+	AMDGPU_MES_CTX_RPTR_OFFS = 0,
+	AMDGPU_MES_CTX_WPTR_OFFS,
+	AMDGPU_MES_CTX_FENCE_OFFS,
+	AMDGPU_MES_CTX_COND_EXE_OFFS,
+	AMDGPU_MES_CTX_TRAIL_FENCE_OFFS,
+	AMDGPU_MES_CTX_MAX_OFFS,
+};
+
+enum {
+	AMDGPU_MES_CTX_RING_OFFS = AMDGPU_MES_CTX_MAX_OFFS,
+	AMDGPU_MES_CTX_IB_OFFS,
+	AMDGPU_MES_CTX_PADDING_OFFS,
+};
+
+#define AMDGPU_MES_CTX_MAX_GFX_RINGS            1
+#define AMDGPU_MES_CTX_MAX_COMPUTE_RINGS        4
+#define AMDGPU_MES_CTX_MAX_SDMA_RINGS           2
+#define AMDGPU_MES_CTX_MAX_RINGS					\
+	(AMDGPU_MES_CTX_MAX_GFX_RINGS +					\
+	 AMDGPU_MES_CTX_MAX_COMPUTE_RINGS +				\
+	 AMDGPU_MES_CTX_MAX_SDMA_RINGS)
+
+#define AMDGPU_CSA_SDMA_SIZE    64
+#define GFX10_MEC_HPD_SIZE	2048
+
+struct amdgpu_wb_slot {
+	uint32_t data[8];
+};
+
+struct amdgpu_mes_ctx_meta_data {
+	struct {
+		uint8_t ring[PAGE_SIZE * 4];
+
+		/* gfx csa */
+		struct v10_gfx_meta_data gfx_meta_data;
+
+		uint8_t gds_backup[64 * 1024];
+
+		struct amdgpu_wb_slot slots[AMDGPU_MES_CTX_MAX_OFFS];
+
+		/* only for ib test */
+		uint32_t ib[256] __aligned(256);
+
+		uint32_t padding[64];
+
+	} __aligned(PAGE_SIZE) gfx[AMDGPU_MES_CTX_MAX_GFX_RINGS];
+
+	struct {
+		uint8_t ring[PAGE_SIZE * 4];
+
+		uint8_t mec_hpd[GFX10_MEC_HPD_SIZE];
+
+		struct amdgpu_wb_slot slots[AMDGPU_MES_CTX_MAX_OFFS];
+
+		/* only for ib test */
+		uint32_t ib[256] __aligned(256);
+
+		uint32_t padding[64];
+
+	} __aligned(PAGE_SIZE) compute[AMDGPU_MES_CTX_MAX_COMPUTE_RINGS];
+
+	struct {
+		uint8_t ring[PAGE_SIZE * 4];
+
+		/* sdma csa for mcbp */
+		uint8_t sdma_meta_data[AMDGPU_CSA_SDMA_SIZE];
+
+		struct amdgpu_wb_slot slots[AMDGPU_MES_CTX_MAX_OFFS];
+
+		/* only for ib test */
+		uint32_t ib[256] __aligned(256);
+
+		uint32_t padding[64];
+
+	} __aligned(PAGE_SIZE) sdma[AMDGPU_MES_CTX_MAX_SDMA_RINGS];
+};
+
+struct amdgpu_mes_ctx_data {
+	struct amdgpu_bo	*meta_data_obj;
+	uint64_t                meta_data_gpu_addr;
+	struct amdgpu_bo_va	*meta_data_va;
+	void                    *meta_data_ptr;
+	uint32_t                gang_ids[AMDGPU_HW_IP_DMA+1];
+};
+
+#define AMDGPU_FENCE_MES_QUEUE_FLAG     0x1000000u
+#define AMDGPU_FENCE_MES_QUEUE_ID_MASK  (AMDGPU_FENCE_MES_QUEUE_FLAG - 1)
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 20dfe5a19a81..112c2b0ef0b1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -364,6 +364,15 @@ static inline void amdgpu_ring_write_multiple(struct amdgpu_ring *ring,
 	ring->count_dw -= count_dw;
 }
 
+#define amdgpu_mes_ctx_get_offs_gpu_addr(ring, offset)			\
+	(ring->is_mes_queue && ring->mes_ctx ?				\
+	 (ring->mes_ctx->meta_data_gpu_addr + offset) : 0)
+
+#define amdgpu_mes_ctx_get_offs_cpu_addr(ring, offset)			\
+	(ring->is_mes_queue && ring->mes_ctx ?				\
+	 (void *)((uint8_t *)(ring->mes_ctx->meta_data_ptr) + offset) : \
+	 NULL)
+
 int amdgpu_ring_test_helper(struct amdgpu_ring *ring);
 
 void amdgpu_debugfs_ring_init(struct amdgpu_device *adev,
-- 
2.35.1


  parent reply	other threads:[~2022-04-29 17:46 UTC|newest]

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-29 17:45 [PATCH 00/73] MES support Alex Deucher
2022-04-29 17:45 ` [PATCH 01/73] drm/amdgpu: define MQD abstract layer for hw ip Alex Deucher
2022-04-29 17:45 ` [PATCH 02/73] drm/amdgpu: add helper function to initialize mqd from ring v4 Alex Deucher
2022-04-29 17:45 ` Alex Deucher [this message]
2022-04-29 17:45 ` [PATCH 04/73] drm/amdgpu: add mes ctx data in amdgpu_ring Alex Deucher
2022-04-29 17:45 ` [PATCH 05/73] drm/amdgpu: define ring structure to access rptr/wptr/fence Alex Deucher
2022-04-29 17:45 ` [PATCH 06/73] drm/amdgpu: use ring structure to access rptr/wptr v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 07/73] drm/amdgpu: initialize/finalize the ring for mes queue Alex Deucher
2022-04-29 17:45 ` [PATCH 08/73] drm/amdgpu: assign the cpu/gpu address of fence from ring Alex Deucher
2022-04-29 17:45 ` [PATCH 09/73] drm/amdgpu/gfx10: implement mqd functions of gfx/compute eng v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 10/73] drm/amdgpu/gfx10: use per ctx CSA for ce metadata Alex Deucher
2022-04-29 17:45 ` [PATCH 11/73] drm/amdgpu/gfx10: use per ctx CSA for de metadata Alex Deucher
2022-04-29 17:45 ` [PATCH 12/73] drm/amdgpu/gfx10: associate mes queue id with fence v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 13/73] drm/amdgpu/gfx10: inherit vmid from mqd Alex Deucher
2022-04-29 17:45 ` [PATCH 14/73] drm/amdgpu/gfx10: use INVALIDATE_TLBS to invalidate TLBs v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 15/73] drm/amdgpu/gmc10: skip emitting pasid mapping packet Alex Deucher
2022-04-29 17:45 ` [PATCH 16/73] drm/amdgpu: use the whole doorbell space for mes Alex Deucher
2022-04-29 17:45 ` [PATCH 17/73] drm/amdgpu: update mes process/gang/queue definitions Alex Deucher
2022-04-29 17:45 ` [PATCH 18/73] drm/amdgpu: add mes_kiq module parameter v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 19/73] drm/amdgpu: allocate doorbell index for mes kiq Alex Deucher
2022-04-29 17:45 ` [PATCH 20/73] drm/amdgpu/mes: extend mes framework to support multiple mes pipes Alex Deucher
2022-04-29 17:45 ` [PATCH 21/73] drm/amdgpu/gfx10: add mes queue fence handling Alex Deucher
2022-04-29 17:45 ` [PATCH 22/73] drm/amdgpu/gfx10: add mes support for gfx ib test Alex Deucher
2022-04-29 17:45 ` [PATCH 23/73] drm/amdgpu: don't use kiq to flush gpu tlb if mes enabled Alex Deucher
2022-04-29 17:45 ` [PATCH 24/73] drm/amdgpu/sdma: use per-ctx sdma csa address for mes sdma queue Alex Deucher
2022-04-29 17:45 ` [PATCH 25/73] drm/amdgpu/sdma5.2: initialize sdma mqd Alex Deucher
2022-04-29 17:45 ` [PATCH 26/73] drm/amdgpu/sdma5.2: associate mes queue id with fence Alex Deucher
2022-04-29 17:45 ` [PATCH 27/73] drm/amdgpu/sdma5.2: add mes queue fence handling Alex Deucher
2022-04-29 17:45 ` [PATCH 28/73] drm/amdgpu/sdma5.2: add mes support for sdma ring test Alex Deucher
2022-04-29 17:45 ` [PATCH 29/73] drm/amdgpu/sdma5.2: add mes support for sdma ib test Alex Deucher
2022-04-29 17:45 ` [PATCH 30/73] drm/amdgpu/sdma5: initialize sdma mqd Alex Deucher
2022-04-29 17:45 ` [PATCH 31/73] drm/amdgpu/sdma5: associate mes queue id with fence Alex Deucher
2022-04-29 17:45 ` [PATCH 32/73] drm/amdgpu/sdma5: add mes queue fence handling Alex Deucher
2022-04-29 17:45 ` [PATCH 33/73] drm/amdgpu/sdma5: add mes support for sdma ring test Alex Deucher
2022-04-29 17:45 ` [PATCH 34/73] drm/amdgpu/sdma5: add mes support for sdma ib test Alex Deucher
2022-04-29 17:45 ` [PATCH 35/73] drm/amdgpu: add mes kiq PSP GFX FW type Alex Deucher
2022-04-29 17:45 ` [PATCH 36/73] drm/amdgpu/mes: add mes kiq callback Alex Deucher
2022-04-29 17:45 ` [PATCH 37/73] drm/amdgpu: add mes kiq frontdoor loading support Alex Deucher
2022-04-29 17:45 ` [PATCH 38/73] drm/amdgpu: enable mes kiq N-1 test on sienna cichlid Alex Deucher
2022-04-29 17:45 ` [PATCH 39/73] drm/amdgpu/mes: manage mes doorbell allocation Alex Deucher
2022-04-29 17:45 ` [PATCH 40/73] drm/amdgpu: add mes queue id mask v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 41/73] drm/amdgpu/mes: initialize/finalize common mes structure v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 42/73] drm/amdgpu/mes: relocate status_fence slot allocation Alex Deucher
2022-04-29 17:45 ` [PATCH 43/73] drm/amdgpu/mes10.1: call general mes initialization Alex Deucher
2022-04-29 17:45 ` [PATCH 44/73] drm/amdgpu/mes10.1: add delay after mes engine enable Alex Deucher
2022-04-29 17:45 ` [PATCH 45/73] drm/amdgpu/mes10.1: implement the suspend/resume routine Alex Deucher
2022-04-29 17:45 ` [PATCH 46/73] drm/amdgpu/mes: implement creating mes process v2 Alex Deucher
2022-04-29 17:45 ` [PATCH 47/73] drm/amdgpu/mes: implement destroying mes process Alex Deucher
2022-04-29 17:45 ` [PATCH 48/73] drm/amdgpu/mes: implement adding mes gang Alex Deucher
2022-04-29 17:46 ` [PATCH 49/73] drm/amdgpu/mes: implement removing " Alex Deucher
2022-04-29 17:46 ` [PATCH 50/73] drm/amdgpu/mes: implement suspending all gangs Alex Deucher
2022-04-29 17:46 ` [PATCH 51/73] drm/amdgpu/mes: implement resuming " Alex Deucher
2022-04-29 17:46 ` [PATCH 52/73] drm/amdgpu/mes: initialize mqd from queue properties Alex Deucher
2022-04-29 17:46 ` [PATCH 53/73] drm/amdgpu/mes: implement adding mes queue Alex Deucher
2022-04-29 17:46 ` [PATCH 54/73] drm/amdgpu/mes: implement removing " Alex Deucher
2022-04-29 17:46 ` [PATCH 55/73] drm/amdgpu/mes: add helper function to convert ring to queue property Alex Deucher
2022-04-29 17:46 ` [PATCH 56/73] drm/amdgpu/mes: add helper function to get the ctx meta data offset Alex Deucher
2022-04-29 17:46 ` [PATCH 57/73] drm/amdgpu/mes: use ring for kernel queue submission Alex Deucher
2022-04-29 17:46 ` [PATCH 58/73] drm/amdgpu/mes: implement removing mes ring Alex Deucher
2022-04-29 17:46 ` [PATCH 59/73] drm/amdgpu/mes: add helper functions to alloc/free ctx metadata Alex Deucher
2022-04-29 17:46 ` [PATCH 60/73] drm/amdgpu: skip kfd routines when mes enabled Alex Deucher
2022-04-29 17:46 ` [PATCH 61/73] drm/amdgpu: Enable KFD with MES enabled Alex Deucher
2022-04-29 17:46 ` [PATCH 62/73] drm/amdgpu: skip some checking for mes queue ib submission Alex Deucher
2022-04-29 17:46 ` [PATCH 63/73] drm/amdgpu: skip kiq ib tests if mes enabled Alex Deucher
2022-04-29 17:46 ` [PATCH 64/73] drm/amdgpu: skip gds switch for mes queue Alex Deucher
2022-04-29 17:46 ` [PATCH 65/73] drm/amdgpu: kiq takes charge of all queues Alex Deucher
2022-04-29 17:46 ` [PATCH 66/73] drm/amdgpu/mes: map ctx metadata for mes self test Alex Deucher
2022-04-29 17:46 ` [PATCH 67/73] drm/amdgpu/mes: create gang and queues " Alex Deucher
2022-04-29 17:46 ` [PATCH 68/73] drm/amdgpu/mes: add ring/ib test " Alex Deucher
2022-04-29 17:46 ` [PATCH 69/73] drm/amdgpu/mes: implement " Alex Deucher
2022-04-29 17:46 ` [PATCH 70/73] drm/amdgpu/mes10.1: add mes self test in late init Alex Deucher
2022-04-29 17:46 ` [PATCH 71/73] drm/amdgpu/mes: fix vm csa update issue Alex Deucher
2022-04-29 17:46 ` [PATCH 72/73] drm/amdgpu/mes: disable mes sdma queue test Alex Deucher
2022-04-29 17:46 ` [PATCH 73/73] drm/amdgpu/mes: Update the doorbell function signatures Alex Deucher

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=20220429174624.459475-4-alexander.deucher@amd.com \
    --to=alexander.deucher@amd.com \
    --cc=Hawking.Zhang@amd.com \
    --cc=Jack.Xiao@amd.com \
    --cc=amd-gfx@lists.freedesktop.org \
    --cc=christian.koenig@amd.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