[PATCH 5.7 102/112] drm/i915: Include asm sources for {ivb, hsw}_clear_kernel.c
From: Greg Kroah-Hartman
Date: Tue Jul 07 2020 - 11:28:16 EST
From: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx>
commit 55fd7e0222ea01246ef3e6aae28b5721fdfb790f upstream.
Alexandre Oliva has recently removed these files from Linux Libre
with concerns that the sources weren't available.
The sources are available on IGT repository, and only open source
tools are used to generate the {ivb,hsw}_clear_kernel.c files.
However, the remaining concern from Alexandre Oliva was around
GPL license and the source not been present when distributing
the code.
So, it looks like 2 alternatives are possible, the use of
linux-firmware.git repository to store the blob or making sure
that the source is also present in our tree. Since the goal
is to limit the i915 firmware to only the micro-controller blobs
let's make sure that we do include the asm sources here in our tree.
Btw, I tried to have some diligence here and make sure that the
asms that these commits are adding are truly the source for
the mentioned files:
igt$ ./scripts/generate_clear_kernel.sh -g ivb \
-m ~/mesa/build/src/intel/tools/i965_asm
Output file not specified - using default file "ivb-cb_assembled"
Generating gen7 CB Kernel assembled file "ivb_clear_kernel.c"
for i915 driver...
igt$ diff ~/i915/drm-tip/drivers/gpu/drm/i915/gt/ivb_clear_kernel.c \
ivb_clear_kernel.c
< * Generated by: IGT Gpu Tools on Fri 21 Feb 2020 05:29:32 AM UTC
> * Generated by: IGT Gpu Tools on Mon 08 Jun 2020 10:00:54 AM PDT
61c61
< };
> };
\ No newline at end of file
igt$ ./scripts/generate_clear_kernel.sh -g hsw \
-m ~/mesa/build/src/intel/tools/i965_asm
Output file not specified - using default file "hsw-cb_assembled"
Generating gen7.5 CB Kernel assembled file "hsw_clear_kernel.c"
for i915 driver...
igt$ diff ~/i915/drm-tip/drivers/gpu/drm/i915/gt/hsw_clear_kernel.c \
hsw_clear_kernel.c
5c5
< * Generated by: IGT Gpu Tools on Fri 21 Feb 2020 05:30:13 AM UTC
> * Generated by: IGT Gpu Tools on Mon 08 Jun 2020 10:01:42 AM PDT
61c61
< };
> };
\ No newline at end of file
Used IGT and Mesa master repositories from Fri Jun 5 2020)
IGT: 53e8c878a6fb ("tests/kms_chamelium: Force reprobe after replugging
the connector")
Mesa: 5d13c7477eb1 ("radv: set keep_statistic_info with
RADV_DEBUG=shaderstats")
Mesa built with: meson build -D platforms=drm,x11 -D dri-drivers=i965 \
-D gallium-drivers=iris -D prefix=/usr \
-D libdir=/usr/lib64/ -Dtools=intel \
-Dkulkan-drivers=intel && ninja -C build
v2: Header clean-up and include build instructions in a readme (Chris)
Modified commit message to respect check-patch
Reference: http://www.fsfla.org/pipermail/linux-libre/2020-June/003374.html
Reference: http://www.fsfla.org/pipermail/linux-libre/2020-June/003375.html
Fixes: 47f8253d2b89 ("drm/i915/gen7: Clear all EU/L3 residual contexts")
Cc: <stable@xxxxxxxxxxxxxxx> # v5.7+
Cc: Alexandre Oliva <lxoliva@xxxxxxxxx>
Cc: Prathap Kumar Valsan <prathap.kumar.valsan@xxxxxxxxx>
Cc: Akeem G Abodunrin <akeem.g.abodunrin@xxxxxxxxx>
Cc: Mika Kuoppala <mika.kuoppala@xxxxxxxxxxxxxxx>
Cc: Chris Wilson <chris@xxxxxxxxxxxxxxxxxx>
Cc: Jani Nikula <jani.nikula@xxxxxxxxx>
Cc: Joonas Lahtinen <joonas.lahtinen@xxxxxxxxxxxxxxx>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@xxxxxxxxx>
Reviewed-by: Jon Bloomfield <jon.bloomfield@xxxxxxxxx>
Link: https://patchwork.freedesktop.org/patch/msgid/20200610201807.191440-1-rodrigo.vivi@xxxxxxxxx
(cherry picked from commit 5a7eeb8ba143d860050ecea924a8f074f02d8023)
Signed-off-by: Jani Nikula <jani.nikula@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
drivers/gpu/drm/i915/gt/shaders/README | 46 +++++++
drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm | 119 +++++++++++++++++++
drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm | 117 ++++++++++++++++++
3 files changed, 282 insertions(+)
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/README
@@ -0,0 +1,46 @@
+ASM sources for auto generated shaders
+======================================
+
+The i915/gt/hsw_clear_kernel.c and i915/gt/ivb_clear_kernel.c files contain
+pre-compiled batch chunks that will clear any residual render cache during
+context switch.
+
+They are generated from their respective platform ASM files present on
+i915/gt/shaders/clear_kernel directory.
+
+The generated .c files should never be modified directly. Instead, any modification
+needs to be done on the on their respective ASM files and build instructions below
+needes to be followed.
+
+Building
+========
+
+Environment
+-----------
+
+IGT GPU tool scripts and the Mesa's i965 instruction assembler tool are used
+on building.
+
+Please make sure your Mesa tool is compiled with "-Dtools=intel" and
+"-Ddri-drivers=i965", and run this script from IGT source root directory"
+
+The instructions bellow assume:
+ * IGT gpu tools source code is located on your home directory (~) as ~/igt
+ * Mesa source code is located on your home directory (~) as ~/mesa
+ and built under the ~/mesa/build directory
+ * Linux kernel source code is under your home directory (~) as ~/linux
+
+Instructions
+------------
+
+~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm \
+ ~/igt/lib/i915/shaders/clear_kernel/ivb.asm
+~ $ cd ~/igt
+igt $ ./scripts/generate_clear_kernel.sh -g ivb \
+ -m ~/mesa/build/src/intel/tools/i965_asm
+
+~ $ cp ~/linux/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm \
+ ~/igt/lib/i915/shaders/clear_kernel/hsw.asm
+~ $ cd ~/igt
+igt $ ./scripts/generate_clear_kernel.sh -g hsw \
+ -m ~/mesa/build/src/intel/tools/i965_asm
\ No newline at end of file
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/hsw.asm
@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright  2020 Intel Corporation
+ */
+
+/*
+ * Kernel for PAVP buffer clear.
+ *
+ * 1. Clear all 64 GRF registers assigned to the kernel with designated value;
+ * 2. Write 32x16 block of all "0" to render target buffer which indirectly clears
+ * 512 bytes of Render Cache.
+ */
+
+/* Store designated "clear GRF" value */
+mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N };
+
+/**
+ * Curbe Format
+ *
+ * DW 1.0 - Block Offset to write Render Cache
+ * DW 1.1 [15:0] - Clear Word
+ * DW 1.2 - Delay iterations
+ * DW 1.3 - Enable Instrumentation (only for debug)
+ * DW 1.4 - Rsvd (intended for context ID)
+ * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount
+ * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count)
+ * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count)
+ *
+ * Binding Table
+ *
+ * BTI 0: 2D Surface to help clear L3 (Render/Data Cache)
+ * BTI 1: Wait/Instrumentation Buffer
+ * Size : (SliceCount * SubSliceCount * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT)
+ * Expected to be initialized to 0 by driver/another kernel
+ * Layout:
+ * RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS]
+ * Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N
+ */
+add(1) g1.2<1>UD g1.2<0,1,0>UD 0x00000001UD { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */
+cmp.z.f0.0(1) null<1>UD g1.3<0,1,0>UD 0x00000000UD { align1 1N };
+(+f0.0) jmpi(1) 352D { align1 WE_all 1N };
+
+/**
+ * State Register has info on where this thread is running
+ * IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ * HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ */
+mov(8) g3<1>UD 0x00000000UD { align1 1Q };
+shr(1) g3<1>D sr0<0,1,0>D 12D { align1 1N };
+and(1) g3<1>D g3<0,1,0>D 1D { align1 1N }; /* g3 has HSID */
+shr(1) g3.1<1>D sr0<0,1,0>D 13D { align1 1N };
+and(1) g3.1<1>D g3.1<0,1,0>D 3D { align1 1N }; /* g3.1 has sliceID */
+mul(1) g3.5<1>D g3.1<0,1,0>D g1.10<0,1,0>UW { align1 1N };
+add(1) g3<1>D g3<0,1,0>D g3.5<0,1,0>D { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */
+shr(1) g3.2<1>D sr0<0,1,0>D 8D { align1 1N };
+and(1) g3.2<1>D g3.2<0,1,0>D 15D { align1 1N }; /* g3.2 = EUID */
+mul(1) g3.4<1>D g3<0,1,0>D 16D { align1 1N };
+add(1) g3.2<1>D g3.2<0,1,0>D g3.4<0,1,0>D { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address ) in instrumentation surf */
+
+mov(8) g5<1>UD 0x00000000UD { align1 1Q };
+and(1) g3.3<1>D sr0<0,1,0>D 7D { align1 1N };
+mul(1) g3.3<1>D g3.3<0,1,0>D 4D { align1 1N };
+
+mov(8) g4<1>UD g0<8,8,1>UD { align1 1Q }; /* Initialize message header with g0 */
+mov(1) g4<1>UD g3.3<0,1,0>UD { align1 1N }; /* Block offset */
+mov(1) g4.1<1>UD g3.2<0,1,0>UD { align1 1N }; /* Block offset */
+mov(1) g4.2<1>UD 0x00000003UD { align1 1N }; /* Block size (1 row x 4 bytes) */
+and(1) g4.3<1>UD g4.3<0,1,0>UW 0xffffffffUD { align1 1N };
+
+/* Media block read to fetch current value at specified location in instrumentation buffer */
+sendc(8) g5<1>UD g4<8,8,1>F 0x02190001
+
+ render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q };
+add(1) g5<1>D g5<0,1,0>D 1D { align1 1N };
+
+/* Media block write for updated value at specified location in instrumentation buffer */
+sendc(8) g5<1>UD g4<8,8,1>F 0x040a8001
+ render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q };
+
+/* Delay thread for specified parameter */
+add.nz.f0.0(1) g1.2<1>UD g1.2<0,1,0>UD -1D { align1 1N };
+(+f0.0) jmpi(1) -32D { align1 WE_all 1N };
+
+/* Store designated "clear GRF" value */
+mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N };
+
+/* Initialize looping parameters */
+mov(1) a0<1>D 0D { align1 1N }; /* Initialize a0.0:w=0 */
+mov(1) a0.4<1>W 127W { align1 1N }; /* Loop count. Each loop contains 16 GRF's */
+
+/* Write 32x16 all "0" block */
+mov(8) g2<1>UD g0<8,8,1>UD { align1 1Q };
+mov(8) g127<1>UD g0<8,8,1>UD { align1 1Q };
+mov(2) g2<1>UD g1<2,2,1>UW { align1 1N };
+mov(1) g2.2<1>UD 0x000f000fUD { align1 1N }; /* Block size (16x16) */
+and(1) g2.3<1>UD g2.3<0,1,0>UW 0xffffffefUD { align1 1N };
+mov(16) g3<1>UD 0x00000000UD { align1 1H };
+mov(16) g4<1>UD 0x00000000UD { align1 1H };
+mov(16) g5<1>UD 0x00000000UD { align1 1H };
+mov(16) g6<1>UD 0x00000000UD { align1 1H };
+mov(16) g7<1>UD 0x00000000UD { align1 1H };
+mov(16) g8<1>UD 0x00000000UD { align1 1H };
+mov(16) g9<1>UD 0x00000000UD { align1 1H };
+mov(16) g10<1>UD 0x00000000UD { align1 1H };
+sendc(8) null<1>UD g2<8,8,1>F 0x120a8000
+ render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+add(1) g2<1>UD g1<0,1,0>UW 0x0010UW { align1 1N };
+sendc(8) null<1>UD g2<8,8,1>F 0x120a8000
+ render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+
+/* Now, clear all GRF registers */
+add.nz.f0.0(1) a0.4<1>W a0.4<0,1,0>W -1W { align1 1N };
+mov(16) g[a0]<1>UW f0.1<0,1,0>UW { align1 1H };
+add(1) a0<1>D a0<0,1,0>D 32D { align1 1N };
+(+f0.0) jmpi(1) -64D { align1 WE_all 1N };
+
+/* Terminante the thread */
+sendc(8) null<1>UD g127<8,8,1>F 0x82000010
+ thread_spawner MsgDesc: mlen 1 rlen 0 { align1 1Q EOT };
--- /dev/null
+++ b/drivers/gpu/drm/i915/gt/shaders/clear_kernel/ivb.asm
@@ -0,0 +1,117 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright  2020 Intel Corporation
+ */
+
+/*
+ * Kernel for PAVP buffer clear.
+ *
+ * 1. Clear all 64 GRF registers assigned to the kernel with designated value;
+ * 2. Write 32x16 block of all "0" to render target buffer which indirectly clears
+ * 512 bytes of Render Cache.
+ */
+
+/* Store designated "clear GRF" value */
+mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N };
+
+/**
+ * Curbe Format
+ *
+ * DW 1.0 - Block Offset to write Render Cache
+ * DW 1.1 [15:0] - Clear Word
+ * DW 1.2 - Delay iterations
+ * DW 1.3 - Enable Instrumentation (only for debug)
+ * DW 1.4 - Rsvd (intended for context ID)
+ * DW 1.5 - [31:16]:SliceCount, [15:0]:SubSlicePerSliceCount
+ * DW 1.6 - Rsvd MBZ (intended for Enable Wait on Total Thread Count)
+ * DW 1.7 - Rsvd MBZ (inteded for Total Thread Count)
+ *
+ * Binding Table
+ *
+ * BTI 0: 2D Surface to help clear L3 (Render/Data Cache)
+ * BTI 1: Wait/Instrumentation Buffer
+ * Size : (SliceCount * SubSliceCount * 16 EUs/SubSlice) rows * (16 threads/EU) cols (Format R32_UINT)
+ * Expected to be initialized to 0 by driver/another kernel
+ * Layout :
+ * RowN: Histogram for EU-N: (SliceID*SubSlicePerSliceCount + SSID)*16 + EUID [assume max 16 EUs / SS]
+ * Col-k[DW-k]: Threads Executed on ThreadID-k for EU-N
+ */
+add(1) g1.2<1>UD g1.2<0,1,0>UD 0x00000001UD { align1 1N }; /* Loop count to delay kernel: Init to (g1.2 + 1) */
+cmp.z.f0.0(1) null<1>UD g1.3<0,1,0>UD 0x00000000UD { align1 1N };
+(+f0.0) jmpi(1) 44D { align1 WE_all 1N };
+
+/**
+ * State Register has info on where this thread is running
+ * IVB: sr0.0 :: [15:13]: MBZ, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ * HSW: sr0.0 :: 15: MBZ, [14:13]: SliceID, 12: HSID (Half-Slice ID), [11:8]EUID, [2:0] ThreadSlotID
+ */
+mov(8) g3<1>UD 0x00000000UD { align1 1Q };
+shr(1) g3<1>D sr0<0,1,0>D 12D { align1 1N };
+and(1) g3<1>D g3<0,1,0>D 1D { align1 1N }; /* g3 has HSID */
+shr(1) g3.1<1>D sr0<0,1,0>D 13D { align1 1N };
+and(1) g3.1<1>D g3.1<0,1,0>D 3D { align1 1N }; /* g3.1 has sliceID */
+mul(1) g3.5<1>D g3.1<0,1,0>D g1.10<0,1,0>UW { align1 1N };
+add(1) g3<1>D g3<0,1,0>D g3.5<0,1,0>D { align1 1N }; /* g3 = sliceID * SubSlicePerSliceCount + HSID */
+shr(1) g3.2<1>D sr0<0,1,0>D 8D { align1 1N };
+and(1) g3.2<1>D g3.2<0,1,0>D 15D { align1 1N }; /* g3.2 = EUID */
+mul(1) g3.4<1>D g3<0,1,0>D 16D { align1 1N };
+add(1) g3.2<1>D g3.2<0,1,0>D g3.4<0,1,0>D { align1 1N }; /* g3.2 now points to EU row number (Y-pixel = V address ) in instrumentation surf */
+
+mov(8) g5<1>UD 0x00000000UD { align1 1Q };
+and(1) g3.3<1>D sr0<0,1,0>D 7D { align1 1N };
+mul(1) g3.3<1>D g3.3<0,1,0>D 4D { align1 1N };
+
+mov(8) g4<1>UD g0<8,8,1>UD { align1 1Q }; /* Initialize message header with g0 */
+mov(1) g4<1>UD g3.3<0,1,0>UD { align1 1N }; /* Block offset */
+mov(1) g4.1<1>UD g3.2<0,1,0>UD { align1 1N }; /* Block offset */
+mov(1) g4.2<1>UD 0x00000003UD { align1 1N }; /* Block size (1 row x 4 bytes) */
+and(1) g4.3<1>UD g4.3<0,1,0>UW 0xffffffffUD { align1 1N };
+
+/* Media block read to fetch current value at specified location in instrumentation buffer */
+sendc(8) g5<1>UD g4<8,8,1>F 0x02190001
+ render MsgDesc: media block read MsgCtrl = 0x0 Surface = 1 mlen 1 rlen 1 { align1 1Q };
+add(1) g5<1>D g5<0,1,0>D 1D { align1 1N };
+
+/* Media block write for updated value at specified location in instrumentation buffer */
+sendc(8) g5<1>UD g4<8,8,1>F 0x040a8001
+ render MsgDesc: media block write MsgCtrl = 0x0 Surface = 1 mlen 2 rlen 0 { align1 1Q };
+/* Delay thread for specified parameter */
+add.nz.f0.0(1) g1.2<1>UD g1.2<0,1,0>UD -1D { align1 1N };
+(+f0.0) jmpi(1) -4D { align1 WE_all 1N };
+
+/* Store designated "clear GRF" value */
+mov(1) f0.1<1>UW g1.2<0,1,0>UW { align1 1N };
+
+/* Initialize looping parameters */
+mov(1) a0<1>D 0D { align1 1N }; /* Initialize a0.0:w=0 */
+mov(1) a0.4<1>W 127W { align1 1N }; /* Loop count. Each loop contains 16 GRF's */
+
+/* Write 32x16 all "0" block */
+mov(8) g2<1>UD g0<8,8,1>UD { align1 1Q };
+mov(8) g127<1>UD g0<8,8,1>UD { align1 1Q };
+mov(2) g2<1>UD g1<2,2,1>UW { align1 1N };
+mov(1) g2.2<1>UD 0x000f000fUD { align1 1N }; /* Block size (16x16) */
+and(1) g2.3<1>UD g2.3<0,1,0>UW 0xffffffefUD { align1 1N };
+mov(16) g3<1>UD 0x00000000UD { align1 1H };
+mov(16) g4<1>UD 0x00000000UD { align1 1H };
+mov(16) g5<1>UD 0x00000000UD { align1 1H };
+mov(16) g6<1>UD 0x00000000UD { align1 1H };
+mov(16) g7<1>UD 0x00000000UD { align1 1H };
+mov(16) g8<1>UD 0x00000000UD { align1 1H };
+mov(16) g9<1>UD 0x00000000UD { align1 1H };
+mov(16) g10<1>UD 0x00000000UD { align1 1H };
+sendc(8) null<1>UD g2<8,8,1>F 0x120a8000
+ render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+add(1) g2<1>UD g1<0,1,0>UW 0x0010UW { align1 1N };
+sendc(8) null<1>UD g2<8,8,1>F 0x120a8000
+ render MsgDesc: media block write MsgCtrl = 0x0 Surface = 0 mlen 9 rlen 0 { align1 1Q };
+
+/* Now, clear all GRF registers */
+add.nz.f0.0(1) a0.4<1>W a0.4<0,1,0>W -1W { align1 1N };
+mov(16) g[a0]<1>UW f0.1<0,1,0>UW { align1 1H };
+add(1) a0<1>D a0<0,1,0>D 32D { align1 1N };
+(+f0.0) jmpi(1) -8D { align1 WE_all 1N };
+
+/* Terminante the thread */
+sendc(8) null<1>UD g127<8,8,1>F 0x82000010
+ thread_spawner MsgDesc: mlen 1 rlen 0 { align1 1Q EOT };