thr3ads.net - Nouveau - [Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore [Nov 2017]

If this information is useful, please help other people find it:
Share via:

Karol Herbst

2017-Nov-01 16:51 UTC

[Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore

fixes compilation issues with recent envytools, because movw was removed
from fuc5, because it doesn't exist there anymore. The current code is
most likely broken for fuc5 hardware as well and might have triggered all
kinds of random memory reclocking fails.

Changes in fuc3 binaries are tue do opcode optimizations using shorter
opcodes when possible.

Signed-off-by: Karol Herbst <kherbst at redhat.com>
---
 drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h |  746 +++++++++----------
 drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h |  802 ++++++++++----------
 drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h | 1006 +++++++++++++-------------
 drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc     |   30 +-
 4 files changed, 1292 insertions(+), 1292 deletions(-)

diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
b/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
index 0bcf0b30..0ce37dd4 100644
--- a/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
+++ b/drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h
@@ -46,8 +46,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x00000756,
-	0x00000748,
+	0x00000754,
+	0x00000746,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x0000075a,
 	0x00000758,
+	0x00000756,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x00000b8a,
-	0x00000a2d,
+	0x00000b88,
+	0x00000a2b,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x00000bb3,
-	0x00000b8c,
+	0x00000bb1,
+	0x00000b8a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ static uint32_t gf100_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000bbf,
 	0x00000bbd,
+	0x00000bbb,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -236,19 +236,19 @@ static uint32_t gf100_pmu_data[] = {
 	0x000005d3,
 	0x00000003,
 	0x00000002,
-	0x0000069d,
+	0x0000069b,
 	0x00040004,
 	0x00000000,
-	0x000006b9,
+	0x000006b7,
 	0x00010005,
 	0x00000000,
-	0x000006d6,
+	0x000006d4,
 	0x00010006,
 	0x00000000,
 	0x0000065b,
 	0x00000007,
 	0x00000000,
-	0x000006e1,
+	0x000006df,
 /* 0x03c4: memx_func_tail */
 /* 0x03c4: memx_ts_start */
 	0x00000000,
@@ -1372,432 +1372,432 @@ static uint32_t gf100_pmu_code[] = {
 /* 0x065b: memx_func_wait_vblank */
 	0x9800f840,
 	0x66b00016,
-	0x130bf400,
+	0x120bf400,
 	0xf40166b0,
 	0x0ef4060b,
 /* 0x066d: memx_func_wait_vblank_head1 */
-	0x2077f12e,
-	0x070ef400,
-/* 0x0674: memx_func_wait_vblank_head0 */
-	0x000877f1,
-/* 0x0678: memx_func_wait_vblank_0 */
-	0x07c467f1,
-	0xcf0664b6,
-	0x67fd0066,
-	0xf31bf404,
-/* 0x0688: memx_func_wait_vblank_1 */
-	0x07c467f1,
-	0xcf0664b6,
-	0x67fd0066,
-	0xf30bf404,
-/* 0x0698: memx_func_wait_vblank_fini */
-	0xf80410b6,
-/* 0x069d: memx_func_wr32 */
-	0x00169800,
-	0xb6011598,
-	0x60f90810,
-	0xd0fc50f9,
-	0x21f4e0fc,
-	0x0242b640,
-	0xf8e91bf4,
-/* 0x06b9: memx_func_wait */
-	0x2c87f000,
-	0xcf0684b6,
-	0x1e980088,
-	0x011d9800,
-	0x98021c98,
-	0x10b6031b,
-	0xa321f410,
-/* 0x06d6: memx_func_delay */
-	0x1e9800f8,
-	0x0410b600,
-	0xf87e21f4,
-/* 0x06e1: memx_func_train */
-/* 0x06e3: memx_exec */
-	0xf900f800,
-	0xb9d0f9e0,
-	0xb2b902c1,
-/* 0x06ed: memx_exec_next */
-	0x00139802,
-	0xe70410b6,
-	0xe701f034,
-	0xb601e033,
-	0x30f00132,
-	0xde35980c,
-	0x12b855f9,
-	0xe41ef406,
-	0x98f10b98,
-	0xcbbbf20c,
-	0xc4b7f102,
-	0x06b4b607,
-	0xfc00bbcf,
-	0xf5e0fcd0,
-	0xf8033621,
-/* 0x0729: memx_info */
-	0x01c67000,
-/* 0x072f: memx_info_data */
-	0xf10e0bf4,
-	0xf103ccc7,
-	0xf40800b7,
-/* 0x073a: memx_info_train */
-	0xc7f10b0e,
-	0xb7f10bcc,
-/* 0x0742: memx_info_send */
-	0x21f50100,
-	0x00f80336,
-/* 0x0748: memx_recv */
-	0xf401d6b0,
-	0xd6b0980b,
-	0xd80bf400,
-/* 0x0756: memx_init */
-	0x00f800f8,
-/* 0x0758: perf_recv */
-/* 0x075a: perf_init */
+	0x2077f02c,
+/* 0x0673: memx_func_wait_vblank_head0 */
+	0xf0060ef4,
+/* 0x0676: memx_func_wait_vblank_0 */
+	0x67f10877,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x0686: memx_func_wait_vblank_1 */
+	0x67f1f31b,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x0696: memx_func_wait_vblank_fini */
+	0x10b6f30b,
+/* 0x069b: memx_func_wr32 */
+	0x9800f804,
+	0x15980016,
+	0x0810b601,
+	0x50f960f9,
+	0xe0fcd0fc,
+	0xb64021f4,
+	0x1bf40242,
+/* 0x06b7: memx_func_wait */
+	0xf000f8e9,
+	0x84b62c87,
+	0x0088cf06,
+	0x98001e98,
+	0x1c98011d,
+	0x031b9802,
+	0xf41010b6,
+	0x00f8a321,
+/* 0x06d4: memx_func_delay */
+	0xb6001e98,
+	0x21f40410,
+/* 0x06df: memx_func_train */
+	0xf800f87e,
+/* 0x06e1: memx_exec */
+	0xf9e0f900,
+	0x02c1b9d0,
+/* 0x06eb: memx_exec_next */
+	0x9802b2b9,
+	0x10b60013,
+	0xf034e704,
+	0xe033e701,
+	0x0132b601,
+	0x980c30f0,
+	0x55f9de35,
+	0xf40612b8,
+	0x0b98e41e,
+	0xf20c98f1,
+	0xf102cbbb,
+	0xb607c4b7,
+	0xbbcf06b4,
+	0xfcd0fc00,
+	0x3621f5e0,
+/* 0x0727: memx_info */
+	0x7000f803,
+	0x0bf401c6,
+/* 0x072d: memx_info_data */
+	0xccc7f10e,
+	0x00b7f103,
+	0x0b0ef408,
+/* 0x0738: memx_info_train */
+	0x0bccc7f1,
+	0x0100b7f1,
+/* 0x0740: memx_info_send */
+	0x033621f5,
+/* 0x0746: memx_recv */
+	0xd6b000f8,
+	0x980bf401,
+	0xf400d6b0,
+	0x00f8d80b,
+/* 0x0754: memx_init */
+/* 0x0756: perf_recv */
 	0x00f800f8,
-/* 0x075c: i2c_drive_scl */
-	0xf40036b0,
-	0x07f1110b,
-	0x04b607e0,
-	0x0001d006,
-	0x00f804bd,
-/* 0x0770: i2c_drive_scl_lo */
-	0x07e407f1,
-	0xd00604b6,
-	0x04bd0001,
-/* 0x077e: i2c_drive_sda */
+/* 0x0758: perf_init */
+/* 0x075a: i2c_drive_scl */
 	0x36b000f8,
 	0x110bf400,
 	0x07e007f1,
 	0xd00604b6,
-	0x04bd0002,
-/* 0x0792: i2c_drive_sda_lo */
+	0x04bd0001,
+/* 0x076e: i2c_drive_scl_lo */
 	0x07f100f8,
 	0x04b607e4,
+	0x0001d006,
+	0x00f804bd,
+/* 0x077c: i2c_drive_sda */
+	0xf40036b0,
+	0x07f1110b,
+	0x04b607e0,
 	0x0002d006,
 	0x00f804bd,
-/* 0x07a0: i2c_sense_scl */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0431fd00,
-	0xf4060bf4,
-/* 0x07b6: i2c_sense_scl_done */
-	0x00f80131,
-/* 0x07b8: i2c_sense_sda */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0432fd00,
-	0xf4060bf4,
-/* 0x07ce: i2c_sense_sda_done */
-	0x00f80131,
-/* 0x07d0: i2c_raise_scl */
-	0x47f140f9,
-	0x37f00898,
-	0x5c21f501,
-/* 0x07dd: i2c_raise_scl_wait */
-	0xe8e7f107,
-	0x7e21f403,
-	0x07a021f5,
-	0xb60901f4,
-	0x1bf40142,
-/* 0x07f1: i2c_raise_scl_done */
-	0xf840fcef,
-/* 0x07f5: i2c_start */
-	0xa021f500,
-	0x0d11f407,
-	0x07b821f5,
-	0xf40611f4,
-/* 0x0806: i2c_start_rep */
-	0x37f0300e,
-	0x5c21f500,
-	0x0137f007,
-	0x077e21f5,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xd021f550,
-	0x0464b607,
-/* 0x0833: i2c_start_send */
-	0xf01f11f4,
+/* 0x0790: i2c_drive_sda_lo */
+	0x07e407f1,
+	0xd00604b6,
+	0x04bd0002,
+/* 0x079e: i2c_sense_scl */
+	0x32f400f8,
+	0xc437f101,
+	0x0634b607,
+	0xfd0033cf,
+	0x0bf40431,
+	0x0131f406,
+/* 0x07b4: i2c_sense_scl_done */
+/* 0x07b6: i2c_sense_sda */
+	0x32f400f8,
+	0xc437f101,
+	0x0634b607,
+	0xfd0033cf,
+	0x0bf40432,
+	0x0131f406,
+/* 0x07cc: i2c_sense_sda_done */
+/* 0x07ce: i2c_raise_scl */
+	0x40f900f8,
+	0x089847f1,
+	0xf50137f0,
+/* 0x07db: i2c_raise_scl_wait */
+	0xf1075a21,
+	0xf403e8e7,
+	0x21f57e21,
+	0x01f4079e,
+	0x0142b609,
+/* 0x07ef: i2c_raise_scl_done */
+	0xfcef1bf4,
+/* 0x07f3: i2c_start */
+	0xf500f840,
+	0xf4079e21,
+	0x21f50d11,
+	0x11f407b6,
+	0x300ef406,
+/* 0x0804: i2c_start_rep */
+	0xf50037f0,
+	0xf0075a21,
+	0x21f50137,
+	0x76bb077c,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb607ce21,
+	0x11f40464,
+/* 0x0831: i2c_start_send */
+	0x0037f01f,
+	0x077c21f5,
+	0x1388e7f1,
+	0xf07e21f4,
 	0x21f50037,
-	0xe7f1077e,
+	0xe7f1075a,
 	0x21f41388,
-	0x0037f07e,
-	0x075c21f5,
-	0x1388e7f1,
-/* 0x084f: i2c_start_out */
-	0xf87e21f4,
-/* 0x0851: i2c_stop */
-	0x0037f000,
-	0x075c21f5,
-	0xf50037f0,
-	0xf1077e21,
-	0xf403e8e7,
-	0x37f07e21,
-	0x5c21f501,
-	0x88e7f107,
-	0x7e21f413,
+/* 0x084d: i2c_start_out */
+/* 0x084f: i2c_stop */
+	0xf000f87e,
+	0x21f50037,
+	0x37f0075a,
+	0x7c21f500,
+	0xe8e7f107,
+	0x7e21f403,
 	0xf50137f0,
-	0xf1077e21,
+	0xf1075a21,
 	0xf41388e7,
-	0x00f87e21,
-/* 0x0884: i2c_bitw */
-	0x077e21f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x07d021f5,
-	0xf40464b6,
-	0xe7f11811,
-	0x21f41388,
-	0x0037f07e,
-	0x075c21f5,
-	0x1388e7f1,
-/* 0x08c3: i2c_bitw_out */
-	0xf87e21f4,
-/* 0x08c5: i2c_bitr */
-	0x0137f000,
-	0x077e21f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x07d021f5,
-	0xf40464b6,
-	0x21f51b11,
-	0x37f007b8,
-	0x5c21f500,
+	0x37f07e21,
+	0x7c21f501,
 	0x88e7f107,
 	0x7e21f413,
-	0xf4013cf0,
-/* 0x090a: i2c_bitr_done */
-	0x00f80131,
-/* 0x090c: i2c_get_byte */
-	0xf00057f0,
-/* 0x0912: i2c_get_byte_next */
-	0x54b60847,
-	0x0076bb01,
+/* 0x0882: i2c_bitw */
+	0x21f500f8,
+	0xe7f1077c,
+	0x21f403e8,
+	0x0076bb7e,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b608c5,
-	0x2b11f404,
-	0xb60553fd,
-	0x1bf40142,
-	0x0137f0d8,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0x8421f550,
-	0x0464b608,
-/* 0x095c: i2c_get_byte_done */
-/* 0x095e: i2c_put_byte */
-	0x47f000f8,
-/* 0x0961: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
+	0x64b607ce,
+	0x1811f404,
+	0x1388e7f1,
+	0xf07e21f4,
+	0x21f50037,
+	0xe7f1075a,
+	0x21f41388,
+/* 0x08c1: i2c_bitw_out */
+/* 0x08c3: i2c_bitr */
+	0xf000f87e,
+	0x21f50137,
+	0xe7f1077c,
+	0x21f403e8,
+	0x0076bb7e,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b607ce,
+	0x1b11f404,
+	0x07b621f5,
+	0xf50037f0,
+	0xf1075a21,
+	0xf41388e7,
+	0x3cf07e21,
+	0x0131f401,
+/* 0x0908: i2c_bitr_done */
+/* 0x090a: i2c_get_byte */
+	0x57f000f8,
+	0x0847f000,
+/* 0x0910: i2c_get_byte_next */
+	0xbb0154b6,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x088421f5,
+	0x08c321f5,
 	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0xc521f550,
-	0x0464b608,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x09b7: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x09b9: i2c_addr */
-	0x0076bb00,
+	0x53fd2b11,
+	0x0142b605,
+	0xf0d81bf4,
+	0x76bb0137,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb6088221,
+/* 0x095a: i2c_get_byte_done */
+	0x00f80464,
+/* 0x095c: i2c_put_byte */
+/* 0x095f: i2c_put_byte_next */
+	0xb60847f0,
+	0x54ff0142,
+	0x0076bb38,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b607f5,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
+	0x64b60882,
+	0x3411f404,
+	0xf40046b0,
+	0x76bbd81b,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb6095e21,
-/* 0x09fe: i2c_addr_done */
-	0x00f80464,
-/* 0x0a00: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b702e4,
-	0xee980d1c,
-/* 0x0a0f: i2c_acquire */
-	0xf500f800,
-	0xf40a0021,
-	0xd9f00421,
-	0x4021f403,
-/* 0x0a1e: i2c_release */
-	0x21f500f8,
-	0x21f40a00,
-	0x03daf004,
-	0xf84021f4,
-/* 0x0a2d: i2c_recv */
-	0x0132f400,
-	0xb6f8c1c7,
-	0x16b00214,
-	0x3a1ff528,
-	0xf413a001,
-	0x0032980c,
-	0x0ccc13a0,
-	0xf4003198,
-	0xd0f90231,
-	0xd0f9e0f9,
-	0x000067f1,
-	0x100063f1,
-	0xbb016792,
+	0xb608c321,
+	0x11f40464,
+	0x0076bb0f,
+	0xf40136b0,
+	0x32f4061b,
+/* 0x09b5: i2c_put_byte_done */
+/* 0x09b7: i2c_addr */
+	0xbb00f801,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0a0f21f5,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b31bf5,
-	0xbb0057f0,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x09b921f5,
-	0xf50464b6,
-	0xc700d011,
-	0x76bbe0c5,
-	0x0465b600,
-	0x659450f9,
-	0x0256bb04,
-	0x75fd50bd,
-	0xf550fc04,
-	0xb6095e21,
-	0x11f50464,
-	0x57f000ad,
+	0x07f321f5,
+	0xf40464b6,
+	0xc3e72911,
+	0x34b6012e,
+	0x0553fd01,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x5c21f550,
+	0x0464b609,
+/* 0x09fc: i2c_addr_done */
+/* 0x09fe: i2c_acquire_addr */
+	0xcec700f8,
+	0x02e4b6f8,
+	0x0d1ce0b7,
+	0xf800ee98,
+/* 0x0a0d: i2c_acquire */
+	0xfe21f500,
+	0x0421f409,
+	0xf403d9f0,
+	0x00f84021,
+/* 0x0a1c: i2c_release */
+	0x09fe21f5,
+	0xf00421f4,
+	0x21f403da,
+/* 0x0a2b: i2c_recv */
+	0xf400f840,
+	0xc1c70132,
+	0x0214b6f8,
+	0xf52816b0,
+	0xa0013a1f,
+	0x980cf413,
+	0x13a00032,
+	0x31980ccc,
+	0x0231f400,
+	0xe0f9d0f9,
+	0x67f1d0f9,
+	0x63f10000,
+	0x67921000,
 	0x0076bb01,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b609b9,
-	0x8a11f504,
+	0x64b60a0d,
+	0xb0d0fc04,
+	0x1bf500d6,
+	0x57f000b3,
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b6090c,
-	0x6a11f404,
-	0xbbe05bcb,
+	0x64b609b7,
+	0xd011f504,
+	0xe0c5c700,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x5c21f550,
+	0x0464b609,
+	0x00ad11f5,
+	0xbb0157f0,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x085121f5,
-	0xb90464b6,
-	0x74bd025b,
-/* 0x0b33: i2c_recv_not_rd08 */
-	0xb0430ef4,
-	0x1bf401d6,
-	0x0057f03d,
-	0x09b921f5,
-	0xc73311f4,
-	0x21f5e0c5,
-	0x11f4095e,
-	0x0057f029,
-	0x09b921f5,
-	0xc71f11f4,
-	0x21f5e0b5,
-	0x11f4095e,
-	0x5121f515,
-	0xc774bd08,
-	0x1bf408c5,
-	0x0232f409,
-/* 0x0b73: i2c_recv_not_wr08 */
-/* 0x0b73: i2c_recv_done */
-	0xc7030ef4,
-	0x21f5f8ce,
-	0xe0fc0a1e,
-	0x12f4d0fc,
-	0x027cb90a,
-	0x033621f5,
-/* 0x0b88: i2c_recv_exit */
-/* 0x0b8a: i2c_init */
-	0x00f800f8,
-/* 0x0b8c: test_recv */
-	0x05d817f1,
+	0x09b721f5,
+	0xf50464b6,
+	0xbb008a11,
+	0x65b60076,
+	0x9450f904,
+	0x56bb0465,
+	0xfd50bd02,
+	0x50fc0475,
+	0x090a21f5,
+	0xf40464b6,
+	0x5bcb6a11,
+	0x0076bbe0,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b6084f,
+	0x025bb904,
+	0x0ef474bd,
+/* 0x0b31: i2c_recv_not_rd08 */
+	0x01d6b043,
+	0xf03d1bf4,
+	0x21f50057,
+	0x11f409b7,
+	0xe0c5c733,
+	0x095c21f5,
+	0xf02911f4,
+	0x21f50057,
+	0x11f409b7,
+	0xe0b5c71f,
+	0x095c21f5,
+	0xf51511f4,
+	0xbd084f21,
+	0x08c5c774,
+	0xf4091bf4,
+	0x0ef40232,
+/* 0x0b71: i2c_recv_not_wr08 */
+/* 0x0b71: i2c_recv_done */
+	0xf8cec703,
+	0x0a1c21f5,
+	0xd0fce0fc,
+	0xb90a12f4,
+	0x21f5027c,
+/* 0x0b86: i2c_recv_exit */
+	0x00f80336,
+/* 0x0b88: i2c_init */
+/* 0x0b8a: test_recv */
+	0x17f100f8,
+	0x14b605d8,
+	0x0011cf06,
+	0xf10110b6,
+	0xb605d807,
+	0x01d00604,
+	0xf104bd00,
+	0xf1d900e7,
+	0xf5134fe3,
+	0xf8025621,
+/* 0x0bb1: test_init */
+	0x00e7f100,
+	0x5621f508,
+/* 0x0bbb: idle_recv */
+	0xf800f802,
+/* 0x0bbd: idle */
+	0x0031f400,
+	0x05d417f1,
 	0xcf0614b6,
 	0x10b60011,
-	0xd807f101,
+	0xd407f101,
 	0x0604b605,
 	0xbd0001d0,
-	0x00e7f104,
-	0x4fe3f1d9,
-	0x5621f513,
-/* 0x0bb3: test_init */
-	0xf100f802,
-	0xf50800e7,
-	0xf8025621,
-/* 0x0bbd: idle_recv */
-/* 0x0bbf: idle */
-	0xf400f800,
-	0x17f10031,
-	0x14b605d4,
-	0x0011cf06,
-	0xf10110b6,
-	0xb605d407,
-	0x01d00604,
-/* 0x0bdb: idle_loop */
-	0xf004bd00,
-	0x32f45817,
-/* 0x0be1: idle_proc */
-/* 0x0be1: idle_proc_exec */
-	0xb910f902,
-	0x21f5021e,
-	0x10fc033f,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x0bf5: idle_proc_next */
-	0x5810b6ef,
-	0xf4061fb8,
-	0x02f4e61b,
-	0x0028f4dd,
-	0x00bb0ef4,
+/* 0x0bd9: idle_loop */
+	0x5817f004,
+/* 0x0bdf: idle_proc */
+/* 0x0bdf: idle_proc_exec */
+	0xf90232f4,
+	0x021eb910,
+	0x033f21f5,
+	0x11f410fc,
+	0x0231f409,
+/* 0x0bf3: idle_proc_next */
+	0xb6ef0ef4,
+	0x1fb85810,
+	0xe61bf406,
+	0xf4dd02f4,
+	0x0ef40028,
+	0x000000bb,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
b/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
index 9cf4e6fc..5d1dde49 100644
--- a/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
+++ b/drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h
@@ -46,8 +46,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x000005f3,
-	0x000005e5,
+	0x000005ee,
+	0x000005e0,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x000005f7,
-	0x000005f5,
+	0x000005f2,
+	0x000005f0,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x000009f8,
-	0x000008a2,
+	0x000009f3,
+	0x0000089d,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x00000a16,
-	0x000009fa,
+	0x00000a11,
+	0x000009f5,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ static uint32_t gk208_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000a21,
-	0x00000a1f,
+	0x00000a1c,
+	0x00000a1a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -233,22 +233,22 @@ static uint32_t gk208_pmu_data[] = {
 /* 0x037c: memx_func_next */
 	0x00000002,
 	0x00000000,
-	0x000004cf,
+	0x000004cc,
 	0x00000003,
 	0x00000002,
-	0x00000546,
+	0x00000541,
 	0x00040004,
 	0x00000000,
-	0x00000563,
+	0x0000055e,
 	0x00010005,
 	0x00000000,
-	0x0000057d,
+	0x00000578,
 	0x00010006,
 	0x00000000,
-	0x00000541,
+	0x0000053c,
 	0x00000007,
 	0x00000000,
-	0x00000589,
+	0x00000584,
 /* 0x03c4: memx_func_tail */
 /* 0x03c4: memx_ts_start */
 	0x00000000,
@@ -1238,454 +1238,454 @@ static uint32_t gk208_pmu_code[] = {
 	0x0001f604,
 	0x00f804bd,
 /* 0x045c: memx_func_enter */
-	0x162067f1,
-	0xf55d77f1,
-	0x047e6eb2,
-	0xd8b20000,
-	0xf90487fd,
-	0xfc80f960,
-	0x7ee0fcd0,
-	0x0700002d,
-	0x7e6eb2fe,
+	0x47162046,
+	0x6eb2f55d,
+	0x0000047e,
+	0x87fdd8b2,
+	0xf960f904,
+	0xfcd0fc80,
+	0x002d7ee0,
+	0xb2fe0700,
+	0x00047e6e,
+	0xfdd8b200,
+	0x60f90487,
+	0xd0fc80f9,
+	0x2d7ee0fc,
+	0xf0460000,
+	0x7e6eb226,
 	0xb2000004,
 	0x0487fdd8,
 	0x80f960f9,
 	0xe0fcd0fc,
 	0x00002d7e,
-	0x26f067f1,
-	0x047e6eb2,
-	0xd8b20000,
-	0xf90487fd,
-	0xfc80f960,
-	0x7ee0fcd0,
-	0x0600002d,
-	0x07e04004,
-	0xbd0006f6,
-/* 0x04b9: memx_func_enter_wait */
-	0x07c04604,
-	0xf00066cf,
-	0x0bf40464,
-	0xcf2c06f7,
-	0x06b50066,
-/* 0x04cf: memx_func_leave */
-	0x0600f8f1,
-	0x0066cf2c,
-	0x06f206b5,
-	0x07e44004,
-	0xbd0006f6,
-/* 0x04e1: memx_func_leave_wait */
-	0x07c04604,
-	0xf00066cf,
-	0x1bf40464,
-	0xf067f1f7,
+	0xe0400406,
+	0x0006f607,
+/* 0x04b6: memx_func_enter_wait */
+	0xc04604bd,
+	0x0066cf07,
+	0xf40464f0,
+	0x2c06f70b,
+	0xb50066cf,
+	0x00f8f106,
+/* 0x04cc: memx_func_leave */
+	0x66cf2c06,
+	0xf206b500,
+	0xe4400406,
+	0x0006f607,
+/* 0x04de: memx_func_leave_wait */
+	0xc04604bd,
+	0x0066cf07,
+	0xf40464f0,
+	0xf046f71b,
 	0xb2010726,
 	0x00047e6e,
 	0xfdd8b200,
 	0x60f90587,
 	0xd0fc80f9,
 	0x2d7ee0fc,
-	0x67f10000,
-	0x6eb21620,
-	0x0000047e,
-	0x87fdd8b2,
-	0xf960f905,
-	0xfcd0fc80,
-	0x002d7ee0,
-	0x0aa24700,
-	0x047e6eb2,
-	0xd8b20000,
-	0xf90587fd,
-	0xfc80f960,
-	0x7ee0fcd0,
-	0xf800002d,
-/* 0x0541: memx_func_wait_vblank */
+	0x20460000,
+	0x7e6eb216,
+	0xb2000004,
+	0x0587fdd8,
+	0x80f960f9,
+	0xe0fcd0fc,
+	0x00002d7e,
+	0xb20aa247,
+	0x00047e6e,
+	0xfdd8b200,
+	0x60f90587,
+	0xd0fc80f9,
+	0x2d7ee0fc,
+	0x00f80000,
+/* 0x053c: memx_func_wait_vblank */
+	0xf80410b6,
+/* 0x0541: memx_func_wr32 */
+	0x00169800,
+	0xb6011598,
+	0x60f90810,
+	0xd0fc50f9,
+	0x2d7ee0fc,
+	0x42b60000,
+	0xe81bf402,
+/* 0x055e: memx_func_wait */
+	0x2c0800f8,
+	0x980088cf,
+	0x1d98001e,
+	0x021c9801,
+	0xb6031b98,
+	0x747e1010,
+	0x00f80000,
+/* 0x0578: memx_func_delay */
+	0xb6001e98,
+	0x587e0410,
+	0x00f80000,
+/* 0x0584: memx_func_train */
+/* 0x0586: memx_exec */
+	0xe0f900f8,
+	0xc1b2d0f9,
+/* 0x058e: memx_exec_next */
+	0x1398b2b2,
 	0x0410b600,
-/* 0x0546: memx_func_wr32 */
-	0x169800f8,
-	0x01159800,
-	0xf90810b6,
-	0xfc50f960,
+	0x01f034e7,
+	0x01e033e7,
+	0xf00132b6,
+	0x35980c30,
+	0xa655f9de,
+	0xe51ef412,
+	0x98f10b98,
+	0xcbbbf20c,
+	0x07c44b02,
+	0xfc00bbcf,
 	0x7ee0fcd0,
-	0xb600002d,
-	0x1bf40242,
-/* 0x0563: memx_func_wait */
-	0x0800f8e8,
-	0x0088cf2c,
-	0x98001e98,
-	0x1c98011d,
-	0x031b9802,
-	0x7e1010b6,
-	0xf8000074,
-/* 0x057d: memx_func_delay */
-	0x001e9800,
-	0x7e0410b6,
-	0xf8000058,
-/* 0x0589: memx_func_train */
-/* 0x058b: memx_exec */
-	0xf900f800,
-	0xb2d0f9e0,
-/* 0x0593: memx_exec_next */
-	0x98b2b2c1,
-	0x10b60013,
-	0xf034e704,
-	0xe033e701,
-	0x0132b601,
-	0x980c30f0,
-	0x55f9de35,
-	0x1ef412a6,
-	0xf10b98e5,
-	0xbbf20c98,
-	0xc44b02cb,
-	0x00bbcf07,
-	0xe0fcd0fc,
-	0x00029f7e,
-/* 0x05ca: memx_info */
-	0xc67000f8,
-	0x0c0bf401,
-/* 0x05d0: memx_info_data */
-	0x4b03cc4c,
-	0x0ef40800,
-/* 0x05d9: memx_info_train */
-	0x0bcc4c09,
-/* 0x05df: memx_info_send */
-	0x7e01004b,
 	0xf800029f,
-/* 0x05e5: memx_recv */
-	0x01d6b000,
-	0xb0a30bf4,
-	0x0bf400d6,
-/* 0x05f3: memx_init */
-	0xf800f8dc,
-/* 0x05f5: perf_recv */
-/* 0x05f7: perf_init */
-	0xf800f800,
-/* 0x05f9: i2c_drive_scl */
-	0x0036b000,
-	0x400d0bf4,
-	0x01f607e0,
-	0xf804bd00,
-/* 0x0609: i2c_drive_scl_lo */
-	0x07e44000,
-	0xbd0001f6,
-/* 0x0613: i2c_drive_sda */
-	0xb000f804,
-	0x0bf40036,
-	0x07e0400d,
-	0xbd0002f6,
-/* 0x0623: i2c_drive_sda_lo */
-	0x4000f804,
-	0x02f607e4,
-	0xf804bd00,
-/* 0x062d: i2c_sense_scl */
-	0x0132f400,
-	0xcf07c443,
-	0x31fd0033,
-	0x060bf404,
-/* 0x063f: i2c_sense_scl_done */
-	0xf80131f4,
-/* 0x0641: i2c_sense_sda */
-	0x0132f400,
-	0xcf07c443,
-	0x32fd0033,
-	0x060bf404,
-/* 0x0653: i2c_sense_sda_done */
-	0xf80131f4,
-/* 0x0655: i2c_raise_scl */
-	0x4440f900,
-	0x01030898,
-	0x0005f97e,
-/* 0x0660: i2c_raise_scl_wait */
-	0x7e03e84e,
-	0x7e000058,
-	0xf400062d,
-	0x42b60901,
-	0xef1bf401,
-/* 0x0674: i2c_raise_scl_done */
-	0x00f840fc,
-/* 0x0678: i2c_start */
-	0x00062d7e,
-	0x7e0d11f4,
-	0xf4000641,
-	0x0ef40611,
-/* 0x0689: i2c_start_rep */
-	0x7e00032e,
-	0x030005f9,
-	0x06137e01,
+/* 0x05c5: memx_info */
+	0x01c67000,
+/* 0x05cb: memx_info_data */
+	0x4c0c0bf4,
+	0x004b03cc,
+	0x090ef408,
+/* 0x05d4: memx_info_train */
+	0x4b0bcc4c,
+/* 0x05da: memx_info_send */
+	0x9f7e0100,
+	0x00f80002,
+/* 0x05e0: memx_recv */
+	0xf401d6b0,
+	0xd6b0a30b,
+	0xdc0bf400,
+/* 0x05ee: memx_init */
+	0x00f800f8,
+/* 0x05f0: perf_recv */
+/* 0x05f2: perf_init */
+	0x00f800f8,
+/* 0x05f4: i2c_drive_scl */
+	0xf40036b0,
+	0xe0400d0b,
+	0x0001f607,
+	0x00f804bd,
+/* 0x0604: i2c_drive_scl_lo */
+	0xf607e440,
+	0x04bd0001,
+/* 0x060e: i2c_drive_sda */
+	0x36b000f8,
+	0x0d0bf400,
+	0xf607e040,
+	0x04bd0002,
+/* 0x061e: i2c_drive_sda_lo */
+	0xe44000f8,
+	0x0002f607,
+	0x00f804bd,
+/* 0x0628: i2c_sense_scl */
+	0x430132f4,
+	0x33cf07c4,
+	0x0431fd00,
+	0xf4060bf4,
+/* 0x063a: i2c_sense_scl_done */
+	0x00f80131,
+/* 0x063c: i2c_sense_sda */
+	0x430132f4,
+	0x33cf07c4,
+	0x0432fd00,
+	0xf4060bf4,
+/* 0x064e: i2c_sense_sda_done */
+	0x00f80131,
+/* 0x0650: i2c_raise_scl */
+	0x984440f9,
+	0x7e010308,
+/* 0x065b: i2c_raise_scl_wait */
+	0x4e0005f4,
+	0x587e03e8,
+	0x287e0000,
+	0x01f40006,
+	0x0142b609,
+/* 0x066f: i2c_raise_scl_done */
+	0xfcef1bf4,
+/* 0x0673: i2c_start */
+	0x7e00f840,
+	0xf4000628,
+	0x3c7e0d11,
+	0x11f40006,
+	0x2e0ef406,
+/* 0x0684: i2c_start_rep */
+	0xf47e0003,
+	0x01030005,
+	0x00060e7e,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x06507e50,
+	0x0464b600,
+/* 0x06af: i2c_start_send */
+	0x031d11f4,
+	0x060e7e00,
+	0x13884e00,
+	0x0000587e,
+	0xf47e0003,
+	0x884e0005,
+	0x00587e13,
+/* 0x06c9: i2c_start_out */
+/* 0x06cb: i2c_stop */
+	0x0300f800,
+	0x05f47e00,
+	0x7e000300,
+	0x4e00060e,
+	0x587e03e8,
+	0x01030000,
+	0x0005f47e,
+	0x7e13884e,
+	0x03000058,
+	0x060e7e01,
+	0x13884e00,
+	0x0000587e,
+/* 0x06fa: i2c_bitw */
+	0x0e7e00f8,
+	0xe84e0006,
+	0x00587e03,
 	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0x557e50fc,
+	0x507e50fc,
 	0x64b60006,
-	0x1d11f404,
-/* 0x06b4: i2c_start_send */
-	0x137e0003,
-	0x884e0006,
-	0x00587e13,
-	0x7e000300,
-	0x4e0005f9,
-	0x587e1388,
-/* 0x06ce: i2c_start_out */
-	0x00f80000,
-/* 0x06d0: i2c_stop */
-	0xf97e0003,
-	0x00030005,
-	0x0006137e,
-	0x7e03e84e,
+	0x1711f404,
+	0x7e13884e,
 	0x03000058,
-	0x05f97e01,
+	0x05f47e00,
 	0x13884e00,
 	0x0000587e,
-	0x137e0103,
-	0x884e0006,
-	0x00587e13,
-/* 0x06ff: i2c_bitw */
-	0x7e00f800,
-	0x4e000613,
-	0x587e03e8,
-	0x76bb0000,
+/* 0x0738: i2c_bitw_out */
+/* 0x073a: i2c_bitr */
+	0x010300f8,
+	0x00060e7e,
+	0x7e03e84e,
+	0xbb000058,
+	0x65b60076,
+	0x9450f904,
+	0x56bb0465,
+	0xfd50bd02,
+	0x50fc0475,
+	0x0006507e,
+	0xf40464b6,
+	0x3c7e1a11,
+	0x00030006,
+	0x0005f47e,
+	0x7e13884e,
+	0xf0000058,
+	0x31f4013c,
+/* 0x077d: i2c_bitr_done */
+/* 0x077f: i2c_get_byte */
+	0x0500f801,
+/* 0x0783: i2c_get_byte_next */
+	0xb6080400,
+	0x76bb0154,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb6000655,
+	0xb600073a,
 	0x11f40464,
-	0x13884e17,
-	0x0000587e,
-	0xf97e0003,
-	0x884e0005,
-	0x00587e13,
-/* 0x073d: i2c_bitw_out */
-/* 0x073f: i2c_bitr */
-	0x0300f800,
-	0x06137e01,
-	0x03e84e00,
-	0x0000587e,
+	0x0553fd2a,
+	0xf40142b6,
+	0x0103d81b,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x06557e50,
+	0x06fa7e50,
 	0x0464b600,
-	0x7e1a11f4,
-	0x03000641,
-	0x05f97e00,
-	0x13884e00,
-	0x0000587e,
-	0xf4013cf0,
-/* 0x0782: i2c_bitr_done */
-	0x00f80131,
-/* 0x0784: i2c_get_byte */
-	0x08040005,
-/* 0x0788: i2c_get_byte_next */
-	0xbb0154b6,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x00073f7e,
-	0xf40464b6,
-	0x53fd2a11,
-	0x0142b605,
-	0x03d81bf4,
-	0x0076bb01,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0xff7e50fc,
-	0x64b60006,
-/* 0x07d1: i2c_get_byte_done */
-/* 0x07d3: i2c_put_byte */
-	0x0400f804,
-/* 0x07d5: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
+/* 0x07cc: i2c_get_byte_done */
+/* 0x07ce: i2c_put_byte */
+	0x080400f8,
+/* 0x07d0: i2c_put_byte_next */
+	0xff0142b6,
+	0x76bb3854,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0x7e50fc04,
+	0xb60006fa,
+	0x11f40464,
+	0x0046b034,
+	0xbbd81bf4,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0006ff7e,
+	0x00073a7e,
 	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
+	0x76bb0f11,
+	0x0136b000,
+	0xf4061bf4,
+/* 0x0826: i2c_put_byte_done */
+	0x00f80132,
+/* 0x0828: i2c_addr */
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0x073f7e50,
+	0x06737e50,
 	0x0464b600,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x082b: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x082d: i2c_addr */
-	0x0076bb00,
+	0xe72911f4,
+	0xb6012ec3,
+	0x53fd0134,
+	0x0076bb05,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0x787e50fc,
-	0x64b60006,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
-	0x0465b600,
-	0x659450f9,
-	0x0256bb04,
-	0x75fd50bd,
-	0x7e50fc04,
-	0xb60007d3,
-/* 0x0872: i2c_addr_done */
-	0x00f80464,
-/* 0x0874: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b705e4,
-	0x00f8d014,
-/* 0x0880: i2c_acquire */
-	0x0008747e,
+	0xce7e50fc,
+	0x64b60007,
+/* 0x086d: i2c_addr_done */
+/* 0x086f: i2c_acquire_addr */
+	0xc700f804,
+	0xe4b6f8ce,
+	0x14e0b705,
+/* 0x087b: i2c_acquire */
+	0x7e00f8d0,
+	0x7e00086f,
+	0xf0000004,
+	0x2d7e03d9,
+	0x00f80000,
+/* 0x088c: i2c_release */
+	0x00086f7e,
 	0x0000047e,
-	0x7e03d9f0,
+	0x7e03daf0,
 	0xf800002d,
-/* 0x0891: i2c_release */
-	0x08747e00,
-	0x00047e00,
-	0x03daf000,
-	0x00002d7e,
-/* 0x08a2: i2c_recv */
-	0x32f400f8,
-	0xf8c1c701,
-	0xb00214b6,
-	0x1ff52816,
-	0x13b80134,
-	0x98000cf4,
-	0x13b80032,
-	0x98000ccc,
-	0x31f40031,
-	0xf9d0f902,
-	0xd6d0f9e0,
-	0x10000000,
-	0xbb016792,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x0008807e,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b01bf5,
-	0x76bb0005,
+/* 0x089d: i2c_recv */
+	0x0132f400,
+	0xb6f8c1c7,
+	0x16b00214,
+	0x341ff528,
+	0xf413b801,
+	0x3298000c,
+	0xcc13b800,
+	0x3198000c,
+	0x0231f400,
+	0xe0f9d0f9,
+	0x00d6d0f9,
+	0x92100000,
+	0x76bb0167,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0x7e50fc04,
-	0xb600082d,
-	0x11f50464,
-	0xc5c700cc,
-	0x0076bbe0,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0xd37e50fc,
-	0x64b60007,
-	0xa911f504,
-	0xbb010500,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x00082d7e,
-	0xf50464b6,
-	0xbb008711,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x0007847e,
-	0xf40464b6,
-	0x5bcb6711,
-	0x0076bbe0,
+	0xb600087b,
+	0xd0fc0464,
+	0xf500d6b0,
+	0x0500b01b,
+	0x0076bb00,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
-	0xd07e50fc,
-	0x64b60006,
-	0xbd5bb204,
-	0x410ef474,
-/* 0x09a4: i2c_recv_not_rd08 */
-	0xf401d6b0,
-	0x00053b1b,
-	0x00082d7e,
-	0xc73211f4,
-	0xd37ee0c5,
-	0x11f40007,
-	0x7e000528,
-	0xf400082d,
-	0xb5c71f11,
-	0x07d37ee0,
-	0x1511f400,
-	0x0006d07e,
-	0xc5c774bd,
-	0x091bf408,
-	0xf40232f4,
-/* 0x09e2: i2c_recv_not_wr08 */
-/* 0x09e2: i2c_recv_done */
-	0xcec7030e,
-	0x08917ef8,
-	0xfce0fc00,
-	0x0912f4d0,
-	0x9f7e7cb2,
-/* 0x09f6: i2c_recv_exit */
-	0x00f80002,
-/* 0x09f8: i2c_init */
-/* 0x09fa: test_recv */
-	0x584100f8,
-	0x0011cf04,
-	0x400110b6,
-	0x01f60458,
-	0xde04bd00,
-	0x134fd900,
-	0x0001de7e,
-/* 0x0a16: test_init */
-	0x004e00f8,
-	0x01de7e08,
-/* 0x0a1f: idle_recv */
+	0x287e50fc,
+	0x64b60008,
+	0xcc11f504,
+	0xe0c5c700,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x07ce7e50,
+	0x0464b600,
+	0x00a911f5,
+	0x76bb0105,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0x7e50fc04,
+	0xb6000828,
+	0x11f50464,
+	0x76bb0087,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0x7e50fc04,
+	0xb600077f,
+	0x11f40464,
+	0xe05bcb67,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x06cb7e50,
+	0x0464b600,
+	0x74bd5bb2,
+/* 0x099f: i2c_recv_not_rd08 */
+	0xb0410ef4,
+	0x1bf401d6,
+	0x7e00053b,
+	0xf4000828,
+	0xc5c73211,
+	0x07ce7ee0,
+	0x2811f400,
+	0x287e0005,
+	0x11f40008,
+	0xe0b5c71f,
+	0x0007ce7e,
+	0x7e1511f4,
+	0xbd0006cb,
+	0x08c5c774,
+	0xf4091bf4,
+	0x0ef40232,
+/* 0x09dd: i2c_recv_not_wr08 */
+/* 0x09dd: i2c_recv_done */
+	0xf8cec703,
+	0x00088c7e,
+	0xd0fce0fc,
+	0xb20912f4,
+	0x029f7e7c,
+/* 0x09f1: i2c_recv_exit */
+/* 0x09f3: i2c_init */
 	0xf800f800,
-/* 0x0a21: idle */
-	0x0031f400,
-	0xcf045441,
-	0x10b60011,
-	0x04544001,
-	0xbd0001f6,
-/* 0x0a35: idle_loop */
-	0xf4580104,
-/* 0x0a3a: idle_proc */
-/* 0x0a3a: idle_proc_exec */
-	0x10f90232,
-	0xa87e1eb2,
-	0x10fc0002,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x0a4d: idle_proc_next */
-	0x5810b6f0,
-	0x1bf41fa6,
-	0xe002f4e8,
-	0xf40028f4,
-	0x0000c60e,
+/* 0x09f5: test_recv */
+	0x04584100,
+	0xb60011cf,
+	0x58400110,
+	0x0001f604,
+	0x00de04bd,
+	0x7e134fd9,
+	0xf80001de,
+/* 0x0a11: test_init */
+	0x08004e00,
+	0x0001de7e,
+/* 0x0a1a: idle_recv */
+	0x00f800f8,
+/* 0x0a1c: idle */
+	0x410031f4,
+	0x11cf0454,
+	0x0110b600,
+	0xf6045440,
+	0x04bd0001,
+/* 0x0a30: idle_loop */
+	0x32f45801,
+/* 0x0a35: idle_proc */
+/* 0x0a35: idle_proc_exec */
+	0xb210f902,
+	0x02a87e1e,
+	0xf410fc00,
+	0x31f40911,
+	0xf00ef402,
+/* 0x0a48: idle_proc_next */
+	0xa65810b6,
+	0xe81bf41f,
+	0xf4e002f4,
+	0x0ef40028,
+	0x000000c6,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
b/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
index 5d692425..419cd546 100644
--- a/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
+++ b/drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h
@@ -46,8 +46,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x584d454d,
-	0x0000083a,
-	0x0000082c,
+	0x00000833,
+	0x00000825,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -68,8 +68,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x46524550,
-	0x0000083e,
-	0x0000083c,
+	0x00000837,
+	0x00000835,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -90,8 +90,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x5f433249,
-	0x00000c6e,
-	0x00000b11,
+	0x00000c67,
+	0x00000b0a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -112,8 +112,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x54534554,
-	0x00000c97,
-	0x00000c70,
+	0x00000c90,
+	0x00000c69,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -134,8 +134,8 @@ static uint32_t gt215_pmu_data[] = {
 	0x00000000,
 	0x00000000,
 	0x454c4449,
-	0x00000ca3,
-	0x00000ca1,
+	0x00000c9c,
+	0x00000c9a,
 	0x00000000,
 	0x00000000,
 	0x00000000,
@@ -233,22 +233,22 @@ static uint32_t gt215_pmu_data[] = {
 /* 0x037c: memx_func_next */
 	0x00000002,
 	0x00000000,
-	0x000005a0,
+	0x0000059f,
 	0x00000003,
 	0x00000002,
-	0x00000632,
+	0x0000062f,
 	0x00040004,
 	0x00000000,
-	0x0000064e,
+	0x0000064b,
 	0x00010005,
 	0x00000000,
-	0x0000066b,
+	0x00000668,
 	0x00010006,
 	0x00000000,
-	0x000005f0,
+	0x000005ef,
 	0x00000007,
 	0x00000000,
-	0x00000676,
+	0x00000673,
 /* 0x03c4: memx_func_tail */
 /* 0x03c4: memx_ts_start */
 	0x00000000,
@@ -1304,560 +1304,560 @@ static uint32_t gt215_pmu_code[] = {
 	0x67f102d7,
 	0x63f1fffc,
 	0x76fdffff,
-	0x0267f104,
-	0x0576fd00,
-	0x70f980f9,
-	0xe0fcd0fc,
-	0xf04021f4,
+	0x0267f004,
+	0xf90576fd,
+	0xfc70f980,
+	0xf4e0fcd0,
+	0x67f04021,
+	0xe007f104,
+	0x0604b607,
+	0xbd0006d0,
+/* 0x0581: memx_func_enter_wait */
+	0xc067f104,
+	0x0664b607,
+	0xf00066cf,
+	0x0bf40464,
+	0x2c67f0f3,
+	0xcf0664b6,
+	0x06800066,
+/* 0x059f: memx_func_leave */
+	0xf000f8f1,
+	0x64b62c67,
+	0x0066cf06,
+	0xf0f20680,
 	0x07f10467,
-	0x04b607e0,
+	0x04b607e4,
 	0x0006d006,
-/* 0x0582: memx_func_enter_wait */
+/* 0x05ba: memx_func_leave_wait */
 	0x67f104bd,
 	0x64b607c0,
 	0x0066cf06,
 	0xf40464f0,
-	0x67f0f30b,
-	0x0664b62c,
-	0x800066cf,
-	0x00f8f106,
-/* 0x05a0: memx_func_leave */
-	0xb62c67f0,
-	0x66cf0664,
-	0xf2068000,
-	0xf10467f0,
-	0xb607e407,
-	0x06d00604,
-/* 0x05bb: memx_func_leave_wait */
-	0xf104bd00,
-	0xb607c067,
-	0x66cf0664,
-	0x0464f000,
-	0xf1f31bf4,
-	0xb9161087,
-	0x21f4028e,
-	0x02d7b904,
-	0xffcc67f1,
-	0xffff63f1,
-	0xf90476fd,
-	0xfc70f980,
-	0xf4e0fcd0,
-	0x00f84021,
-/* 0x05f0: memx_func_wait_vblank */
-	0xb0001698,
-	0x0bf40066,
-	0x0166b013,
-	0xf4060bf4,
-/* 0x0602: memx_func_wait_vblank_head1 */
-	0x77f12e0e,
-	0x0ef40020,
-/* 0x0609: memx_func_wait_vblank_head0 */
-	0x0877f107,
-/* 0x060d: memx_func_wait_vblank_0 */
-	0xc467f100,
-	0x0664b607,
-	0xfd0066cf,
-	0x1bf40467,
-/* 0x061d: memx_func_wait_vblank_1 */
-	0xc467f1f3,
-	0x0664b607,
-	0xfd0066cf,
-	0x0bf40467,
-/* 0x062d: memx_func_wait_vblank_fini */
-	0x0410b6f3,
-/* 0x0632: memx_func_wr32 */
-	0x169800f8,
-	0x01159800,
-	0xf90810b6,
-	0xfc50f960,
-	0xf4e0fcd0,
-	0x42b64021,
-	0xe91bf402,
-/* 0x064e: memx_func_wait */
-	0x87f000f8,
-	0x0684b62c,
-	0x980088cf,
-	0x1d98001e,
-	0x021c9801,
-	0xb6031b98,
-	0x21f41010,
-/* 0x066b: memx_func_delay */
-	0x9800f8a3,
-	0x10b6001e,
-	0x7e21f404,
-/* 0x0676: memx_func_train */
-	0x57f100f8,
-	0x77f10003,
-	0x97f10000,
-	0x93f00000,
-	0x029eb970,
-	0xb90421f4,
-	0xe7f102d8,
-	0x21f42710,
-/* 0x0695: memx_func_train_loop_outer */
-	0x0158e07e,
-	0x0083f101,
-	0xe097f102,
-	0x1193f011,
-	0x80f990f9,
+	0x87f1f31b,
+	0x8eb91610,
+	0x0421f402,
+	0xf102d7b9,
+	0xf1ffcc67,
+	0xfdffff63,
+	0x80f90476,
+	0xd0fc70f9,
+	0x21f4e0fc,
+/* 0x05ef: memx_func_wait_vblank */
+	0x9800f840,
+	0x66b00016,
+	0x120bf400,
+	0xf40166b0,
+	0x0ef4060b,
+/* 0x0601: memx_func_wait_vblank_head1 */
+	0x2077f02c,
+/* 0x0607: memx_func_wait_vblank_head0 */
+	0xf0060ef4,
+/* 0x060a: memx_func_wait_vblank_0 */
+	0x67f10877,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x061a: memx_func_wait_vblank_1 */
+	0x67f1f31b,
+	0x64b607c4,
+	0x0066cf06,
+	0xf40467fd,
+/* 0x062a: memx_func_wait_vblank_fini */
+	0x10b6f30b,
+/* 0x062f: memx_func_wr32 */
+	0x9800f804,
+	0x15980016,
+	0x0810b601,
+	0x50f960f9,
 	0xe0fcd0fc,
-	0xf94021f4,
-	0x0067f150,
-/* 0x06b5: memx_func_train_loop_inner */
-	0x1187f100,
-	0x9068ff11,
-	0xfd109894,
-	0x97f10589,
-	0x93f00720,
-	0xf990f910,
-	0xfcd0fc80,
-	0x4021f4e0,
-	0x008097f1,
-	0xb91093f0,
-	0x21f4029e,
-	0x02d8b904,
-	0xf92088c5,
+	0xb64021f4,
+	0x1bf40242,
+/* 0x064b: memx_func_wait */
+	0xf000f8e9,
+	0x84b62c87,
+	0x0088cf06,
+	0x98001e98,
+	0x1c98011d,
+	0x031b9802,
+	0xf41010b6,
+	0x00f8a321,
+/* 0x0668: memx_func_delay */
+	0xb6001e98,
+	0x21f40410,
+/* 0x0673: memx_func_train */
+	0xf000f87e,
+	0x77f00357,
+	0x0097f100,
+	0x7093f000,
+	0xf4029eb9,
+	0xd8b90421,
+	0x10e7f102,
+	0x7e21f427,
+/* 0x0690: memx_func_train_loop_outer */
+	0x010158e0,
+	0x020083f1,
+	0x11e097f1,
+	0xf91193f0,
+	0xfc80f990,
+	0xf4e0fcd0,
+	0x50f94021,
+/* 0x06af: memx_func_train_loop_inner */
+	0xf10067f0,
+	0xff111187,
+	0x98949068,
+	0x0589fd10,
+	0x072097f1,
+	0xf91093f0,
 	0xfc80f990,
 	0xf4e0fcd0,
 	0x97f14021,
-	0x93f0053c,
-	0x0287f110,
-	0x0083f130,
-	0xf990f980,
+	0x93f00080,
+	0x029eb910,
+	0xb90421f4,
+	0x88c502d8,
+	0xf990f920,
 	0xfcd0fc80,
 	0x4021f4e0,
-	0x0560e7f1,
-	0xf110e3f0,
-	0xf10000d7,
-	0x908000d3,
-	0xb7f100dc,
-	0xb3f08480,
-	0xa321f41e,
-	0x000057f1,
-	0xffff97f1,
-	0x830093f1,
-/* 0x0734: memx_func_train_loop_4x */
-	0x0080a7f1,
-	0xb910a3f0,
-	0x21f402ae,
-	0x02d8b904,
-	0xffdfb7f1,
-	0xffffb3f1,
-	0xf9048bfd,
-	0xfc80f9a0,
+	0x053c97f1,
+	0xf11093f0,
+	0xf1300287,
+	0xf9800083,
+	0xfc80f990,
 	0xf4e0fcd0,
-	0xa7f14021,
-	0xa3f0053c,
-	0x0287f110,
-	0x0083f130,
-	0xf9a0f980,
-	0xfcd0fc80,
-	0x4021f4e0,
-	0x0560e7f1,
-	0xf110e3f0,
-	0xf10000d7,
-	0xb98000d3,
-	0xb7f102dc,
-	0xb3f02710,
-	0xa321f400,
-	0xf402eeb9,
-	0xddb90421,
-	0x949dff02,
+	0xe7f14021,
+	0xe3f00560,
+	0x00d7f110,
+	0x00d3f100,
+	0x00dc9080,
+	0x8480b7f1,
+	0xf41eb3f0,
+	0x57f0a321,
+	0xff97f100,
+	0x0093f1ff,
+/* 0x072d: memx_func_train_loop_4x */
+	0x80a7f183,
+	0x10a3f000,
+	0xf402aeb9,
+	0xd8b90421,
+	0xdfb7f102,
+	0xffb3f1ff,
+	0x048bfdff,
+	0x80f9a0f9,
+	0xe0fcd0fc,
+	0xf14021f4,
+	0xf0053ca7,
+	0x87f110a3,
+	0x83f13002,
+	0xa0f98000,
+	0xd0fc80f9,
+	0x21f4e0fc,
+	0x60e7f140,
+	0x10e3f005,
+	0x0000d7f1,
+	0x8000d3f1,
+	0xf102dcb9,
+	0xf02710b7,
+	0x21f400b3,
+	0x02eeb9a3,
+	0xb90421f4,
+	0x9dff02dd,
+	0x0150b694,
+	0xf4045670,
+	0x7aa0921e,
+	0xa9800bcc,
+	0x0160b600,
+	0x700470b6,
+	0x1ef51066,
+	0x50fcff01,
 	0x700150b6,
-	0x1ef40456,
-	0xcc7aa092,
-	0x00a9800b,
-	0xb60160b6,
-	0x66700470,
-	0x001ef510,
-	0xb650fcff,
-	0x56700150,
-	0xd41ef507,
-/* 0x07c7: memx_exec */
-	0xf900f8fe,
-	0xb9d0f9e0,
-	0xb2b902c1,
-/* 0x07d1: memx_exec_next */
-	0x00139802,
-	0xe70410b6,
-	0xe701f034,
-	0xb601e033,
-	0x30f00132,
-	0xde35980c,
-	0x12b855f9,
-	0xe41ef406,
-	0x98f10b98,
-	0xcbbbf20c,
-	0xc4b7f102,
-	0x06b4b607,
-	0xfc00bbcf,
-	0xf5e0fcd0,
+	0x1ef50756,
+	0x00f8fed6,
+/* 0x07c0: memx_exec */
+	0xd0f9e0f9,
+	0xb902c1b9,
+/* 0x07ca: memx_exec_next */
+	0x139802b2,
+	0x0410b600,
+	0x01f034e7,
+	0x01e033e7,
+	0xf00132b6,
+	0x35980c30,
+	0xb855f9de,
+	0x1ef40612,
+	0xf10b98e4,
+	0xbbf20c98,
+	0xb7f102cb,
+	0xb4b607c4,
+	0x00bbcf06,
+	0xe0fcd0fc,
+	0x033621f5,
+/* 0x0806: memx_info */
+	0xc67000f8,
+	0x0e0bf401,
+/* 0x080c: memx_info_data */
+	0x03ccc7f1,
+	0x0800b7f1,
+/* 0x0817: memx_info_train */
+	0xf10b0ef4,
+	0xf10bccc7,
+/* 0x081f: memx_info_send */
+	0xf50100b7,
 	0xf8033621,
-/* 0x080d: memx_info */
-	0x01c67000,
-/* 0x0813: memx_info_data */
-	0xf10e0bf4,
-	0xf103ccc7,
-	0xf40800b7,
-/* 0x081e: memx_info_train */
-	0xc7f10b0e,
-	0xb7f10bcc,
-/* 0x0826: memx_info_send */
-	0x21f50100,
-	0x00f80336,
-/* 0x082c: memx_recv */
-	0xf401d6b0,
-	0xd6b0980b,
-	0xd80bf400,
-/* 0x083a: memx_init */
-	0x00f800f8,
-/* 0x083c: perf_recv */
-/* 0x083e: perf_init */
-	0x00f800f8,
-/* 0x0840: i2c_drive_scl */
-	0xf40036b0,
-	0x07f1110b,
-	0x04b607e0,
-	0x0001d006,
-	0x00f804bd,
-/* 0x0854: i2c_drive_scl_lo */
-	0x07e407f1,
-	0xd00604b6,
-	0x04bd0001,
-/* 0x0862: i2c_drive_sda */
-	0x36b000f8,
-	0x110bf400,
-	0x07e007f1,
-	0xd00604b6,
-	0x04bd0002,
-/* 0x0876: i2c_drive_sda_lo */
-	0x07f100f8,
-	0x04b607e4,
-	0x0002d006,
-	0x00f804bd,
-/* 0x0884: i2c_sense_scl */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0431fd00,
-	0xf4060bf4,
-/* 0x089a: i2c_sense_scl_done */
-	0x00f80131,
-/* 0x089c: i2c_sense_sda */
-	0xf10132f4,
-	0xb607c437,
-	0x33cf0634,
-	0x0432fd00,
-	0xf4060bf4,
-/* 0x08b2: i2c_sense_sda_done */
-	0x00f80131,
-/* 0x08b4: i2c_raise_scl */
-	0x47f140f9,
-	0x37f00898,
-	0x4021f501,
-/* 0x08c1: i2c_raise_scl_wait */
+/* 0x0825: memx_recv */
+	0x01d6b000,
+	0xb0980bf4,
+	0x0bf400d6,
+/* 0x0833: memx_init */
+	0xf800f8d8,
+/* 0x0835: perf_recv */
+/* 0x0837: perf_init */
+	0xf800f800,
+/* 0x0839: i2c_drive_scl */
+	0x0036b000,
+	0xf1110bf4,
+	0xb607e007,
+	0x01d00604,
+	0xf804bd00,
+/* 0x084d: i2c_drive_scl_lo */
+	0xe407f100,
+	0x0604b607,
+	0xbd0001d0,
+/* 0x085b: i2c_drive_sda */
+	0xb000f804,
+	0x0bf40036,
+	0xe007f111,
+	0x0604b607,
+	0xbd0002d0,
+/* 0x086f: i2c_drive_sda_lo */
+	0xf100f804,
+	0xb607e407,
+	0x02d00604,
+	0xf804bd00,
+/* 0x087d: i2c_sense_scl */
+	0x0132f400,
+	0x07c437f1,
+	0xcf0634b6,
+	0x31fd0033,
+	0x060bf404,
+/* 0x0893: i2c_sense_scl_done */
+	0xf80131f4,
+/* 0x0895: i2c_sense_sda */
+	0x0132f400,
+	0x07c437f1,
+	0xcf0634b6,
+	0x32fd0033,
+	0x060bf404,
+/* 0x08ab: i2c_sense_sda_done */
+	0xf80131f4,
+/* 0x08ad: i2c_raise_scl */
+	0xf140f900,
+	0xf0089847,
+	0x21f50137,
+/* 0x08ba: i2c_raise_scl_wait */
+	0xe7f10839,
+	0x21f403e8,
+	0x7d21f57e,
+	0x0901f408,
+	0xf40142b6,
+/* 0x08ce: i2c_raise_scl_done */
+	0x40fcef1b,
+/* 0x08d2: i2c_start */
+	0x21f500f8,
+	0x11f4087d,
+	0x9521f50d,
+	0x0611f408,
+/* 0x08e3: i2c_start_rep */
+	0xf0300ef4,
+	0x21f50037,
+	0x37f00839,
+	0x5b21f501,
+	0x0076bb08,
+	0xf90465b6,
+	0x04659450,
+	0xbd0256bb,
+	0x0475fd50,
+	0x21f550fc,
+	0x64b608ad,
+	0x1f11f404,
+/* 0x0910: i2c_start_send */
+	0xf50037f0,
+	0xf1085b21,
+	0xf41388e7,
+	0x37f07e21,
+	0x3921f500,
+	0x88e7f108,
+	0x7e21f413,
+/* 0x092c: i2c_start_out */
+/* 0x092e: i2c_stop */
+	0x37f000f8,
+	0x3921f500,
+	0x0037f008,
+	0x085b21f5,
+	0x03e8e7f1,
+	0xf07e21f4,
+	0x21f50137,
+	0xe7f10839,
+	0x21f41388,
+	0x0137f07e,
+	0x085b21f5,
+	0x1388e7f1,
+	0xf87e21f4,
+/* 0x0961: i2c_bitw */
+	0x5b21f500,
 	0xe8e7f108,
 	0x7e21f403,
-	0x088421f5,
-	0xb60901f4,
-	0x1bf40142,
-/* 0x08d5: i2c_raise_scl_done */
-	0xf840fcef,
-/* 0x08d9: i2c_start */
-	0x8421f500,
-	0x0d11f408,
-	0x089c21f5,
-	0xf40611f4,
-/* 0x08ea: i2c_start_rep */
-	0x37f0300e,
-	0x4021f500,
-	0x0137f008,
-	0x086221f5,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xb421f550,
+	0xad21f550,
 	0x0464b608,
-/* 0x0917: i2c_start_send */
-	0xf01f11f4,
-	0x21f50037,
-	0xe7f10862,
-	0x21f41388,
-	0x0037f07e,
-	0x084021f5,
-	0x1388e7f1,
-/* 0x0933: i2c_start_out */
-	0xf87e21f4,
-/* 0x0935: i2c_stop */
-	0x0037f000,
-	0x084021f5,
-	0xf50037f0,
-	0xf1086221,
-	0xf403e8e7,
+	0xf11811f4,
+	0xf41388e7,
 	0x37f07e21,
-	0x4021f501,
+	0x3921f500,
 	0x88e7f108,
 	0x7e21f413,
-	0xf50137f0,
-	0xf1086221,
-	0xf41388e7,
-	0x00f87e21,
-/* 0x0968: i2c_bitw */
-	0x086221f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x08b421f5,
-	0xf40464b6,
-	0xe7f11811,
+/* 0x09a0: i2c_bitw_out */
+/* 0x09a2: i2c_bitr */
+	0x37f000f8,
+	0x5b21f501,
+	0xe8e7f108,
+	0x7e21f403,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xad21f550,
+	0x0464b608,
+	0xf51b11f4,
+	0xf0089521,
+	0x21f50037,
+	0xe7f10839,
 	0x21f41388,
-	0x0037f07e,
-	0x084021f5,
-	0x1388e7f1,
-/* 0x09a7: i2c_bitw_out */
-	0xf87e21f4,
-/* 0x09a9: i2c_bitr */
-	0x0137f000,
-	0x086221f5,
-	0x03e8e7f1,
-	0xbb7e21f4,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x08b421f5,
-	0xf40464b6,
-	0x21f51b11,
-	0x37f0089c,
-	0x4021f500,
-	0x88e7f108,
-	0x7e21f413,
-	0xf4013cf0,
-/* 0x09ee: i2c_bitr_done */
-	0x00f80131,
-/* 0x09f0: i2c_get_byte */
-	0xf00057f0,
-/* 0x09f6: i2c_get_byte_next */
-	0x54b60847,
+	0x013cf07e,
+/* 0x09e7: i2c_bitr_done */
+	0xf80131f4,
+/* 0x09e9: i2c_get_byte */
+	0x0057f000,
+/* 0x09ef: i2c_get_byte_next */
+	0xb60847f0,
+	0x76bb0154,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb609a221,
+	0x11f40464,
+	0x0553fd2b,
+	0xf40142b6,
+	0x37f0d81b,
 	0x0076bb01,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b609a9,
-	0x2b11f404,
-	0xb60553fd,
-	0x1bf40142,
-	0x0137f0d8,
-	0xb60076bb,
-	0x50f90465,
-	0xbb046594,
-	0x50bd0256,
-	0xfc0475fd,
-	0x6821f550,
-	0x0464b609,
-/* 0x0a40: i2c_get_byte_done */
-/* 0x0a42: i2c_put_byte */
-	0x47f000f8,
-/* 0x0a45: i2c_put_byte_next */
-	0x0142b608,
-	0xbb3854ff,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x096821f5,
-	0xf40464b6,
-	0x46b03411,
-	0xd81bf400,
+	0x64b60961,
+/* 0x0a39: i2c_get_byte_done */
+/* 0x0a3b: i2c_put_byte */
+	0xf000f804,
+/* 0x0a3e: i2c_put_byte_next */
+	0x42b60847,
+	0x3854ff01,
 	0xb60076bb,
 	0x50f90465,
 	0xbb046594,
 	0x50bd0256,
 	0xfc0475fd,
-	0xa921f550,
+	0x6121f550,
 	0x0464b609,
-	0xbb0f11f4,
-	0x36b00076,
-	0x061bf401,
-/* 0x0a9b: i2c_put_byte_done */
-	0xf80132f4,
-/* 0x0a9d: i2c_addr */
-	0x0076bb00,
+	0xb03411f4,
+	0x1bf40046,
+	0x0076bbd8,
 	0xf90465b6,
 	0x04659450,
 	0xbd0256bb,
 	0x0475fd50,
 	0x21f550fc,
-	0x64b608d9,
-	0x2911f404,
-	0x012ec3e7,
-	0xfd0134b6,
-	0x76bb0553,
+	0x64b609a2,
+	0x0f11f404,
+	0xb00076bb,
+	0x1bf40136,
+	0x0132f406,
+/* 0x0a94: i2c_put_byte_done */
+/* 0x0a96: i2c_addr */
+	0x76bb00f8,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb60a4221,
-/* 0x0ae2: i2c_addr_done */
-	0x00f80464,
-/* 0x0ae4: i2c_acquire_addr */
-	0xb6f8cec7,
-	0xe0b702e4,
-	0xee980d1c,
-/* 0x0af3: i2c_acquire */
-	0xf500f800,
-	0xf40ae421,
-	0xd9f00421,
-	0x4021f403,
-/* 0x0b02: i2c_release */
-	0x21f500f8,
-	0x21f40ae4,
-	0x03daf004,
-	0xf84021f4,
-/* 0x0b11: i2c_recv */
-	0x0132f400,
-	0xb6f8c1c7,
-	0x16b00214,
-	0x3a1ff528,
-	0xf413a001,
-	0x0032980c,
-	0x0ccc13a0,
-	0xf4003198,
-	0xd0f90231,
-	0xd0f9e0f9,
-	0x000067f1,
-	0x100063f1,
-	0xbb016792,
+	0xb608d221,
+	0x11f40464,
+	0x2ec3e729,
+	0x0134b601,
+	0xbb0553fd,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0af321f5,
-	0xfc0464b6,
-	0x00d6b0d0,
-	0x00b31bf5,
-	0xbb0057f0,
+	0x0a3b21f5,
+/* 0x0adb: i2c_addr_done */
+	0xf80464b6,
+/* 0x0add: i2c_acquire_addr */
+	0xf8cec700,
+	0xb702e4b6,
+	0x980d1ce0,
+	0x00f800ee,
+/* 0x0aec: i2c_acquire */
+	0x0add21f5,
+	0xf00421f4,
+	0x21f403d9,
+/* 0x0afb: i2c_release */
+	0xf500f840,
+	0xf40add21,
+	0xdaf00421,
+	0x4021f403,
+/* 0x0b0a: i2c_recv */
+	0x32f400f8,
+	0xf8c1c701,
+	0xb00214b6,
+	0x1ff52816,
+	0x13a0013a,
+	0x32980cf4,
+	0xcc13a000,
+	0x0031980c,
+	0xf90231f4,
+	0xf9e0f9d0,
+	0x0067f1d0,
+	0x0063f100,
+	0x01679210,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0xec21f550,
+	0x0464b60a,
+	0xd6b0d0fc,
+	0xb31bf500,
+	0x0057f000,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x9621f550,
+	0x0464b60a,
+	0x00d011f5,
+	0xbbe0c5c7,
 	0x65b60076,
 	0x9450f904,
 	0x56bb0465,
 	0xfd50bd02,
 	0x50fc0475,
-	0x0a9d21f5,
+	0x0a3b21f5,
 	0xf50464b6,
-	0xc700d011,
-	0x76bbe0c5,
+	0xf000ad11,
+	0x76bb0157,
 	0x0465b600,
 	0x659450f9,
 	0x0256bb04,
 	0x75fd50bd,
 	0xf550fc04,
-	0xb60a4221,
+	0xb60a9621,
 	0x11f50464,
-	0x57f000ad,
-	0x0076bb01,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0x21f550fc,
-	0x64b60a9d,
-	0x8a11f504,
-	0x0076bb00,
-	0xf90465b6,
-	0x04659450,
-	0xbd0256bb,
-	0x0475fd50,
-	0x21f550fc,
-	0x64b609f0,
-	0x6a11f404,
-	0xbbe05bcb,
-	0x65b60076,
-	0x9450f904,
-	0x56bb0465,
-	0xfd50bd02,
-	0x50fc0475,
-	0x093521f5,
-	0xb90464b6,
-	0x74bd025b,
-/* 0x0c17: i2c_recv_not_rd08 */
-	0xb0430ef4,
-	0x1bf401d6,
-	0x0057f03d,
-	0x0a9d21f5,
-	0xc73311f4,
-	0x21f5e0c5,
-	0x11f40a42,
-	0x0057f029,
-	0x0a9d21f5,
-	0xc71f11f4,
-	0x21f5e0b5,
-	0x11f40a42,
-	0x3521f515,
-	0xc774bd09,
-	0x1bf408c5,
-	0x0232f409,
-/* 0x0c57: i2c_recv_not_wr08 */
-/* 0x0c57: i2c_recv_done */
-	0xc7030ef4,
-	0x21f5f8ce,
-	0xe0fc0b02,
-	0x12f4d0fc,
-	0x027cb90a,
-	0x033621f5,
-/* 0x0c6c: i2c_recv_exit */
-/* 0x0c6e: i2c_init */
+	0x76bb008a,
+	0x0465b600,
+	0x659450f9,
+	0x0256bb04,
+	0x75fd50bd,
+	0xf550fc04,
+	0xb609e921,
+	0x11f40464,
+	0xe05bcb6a,
+	0xb60076bb,
+	0x50f90465,
+	0xbb046594,
+	0x50bd0256,
+	0xfc0475fd,
+	0x2e21f550,
+	0x0464b609,
+	0xbd025bb9,
+	0x430ef474,
+/* 0x0c10: i2c_recv_not_rd08 */
+	0xf401d6b0,
+	0x57f03d1b,
+	0x9621f500,
+	0x3311f40a,
+	0xf5e0c5c7,
+	0xf40a3b21,
+	0x57f02911,
+	0x9621f500,
+	0x1f11f40a,
+	0xf5e0b5c7,
+	0xf40a3b21,
+	0x21f51511,
+	0x74bd092e,
+	0xf408c5c7,
+	0x32f4091b,
+	0x030ef402,
+/* 0x0c50: i2c_recv_not_wr08 */
+/* 0x0c50: i2c_recv_done */
+	0xf5f8cec7,
+	0xfc0afb21,
+	0xf4d0fce0,
+	0x7cb90a12,
+	0x3621f502,
+/* 0x0c65: i2c_recv_exit */
+/* 0x0c67: i2c_init */
+	0xf800f803,
+/* 0x0c69: test_recv */
+	0xd817f100,
+	0x0614b605,
+	0xb60011cf,
+	0x07f10110,
+	0x04b605d8,
+	0x0001d006,
+	0xe7f104bd,
+	0xe3f1d900,
+	0x21f5134f,
+	0x00f80256,
+/* 0x0c90: test_init */
+	0x0800e7f1,
+	0x025621f5,
+/* 0x0c9a: idle_recv */
 	0x00f800f8,
-/* 0x0c70: test_recv */
-	0x05d817f1,
-	0xcf0614b6,
-	0x10b60011,
-	0xd807f101,
-	0x0604b605,
-	0xbd0001d0,
-	0x00e7f104,
-	0x4fe3f1d9,
-	0x5621f513,
-/* 0x0c97: test_init */
-	0xf100f802,
-	0xf50800e7,
-	0xf8025621,
-/* 0x0ca1: idle_recv */
-/* 0x0ca3: idle */
-	0xf400f800,
-	0x17f10031,
-	0x14b605d4,
-	0x0011cf06,
-	0xf10110b6,
-	0xb605d407,
-	0x01d00604,
-/* 0x0cbf: idle_loop */
-	0xf004bd00,
-	0x32f45817,
-/* 0x0cc5: idle_proc */
-/* 0x0cc5: idle_proc_exec */
-	0xb910f902,
-	0x21f5021e,
-	0x10fc033f,
-	0xf40911f4,
-	0x0ef40231,
-/* 0x0cd9: idle_proc_next */
-	0x5810b6ef,
-	0xf4061fb8,
-	0x02f4e61b,
-	0x0028f4dd,
-	0x00bb0ef4,
+/* 0x0c9c: idle */
+	0xf10031f4,
+	0xb605d417,
+	0x11cf0614,
+	0x0110b600,
+	0x05d407f1,
+	0xd00604b6,
+	0x04bd0001,
+/* 0x0cb8: idle_loop */
+	0xf45817f0,
+/* 0x0cbe: idle_proc */
+/* 0x0cbe: idle_proc_exec */
+	0x10f90232,
+	0xf5021eb9,
+	0xfc033f21,
+	0x0911f410,
+	0xf40231f4,
+/* 0x0cd2: idle_proc_next */
+	0x10b6ef0e,
+	0x061fb858,
+	0xf4e61bf4,
+	0x28f4dd02,
+	0xbb0ef400,
+	0x00000000,
+	0x00000000,
 	0x00000000,
 	0x00000000,
 	0x00000000,
diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
b/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
index ec03f9a4..1663bf94 100644
--- a/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
+++ b/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
@@ -82,15 +82,15 @@ memx_train_tail:
 // $r0  - zero
 memx_func_enter:
 #if NVKM_PPWR_CHIPSET == GT215
-	movw $r8 0x1610
+	mov $r8 0x1610
 	nv_rd32($r7, $r8)
 	imm32($r6, 0xfffffffc)
 	and $r7 $r6
-	movw $r6 0x2
+	mov $r6 0x2
 	or $r7 $r6
 	nv_wr32($r8, $r7)
 #else
-	movw $r6 0x001620
+	mov $r6 0x001620
 	imm32($r7, ~0x00000aa2);
 	nv_rd32($r8, $r6)
 	and $r8 $r7
@@ -101,7 +101,7 @@ memx_func_enter:
 	and $r8 $r7
 	nv_wr32($r6, $r8)
 
-	movw $r6 0x0026f0
+	mov $r6 0x0026f0
 	nv_rd32($r8, $r6)
 	and $r8 $r7
 	nv_wr32($r6, $r8)
@@ -136,19 +136,19 @@ memx_func_leave:
 		bra nz #memx_func_leave_wait
 
 #if NVKM_PPWR_CHIPSET == GT215
-	movw $r8 0x1610
+	mov $r8 0x1610
 	nv_rd32($r7, $r8)
 	imm32($r6, 0xffffffcc)
 	and $r7 $r6
 	nv_wr32($r8, $r7)
 #else
-	movw $r6 0x0026f0
+	mov $r6 0x0026f0
 	imm32($r7, 0x00000001)
 	nv_rd32($r8, $r6)
 	or $r8 $r7
 	nv_wr32($r6, $r8)
 
-	movw $r6 0x001620
+	mov $r6 0x001620
 	nv_rd32($r8, $r6)
 	or $r8 $r7
 	nv_wr32($r6, $r8)
@@ -177,11 +177,11 @@ memx_func_wait_vblank:
 	bra #memx_func_wait_vblank_fini
 
 	memx_func_wait_vblank_head1:
-	movw $r7 0x20
+	mov $r7 0x20
 	bra #memx_func_wait_vblank_0
 
 	memx_func_wait_vblank_head0:
-	movw $r7 0x8
+	mov $r7 0x8
 
 	memx_func_wait_vblank_0:
 		nv_iord($r6, NV_PPWR_INPUT)
@@ -273,13 +273,13 @@ memx_func_train:
 // $r5 - outer loop counter
 // $r6 - inner loop counter
 // $r7 - entry counter (#memx_train_head + $r7)
-	movw $r5 0x3
-	movw $r7 0x0
+	mov $r5 0x3
+	mov $r7 0x0
 
 // Read random memory to wake up... things
 	imm32($r9, 0x700000)
 	nv_rd32($r8,$r9)
-	movw $r14 0x2710
+	mov $r14 0x2710
 	call(nsec)
 
 	memx_func_train_loop_outer:
@@ -289,9 +289,9 @@ memx_func_train:
 		nv_wr32($r9, $r8)
 		push $r5
 
-		movw $r6 0x0
+		mov $r6 0x0
 		memx_func_train_loop_inner:
-			movw $r8 0x1111
+			mov $r8 0x1111
 			mulu $r9 $r6 $r8
 			shl b32 $r8 $r9 0x10
 			or $r8 $r9
@@ -315,7 +315,7 @@ memx_func_train:
 
 			// $r5 - inner inner loop counter
 			// $r9 - result
-			movw $r5 0
+			mov $r5 0
 			imm32($r9, 0x8300ffff)
 			memx_func_train_loop_4x:
 				imm32($r10, 0x100080)
-- 
2.14.2

Ilia Mirkin

2017-Nov-01 17:14 UTC

head link

[Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore

On Wed, Nov 1, 2017 at 12:51 PM, Karol Herbst <kherbst at redhat.com>
wrote:> fixes compilation issues with recent envytools, because movw was removed
> from fuc5, because it doesn't exist there anymore. The current code is
> most likely broken for fuc5 hardware as well and might have triggered all
> kinds of random memory reclocking fails.
>
> Changes in fuc3 binaries are tue do opcode optimizations using shorter
> opcodes when possible.
Might I suggest the following wording for the commit:

---------------8<----------------
Fixes failure to compile with recent envyas as a result of the 'movw'
alias being removed for v5.

A bit of history:

v3 only has a 16-bit sign-extended immediate mov op. In order to set
the high bits, there's a separate 'sethi' op. envyas validates that
the value passed to mov(imm) is between -0x8000 and 0x7fff. In order
to simplify macros that load both the low and high word, a 'movw'
alias was added which takes an unsigned 16-bit immediate. However the
actual hardware op still sign extends.

v5 has a full 32-bit immediate mov op. The v3 16-bit immediate mov op
is gone (loads 0 into the dst reg). However due to a bug in envyas,
the movw alias still existed, and selected the no-longer-present v3
16-bit immediate mov op. As a result usage of movw on v5 is the same
as mov with a 0x0 argument.

The proper fix throughout is to only ever use the 'movw' alias in
combination with 'sethi'. Anything else should get the sign-extended
validation to ensure that the intended value ends up in the
destination register.

Changes in fuc3 binaries is the result of a different encoding being
selected for a mov with an 8-bit value.
---------------8<----------------
>
> Signed-off-by: Karol Herbst <kherbst at redhat.com>
> ---
>  drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h |  746 +++++++++----------
>  drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h |  802 ++++++++++----------
>  drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h | 1006
+++++++++++++-------------
>  drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc     |   30 +-
>  4 files changed, 1292 insertions(+), 1292 deletions(-)
>
[...]
> diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
b/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> index ec03f9a4..1663bf94 100644
> --- a/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> +++ b/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> @@ -82,15 +82,15 @@ memx_train_tail:
>  // $r0  - zero
>  memx_func_enter:
>  #if NVKM_PPWR_CHIPSET == GT215
> -       movw $r8 0x1610
> +       mov $r8 0x1610
>         nv_rd32($r7, $r8)
>         imm32($r6, 0xfffffffc)
>         and $r7 $r6
> -       movw $r6 0x2
> +       mov $r6 0x2
>         or $r7 $r6
>         nv_wr32($r8, $r7)
>  #else
> -       movw $r6 0x001620
> +       mov $r6 0x001620
>         imm32($r7, ~0x00000aa2);
>         nv_rd32($r8, $r6)
>         and $r8 $r7
> @@ -101,7 +101,7 @@ memx_func_enter:
>         and $r8 $r7
>         nv_wr32($r6, $r8)
>
> -       movw $r6 0x0026f0
> +       mov $r6 0x0026f0
>         nv_rd32($r8, $r6)
>         and $r8 $r7
>         nv_wr32($r6, $r8)
> @@ -136,19 +136,19 @@ memx_func_leave:
>                 bra nz #memx_func_leave_wait
>
>  #if NVKM_PPWR_CHIPSET == GT215
> -       movw $r8 0x1610
> +       mov $r8 0x1610
>         nv_rd32($r7, $r8)
>         imm32($r6, 0xffffffcc)
>         and $r7 $r6
>         nv_wr32($r8, $r7)
>  #else
> -       movw $r6 0x0026f0
> +       mov $r6 0x0026f0
>         imm32($r7, 0x00000001)
>         nv_rd32($r8, $r6)
>         or $r8 $r7
>         nv_wr32($r6, $r8)
>
> -       movw $r6 0x001620
> +       mov $r6 0x001620
>         nv_rd32($r8, $r6)
>         or $r8 $r7
>         nv_wr32($r6, $r8)
> @@ -177,11 +177,11 @@ memx_func_wait_vblank:
>         bra #memx_func_wait_vblank_fini
>
>         memx_func_wait_vblank_head1:
> -       movw $r7 0x20
> +       mov $r7 0x20
>         bra #memx_func_wait_vblank_0
>
>         memx_func_wait_vblank_head0:
> -       movw $r7 0x8
> +       mov $r7 0x8
>
>         memx_func_wait_vblank_0:
>                 nv_iord($r6, NV_PPWR_INPUT)
> @@ -273,13 +273,13 @@ memx_func_train:
>  // $r5 - outer loop counter
>  // $r6 - inner loop counter
>  // $r7 - entry counter (#memx_train_head + $r7)
> -       movw $r5 0x3
> -       movw $r7 0x0
> +       mov $r5 0x3
> +       mov $r7 0x0
>
>  // Read random memory to wake up... things
>         imm32($r9, 0x700000)
>         nv_rd32($r8,$r9)
> -       movw $r14 0x2710
> +       mov $r14 0x2710
>         call(nsec)
>
>         memx_func_train_loop_outer:
> @@ -289,9 +289,9 @@ memx_func_train:
>                 nv_wr32($r9, $r8)
>                 push $r5
>
> -               movw $r6 0x0
> +               mov $r6 0x0
>                 memx_func_train_loop_inner:
> -                       movw $r8 0x1111
> +                       mov $r8 0x1111
>                         mulu $r9 $r6 $r8
>                         shl b32 $r8 $r9 0x10
>                         or $r8 $r9
> @@ -315,7 +315,7 @@ memx_func_train:
>
>                         // $r5 - inner inner loop counter
>                         // $r9 - result
> -                       movw $r5 0
> +                       mov $r5 0
>                         imm32($r9, 0x8300ffff)
>                         memx_func_train_loop_4x:
>                                 imm32($r10, 0x100080)
> --
> 2.14.2
>
> _______________________________________________
> Nouveau mailing list
> Nouveau at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/nouveau

Karol Herbst

2017-Nov-01 20:00 UTC

head link

[Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore

On Wed, Nov 1, 2017 at 6:14 PM, Ilia Mirkin <imirkin at alum.mit.edu>
wrote:
> On Wed, Nov 1, 2017 at 12:51 PM, Karol Herbst <kherbst at redhat.com>
wrote:
> > fixes compilation issues with recent envytools, because movw was
removed
> > from fuc5, because it doesn't exist there anymore. The current
code is
> > most likely broken for fuc5 hardware as well and might have triggered
all
> > kinds of random memory reclocking fails.
> >
> > Changes in fuc3 binaries are tue do opcode optimizations using shorter
> > opcodes when possible.
>
> Might I suggest the following wording for the commit:
>
> ---------------8<----------------
> Fixes failure to compile with recent envyas as a result of the
'movw'
> alias being removed for v5.
>
> A bit of history:
>
> v3 only has a 16-bit sign-extended immediate mov op. In order to set
> the high bits, there's a separate 'sethi' op. envyas validates
that
> the value passed to mov(imm) is between -0x8000 and 0x7fff. In order
> to simplify macros that load both the low and high word, a 'movw'
> alias was added which takes an unsigned 16-bit immediate. However the
> actual hardware op still sign extends.
>
> v5 has a full 32-bit immediate mov op. The v3 16-bit immediate mov op
> is gone (loads 0 into the dst reg). However due to a bug in envyas,
> the movw alias still existed, and selected the no-longer-present v3
> 16-bit immediate mov op. As a result usage of movw on v5 is the same
> as mov with a 0x0 argument.
>
> The proper fix throughout is to only ever use the 'movw' alias in
> combination with 'sethi'. Anything else should get the
sign-extended
> validation to ensure that the intended value ends up in the
> destination register.
>
> Changes in fuc3 binaries is the result of a different encoding being
> selected for a mov with an 8-bit value.
> ---------------8<----------------
>
yeah, that sounds perfect. Thanks!

>
> >
> > Signed-off-by: Karol Herbst <kherbst at redhat.com>
> > ---
> >  drm/nouveau/nvkm/subdev/pmu/fuc/gf100.fuc3.h |  746
+++++++++----------
> >  drm/nouveau/nvkm/subdev/pmu/fuc/gk208.fuc5.h |  802
> ++++++++++----------
> >  drm/nouveau/nvkm/subdev/pmu/fuc/gt215.fuc3.h | 1006
> +++++++++++++-------------
> >  drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc     |   30 +-
> >  4 files changed, 1292 insertions(+), 1292 deletions(-)
> >
>
> [...]
>
> > diff --git a/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> b/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> > index ec03f9a4..1663bf94 100644
> > --- a/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> > +++ b/drm/nouveau/nvkm/subdev/pmu/fuc/memx.fuc
> > @@ -82,15 +82,15 @@ memx_train_tail:
> >  // $r0  - zero
> >  memx_func_enter:
> >  #if NVKM_PPWR_CHIPSET == GT215
> > -       movw $r8 0x1610
> > +       mov $r8 0x1610
> >         nv_rd32($r7, $r8)
> >         imm32($r6, 0xfffffffc)
> >         and $r7 $r6
> > -       movw $r6 0x2
> > +       mov $r6 0x2
> >         or $r7 $r6
> >         nv_wr32($r8, $r7)
> >  #else
> > -       movw $r6 0x001620
> > +       mov $r6 0x001620
> >         imm32($r7, ~0x00000aa2);
> >         nv_rd32($r8, $r6)
> >         and $r8 $r7
> > @@ -101,7 +101,7 @@ memx_func_enter:
> >         and $r8 $r7
> >         nv_wr32($r6, $r8)
> >
> > -       movw $r6 0x0026f0
> > +       mov $r6 0x0026f0
> >         nv_rd32($r8, $r6)
> >         and $r8 $r7
> >         nv_wr32($r6, $r8)
> > @@ -136,19 +136,19 @@ memx_func_leave:
> >                 bra nz #memx_func_leave_wait
> >
> >  #if NVKM_PPWR_CHIPSET == GT215
> > -       movw $r8 0x1610
> > +       mov $r8 0x1610
> >         nv_rd32($r7, $r8)
> >         imm32($r6, 0xffffffcc)
> >         and $r7 $r6
> >         nv_wr32($r8, $r7)
> >  #else
> > -       movw $r6 0x0026f0
> > +       mov $r6 0x0026f0
> >         imm32($r7, 0x00000001)
> >         nv_rd32($r8, $r6)
> >         or $r8 $r7
> >         nv_wr32($r6, $r8)
> >
> > -       movw $r6 0x001620
> > +       mov $r6 0x001620
> >         nv_rd32($r8, $r6)
> >         or $r8 $r7
> >         nv_wr32($r6, $r8)
> > @@ -177,11 +177,11 @@ memx_func_wait_vblank:
> >         bra #memx_func_wait_vblank_fini
> >
> >         memx_func_wait_vblank_head1:
> > -       movw $r7 0x20
> > +       mov $r7 0x20
> >         bra #memx_func_wait_vblank_0
> >
> >         memx_func_wait_vblank_head0:
> > -       movw $r7 0x8
> > +       mov $r7 0x8
> >
> >         memx_func_wait_vblank_0:
> >                 nv_iord($r6, NV_PPWR_INPUT)
> > @@ -273,13 +273,13 @@ memx_func_train:
> >  // $r5 - outer loop counter
> >  // $r6 - inner loop counter
> >  // $r7 - entry counter (#memx_train_head + $r7)
> > -       movw $r5 0x3
> > -       movw $r7 0x0
> > +       mov $r5 0x3
> > +       mov $r7 0x0
> >
> >  // Read random memory to wake up... things
> >         imm32($r9, 0x700000)
> >         nv_rd32($r8,$r9)
> > -       movw $r14 0x2710
> > +       mov $r14 0x2710
> >         call(nsec)
> >
> >         memx_func_train_loop_outer:
> > @@ -289,9 +289,9 @@ memx_func_train:
> >                 nv_wr32($r9, $r8)
> >                 push $r5
> >
> > -               movw $r6 0x0
> > +               mov $r6 0x0
> >                 memx_func_train_loop_inner:
> > -                       movw $r8 0x1111
> > +                       mov $r8 0x1111
> >                         mulu $r9 $r6 $r8
> >                         shl b32 $r8 $r9 0x10
> >                         or $r8 $r9
> > @@ -315,7 +315,7 @@ memx_func_train:
> >
> >                         // $r5 - inner inner loop counter
> >                         // $r9 - result
> > -                       movw $r5 0
> > +                       mov $r5 0
> >                         imm32($r9, 0x8300ffff)
> >                         memx_func_train_loop_4x:
> >                                 imm32($r10, 0x100080)
> > --
> > 2.14.2
> >
> > _______________________________________________
> > Nouveau mailing list
> > Nouveau at lists.freedesktop.org
> > https://lists.freedesktop.org/mailman/listinfo/nouveau
> _______________________________________________
> Nouveau mailing list
> Nouveau at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/nouveau
>-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<https://lists.freedesktop.org/archives/nouveau/attachments/20171101/4e00ca20/attachment.html>

Possibly Parallel Threads

Search for more seemingly similar threads

Nouveau - Nov 2017 - [PATCH] pmu/fuc: don't use movw directly anymore

[Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore

[Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore

[Nouveau] [PATCH] pmu/fuc: don't use movw directly anymore

Possibly Parallel Threads