Skip to contentSkip to conversation

drm/i915/mocs: Program MOCS for all engines on init

PATCH In review Peter Antoine 3 participants 8 messages Mar 14, 2016 – Apr 13, 2016

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH v4 1/1 drm/i915/mocs: Program MOCS for all engines on init

Allow for the MOCS to be programmed for all engines. Currently we program the MOCS when the first render batch goes through. This works on most platforms but fails on platforms that do not run a render batch early,
i.e. headless servers. The patch now programs all initialised engines on init and the RCS is programmed again within the initial batch. This is done for predictable consistency with regards to the hardware context.

Hardware context loading sets the values of the MOCS for RCS and L3CC. Programming them from within the batch makes sure that the render context is valid, no matter what the previous state of the saved-context was.

v2: posted correct version to the mailing list.
v3: moved programming to within engine->init_hw() (Chris Wilson)
v4: code formatting and white-space changes. (Chris Wilson)

---
 drivers/gpu/drm/i915/i915_gem.c   |   3 +
 drivers/gpu/drm/i915/intel_lrc.c  |   2 +-
 drivers/gpu/drm/i915/intel_mocs.c | 132 ++++++++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/intel_mocs.h |   2 +
 4 files changed, 110 insertions(+), 29 deletions(-)
drivers/gpu/drm/i915/i915_gem.c +3 -0
index b854af2..73e4892 100644
@@ -32,6 +32,7 @@
 #include "i915_vgpu.h"
 #include "i915_trace.h"
 #include "intel_drv.h"
+#include "intel_mocs.h"
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -4882,6 +4883,8 @@ i915_gem_init_hw(struct drm_device *dev)
 			goto out;
 	}
 
+	intel_mocs_init_l3cc_table(dev);
+
 	/* We can't enable contexts until all firmware is loaded */
 	if (HAS_GUC_UCODE(dev)) {
 		ret = intel_guc_ucode_load(dev);
drivers/gpu/drm/i915/intel_lrc.c +1 -1
index 27c9ee3..03ead7f 100644
@@ -1603,7 +1603,7 @@ static int gen8_init_common_ring(struct intel_engine_cs *ring)
 
 	memset(&ring->hangcheck, 0, sizeof(ring->hangcheck));
 
-	return 0;
+	return intel_mocs_init_engine(ring);
 }
 
 static int gen8_init_render_ring(struct intel_engine_cs *ring)
drivers/gpu/drm/i915/intel_mocs.c +104 -28

187 lines not on this page · raw message

drivers/gpu/drm/i915/intel_mocs.h +2 -0
index 76e45b1..4640299 100644
@@ -53,5 +53,7 @@
 #include "i915_drv.h"
 
 int intel_rcs_context_init_mocs(struct drm_i915_gem_request *req);
+void intel_mocs_init_l3cc_table(struct drm_device *dev);
+int intel_mocs_init_engine(struct intel_engine_cs *ring);
 
 #endif
Signature · 6 lines
1.9.1

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#1 lore raw

✗ Fi.CI.BAT: failure for drm/i915/mocs: Program MOCS for all engines on init (rev6)

== Series Details ==

== Series Details ==

Series: drm/i915/mocs: Program MOCS for all engines on init (rev6)
URL : https://patchwork.freedesktop.org/series/4310/
State : failure

== Summary ==

Series 4310v6 drm/i915/mocs: Program MOCS for all engines on init
http://patchwork.freedesktop.org/api/1.0/series/4310/revisions/6/mbox/

Test drv_hangman:

        Subgroup error-state-basic:
                pass       -> INCOMPLETE (snb-dellxps)
Test gem_exec_basic:
        Subgroup readonly-render:
                incomplete -> PASS       (ilk-hp8440p)
Test gem_mmap_gtt:
        Subgroup basic-small-copy:
                pass       -> DMESG-WARN (ilk-hp8440p)
        Subgroup basic-write-no-prefault:
                incomplete -> PASS       (ilk-hp8440p)
Test gem_ringfill:
        Subgroup basic-default-s3:
                dmesg-warn -> PASS       (bsw-nuc-2)
                incomplete -> DMESG-WARN (ilk-hp8440p)
Test kms_addfb_basic:
        Subgroup addfb25-yf-tiled:
                incomplete -> PASS       (ilk-hp8440p)
        Subgroup bad-pitch-1024:
                incomplete -> PASS       (ilk-hp8440p)
        Subgroup size-max:
                incomplete -> PASS       (ilk-hp8440p)
        Subgroup small-bo:
                incomplete -> PASS       (ilk-hp8440p)
        Subgroup unused-offsets:
                incomplete -> PASS       (ilk-hp8440p)
Test kms_flip:
        Subgroup basic-flip-vs-dpms:
                dmesg-warn -> PASS       (bdw-ultra)
                pass       -> DMESG-WARN (ilk-hp8440p) UNSTABLE
        Subgroup basic-flip-vs-modeset:
                incomplete -> PASS       (bsw-nuc-2)
Test kms_pipe_crc_basic:
        Subgroup nonblocking-crc-pipe-b:
                pass       -> DMESG-WARN (hsw-brixbox)
        Subgroup suspend-read-crc-pipe-a:
                incomplete -> PASS       (hsw-gt2)
Test pm_rpm:
        Subgroup basic-pci-d3-state:
                dmesg-warn -> PASS       (bsw-nuc-2)
                pass       -> DMESG-WARN (snb-dellxps)
Test prime_self_import:
        Subgroup basic-llseek-size:
                incomplete -> PASS       (ilk-hp8440p)
bdw-nuci7        total:194  pass:182  dwarn:0   dfail:0   fail:0   skip:12 
bdw-ultra        total:194  pass:173  dwarn:0   dfail:0   fail:0   skip:21 
bsw-nuc-2        total:194  pass:156  dwarn:1   dfail:0   fail:0   skip:37 
hsw-brixbox      total:194  pass:171  dwarn:1   dfail:0   fail:0   skip:22 
hsw-gt2          total:194  pass:177  dwarn:0   dfail:0   fail:0   skip:17 
ilk-hp8440p      total:194  pass:124  dwarn:6   dfail:0   fail:1   skip:63 
ivb-t430s        total:194  pass:169  dwarn:0   dfail:0   fail:0   skip:25 
skl-i5k-2        total:194  pass:171  dwarn:0   dfail:0   fail:0   skip:23 
skl-i7k-2        total:194  pass:171  dwarn:0   dfail:0   fail:0   skip:23 
skl-nuci5        total:194  pass:183  dwarn:0   dfail:0   fail:0   skip:11 
snb-dellxps      total:152  pass:124  dwarn:1   dfail:0   fail:0   skip:26 
snb-x220t        total:194  pass:159  dwarn:1   dfail:0   fail:1   skip:33 

Results at /archive/results/CI_IGT_test/Patchwork_1594/

3e5ecc8c5ff80cb1fb635ce1cf16b7cd4cfb1979 drm-intel-nightly: 2016y-03m-14d-09h-06m-00s UTC integration manifest 2825cd26c9cf60a6122737f79520aecde49098a1 drm/i915/mocs: Program MOCS for all engines on init

_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#2 lore raw
In reply to Peter Antoine
Quoted 14 lines · Peter Antoine

Allow for the MOCS to be programmed for all engines. Currently we program the MOCS when the first render batch goes through. This works on most platforms but fails on platforms that do not run a render batch early,
i.e. headless servers. The patch now programs all initialised engines on init and the RCS is programmed again within the initial batch. This is done for predictable consistency with regards to the hardware context.

Hardware context loading sets the values of the MOCS for RCS and L3CC. Programming them from within the batch makes sure that the render context is valid, no matter what the previous state of the saved-context was.

Quoted 5 lines

v2: posted correct version to the mailing list.
v3: moved programming to within engine->init_hw() (Chris Wilson)
v4: code formatting and white-space changes. (Chris Wilson)

So testcase?

Execute a bunch of MI_STORE_REGISTER_MEM on the various rings in a fresh context each time and confirm the ABI for the first N locations.

Repeat across suspend/resume (i.e. make sure the context image maintain the register state). Then verify that freshly constructed contexts also have the correct settings after resume.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#3 lore raw

Chris,

Testcases are underway, validation are working on them.

Peter.

Quoted 23 lines · Chris Wilson
Quoted 14 lines · Peter Antoine

Allow for the MOCS to be programmed for all engines. Currently we program the MOCS when the first render batch goes through. This works on most platforms but fails on platforms that do not run a render batch early,
i.e. headless servers. The patch now programs all initialised engines on init and the RCS is programmed again within the initial batch. This is done for predictable consistency with regards to the hardware context.

Hardware context loading sets the values of the MOCS for RCS and L3CC. Programming them from within the batch makes sure that the render context is valid, no matter what the previous state of the saved-context was.

Quoted 5 lines

v2: posted correct version to the mailing list.
v3: moved programming to within engine->init_hw() (Chris Wilson)
v4: code formatting and white-space changes. (Chris Wilson)

So testcase?

Quoted 9 lines

Execute a bunch of MI_STORE_REGISTER_MEM on the various rings in a fresh context each time and confirm the ABI for the first N locations.

Repeat across suspend/resume (i.e. make sure the context image maintain the register state). Then verify that freshly constructed contexts also have the correct settings after resume.
-Chris

--
Peter Antoine (Android Graphics Driver Software Engineer)
---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47
_______________________________________________
Intel-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#4 lore raw

Chris.

Can these patches be reviewed without the tests or are they blocked waiting for the tests.

Are the patches acceptable?

Thanks,
Peter.

Quoted 41 lines · Peter Antoine

Chris,

Testcases are underway, validation are working on them.

Peter.

Quoted 23 lines · Chris Wilson
Quoted 14 lines · Peter Antoine

Allow for the MOCS to be programmed for all engines. Currently we program the MOCS when the first render batch goes through. This works on most platforms but fails on platforms that do not run a render batch early,
i.e. headless servers. The patch now programs all initialised engines on init and the RCS is programmed again within the initial batch. This is done for predictable consistency with regards to the hardware context.

Hardware context loading sets the values of the MOCS for RCS and L3CC. Programming them from within the batch makes sure that the render context is valid, no matter what the previous state of the saved-context was.

Quoted 5 lines

v2: posted correct version to the mailing list.
v3: moved programming to within engine->init_hw() (Chris Wilson)
v4: code formatting and white-space changes. (Chris Wilson)

So testcase?

Quoted 9 lines

Execute a bunch of MI_STORE_REGISTER_MEM on the various rings in a fresh context each time and confirm the ABI for the first N locations.

Repeat across suspend/resume (i.e. make sure the context image maintain the register state). Then verify that freshly constructed contexts also have the correct settings after resume.
-Chris

Quoted 8 lines

--
Peter Antoine (Android Graphics Driver Software Engineer)
---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47

--
Peter Antoine (Android Graphics Driver Software Engineer)
---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47
_______________________________________________
Intel-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#5 lore raw
Quoted 4 lines · Peter Antoine

Chris.

Can these patches be reviewed without the tests or are they blocked waiting for the tests.

More or less waiting upon the tests. Or where is the bugzilla?

It would only take a couple of hours to write something like:

for_each_engine() {
	switch (mode) {
	case NOTHING: break;
	case RESET: reset_gpu(); break;
	case SUSPEND: suspend_autoresume(); brea;
	case HIBERNATE: hibernate_autoresume(); brea;
	}
	fd = drm_open_driver();
	if (use_context)
		ctx = gem_context_create();
	for_each_mocs()
		MI_STORE_REGISTER_MEM(engine, mocs, out[i]);
	execbuf(engine)

	gem_set_domain(out, DOMAIN_COU, 0);
	/* Check ABI caching levels */
	for_each_mocs()
		igt_assert(out[i], foo);
	close(fd);
}
Quoted 1 line

Are the patches acceptable?

Yes, with a reference to a bug demonstrating the impact and a testcase to demonstrate it works.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
#6 lore raw
In reply to Peter Antoine

Chris,

If the test is ok, can you review-by this patch.

Thanks,
Peter.

Quoted 61 lines · Peter Antoine

Chris.

Can these patches be reviewed without the tests or are they blocked waiting for the tests.

Are the patches acceptable?

Thanks,
Peter.

Quoted 41 lines · Peter Antoine

Chris,

Testcases are underway, validation are working on them.

Peter.

Quoted 23 lines · Chris Wilson
Quoted 14 lines · Peter Antoine

Allow for the MOCS to be programmed for all engines. Currently we program the MOCS when the first render batch goes through. This works on most platforms but fails on platforms that do not run a render batch early,
i.e. headless servers. The patch now programs all initialised engines on init and the RCS is programmed again within the initial batch. This is done for predictable consistency with regards to the hardware context.

Hardware context loading sets the values of the MOCS for RCS and L3CC. Programming them from within the batch makes sure that the render context is valid, no matter what the previous state of the saved-context was.

Quoted 5 lines

v2: posted correct version to the mailing list.
v3: moved programming to within engine->init_hw() (Chris Wilson)
v4: code formatting and white-space changes. (Chris Wilson)

So testcase?

Quoted 9 lines

Execute a bunch of MI_STORE_REGISTER_MEM on the various rings in a fresh context each time and confirm the ABI for the first N locations.

Repeat across suspend/resume (i.e. make sure the context image maintain the register state). Then verify that freshly constructed contexts also have the correct settings after resume.
-Chris

Quoted 8 lines

--
Peter Antoine (Android Graphics Driver Software Engineer)
---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47

Quoted 8 lines

--
Peter Antoine (Android Graphics Driver Software Engineer)
---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47

--
Peter Antoine (Android Graphics Driver Software Engineer)
---------------------------------------------------------------------
Intel Corporation (UK) Limited
Registered No. 1134945 (England)
Registered Office: Pipers Way, Swindon SN3 1RJ VAT No: 860 2173 47
_______________________________________________
Intel-gfx mailing list [email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

#7 lore raw
Quoted 3 lines · Peter Antoine

Chris,

If the test is ok, can you review-by this patch.

Yup, my box decided that was good time to suffer fs corruption. Patched up and resent for CI with my r-b.
-Chris

Signature · 5 lines
Chris Wilson, Intel Open Source Technology Centre
_______________________________________________
Intel-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/intel-gfx