drm/i915: Clean up the HWSTAM mess

Currently we're unmasking some random looking bits in HWSTAM
on gen3/4/5. The two bits we apparently unmask are 0 and 12,
and also bits 16-31 on gen4/5.
What those bits do depends on the gen as follows:
 bit 0: Breakpoint (gen2), ASLE (gen3), reserved (gen4), render user interrupt (gen5)
 bit 12: Sync flush statusa (gen2-4), reserved (gen5)
 bit 16-31: The ones that can unmasked seem to be mostly some
            display stuff on gen4. Bit 18 is the PIPE_CONTROL notify,
    which might be the only intresting one. On gen5 all the
    bits are reserved.

So I don't know whether we actually depend on that status page write
somehow. Extra seqno coherency by accident perhaps? Except we don't
even unmask the user interrupt bit in HWSTAM except on gen5, and
sync flush isn't something we use normally, so seems unlikely. So
let's just assume we don't need any of this and mask everything in
HWSTAM.

From gen6 onwards there's a separate HWSTAM for each engine, and so
we deal with them during the engine setup.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-15-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Mask everything in ring HWSTAM on gen6+ in ringbuffer mode

The execlist code already masks everything in the ring HWSTAM, but
the ringbuffer code doesn't. Let's go ahead and do that. Pre-gen6
platforms setup HWSTAM during irq setup already since there's just
the one register, and it also contains bits for non-ring interrupts.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-13-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Extend private i915_param_named macro with description

We're always specifying description of each module param in
separate macro. Let's combine description into our main macro.
Started with Coccinelle, followed by minor cleanup.

@match1@
declarer name MODULE_PARM_DESC;
identifier n;
constant c;
@@
(
- MODULE_PARM_DESC(n, c);
)

@fix1 depends on match1@
declarer name i915_param_named;
declarer name i915_param_named_unsafe;
identifier match1.n;
constant match1.c;
@@
(
i915_param_named(n, ...
+ , c
);
|
i915_param_named_unsafe(n, ...
+ , c
);
)

Suggested-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170914150805.28376-4-michal.wajdeczko@intel.com

drm/i915: Introduce custom variant of module_param_named macro

As we now use same name for public module param and its local
representation we can simplify param definition macro.

Changes done with Coccinelle:

@@
declarer name module_param_named;
declarer name module_param_named_unsafe;
declarer name i915_param_named;
declarer name i915_param_named_unsafe;
identifier n;
@@

(
-module_param_named(n, i915.n,
+i915_module_param_named(n,
  ...);
|
-module_param_named_unsafe(n, i915.n,
+i915_module_param_named_unsafe(n,
 ...);
)

Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170914150805.28376-3-michal.wajdeczko@intel.com

drm/i915: Rename lvds_use_ssc modparam to panel_use_ssc

This modparam affects not only LVDS but also eDP panels. Additionally
with this rename we will keep modparam and i915_params field name in sync.
This patch will unblock us with further improvements around params defs.

Suggested-by: Ville Syrjala <ville.syrjala@intel.com>
Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Ville Syrjala <ville.syrjala@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170914150805.28376-2-michal.wajdeczko@intel.com

drm/i915: Mark the userptr invalidate workqueue as WQ_MEM_RECLAIM

To silence the critcs:

[56532.161115] workqueue: PF_MEMALLOC task 36(khugepaged) is flushing !WQ_MEM_RECLAIM i915-userptr-release:          (null)
[56532.161138] ------------[ cut here ]------------
[56532.161144] WARNING: CPU: 1 PID: 36 at kernel/workqueue.c:2418 check_flush_dependency+0xe8/0xf0
[56532.161145] Modules linked in: wmi_bmof
[56532.161148] CPU: 1 PID: 36 Comm: khugepaged Not tainted 4.13.0-krejzi #1
[56532.161149] Hardware name: HP HP ProBook 470 G3/8102, BIOS N78 Ver. 01.17 06/08/2017
[56532.161150] task: ffff8802371ee200 task.stack: ffffc90000174000
[56532.161152] RIP: 0010:check_flush_dependency+0xe8/0xf0
[56532.161152] RSP: 0018:ffffc900001777b8 EFLAGS: 00010286
[56532.161153] RAX: 000000000000006c RBX: ffff88022fc5a000 RCX: 0000000000000001
[56532.161154] RDX: 0000000000000000 RSI: 0000000000000086 RDI: 00000000ffffffff
[56532.161155] RBP: 0000000000000000 R08: 14f038bb55f6dae0 R09: 0000000000000516
[56532.161155] R10: ffffc900001778a0 R11: 000000006c756e28 R12: ffff8802371ee200
[56532.161156] R13: 0000000000000000 R14: 000000000000000b R15: ffffc90000177810
[56532.161157] FS:  0000000000000000(0000) GS:ffff880240480000(0000) knlGS:0000000000000000
[56532.161158] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[56532.161158] CR2: 0000000004795ff8 CR3: 000000000220a000 CR4: 00000000003406e0
[56532.161159] Call Trace:
[56532.161161]  ? flush_workqueue+0x136/0x3e0
[56532.161178]  ? _raw_spin_unlock_irqrestore+0xf/0x30
[56532.161179]  ? try_to_wake_up+0x1ce/0x3b0
[56532.161183]  ? i915_gem_userptr_mn_invalidate_range_start+0x13f/0x150
[56532.161184]  ? _raw_spin_unlock+0xd/0x20
[56532.161186]  ? i915_gem_userptr_mn_invalidate_range_start+0x13f/0x150
[56532.161189]  ? __mmu_notifier_invalidate_range_start+0x4a/0x70
[56532.161191]  ? try_to_unmap_one+0x5e5/0x660
[56532.161193]  ? rmap_walk_file+0xe4/0x240
[56532.161195]  ? __ClearPageMovable+0x10/0x10
[56532.161196]  ? try_to_unmap+0x8c/0xe0
[56532.161197]  ? page_remove_rmap+0x280/0x280
[56532.161199]  ? page_not_mapped+0x10/0x10
[56532.161200]  ? page_get_anon_vma+0x90/0x90
[56532.161202]  ? migrate_pages+0x6a5/0x940
[56532.161203]  ? isolate_freepages_block+0x330/0x330
[56532.161205]  ? compact_zone+0x593/0x6a0
[56532.161206]  ? enqueue_task_fair+0xc3/0x1180
[56532.161208]  ? compact_zone_order+0x9b/0xc0
[56532.161210]  ? get_page_from_freelist+0x24a/0x900
[56532.161212]  ? try_to_compact_pages+0xc8/0x240
[56532.161213]  ? try_to_compact_pages+0xc8/0x240
[56532.161215]  ? __alloc_pages_direct_compact+0x45/0xe0
[56532.161216]  ? __alloc_pages_slowpath+0x845/0xb90
[56532.161218]  ? __alloc_pages_nodemask+0x176/0x1f0
[56532.161220]  ? wait_woken+0x80/0x80
[56532.161222]  ? khugepaged+0x29e/0x17d0
[56532.161223]  ? wait_woken+0x80/0x80
[56532.161225]  ? collapse_shmem.isra.39+0xa60/0xa60
[56532.161226]  ? kthread+0x10d/0x130
[56532.161227]  ? kthread_create_on_node+0x60/0x60
[56532.161228]  ? ret_from_fork+0x22/0x30
[56532.161229] Code: 00 8b b0 10 05 00 00 48 8d 8b b0 00 00 00 48 8d 90 b8 06 00 00 49 89 e8 48 c7 c7 38 55 09 82 c6 05 f9 c6 1d 01 01 e8 0e a1 03 00 <0f> ff e9 6b ff ff ff 90 48 8b 37 40 f6 c6 04 75 1b 48 c1 ee 05
[56532.161251] ---[ end trace 2ce2b4f5f69b803b ]---

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170911084135.22903-2-chris@chris-wilson.co.uk
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>

drm/i915: Remove unused 'in_vbl' from i915_get_crtc_scanoutpos()

Commit 1bf6ad622b9b ("drm/vblank: drop the mode argument from
drm_calc_vbltimestamp_from_scanoutpos") removed the use of in_vbl, but
did not remove the local variable. Do so now.

Fixes: 1bf6ad622b9b ("drm/vblank: drop the mode argument from drm_calc_vbltimestamp_from_scanoutpos")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170914164213.18461-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

drm/i915/cnl: Change the macro name to DPLL_CFGCR0_DCO_FRACTION_SHIFT

No functional changes. Only change the macro from
"DPLL_CFGCR0_DC0_FRAC_SHIFT to DPLL_CFGCR0_DCO_FRACTION_SHIFT
to be consistent with DPLL_CFGCR0_DCO_FRACTION_MASK
and DPLL_CFGCR0_DCO_FRACTION

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505413899-30876-1-git-send-email-manasi.d.navare@intel.com

drm/i915: Gen3 HWSTAM is actually 32 bits

Bspec claims that HWSTAM is only 16 bits on gen3, but the other
interrupts registers are 32 bits and there are 18 valid interrupt
bits. Hence a 16 bit HWSTAM wouldn't be able to contain all the
bits, so it seems the spec is incorrect about the size of the
register. And indeed I can clear bits 16 and 17 just fine with
a 32 bit write. So let's adjust the code to treat the register
as 32 bits.

Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-14-ville.syrjala@linux.intel.com

drm/i915: Rewrite GMCH irq handlers to avoid loops

Eliminate the loops from the gen2-3 irq handlers. Since we don't use
MSI anymore on these platforms, and thus the CPU interrupt will be level
triggered, we shouldn't need to play any tricks with IER to induce edges
from IIR. IIR itself still detects only edges from PIPESTAT & co. on
gen4 but since IIR is double buffered and we only clear one bit per irq
handler invocation we can use the normal "clear PIPESTAT & co. -> clear
IIR" approach to ack the interrupts. On gen2 everything is level
triggered, and gen3 presumably follows either the gen2 or gen4 approach
since nothing else would really make sense.

v2: Drop the IER tricks since we no longer use MSI

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-12-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Extract PIPESTAT irq handling into separate functions

Extract the gen2-4 PIPESTAT irq handling into separate functions just
like we already do on VLV/CHV.

We can share valleyview_pipestat_irq_ack() on all gmch platforms to
actually read and clear the PIPESTAT status bits, so let's rename
it to i9xx_pipestat_irq_ack().

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-11-ville.syrjala@linux.intel.com

drm/i915: Remove NULL dev_priv checks from irq_uninstall

There should be no way to land in irq_uninstall without a
valid dev_priv. Let's kill off the remaining checks, which are
probably some kind of UMS leftovers. Not all the irq_uninstall
hooks even had them anymore.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-10-ville.syrjala@linux.intel.com

drm/i915: Unify the appearance of gen3/4 irq_postistall hooks

Do the irq_mask/enable_mask setup in the same way on gen3/4, and also
reorder the steps to make the code more uniform.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-9-ville.syrjala@linux.intel.com

drm/i915: Eliminate PORT_HOTPLUG_EN setup from gen3/4 irq_postinstall

We've already cleared PORT_HOTPLUG_EN in the .irq_preinstall hook
so doing it again in the .irq_postinstall is pointless.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-8-ville.syrjala@linux.intel.com

drm/i915: Setup EMR first on all gen2-4

Unify the appaerance of the gen2-4 irq postinstall hooks a little
bit by doing the EMR setup first on all the platforms.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-7-ville.syrjala@linux.intel.com

drm/i915: Introduce GEN2_IRQ_RESET/INIT

Unify the appearance of the gen2 irq code with the gen3+ code by
introducing the GEN2_IRQ_RESET/INIT macros.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-6-ville.syrjala@linux.intel.com

drm/i915: Use GEN3_IRQ_RESET/INIT on gen3/4

Replace the manual IMR+IER+IIR write sequences with the appropriate
GEN3_IRQ_RESET/INIT macro invocations in gen3/4.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-5-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: s/GEN5/GEN3/

The GEN5_IRQ_RESET/INIT macros are perfectly suitable even for
gen3/4 hardware as those have 32 bit interrupt registers. Let's
rename the macros to reflect that fact.

Gen2 on the other hand has 16 bit interrupt registers so these
macros aren't really appropriate there.

v2: Fix patch subject (Maarten)

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-4-ville.syrjala@linux.intel.com

drm/i915: Clear pipestat consistently

We have a lot of different ways of clearing the PIPESTAT registers.
Let's unify it all into one function. There's no magic in PIPESTAT
that would require any of the double clearing and whatnot that
some of the code tries to do. All we can really do is clear the status
bits and disable the enable bits. There is no way to mask anything
so as soon as another event happens the status bit will become set
again, and trying to clear them twice or something can't protect
against that.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-3-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>

drm/i915: Don't enable/unmask flip interrupts

commit fd3a40242e87 ("drm/i915: Rip out legacy page_flip completion/irq
handling") removed the code to hande the flip done/pending interrupts,
but it failed to actually disable/mask those interrupts. Let's do that
now.

Also remove a stale comment that was left behind.

Cc: Daniel Vetter <daniel.vetter@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170818183705.27850-2-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>

drm/i915: Remove the "INDEX" suffix from PPAT marcos

Remove the "INDEX" suffix from PPAT marcos as they are bits actually, not
indexes.

Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505392783-4084-2-git-send-email-zhi.a.wang@intel.com

drm/i915: Introduce private PAT management

The private PAT management is to support PPAT entry manipulation. Two
APIs are introduced for dynamically managing PPAT entries: intel_ppat_get
and intel_ppat_put.

intel_ppat_get will search for an existing PPAT entry which perfectly
matches the required PPAT value. If not, it will try to allocate a new
entry if there is any available PPAT indexs, or return a partially
matched PPAT entry if there is no available PPAT indexes.

intel_ppat_put will put back the PPAT entry which comes from
intel_ppat_get. If it's dynamically allocated, the reference count will
be decreased. If the reference count turns into zero, the PPAT index is
freed again.

Besides, another two callbacks are introduced to support the private PAT
management framework. One is ppat->update_hw(), which writes the PPAT
configurations in ppat->entries into HW. Another one is ppat->match, which
will return a score to show how two PPAT values match with each other.

v17:

- Refine the comparision of score of BDW. (Joonas)

v16:

- Fix a bug in PPAT match function of BDW. (Joonas)

v15:

- Refine some code flow. (Joonas)

v12:

- Fix a problem "not returning the entry of best score". (Zhenyu)

v7:

- Keep all the register writes unchanged in this patch. (Joonas)

v6:

- Address all comments from Chris:
http://www.spinics.net/lists/intel-gfx/msg136850.html

- Address all comments from Joonas:
http://www.spinics.net/lists/intel-gfx/msg136845.html

v5:

- Add check and warnnings for those platforms which don't have PPAT.

v3:

- Introduce dirty bitmap for PPAT registers. (Chris)
- Change the name of the pointer "dev_priv" to "i915". (Chris)
- intel_ppat_{get, put} returns/takes a const intel_ppat_entry *. (Chris)

v2:

- API re-design. (Chris)

Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> #v7
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
[Joonas: Use BIT() in the enum in bdw_private_pat_match]
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505392783-4084-1-git-send-email-zhi.a.wang@intel.com

drm/i915: Switch over to the LLC/eLLC hotspot avoidance hash mode for CCS

Use the LLC/eLLC hotspot avoidance mode for CCS on LLC machines. This is
reported to give better performance.

Testing has indicated that we don't need to enforce any massive 2 or 4
MiB alignment for all compressed resources even though there are still
plenty of stale comments in the spec suggesting that we do.

We do need to make sure every hardware unit that deals with the
compressed data uses the same hash mode.

Cc: Ben Widawsky <ben@bwidawsk.net>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Cc: Daniel Stone <daniels@collabora.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170824191100.10949-4-ville.syrjala@linux.intel.com
Reviewed-by: Ben Widawsky <ben@bwidawsk.net>

drm/i915: Simplify i915_reg_read_ioctl

Convert to use the freshly available made INTEL_GEN_MASK for easier
grepping and improve function readability and clarify the UABI
documentation.

No functional changes.

v2:
- Lift GEM_BUG_ONs and use is_power_of_2 (Chris)
- Retain -EINVAL on bad flags behavior (Chris)

v3:
- Extract flags with 'entry->size - 1' (Chris)

v4:
- Add GEM_BUG_ON on for flags vs entry offset (Chris)

v5:
- Use 'u16' to match 'dev_priv' (Ville)

v6:
- Fix checkpatch.pl errors

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913115255.13851-2-joonas.lahtinen@linux.intel.com

drm/i915: Introduce INTEL_GEN_MASK

Split INTEL_GEN_MASK out of IS_GEN macro, and make it usable
within static declarations (unlike compound statements).

v2:
- s/combound/compound/ (Tvrtko)
- Fix whitespace (yes, we need automatic checkpatch.pl)

Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913115255.13851-1-joonas.lahtinen@linux.intel.com

drm/i915: Refresh VLV/CHV PSR comments on HW PSR_state machine.

DK had pointed out a comment there was hard to understand, so I
tried to read back again and I couldn't understand that as well.
So let me re-phrase that in a way that anyone can understand
later, even myself.

Also fixed the comment block style.

v2: Accept DK's suggestion on PSR_state 2 and PSR_state 3 named
    as spec.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170912183059.5086-1-rodrigo.vivi@intel.com

drm/i915/execlists: Read the context-status HEAD from the HWSP

The engine also provides a mirror of the CSB write pointer in the HWSP,
but not of our read pointer. To take advantage of this we need to
remember where we read up to on the last interrupt and continue off from
there. This poses a problem following a reset, as we don't know where
the hw will start writing from, and due to the use of power contexts we
cannot perform that query during the reset itself. So we continue the
current modus operandi of delaying the first read of the context-status
read/write pointers until after the first interrupt. With this we should
now have eliminated all uncached mmio reads in handling the
context-status interrupt, though we still have the uncached mmio writes
for submitting new work, and many uncached mmio reads in the global
interrupt handler itself. Still a step in the right direction towards
reducing our resubmit latency, although it appears lost in the noise!

v2: Cannonlake moved the CSB write index
v3: Include the sw/hwsp state in debugfs/i915_engine_info
v4: Also revert to using CSB mmio for GVT-g
v5: Prevent the compiler reloading tail (Mika)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Acked-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913085605.18299-6-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>

drm/i915/execlists: Read the context-status buffer from the HWSP

The engine provides a mirror of the CSB in the HWSP. If we use the
cacheable reads from the HWSP, we can shave off a few mmio reads per
context-switch interrupt (which are quite frequent!). Just removing a
couple of mmio is not enough to actually reduce any latency, but a small
reduction in overall cpu usage.

Much appreciation for Ben dropping the bombshell that the CSB was in the
HWSP and for Michel in digging out the details.

v2: Don't be lazy, add the defines for the indices.
v3: Include the HWSP in debugfs/i915_engine_info
v4: Check for GVT-g, it currently depends on intercepting CSB mmio
v5: Fixup GVT-g mmio path
v6: Disable HWSP if VT-d is active as the iommu adds unpredictable
memory latency. (Mika)
v7: Also markup the CSB read with READ_ONCE() as it may still be an mmio
read and we want to stop the compiler from issuing a later (v.slow) reload.

Suggested-by: Ben Widawsky <benjamin.widawsky@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Acked-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913133534.26927-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>

drm/i915: Allow HW status page to be bound high

At the time of commit 1f767e02d69f ("drm/i915: HWS must be in the
mappable region for g33"), drm_mm insertion would often default to
placing a new object high in the zone forcing us to specify that certain
HWSP must be bound within the low mappable region. Since then, drm_mm
has gained more finesse over its placement and exposes that to the
caller, commit 4e64e5539d15 ("drm: Improve drm_mm search (and fix
topdown allocation) with rbtrees"). As such where possible we want the
HWSP to be outside of the mappable aperture and so need to specify that
can be pinned high.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913085605.18299-4-chris@chris-wilson.co.uk

drm/i915/lrc: allocate separate page for HWSP

On gen8+ we're currently using the PPHWSP of the kernel ctx as the
global HWSP. However, when the kernel ctx gets submitted (e.g. from
__intel_autoenable_gt_powersave) the HW will use that page as both
HWSP and PPHWSP. This causes a conflict in the register arena of the
HWSP, i.e. dword indices below 0x30. We don't current utilize this arena,
but in the following patches we will take advantage of the cached
register state for handling execlist's context status interrupt.

To avoid the conflict, instead of re-using the PPHWSP of the kernel
ctx we can allocate a separate page for the HWSP like what happens for
pre-execlists platform.

v2: Add a use-case for the register arena of the HWSP.

Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1499357440-34688-1-git-send-email-daniele.ceraolospurio@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913085605.18299-3-chris@chris-wilson.co.uk

drm/i915/guc: Don't make assumptions while getting the lrca offset

Using the HWSP ggtt_offset to get the lrca offset is only correct if the
HWSP happens to be before it (when we reuse the PPHWSP of the kernel
context as the engine HWSP). Instead of making this assumption, get the
lrca offset from the kernel_context engine state.

And while looking at this part of the GuC interaction, it was also
noticed that the firmware expects the size of only the engine context
(context minus the execlist part, i.e. don't include the first 80
dwords), so pass the right size.

v2: Use the new macros to prevent abusive overuse of the old ones (Chris).

Reported-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170712193032.27080-2-michel.thierry@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913085605.18299-2-chris@chris-wilson.co.uk

drm/i915/lrc: Clarify the format of the context image

Not only the context image consist of two parts (the PPHWSP, and the
logical context state), but we also allocate a header at the start of
for sharing data with GuC. Thus every lrc looks like this:

  | [guc]          | [hwsp] [logical state] |
  |<- our header ->|<- context image      ->|

So far, we have oversimplified whenever we use each of these parts of the
context, just because the GuC header happens to be in page 0, and the
(PP)HWSP is in page 1. But this had led to using the same define for more
than one meaning (as a page index in the lrc and as 1 page).

This patch adds defines for the GuC shared page, the PPHWSP page and the
start of the logical state. It also updated the places where the old
define was being used. Since we are not changing the size (or format) of
the context, there are no functional changes.

v2: Use PPHWSP index for hws again.

Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: intel-gvt-dev@lists.freedesktop.org
Link: http://patchwork.freedesktop.org/patch/msgid/20170712193032.27080-1-michel.thierry@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913085605.18299-1-chris@chris-wilson.co.uk

drm/i915/selftests: Use mul_u32_u32() for 32b x 32b -> 64b result

As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913105154.2910-2-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

drm/i915: Use mul_u32_u32() for 32b x 32b -> 64b result

As realised by commit 9e3d6223d209 ("math64, timers: Fix 32bit
mul_u64_u32_shr() and friends"), GCC does not always generate ideal code
for performing a 32b x 32b multiply returning a 64b result (i.e. where
we idiomatically use u64 result = (u64)x * (u32)x). This catches a
couple of instances in the display code using (u64)x * (u32)y.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913105154.2910-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

drm/i915: Squelch smatch warning for statement with no effect

The sgt iterators cause an

drivers/gpu/drm/i915/i915_gpu_error.c:846 i915_error_object_create() warn: statement has no effect 7

everywhere they are used. If we change the code slightly, we can achieve
the same increment without altering the output or raising a warning.

   text    data     bss     dec     hex filename
1267906   20587    3168 1291661  13b58d before
1267906   20587    3168 1291661  13b58d after

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170913105754.4423-1-chris@chris-wilson.co.uk

drm/i915/guc: Small improvements to guc_wq_item_append

Spare some comments and other small style changes.

Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505252197-27696-3-git-send-email-oscar.mateo@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915/guc: Remove WQ_WORKLOAD_SHIFT define

We never used it in i915 and it's going to be removed
in newer GuC firmwares anyway.

Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505252197-27696-2-git-send-email-oscar.mateo@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915/guc: Name the default GuC scheduling policy

The default values for the default scheduling policy come from the
GuC firmware itself. Transform the magic numbers into defines.

Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505252197-27696-1-git-send-email-oscar.mateo@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Move the context descriptor to an inline helper

The context descriptor is stored inside the per-engine context state, as
we only need to compute it once and access it frequently. However,
currently only intel_lrc.c has easy access, but i915_guc_submission.c
would like to frequently read it as well, and more so only ever needs
the lower 32bits. Make it an inline as the compiler should be able to
retrieve the value in less instructions than it takes to do the function
call:

add/remove: 0/1 grow/shrink: 1/0 up/down: 8/-45 (-37)
function                                     old     new   delta
i915_guc_submit                              621     629      +8
intel_lr_context_descriptor                   45       -     -45

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170912214905.21987-1-chris@chris-wilson.co.uk
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>

drm/i915/dsi: Replace MIPI command error message with debug message

Error message indicating that the same MIPI command is sent
consecutively is perhaps too strongly said. Let's replace that as a
debug message instead.

Signed-off-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504252261-28964-3-git-send-email-mika.kahola@intel.com

drm/i915/cnp: set min brightness from VBT

Min brightness value from vbt was missing for CNP platform.
This setting have to refer backlight ic spec to restrict
min backlight output. Without this restriction, driver would
allow to configure lower brightness value and violate
backlight ic requirement.

Fixes: 4c9f7086ac6d ("drm/i915/cnp: Backlight support for CNP.")
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Shawn Lee <shawn.c.lee@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505279961-16140-1-git-send-email-shawn.c.lee@intel.com

Revert "drm/i915/bxt: Disable device ready before shutdown command"

This reverts commit bbdf0b2ff32a ("drm/i915/bxt: Disable device ready
before shutdown command").

Disable device ready before shutdown command was added previously to
avoid a split screen issue seen on dual link DSI panels. As of now, dual
link is not supported and will need some rework in the upstream
code. For single link DSI panels, the change is not required. This will
cause failure in sending SHUTDOWN packet during disable. Hence reverting
the change. Will handle the change as part of dual link enabling in
upstream.

Fixes: bbdf0b2ff32a ("drm/i915/bxt: Disable device ready before shutdown command")
Cc: <stable@vger.kernel.org> # v4.12+
Signed-off-by: Uma Shankar <uma.shankar@intel.com>
Signed-off-by: Vidya Srinivas <vidya.srinivas@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504604671-17237-1-git-send-email-vidya.srinivas@intel.com

drm/i915: Cleanup error paths through eb_lookup_vma()

Following the simplification to a single lookup loop in commit
170fa29b14fa ("drm/i915: Simplify eb_lookup_vmas()") and commit
d1b48c1e7184 ("drm/i915: Replace execbuf vma ht with an idr"), we can go
one step further and reorder the error paths so that the state of the
local variable obj is always known to the compiler and doesn't need the
uninitialized_var markup to squelch a compiler warning.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170912150752.20411-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>

drm/i915/spt+: Don't reset invalid AUX channel interrupt bits in SDEIMR

The SDE interrupt bits 25, 26 and 27 are either reserved or meant for
DDI E hotplug in SPT+. These bits are meant for AUX channels only in LPT
and CPT, so add the appropriate checks.

Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170909004255.14827-1-dhinakaran.pandiyan@intel.com

drm/i915: Name the IPS_PCODE_CONTROL bit

Give a name to the bit which tells pcode to control IPS.

v2: Note that IPS_CTL bits apply to DISPLAY_IPS_CONTROL as well (Chris)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170912153411.20171-2-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Nuke some bogus tabs from the pcode defines

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170912153411.20171-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Factor out setup_private_pat()

Factor out setup_private_pat() for introducing the following patches.

Signed-off-by: Zhi Wang <zhi.a.wang@intel.com>
Cc: Ben Widawsky <benjamin.widawsky@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ben Widawsky <benjamin.widawsky@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505202148-22959-1-git-send-email-zhi.a.wang@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915/bxt: set min brightness from VBT

Min brightness value from vbt was missing for BXT platform.
This setting have to refer backlight ic spec to restrict
min backlight output. Without this restriction, driver would
allow to configure lower brightness value and violate
backlight ic requirement.

Fixes: 0fb890c01349 ("drm/i915/bxt: BLC implementation")
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Cooper Chiou <cooper.chiou@intel.com>
Cc: Gary C Wang <gary.c.wang@intel.com>
Signed-off-by: Shawn Lee <shawn.c.lee@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1505187390-7039-1-git-send-email-shawn.c.lee@intel.com

drm/i915: Increase poll time for BDW FCLK_DONE

During IGT testing it has been shown that the specification
defined polling time of 1 us for FCLK_DONE, is sometimes not
enough. The issue is still reproducible while disabling
C-states through the PM QoS framework and also while disabling
preemtion. From this the most plausible explanation is that the
issue is due to a firmware flaw.
As a workaround, it is better to wait a little bit longer for
the FCLK_DONE to come around, than to leave with an DRM_ERROR
and having FCLK_DONE at a randome time after.
While spinning a list of igt tests prone to reproduce the issue
the FCLK_DONE poll failed at approximately 2% of the invocations
of the bdw_set_cdclk function. The longest poll time during this
testing was measured to ~7us. So, the suggested new poll time of
100us is on the safe side.

v2: Added more documentation about investigations done.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=102243
Signed-off-by: Marta Lofstedt <marta.lofstedt@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170908132829.6312-1-marta.lofstedt@intel.com

drm/i915/psr: Add enable_source vfunc.

Continue on VLV PSR split with vfunc, let's also create one
for enabling source.

Also since we are touching *_enable_source functions let's
fix a comment with wrong name for vlv's one.

v2: Fix typo on commit message (DK).

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-12-rodrigo.vivi@intel.com

drm/i915/psr: Add enable_sink vfunc.

Continue on VLV PSR split with vfunc, let's also create one
for enabling sink.

v2: Fix typo on commit message (DK).

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-11-rodrigo.vivi@intel.com

drm/i915/psr: Add setup VSC vfunc.

Continue on VLV PSR split with vfunc, let's also create
one for setting up VSC.

v2: Rebased on top of commit d2419ffc10e4 ("drm/i915: Plumb
    crtc_state to PSR enable/disable")

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-10-rodrigo.vivi@intel.com

drm/i915/psr: Re-org Activate after enable

Let's move the activation calls together after enable is done.

No real functional change should be expected here. Just an attempt
to get it clear when we are really activating PSR after enabling it.

v2: Add braces on if/else because commit message there is too long
    as suggested by Jani.
v3: Rebased on top of commit d2419ffc10e4 ("drm/i915: Plumb
    crtc_state to PSR enable/disable")

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-9-rodrigo.vivi@intel.com

drm/i915/psr: Move hsw_enable_source after enabling sink.

No functional change is expected here since at this point
PSR is not allowed to go to any active state. In other
words, not really enabled.

However let's do in a separated patch so it gets clear
on what is change and specially it can helps on bisect
case if we figure something has caused changes in behaviour.

But this needs to be done before we make the vfunc to
enable source to be in parity with VLV implementation.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-8-rodrigo.vivi@intel.com

drm/i915/psr: Re-create a hsw_psr_enable_source.

This sequence is part of enable source anyways, but they
only need to be executed once and not on every activation,
So let's re-create hsw_enable_source.

v2: Avoid changing order here to avoid changing behaviour
    as suggested by Jani.
v3: Rebased on top of commit d2419ffc10e4 ("drm/i915: Plumb
    crtc_state to PSR enable/disable")

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-7-rodrigo.vivi@intel.com

drm/i915/psr: Unify VSC setup functions.

VSC package is decided per eDP spec for psr1 or psr2,
and not per platform, so let's unify it and kill "skl"
func.

v2: Rebased on top of commit d2419ffc10e4 ("drm/i915: Plumb
    crtc_state to PSR enable/disable")

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-6-rodrigo.vivi@intel.com

drm/i915/psr: Add activate vfunc.

Continue on VLV PSR split with vfunc, let's move activate
function there.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-5-rodrigo.vivi@intel.com

drm/i915/psr: hsw_psr_activate.

On HSW+ the real activate of PSR is decided by the source
after certain amount of configured idle frames.

However for the driver perspective where we track psr.active
variable this function here is the actual activate one. So
let's rename it before moving to vfunc with that.

v2: Fix typo on commit message (DK).

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-4-rodrigo.vivi@intel.com

drm/i915/psr: vfunc for disabling source.

VLV/CHV has a total different PSR implementation than the
other platforms, so let's start moving that to vfuncs.
Let's start with disable_src one.

v2: Rebased on top of commit d2419ffc10e4 ("drm/i915: Plumb
    crtc_state to PSR enable/disable")

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-3-rodrigo.vivi@intel.com

drm/i915/psr: Avoid any PSR stuff on platforms without support.

We really don't want to setup vfuncs and lock mutexes on
platforms that has no support to PSR.

Also we know what platforms they are so let's do it quietly.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907230041.22978-2-rodrigo.vivi@intel.com

drm/i915: Fix an error handling in 'intel_framebuffer_init()'

We should go through the error handling path to decrease the
'framebuffer_references' as done everywhere else in this function.

Fixes: 2e2adb05736c ("drm/i915: Add render decompression support")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170910085642.13673-1-christophe.jaillet@wanadoo.fr

drm/i915: Only initialize partially filled pagetables

If we know that we will completely fill a pagetable (i.e. we are
inserting a complete set of 512 pages), we can skip prefilling that PT
with scratch entries. If we have to abort the insertion prior to writing
the real entries, we will teardown the pagetable and remove it from the
page directory (so that we will restart the allocation next time).

We could do similar tricks for the PD and PDP, but the likelihood of a
single insertion covering the entire 512 entries diminishes, as do the
cycle savings. The saving are even greater (relatively) when we are
preallocating page tables for huge pages, as then we never need to fill
the page table.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170908181622.17791-1-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>

drm/i915: Make PAT macros more robust

Macro params shall be wrapped into () to avoid unexpected results.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170908161130.22424-1-michal.wajdeczko@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Add a default case in gen7 hwsp switch-case

Gen7 won't get any new engines, and we already added VCS2 there to just
silence gcc's not handled in switch warnings.

Use a default case instead, otherwise we will need to keep adding extra
cases if changes happen in the future.

v2: Since reaching the default case is impossible, use GEM_BUG_ON (Chris).

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170830180115.907-1-michel.thierry@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

Merge tag 'gvt-next-2017-09-08' of https://github.com/01org/gvt-linux into drm-intel-next-queued

gvt-next-2017-09-08

- PCI config sanitize series (Changbin)
- Workload submission error handling series (Fred)

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170908063155.l54lvpivxntjm7hq@zhen-hp.sh.intel.com

drm/i915/gvt: Add support for PCIe extended configuration space

IGD is PCIe device and has extended configuration space. Checking
the binary dump, we can see we have Caps located out of PCI compatible
Configuration Space range.

0x000: 86 80 12 19 17 04 10 00 06 00 00 03 00 00 00 00
0x010: 04 00 00 10 08 00 00 00 0c 00 00 00 08 00 00 00
0x020: 00 00 00 00 00 00 00 00 00 00 00 00 28 10 b9 06
0x030: 00 f8 ff ff 40 00 00 00 00 00 00 00 0b 01 00 00
0x040: 09 70 0c 01 71 26 01 62 c8 00 04 84 00 00 00 00
0x050: c1 00 00 00 39 00 00 00 00 00 00 00 01 00 00 a2
0x060: 00 00 01 00 00 00 00 00 00 00 00 00 00 00 00 00
0x070: 10 ac 92 00 00 80 00 10 00 00 00 00 00 00 00 00
0x080: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x090: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0a0: 00 00 00 00 00 00 00 00 00 00 00 00 05 d0 01 00
0x0b0: 18 00 e0 fe 00 00 00 00 00 00 00 00 00 00 00 00
0x0c0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x0d0: 01 00 22 00 00 80 00 00 00 00 00 00 00 00 00 00
0x0e0: 00 00 00 00 00 00 00 00 00 80 00 00 00 00 00 00
0x0f0: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00
0x100: 1b 00 01 20 02 14 00 00 00 00 00 00 00 00 00 00
...

Currently, we only emulate the PCI compatible Configuration Space.
This is okay if we attach vGPU to PCI bus. But when we attach to
a PCI Express bus (when Qemu emulates a Intel Q35 chipset which has
PCIe slot), it will not work. Extended Configuration Space is required
for a PCIe device.

This patch extended the virtual configuration space from 256 bytes
to 4KB bytes. So we are to be a *real* PCIe device. And for the
Extended CapList we keep same to physical GPU.

Cc: Laszlo Ersek <lersek@redhat.com>
Tested-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Fix incorrect PCI BARs reporting

Looking at our virtual PCI device, we can see surprising Region 4 and Region 5.
00:10.0 VGA compatible controller: Intel Corporation Sky Lake Integrated Graphics (rev 06) (prog-if 00 [VGA controller])
        ....
        Region 0: Memory at 140000000 (64-bit, non-prefetchable) [size=16M]
        Region 2: Memory at 180000000 (64-bit, prefetchable) [size=1G]
        Region 4: Memory at <ignored> (32-bit, non-prefetchable)
        Region 5: Memory at <ignored> (32-bit, non-prefetchable)
        Expansion ROM at febd6000 [disabled] [size=2K]

The fact is that we only implemented BAR0 and BAR2. Surprising Region 4 and
Region 5 are shown because we report their size as 0xffffffff. They should
report size 0 instead.

BTW, the physical GPU has a PIO BAR. GVTg hasn't implemented PIO access, so
we ignored this BAR for vGPU device.

v2: fix BAR size value calculation.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=1458032
Signed-off-by: Changbin Du <changbin.du@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Refine error handling for perform_bb_shadow

fix the wrong return type and return error once the unknown
command is scanned.

v2:
- separate this error handle from healthy rating code. (Zhenyu)

Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Refine error handling in dispatch_workload

When an error occurs in dispatch_workload, this patch is to do the
proper cleanup and rollback to the original states before the workload
is abandoned.

v2:
- split the mixed several error paths for better review. (Zhenyu)

v3:
- original PTR_ERR(cs) is good and code cleanup. (Zhenyu)

v4:
- reuse the existing i915_add_request for error handling. (Zhenyu)

v5:
- remove the duplicate error handling release_shadow_wa_ctx and
  move the engine->context_unpin upper. (Zhenyu)

v6:
- keep the old label "out". (Zhenyu)

Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Refine error handling for intel_vgpu_pin_mm

When it is failed in shadow_mm, the pin_count should rollback
to the original states before return.

v2:
- split the mixed several error paths for better review. (Zhenyu)

v3:
  increase the pincount after shadow success. (Zhenyu)

Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Refine error handling for prepare_execlist_workload

refine the error handling for prepare_execlist_workload to restore to the
original states once error occurs.

only release the shadowed batch buffer and wa ctx when the workload is
completed successfully.

v2:
- split the mixed several error paths for better review. (Zhenyu)

v3:
- handle prepare batch buffer/wa ctx pin errors and
- emulate_schedule_in null issue. (Zhenyu)

v4:
- no need to handle emulate_schedule_in null issue. (Zhenyu)

v5:
- release the shadowed batch buffer and wa ctx only for the
  successful workload. (Zhenyu)

v6:
- polish the return style. (Zhenyu)

Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Add error handling for intel_gvt_scan_and_shadow_workload

When an error occurs after shadow_indirect_ctx, this patch is to do the
proper cleanup and rollback to the original states for shadowed indirect
context before the workload is abandoned.

v2:
- split the mixed several error paths for better review. (Zhenyu)

v3:
- no return check for clean up functions. (Changbin)

v4:
- expose and reuse the existing release_shadow_wa_ctx. (Zhenyu)

v5:
- move the release function to scheduler.c file. (Zhenyu)

v6:
- move error handling code of intel_gvt_scan_and_shadow_workload
  to here. (Zhenyu)

Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Separate cmd scan from request allocation

Currently i915 request structure and shadow ring buffer are allocated
before command scan, so it will have to restore to previous states once
any error happens afterwards in the long dispatch_workload path.

This patch is to introduce a reserved ring buffer created at the beginning
of vGPU initialization. Workload will be coped to this reserved buffer and
be scanned first, the i915 request and shadow ring buffer are only
allocated after the result of scan is successful.

To balance the memory usage and buffer alloc time, the coming bigger ring
buffer will be reallocated and kept until more bigger buffer is coming.

v2:
- use kmalloc for the smaller ring buffer, realloc if required. (Zhenyu)

v3:
- remove the dynamically allocated ring buffer. (Zhenyu)

v4:
- code style polish.
- kfree previous allocated buffer once kmalloc failed. (Zhenyu)

Signed-off-by: fred gao <fred.gao@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/gvt: Add emulation for BAR2 (aperture) with normal file RW approach

For vfio-pci, if the region support MMAP then it should support both
mmap and normal file access. The user-space is free to choose which is
being used. For qemu, we just need add 'x-no-mmap=on' for vfio-pci
option.

Currently GVTg only support MMAP for BAR2. So GVTg will not work when
user turn on x-no-mmap option.

This patch added file style access for BAR2, aka the GPU aperture. We
map the entire aperture partition of active vGPU to kernel space when
guest driver try to enable PCI Memory Space. Then we redirect the file
RW operation from kvmgt to this mapped area.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=1458032
Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915/kvmgt: Sanitize PCI bar emulation

For PCI, 64bit bar consumes two BAR registers, but this doesn't mean
both of two BAR are valid. Actually the second BAR is regarded as
reserved in this case. So we shouldn't emulate the second BAR.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>

drm/i915: Transform WaDisablePooledEuLoadBalancingFix into a simple register write

FF_SLICE_CS_CHICKEN2 does not belong to the context image.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504798809-5653-6-git-send-email-oscar.mateo@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Transform WaDisableDynamicCreditSharing into a simple register write

GAMT_CHKN_BIT_REG does not live in the context image.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504798809-5653-5-git-send-email-oscar.mateo@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Transform WaDisableGafsUnitClkGating into a simple reg write

GEN7_UCGCTL4 does not live in the context.

v2: Missing parenthesis

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504798809-5653-4-git-send-email-oscar.mateo@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: WaPushConstantDereferenceHoldDisable needs to modify a masked register

So do it correctly.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504798809-5653-3-git-send-email-oscar.mateo@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Transform WaDisableI2mCycleOnWRPort into a simple reg write

GAMT_CHKN_BIT_REG does not live in the context.

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504798809-5653-2-git-send-email-oscar.mateo@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Transform WaInPlaceDecompressionHang into a simple reg write

Afaict, GEN9_GAMT_ECO_REG_RW_IA does not live in the context, so writing
it on every context creation is overkill (and wrong).

v2: Missing end parenthesis

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1504798809-5653-1-git-send-email-oscar.mateo@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Apply the GTT write flush for all !llc machines

We also see the delayed GTT write issue on i915g/i915gm, so let's
presume that it is a universal problem for all !llc machines, and that we
just haven't yet noticed on g33, gen4 and gen5 machines.

v2: Use a register that exists on all platforms

Testcase: igt/gem_mmap_gtt/coherency # i915gm
References: https://bugs.freedesktop.org/show_bug.cgi?id=102577
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907184520.5032-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>

i915: Fix obj size vs. alignment for drm_pci_alloc()

drm_pci_alloc() refuses to cooperate if the passed alignment exceeds the
object size. So round up the obj size to the next power of two as well
to make this actually work.

Obviously things work just fine as long as the size was a power of two
to begin with. However kms_cursor_crc doesn't always use power of two
sizes so we hit a failure when we try to allocate the phys memory.

Testcase: igt/kms_cursor_crc
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907143203.13055-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>

drm/i915: Disable mmio debugging during user access

If the user bypasses i915 and accesses mmio directly, that easily
confuses our automatic mmio debugging (any error we then detect is
likely to be as a result of the user). Since we expect userspace to open
debugfs/i915_forcewake_user if i915.ko is loaded and they want mmio
access, that makes the opportune time to disable our debugging for
duration of the bypass.

v2: Move the fiddling of uncore internals to uncore.c

References: https://bugs.freedesktop.org/show_bug.cgi?id=102543
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170907134441.12881-1-chris@chris-wilson.co.uk

drm/i915/skl+: debugfs entry to control IPC

This patch creates an entry in debugfs to check the status of IPC.
This can also be used to enable/disable IPC in supported platforms.

Changes since V1:
 - fix use of HAS_IPC
 - use kstrtobool_from_user (Maarten)
 - drm_info log, while enabling IPC (Maarten)

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-9-mahesh1.kumar@intel.com
[mlankhorst: enableddisabled -> yesno to match ipc write]

drm/i915/bxt+: Enable IPC support

This patch adds IPC support. This patch also enables IPC in all supported
platforms based on has_ipc flag.
IPC (Isochronous Priority Control) is the hardware feature, which
dynamically controls the memory read priority of Display.

When IPC is enabled, plane read requests are sent at high priority until
filling above the transition watermark, then the requests are sent at
lower priority until dropping below the level 0 watermark.
The lower priority requests allow other memory clients to have better
memory access. When IPC is disabled, all plane read requests are sent at
high priority.

Changes since V1:
 - Remove commandline parameter to disable ipc
 - Address Paulo's comments
Changes since V2:
 - Address review comments
 - Set ipc_enabled flag
Changes since V3:
 - move ipc_enabled flag assignment inside intel_ipc_enable function
Changes since V4:
 - Re-enable IPC after suspend/resume
Changes since V5:
 - Enable IPC for all gen >=9 except SKL
Changes since V6:
 - fix commit msg
 - after resume program IPC based on SW state.
Changes since V7:
 - Modify IPC support check based on HAS_IPC macro (suggested by Chris)

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-8-mahesh1.kumar@intel.com

drm/i915/gen9+: Add has_ipc flag in device info structure

New Isochronous Priority Control (IPC) capability is introduced in newer
GEN platforms. This patch adds a device info flag to indicate if platform
supports IPC. Patch also sets this flag in supported platforms.

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-7-mahesh1.kumar@intel.com

drm/i915/cnl: Extend WM workaround with IPC for CNL

CNL:A & CNL:B have same workaround as KBL to increase wm level latency
by 4us if IPC is enabled.

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-6-mahesh1.kumar@intel.com

drm/i915/glk: IPC linetime watermark workaround for GLK

IF IPC is enabled LINETIME_WM value should be half of calculated value
 line time = ROUNDDOWN(1/2 * Calculated Line Time)

Earlier code was rounding-up the value, But updated Bspec says we should
take the ROUNDDOWN. This patch corrects that as well.

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-5-mahesh1.kumar@intel.com

drm/i915/gen10: Calculate and enable transition WM

GEN > 9 require transition WM to be programmed if IPC is enabled.
This patch calculates & enable transition WM for supported platforms.
If transition WM is enabled, Plane read requests are sent at high
priority until filling above the transition watermark, then the
requests are sent at lower priority until dropping below the level-0 WM.
The lower priority requests allow other memory clients to have better
memory access.

transition minimum is the minimum amount needed for trans_wm to work to
ensure  the demote does not happen before enough data has been read to
meet the level 0 watermark requirements.

transition amount is configurable value. Higher values will
tend to cause longer periods of high priority reads followed by longer
periods of lower priority reads. Tuning to lower values will tend to
cause shorter periods of high and lower priority reads.

Keeping transition amount to 10 in this patch, as suggested by HW team.

Changes since V1:
 - Address review comments from Maarten

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-4-mahesh1.kumar@intel.com

drm/i915/skl+: Optimize WM calculation

Plane configuration parameters doesn't change for each WM-level
calculation. Currently we compute same parameters 8 times for each
wm-level.
This patch optimizes it by calculating these parameters in beginning
& reuse during each level-wm calculation.

Changes since V1:
 - rebase on top of Rodrigo's series for CNL

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-3-mahesh1.kumar@intel.com

drm/i915: Fixed point fixed16 wrapper cleanup

As per suggestion from Jani, cleanup the code. Cleanup includes
 - Instead of left shifting & check, compare with U32/16_MAX
 - Use typecast instead of clamp_t

Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170817134529.2839-2-mahesh1.kumar@intel.com

tools/testing/scatterlist: Test new __sg_alloc_table_from_pages

Exercise the new __sg_alloc_table_from_pages API (and through
it also the old sg_alloc_table_from_pages), checking that the
created table has the expected number of segments depending on
the sequence of input pages and other conditions.

v2: Move to data driven for readability.
v3: Add some more testcases and -fsanitize=undefined. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20170906145506.14952-1-tvrtko.ursulin@linux.intel.com
[tursulin: whitespace fixup]

drm/i915: Use __sg_alloc_table_from_pages for userptr allocations

With the addition of __sg_alloc_table_from_pages we can control
the maximum coalescing size and eliminate a separate path for
allocating backing store here.

Similar to 871dfbd67d4e ("drm/i915: Allow compaction upto
SWIOTLB max segment size") this enables more compact sg lists to
be created and so has a beneficial effect on workloads with many
and/or large objects of this class.

v2:
 * Rename helper to i915_sg_segment_size and fix swiotlb override.
 * Commit message update.

v3:
 * Actually include the swiotlb override fix.

v4:
 * Regroup parameters a bit. (Chris Wilson)

v5:
 * Rebase for swiotlb_max_segment.
 * Add DMA map failure handling as in abb0deacb5a6
   ("drm/i915: Fallback to single PAGE_SIZE segments for DMA remapping").

v6: Handle swiotlb_max_segment() returning 1. (Joonas Lahtinen)

v7: Rebase.
v8: Commit spelling fix.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170803091417.23677-1-tvrtko.ursulin@linux.intel.com

lib/scatterlist: Introduce and export __sg_alloc_table_from_pages

Drivers like i915 benefit from being able to control the maxium
size of the sg coalesced segment while building the scatter-
gather list.

Introduce and export the __sg_alloc_table_from_pages function
which will allow it that control.

v2: Reorder parameters. (Chris Wilson)
v3: Fix incomplete reordering in v2.
v4: max_segment needs to be page aligned.
v5: Rebase.
v6: Rebase.
v7: Fix spelling in commit and mention max segment size in
    __sg_alloc_table_from_pages kerneldoc. (Andrew Morton)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: linux-kernel@vger.kernel.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20170803091351.23594-1-tvrtko.ursulin@linux.intel.com

lib/scatterlist: Avoid potential scatterlist entry overflow

Since the scatterlist length field is an unsigned int, make
sure that sg_alloc_table_from_pages does not overflow it while
coalescing pages to a single entry.

v2: Drop reference to future use. Use UINT_MAX.
v3: max_segment must be page aligned.
v4: Do not rely on compiler to optimise out the rounddown.
    (Joonas Lahtinen)
v5: Simplified loops and use post-increments rather than
    pre-increments. Use PAGE_MASK and fix comment typo.
    (Andy Shevchenko)
v6: Commit spelling fix.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: linux-kernel@vger.kernel.org
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170803091312.22875-1-tvrtko.ursulin@linux.intel.com

lib/scatterlist: Fix offset type in sg_alloc_table_from_pages

Scatterlist entries have an unsigned int for the offset so
correct the sg_alloc_table_from_pages function accordingly.

Since these are offsets withing a page, unsigned int is
wide enough.

Also converts callers which were using unsigned long locally
with the lower_32_bits annotation to make it explicitly
clear what is happening.

v2: Use offset_in_page. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Pawel Osciak <pawel@osciak.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Cc: Tomasz Stanislawski <t.stanislaws@samsung.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: linux-media@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com> (v1)
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170731185512.20010-1-tvrtko.ursulin@linux.intel.com

drm/i915: Disable snooping (userptr, set-cache-level) on gen4

The original gen4 has an issue where writes (both render and blt) into
snoopable pages are lost. We've previously worked around this in
userspace (ddx, igt) by simply not requesting snoopable buffers, but upon
rediscovering this problem for a third time, make the kernel reject such
requests with -ENODEV.

This disables snooping on userspace buffers for i965g and i965gm (original
gen4) machines.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170906192424.26970-1-chris@chris-wilson.co.uk

drm/i915: Update DRIVER_DATE to 20170907

Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

drm/i915/cnl: WaThrottleEUPerfToAvoidTDBackPressure:cnl(pre-prod)

Wa for B-stepping only.

A for a hang issue that requires throttling EU performace
to 12.5% to avoid back pressure to thread dispatch

v2: Rebased. No change from v1.

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20170906220325.24524-1-rodrigo.vivi@intel.com