intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: "Kumar, Mahesh" <mahesh1.kumar@intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: paulo.r.zanoni@intel.com
Subject: [PATCH v3 0/9] New DDB Algo and WM fixes
Date: Fri,  9 Sep 2016 13:30:57 +0530	[thread overview]
Message-ID: <20160909080106.17506-1-mahesh1.kumar@intel.com> (raw)

From: Mahesh Kumar <mahesh1.kumar@intel.com>

This series implements new DDB allocation algorithm to solve the cases,
where we have sufficient DDB available to enable multiple planes, But
due to the current algorithm not dividing it properly among planes, we
end-up failing the flip.
It also takes care of enabling same watermark level for each
plane, for efficient power saving.
This series also implements Transition Watermarks and Gen-9 related
arbitrated display bandwidth Workarounds.

There are two steps in current WM programming.

1. Calculate minimum number of blocks required  for a WM level to be
enabled. For 1440x2560 panel we need 41 blocks as minimum number of
blocks to enable WM0. This is the step which doesn't use vertical size.
It only depends on Pipe drain rate and plane horizontal size as per the
current Bspec algorithm.
So all the plane below have minimum  number of blocks required to enable
WM0 as 41
    Plane 1  - 1440x2560        -    Min blocks to enable WM0 = 41
    Plane 2  - 1440x2560        -    Min blocks to enable WM0 = 41
    Plane 3  - 1440x48          -    Min blocks to enable WM0 = 41
    Plane 4  - 1440x96          -    Min blocks to enable WM0 = 41

2. Number of blocks allotted by the driver
    Driver allocates  12 for Plane 3   &  16 for plane 4

    Total Dbuf Available = 508
    Dbuf Available after 32 blocks for cursor = 508 - (32)  = 476
    allocate minimum blocks for each plane 8 * 4 = 32
    remaining blocks = 476 - 32 = 444
    Relative Data Rate for Planes
       Plane 1  =  1440 * 2560 * 3  =  11059200
       Plane 2  =  1440 * 2560 * 3  =  11059200
       Plane 3  =  1440 * 48   * 3  =  207360
       Plane 4  =  1440 * 96   * 3  =  414720
       Total Relative BW            =  22740480

-   Allocate Buffer
    buffer allocation = (Plane relative data rate / total data rate)
		    * total remaming DDB + minimum plane DDB
     Plane 1  buffer allocation = (11059200 / 22740480) * 444 + 8 = 223
     Plane 2  buffer allocation = (11059200 / 22740480) * 444 + 8 = 223
     Plane 3  buffer allocation = (207360   / 22740480) * 444 + 8 = 12
     Plane 4  buffer allocation = (414720   / 22740480) * 444 + 8 = 16

In this case it forced driver to disable Plane 3 & 4. Driver need to use
more efficient way to allocate buffer that is optimum for power.

New Algorithm suggested by HW team is:

1. Calculate minimum buffer allocations for each plane and for each
    watermark level

2. Add minimum buffer allocations required for enabling WM7
    for all the planes

Level 0 =  41 + 41 + 41 + 41  = 164
Level 1 =  42 + 42 + 42 + 42  = 168
Level 2 =  42 + 42 + 42 + 42  = 168
Level 3 =  94 + 94 + 94 + 94 =  376
Level 4 =  94 + 94 + 94 + 94 =  376
Level 5 =  94 + 94 + 94 + 94 =  376
Level 6 =  94 + 94 + 94 + 94 =  376
Level 7 =  94 + 94 + 94 + 94 =  376

3. Check to see how many buffer allocation are left and enable
the best case. In this case since we have 476 blocks we can enable
WM0-7 on all 4 planes.
Let's say if we have only 200 block available then the best cases
allocation is to enable Level2 which requires 168 blocks

Changes since v1:
 - Rebased the series on top of Paulo's patches (under review)
    https://patchwork.freedesktop.org/series/12082/
 - Add changes to calculate WM in fixed point 16.16
 - Address review comments for Transition WM
Changes since v2:
 - Added Paulo's WM fixes series URL in cover letter

Mahesh Kumar (9):
  drm/i915/skl: pass pipe_wm in skl_compute_(wm_level/plane_wm)
    functions
  drm/i915/skl+: use linetime latency instead of ddb size
  drm/i915/skl: New ddb allocation algorithm
  drm/i915: Decode system memory bandwidth
  drm/i915/gen9: WM memory bandwidth related workaround
  drm/i915/skl+: change WM calc to fixed point 16.16
  drm/i915/bxt: Enable IPC support
  drm/i915/bxt: set chicken bit as IPC y-tile WA
  drm/i915/bxt: Implement Transition WM

 drivers/gpu/drm/i915/i915_drv.c      | 101 +++++++++
 drivers/gpu/drm/i915/i915_drv.h      |  29 +++
 drivers/gpu/drm/i915/i915_params.c   |   5 +
 drivers/gpu/drm/i915/i915_params.h   |   1 +
 drivers/gpu/drm/i915/i915_reg.h      |  29 +++
 drivers/gpu/drm/i915/intel_display.c |  50 +++++
 drivers/gpu/drm/i915/intel_drv.h     |  12 +
 drivers/gpu/drm/i915/intel_pm.c      | 412 +++++++++++++++++++++++++++--------
 8 files changed, 551 insertions(+), 88 deletions(-)

-- 
2.8.3

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx

             reply	other threads:[~2016-09-09  7:57 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-09-09  8:00 Kumar, Mahesh [this message]
2016-09-09  8:00 ` [PATCH v3 1/9] drm/i915/skl: pass pipe_wm in skl_compute_(wm_level/plane_wm) functions Kumar, Mahesh
2016-09-20 12:17   ` Paulo Zanoni
2016-09-21 13:48     ` Mahesh Kumar
2016-09-21 13:59       ` Paulo Zanoni
2016-09-09  8:00 ` [PATCH v3 2/9] drm/i915/skl+: use linetime latency instead of ddb size Kumar, Mahesh
2016-09-12  8:56   ` Maarten Lankhorst
2016-09-19 18:19   ` Paulo Zanoni
2016-09-19 18:24     ` Zanoni, Paulo R
2016-09-22  8:02       ` Mahesh Kumar
2016-09-09  8:01 ` [PATCH v3 3/9] drm/i915/skl: New ddb allocation algorithm Kumar, Mahesh
2016-09-12 10:50   ` Maarten Lankhorst
2016-09-12 13:11   ` Maarten Lankhorst
2016-09-13  6:21     ` Mahesh Kumar
2016-09-13 12:15     ` [PATCH v4] " Kumar, Mahesh
2016-09-13 12:40       ` Maarten Lankhorst
2016-09-14 12:36         ` Mahesh Kumar
2016-09-19  8:27           ` Maarten Lankhorst
2016-09-19  9:55           ` Maarten Lankhorst
2016-09-21 13:03             ` Mahesh Kumar
2016-09-09  8:01 ` [PATCH v3 4/9] drm/i915: Decode system memory bandwidth Kumar, Mahesh
2016-09-16  8:02   ` Pandiyan, Dhinakaran
2016-09-16 11:35     ` Mahesh Kumar
2016-09-19 20:41   ` Paulo Zanoni
2016-09-09  8:01 ` [PATCH v3 5/9] drm/i915/gen9: WM memory bandwidth related workaround Kumar, Mahesh
2016-09-12 11:02   ` Maarten Lankhorst
2016-09-12 11:12     ` Maarten Lankhorst
2016-09-09  8:01 ` [PATCH v3 6/9] drm/i915/skl+: change WM calc to fixed point 16.16 Kumar, Mahesh
2016-09-21 18:32   ` Paulo Zanoni
2016-09-22  9:25     ` Mahesh Kumar
2016-09-09  8:01 ` [PATCH v3 7/9] drm/i915/bxt: Enable IPC support Kumar, Mahesh
2016-09-21 20:06   ` Paulo Zanoni
2016-09-22 10:14     ` Mahesh Kumar
2016-09-09  8:01 ` [PATCH v3 8/9] drm/i915/bxt: set chicken bit as IPC y-tile WA Kumar, Mahesh
2016-09-21 20:23   ` Paulo Zanoni
2016-09-22  9:43     ` Mahesh Kumar
2016-09-22 11:53       ` Paulo Zanoni
2016-09-09  8:01 ` [PATCH v3 9/9] drm/i915/bxt: Implement Transition WM Kumar, Mahesh
2016-09-14 11:54   ` [PATCH v4] " Kumar, Mahesh
2016-09-21 20:27     ` Paulo Zanoni

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20160909080106.17506-1-mahesh1.kumar@intel.com \
    --to=mahesh1.kumar@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=paulo.r.zanoni@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).