All of lore.kernel.org
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Subject: [PATCH 42/46] drm/i915: Enlarge vma->pin_count
Date: Mon,  7 Jan 2019 11:55:05 +0000	[thread overview]
Message-ID: <20190107115509.12523-42-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20190107115509.12523-1-chris@chris-wilson.co.uk>

Previously we only accommodated having a vma pinned by a small number of
users, with the maximum being pinned for use by the display engine. As
such, we used a small bitfield only large enough to allow the vma to
be pinned twice (for back/front buffers) in each scanout plane. Keeping
the maximum permissible pin_count small allows us to quickly catch a
potential leak. However, as we want to split a 4096B page into 64
different cachelines and pin each cacheline for use by a different
timeline, we will exceed the current maximum permissible vma->pin_count
and so time has come to enlarge it.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_gem_gtt.h | 26 +++++++++++++-------------
 drivers/gpu/drm/i915/i915_vma.h     | 28 +++++++++-------------------
 2 files changed, 22 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index bd679c8c56dd..03ade71b8d9a 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -642,19 +642,19 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 
 /* Flags used by pin/bind&friends. */
 #define PIN_NONBLOCK		BIT_ULL(0)
-#define PIN_MAPPABLE		BIT_ULL(1)
-#define PIN_ZONE_4G		BIT_ULL(2)
-#define PIN_NONFAULT		BIT_ULL(3)
-#define PIN_NOEVICT		BIT_ULL(4)
-
-#define PIN_MBZ			BIT_ULL(5) /* I915_VMA_PIN_OVERFLOW */
-#define PIN_GLOBAL		BIT_ULL(6) /* I915_VMA_GLOBAL_BIND */
-#define PIN_USER		BIT_ULL(7) /* I915_VMA_LOCAL_BIND */
-#define PIN_UPDATE		BIT_ULL(8)
-
-#define PIN_HIGH		BIT_ULL(9)
-#define PIN_OFFSET_BIAS		BIT_ULL(10)
-#define PIN_OFFSET_FIXED	BIT_ULL(11)
+#define PIN_NONFAULT		BIT_ULL(1)
+#define PIN_NOEVICT		BIT_ULL(2)
+#define PIN_MAPPABLE		BIT_ULL(3)
+#define PIN_ZONE_4G		BIT_ULL(4)
+#define PIN_HIGH		BIT_ULL(5)
+#define PIN_OFFSET_BIAS		BIT_ULL(6)
+#define PIN_OFFSET_FIXED	BIT_ULL(7)
+
+#define PIN_MBZ			BIT_ULL(8) /* I915_VMA_PIN_OVERFLOW */
+#define PIN_GLOBAL		BIT_ULL(9) /* I915_VMA_GLOBAL_BIND */
+#define PIN_USER		BIT_ULL(10) /* I915_VMA_LOCAL_BIND */
+#define PIN_UPDATE		BIT_ULL(11)
+
 #define PIN_OFFSET_MASK		(-I915_GTT_PAGE_SIZE)
 
 #endif
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 7252abc73d3e..266b226ebef2 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -70,30 +70,20 @@ struct i915_vma {
 	 */
 	unsigned int open_count;
 	unsigned long flags;
-	/**
-	 * How many users have pinned this object in GTT space. The following
-	 * users can each hold at most one reference: pwrite/pread, execbuffer
-	 * (objects are not allowed multiple times for the same batchbuffer),
-	 * and the framebuffer code. When switching/pageflipping, the
-	 * framebuffer code has at most two buffers pinned per crtc.
-	 *
-	 * In the worst case this is 1 + 1 + 1 + 2*2 = 7. That would fit into 3
-	 * bits with absolutely no headroom. So use 4 bits.
-	 */
-#define I915_VMA_PIN_MASK 0xf
-#define I915_VMA_PIN_OVERFLOW	BIT(5)
+#define I915_VMA_PIN_MASK 0xff
+#define I915_VMA_PIN_OVERFLOW	BIT(8)
 
 	/** Flags and address space this VMA is bound to */
-#define I915_VMA_GLOBAL_BIND	BIT(6)
-#define I915_VMA_LOCAL_BIND	BIT(7)
+#define I915_VMA_GLOBAL_BIND	BIT(9)
+#define I915_VMA_LOCAL_BIND	BIT(10)
 #define I915_VMA_BIND_MASK (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND | I915_VMA_PIN_OVERFLOW)
 
-#define I915_VMA_GGTT		BIT(8)
-#define I915_VMA_CAN_FENCE	BIT(9)
-#define I915_VMA_CLOSED		BIT(10)
-#define I915_VMA_USERFAULT_BIT	11
+#define I915_VMA_GGTT		BIT(11)
+#define I915_VMA_CAN_FENCE	BIT(12)
+#define I915_VMA_CLOSED		BIT(13)
+#define I915_VMA_USERFAULT_BIT	14
 #define I915_VMA_USERFAULT	BIT(I915_VMA_USERFAULT_BIT)
-#define I915_VMA_GGTT_WRITE	BIT(12)
+#define I915_VMA_GGTT_WRITE	BIT(15)
 
 	unsigned int active_count;
 	struct rb_root active;
-- 
2.20.1

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

  parent reply	other threads:[~2019-01-07 11:55 UTC|newest]

Thread overview: 111+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-01-07 11:54 [PATCH 01/46] drm/i915: Return immediately if trylock fails for direct-reclaim Chris Wilson
2019-01-07 11:54 ` [PATCH 02/46] drm/i915: Report the number of closed vma held by each context in debugfs Chris Wilson
2019-01-07 12:35   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 03/46] drm/i915: Track all held rpm wakerefs Chris Wilson
2019-01-07 13:14   ` Mika Kuoppala
2019-01-07 13:22     ` Chris Wilson
2019-01-08 11:45   ` [PATCH v2] " Chris Wilson
2019-01-08 12:22   ` [PATCH v3] " Chris Wilson
2019-01-08 12:49     ` Mika Kuoppala
2019-01-08 20:05     ` kbuild test robot
2019-01-07 11:54 ` [PATCH 04/46] drm/i915: Markup paired operations on wakerefs Chris Wilson
2019-01-08 16:23   ` Mika Kuoppala
2019-01-08 16:41     ` Chris Wilson
2019-01-09  9:23       ` Mika Kuoppala
2019-01-09 11:51         ` Chris Wilson
2019-01-09 23:33           ` John Harrison
2019-01-07 11:54 ` [PATCH 05/46] drm/i915: Track GT wakeref Chris Wilson
2019-01-09  9:52   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 06/46] drm/i915: Track the rpm wakerefs for error handling Chris Wilson
2019-01-09 10:12   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 07/46] drm/i915: Mark up sysfs with rpm wakeref tracking Chris Wilson
2019-01-09 10:13   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 08/46] drm/i915: Mark up debugfs " Chris Wilson
2019-01-09 10:20   ` Mika Kuoppala
2019-01-09 11:49     ` Chris Wilson
2019-01-07 11:54 ` [PATCH 09/46] drm/i915/perf: Track the rpm wakeref Chris Wilson
2019-01-09 10:30   ` Mika Kuoppala
2019-01-09 11:45     ` Chris Wilson
2019-01-07 11:54 ` [PATCH 10/46] drm/i915/pmu: Track " Chris Wilson
2019-01-09 10:37   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 11/46] drm/i915/guc: Track the " Chris Wilson
2019-01-09 10:53   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 12/46] drm/i915/gem: Track the rpm wakerefs Chris Wilson
2019-01-09 11:16   ` Mika Kuoppala
2019-01-09 23:45     ` John Harrison
2019-01-07 11:54 ` [PATCH 13/46] drm/i915/fb: Track " Chris Wilson
2019-01-09 11:39   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 14/46] drm/i915/hotplug: Track temporary rpm wakeref Chris Wilson
2019-01-09 11:40   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 15/46] drm/i915/panel: " Chris Wilson
2019-01-09 11:41   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 16/46] drm/i915/selftests: Mark up rpm wakerefs Chris Wilson
2019-01-09 12:54   ` Mika Kuoppala
2019-01-07 11:54 ` [PATCH 17/46] drm/i915: Syntatic sugar for using intel_runtime_pm Chris Wilson
2019-01-09 14:30   ` Mika Kuoppala
2019-01-10  0:24   ` John Harrison
2019-01-10  1:10     ` John Harrison
2019-01-10  9:59       ` Chris Wilson
2019-01-07 11:54 ` [PATCH 18/46] drm/i915: Markup paired operations on display power domains Chris Wilson
2019-01-10  0:55   ` John Harrison
2019-01-10 10:00     ` Chris Wilson
2019-01-07 11:54 ` [PATCH 19/46] drm/i915: Track the wakeref used to initialise " Chris Wilson
2019-01-07 11:54 ` [PATCH 20/46] drm/i915: Combined gt.awake/gt.power wakerefs Chris Wilson
2019-01-07 11:54 ` [PATCH 21/46] drm/i915/dp: Markup pps lock power well Chris Wilson
2019-01-07 11:54 ` [PATCH 22/46] drm/i915: Complain if hsw_get_pipe_config acquires the same power well twice Chris Wilson
2019-01-07 11:54 ` [PATCH 23/46] drm/i915: Mark up Ironlake ips with rpm wakerefs Chris Wilson
2019-01-07 11:54 ` [PATCH 24/46] drm/i915: Serialise concurrent calls to i915_gem_set_wedged() Chris Wilson
2019-01-07 11:54 ` [PATCH 25/46] drm/i915: Differentiate between ggtt->mutex and ppgtt->mutex Chris Wilson
2019-01-08  9:00   ` Tvrtko Ursulin
2019-01-07 11:54 ` [PATCH 26/46] drm/i915: Pull all the reset functionality together into i915_reset.c Chris Wilson
2019-01-07 11:54 ` [PATCH 27/46] drm/i915: Make all GPU resets atomic Chris Wilson
2019-01-07 11:54 ` [PATCH 28/46] drm/i915/guc: Disable global reset Chris Wilson
2019-01-07 11:54 ` [PATCH 29/46] drm/i915: Remove GPU reset dependence on struct_mutex Chris Wilson
2019-01-07 11:54 ` [PATCH 30/46] drm/i915: Issue engine resets onto idle engines Chris Wilson
2019-01-07 11:54 ` [PATCH 31/46] drm/i915: Stop tracking MRU activity on VMA Chris Wilson
2019-01-16 16:27   ` Tvrtko Ursulin
2019-01-16 16:37     ` Chris Wilson
2019-01-07 11:54 ` [PATCH 32/46] drm/i915: Pull VM lists under the VM mutex Chris Wilson
2019-01-16 16:47   ` Tvrtko Ursulin
2019-01-16 17:01     ` Chris Wilson
2019-01-17 16:23       ` Tvrtko Ursulin
2019-01-17 23:20         ` Chris Wilson
2019-01-07 11:54 ` [PATCH 33/46] drm/i915: Move vma lookup to its own lock Chris Wilson
2019-01-07 11:54 ` [PATCH 34/46] drm/i915: Move intel_execlists_show_requests() aside Chris Wilson
2019-01-07 11:54 ` [PATCH 35/46] drm/i915: Use b->irq_enable() as predicate for mock engine Chris Wilson
2019-01-07 11:54 ` [PATCH 36/46] drm/i915/selftests: Allocate mock ring/timeline per context Chris Wilson
2019-01-07 11:55 ` [PATCH 37/46] drm/i915/selftests: Make evict tolerant of foreign objects Chris Wilson
2019-01-07 11:55 ` [PATCH 38/46] drm/i915: Remove the intel_engine_notify tracepoint Chris Wilson
2019-01-07 11:55 ` [PATCH 39/46] drm/i915: Always allocate an object/vma for the HWSP Chris Wilson
2019-01-10 10:52   ` Matthew Auld
2019-01-10 11:07     ` Chris Wilson
2019-01-10 11:24   ` Matthew Auld
2019-01-07 11:55 ` [PATCH 40/46] drm/i915: Move list of timelines under its own lock Chris Wilson
2019-01-07 11:55 ` [PATCH 41/46] drm/i915: Introduce concept of per-timeline (context) HWSP Chris Wilson
2019-01-15  0:55   ` John Harrison
2019-01-15  9:14     ` Chris Wilson
2019-01-15 15:40       ` Chris Wilson
2019-01-15 17:56         ` John Harrison
2019-01-07 11:55 ` Chris Wilson [this message]
2019-01-15 19:57   ` [PATCH 42/46] drm/i915: Enlarge vma->pin_count John Harrison
2019-01-15 20:17     ` Chris Wilson
2019-01-16  0:18       ` John Harrison
2019-01-07 11:55 ` [PATCH 43/46] drm/i915: Allocate a status page for each timeline Chris Wilson
2019-01-15  0:56   ` John Harrison
2019-01-15  9:50     ` Chris Wilson
2019-01-15 18:17       ` John Harrison
2019-01-15 18:43         ` Chris Wilson
2019-01-16 21:06           ` John Harrison
2019-01-16 21:15             ` Chris Wilson
2019-01-07 11:55 ` [PATCH 44/46] drm/i915: Track the context's seqno in its own timeline HWSP Chris Wilson
2019-01-07 11:55 ` [PATCH 45/46] drm/i915: Identify active requests Chris Wilson
2019-01-07 11:55 ` [PATCH 46/46] drm/i915: Replace global breadcrumbs with per-context interrupt tracking Chris Wilson
2019-01-07 12:45 ` ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/46] drm/i915: Return immediately if trylock fails for direct-reclaim Patchwork
2019-01-07 13:02 ` ✗ Fi.CI.SPARSE: " Patchwork
2019-01-07 13:05 ` ✓ Fi.CI.BAT: success " Patchwork
2019-01-07 14:00 ` [PATCH 01/46] " Tvrtko Ursulin
2019-01-07 14:07   ` Chris Wilson
2019-01-08  8:58     ` Tvrtko Ursulin
2019-01-07 17:10 ` ✗ Fi.CI.IGT: failure for series starting with [01/46] " Patchwork
2019-01-07 17:19   ` Chris Wilson
2019-01-08 13:50 ` ✗ Fi.CI.BAT: failure for series starting with [01/46] drm/i915: Return immediately if trylock fails for direct-reclaim (rev3) Patchwork

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=20190107115509.12523-42-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.