All of lore.kernel.org
 help / color / mirror / Atom feed
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
To: intel-gfx@lists.freedesktop.org
Cc: Lucas De Marchi <lucas.demarchi@intel.com>,
	Chris Wilson <chris.p.wilson@intel.com>
Subject: [PATCH v2 2/3] drm/i915/perf: enable OAR context save/restore of performance counters
Date: Thu, 17 Oct 2019 17:50:27 -0700	[thread overview]
Message-ID: <20191018005028.47441-2-umesh.nerlige.ramappa@intel.com> (raw)
In-Reply-To: <20191018005028.47441-1-umesh.nerlige.ramappa@intel.com>

From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>

We want this so we can preempt performance queries and keep the system
responsive even when long running queries are ongoing. We avoid doing
it for all contexts.

v2: use LRI to modify context control (Chris)
v3: use MASKED_FIELD to program just the masked bits (Chris)
v4: reuse request created during emit_oa_config (Lionel)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
---
 drivers/gpu/drm/i915/gt/intel_lrc.h |  1 +
 drivers/gpu/drm/i915/i915_perf.c    | 35 ++++++++++++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.h b/drivers/gpu/drm/i915/gt/intel_lrc.h
index 99dc576a4e25..b6daac712c9e 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.h
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.h
@@ -43,6 +43,7 @@ struct intel_engine_cs;
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
 #define   CTX_CTRL_RS_CTX_ENABLE		(1 << 1)
 #define	  CTX_CTRL_ENGINE_CTX_SAVE_INHIBIT	(1 << 2)
+#define	  GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE	(1 << 8)
 #define RING_CONTEXT_STATUS_PTR(base)		_MMIO((base) + 0x3a0)
 #define RING_EXECLIST_SQ_CONTENTS(base)		_MMIO((base) + 0x510)
 #define RING_EXECLIST_CONTROL(base)		_MMIO((base) + 0x550)
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 91707558a0f5..ce97af484a32 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1862,14 +1862,36 @@ get_oa_vma(struct i915_perf_stream *stream, struct i915_oa_config *oa_config)
 	return i915_vma_get(oa_bo->vma);
 }
 
+static int gen12_emit_oar_config(struct i915_request *rq,
+				 struct intel_context *ce,
+				 bool enable)
+{
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_CONTEXT_CONTROL(ce->engine->mmio_base));
+	*cs++ = _MASKED_FIELD(GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE,
+			      enable ? GEN12_CTX_CTRL_OAR_CONTEXT_ENABLE : 0);
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
 static int emit_oa_config(struct i915_perf_stream *stream,
 			  struct intel_context *ce)
 {
+	struct i915_oa_config *oa_config = stream->oa_config;
 	struct i915_request *rq;
 	struct i915_vma *vma;
 	int err;
 
-	vma = get_oa_vma(stream, stream->oa_config);
+	vma = get_oa_vma(stream, oa_config);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
@@ -1891,6 +1913,17 @@ static int emit_oa_config(struct i915_perf_stream *stream,
 	if (err)
 		goto err_add_request;
 
+	/*
+	 * For Gen12, performance counters are context saved/restored.
+	 * Only enable it for the context that requested this.
+	 */
+	if (ce == stream->pinned_ctx && IS_GEN(stream->perf->i915, 12)) {
+		err = gen12_emit_oar_config(rq, ce, oa_config != NULL);
+		if (err)
+			goto err_add_request;
+
+	}
+
 	err = rq->engine->emit_bb_start(rq,
 					vma->node.start, 0,
 					I915_DISPATCH_SECURE);
-- 
2.20.1

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

  reply	other threads:[~2019-10-18  0:50 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-10-18  0:50 [PATCH v2 1/3] drm/i915/perf: Add helper macros for comparing with whitelisted registers Umesh Nerlige Ramappa
2019-10-18  0:50 ` Umesh Nerlige Ramappa [this message]
2019-10-18  7:54   ` [PATCH v2 2/3] drm/i915/perf: enable OAR context save/restore of performance counters Lionel Landwerlin
2019-10-18 23:22   ` Chris Wilson
2019-10-19  7:18     ` Lionel Landwerlin
2019-10-18  0:50 ` [PATCH v2 3/3] drm/i915/tgl: Add perf support on TGL Umesh Nerlige Ramappa
2019-10-18  2:35 ` ✗ Fi.CI.CHECKPATCH: warning for series starting with [v2,1/3] drm/i915/perf: Add helper macros for comparing with whitelisted registers Patchwork
2019-10-18  2:37 ` ✗ Fi.CI.SPARSE: " Patchwork
2019-10-18  3:08 ` ✗ Fi.CI.BAT: failure " Patchwork
  -- strict thread matches above, loose matches on Subject: below --
2019-10-17 22:57 [PATCH v2 1/3] " Umesh Nerlige Ramappa
2019-10-17 22:57 ` [PATCH v2 2/3] drm/i915/perf: enable OAR context save/restore of performance counters Umesh Nerlige Ramappa

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=20191018005028.47441-2-umesh.nerlige.ramappa@intel.com \
    --to=umesh.nerlige.ramappa@intel.com \
    --cc=chris.p.wilson@intel.com \
    --cc=intel-gfx@lists.freedesktop.org \
    --cc=lucas.demarchi@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 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.