linux-kernel - [PATCH 4.2.y-ckt 255/305] drm/i915: Only spin whilst waiting on the current request

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <1452902519-2754-256-git-send-email-kamal@canonical.com>
Date:	Fri, 15 Jan 2016 16:01:09 -0800
From:	Kamal Mostafa <kamal@...onical.com>
To:	linux-kernel@...r.kernel.org, stable@...r.kernel.org,
	kernel-team@...ts.ubuntu.com
Cc:	Chris Wilson <chris@...is-wilson.co.uk>,
	"Rogozhkin, Dmitry V" <dmitry.v.rogozhkin@...el.com>,
	Daniel Vetter <daniel.vetter@...ll.ch>,
	Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>,
	Eero Tamminen <eero.t.tamminen@...el.com>,
	"Rantala, Valtteri" <valtteri.rantala@...el.com>,
	Jani Nikula <jani.nikula@...el.com>,
	Kamal Mostafa <kamal@...onical.com>
Subject: [PATCH 4.2.y-ckt 255/305] drm/i915: Only spin whilst waiting on the current request

4.2.8-ckt2 -stable review patch.  If anyone has any objections, please let me know.

---8<------------------------------------------------------------

From: Chris Wilson <chris@...is-wilson.co.uk>

commit 0f0cd472062eca6f9fac8be0cd5585f9a2df1ab2 upstream.

Limit busywaiting only to the request currently being processed by the
GPU. If the request is not currently being processed by the GPU, there
is a very low likelihood of it being completed within the 2 microsecond
spin timeout and so we will just be wasting CPU cycles.

v2: Check for logical inversion when rebasing - we were incorrectly
checking for this request being active, and instead busywaiting for
when the GPU was not yet processing the request of interest.

v3: Try another colour for the seqno names.
v4: Another colour for the function names.

v5: Remove the forced coherency when checking for the active request. On
reflection and plenty of recent experimentation, the issue is not a
cache coherency problem - but an irq/seqno ordering problem (timing issue).
Here, we do not need the w/a to force ordering of the read with an
interrupt.

Signed-off-by: Chris Wilson <chris@...is-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>
Cc: "Rogozhkin, Dmitry V" <dmitry.v.rogozhkin@...el.com>
Cc: Daniel Vetter <daniel.vetter@...ll.ch>
Cc: Tvrtko Ursulin <tvrtko.ursulin@...ux.intel.com>
Cc: Eero Tamminen <eero.t.tamminen@...el.com>
Cc: "Rantala, Valtteri" <valtteri.rantala@...el.com>
Signed-off-by: Daniel Vetter <daniel.vetter@...ll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1449833608-22125-4-git-send-email-chris@chris-wilson.co.uk
(cherry picked from commit 821485dc2ad665f136c57ee589bf7a8210160fe2)
Signed-off-by: Jani Nikula <jani.nikula@...el.com>
Signed-off-by: Kamal Mostafa <kamal@...onical.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 27 +++++++++++++++++++--------
 drivers/gpu/drm/i915/i915_gem.c |  8 +++++++-
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e1df8feb..f4e2f54 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2119,8 +2119,17 @@ struct drm_i915_gem_request {
 	struct drm_i915_private *i915;
 	struct intel_engine_cs *ring;
 
-	/** GEM sequence number associated with this request. */
-	uint32_t seqno;
+	 /** GEM sequence number associated with the previous request,
+	  * when the HWS breadcrumb is equal to this the GPU is processing
+	  * this request.
+	  */
+	u32 previous_seqno;
+
+	 /** GEM sequence number associated with this request,
+	  * when the HWS breadcrumb is equal or greater than this the GPU
+	  * has finished processing this request.
+	  */
+	u32 seqno;
 
 	/** Position in the ringbuffer of the start of the request */
 	u32 head;
@@ -2797,15 +2806,17 @@ i915_seqno_passed(uint32_t seq1, uint32_t seq2)
 	return (int32_t)(seq1 - seq2) >= 0;
 }
 
+static inline bool i915_gem_request_started(struct drm_i915_gem_request *req,
+					   bool lazy_coherency)
+{
+	u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency);
+	return i915_seqno_passed(seqno, req->previous_seqno);
+}
+
 static inline bool i915_gem_request_completed(struct drm_i915_gem_request *req,
 					      bool lazy_coherency)
 {
-	u32 seqno;
-
-	BUG_ON(req == NULL);
-
-	seqno = req->ring->get_seqno(req->ring, lazy_coherency);
-
+	u32 seqno = req->ring->get_seqno(req->ring, lazy_coherency);
 	return i915_seqno_passed(seqno, req->seqno);
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ace38a7..da7653c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1221,9 +1221,13 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 	 * takes to sleep on a request, on the order of a microsecond.
 	 */
 
-	if (i915_gem_request_get_ring(req)->irq_refcount)
+	if (req->ring->irq_refcount)
 		return -EBUSY;
 
+	/* Only spin if we know the GPU is processing this request */
+	if (!i915_gem_request_started(req, true))
+		return -EAGAIN;
+
 	timeout = local_clock_us(&cpu) + 5;
 	while (!need_resched()) {
 		if (i915_gem_request_completed(req, true))
@@ -1237,6 +1241,7 @@ static int __i915_spin_request(struct drm_i915_gem_request *req, int state)
 
 		cpu_relax_lowlatency();
 	}
+
 	if (i915_gem_request_completed(req, false))
 		return 0;
 
@@ -2594,6 +2599,7 @@ int __i915_add_request(struct intel_engine_cs *ring,
 	}
 
 	request->emitted_jiffies = jiffies;
+	request->previous_seqno = ring->last_submitted_seqno;
 	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 	request->file_priv = NULL;
-- 
1.9.1