dri-devel.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Jason Ekstrand <jason@jlekstrand.net>
To: intel-gfx@lists.freedesktop.org, dri-devel@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>,
	Jason Ekstrand <jason@jlekstrand.net>
Subject: [PATCH 13/25] drm/i915: Stop manually RCU banging in reset_stats_ioctl (v2)
Date: Thu, 29 Apr 2021 14:03:28 -0500	[thread overview]
Message-ID: <20210429190340.1555632-14-jason@jlekstrand.net> (raw)
In-Reply-To: <20210429190340.1555632-1-jason@jlekstrand.net>

As far as I can tell, the only real reason for this is to avoid taking a
reference to the i915_gem_context.  The cost of those two atomics
probably pales in comparison to the cost of the ioctl itself so we're
really not buying ourselves anything here.  We're about to make context
lookup a tiny bit more complicated, so let's get rid of the one hand-
rolled case.

Some usermode drivers such as our Vulkan driver call GET_RESET_STATS on
every execbuf so the perf here could theoretically be an issue.  If this
ever does become a performance issue for any such userspace drivers,
they can use set CONTEXT_PARAM_RECOVERABLE to false and look for -EIO
coming from execbuf to check for hangs instead.

v2 (Daniel Vetter):
 - Add a comment in the commit message about recoverable contexts

Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/gem/i915_gem_context.c | 13 ++++---------
 drivers/gpu/drm/i915/i915_drv.h             |  8 +-------
 2 files changed, 5 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index 8e254d83d65f2..c073d5939482b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -2091,16 +2091,13 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 	struct drm_i915_private *i915 = to_i915(dev);
 	struct drm_i915_reset_stats *args = data;
 	struct i915_gem_context *ctx;
-	int ret;
 
 	if (args->flags || args->pad)
 		return -EINVAL;
 
-	ret = -ENOENT;
-	rcu_read_lock();
-	ctx = __i915_gem_context_lookup_rcu(file->driver_priv, args->ctx_id);
+	ctx = i915_gem_context_lookup(file->driver_priv, args->ctx_id);
 	if (!ctx)
-		goto out;
+		return -ENOENT;
 
 	/*
 	 * We opt for unserialised reads here. This may result in tearing
@@ -2117,10 +2114,8 @@ int i915_gem_context_reset_stats_ioctl(struct drm_device *dev,
 	args->batch_active = atomic_read(&ctx->guilty_count);
 	args->batch_pending = atomic_read(&ctx->active_count);
 
-	ret = 0;
-out:
-	rcu_read_unlock();
-	return ret;
+	i915_gem_context_put(ctx);
+	return 0;
 }
 
 /* GEM context-engines iterator: for_each_gem_engine() */
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0b44333eb7033..8571c5c1509a7 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1840,19 +1840,13 @@ struct drm_gem_object *i915_gem_prime_import(struct drm_device *dev,
 
 struct dma_buf *i915_gem_prime_export(struct drm_gem_object *gem_obj, int flags);
 
-static inline struct i915_gem_context *
-__i915_gem_context_lookup_rcu(struct drm_i915_file_private *file_priv, u32 id)
-{
-	return xa_load(&file_priv->context_xa, id);
-}
-
 static inline struct i915_gem_context *
 i915_gem_context_lookup(struct drm_i915_file_private *file_priv, u32 id)
 {
 	struct i915_gem_context *ctx;
 
 	rcu_read_lock();
-	ctx = __i915_gem_context_lookup_rcu(file_priv, id);
+	ctx = xa_load(&file_priv->context_xa, id);
 	if (ctx && !kref_get_unless_zero(&ctx->ref))
 		ctx = NULL;
 	rcu_read_unlock();
-- 
2.31.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel

  parent reply	other threads:[~2021-04-29 19:04 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-04-29 19:03 [PATCH 00/25] drm/i915/gem: ioctl clean-ups (v4) Jason Ekstrand
2021-04-29 19:03 ` [PATCH 01/25] drm/i915: Drop I915_CONTEXT_PARAM_RINGSIZE Jason Ekstrand
2021-04-29 19:03 ` [PATCH 02/25] drm/i915: Stop storing the ring size in the ring pointer Jason Ekstrand
2021-04-29 19:03 ` [PATCH 03/25] drm/i915: Drop I915_CONTEXT_PARAM_NO_ZEROMAP Jason Ekstrand
2021-04-29 19:03 ` [PATCH 04/25] drm/i915/gem: Set the watchdog timeout directly in intel_context_set_gem (v2) Jason Ekstrand
2021-04-29 19:03 ` [PATCH 05/25] drm/i915/gem: Return void from context_apply_all Jason Ekstrand
2021-04-29 19:03 ` [PATCH 06/25] drm/i915: Drop the CONTEXT_CLONE API Jason Ekstrand
2021-04-29 19:03 ` [PATCH 07/25] drm/i915: Implement SINGLE_TIMELINE with a syncobj (v4) Jason Ekstrand
2021-04-29 19:03 ` [PATCH 08/25] drm/i915: Drop getparam support for I915_CONTEXT_PARAM_ENGINES Jason Ekstrand
2021-04-29 19:03 ` [PATCH 09/25] drm/i915/gem: Disallow bonding of virtual engines (v3) Jason Ekstrand
2021-04-29 19:03 ` [PATCH 10/25] drm/i915/gem: Remove engine auto-magic with FENCE_SUBMIT Jason Ekstrand
2021-04-29 19:03 ` [PATCH 11/25] drm/i915/request: Remove the hook from await_execution Jason Ekstrand
2021-04-29 19:03 ` [PATCH 12/25] drm/i915/gem: Disallow creating contexts with too many engines Jason Ekstrand
2021-04-29 19:03 ` Jason Ekstrand [this message]
2021-04-29 19:03 ` [PATCH 14/25] drm/i915/gem: Add a separate validate_priority helper Jason Ekstrand
2021-04-29 19:03 ` [PATCH 15/25] drm/i915: Add gem/i915_gem_context.h to the docs Jason Ekstrand
2021-04-29 19:03 ` [PATCH 16/25] drm/i915/gem: Add an intermediate proto_context struct Jason Ekstrand
2021-04-29 19:03 ` [PATCH 17/25] drm/i915/gem: Use the proto-context to handle create parameters Jason Ekstrand
2021-04-29 19:03 ` [PATCH 18/25] drm/i915/gem: Return an error ptr from context_lookup Jason Ekstrand
2021-04-29 19:03 ` [PATCH 19/25] drm/i915/gt: Drop i915_address_space::file (v2) Jason Ekstrand
2021-04-29 19:03 ` [PATCH 20/25] drm/i915/gem: Delay context creation Jason Ekstrand
2021-04-29 19:03 ` [PATCH 21/25] drm/i915/gem: Don't allow changing the VM on running contexts Jason Ekstrand
2021-04-29 19:03 ` [PATCH 22/25] drm/i915/gem: Don't allow changing the engine set " Jason Ekstrand
2021-04-29 19:03 ` [PATCH 23/25] drm/i915/selftests: Take a VM in kernel_context() Jason Ekstrand
2021-04-29 19:03 ` [PATCH 24/25] i915/gem/selftests: Assign the VM at context creation in igt_shared_ctx_exec Jason Ekstrand
2021-04-29 19:03 ` [PATCH 25/25] drm/i915/gem: Roll all of context creation together Jason Ekstrand

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=20210429190340.1555632-14-jason@jlekstrand.net \
    --to=jason@jlekstrand.net \
    --cc=daniel.vetter@ffwll.ch \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=intel-gfx@lists.freedesktop.org \
    --subject='Re: [PATCH 13/25] drm/i915: Stop manually RCU banging in reset_stats_ioctl (v2)' \
    /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

This is a public inbox, see mirroring instructions
on how to clone and mirror all data and code used for this inbox