From: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
To: Jason Ekstrand <jason@jlekstrand.net>,
dri-devel@lists.freedesktop.org, intel-gfx@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@intel.com>,
Matthew Auld <matthew.auld@intel.com>
Subject: Re: [Intel-gfx] [PATCH 2/5] drm/i915: Use a simpler scheme for caching i915_request
Date: Thu, 10 Jun 2021 11:08:40 +0100 [thread overview]
Message-ID: <2902ebcf-ec60-fdd3-2e61-a113bca835fd@linux.intel.com> (raw)
In-Reply-To: <20210609212959.471209-3-jason@jlekstrand.net>
On 09/06/2021 22:29, Jason Ekstrand wrote:
> Instead of attempting to recycle a request in to the cache when it
> retires, stuff a new one in the cache every time we allocate a request
> for some other reason.
I supposed the "why?" is "simpler scheme" - but in what way it is simpler?
> Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
> Cc: Jon Bloomfield <jon.bloomfield@intel.com>
> Cc: Daniel Vetter <daniel.vetter@intel.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> ---
> drivers/gpu/drm/i915/i915_request.c | 66 ++++++++++++++---------------
> 1 file changed, 31 insertions(+), 35 deletions(-)
>
> diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
> index 48c5f8527854b..e531c74f0b0e2 100644
> --- a/drivers/gpu/drm/i915/i915_request.c
> +++ b/drivers/gpu/drm/i915/i915_request.c
> @@ -128,41 +128,6 @@ static void i915_fence_release(struct dma_fence *fence)
> i915_sw_fence_fini(&rq->submit);
> i915_sw_fence_fini(&rq->semaphore);
>
> - /*
> - * Keep one request on each engine for reserved use under mempressure
> - *
> - * We do not hold a reference to the engine here and so have to be
> - * very careful in what rq->engine we poke. The virtual engine is
> - * referenced via the rq->context and we released that ref during
> - * i915_request_retire(), ergo we must not dereference a virtual
> - * engine here. Not that we would want to, as the only consumer of
> - * the reserved engine->request_pool is the power management parking,
> - * which must-not-fail, and that is only run on the physical engines.
> - *
> - * Since the request must have been executed to be have completed,
> - * we know that it will have been processed by the HW and will
> - * not be unsubmitted again, so rq->engine and rq->execution_mask
> - * at this point is stable. rq->execution_mask will be a single
> - * bit if the last and _only_ engine it could execution on was a
> - * physical engine, if it's multiple bits then it started on and
> - * could still be on a virtual engine. Thus if the mask is not a
> - * power-of-two we assume that rq->engine may still be a virtual
> - * engine and so a dangling invalid pointer that we cannot dereference
> - *
> - * For example, consider the flow of a bonded request through a virtual
> - * engine. The request is created with a wide engine mask (all engines
> - * that we might execute on). On processing the bond, the request mask
> - * is reduced to one or more engines. If the request is subsequently
> - * bound to a single engine, it will then be constrained to only
> - * execute on that engine and never returned to the virtual engine
> - * after timeslicing away, see __unwind_incomplete_requests(). Thus we
> - * know that if the rq->execution_mask is a single bit, rq->engine
> - * can be a physical engine with the exact corresponding mask.
> - */
> - if (is_power_of_2(rq->execution_mask) &&
> - !cmpxchg(&rq->engine->request_pool, NULL, rq))
> - return;
> -
> kmem_cache_free(global.slab_requests, rq);
> }
>
> @@ -869,6 +834,29 @@ static void retire_requests(struct intel_timeline *tl)
> break;
> }
>
> +static void
> +ensure_cached_request(struct i915_request **rsvd, gfp_t gfp)
> +{
> + struct i915_request *rq;
> +
> + /* Don't try to add to the cache if we don't allow blocking. That
> + * just increases the chance that the actual allocation will fail.
> + */
Linus has been known to rant passionately against this comment style so
we actively try to never use it.
Rega4rds,
Tvrtko
> + if (gfpflags_allow_blocking(gfp))
> + return;
> +
> + if (READ_ONCE(rsvd))
> + return;
> +
> + rq = kmem_cache_alloc(global.slab_requests,
> + gfp | __GFP_RETRY_MAYFAIL | __GFP_NOWARN);
> + if (!rq)
> + return; /* Oops but nothing we can do */
> +
> + if (cmpxchg(rsvd, NULL, rq))
> + kmem_cache_free(global.slab_requests, rq);
> +}
> +
> static noinline struct i915_request *
> request_alloc_slow(struct intel_timeline *tl,
> struct i915_request **rsvd,
> @@ -937,6 +925,14 @@ __i915_request_create(struct intel_context *ce, gfp_t gfp)
> /* Check that the caller provided an already pinned context */
> __intel_context_pin(ce);
>
> + /* Before we do anything, try to make sure we have at least one
> + * request in the engine's cache. If we get here with GPF_NOWAIT
> + * (this can happen when switching to a kernel context), we we want
> + * to try very hard to not fail and we fall back to this cache.
> + * Top it off with a fresh request whenever it's empty.
> + */
> + ensure_cached_request(&ce->engine->request_pool, gfp);
> +
> /*
> * Beware: Dragons be flying overhead.
> *
>
next prev parent reply other threads:[~2021-06-10 10:09 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-06-09 21:29 [PATCH 0/5] dma-fence, i915: Stop allowing SLAB_TYPESAFE_BY_RCU for dma_fence Jason Ekstrand
2021-06-09 21:29 ` [PATCH 1/5] drm/i915: Move intel_engine_free_request_pool to i915_request.c Jason Ekstrand
2021-06-10 10:03 ` [Intel-gfx] " Tvrtko Ursulin
2021-06-10 13:57 ` Jason Ekstrand
2021-06-10 15:07 ` Tvrtko Ursulin
2021-06-10 16:32 ` Jason Ekstrand
2021-06-09 21:29 ` [PATCH 2/5] drm/i915: Use a simpler scheme for caching i915_request Jason Ekstrand
2021-06-10 10:08 ` Tvrtko Ursulin [this message]
2021-06-10 13:50 ` [Intel-gfx] " Jason Ekstrand
2021-06-09 21:29 ` [PATCH 3/5] drm/i915: Stop using SLAB_TYPESAFE_BY_RCU for i915_request Jason Ekstrand
2021-06-09 21:29 ` [PATCH 4/5] dma-buf: Stop using SLAB_TYPESAFE_BY_RCU in selftests Jason Ekstrand
2021-06-16 12:47 ` [Intel-gfx] " kernel test robot
2021-06-09 21:29 ` [PATCH 5/5] DONOTMERGE: dma-buf: Get rid of dma_fence_get_rcu_safe Jason Ekstrand
2021-06-10 6:51 ` Christian König
2021-06-10 13:59 ` Jason Ekstrand
2021-06-10 15:13 ` Daniel Vetter
2021-06-10 16:24 ` Jason Ekstrand
2021-06-10 16:37 ` Daniel Vetter
2021-06-10 16:52 ` Jason Ekstrand
2021-06-10 17:06 ` Daniel Vetter
2021-06-10 16:54 ` Christian König
2021-06-10 17:11 ` Daniel Vetter
2021-06-10 18:12 ` Christian König
2021-06-16 16:38 ` [Intel-gfx] " kernel test robot
2021-06-10 9:29 ` [Intel-gfx] [PATCH 0/5] dma-fence, i915: Stop allowing SLAB_TYPESAFE_BY_RCU for dma_fence Tvrtko Ursulin
2021-06-10 9:39 ` Christian König
2021-06-10 11:29 ` Daniel Vetter
2021-06-10 11:53 ` Daniel Vetter
2021-06-10 13:07 ` Tvrtko Ursulin
2021-06-10 13:35 ` Jason Ekstrand
2021-06-10 20:09 ` Jason Ekstrand
2021-06-10 20:42 ` Daniel Vetter
2021-06-11 6:55 ` Christian König
2021-06-11 7:20 ` Daniel Vetter
2021-06-11 7:42 ` Christian König
2021-06-11 9:33 ` Daniel Vetter
2021-06-11 10:03 ` Christian König
2021-06-11 15:08 ` Daniel Vetter
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=2902ebcf-ec60-fdd3-2e61-a113bca835fd@linux.intel.com \
--to=tvrtko.ursulin@linux.intel.com \
--cc=daniel.vetter@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=intel-gfx@lists.freedesktop.org \
--cc=jason@jlekstrand.net \
--cc=matthew.auld@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 read-only IMAP folder(s) and NNTP newsgroup(s).