From 86d8ddc74124c3fdfc139f246ba6da15e45e86e3 Mon Sep 17 00:00:00 2001
From: John Harrison <John.C.Harrison@Intel.com>
Date: Thu, 26 Jan 2023 16:28:36 -0800
Subject: [PATCH] drm/i915: Fix request ref counting during error capture & debugfs dump
Git-commit: 86d8ddc74124c3fdfc139f246ba6da15e45e86e3
Patch-mainline: v6.2-rc7
Alt-commit: 3700e353781e27f1bc7222f51f2cc36cbeb9b4ec
References: git-fixes
When GuC support was added to error capture, the reference counting
around the request object was broken. Fix it up.
The context based search manages the spinlocking around the search
internally. So it needs to grab the reference count internally as
well. The execlist only request based search relies on external
locking, so it needs an external reference count but within the
spinlock not outside it.
The only other caller of the context based search is the code for
dumping engine state to debugfs. That code wasn't previously getting
an explicit reference at all as it does everything while holding the
execlist specific spinlock. So, that needs updaing as well as that
spinlock doesn't help when using GuC submission. Rather than trying to
conditionally get/put depending on submission model, just change it to
always do the get/put.
V2: Explicitly document adding an extra blank line in some dense code
(Andy Shevchenko). Fix multiple potential null pointer derefs in case
of no request found (some spotted by Tvrtko, but there was more!).
Also fix a leaked request in case of !started and another in
__guc_reset_context now that intel_context_find_active_request is
actually reference counting the returned request.
V3: Add a _get suffix to intel_context_find_active_request now that it
grabs a reference (Daniele).
V4: Split the intel_guc_find_hung_context change to a separate patch
and rename intel_context_find_active_request_get to
intel_context_get_active_request (Tvrtko).
V5: s/locking/reference counting/ in commit message (Tvrtko)
Fixes: dc0dad365c5e ("drm/i915/guc: Fix for error capture after full GPU reset with GuC")
Fixes: 573ba126aef3 ("drm/i915/guc: Capture error state on context reset")
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Acked-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Andrzej Hajda <andrzej.hajda@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Cc: Michael Cheng <michael.cheng@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Tejas Upadhyay <tejaskumarx.surendrakumar.upadhyay@intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Cc: Alan Previn <alan.previn.teres.alexis@intel.com>
Cc: Bruce Chang <yu.bruce.chang@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230127002842.3169194-3-John.C.Harrison@Intel.com
(cherry picked from commit 3700e353781e27f1bc7222f51f2cc36cbeb9b4ec)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Takashi Iwai <tiwai@suse.de>
---
drivers/gpu/drm/i915/gt/intel_context.c | 4 +++-
drivers/gpu/drm/i915/gt/intel_context.h | 3 +--
drivers/gpu/drm/i915/gt/intel_engine_cs.c | 6 +++++-
drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 3 ++-
drivers/gpu/drm/i915/i915_gpu_error.c | 13 ++++++-------
5 files changed, 17 insertions(+), 12 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index e94365b08f1e..2aa63ec521b8 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -528,7 +528,7 @@ struct i915_request *intel_context_create_request(struct intel_context *ce)
return rq;
}
-struct i915_request *intel_context_find_active_request(struct intel_context *ce)
+struct i915_request *intel_context_get_active_request(struct intel_context *ce)
{
struct intel_context *parent = intel_context_to_parent(ce);
struct i915_request *rq, *active = NULL;
@@ -552,6 +552,8 @@ struct i915_request *intel_context_find_active_request(struct intel_context *ce)
active = rq;
}
+ if (active)
+ active = i915_request_get_rcu(active);
spin_unlock_irqrestore(&parent->guc_state.lock, flags);
return active;
diff --git a/drivers/gpu/drm/i915/gt/intel_context.h b/drivers/gpu/drm/i915/gt/intel_context.h
index fb62b7b8cbcd..0a8d553da3f4 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.h
+++ b/drivers/gpu/drm/i915/gt/intel_context.h
@@ -268,8 +268,7 @@ int intel_context_prepare_remote_request(struct intel_context *ce,
struct i915_request *intel_context_create_request(struct intel_context *ce);
-struct i915_request *
-intel_context_find_active_request(struct intel_context *ce);
+struct i915_request *intel_context_get_active_request(struct intel_context *ce);
static inline bool intel_context_is_barrier(const struct intel_context *ce)
{
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index c33e0d72d670..3e090db01a18 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -2217,9 +2217,11 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d
if (guc) {
ce = intel_engine_get_hung_context(engine);
if (ce)
- hung_rq = intel_context_find_active_request(ce);
+ hung_rq = intel_context_get_active_request(ce);
} else {
hung_rq = intel_engine_execlist_find_hung_request(engine);
+ if (hung_rq)
+ hung_rq = i915_request_get_rcu(hung_rq);
}
if (hung_rq)
@@ -2230,6 +2232,8 @@ static void engine_dump_active_requests(struct intel_engine_cs *engine, struct d
else
intel_engine_dump_active_requests(&engine->sched_engine->requests,
hung_rq, m);
+ if (hung_rq)
+ i915_request_put(hung_rq);
}
void intel_engine_dump(struct intel_engine_cs *engine,
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 3d2b25bc5d7d..c10977cb06b9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1702,7 +1702,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
goto next_context;
guilty = false;
- rq = intel_context_find_active_request(ce);
+ rq = intel_context_get_active_request(ce);
if (!rq) {
head = ce->ring->tail;
goto out_replay;
@@ -1715,6 +1715,7 @@ static void __guc_reset_context(struct intel_context *ce, intel_engine_mask_t st
head = intel_ring_wrap(ce->ring, rq->head);
__i915_request_reset(rq, guilty);
+ i915_request_put(rq);
out_replay:
guc_reset_state(ce, head, guilty);
next_context:
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9d5d5a397b64..9e2d17785a9a 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1607,7 +1607,7 @@ capture_engine(struct intel_engine_cs *engine,
ce = intel_engine_get_hung_context(engine);
if (ce) {
intel_engine_clear_hung_context(engine);
- rq = intel_context_find_active_request(ce);
+ rq = intel_context_get_active_request(ce);
if (!rq || !i915_request_started(rq))
goto no_request_capture;
} else {
@@ -1618,21 +1618,18 @@ capture_engine(struct intel_engine_cs *engine,
if (!intel_uc_uses_guc_submission(&engine->gt->uc)) {
spin_lock_irqsave(&engine->sched_engine->lock, flags);
rq = intel_engine_execlist_find_hung_request(engine);
+ if (rq)
+ rq = i915_request_get_rcu(rq);
spin_unlock_irqrestore(&engine->sched_engine->lock,
flags);
}
}
- if (rq)
- rq = i915_request_get_rcu(rq);
-
if (!rq)
goto no_request_capture;
capture = intel_engine_coredump_add_request(ee, rq, ATOMIC_MAYFAIL);
- if (!capture) {
- i915_request_put(rq);
+ if (!capture)
goto no_request_capture;
- }
if (dump_flags & CORE_DUMP_FLAG_IS_GUC_CAPTURE)
intel_guc_capture_get_matching_node(engine->gt, ee, ce);
@@ -1642,6 +1639,8 @@ capture_engine(struct intel_engine_cs *engine,
return ee;
no_request_capture:
+ if (rq)
+ i915_request_put(rq);
kfree(ee);
return NULL;
}
--
2.35.3