Blob Blame History Raw
From e8c49fa96838101435b9e4884d49b30da7a4e0c6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 9 Nov 2017 08:55:40 +0000
Subject: [PATCH] drm/i915: Reorder context-close to avoid calling i915_vma_close() under RCU
Git-commit: e8c49fa96838101435b9e4884d49b30da7a4e0c6
Patch-mainline: v4.15-rc1
References: FATE#322643 bsc#1055900
No-fix: 94dec87159af6f3dcc0b78d3f909aefa9e29c01a

When we close the VMA, we unbind it from the ppgtt and tear down the
page directory pointing at it. That may trigger us to return WC pages
back to the system, requiring conversion back to WB which itself may
sleep. That makes i915_vma_close() unsuitable for use inside the RCU
read lock, which we need to hold to iterate the radixtree.

The fix is quite simple, we can close all the VMA as we close the ppgtt,
we only need to do that instead of closing them during destruction of
the LUT.

V2: Order between closing the LUT and the ppgtt is important; we use the
vma inside the LUT as a means of retrieving the object, and so we must
clear the LUT before freeing the VMA when closing the ppgtt.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103638
Fixes: 547da76b5777 ("drm/i915: Hold rcu_read_lock when iterating over the radixtree (vma idr)")
Fixes: d1b48c1e7184 ("drm/i915: Replace execbuf vma ht with an idr")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171109085540.32264-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
(cherry picked from commit 94dec87159af6f3dcc0b78d3f909aefa9e29c01a)

Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Takashi Iwai <tiwai@suse.de>

---
 drivers/gpu/drm/i915/i915_gem_context.c |   12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -107,14 +107,9 @@ static void lut_close(struct i915_gem_co
 	rcu_read_lock();
 	radix_tree_for_each_slot(slot, &ctx->handles_vma, &iter, 0) {
 		struct i915_vma *vma = rcu_dereference_raw(*slot);
-		struct drm_i915_gem_object *obj = vma->obj;
 
 		radix_tree_iter_delete(&ctx->handles_vma, &iter, slot);
-
-		if (!i915_vma_is_ggtt(vma))
-			i915_vma_close(vma);
-
-		__i915_gem_object_release_unless_active(obj);
+		__i915_gem_object_release_unless_active(vma->obj);
 	}
 	rcu_read_unlock();
 }
@@ -200,6 +195,11 @@ static void context_close(struct i915_ge
 {
 	i915_gem_context_set_closed(ctx);
 
+	/*
+	 * The LUT uses the VMA as a backpointer to unref the object,
+	 * so we need to clear the LUT before we close all the VMA (inside
+	 * the ppgtt).
+	 */
 	lut_close(ctx);
 	if (ctx->ppgtt)
 		i915_ppgtt_close(&ctx->ppgtt->base);