[Intel-gfx] [PATCH] drm/i915: Keep drm_i915_file_private around under RCU

[Chris Wilson]

Ensure that the drm_i915_file_private continues to exist as we attempt
to remove a request from its list, which may race with the destruction
of the file.

<6> [38.380714] [IGT] gem_ctx_create: starting subtest basic-files
<0> [42.201329] BUG: spinlock bad magic on CPU#0, kworker/u16:0/7
<4> [42.201356] general protection fault: 0000 [#1] PREEMPT SMP PTI
<4> [42.201371] CPU: 0 PID: 7 Comm: kworker/u16:0 Tainted: G     U            5.3.0-rc5-CI-Patchwork_14169+ #1
<4> [42.201391] Hardware name: Dell Inc.                 OptiPlex 745                 /0GW726, BIOS 2.3.1  05/21/2007
<4> [42.201594] Workqueue: i915 retire_work_handler [i915]
<4> [42.201614] RIP: 0010:spin_dump+0x5a/0x90
<4> [42.201625] Code: 00 48 8d 88 c0 06 00 00 48 c7 c7 00 71 09 82 e8 35 ef 00 00 48 85 db 44 8b 4d 08 41 b8 ff ff ff ff 48 c7 c1 0b cd 0f 82 74 0e <44> 8b 83 e0 04 00 00 48 8d 8b c0 06 00 00 8b 55 04 48 89 ee 48 c7
<4> [42.201660] RSP: 0018:ffffc9000004bd80 EFLAGS: 00010202
<4> [42.201673] RAX: 0000000000000031 RBX: 6b6b6b6b6b6b6b6b RCX: ffffffff820fcd0b
<4> [42.201688] RDX: 0000000000000000 RSI: ffff88803de266f8 RDI: 00000000ffffffff
<4> [42.201703] RBP: ffff888038381ff8 R08: 00000000ffffffff R09: 000000006b6b6b6b
<4> [42.201718] R10: 0000000041cb0b89 R11: 646162206b636f6c R12: ffff88802a618500
<4> [42.201733] R13: ffff88802b32c288 R14: ffff888038381ff8 R15: ffff88802b32c250
<4> [42.201748] FS:  0000000000000000(0000) GS:ffff88803de00000(0000) knlGS:0000000000000000
<4> [42.201765] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
<4> [42.201778] CR2: 00007f2cefc6d180 CR3: 00000000381ee000 CR4: 00000000000006f0
<4> [42.201793] Call Trace:
<4> [42.201805]  do_raw_spin_lock+0x66/0xb0
<4> [42.201898]  i915_request_retire+0x548/0x7c0 [i915]
<4> [42.201989]  retire_requests+0x4d/0x60 [i915]
<4> [42.202078]  i915_retire_requests+0x144/0x2e0 [i915]
<4> [42.202169]  retire_work_handler+0x10/0x40 [i915]

Recently, in commit 44c22f3f1a0a ("drm/i915: Serialize insertion into the
file->mm.request_list"), we fixed a race on insertion. Now, it appears
we also have a race with destruction!

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld at intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_throttle.c |  4 +---
 drivers/gpu/drm/i915/i915_drv.c              |  2 +-
 drivers/gpu/drm/i915/i915_drv.h              |  6 +++++-
 drivers/gpu/drm/i915/i915_request.c          | 10 +++++-----
 4 files changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
index 1e372420771b..540ef0551789 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_throttle.c
@@ -50,10 +50,8 @@ i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
 		if (time_after_eq(request->emitted_jiffies, recent_enough))
 			break;
 
-		if (target) {
+		if (target && xchg(&target->file_priv, NULL))
 			list_del(&target->client_link);
-			target->file_priv = NULL;
-		}
 
 		target = request;
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c44770b9591b..1c4576a4a5e9 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1693,7 +1693,7 @@ static void i915_driver_postclose(struct drm_device *dev, struct drm_file *file)
 	i915_gem_release(dev, file);
 	mutex_unlock(&dev->struct_mutex);
 
-	kfree(file_priv);
+	kfree_rcu(file_priv, rcu);
 
 	/* Catch up with all the deferred frees from "this" client */
 	i915_gem_flush_free_objects(to_i915(dev));
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 048896b1348b..1659f27c2dfb 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -185,7 +185,11 @@ struct i915_mmu_object;
 
 struct drm_i915_file_private {
 	struct drm_i915_private *dev_priv;
-	struct drm_file *file;
+
+	union {
+		struct drm_file *file;
+		struct rcu_head rcu;
+	};
 
 	struct {
 		spinlock_t lock;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f1a0a57fc6fc..0e025ab21d53 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -169,15 +169,12 @@ remove_from_client(struct i915_request *request)
 {
 	struct drm_i915_file_private *file_priv;
 
-	file_priv = READ_ONCE(request->file_priv);
+	file_priv = xchg(&request->file_priv, NULL);
 	if (!file_priv)
 		return;
 
 	spin_lock(&file_priv->mm.lock);
-	if (request->file_priv) {
-		list_del(&request->client_link);
-		request->file_priv = NULL;
-	}
+	list_del(&request->client_link);
 	spin_unlock(&file_priv->mm.lock);
 }
 
@@ -282,7 +279,10 @@ static bool i915_request_retire(struct i915_request *rq)
 
 	local_irq_enable();
 
+	rcu_read_lock();
 	remove_from_client(rq);
+	rcu_read_unlock();
+
 	list_del(&rq->link);
 
 	intel_context_exit(rq->hw_context);
-- 
2.23.0