From 6085c90f499c642bc41a646b0efbdfe60e096c74 Mon Sep 17 00:00:00 2001 From: Konsta Holtta Date: Fri, 6 Mar 2015 16:33:43 +0200 Subject: gpu: nvgpu: add per-channel refcounting Add reference counting for channels, and wait for reference count to get to 0 in gk20a_channel_free() before actually freeing the channel. Also, change free channel tracking a bit by employing a list of free channels, which simplifies the procedure of finding available channels with reference counting. Each use of a channel must have a reference taken before use or held by the caller. Taking a reference of a wild channel pointer may fail, if the channel is either not opened or in a process of being closed. Also, add safeguards for protecting accidental use of closed channels, specifically, by setting ch->g = NULL in channel free. This will make it obvious if freed channel is attempted to be used. The last user of a channel might be the deferred interrupt handler, so wait for deferred interrupts to be processed twice in the channel free procedure: once for providing last notifications to the channel and once to make sure there are no stale pointers left after referencing to the channel has been denied. Finally, fix some races in channel and TSG force reset IOCTL path, by pausing the channel scheduler in gk20a_fifo_recover_ch() and gk20a_fifo_recover_tsg(), while the affected engines have been identified, the appropriate MMU faults triggered, and the MMU faults handled. In this case, make sure that the MMU fault does not attempt to query the hardware about the failing channel or TSG ids. This should make channel recovery more safe also in the regular (i.e., not in the interrupt handler) context. Bug 1530226 Bug 1597493 Bug 1625901 Bug 200076344 Bug 200071810 Change-Id: Ib274876908e18219c64ea41e50ca443df81d957b Signed-off-by: Terje Bergstrom Signed-off-by: Konsta Holtta Signed-off-by: Sami Kiminki Reviewed-on: http://git-master/r/448463 (cherry picked from commit 3f03aeae64ef2af4829e06f5f63062e8ebd21353) Reviewed-on: http://git-master/r/755147 Reviewed-by: Automatic_Commit_Validation_User --- drivers/gpu/nvgpu/gk20a/fifo_gk20a.h | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) (limited to 'drivers/gpu/nvgpu/gk20a/fifo_gk20a.h') diff --git a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.h b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.h index dd320ae1..fdf843d2 100644 --- a/drivers/gpu/nvgpu/gk20a/fifo_gk20a.h +++ b/drivers/gpu/nvgpu/gk20a/fifo_gk20a.h @@ -3,7 +3,7 @@ * * GK20A graphics fifo (gr host) * - * Copyright (c) 2011-2014, NVIDIA CORPORATION. All rights reserved. + * Copyright (c) 2011-2015, NVIDIA CORPORATION. All rights reserved. * * This program is free software; you can redistribute it and/or modify it * under the terms and conditions of the GNU General Public License, @@ -106,7 +106,9 @@ struct fifo_gk20a { u32 userd_entry_size; struct channel_gk20a *channel; - struct mutex ch_inuse_mutex; /* protect unused chid look up */ + /* zero-kref'd channels here */ + struct list_head free_chs; + struct mutex free_chs_mutex; struct tsg_gk20a *tsg; struct mutex tsg_inuse_mutex; @@ -130,7 +132,7 @@ struct fifo_gk20a { } intr; - u32 mmu_fault_engines; + u32 deferred_fault_engines; bool deferred_reset_pending; struct mutex deferred_reset_mutex; }; @@ -157,7 +159,12 @@ int gk20a_fifo_update_runlist(struct gk20a *g, u32 engine_id, u32 hw_chid, int gk20a_fifo_suspend(struct gk20a *g); bool gk20a_fifo_mmu_fault_pending(struct gk20a *g); -void gk20a_fifo_recover(struct gk20a *g, u32 engine_ids, bool verbose); + +void gk20a_fifo_recover(struct gk20a *g, + u32 engine_ids, /* if zero, will be queried from HW */ + u32 hw_id, /* if ~0, will be queried from HW */ + bool hw_id_is_tsg, /* ignored if hw_id == ~0 */ + bool verbose); void gk20a_fifo_recover_ch(struct gk20a *g, u32 hw_chid, bool verbose); void gk20a_fifo_recover_tsg(struct gk20a *g, u32 tsgid, bool verbose); int gk20a_fifo_force_reset_ch(struct channel_gk20a *ch, bool verbose); -- cgit v1.2.2