| Age | Commit message (Collapse) | Author |
|---|
|
The rcu_barrier() takes the cpu_hotplug mutex which itself is not
reclaim-safe, and so rcu_barrier() is illegal from inside the shrinker.
[ 309.661373] =========================================================
[ 309.661376] [ INFO: possible irq lock inversion dependency detected ]
[ 309.661380] 4.11.0-rc1-CI-CI_DRM_2333+ #1 Tainted: G W
[ 309.661383] ---------------------------------------------------------
[ 309.661386] gem_exec_gttfil/6435 just changed the state of lock:
[ 309.661389] (rcu_preempt_state.barrier_mutex){+.+.-.}, at: [<ffffffff81100731>] _rcu_barrier+0x31/0x160
[ 309.661399] but this lock took another, RECLAIM_FS-unsafe lock in the past:
[ 309.661402] (cpu_hotplug.lock){+.+.+.}
[ 309.661404]
and interrupts could create inverse lock ordering between them.
[ 309.661410]
other info that might help us debug this:
[ 309.661414] Possible interrupt unsafe locking scenario:
[ 309.661417] CPU0 CPU1
[ 309.661419] ---- ----
[ 309.661421] lock(cpu_hotplug.lock);
[ 309.661425] local_irq_disable();
[ 309.661432] lock(rcu_preempt_state.barrier_mutex);
[ 309.661441] lock(cpu_hotplug.lock);
[ 309.661446] <Interrupt>
[ 309.661448] lock(rcu_preempt_state.barrier_mutex);
[ 309.661453]
*** DEADLOCK ***
[ 309.661460] 4 locks held by gem_exec_gttfil/6435:
[ 309.661464] #0: (sb_writers#10){.+.+.+}, at: [<ffffffff8120d83d>] vfs_write+0x17d/0x1f0
[ 309.661475] #1: (debugfs_srcu){......}, at: [<ffffffff81320491>] debugfs_use_file_start+0x41/0xa0
[ 309.661486] #2: (&attr->mutex){+.+.+.}, at: [<ffffffff8123a3e7>] simple_attr_write+0x37/0xe0
[ 309.661495] #3: (&dev->struct_mutex){+.+.+.}, at: [<ffffffffa0091b4a>] i915_drop_caches_set+0x3a/0x150 [i915]
[ 309.661540]
the shortest dependencies between 2nd lock and 1st lock:
[ 309.661547] -> (cpu_hotplug.lock){+.+.+.} ops: 829 {
[ 309.661553] HARDIRQ-ON-W at:
[ 309.661560] __lock_acquire+0x5e5/0x1b50
[ 309.661565] lock_acquire+0xc9/0x220
[ 309.661572] __mutex_lock+0x6e/0x990
[ 309.661576] mutex_lock_nested+0x16/0x20
[ 309.661583] get_online_cpus+0x61/0x80
[ 309.661590] kmem_cache_create+0x25/0x1d0
[ 309.661596] debug_objects_mem_init+0x30/0x249
[ 309.661602] start_kernel+0x341/0x3fe
[ 309.661607] x86_64_start_reservations+0x2a/0x2c
[ 309.661612] x86_64_start_kernel+0x173/0x186
[ 309.661619] verify_cpu+0x0/0xfc
[ 309.661622] SOFTIRQ-ON-W at:
[ 309.661627] __lock_acquire+0x611/0x1b50
[ 309.661632] lock_acquire+0xc9/0x220
[ 309.661636] __mutex_lock+0x6e/0x990
[ 309.661641] mutex_lock_nested+0x16/0x20
[ 309.661646] get_online_cpus+0x61/0x80
[ 309.661650] kmem_cache_create+0x25/0x1d0
[ 309.661655] debug_objects_mem_init+0x30/0x249
[ 309.661660] start_kernel+0x341/0x3fe
[ 309.661664] x86_64_start_reservations+0x2a/0x2c
[ 309.661669] x86_64_start_kernel+0x173/0x186
[ 309.661674] verify_cpu+0x0/0xfc
[ 309.661677] RECLAIM_FS-ON-W at:
[ 309.661682] mark_held_locks+0x6f/0xa0
[ 309.661687] lockdep_trace_alloc+0xb3/0x100
[ 309.661693] kmem_cache_alloc_trace+0x31/0x2e0
[ 309.661699] __smpboot_create_thread.part.1+0x27/0xe0
[ 309.661704] smpboot_create_threads+0x61/0x90
[ 309.661709] cpuhp_invoke_callback+0x9c/0x8a0
[ 309.661713] cpuhp_up_callbacks+0x31/0xb0
[ 309.661718] _cpu_up+0x7a/0xc0
[ 309.661723] do_cpu_up+0x5f/0x80
[ 309.661727] cpu_up+0xe/0x10
[ 309.661734] smp_init+0x71/0xb3
[ 309.661738] kernel_init_freeable+0x94/0x19e
[ 309.661743] kernel_init+0x9/0xf0
[ 309.661748] ret_from_fork+0x2e/0x40
[ 309.661752] INITIAL USE at:
[ 309.661757] __lock_acquire+0x234/0x1b50
[ 309.661761] lock_acquire+0xc9/0x220
[ 309.661766] __mutex_lock+0x6e/0x990
[ 309.661771] mutex_lock_nested+0x16/0x20
[ 309.661775] get_online_cpus+0x61/0x80
[ 309.661780] __cpuhp_setup_state+0x44/0x170
[ 309.661785] page_alloc_init+0x23/0x3a
[ 309.661790] start_kernel+0x124/0x3fe
[ 309.661794] x86_64_start_reservations+0x2a/0x2c
[ 309.661799] x86_64_start_kernel+0x173/0x186
[ 309.661804] verify_cpu+0x0/0xfc
[ 309.661807] }
[ 309.661813] ... key at: [<ffffffff81e37690>] cpu_hotplug+0xb0/0x100
[ 309.661817] ... acquired at:
[ 309.661821] lock_acquire+0xc9/0x220
[ 309.661825] __mutex_lock+0x6e/0x990
[ 309.661829] mutex_lock_nested+0x16/0x20
[ 309.661833] get_online_cpus+0x61/0x80
[ 309.661837] _rcu_barrier+0x9f/0x160
[ 309.661841] rcu_barrier+0x10/0x20
[ 309.661847] netdev_run_todo+0x5f/0x310
[ 309.661852] rtnl_unlock+0x9/0x10
[ 309.661856] default_device_exit_batch+0x133/0x150
[ 309.661862] ops_exit_list.isra.0+0x4d/0x60
[ 309.661866] cleanup_net+0x1d8/0x2c0
[ 309.661872] process_one_work+0x1f4/0x6d0
[ 309.661876] worker_thread+0x49/0x4a0
[ 309.661881] kthread+0x107/0x140
[ 309.661884] ret_from_fork+0x2e/0x40
[ 309.661890] -> (rcu_preempt_state.barrier_mutex){+.+.-.} ops: 179 {
[ 309.661896] HARDIRQ-ON-W at:
[ 309.661901] __lock_acquire+0x5e5/0x1b50
[ 309.661905] lock_acquire+0xc9/0x220
[ 309.661910] __mutex_lock+0x6e/0x990
[ 309.661914] mutex_lock_nested+0x16/0x20
[ 309.661919] _rcu_barrier+0x31/0x160
[ 309.661923] rcu_barrier+0x10/0x20
[ 309.661928] netdev_run_todo+0x5f/0x310
[ 309.661932] rtnl_unlock+0x9/0x10
[ 309.661936] default_device_exit_batch+0x133/0x150
[ 309.661941] ops_exit_list.isra.0+0x4d/0x60
[ 309.661946] cleanup_net+0x1d8/0x2c0
[ 309.661951] process_one_work+0x1f4/0x6d0
[ 309.661955] worker_thread+0x49/0x4a0
[ 309.661960] kthread+0x107/0x140
[ 309.661964] ret_from_fork+0x2e/0x40
[ 309.661968] SOFTIRQ-ON-W at:
[ 309.661972] __lock_acquire+0x611/0x1b50
[ 309.661977] lock_acquire+0xc9/0x220
[ 309.661981] __mutex_lock+0x6e/0x990
[ 309.661986] mutex_lock_nested+0x16/0x20
[ 309.661990] _rcu_barrier+0x31/0x160
[ 309.661995] rcu_barrier+0x10/0x20
[ 309.661999] netdev_run_todo+0x5f/0x310
[ 309.662003] rtnl_unlock+0x9/0x10
[ 309.662008] default_device_exit_batch+0x133/0x150
[ 309.662013] ops_exit_list.isra.0+0x4d/0x60
[ 309.662017] cleanup_net+0x1d8/0x2c0
[ 309.662022] process_one_work+0x1f4/0x6d0
[ 309.662027] worker_thread+0x49/0x4a0
[ 309.662031] kthread+0x107/0x140
[ 309.662035] ret_from_fork+0x2e/0x40
[ 309.662039] IN-RECLAIM_FS-W at:
[ 309.662043] __lock_acquire+0x638/0x1b50
[ 309.662048] lock_acquire+0xc9/0x220
[ 309.662053] __mutex_lock+0x6e/0x990
[ 309.662058] mutex_lock_nested+0x16/0x20
[ 309.662062] _rcu_barrier+0x31/0x160
[ 309.662067] rcu_barrier+0x10/0x20
[ 309.662089] i915_gem_shrink_all+0x33/0x40 [i915]
[ 309.662109] i915_drop_caches_set+0x141/0x150 [i915]
[ 309.662114] simple_attr_write+0xc7/0xe0
[ 309.662119] full_proxy_write+0x4f/0x70
[ 309.662124] __vfs_write+0x23/0x120
[ 309.662128] vfs_write+0xc6/0x1f0
[ 309.662133] SyS_write+0x44/0xb0
[ 309.662138] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 309.662142] INITIAL USE at:
[ 309.662147] __lock_acquire+0x234/0x1b50
[ 309.662151] lock_acquire+0xc9/0x220
[ 309.662156] __mutex_lock+0x6e/0x990
[ 309.662160] mutex_lock_nested+0x16/0x20
[ 309.662165] _rcu_barrier+0x31/0x160
[ 309.662169] rcu_barrier+0x10/0x20
[ 309.662174] netdev_run_todo+0x5f/0x310
[ 309.662178] rtnl_unlock+0x9/0x10
[ 309.662183] default_device_exit_batch+0x133/0x150
[ 309.662188] ops_exit_list.isra.0+0x4d/0x60
[ 309.662192] cleanup_net+0x1d8/0x2c0
[ 309.662197] process_one_work+0x1f4/0x6d0
[ 309.662202] worker_thread+0x49/0x4a0
[ 309.662206] kthread+0x107/0x140
[ 309.662210] ret_from_fork+0x2e/0x40
[ 309.662214] }
[ 309.662220] ... key at: [<ffffffff81e4e1c8>] rcu_preempt_state+0x508/0x780
[ 309.662225] ... acquired at:
[ 309.662229] check_usage_forwards+0x12b/0x130
[ 309.662233] mark_lock+0x360/0x6f0
[ 309.662237] __lock_acquire+0x638/0x1b50
[ 309.662241] lock_acquire+0xc9/0x220
[ 309.662245] __mutex_lock+0x6e/0x990
[ 309.662249] mutex_lock_nested+0x16/0x20
[ 309.662253] _rcu_barrier+0x31/0x160
[ 309.662257] rcu_barrier+0x10/0x20
[ 309.662279] i915_gem_shrink_all+0x33/0x40 [i915]
[ 309.662298] i915_drop_caches_set+0x141/0x150 [i915]
[ 309.662303] simple_attr_write+0xc7/0xe0
[ 309.662307] full_proxy_write+0x4f/0x70
[ 309.662311] __vfs_write+0x23/0x120
[ 309.662315] vfs_write+0xc6/0x1f0
[ 309.662319] SyS_write+0x44/0xb0
[ 309.662323] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 309.662329]
stack backtrace:
[ 309.662335] CPU: 1 PID: 6435 Comm: gem_exec_gttfil Tainted: G W 4.11.0-rc1-CI-CI_DRM_2333+ #1
[ 309.662342] Hardware name: Hewlett-Packard HP Compaq 8100 Elite SFF PC/304Ah, BIOS 786H1 v01.13 07/14/2011
[ 309.662348] Call Trace:
[ 309.662354] dump_stack+0x67/0x92
[ 309.662359] print_irq_inversion_bug.part.19+0x1a4/0x1b0
[ 309.662365] check_usage_forwards+0x12b/0x130
[ 309.662369] mark_lock+0x360/0x6f0
[ 309.662374] ? print_shortest_lock_dependencies+0x1a0/0x1a0
[ 309.662379] __lock_acquire+0x638/0x1b50
[ 309.662383] ? __mutex_unlock_slowpath+0x3e/0x2e0
[ 309.662388] ? trace_hardirqs_on+0xd/0x10
[ 309.662392] ? _rcu_barrier+0x31/0x160
[ 309.662396] lock_acquire+0xc9/0x220
[ 309.662400] ? _rcu_barrier+0x31/0x160
[ 309.662404] ? _rcu_barrier+0x31/0x160
[ 309.662409] __mutex_lock+0x6e/0x990
[ 309.662412] ? _rcu_barrier+0x31/0x160
[ 309.662416] ? _rcu_barrier+0x31/0x160
[ 309.662421] ? synchronize_rcu_expedited+0x35/0xb0
[ 309.662426] ? _raw_spin_unlock_irqrestore+0x52/0x60
[ 309.662434] mutex_lock_nested+0x16/0x20
[ 309.662438] _rcu_barrier+0x31/0x160
[ 309.662442] rcu_barrier+0x10/0x20
[ 309.662464] i915_gem_shrink_all+0x33/0x40 [i915]
[ 309.662484] i915_drop_caches_set+0x141/0x150 [i915]
[ 309.662489] simple_attr_write+0xc7/0xe0
[ 309.662494] full_proxy_write+0x4f/0x70
[ 309.662498] __vfs_write+0x23/0x120
[ 309.662503] ? rcu_read_lock_sched_held+0x75/0x80
[ 309.662507] ? rcu_sync_lockdep_assert+0x2a/0x50
[ 309.662512] ? __sb_start_write+0x102/0x210
[ 309.662516] ? vfs_write+0x17d/0x1f0
[ 309.662520] vfs_write+0xc6/0x1f0
[ 309.662524] ? trace_hardirqs_on_caller+0xe7/0x200
[ 309.662529] SyS_write+0x44/0xb0
[ 309.662533] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 309.662537] RIP: 0033:0x7f507eac24a0
[ 309.662541] RSP: 002b:00007fffda8720e8 EFLAGS: 00000246 ORIG_RAX: 0000000000000001
[ 309.662548] RAX: ffffffffffffffda RBX: ffffffff81482bd3 RCX: 00007f507eac24a0
[ 309.662552] RDX: 0000000000000005 RSI: 00007fffda8720f0 RDI: 0000000000000005
[ 309.662557] RBP: ffffc9000048bf88 R08: 0000000000000000 R09: 000000000000002c
[ 309.662561] R10: 0000000000000014 R11: 0000000000000246 R12: 00007fffda872230
[ 309.662566] R13: 00007fffda872228 R14: 0000000000000201 R15: 00007fffda8720f0
[ 309.662572] ? __this_cpu_preempt_check+0x13/0x20
Fixes: 0eafec6d3244 ("drm/i915: Enable lockless lookup of request tracking via RCU")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100192
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: <stable@vger.kernel.org> # v4.9+
Link: http://patchwork.freedesktop.org/patch/msgid/20170314115019.18127-1-chris@chris-wilson.co.uk
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
(cherry picked from commit bd784b7cc41af7a19cfb705fa6d800e511c4ab02)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170321144531.12344-1-chris@chris-wilson.co.uk
|
|
Pull drm updates from Dave Airlie:
"This is the main pull request for drm for 4.10 kernel.
New drivers:
- ZTE VOU display driver (zxdrm)
- Amlogic Meson Graphic Controller GXBB/GXL/GXM SoCs (meson)
- MXSFB support (mxsfb)
Core:
- Format handling has been reworked
- Better atomic state debugging
- drm_mm leak debugging
- Atomic explicit fencing support
- fbdev helper ops
- Documentation updates
- MST fbcon fixes
Bridge:
- Silicon Image SiI8620 driver
Panel:
- Add support for new simple panels
i915:
- GVT Device model
- Better HDMI2.0 support on skylake
- More watermark fixes
- GPU idling rework for suspend/resume
- DP Audio workarounds
- Scheduler prep-work
- Opregion CADL handling
- GPU scheduler and priority boosting
amdgfx/radeon:
- Support for virtual devices
- New VM manager for non-contig VRAM buffers
- UVD powergating
- SI register header cleanup
- Cursor fixes
- Powermanagement fixes
nouveau:
- Powermangement reworks for better voltage/clock changes
- Atomic modesetting support
- Displayport Multistream (MST) support.
- GP102/104 hang and cursor fixes
- GP106 support
hisilicon:
- hibmc support (BMC chip for aarch64 servers)
armada:
- add tracing support for overlay change
- refactor plane support
- de-midlayer the driver
omapdrm:
- Timing code cleanups
rcar-du:
- R8A7792/R8A7796 support
- Misc fixes.
sunxi:
- A31 SoC display engine support
imx-drm:
- YUV format support
- Cleanup plane atomic update
mali-dp:
- Misc fixes
dw-hdmi:
- Add support for HDMI i2c master controller
tegra:
- IOMMU support fixes
- Error handling fixes
tda998x:
- Fix connector registration
- Improved robustness
- Fix infoframe/audio compliance
virtio:
- fix busid issues
- allocate more vbufs
qxl:
- misc fixes and cleanups.
vc4:
- Fragment shader threading
- ETC1 support
- VEC (tv-out) support
msm:
- A5XX GPU support
- Lots of atomic changes
tilcdc:
- Misc fixes and cleanups.
etnaviv:
- Fix dma-buf export path
- DRAW_INSTANCED support
- fix driver on i.MX6SX
exynos:
- HDMI refactoring
fsl-dcu:
- fbdev changes"
* tag 'drm-for-v4.10' of git://people.freedesktop.org/~airlied/linux: (1343 commits)
drm/nouveau/kms/nv50: fix atomic regression on original G80
drm/nouveau/bl: Do not register interface if Apple GMUX detected
drm/nouveau/bl: Assign different names to interfaces
drm/nouveau/bios/dp: fix handling of LevelEntryTableIndex on DP table 4.2
drm/nouveau/ltc: protect clearing of comptags with mutex
drm/nouveau/gr/gf100-: handle GPC/TPC/MPC trap
drm/nouveau/core: recognise GP106 chipset
drm/nouveau/ttm: wait for bo fence to signal before unmapping vmas
drm/nouveau/gr/gf100-: FECS intr handling is not relevant on proprietary ucode
drm/nouveau/gr/gf100-: properly ack all FECS error interrupts
drm/nouveau/fifo/gf100-: recover from host mmu faults
drm: Add fake controlD* symlinks for backwards compat
drm/vc4: Don't use drm_put_dev
drm/vc4: Document VEC DT binding
drm/vc4: Add support for the VEC (Video Encoder) IP
drm: Add TV connector states to drm_connector_state
drm: Turn DRM_MODE_SUBCONNECTOR_xx definitions into an enum
drm/vc4: Fix ->clock_select setting for the VEC encoder
drm/amdgpu/dce6: Set MASTER_UPDATE_MODE to 0 in resume_mc_access as well
drm/amdgpu: use pin rather than pin_restricted in a few cases
...
|
|
By popular DRM demand, introduce mutex_trylock_recursive() to fix up the
two GEM users.
Without this it is very easy for these drivers to get stuck in
low-memory situations and trigger OOM. Work is in progress to remove the
need for this in at least i915.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Ding Tianhong <dingtianhong@huawei.com>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Jason Low <jason.low2@hpe.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@us.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Terry Rudd <terry.rudd@hpe.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Will Deacon <Will.Deacon@arm.com>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Mike Krinkin reported hangs in the DRM code and bisected it to:
3ab7c086d5ec72585ef0 ("locking/drm: Kill mutex trickery")
Hugh Dickins observed:
"i915_gem_shrinker_lock() is broken: but copy the pattern from
msm_gem_shrinker_lock() and it's okay - patch below."
Pick up the fix in isolation to make sure the bug is fixed, cleanup
patch will follow up.
Originally-From: Hugh Dickins <hughd@google.com>
Reported-by: Hugh Dickins <hughd@google.com>
Reported-by: Mike Krinkin <krinkin.m.u@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: chris@chris-wilson.co.uk
Cc: jason.low2@hpe.com
Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1610301645180.28429@eggly.anvils
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
$ sed -i -r 's/\bglobal_list\b/global_link/g' *.c *.h
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1478081764-8058-1-git-send-email-joonas.lahtinen@linux.intel.com
|
|
Commit 1bec9b0bda3d ("drm/i915/shrinker: Only shmemfs objects
are backed by swap") stopped considering the userptr objects
in shrinker callbacks.
Restore that so idle userptr objects can be discarded in order
to free up memory.
One change further to what was introduced in 1bec9b0bda3d is
to start considering userptr objects in oom but that should
also be a correct thing to do.
v2: Introduce I915_GEM_OBJECT_IS_SHRINKABLE. (Chris Wilson)
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 1bec9b0bda3d ("drm/i915/shrinker: Only shmemfs objects are backed by swap")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: <stable@vger.kernel.org>
Link: http://patchwork.freedesktop.org/patch/msgid/1478011450-6634-1-git-send-email-tvrtko.ursulin@linux.intel.com
|
|
The shrinker may appear to recurse into obj->mm.lock as the shrinker may
be called from a direct reclaim path whilst handling get_pages. We
filter out recursing on the same obj->mm.lock by inspecting
obj->mm.pages, but we do want to take the lock on a second object in
order to reap their pages. lockdep spots the recursion on the same
lockclass and needs annotation to avoid a false positive. To keep the
two paths distinct, create an enum to indicate which subclass of
obj->mm.lock we are using. This removes the false positive and avoids
masking real bugs.
Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161101121134.27504-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
During shrinking, we walk over the list of objects searching for
victims. Any that are not removed are put back into the global list.
Currently, they are put back in order (at the front) which means they
will be first to be scanned again. If we instead move them to the rear
of the list, we will scan new potential victims on the next pass and
waste less time rescanning unshrinkable objects. Normally the lists are
kept in rough order to shrinking (with object least frequently used at
the start), by moving just scanned objects to the rear we are
acknowledging that they are still in use.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161101084843.3961-3-chris@chris-wilson.co.uk
|
|
In the shrinker, we can safely remove an empty object (obj->mm.pages ==
NULL) after having discarded the pages because we are holding the
struct_mutex.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161101084843.3961-2-chris@chris-wilson.co.uk
|
|
As we may allocate from within the obj->mm.lock we may enter the
shrinker for direct reclaim. Operating on the current object is
prevented by checking for obj->mm.pages (which is only set as the last
operation in the allocation path). However, we need to identify the
single recursion of accessing another object's obj->mm.lock as the two
locks have identical class and so appear to be the same to lockdep,
convincing it that a deadlock is possible. Use mutex_lock_nested() to
remove the false positive.
[ 2165.945734] =================================
[ 2165.945749] [ INFO: inconsistent lock state ]
[ 2165.945765] 4.9.0-rc2+ #2 Tainted: G W
[ 2165.945781] ---------------------------------
[ 2165.945796] inconsistent {RECLAIM_FS-ON-W} -> {IN-RECLAIM_FS-W} usage.
[ 2165.945816] kswapd0/62 [HC0[0]:SC0[0]:HE1:SE1] takes: (&obj->mm.lock){+.+.?.}, at: [<ffffffffc0289a1f>] i915_gem_shrink+0x29f/0x500 [i915]
[ 2165.945904] {RECLAIM_FS-ON-W} state was registered at:
[ 2165.945931] [<ffffffffb10bd50f>] mark_held_locks+0x6f/0xa0
[ 2165.945956] [<ffffffffb10bf889>] lockdep_trace_alloc+0x69/0xc0
[ 2165.945982] [<ffffffffb11eea53>] kmem_cache_alloc_trace+0x33/0x2a0
[ 2165.946019] [<ffffffffc028a28a>] i915_gem_object_get_pages_stolen+0x6a/0xd0 [i915]
[ 2165.946060] [<ffffffffc027e1d0>] ____i915_gem_object_get_pages+0x20/0x60 [i915]
[ 2165.946098] [<ffffffffc027e268>] __i915_gem_object_get_pages+0x58/0x70 [i915]
[ 2165.946138] [<ffffffffc028a3dc>] _i915_gem_object_create_stolen+0xec/0x120 [i915]
[ 2165.946177] [<ffffffffc028af73>] i915_gem_object_create_stolen_for_preallocated+0xf3/0x3f0 [i915]
[ 2165.946222] [<ffffffffc02bae43>] intel_alloc_initial_plane_obj.isra.125+0xd3/0x200 [i915]
[ 2165.946266] [<ffffffffc02cb1c1>] intel_modeset_init+0x931/0x1530 [i915]
[ 2165.946301] [<ffffffffc023d584>] i915_driver_load+0xa14/0x14a0 [i915]
[ 2165.946335] [<ffffffffc0248aff>] i915_pci_probe+0x4f/0x70 [i915]
[ 2165.946362] [<ffffffffb13cc452>] local_pci_probe+0x42/0xa0
[ 2165.946386] [<ffffffffb13cd903>] pci_device_probe+0x103/0x150
[ 2165.946411] [<ffffffffb14adeb3>] driver_probe_device+0x223/0x430
[ 2165.946436] [<ffffffffb14ae1a3>] __driver_attach+0xe3/0xf0
[ 2165.946461] [<ffffffffb14ab943>] bus_for_each_dev+0x73/0xc0
[ 2165.946485] [<ffffffffb14ad5ee>] driver_attach+0x1e/0x20
[ 2165.946508] [<ffffffffb14ad003>] bus_add_driver+0x173/0x270
[ 2165.946533] [<ffffffffb14aee70>] driver_register+0x60/0xe0
[ 2165.946557] [<ffffffffb13cbd6d>] __pci_register_driver+0x5d/0x60
[ 2165.946606] [<ffffffffc0378057>] soundcore_open+0x17/0x230 [soundcore]
[ 2165.946636] [<ffffffffb1000450>] do_one_initcall+0x50/0x180
[ 2165.946661] [<ffffffffb117fd2d>] do_init_module+0x5f/0x1f1
[ 2165.946685] [<ffffffffb1108964>] load_module+0x2174/0x2a80
[ 2165.946709] [<ffffffffb11094df>] SYSC_finit_module+0xdf/0x110
[ 2165.946734] [<ffffffffb110952e>] SyS_finit_module+0xe/0x10
[ 2165.946758] [<ffffffffb1742aea>] entry_SYSCALL_64_fastpath+0x18/0xad
[ 2165.946776] irq event stamp: 90871
[ 2165.946788] hardirqs last enabled at (90871):
[ 2165.946805] [<ffffffffb173e9da>] __mutex_unlock_slowpath+0x11a/0x1c0
[ 2165.946823] hardirqs last disabled at (90870):
[ 2165.946839] [<ffffffffb173e91b>] __mutex_unlock_slowpath+0x5b/0x1c0
[ 2165.946856] softirqs last enabled at (90858):
[ 2165.946872] [<ffffffffb174581a>] __do_softirq+0x39a/0x4c6
[ 2165.946887] softirqs last disabled at (90671):
[ 2165.946902] [<ffffffffb1066cea>] irq_exit+0xea/0xf0
[ 2165.946916] other info that might help us debug this:
[ 2165.946936] Possible unsafe locking scenario:
[ 2165.946955] CPU0
[ 2165.946965] ----
[ 2165.946975] lock(&obj->mm.lock);
[ 2165.947000] <Interrupt>
[ 2165.947010] lock(&obj->mm.lock);
[ 2165.947035] *** DEADLOCK ***
[ 2165.947054] 2 locks held by kswapd0/62:
[ 2165.947067] #0: (shrinker_rwsem){++++..}, at: [<ffffffffb119a20e>] shrink_slab.part.40+0x5e/0x5d0
[ 2165.947120] #1: (&dev->struct_mutex){+.+.+.}, at: [<ffffffffc028954b>] i915_gem_shrinker_lock+0x1b/0x60 [i915]
[ 2165.948909] stack backtrace:
[ 2165.950650] CPU: 2 PID: 62 Comm: kswapd0 Tainted: G W 4.9.0-rc2+ #2
[ 2165.951587] Hardware name: LENOVO 80MX/Lenovo E31-80, BIOS DCCN34WW(V2.03) 12/01/2015
[ 2165.952484] ffffc90000b5f8c8 ffffffffb137f645 ffff88016c5a2700 ffffffffb25f20a0
[ 2165.953395] ffffc90000b5f918 ffffffffb10bcecd 0000000000000000 ffff880100000001
[ 2165.954305] 0000000000000001 000000000000000a ffff88016c5a2fd0 ffff88016c5a2700
[ 2165.955240] Call Trace:
[ 2165.956170] [<ffffffffb137f645>] dump_stack+0x68/0x93
[ 2165.957071] [<ffffffffb10bcecd>] print_usage_bug+0x1dd/0x1f0
[ 2165.957979] [<ffffffffb10bd439>] mark_lock+0x559/0x5c0
[ 2165.958875] [<ffffffffb10bc3f0>] ? print_shortest_lock_dependencies+0x1b0/0x1b0
[ 2165.959829] [<ffffffffb10be04d>] __lock_acquire+0x66d/0x12a0
[ 2165.960729] [<ffffffffb11ef541>] ? __slab_free+0xa1/0x340
[ 2165.961625] [<ffffffffb10dba5d>] ? debug_lockdep_rcu_enabled+0x1d/0x20
[ 2165.962530] [<ffffffffb10bd50f>] ? mark_held_locks+0x6f/0xa0
[ 2165.963457] [<ffffffffb10bf0b0>] lock_acquire+0xf0/0x1f0
[ 2165.964368] [<ffffffffc0289a1f>] ? i915_gem_shrink+0x29f/0x500 [i915]
[ 2165.965269] [<ffffffffc0289a1f>] ? i915_gem_shrink+0x29f/0x500 [i915]
[ 2165.966150] [<ffffffffb173d837>] mutex_lock_nested+0x77/0x420
[ 2165.967030] [<ffffffffc0289a1f>] ? i915_gem_shrink+0x29f/0x500 [i915]
[ 2165.967952] [<ffffffffc027c7a1>] ? __i915_gem_object_put_pages.part.58+0x161/0x1b0 [i915]
[ 2165.968835] [<ffffffffc0289a1f>] i915_gem_shrink+0x29f/0x500 [i915]
[ 2165.969712] [<ffffffffc0289e40>] i915_gem_shrinker_scan+0x70/0xb0 [i915]
[ 2165.970591] [<ffffffffb119a3ae>] shrink_slab.part.40+0x1fe/0x5d0
[ 2165.971504] [<ffffffffb119f19c>] shrink_node+0x22c/0x320
[ 2165.972371] [<ffffffffb11a05fb>] kswapd+0x38b/0x9b0
[ 2165.973238] [<ffffffffb11a0270>] ? mem_cgroup_shrink_node+0x330/0x330
[ 2165.974068] [<ffffffffb108630f>] kthread+0xff/0x120
[ 2165.974929] [<ffffffffb1086210>] ? kthread_park+0x60/0x60
[ 2165.975847] [<ffffffffb1742d57>] ret_from_fork+0x27/0x40
Reported-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Fixes: 1233e2db199d ("drm/i915: Move object backing storage manipulation...")
Testcase: igt/gem_ctx_create/maximum-swap
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>
Link: http://patchwork.freedesktop.org/patch/msgid/20161031124048.30355-1-chris@chris-wilson.co.uk
|
|
We want to hide the latency of releasing objects and their backing
storage from the submission, so we move the actual free to a worker.
This allows us to switch to struct_mutex freeing of the object in the
next patch.
Furthermore, if we know that the object we are dereferencing remains valid
for the duration of our access, we can forgo the usual synchronisation
barriers and atomic reference counting. To ensure this we defer freeing
an object til after an RCU grace period, such that any lookup of the
object within an RCU read critical section will remain valid until
after we exit that critical section. We also employ this delay for
rate-limiting the serialisation on reallocation - we have to slow down
object creation in order to prevent resource starvation (in particular,
files).
v2: Return early in i915_gem_tiling() ioctl to skip over superfluous
work on error.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161028125858.23563-19-chris@chris-wilson.co.uk
|
|
Break the allocation of the backing storage away from struct_mutex into
a per-object lock. This allows parallel page allocation, provided we can
do so outside of struct_mutex (i.e. set-domain-ioctl, pwrite, GTT
fault), i.e. before execbuf! The increased cost of the atomic counters
are hidden behind i915_vma_pin() for the typical case of execbuf, i.e.
as the object is typically bound between execbufs, the page_pin_count is
static. The cost will be felt around set-domain and pwrite, but offset
by the improvement from reduced struct_mutex contention.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161028125858.23563-14-chris@chris-wilson.co.uk
|
|
The plan is to move obj->pages out from under the struct_mutex into its
own per-object lock. We need to prune any assumption of the struct_mutex
from the get_pages/put_pages backends, and to make it easier we pass
around the sg_table to operate on rather than indirectly via the obj.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161028125858.23563-13-chris@chris-wilson.co.uk
|
|
The plan is to make obtaining the backing storage for the object avoid
struct_mutex (i.e. use its own locking). The first step is to update the
API so that normal users only call pin/unpin whilst working on the
backing storage.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161028125858.23563-12-chris@chris-wilson.co.uk
|
|
Poking at lock internals is not cool. Since I'm going to change the
implementation this will break, take it out.
Tested-by: Jason Low <jason.low2@hpe.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rob Clark <robdclark@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
|
|
Treat a framebuffer reference with the same priority as an active
reference whilst shrinking. Framebuffers are likely to be reused and
typically cost more to migrate to and from GPU memory (on LLC
architectures we need to clflush), so defer the temptation to purge them
during a kswapd run until we have run out of cheap buffers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: John Harrison <john.c.harrison@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20161012124824.23521-1-chris@chris-wilson.co.uk
|
|
In the next patch we want to handle reset directly by a locked waiter in
order to avoid issues with returning before the reset is handled. To
handle the reset, we must first know whether we hold the struct_mutex.
If we do not hold the struct_mtuex we can not perform the reset, but we do
not block the reset worker either (and so we can just continue to wait for
request completion) - otherwise we must relinquish the mutex.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-10-chris@chris-wilson.co.uk
|
|
We need finer control over wakeup behaviour during i915_wait_request(),
so expand the current bool interruptible to a bitmask.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20160909131201.16673-9-chris@chris-wilson.co.uk
|
|
After removing the user of this wart, we can remove the wart entirely.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-10-git-send-email-chris@chris-wilson.co.uk
|
|
We can now wait for the GPU (all engines) to become idle without
requiring the struct_mutex. Inside the shrinker, we need to currently
take the struct_mutex in order to purge objects and to purge the objects
we need the GPU to be idle - causing a stall whilst we hold the
struct_mutex. We can hide most of that stall by performing the wait
before taking the struct_mutex and only doing essential waits for
new rendering on objects to be freed.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-8-git-send-email-chris@chris-wilson.co.uk
|
|
The principal motivation for this was to try and eliminate the
struct_mutex from i915_gem_suspend - but we still need to hold the mutex
current for the i915_gem_context_lost(). (The issue there is that there
may be an indirect lockdep cycle between cpu_hotplug (i.e. suspend) and
struct_mutex via the stop_machine().) For the moment, enabling last
request tracking for the engine, allows us to do busyness checking and
waiting without requiring the struct_mutex - which is useful in its own
right.
As a side-effect of having a robust means for tracking engine busyness,
we can replace our other busyness heuristic, that of comparing against
the last submitted seqno. For paranoid reasons, we have a semi-ordered
check of that seqno inside the hangchecker, which we can now improve to
an ordered check of the engine's busyness (removing a locked xchg in the
process).
v2: Pass along "bool interruptible" as being unlocked we cannot rely on
i915->mm.interruptible being stable or even under our control.
v3: Replace check Ironlake i915_gpu_busy() with the common precalculated value
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470388464-28458-6-git-send-email-chris@chris-wilson.co.uk
|
|
If we enable RCU for the requests (providing a grace period where we can
inspect a "dead" request before it is freed), we can allow callers to
carefully perform lockless lookup of an active request.
However, by enabling deferred freeing of requests, we can potentially
hog a lot of memory when dealing with tens of thousands of requests per
second - with a quick insertion of a synchronize_rcu() inside our
shrinker callback, that issue disappears.
v2: Currently, it is our responsibility to handle reclaim i.e. to avoid
hogging memory with the delayed slab frees. At the moment, we wait for a
grace period in the shrinker, and block for all RCU callbacks on oom.
Suggested alternatives focus on flushing our RCU callback when we have a
certain number of outstanding request frees, and blocking on that flush
after a second high watermark. (So rather than wait for the system to
run out of memory, we stop issuing requests - both are nondeterministic.)
Paul E. McKenney wrote:
Another approach is synchronize_rcu() after some largish number of
requests. The advantage of this approach is that it throttles the
production of callbacks at the source. The corresponding disadvantage
is that it slows things up.
Another approach is to use call_rcu(), but if the previous call_rcu()
is still in flight, block waiting for it. Yet another approach is
the get_state_synchronize_rcu() / cond_synchronize_rcu() pair. The
idea is to do something like this:
cond_synchronize_rcu(cookie);
cookie = get_state_synchronize_rcu();
You would of course do an initial get_state_synchronize_rcu() to
get things going. This would not block unless there was less than
one grace period's worth of time between invocations. But this
assumes a busy system, where there is almost always a grace period
in flight. But you can make that happen as follows:
cond_synchronize_rcu(cookie);
cookie = get_state_synchronize_rcu();
call_rcu(&my_rcu_head, noop_function);
Note that you need additional code to make sure that the old callback
has completed before doing a new one. Setting and clearing a flag
with appropriate memory ordering control suffices (e.g,. smp_load_acquire()
and smp_store_release()).
v3: More comments on compiler and processor order of operations within
the RCU lookup and discover we can use rcu_access_pointer() here instead.
v4: Wrap i915_gem_active_get_rcu() to take the rcu_read_lock itself.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: "Goel, Akash" <akash.goel@intel.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-25-git-send-email-chris@chris-wilson.co.uk
|
|
We are motivated to avoid using a bitfield for obj->active for a couple
of reasons. Firstly, we wish to document our lockless read of obj->active
using READ_ONCE inside i915_gem_busy_ioctl() and that requires an
integral type (i.e. not a bitfield). Secondly, gcc produces abysmal code
when presented with a bitfield and that shows up high on the profiles of
request tracking (mainly due to excess memory traffic as it converts
the bitfield to a register and back and generates frequent AGI in the
process).
v2: BIT, break up a long line in compute the other engines, new paint
for i915_gem_object_is_active (now i915_gem_object_get_active).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-23-git-send-email-chris@chris-wilson.co.uk
|
|
In preparation to perform some magic to speed up i915_vma_pin(), which
is among the hottest of hot paths in execbuf, refactor all the bitfields
accessed by i915_vma_pin() into a single unified set of flags.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-16-git-send-email-chris@chris-wilson.co.uk
|
|
When we call i915_vma_unbind(), we will wait upon outstanding rendering.
This will also trigger a retirement phase, which may update the object
lists. If, we extend request tracking to the VMA itself (rather than
keep it at the encompassing object), then there is a potential that the
obj->vma_list be modified for other elements upon i915_vma_unbind(). As
a result, if we walk over the object list and call i915_vma_unbind(), we
need to be prepared for that list to change.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470293567-10811-8-git-send-email-chris@chris-wilson.co.uk
|
|
Since we may have VMA allocated for an object, but we interrupted their
binding, there is a disparity between have elements on the obj->vma_list
and being bound. i915_gem_obj_bound_any() does this check, but this is
not rigorously observed - add an explicit count to make it easier.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470293567-10811-7-git-send-email-chris@chris-wilson.co.uk
|
|
list_first_entry_or_null() can generate better code than using
if (!list_empty()) {ptr = list_first_entry()) ..., so put it to use.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1469432687-22756-3-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1469530913-17180-2-git-send-email-chris@chris-wilson.co.uk
|
|
Ultimately wraps kref_put(), so adopt its nomenclature for consistency
with other subsystems.
s/drm_gem_object_unreference/i915_gem_object_put/
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1469005202-9659-6-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1469017917-15134-5-git-send-email-chris@chris-wilson.co.uk
|
|
Ultimately wraps kref_get(), so adopt its nomenclature for consistency
with other subsystems.
s/drm_gem_object_reference/i915_gem_object_get/
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1469005202-9659-5-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Dave Gordon <david.s.gordon@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1469017917-15134-4-git-send-email-chris@chris-wilson.co.uk
|
|
In commit 7608a43d8f2e ("locking/mutexes: Use MUTEX_SPIN_ON_OWNER when
appropriate") the owner field in the mutex was updated from being
dependent upon CONFIG_SMP to using optimistic spin. Update our peek
function to suite.
Fixes:7608a43d8f2e ("locking/mutexes: Use MUTEX_SPIN_ON_OWNER...")
Reported-by: Hong Liu <hong.liu@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1468244777-4888-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
|
|
Since drm_i915_private is now a subclass of drm_device we do not need to
chase the drm_i915_private->dev backpointer and can instead simply
access drm_i915_private->drm directly.
text data bss dec hex filename
1068757 4565 416 1073738 10624a drivers/gpu/drm/i915/i915.ko
1066949 4565 416 1071930 105b3a drivers/gpu/drm/i915/i915.ko
Created by the coccinelle script:
@@
struct drm_i915_private *d;
identifier i;
@@
(
- d->dev->i
+ d->drm.i
|
- d->dev
+ &d->drm
)
and for good measure the dev_priv->dev backpointer was removed entirely.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467711623-2905-4-git-send-email-chris@chris-wilson.co.uk
|
|
As we inspect obj->active to decide how many objects we can shrink (we
only shrink idle objects), it helps to flush the active lists first
in order to have a more accurate count of available objects.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1467390209-3576-1-git-send-email-chris@chris-wilson.co.uk
|
|
We only need to force a switch to the kernel context placeholder during
eviction. All other uses of i915_gpu_idle() just want to wait until
existing work on the GPU is idle. Rename i915_gpu_idle() to
i915_gem_wait_for_idle() to avoid any implications about "parking" the
context first.
v2: Tweak an error message if the wait fails for the ilk vtd w/a
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1466776558-21516-6-git-send-email-chris@chris-wilson.co.uk
|
|
text data bss dec hex filename
6309351 3578714 696320 10584385 a18141 vmlinux
6308391 3578714 696320 10583425 a17d81 vmlinux
Almost 1KiB of code reduction.
v2: More s/INTEL_INFO()->gen/INTEL_GEN()/ and IS_GENx() conversions
text data bss dec hex filename
6304579 3578778 696320 10579677 a16edd vmlinux
6303427 3578778 696320 10578525 a16a5d vmlinux
Now over 1KiB!
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1462545621-30125-3-git-send-email-chris@chris-wilson.co.uk
|
|
i915_gem_shrink() will scan the bound list only if device is not
suspended but in OOM failure scenario it becomes absolutely necessary
to release as much memory as possible. Also in allocation failure from
vmap address space, it is incumbent on the Driver to reap all its
vmaps. So, adding rpm get/put in i915_gem_shrinker_oom() and
i915_gem_shrinker_vmap() to ensure shrinking of bound objects as well.
Signed-off-by: Praveen Paneri <praveen.paneri@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1462178429-13449-2-git-send-email-praveen.paneri@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
|
|
When the system is running low on memory, gem shrinker is invoked.
In this process objects will be unbounded from GTT and unbinding process
will require access to GTT(GTTADR) and also to fence register potentially.
That requires a resume of gfx device, if suspended, in the shrinker path.
Considering the power leakage due to intermediate resume, perform unbinding
operation only if device is already runtime active.
v2: Use newly implemented intel_runtime_pm_get_if_in_use (Chris)
Signed-off-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Praveen Paneri <praveen.paneri@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: http://patchwork.freedesktop.org/patch/msgid/1462178429-13449-1-git-send-email-praveen.paneri@intel.com
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
|
|
By tracking the iomapping on the VMA itself, we can share that area
between multiple users. Also by only revoking the iomapping upon
unbinding from the mappable portion of the GGTT, we can keep that iomap
across multiple invocations (e.g. execlists context pinning).
Note that by moving the iounnmap tracking to the VMA, we actually end up
fixing a leak of the iomapping in intel_fbdev.
v1.5: Rebase prompted by Tvrtko
v2: Drop dev_priv parameter, we can recover the i915_ggtt from the vma.
v3: Move handling of ioremap space exhaustion to vmap_purge and also
allow vmallocs to recover old iomaps. Add Tvrtko's kerneldoc.
v4: Fix a use-after-free in shrinker and rearrange i915_vma_iomap
v5: Back to i915_vm_to_ggtt
v6: Use i915_vma_pin_iomap and i915_vma_unpin_iomap to mark critical
sections and ensure the VMA cannot be reaped whilst mapped.
v7: Move i915_vma_iounmap so that consumers of the API are not tempted,
and add iomem annotations
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1461833819-3991-5-git-send-email-chris@chris-wilson.co.uk
|
|
Since we can only swap out shmemfs objects, those are the only ones that
can influence the ability of the shrinker to free pages. Currently, all
non-shmemfs objects have a raised pages_pin_count to protect them from
the shrinker, so this just makes the logic for can_release_pages()
clearer (and safer in future so that we don't over estimate our ability
to free up pages from future non-swappable objects).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1461150592-27818-3-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
|
|
Inside the shrinker we call can_release_pages() to indicate whether or
not we can make forward progress in freeing up memory by unbinding that
object. When adding our report to oom, we should be using the same
logic.
Whilst here, change the reporting from bytes to pages so that it looks
smaller to the user!, is consistent with the neighbouring oom report
itself which displays counts in pages, and makes the unsigned long
overflow less likely.
v2: Split oversized format string into two lines
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1461150592-27818-2-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
When iterating over the bound list, we expect all objects there to have
their pages pinned (by the bound VMA). So only report those objects with
additional pin count on their pages as "pinned". These should be those
objects used for display and hardware access.
Reported-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Akash Goel <akash.goel@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1461150592-27818-1-git-send-email-chris@chris-wilson.co.uk
|
|
When called because we have run out of vmap address space, we only need
to recover objects that have vmappings and not all.
v2: Start using is_vmalloc_addr()
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1460113874-17366-5-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
|
|
Both the oom and vmap notifier callbacks have a loop to acquire the
struct_mutex and set the device as uninterruptible, within a certain
time. Refactor the common code into a pair of functions.
Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1459848145-24042-1-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
If the core runs out of vmap address space, it will call a notifier in
case any driver can reap some of its vmaps. As i915.ko is possibily
holding onto vmap address space that could be recovered, hook into the
notifier chain and try and reap objects holding onto vmaps.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Roman Pen <r.peniaev@gmail.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kahola <mika.kahola@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1459777603-23618-4-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Since we only attempt to purge an object if can_release_pages() report
true, we should also only add it to the count of potential recoverable
pages when can_release_pages() is true.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Akash Goel <akash.goel@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1459777603-23618-2-git-send-email-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
|
|
Elsewhere we have adopted the convention of using '_link' to denote
elements in the list (and '_list' for the actual list_head itself), and
that the name should indicate which list the link belongs to (and
preferrably not just where the link is being stored).
s/vma_link/obj_link/ (we iterate over obj->vma_list)
s/mm_list/vm_link/ (we iterate over vm->[in]active_list)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
|
|
Factor out the common GEM shrinker clean-up code and call the shrinker
init function from the same function from where the corresponding
shrinker clean-up function is called. Also add sanity checking to the
shrinker and OOM registration calls.
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: David Weinehall <david.weinehall@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1453209992-25995-4-git-send-email-imre.deak@intel.com
|
|
If the system has no available swap pages, we cannot make forward
progress in the shrinker by releasing active pages, only by releasing
purgeable pages which are immediately reaped. Take total_swap_pages into
account when counting up available objects to be shrunk and subsequently
shrinking them. By doing so, we avoid unbinding objects that cannot be
shrunk and so wasting CPU cycles flushing those objects from the GPU to
the system and then immediately back again (as they will more than
likely be reused shortly after).
Based on a patch by Akash Goel.
v2: frontswap registers extra swap pages available for the system, so it
is already include in the count of available swap pages.
v3: Use get_nr_swap_pages() to query the currently available amount of
swap space. This should also stop us from shrinking the GPU buffers if
we ever run out of swap space. Though at that point, we would expect the
oom-notifier to be running and failing miserably...
Reported-by: Akash Goel <akash.goel@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: linux-mm@kvack.org
Cc: Akash Goel <akash.goel@intel.com>
Cc: sourab.gupta@intel.com
Link: http://patchwork.freedesktop.org/patch/msgid/1449244734-25733-2-git-send-email-chris@chris-wilson.co.uk
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
Exclude active GPU pages from the purview of the background shrinker
(kswapd), as these cause uncontrollable GPU stalls. Given that the
shrinker is rerun until the freelists are satisfied, we should have
opportunity in subsequent passes to recover the pages once idle. If the
machine does run out of memory entirely, we have the forced idling in the
oom-notifier as a means of releasing all the pages we can before an oom
is prematurely executed.
Note that this relies upon an up-front retire_requests to keep the
inactive list in shape, which was added in a previous patch, mostly as
execlist ctx pinning band-aids.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Damien Lespiau <damien.lespiau@intel.com>
[danvet: Add note about retire_requests.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
We can forgo an evict-everything here as the shrinker operation itself
will unbind any vma as required. If we explicitly idle the GPU through a
switch to the default context, we not only create a request in an
illegal context (e.g. whilst shrinking during execbuf with a request
already allocated), but switching to the default context will not free
up the memory backing the active contexts - unless in the unlikely
situation that context had already been closed (and just kept arrive by
being the current context). The saving is near zero and the danger real.
To compensate for the loss of the forced retire, add a couple of
retire-requests to i915_gem_shirnk() - this should help free up any
transitive cache from the requests.
Note that the second retire_requests is for the benefit of the
hand-rolled execlist ctx active tracking: We need to manually kick
requests to get those unpinned again. Once that's fixed we can try to
remove this again.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add summary of why we need a pile of retire_requests.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
|
Often it is very useful to know why we suddenly purge vast tracts of
memory and surprisingly up until now we didn't even have a tracepoint
for when we shrink our memory.
Note that there are slab_start/end tracepoints already, but those
don't cover the internal recursion when we directly call into our
shrinker code. Hence a separate tracepoint seems justified. Also note
that we don't really need a separate tracepoint for the actual amount
of pages freed since we already have an unbind tracpoint for that.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
[danvet: Add a note that there's also slab_start/end and why they're
insufficient.]
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
|
