alistair23-linux/drivers/gpu/drm/i915/i915_gem_shrinker.c
Chris Wilson bd784b7cc4 drm/i915: Avoid rcu_barrier() from reclaim paths (shrinker)
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: 0eafec6d32 ("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>
2017-03-14 14:19:51 +00:00

500 lines
15 KiB
C

/*
* Copyright © 2008-2015 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*
*/
#include <linux/oom.h>
#include <linux/shmem_fs.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/pci.h>
#include <linux/dma-buf.h>
#include <linux/vmalloc.h>
#include <drm/drmP.h>
#include <drm/i915_drm.h>
#include "i915_drv.h"
#include "i915_trace.h"
static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
{
switch (mutex_trylock_recursive(&dev->struct_mutex)) {
case MUTEX_TRYLOCK_FAILED:
return false;
case MUTEX_TRYLOCK_SUCCESS:
*unlock = true;
return true;
case MUTEX_TRYLOCK_RECURSIVE:
*unlock = false;
return true;
}
BUG();
}
static bool any_vma_pinned(struct drm_i915_gem_object *obj)
{
struct i915_vma *vma;
list_for_each_entry(vma, &obj->vma_list, obj_link)
if (i915_vma_is_pinned(vma))
return true;
return false;
}
static bool swap_available(void)
{
return get_nr_swap_pages() > 0;
}
static bool can_release_pages(struct drm_i915_gem_object *obj)
{
if (!obj->mm.pages)
return false;
/* Consider only shrinkable ojects. */
if (!i915_gem_object_is_shrinkable(obj))
return false;
/* Only report true if by unbinding the object and putting its pages
* we can actually make forward progress towards freeing physical
* pages.
*
* If the pages are pinned for any other reason than being bound
* to the GPU, simply unbinding from the GPU is not going to succeed
* in releasing our pin count on the pages themselves.
*/
if (atomic_read(&obj->mm.pages_pin_count) > obj->bind_count)
return false;
if (any_vma_pinned(obj))
return false;
/* We can only return physical pages to the system if we can either
* discard the contents (because the user has marked them as being
* purgeable) or if we can move their contents out to swap.
*/
return swap_available() || obj->mm.madv == I915_MADV_DONTNEED;
}
static bool unsafe_drop_pages(struct drm_i915_gem_object *obj)
{
if (i915_gem_object_unbind(obj) == 0)
__i915_gem_object_put_pages(obj, I915_MM_SHRINKER);
return !READ_ONCE(obj->mm.pages);
}
/**
* i915_gem_shrink - Shrink buffer object caches
* @dev_priv: i915 device
* @target: amount of memory to make available, in pages
* @flags: control flags for selecting cache types
*
* This function is the main interface to the shrinker. It will try to release
* up to @target pages of main memory backing storage from buffer objects.
* Selection of the specific caches can be done with @flags. This is e.g. useful
* when purgeable objects should be removed from caches preferentially.
*
* Note that it's not guaranteed that released amount is actually available as
* free system memory - the pages might still be in-used to due to other reasons
* (like cpu mmaps) or the mm core has reused them before we could grab them.
* Therefore code that needs to explicitly shrink buffer objects caches (e.g. to
* avoid deadlocks in memory reclaim) must fall back to i915_gem_shrink_all().
*
* Also note that any kind of pinning (both per-vma address space pins and
* backing storage pins at the buffer object level) result in the shrinker code
* having to skip the object.
*
* Returns:
* The number of pages of backing storage actually released.
*/
unsigned long
i915_gem_shrink(struct drm_i915_private *dev_priv,
unsigned long target, unsigned flags)
{
const struct {
struct list_head *list;
unsigned int bit;
} phases[] = {
{ &dev_priv->mm.unbound_list, I915_SHRINK_UNBOUND },
{ &dev_priv->mm.bound_list, I915_SHRINK_BOUND },
{ NULL, 0 },
}, *phase;
unsigned long count = 0;
bool unlock;
if (!i915_gem_shrinker_lock(&dev_priv->drm, &unlock))
return 0;
trace_i915_gem_shrink(dev_priv, target, flags);
i915_gem_retire_requests(dev_priv);
/*
* Unbinding of objects will require HW access; Let us not wake the
* device just to recover a little memory. If absolutely necessary,
* we will force the wake during oom-notifier.
*/
if ((flags & I915_SHRINK_BOUND) &&
!intel_runtime_pm_get_if_in_use(dev_priv))
flags &= ~I915_SHRINK_BOUND;
/*
* As we may completely rewrite the (un)bound list whilst unbinding
* (due to retiring requests) we have to strictly process only
* one element of the list at the time, and recheck the list
* on every iteration.
*
* In particular, we must hold a reference whilst removing the
* object as we may end up waiting for and/or retiring the objects.
* This might release the final reference (held by the active list)
* and result in the object being freed from under us. This is
* similar to the precautions the eviction code must take whilst
* removing objects.
*
* Also note that although these lists do not hold a reference to
* the object we can safely grab one here: The final object
* unreferencing and the bound_list are both protected by the
* dev->struct_mutex and so we won't ever be able to observe an
* object on the bound_list with a reference count equals 0.
*/
for (phase = phases; phase->list; phase++) {
struct list_head still_in_list;
struct drm_i915_gem_object *obj;
if ((flags & phase->bit) == 0)
continue;
INIT_LIST_HEAD(&still_in_list);
while (count < target &&
(obj = list_first_entry_or_null(phase->list,
typeof(*obj),
global_link))) {
list_move_tail(&obj->global_link, &still_in_list);
if (!obj->mm.pages) {
list_del_init(&obj->global_link);
continue;
}
if (flags & I915_SHRINK_PURGEABLE &&
obj->mm.madv != I915_MADV_DONTNEED)
continue;
if (flags & I915_SHRINK_VMAPS &&
!is_vmalloc_addr(obj->mm.mapping))
continue;
if (!(flags & I915_SHRINK_ACTIVE) &&
(i915_gem_object_is_active(obj) ||
i915_gem_object_is_framebuffer(obj)))
continue;
if (!can_release_pages(obj))
continue;
if (unsafe_drop_pages(obj)) {
/* May arrive from get_pages on another bo */
mutex_lock_nested(&obj->mm.lock,
I915_MM_SHRINKER);
if (!obj->mm.pages) {
__i915_gem_object_invalidate(obj);
list_del_init(&obj->global_link);
count += obj->base.size >> PAGE_SHIFT;
}
mutex_unlock(&obj->mm.lock);
}
}
list_splice_tail(&still_in_list, phase->list);
}
if (flags & I915_SHRINK_BOUND)
intel_runtime_pm_put(dev_priv);
i915_gem_retire_requests(dev_priv);
if (unlock)
mutex_unlock(&dev_priv->drm.struct_mutex);
/* expedite the RCU grace period to free some request slabs */
synchronize_rcu_expedited();
return count;
}
/**
* i915_gem_shrink_all - Shrink buffer object caches completely
* @dev_priv: i915 device
*
* This is a simple wraper around i915_gem_shrink() to aggressively shrink all
* caches completely. It also first waits for and retires all outstanding
* requests to also be able to release backing storage for active objects.
*
* This should only be used in code to intentionally quiescent the gpu or as a
* last-ditch effort when memory seems to have run out.
*
* Returns:
* The number of pages of backing storage actually released.
*/
unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
{
unsigned long freed;
intel_runtime_pm_get(dev_priv);
freed = i915_gem_shrink(dev_priv, -1UL,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_ACTIVE);
intel_runtime_pm_put(dev_priv);
synchronize_rcu(); /* wait for our earlier RCU delayed slab frees */
return freed;
}
static unsigned long
i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
{
struct drm_i915_private *dev_priv =
container_of(shrinker, struct drm_i915_private, mm.shrinker);
struct drm_device *dev = &dev_priv->drm;
struct drm_i915_gem_object *obj;
unsigned long count;
bool unlock;
if (!i915_gem_shrinker_lock(dev, &unlock))
return 0;
i915_gem_retire_requests(dev_priv);
count = 0;
list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_link)
if (can_release_pages(obj))
count += obj->base.size >> PAGE_SHIFT;
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_link) {
if (!i915_gem_object_is_active(obj) && can_release_pages(obj))
count += obj->base.size >> PAGE_SHIFT;
}
if (unlock)
mutex_unlock(&dev->struct_mutex);
return count;
}
static unsigned long
i915_gem_shrinker_scan(struct shrinker *shrinker, struct shrink_control *sc)
{
struct drm_i915_private *dev_priv =
container_of(shrinker, struct drm_i915_private, mm.shrinker);
struct drm_device *dev = &dev_priv->drm;
unsigned long freed;
bool unlock;
if (!i915_gem_shrinker_lock(dev, &unlock))
return SHRINK_STOP;
freed = i915_gem_shrink(dev_priv,
sc->nr_to_scan,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_PURGEABLE);
if (freed < sc->nr_to_scan)
freed += i915_gem_shrink(dev_priv,
sc->nr_to_scan - freed,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND);
if (unlock)
mutex_unlock(&dev->struct_mutex);
return freed;
}
struct shrinker_lock_uninterruptible {
bool was_interruptible;
bool unlock;
};
static bool
i915_gem_shrinker_lock_uninterruptible(struct drm_i915_private *dev_priv,
struct shrinker_lock_uninterruptible *slu,
int timeout_ms)
{
unsigned long timeout = jiffies + msecs_to_jiffies_timeout(timeout_ms);
do {
if (i915_gem_wait_for_idle(dev_priv, 0) == 0 &&
i915_gem_shrinker_lock(&dev_priv->drm, &slu->unlock))
break;
schedule_timeout_killable(1);
if (fatal_signal_pending(current))
return false;
if (time_after(jiffies, timeout)) {
pr_err("Unable to lock GPU to purge memory.\n");
return false;
}
} while (1);
slu->was_interruptible = dev_priv->mm.interruptible;
dev_priv->mm.interruptible = false;
return true;
}
static void
i915_gem_shrinker_unlock_uninterruptible(struct drm_i915_private *dev_priv,
struct shrinker_lock_uninterruptible *slu)
{
dev_priv->mm.interruptible = slu->was_interruptible;
if (slu->unlock)
mutex_unlock(&dev_priv->drm.struct_mutex);
}
static int
i915_gem_shrinker_oom(struct notifier_block *nb, unsigned long event, void *ptr)
{
struct drm_i915_private *dev_priv =
container_of(nb, struct drm_i915_private, mm.oom_notifier);
struct shrinker_lock_uninterruptible slu;
struct drm_i915_gem_object *obj;
unsigned long unevictable, bound, unbound, freed_pages;
if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000))
return NOTIFY_DONE;
freed_pages = i915_gem_shrink_all(dev_priv);
/* Because we may be allocating inside our own driver, we cannot
* assert that there are no objects with pinned pages that are not
* being pointed to by hardware.
*/
unbound = bound = unevictable = 0;
list_for_each_entry(obj, &dev_priv->mm.unbound_list, global_link) {
if (!obj->mm.pages)
continue;
if (!can_release_pages(obj))
unevictable += obj->base.size >> PAGE_SHIFT;
else
unbound += obj->base.size >> PAGE_SHIFT;
}
list_for_each_entry(obj, &dev_priv->mm.bound_list, global_link) {
if (!obj->mm.pages)
continue;
if (!can_release_pages(obj))
unevictable += obj->base.size >> PAGE_SHIFT;
else
bound += obj->base.size >> PAGE_SHIFT;
}
i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu);
if (freed_pages || unbound || bound)
pr_info("Purging GPU memory, %lu pages freed, "
"%lu pages still pinned.\n",
freed_pages, unevictable);
if (unbound || bound)
pr_err("%lu and %lu pages still available in the "
"bound and unbound GPU page lists.\n",
bound, unbound);
*(unsigned long *)ptr += freed_pages;
return NOTIFY_DONE;
}
static int
i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr)
{
struct drm_i915_private *dev_priv =
container_of(nb, struct drm_i915_private, mm.vmap_notifier);
struct shrinker_lock_uninterruptible slu;
struct i915_vma *vma, *next;
unsigned long freed_pages = 0;
int ret;
if (!i915_gem_shrinker_lock_uninterruptible(dev_priv, &slu, 5000))
return NOTIFY_DONE;
/* Force everything onto the inactive lists */
ret = i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
if (ret)
goto out;
intel_runtime_pm_get(dev_priv);
freed_pages += i915_gem_shrink(dev_priv, -1UL,
I915_SHRINK_BOUND |
I915_SHRINK_UNBOUND |
I915_SHRINK_ACTIVE |
I915_SHRINK_VMAPS);
intel_runtime_pm_put(dev_priv);
/* We also want to clear any cached iomaps as they wrap vmap */
list_for_each_entry_safe(vma, next,
&dev_priv->ggtt.base.inactive_list, vm_link) {
unsigned long count = vma->node.size >> PAGE_SHIFT;
if (vma->iomap && i915_vma_unbind(vma) == 0)
freed_pages += count;
}
out:
i915_gem_shrinker_unlock_uninterruptible(dev_priv, &slu);
*(unsigned long *)ptr += freed_pages;
return NOTIFY_DONE;
}
/**
* i915_gem_shrinker_init - Initialize i915 shrinker
* @dev_priv: i915 device
*
* This function registers and sets up the i915 shrinker and OOM handler.
*/
void i915_gem_shrinker_init(struct drm_i915_private *dev_priv)
{
dev_priv->mm.shrinker.scan_objects = i915_gem_shrinker_scan;
dev_priv->mm.shrinker.count_objects = i915_gem_shrinker_count;
dev_priv->mm.shrinker.seeks = DEFAULT_SEEKS;
WARN_ON(register_shrinker(&dev_priv->mm.shrinker));
dev_priv->mm.oom_notifier.notifier_call = i915_gem_shrinker_oom;
WARN_ON(register_oom_notifier(&dev_priv->mm.oom_notifier));
dev_priv->mm.vmap_notifier.notifier_call = i915_gem_shrinker_vmap;
WARN_ON(register_vmap_purge_notifier(&dev_priv->mm.vmap_notifier));
}
/**
* i915_gem_shrinker_cleanup - Clean up i915 shrinker
* @dev_priv: i915 device
*
* This function unregisters the i915 shrinker and OOM handler.
*/
void i915_gem_shrinker_cleanup(struct drm_i915_private *dev_priv)
{
WARN_ON(unregister_vmap_purge_notifier(&dev_priv->mm.vmap_notifier));
WARN_ON(unregister_oom_notifier(&dev_priv->mm.oom_notifier));
unregister_shrinker(&dev_priv->mm.shrinker);
}