linux_dsm_epyc7002/drivers/gpu/drm/i915/intel_wakeref.c

190 lines
4.4 KiB
C
Raw Normal View History

/*
* SPDX-License-Identifier: MIT
*
* Copyright © 2019 Intel Corporation
*/
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
#include <linux/wait_bit.h>
#include "intel_runtime_pm.h"
#include "intel_wakeref.h"
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
static void rpm_get(struct intel_wakeref *wf)
{
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
wf->wakeref = intel_runtime_pm_get(wf->rpm);
}
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
static void rpm_put(struct intel_wakeref *wf)
{
intel_wakeref_t wakeref = fetch_and_zero(&wf->wakeref);
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
intel_runtime_pm_put(wf->rpm, wakeref);
INTEL_WAKEREF_BUG_ON(!wakeref);
}
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
int __intel_wakeref_get_first(struct intel_wakeref *wf)
{
/*
* Treat get/put as different subclasses, as we may need to run
* the put callback from under the shrinker and do not want to
* cross-contanimate that callback with any extra work performed
* upon acquiring the wakeref.
*/
mutex_lock_nested(&wf->mutex, SINGLE_DEPTH_NESTING);
if (!atomic_read(&wf->count)) {
int err;
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
rpm_get(wf);
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
err = wf->ops->get(wf);
if (unlikely(err)) {
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
rpm_put(wf);
mutex_unlock(&wf->mutex);
return err;
}
smp_mb__before_atomic(); /* release wf->count */
}
atomic_inc(&wf->count);
mutex_unlock(&wf->mutex);
INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
return 0;
}
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
static void ____intel_wakeref_put_last(struct intel_wakeref *wf)
{
INTEL_WAKEREF_BUG_ON(atomic_read(&wf->count) <= 0);
if (unlikely(!atomic_dec_and_test(&wf->count)))
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
goto unlock;
drm/i915: Push the wakeref->count deferral to the backend If the backend wishes to defer the wakeref parking, make it responsible for unlocking the wakeref (i.e. bumping the counter). This allows it to time the unlock much more carefully in case it happens to needs the wakeref to be active during its deferral. For instance, during engine parking we may choose to emit an idle barrier (a request). To do so, we borrow the engine->kernel_context timeline and to ensure exclusive access we keep the engine->wakeref.count as 0. However, to submit that request to HW may require a intel_engine_pm_get() (e.g. to keep the submission tasklet alive) and before we allow that we have to rewake our wakeref to avoid a recursive deadlock. <4> [257.742916] IRQs not enabled as expected <4> [257.742930] WARNING: CPU: 0 PID: 0 at kernel/softirq.c:169 __local_bh_enable_ip+0xa9/0x100 <4> [257.742936] Modules linked in: vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic i915 btusb btrtl btbcm btintel snd_hda_intel snd_intel_nhlt bluetooth snd_hda_codec coretemp snd_hwdep crct10dif_pclmul snd_hda_core crc32_pclmul ecdh_generic ecc ghash_clmulni_intel snd_pcm r8169 realtek lpc_ich prime_numbers i2c_hid <4> [257.742991] CPU: 0 PID: 0 Comm: swapper/0 Tainted: G U W 5.3.0-rc3-g5d0a06cd532c-drmtip_340+ #1 <4> [257.742998] Hardware name: GIGABYTE GB-BXBT-1900/MZBAYAB-00, BIOS F6 02/17/2015 <4> [257.743008] RIP: 0010:__local_bh_enable_ip+0xa9/0x100 <4> [257.743017] Code: 37 5b 5d c3 8b 80 50 08 00 00 85 c0 75 a9 80 3d 0b be 25 01 00 75 a0 48 c7 c7 f3 0c 06 ac c6 05 fb bd 25 01 01 e8 77 84 ff ff <0f> 0b eb 89 48 89 ef e8 3b 41 06 00 eb 98 e8 e4 5c f4 ff 5b 5d c3 <4> [257.743025] RSP: 0018:ffffa78600003cb8 EFLAGS: 00010086 <4> [257.743035] RAX: 0000000000000000 RBX: 0000000000000200 RCX: 0000000000010302 <4> [257.743042] RDX: 0000000080010302 RSI: 0000000000000000 RDI: 00000000ffffffff <4> [257.743050] RBP: ffffffffc0494bb3 R08: 0000000000000000 R09: 0000000000000001 <4> [257.743058] R10: 0000000014c8f0e9 R11: 00000000fee2ff8e R12: ffffa23ba8c38008 <4> [257.743065] R13: ffffa23bacc579c0 R14: ffffa23bb7db0f60 R15: ffffa23b9cc8c430 <4> [257.743074] FS: 0000000000000000(0000) GS:ffffa23bbba00000(0000) knlGS:0000000000000000 <4> [257.743082] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 <4> [257.743089] CR2: 00007fe477b20778 CR3: 000000011f72a000 CR4: 00000000001006f0 <4> [257.743096] Call Trace: <4> [257.743104] <IRQ> <4> [257.743265] __i915_request_commit+0x240/0x5d0 [i915] <4> [257.743427] ? __i915_request_create+0x228/0x4c0 [i915] <4> [257.743584] __engine_park+0x64/0x250 [i915] <4> [257.743730] ____intel_wakeref_put_last+0x1c/0x70 [i915] <4> [257.743878] i915_sample+0x2ee/0x310 [i915] <4> [257.744030] ? i915_pmu_cpu_offline+0xb0/0xb0 [i915] <4> [257.744040] __hrtimer_run_queues+0x11e/0x4b0 <4> [257.744068] hrtimer_interrupt+0xea/0x250 <4> [257.744079] ? lockdep_hardirqs_off+0x79/0xd0 <4> [257.744101] smp_apic_timer_interrupt+0x96/0x280 <4> [257.744114] apic_timer_interrupt+0xf/0x20 <4> [257.744125] RIP: 0010:__do_softirq+0xb3/0x4ae v2: Keep the priority_hint assert v3: That assert was desperately trying to point out my bug. Sorry, little assert. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111378 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190813190705.23869-1-chris@chris-wilson.co.uk
2019-08-14 02:07:05 +07:00
/* ops->put() must reschedule its own release on error/deferral */
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
if (likely(!wf->ops->put(wf))) {
rpm_put(wf);
wake_up_var(&wf->wakeref);
}
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
unlock:
mutex_unlock(&wf->mutex);
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
}
void __intel_wakeref_put_last(struct intel_wakeref *wf, unsigned long flags)
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
{
INTEL_WAKEREF_BUG_ON(delayed_work_pending(&wf->work));
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
/* Assume we are not in process context and so cannot sleep. */
if (flags & INTEL_WAKEREF_PUT_ASYNC || !mutex_trylock(&wf->mutex)) {
mod_delayed_work(system_wq, &wf->work,
FIELD_GET(INTEL_WAKEREF_PUT_DELAY, flags));
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
return;
}
____intel_wakeref_put_last(wf);
}
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
static void __intel_wakeref_put_work(struct work_struct *wrk)
{
struct intel_wakeref *wf = container_of(wrk, typeof(*wf), work.work);
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
if (atomic_add_unless(&wf->count, -1, 1))
return;
mutex_lock(&wf->mutex);
____intel_wakeref_put_last(wf);
}
void __intel_wakeref_init(struct intel_wakeref *wf,
struct intel_runtime_pm *rpm,
const struct intel_wakeref_ops *ops,
struct intel_wakeref_lockclass *key)
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
{
wf->rpm = rpm;
wf->ops = ops;
__mutex_init(&wf->mutex, "wakeref.mutex", &key->mutex);
atomic_set(&wf->count, 0);
wf->wakeref = 0;
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
INIT_DELAYED_WORK(&wf->work, __intel_wakeref_put_work);
lockdep_init_map(&wf->work.work.lockdep_map,
"wakeref.work", &key->work, 0);
drm/i915: Defer final intel_wakeref_put to process context As we need to acquire a mutex to serialise the final intel_wakeref_put, we need to ensure that we are in process context at that time. However, we want to allow operation on the intel_wakeref from inside timer and other hardirq context, which means that need to defer that final put to a workqueue. Inside the final wakeref puts, we are safe to operate in any context, as we are simply marking up the HW and state tracking for the potential sleep. It's only the serialisation with the potential sleeping getting that requires careful wait avoidance. This allows us to retain the immediate processing as before (we only need to sleep over the same races as the current mutex_lock). v2: Add a selftest to ensure we exercise the code while lockdep watches. v3: That test was extremely loud and complained about many things! v4: Not a whale! Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=111295 References: https://bugs.freedesktop.org/show_bug.cgi?id=111245 References: https://bugs.freedesktop.org/show_bug.cgi?id=111256 Fixes: 18398904ca9e ("drm/i915: Only recover active engines") Fixes: 51fbd8de87dc ("drm/i915/pmu: Atomically acquire the gt_pm wakeref") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20190808202758.10453-1-chris@chris-wilson.co.uk
2019-08-09 03:27:58 +07:00
}
int intel_wakeref_wait_for_idle(struct intel_wakeref *wf)
{
int err;
might_sleep();
err = wait_var_event_killable(&wf->wakeref,
!intel_wakeref_is_active(wf));
if (err)
return err;
intel_wakeref_unlock_wait(wf);
return 0;
}
static void wakeref_auto_timeout(struct timer_list *t)
{
struct intel_wakeref_auto *wf = from_timer(wf, t, timer);
intel_wakeref_t wakeref;
unsigned long flags;
if (!refcount_dec_and_lock_irqsave(&wf->count, &wf->lock, &flags))
return;
wakeref = fetch_and_zero(&wf->wakeref);
spin_unlock_irqrestore(&wf->lock, flags);
intel_runtime_pm_put(wf->rpm, wakeref);
}
void intel_wakeref_auto_init(struct intel_wakeref_auto *wf,
struct intel_runtime_pm *rpm)
{
spin_lock_init(&wf->lock);
timer_setup(&wf->timer, wakeref_auto_timeout, 0);
refcount_set(&wf->count, 0);
wf->wakeref = 0;
wf->rpm = rpm;
}
void intel_wakeref_auto(struct intel_wakeref_auto *wf, unsigned long timeout)
{
unsigned long flags;
if (!timeout) {
if (del_timer_sync(&wf->timer))
wakeref_auto_timeout(&wf->timer);
return;
}
/* Our mission is that we only extend an already active wakeref */
assert_rpm_wakelock_held(wf->rpm);
if (!refcount_inc_not_zero(&wf->count)) {
spin_lock_irqsave(&wf->lock, flags);
if (!refcount_inc_not_zero(&wf->count)) {
INTEL_WAKEREF_BUG_ON(wf->wakeref);
wf->wakeref = intel_runtime_pm_get_if_in_use(wf->rpm);
refcount_set(&wf->count, 1);
}
spin_unlock_irqrestore(&wf->lock, flags);
}
/*
* If we extend a pending timer, we will only get a single timer
* callback and so need to cancel the local inc by running the
* elided callback to keep the wf->count balanced.
*/
if (mod_timer(&wf->timer, jiffies + timeout))
wakeref_auto_timeout(&wf->timer);
}
void intel_wakeref_auto_fini(struct intel_wakeref_auto *wf)
{
intel_wakeref_auto(wf, 0);
INTEL_WAKEREF_BUG_ON(wf->wakeref);
}