From: Rob Clark <[email protected]>
Inspired by https://lore.kernel.org/dri-devel/[email protected]/
it seemed like a good idea to get rid of memory allocation in job_run()
fence signaling path, and use lockdep annotations to yell at us about
anything that could deadlock against shrinker/reclaim. Anything that
can trigger reclaim, or block on any other thread that has triggered
reclaim, can block the GPU shrinker from releasing memory if it is
waiting the job to complete, causing deadlock.
The first two patches decouple allocation from devfreq->lock, and teach
lockdep that devfreq->lock can be acquired in paths that the shrinker
indirectly depends on.
The next three patches do the same for PM QoS. And the next two do a
similar thing for interconnect.
And then finally the last two patches enable the lockdep fence-
signalling annotations.
v2: Switch from embedding hw_fence in submit/job object to preallocating
the hw_fence. Rework "fenced unpin" locking to drop obj lock from
fence signaling path (ie. the part that was still WIP in the first
iteration of the patchset). Adds the final patch to enable fence
signaling annotations now that job_run() and job_free() are safe.
The PM devfreq/QoS and interconnect patches are unchanged.
v3: Mostly unchanged, but series is much smaller now that drm changes
have landed, mostly consisting of the remaining devfreq/qos/
interconnect fixes.
v4: Re-work PM / QoS patch based on Rafael's suggestion
Rob Clark (9):
PM / devfreq: Drop unneed locking to appease lockdep
PM / devfreq: Teach lockdep about locking order
PM / QoS: Fix constraints alloc vs reclaim locking
PM / QoS: Decouple request alloc from dev_pm_qos_mtx
PM / QoS: Teach lockdep about dev_pm_qos_mtx locking order
interconnect: Fix locking for runpm vs reclaim
interconnect: Teach lockdep about icc_bw_lock order
drm/sched: Add (optional) fence signaling annotation
drm/msm: Enable fence signalling annotations
drivers/base/power/qos.c | 98 +++++++++++++++++++-------
drivers/devfreq/devfreq.c | 52 +++++++-------
drivers/gpu/drm/msm/msm_ringbuffer.c | 1 +
drivers/gpu/drm/scheduler/sched_main.c | 9 +++
drivers/interconnect/core.c | 18 ++++-
include/drm/gpu_scheduler.h | 2 +
6 files changed, 127 insertions(+), 53 deletions(-)
--
2.41.0
From: Rob Clark <[email protected]>
Similar to the previous patch, move the allocation out from under
dev_pm_qos_mtx, by speculatively doing the allocation and handle
any race after acquiring dev_pm_qos_mtx by freeing the redundant
allocation.
Signed-off-by: Rob Clark <[email protected]>
---
drivers/base/power/qos.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/drivers/base/power/qos.c b/drivers/base/power/qos.c
index 7e95760d16dc..5ec06585b6d1 100644
--- a/drivers/base/power/qos.c
+++ b/drivers/base/power/qos.c
@@ -930,8 +930,12 @@ s32 dev_pm_qos_get_user_latency_tolerance(struct device *dev)
int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
{
struct dev_pm_qos *qos = dev_pm_qos_constraints_allocate(dev);
+ struct dev_pm_qos_request *req = NULL;
int ret = 0;
+ if (!dev->power.qos->latency_tolerance_req)
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+
mutex_lock(&dev_pm_qos_mtx);
dev_pm_qos_constraints_set(dev, qos);
@@ -945,8 +949,6 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
goto out;
if (!dev->power.qos->latency_tolerance_req) {
- struct dev_pm_qos_request *req;
-
if (val < 0) {
if (val == PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT)
ret = 0;
@@ -954,17 +956,15 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
ret = -EINVAL;
goto out;
}
- req = kzalloc(sizeof(*req), GFP_KERNEL);
if (!req) {
ret = -ENOMEM;
goto out;
}
ret = __dev_pm_qos_add_request(dev, req, DEV_PM_QOS_LATENCY_TOLERANCE, val);
- if (ret < 0) {
- kfree(req);
+ if (ret < 0)
goto out;
- }
dev->power.qos->latency_tolerance_req = req;
+ req = NULL;
} else {
if (val < 0) {
__dev_pm_qos_drop_user_request(dev, DEV_PM_QOS_LATENCY_TOLERANCE);
@@ -976,6 +976,7 @@ int dev_pm_qos_update_user_latency_tolerance(struct device *dev, s32 val)
out:
mutex_unlock(&dev_pm_qos_mtx);
+ kfree(req);
return ret;
}
EXPORT_SYMBOL_GPL(dev_pm_qos_update_user_latency_tolerance);
--
2.41.0
From: Rob Clark <[email protected]>
For cases where icc_bw_set() can be called in callbaths that could
deadlock against shrinker/reclaim, such as runpm resume, we need to
decouple the icc locking. Introduce a new icc_bw_lock for cases where
we need to serialize bw aggregation and update to decouple that from
paths that require memory allocation such as node/link creation/
destruction.
Fixes this lockdep splat:
======================================================
WARNING: possible circular locking dependency detected
6.2.0-rc8-debug+ #554 Not tainted
------------------------------------------------------
ring0/132 is trying to acquire lock:
ffffff80871916d0 (&gmu->lock){+.+.}-{3:3}, at: a6xx_pm_resume+0xf0/0x234
but task is already holding lock:
ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #4 (dma_fence_map){++++}-{0:0}:
__dma_fence_might_wait+0x74/0xc0
dma_resv_lockdep+0x1f4/0x2f4
do_one_initcall+0x104/0x2bc
kernel_init_freeable+0x344/0x34c
kernel_init+0x30/0x134
ret_from_fork+0x10/0x20
-> #3 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}:
fs_reclaim_acquire+0x80/0xa8
slab_pre_alloc_hook.constprop.0+0x40/0x25c
__kmem_cache_alloc_node+0x60/0x1cc
__kmalloc+0xd8/0x100
topology_parse_cpu_capacity+0x8c/0x178
get_cpu_for_node+0x88/0xc4
parse_cluster+0x1b0/0x28c
parse_cluster+0x8c/0x28c
init_cpu_topology+0x168/0x188
smp_prepare_cpus+0x24/0xf8
kernel_init_freeable+0x18c/0x34c
kernel_init+0x30/0x134
ret_from_fork+0x10/0x20
-> #2 (fs_reclaim){+.+.}-{0:0}:
__fs_reclaim_acquire+0x3c/0x48
fs_reclaim_acquire+0x54/0xa8
slab_pre_alloc_hook.constprop.0+0x40/0x25c
__kmem_cache_alloc_node+0x60/0x1cc
__kmalloc+0xd8/0x100
kzalloc.constprop.0+0x14/0x20
icc_node_create_nolock+0x4c/0xc4
icc_node_create+0x38/0x58
qcom_icc_rpmh_probe+0x1b8/0x248
platform_probe+0x70/0xc4
really_probe+0x158/0x290
__driver_probe_device+0xc8/0xe0
driver_probe_device+0x44/0x100
__driver_attach+0xf8/0x108
bus_for_each_dev+0x78/0xc4
driver_attach+0x2c/0x38
bus_add_driver+0xd0/0x1d8
driver_register+0xbc/0xf8
__platform_driver_register+0x30/0x3c
qnoc_driver_init+0x24/0x30
do_one_initcall+0x104/0x2bc
kernel_init_freeable+0x344/0x34c
kernel_init+0x30/0x134
ret_from_fork+0x10/0x20
-> #1 (icc_lock){+.+.}-{3:3}:
__mutex_lock+0xcc/0x3c8
mutex_lock_nested+0x30/0x44
icc_set_bw+0x88/0x2b4
_set_opp_bw+0x8c/0xd8
_set_opp+0x19c/0x300
dev_pm_opp_set_opp+0x84/0x94
a6xx_gmu_resume+0x18c/0x804
a6xx_pm_resume+0xf8/0x234
adreno_runtime_resume+0x2c/0x38
pm_generic_runtime_resume+0x30/0x44
__rpm_callback+0x15c/0x174
rpm_callback+0x78/0x7c
rpm_resume+0x318/0x524
__pm_runtime_resume+0x78/0xbc
adreno_load_gpu+0xc4/0x17c
msm_open+0x50/0x120
drm_file_alloc+0x17c/0x228
drm_open_helper+0x74/0x118
drm_open+0xa0/0x144
drm_stub_open+0xd4/0xe4
chrdev_open+0x1b8/0x1e4
do_dentry_open+0x2f8/0x38c
vfs_open+0x34/0x40
path_openat+0x64c/0x7b4
do_filp_open+0x54/0xc4
do_sys_openat2+0x9c/0x100
do_sys_open+0x50/0x7c
__arm64_sys_openat+0x28/0x34
invoke_syscall+0x8c/0x128
el0_svc_common.constprop.0+0xa0/0x11c
do_el0_svc+0xac/0xbc
el0_svc+0x48/0xa0
el0t_64_sync_handler+0xac/0x13c
el0t_64_sync+0x190/0x194
-> #0 (&gmu->lock){+.+.}-{3:3}:
__lock_acquire+0xe00/0x1060
lock_acquire+0x1e0/0x2f8
__mutex_lock+0xcc/0x3c8
mutex_lock_nested+0x30/0x44
a6xx_pm_resume+0xf0/0x234
adreno_runtime_resume+0x2c/0x38
pm_generic_runtime_resume+0x30/0x44
__rpm_callback+0x15c/0x174
rpm_callback+0x78/0x7c
rpm_resume+0x318/0x524
__pm_runtime_resume+0x78/0xbc
pm_runtime_get_sync.isra.0+0x14/0x20
msm_gpu_submit+0x58/0x178
msm_job_run+0x78/0x150
drm_sched_main+0x290/0x370
kthread+0xf0/0x100
ret_from_fork+0x10/0x20
other info that might help us debug this:
Chain exists of:
&gmu->lock --> mmu_notifier_invalidate_range_start --> dma_fence_map
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(dma_fence_map);
lock(mmu_notifier_invalidate_range_start);
lock(dma_fence_map);
lock(&gmu->lock);
*** DEADLOCK ***
2 locks held by ring0/132:
#0: ffffff8087191170 (&gpu->lock){+.+.}-{3:3}, at: msm_job_run+0x64/0x150
#1: ffffffdb5aee57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150
stack backtrace:
CPU: 7 PID: 132 Comm: ring0 Not tainted 6.2.0-rc8-debug+ #554
Hardware name: Google Lazor (rev1 - 2) with LTE (DT)
Call trace:
dump_backtrace.part.0+0xb4/0xf8
show_stack+0x20/0x38
dump_stack_lvl+0x9c/0xd0
dump_stack+0x18/0x34
print_circular_bug+0x1b4/0x1f0
check_noncircular+0x78/0xac
__lock_acquire+0xe00/0x1060
lock_acquire+0x1e0/0x2f8
__mutex_lock+0xcc/0x3c8
mutex_lock_nested+0x30/0x44
a6xx_pm_resume+0xf0/0x234
adreno_runtime_resume+0x2c/0x38
pm_generic_runtime_resume+0x30/0x44
__rpm_callback+0x15c/0x174
rpm_callback+0x78/0x7c
rpm_resume+0x318/0x524
__pm_runtime_resume+0x78/0xbc
pm_runtime_get_sync.isra.0+0x14/0x20
msm_gpu_submit+0x58/0x178
msm_job_run+0x78/0x150
drm_sched_main+0x290/0x370
kthread+0xf0/0x100
ret_from_fork+0x10/0x20
Signed-off-by: Rob Clark <[email protected]>
---
drivers/interconnect/core.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 5fac448c28fd..e15a92a79df1 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -28,6 +28,7 @@ static LIST_HEAD(icc_providers);
static int providers_count;
static bool synced_state;
static DEFINE_MUTEX(icc_lock);
+static DEFINE_MUTEX(icc_bw_lock);
static struct dentry *icc_debugfs_dir;
static void icc_summary_show_one(struct seq_file *s, struct icc_node *n)
@@ -631,7 +632,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw)
if (WARN_ON(IS_ERR(path) || !path->num_nodes))
return -EINVAL;
- mutex_lock(&icc_lock);
+ mutex_lock(&icc_bw_lock);
old_avg = path->reqs[0].avg_bw;
old_peak = path->reqs[0].peak_bw;
@@ -663,7 +664,7 @@ int icc_set_bw(struct icc_path *path, u32 avg_bw, u32 peak_bw)
apply_constraints(path);
}
- mutex_unlock(&icc_lock);
+ mutex_unlock(&icc_bw_lock);
trace_icc_set_bw_end(path, ret);
@@ -872,6 +873,7 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider)
return;
mutex_lock(&icc_lock);
+ mutex_lock(&icc_bw_lock);
node->provider = provider;
list_add_tail(&node->node_list, &provider->nodes);
@@ -900,6 +902,7 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider)
node->avg_bw = 0;
node->peak_bw = 0;
+ mutex_unlock(&icc_bw_lock);
mutex_unlock(&icc_lock);
}
EXPORT_SYMBOL_GPL(icc_node_add);
@@ -1025,6 +1028,7 @@ void icc_sync_state(struct device *dev)
return;
mutex_lock(&icc_lock);
+ mutex_lock(&icc_bw_lock);
synced_state = true;
list_for_each_entry(p, &icc_providers, provider_list) {
dev_dbg(p->dev, "interconnect provider is in synced state\n");
--
2.41.0
From: Rob Clark <[email protected]>
Based on
https://lore.kernel.org/dri-devel/[email protected]/
but made to be optional.
Signed-off-by: Rob Clark <[email protected]>
Reviewed-by: Luben Tuikov <[email protected]>
---
drivers/gpu/drm/scheduler/sched_main.c | 9 +++++++++
include/drm/gpu_scheduler.h | 2 ++
2 files changed, 11 insertions(+)
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 7b2bfc10c1a5..b0368b815ff5 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -1005,10 +1005,15 @@ static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
static int drm_sched_main(void *param)
{
struct drm_gpu_scheduler *sched = (struct drm_gpu_scheduler *)param;
+ const bool fence_signalling = sched->fence_signalling;
+ bool fence_cookie;
int r;
sched_set_fifo_low(current);
+ if (fence_signalling)
+ fence_cookie = dma_fence_begin_signalling();
+
while (!kthread_should_stop()) {
struct drm_sched_entity *entity = NULL;
struct drm_sched_fence *s_fence;
@@ -1064,6 +1069,10 @@ static int drm_sched_main(void *param)
wake_up(&sched->job_scheduled);
}
+
+ if (fence_signalling)
+ dma_fence_end_signalling(fence_cookie);
+
return 0;
}
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index e95b4837e5a3..58d958ad31a1 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -493,6 +493,7 @@ struct drm_sched_backend_ops {
* @ready: marks if the underlying HW is ready to work
* @free_guilty: A hit to time out handler to free the guilty job.
* @dev: system &struct device
+ * @fence_signalling: Opt in to fence signalling annotations
*
* One scheduler is implemented for each hardware ring.
*/
@@ -517,6 +518,7 @@ struct drm_gpu_scheduler {
bool ready;
bool free_guilty;
struct device *dev;
+ bool fence_signalling;
};
int drm_sched_init(struct drm_gpu_scheduler *sched,
--
2.41.0
From: Rob Clark <[email protected]>
This will make it easier to catch places doing allocations that can
trigger reclaim under devfreq->lock.
Because devfreq->lock is held over various devfreq_dev_profile
callbacks, there might be some fallout if those callbacks do allocations
that can trigger reclaim, but I've looked through the various callback
implementations and don't see anything obvious. If it does trigger any
lockdep splats, those should be fixed.
Signed-off-by: Rob Clark <[email protected]>
---
drivers/devfreq/devfreq.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e5558ec68ce8..81add6064406 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -817,6 +817,12 @@ struct devfreq *devfreq_add_device(struct device *dev,
}
mutex_init(&devfreq->lock);
+
+ /* Teach lockdep about lock ordering wrt. shrinker: */
+ fs_reclaim_acquire(GFP_KERNEL);
+ might_lock(&devfreq->lock);
+ fs_reclaim_release(GFP_KERNEL);
+
devfreq->dev.parent = dev;
devfreq->dev.class = devfreq_class;
devfreq->dev.release = devfreq_dev_release;
--
2.41.0
From: Rob Clark <[email protected]>
In the process of adding lockdep annotation for GPU job_run() path to
catch potential deadlocks against the shrinker/reclaim path, I turned
up this lockdep splat:
======================================================
WARNING: possible circular locking dependency detected
6.2.0-rc8-debug+ #556 Not tainted
------------------------------------------------------
ring0/123 is trying to acquire lock:
ffffff8087219078 (&devfreq->lock){+.+.}-{3:3}, at: devfreq_monitor_resume+0x3c/0xf0
but task is already holding lock:
ffffffd6f64e57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #3 (dma_fence_map){++++}-{0:0}:
__dma_fence_might_wait+0x74/0xc0
dma_resv_lockdep+0x1f4/0x2f4
do_one_initcall+0x104/0x2bc
kernel_init_freeable+0x344/0x34c
kernel_init+0x30/0x134
ret_from_fork+0x10/0x20
-> #2 (mmu_notifier_invalidate_range_start){+.+.}-{0:0}:
fs_reclaim_acquire+0x80/0xa8
slab_pre_alloc_hook.constprop.0+0x40/0x25c
__kmem_cache_alloc_node+0x60/0x1cc
__kmalloc+0xd8/0x100
topology_parse_cpu_capacity+0x8c/0x178
get_cpu_for_node+0x88/0xc4
parse_cluster+0x1b0/0x28c
parse_cluster+0x8c/0x28c
init_cpu_topology+0x168/0x188
smp_prepare_cpus+0x24/0xf8
kernel_init_freeable+0x18c/0x34c
kernel_init+0x30/0x134
ret_from_fork+0x10/0x20
-> #1 (fs_reclaim){+.+.}-{0:0}:
__fs_reclaim_acquire+0x3c/0x48
fs_reclaim_acquire+0x54/0xa8
slab_pre_alloc_hook.constprop.0+0x40/0x25c
__kmem_cache_alloc_node+0x60/0x1cc
__kmalloc_node_track_caller+0xb8/0xe0
kstrdup+0x70/0x90
kstrdup_const+0x38/0x48
kvasprintf_const+0x48/0xbc
kobject_set_name_vargs+0x40/0xb0
dev_set_name+0x64/0x8c
devfreq_add_device+0x31c/0x55c
devm_devfreq_add_device+0x6c/0xb8
msm_devfreq_init+0xa8/0x16c
msm_gpu_init+0x38c/0x570
adreno_gpu_init+0x1b4/0x2b4
a6xx_gpu_init+0x15c/0x3e4
adreno_bind+0x218/0x254
component_bind_all+0x114/0x1ec
msm_drm_bind+0x2b8/0x608
try_to_bring_up_aggregate_device+0x88/0x1a4
__component_add+0xec/0x13c
component_add+0x1c/0x28
dsi_dev_attach+0x28/0x34
dsi_host_attach+0xdc/0x124
mipi_dsi_attach+0x30/0x44
devm_mipi_dsi_attach+0x2c/0x70
ti_sn_bridge_probe+0x298/0x2c4
auxiliary_bus_probe+0x7c/0x94
really_probe+0x158/0x290
__driver_probe_device+0xc8/0xe0
driver_probe_device+0x44/0x100
__device_attach_driver+0x64/0xdc
bus_for_each_drv+0xa0/0xc8
__device_attach+0xd8/0x168
device_initial_probe+0x1c/0x28
bus_probe_device+0x38/0xa0
deferred_probe_work_func+0xc8/0xe0
process_one_work+0x2d8/0x478
process_scheduled_works+0x4c/0x50
worker_thread+0x218/0x274
kthread+0xf0/0x100
ret_from_fork+0x10/0x20
-> #0 (&devfreq->lock){+.+.}-{3:3}:
__lock_acquire+0xe00/0x1060
lock_acquire+0x1e0/0x2f8
__mutex_lock+0xcc/0x3c8
mutex_lock_nested+0x30/0x44
devfreq_monitor_resume+0x3c/0xf0
devfreq_simple_ondemand_handler+0x54/0x7c
devfreq_resume_device+0xa4/0xe8
msm_devfreq_resume+0x78/0xa8
a6xx_pm_resume+0x110/0x234
adreno_runtime_resume+0x2c/0x38
pm_generic_runtime_resume+0x30/0x44
__rpm_callback+0x15c/0x174
rpm_callback+0x78/0x7c
rpm_resume+0x318/0x524
__pm_runtime_resume+0x78/0xbc
pm_runtime_get_sync.isra.0+0x14/0x20
msm_gpu_submit+0x58/0x178
msm_job_run+0x78/0x150
drm_sched_main+0x290/0x370
kthread+0xf0/0x100
ret_from_fork+0x10/0x20
other info that might help us debug this:
Chain exists of:
&devfreq->lock --> mmu_notifier_invalidate_range_start --> dma_fence_map
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
lock(dma_fence_map);
lock(mmu_notifier_invalidate_range_start);
lock(dma_fence_map);
lock(&devfreq->lock);
*** DEADLOCK ***
2 locks held by ring0/123:
#0: ffffff8087201170 (&gpu->lock){+.+.}-{3:3}, at: msm_job_run+0x64/0x150
#1: ffffffd6f64e57e8 (dma_fence_map){++++}-{0:0}, at: msm_job_run+0x68/0x150
stack backtrace:
CPU: 6 PID: 123 Comm: ring0 Not tainted 6.2.0-rc8-debug+ #556
Hardware name: Google Lazor (rev1 - 2) with LTE (DT)
Call trace:
dump_backtrace.part.0+0xb4/0xf8
show_stack+0x20/0x38
dump_stack_lvl+0x9c/0xd0
dump_stack+0x18/0x34
print_circular_bug+0x1b4/0x1f0
check_noncircular+0x78/0xac
__lock_acquire+0xe00/0x1060
lock_acquire+0x1e0/0x2f8
__mutex_lock+0xcc/0x3c8
mutex_lock_nested+0x30/0x44
devfreq_monitor_resume+0x3c/0xf0
devfreq_simple_ondemand_handler+0x54/0x7c
devfreq_resume_device+0xa4/0xe8
msm_devfreq_resume+0x78/0xa8
a6xx_pm_resume+0x110/0x234
adreno_runtime_resume+0x2c/0x38
pm_generic_runtime_resume+0x30/0x44
__rpm_callback+0x15c/0x174
rpm_callback+0x78/0x7c
rpm_resume+0x318/0x524
__pm_runtime_resume+0x78/0xbc
pm_runtime_get_sync.isra.0+0x14/0x20
msm_gpu_submit+0x58/0x178
msm_job_run+0x78/0x150
drm_sched_main+0x290/0x370
kthread+0xf0/0x100
ret_from_fork+0x10/0x20
The issue is that we cannot be holding any lock while doing memory
allocations that is also needed in the job_run (and in the case of
devfreq, this means runpm_resume()) because lockdep sees this as a
potential dependency.
Fortunately there is really no reason to hold the devfreq lock when
we are creating the devfreq device, as it is not yet visible to any
other task. The only reason it was needed was for a lockdep assert
in devfreq_get_freq_range(). Instead, split this up into an internal
fxn that is used in the devfreq_add_device() (where the lock is not
required).
Signed-off-by: Rob Clark <[email protected]>
---
drivers/devfreq/devfreq.c | 46 ++++++++++++++++++---------------------
1 file changed, 21 insertions(+), 25 deletions(-)
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e36cbb920ec8..e5558ec68ce8 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -111,23 +111,13 @@ static unsigned long find_available_max_freq(struct devfreq *devfreq)
return max_freq;
}
-/**
- * devfreq_get_freq_range() - Get the current freq range
- * @devfreq: the devfreq instance
- * @min_freq: the min frequency
- * @max_freq: the max frequency
- *
- * This takes into consideration all constraints.
- */
-void devfreq_get_freq_range(struct devfreq *devfreq,
- unsigned long *min_freq,
- unsigned long *max_freq)
+static void __get_freq_range(struct devfreq *devfreq,
+ unsigned long *min_freq,
+ unsigned long *max_freq)
{
unsigned long *freq_table = devfreq->freq_table;
s32 qos_min_freq, qos_max_freq;
- lockdep_assert_held(&devfreq->lock);
-
/*
* Initialize minimum/maximum frequency from freq table.
* The devfreq drivers can initialize this in either ascending or
@@ -158,6 +148,23 @@ void devfreq_get_freq_range(struct devfreq *devfreq,
if (*min_freq > *max_freq)
*min_freq = *max_freq;
}
+
+/**
+ * devfreq_get_freq_range() - Get the current freq range
+ * @devfreq: the devfreq instance
+ * @min_freq: the min frequency
+ * @max_freq: the max frequency
+ *
+ * This takes into consideration all constraints.
+ */
+void devfreq_get_freq_range(struct devfreq *devfreq,
+ unsigned long *min_freq,
+ unsigned long *max_freq)
+{
+ lockdep_assert_held(&devfreq->lock);
+
+ __get_freq_range(devfreq, min_freq, max_freq);
+}
EXPORT_SYMBOL(devfreq_get_freq_range);
/**
@@ -810,7 +817,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
}
mutex_init(&devfreq->lock);
- mutex_lock(&devfreq->lock);
devfreq->dev.parent = dev;
devfreq->dev.class = devfreq_class;
devfreq->dev.release = devfreq_dev_release;
@@ -823,17 +829,14 @@ struct devfreq *devfreq_add_device(struct device *dev,
if (devfreq->profile->timer < 0
|| devfreq->profile->timer >= DEVFREQ_TIMER_NUM) {
- mutex_unlock(&devfreq->lock);
err = -EINVAL;
goto err_dev;
}
if (!devfreq->profile->max_state || !devfreq->profile->freq_table) {
- mutex_unlock(&devfreq->lock);
err = set_freq_table(devfreq);
if (err < 0)
goto err_dev;
- mutex_lock(&devfreq->lock);
} else {
devfreq->freq_table = devfreq->profile->freq_table;
devfreq->max_state = devfreq->profile->max_state;
@@ -841,19 +844,17 @@ struct devfreq *devfreq_add_device(struct device *dev,
devfreq->scaling_min_freq = find_available_min_freq(devfreq);
if (!devfreq->scaling_min_freq) {
- mutex_unlock(&devfreq->lock);
err = -EINVAL;
goto err_dev;
}
devfreq->scaling_max_freq = find_available_max_freq(devfreq);
if (!devfreq->scaling_max_freq) {
- mutex_unlock(&devfreq->lock);
err = -EINVAL;
goto err_dev;
}
- devfreq_get_freq_range(devfreq, &min_freq, &max_freq);
+ __get_freq_range(devfreq, &min_freq, &max_freq);
devfreq->suspend_freq = dev_pm_opp_get_suspend_opp_freq(dev);
devfreq->opp_table = dev_pm_opp_get_opp_table(dev);
@@ -865,7 +866,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
dev_set_name(&devfreq->dev, "%s", dev_name(dev));
err = device_register(&devfreq->dev);
if (err) {
- mutex_unlock(&devfreq->lock);
put_device(&devfreq->dev);
goto err_out;
}
@@ -876,7 +876,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
devfreq->max_state),
GFP_KERNEL);
if (!devfreq->stats.trans_table) {
- mutex_unlock(&devfreq->lock);
err = -ENOMEM;
goto err_devfreq;
}
@@ -886,7 +885,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
sizeof(*devfreq->stats.time_in_state),
GFP_KERNEL);
if (!devfreq->stats.time_in_state) {
- mutex_unlock(&devfreq->lock);
err = -ENOMEM;
goto err_devfreq;
}
@@ -896,8 +894,6 @@ struct devfreq *devfreq_add_device(struct device *dev,
srcu_init_notifier_head(&devfreq->transition_notifier_list);
- mutex_unlock(&devfreq->lock);
-
err = dev_pm_qos_add_request(dev, &devfreq->user_min_freq_req,
DEV_PM_QOS_MIN_FREQUENCY, 0);
if (err < 0)
--
2.41.0