Rob Clark reports a lockdep splat that involves the prepare_lock chained with the mmap semaphore.
====================================================== [ INFO: possible circular locking dependency detected ] 3.17.0-rc1-00050-g07a489b #802 Tainted: G W ------------------------------------------------------- Xorg.bin/5413 is trying to acquire lock: (prepare_lock){+.+.+.}, at: [<c0781280>] clk_prepare_lock+0x88/0xfc
but task is already holding lock: (qcom_iommu_lock){+.+...}, at: [<c079f664>] qcom_iommu_unmap+0x1c/0x1f0
which lock already depends on the new lock.
the existing dependency chain (in reverse order) is:
-> #4 (qcom_iommu_lock){+.+...}: [<c079f860>] qcom_iommu_map+0x28/0x450 [<c079eb50>] iommu_map+0xc8/0x12c [<c056c1fc>] msm_iommu_map+0xb4/0x130 [<c05697bc>] msm_gem_get_iova_locked+0x9c/0xe8 [<c0569854>] msm_gem_get_iova+0x4c/0x64 [<c0562208>] mdp4_kms_init+0x4c4/0x6c0 [<c056881c>] msm_load+0x2ac/0x34c [<c0545724>] drm_dev_register+0xac/0x108 [<c0547510>] drm_platform_init+0x50/0xf0 [<c0578a60>] try_to_bring_up_master.part.3+0xc8/0x108 [<c0578b48>] component_master_add_with_match+0xa8/0x104 [<c0568294>] msm_pdev_probe+0x64/0x70 [<c057e704>] platform_drv_probe+0x2c/0x60 [<c057cff8>] driver_probe_device+0x108/0x234 [<c057b65c>] bus_for_each_drv+0x64/0x98 [<c057cec0>] device_attach+0x78/0x8c [<c057c590>] bus_probe_device+0x88/0xac [<c057c9b8>] deferred_probe_work_func+0x68/0x9c [<c0259db4>] process_one_work+0x1a0/0x40c [<c025a710>] worker_thread+0x44/0x4d8 [<c025ec54>] kthread+0xd8/0xec [<c020e9a8>] ret_from_fork+0x14/0x2c
-> #3 (&dev->struct_mutex){+.+.+.}: [<c0541188>] drm_gem_mmap+0x38/0xd0 [<c05695b8>] msm_gem_mmap+0xc/0x5c [<c02f0b6c>] mmap_region+0x35c/0x6c8 [<c02f11ec>] do_mmap_pgoff+0x314/0x398 [<c02de1e0>] vm_mmap_pgoff+0x84/0xb4 [<c02ef83c>] SyS_mmap_pgoff+0x94/0xbc [<c020e8e0>] ret_fast_syscall+0x0/0x48
-> #2 (&mm->mmap_sem){++++++}: [<c0321138>] filldir64+0x68/0x180 [<c0333fe0>] dcache_readdir+0x188/0x22c [<c0320ed0>] iterate_dir+0x9c/0x11c [<c03213b0>] SyS_getdents64+0x78/0xe8 [<c020e8e0>] ret_fast_syscall+0x0/0x48
-> #1 (&sb->s_type->i_mutex_key#3){+.+.+.}: [<c03fc544>] __create_file+0x58/0x1dc [<c03fc70c>] debugfs_create_dir+0x1c/0x24 [<c0781c7c>] clk_debug_create_subtree+0x20/0x170 [<c0be2af8>] clk_debug_init+0xec/0x14c [<c0208c70>] do_one_initcall+0x8c/0x1c8 [<c0b9cce4>] kernel_init_freeable+0x13c/0x1dc [<c0877bc4>] kernel_init+0x8/0xe8 [<c020e9a8>] ret_from_fork+0x14/0x2c
-> #0 (prepare_lock){+.+.+.}: [<c087c408>] mutex_lock_nested+0x70/0x3e8 [<c0781280>] clk_prepare_lock+0x88/0xfc [<c0782c50>] clk_prepare+0xc/0x24 [<c079f474>] __enable_clocks.isra.4+0x18/0xa4 [<c079f614>] __flush_iotlb_va+0xe0/0x114 [<c079f6f4>] qcom_iommu_unmap+0xac/0x1f0 [<c079ea3c>] iommu_unmap+0x9c/0xe8 [<c056c2fc>] msm_iommu_unmap+0x64/0x84 [<c0569da4>] msm_gem_free_object+0x11c/0x338 [<c05413ec>] drm_gem_object_handle_unreference_unlocked+0xfc/0x130 [<c0541604>] drm_gem_object_release_handle+0x50/0x68 [<c0447a98>] idr_for_each+0xa8/0xdc [<c0541c10>] drm_gem_release+0x1c/0x28 [<c0540b3c>] drm_release+0x370/0x428 [<c031105c>] __fput+0x98/0x1e8 [<c025d73c>] task_work_run+0xb0/0xfc [<c02477ec>] do_exit+0x2ec/0x948 [<c0247ec0>] do_group_exit+0x4c/0xb8 [<c025180c>] get_signal+0x28c/0x6ac [<c0211204>] do_signal+0xc4/0x3e4 [<c02116cc>] do_work_pending+0xb4/0xc4 [<c020e938>] work_pending+0xc/0x20
other info that might help us debug this:
Chain exists of: prepare_lock --> &dev->struct_mutex --> qcom_iommu_lock
Possible unsafe locking scenario:
CPU0 CPU1 ---- ---- lock(qcom_iommu_lock); lock(&dev->struct_mutex); lock(qcom_iommu_lock); lock(prepare_lock);
*** DEADLOCK ***
3 locks held by Xorg.bin/5413: #0: (drm_global_mutex){+.+.+.}, at: [<c0540800>] drm_release+0x34/0x428 #1: (&dev->struct_mutex){+.+.+.}, at: [<c05413bc>] drm_gem_object_handle_unreference_unlocked+0xcc/0x130 #2: (qcom_iommu_lock){+.+...}, at: [<c079f664>] qcom_iommu_unmap+0x1c/0x1f0
stack backtrace: CPU: 1 PID: 5413 Comm: Xorg.bin Tainted: G W 3.17.0-rc1-00050-g07a489b #802 [<c0216290>] (unwind_backtrace) from [<c0211d8c>] (show_stack+0x10/0x14) [<c0211d8c>] (show_stack) from [<c087a078>] (dump_stack+0x98/0xb8) [<c087a078>] (dump_stack) from [<c027f024>] (print_circular_bug+0x218/0x340) [<c027f024>] (print_circular_bug) from [<c0283e08>] (__lock_acquire+0x1d24/0x20b8) [<c0283e08>] (__lock_acquire) from [<c0284774>] (lock_acquire+0x9c/0xbc) [<c0284774>] (lock_acquire) from [<c087c408>] (mutex_lock_nested+0x70/0x3e8) [<c087c408>] (mutex_lock_nested) from [<c0781280>] (clk_prepare_lock+0x88/0xfc) [<c0781280>] (clk_prepare_lock) from [<c0782c50>] (clk_prepare+0xc/0x24) [<c0782c50>] (clk_prepare) from [<c079f474>] (__enable_clocks.isra.4+0x18/0xa4) [<c079f474>] (__enable_clocks.isra.4) from [<c079f614>] (__flush_iotlb_va+0xe0/0x114) [<c079f614>] (__flush_iotlb_va) from [<c079f6f4>] (qcom_iommu_unmap+0xac/0x1f0) [<c079f6f4>] (qcom_iommu_unmap) from [<c079ea3c>] (iommu_unmap+0x9c/0xe8) [<c079ea3c>] (iommu_unmap) from [<c056c2fc>] (msm_iommu_unmap+0x64/0x84) [<c056c2fc>] (msm_iommu_unmap) from [<c0569da4>] (msm_gem_free_object+0x11c/0x338) [<c0569da4>] (msm_gem_free_object) from [<c05413ec>] (drm_gem_object_handle_unreference_unlocked+0xfc/0x130) [<c05413ec>] (drm_gem_object_handle_unreference_unlocked) from [<c0541604>] (drm_gem_object_release_handle+0x50/0x68) [<c0541604>] (drm_gem_object_release_handle) from [<c0447a98>] (idr_for_each+0xa8/0xdc) [<c0447a98>] (idr_for_each) from [<c0541c10>] (drm_gem_release+0x1c/0x28) [<c0541c10>] (drm_gem_release) from [<c0540b3c>] (drm_release+0x370/0x428) [<c0540b3c>] (drm_release) from [<c031105c>] (__fput+0x98/0x1e8) [<c031105c>] (__fput) from [<c025d73c>] (task_work_run+0xb0/0xfc) [<c025d73c>] (task_work_run) from [<c02477ec>] (do_exit+0x2ec/0x948) [<c02477ec>] (do_exit) from [<c0247ec0>] (do_group_exit+0x4c/0xb8) [<c0247ec0>] (do_group_exit) from [<c025180c>] (get_signal+0x28c/0x6ac) [<c025180c>] (get_signal) from [<c0211204>] (do_signal+0xc4/0x3e4) [<c0211204>] (do_signal) from [<c02116cc>] (do_work_pending+0xb4/0xc4) [<c02116cc>] (do_work_pending) from [<c020e938>] (work_pending+0xc/0x20)
We can break this chain if we don't hold the prepare_lock while creating debugfs directories. We only hold the prepare_lock right now because we're traversing the clock tree recursively and we don't want the hierarchy to change during the traversal. Replacing this traversal with a simple linked list walk allows us to only grab a list lock instead of the prepare_lock, thus breaking the lock chain.
Signed-off-by: Stephen Boyd sboyd@codeaurora.org --- drivers/clk/clk.c | 38 +++++++------------------------------- 1 file changed, 7 insertions(+), 31 deletions(-)
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c index cf5df744cb21..ffec3814915a 100644 --- a/drivers/clk/clk.c +++ b/drivers/clk/clk.c @@ -302,26 +302,12 @@ out: return ret; }
-/* caller must hold prepare_lock */ static int clk_debug_create_subtree(struct clk *clk, struct dentry *pdentry) { - struct clk *child; - int ret = -EINVAL;; - if (!clk || !pdentry) - goto out; - - ret = clk_debug_create_one(clk, pdentry); - - if (ret) - goto out; - - hlist_for_each_entry(child, &clk->children, child_node) - clk_debug_create_subtree(child, pdentry); + return -EINVAL;
- ret = 0; -out: - return ret; + return clk_debug_create_one(clk, pdentry); }
/** @@ -337,15 +323,10 @@ out: */ static int clk_debug_register(struct clk *clk) { - int ret = 0; - if (!inited) - goto out; - - ret = clk_debug_create_subtree(clk, rootdir); + return 0;
-out: - return ret; + return clk_debug_create_subtree(clk, rootdir); }
/** @@ -417,17 +398,12 @@ static int __init clk_debug_init(void) if (!d) return -ENOMEM;
- clk_prepare_lock(); - - hlist_for_each_entry(clk, &clk_root_list, child_node) - clk_debug_create_subtree(clk, rootdir); - - hlist_for_each_entry(clk, &clk_orphan_list, child_node) + mutex_lock(&clk_lookup_lock); + hlist_for_each_entry(clk, &clk_lookup_list, lookup_node) clk_debug_create_subtree(clk, rootdir);
inited = 1; - - clk_prepare_unlock(); + mutex_unlock(&clk_lookup_lock);
return 0; }