diff options
author | Chris Wilson <chris@chris-wilson.co.uk> | 2017-11-22 17:26:21 +0000 |
---|---|---|
committer | Chris Wilson <chris@chris-wilson.co.uk> | 2017-11-22 17:40:37 +0000 |
commit | ee48700dd57d9ce783ec40f035b324d0b75632e4 (patch) | |
tree | 25fa2830c20864760f3e575d1b49292d0ca563ce | |
parent | 62d0fe45297d213ba923e252dcdbcee6f41a3bc6 (diff) |
drm/i915: Call i915_gem_init_userptr() before taking struct_mutex
We don't need struct_mutex to initialise userptr (it just allocates a
workqueue for itself etc), but we do need struct_mutex later on in
i915_gem_init() in order to feed requests onto the HW.
This should break the chain
[ 385.697902] ======================================================
[ 385.697907] WARNING: possible circular locking dependency detected
[ 385.697913] 4.14.0-CI-Patchwork_7234+ #1 Tainted: G U
[ 385.697917] ------------------------------------------------------
[ 385.697922] perf_pmu/2631 is trying to acquire lock:
[ 385.697927] (&mm->mmap_sem){++++}, at: [<ffffffff811bfe1e>] __might_fault+0x3e/0x90
[ 385.697941]
but task is already holding lock:
[ 385.697946] (&cpuctx_mutex){+.+.}, at: [<ffffffff8116fe8c>] perf_event_ctx_lock_nested+0xbc/0x1d0
[ 385.697957]
which lock already depends on the new lock.
[ 385.697963]
the existing dependency chain (in reverse order) is:
[ 385.697970]
-> #4 (&cpuctx_mutex){+.+.}:
[ 385.697980] __mutex_lock+0x86/0x9b0
[ 385.697985] perf_event_init_cpu+0x5a/0x90
[ 385.697991] perf_event_init+0x178/0x1a4
[ 385.697997] start_kernel+0x27f/0x3f1
[ 385.698003] verify_cpu+0x0/0xfb
[ 385.698006]
-> #3 (pmus_lock){+.+.}:
[ 385.698015] __mutex_lock+0x86/0x9b0
[ 385.698020] perf_event_init_cpu+0x21/0x90
[ 385.698025] cpuhp_invoke_callback+0xca/0xc00
[ 385.698030] _cpu_up+0xa7/0x170
[ 385.698035] do_cpu_up+0x57/0x70
[ 385.698039] smp_init+0x62/0xa6
[ 385.698044] kernel_init_freeable+0x97/0x193
[ 385.698050] kernel_init+0xa/0x100
[ 385.698055] ret_from_fork+0x27/0x40
[ 385.698058]
-> #2 (cpu_hotplug_lock.rw_sem){++++}:
[ 385.698068] cpus_read_lock+0x39/0xa0
[ 385.698073] apply_workqueue_attrs+0x12/0x50
[ 385.698078] __alloc_workqueue_key+0x1d8/0x4d8
[ 385.698134] i915_gem_init_userptr+0x5f/0x80 [i915]
[ 385.698176] i915_gem_init+0x7c/0x390 [i915]
[ 385.698213] i915_driver_load+0x99e/0x15c0 [i915]
[ 385.698250] i915_pci_probe+0x33/0x90 [i915]
[ 385.698256] pci_device_probe+0xa1/0x130
[ 385.698262] driver_probe_device+0x293/0x440
[ 385.698267] __driver_attach+0xde/0xe0
[ 385.698272] bus_for_each_dev+0x5c/0x90
[ 385.698277] bus_add_driver+0x16d/0x260
[ 385.698282] driver_register+0x57/0xc0
[ 385.698287] do_one_initcall+0x3e/0x160
[ 385.698292] do_init_module+0x5b/0x1fa
[ 385.698297] load_module+0x2374/0x2dc0
[ 385.698302] SyS_finit_module+0xaa/0xe0
[ 385.698307] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 385.698311]
-> #1 (&dev->struct_mutex){+.+.}:
[ 385.698320] __mutex_lock+0x86/0x9b0
[ 385.698361] i915_mutex_lock_interruptible+0x4c/0x130 [i915]
[ 385.698403] i915_gem_fault+0x206/0x760 [i915]
[ 385.698409] __do_fault+0x1a/0x70
[ 385.698413] __handle_mm_fault+0x7c4/0xdb0
[ 385.698417] handle_mm_fault+0x154/0x300
[ 385.698440] __do_page_fault+0x2d6/0x570
[ 385.698445] page_fault+0x22/0x30
[ 385.698449]
-> #0 (&mm->mmap_sem){++++}:
[ 385.698459] lock_acquire+0xaf/0x200
[ 385.698464] __might_fault+0x68/0x90
[ 385.698470] _copy_to_user+0x1e/0x70
[ 385.698475] perf_read+0x1aa/0x290
[ 385.698480] __vfs_read+0x23/0x120
[ 385.698484] vfs_read+0xa3/0x150
[ 385.698488] SyS_read+0x45/0xb0
[ 385.698493] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 385.698497]
other info that might help us debug this:
[ 385.698505] Chain exists of:
&mm->mmap_sem --> pmus_lock --> &cpuctx_mutex
[ 385.698517] Possible unsafe locking scenario:
[ 385.698522] CPU0 CPU1
[ 385.698526] ---- ----
[ 385.698529] lock(&cpuctx_mutex);
[ 385.698553] lock(pmus_lock);
[ 385.698558] lock(&cpuctx_mutex);
[ 385.698564] lock(&mm->mmap_sem);
[ 385.698568]
*** DEADLOCK ***
[ 385.698574] 1 lock held by perf_pmu/2631:
[ 385.698578] #0: (&cpuctx_mutex){+.+.}, at: [<ffffffff8116fe8c>] perf_event_ctx_lock_nested+0xbc/0x1d0
[ 385.698589]
stack backtrace:
[ 385.698595] CPU: 3 PID: 2631 Comm: perf_pmu Tainted: G U 4.14.0-CI-Patchwork_7234+ #1
[ 385.698602] Hardware name: /NUC6CAYB, BIOS AYAPLCEL.86A.0040.2017.0619.1722 06/19/2017
[ 385.698609] Call Trace:
[ 385.698615] dump_stack+0x5f/0x86
[ 385.698621] print_circular_bug.isra.18+0x1d0/0x2c0
[ 385.698627] __lock_acquire+0x19c3/0x1b60
[ 385.698634] ? generic_exec_single+0x77/0xe0
[ 385.698640] ? lock_acquire+0xaf/0x200
[ 385.698644] lock_acquire+0xaf/0x200
[ 385.698650] ? __might_fault+0x3e/0x90
[ 385.698655] __might_fault+0x68/0x90
[ 385.698660] ? __might_fault+0x3e/0x90
[ 385.698665] _copy_to_user+0x1e/0x70
[ 385.698670] perf_read+0x1aa/0x290
[ 385.698675] __vfs_read+0x23/0x120
[ 385.698682] ? __fget+0x101/0x1f0
[ 385.698686] vfs_read+0xa3/0x150
[ 385.698691] SyS_read+0x45/0xb0
[ 385.698696] entry_SYSCALL_64_fastpath+0x1c/0xb1
[ 385.698701] RIP: 0033:0x7ff1c46876ed
[ 385.698705] RSP: 002b:00007fff13552f90 EFLAGS: 00000293 ORIG_RAX: 0000000000000000
[ 385.698712] RAX: ffffffffffffffda RBX: ffffc90000647ff0 RCX: 00007ff1c46876ed
[ 385.698718] RDX: 0000000000000010 RSI: 00007fff13552fa0 RDI: 0000000000000005
[ 385.698723] RBP: 000056063d300580 R08: 0000000000000000 R09: 0000000000000060
[ 385.698729] R10: 0000000000000000 R11: 0000000000000293 R12: 0000000000000046
[ 385.698734] R13: 00007fff13552c6f R14: 00007ff1c6279d00 R15: 00007ff1c6279a40
Testcase: igt/perf_pmu
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20171122172621.16158-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
-rw-r--r-- | drivers/gpu/drm/i915/i915_gem.c | 11 |
1 files changed, 5 insertions, 6 deletions
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 21ca680e9e63..e03d6c2554e2 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5116,8 +5116,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv) { int ret; - mutex_lock(&dev_priv->drm.struct_mutex); - /* * We need to fallback to 4K pages since gvt gtt handling doesn't * support huge page entries - we will need to check either hypervisor @@ -5137,18 +5135,19 @@ int i915_gem_init(struct drm_i915_private *dev_priv) dev_priv->gt.cleanup_engine = intel_engine_cleanup; } + ret = i915_gem_init_userptr(dev_priv); + if (ret) + return ret; + /* This is just a security blanket to placate dragons. * On some systems, we very sporadically observe that the first TLBs * used by the CS may be stale, despite us poking the TLB reset. If * we hold the forcewake during initialisation these problems * just magically go away. */ + mutex_lock(&dev_priv->drm.struct_mutex); intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL); - ret = i915_gem_init_userptr(dev_priv); - if (ret) - goto out_unlock; - ret = i915_gem_init_ggtt(dev_priv); if (ret) goto out_unlock; |