[Intel-gfx] [PATCH] drm/i915: Call i915_gem_init_userptr() before taking struct_mutex

Chris Wilson chris at chris-wilson.co.uk
Wed Nov 22 18:37:48 UTC 2017


Quoting Tvrtko Ursulin (2017-11-22 17:30:52)
> 
> On 22/11/2017 17:26, Chris Wilson wrote:
> > We don't need struct_mutex to initialise userptr (it just allocates a
> > workqueue for itself etc), but we do need struct_mutex 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 at chris-wilson.co.uk>
> > Cc: Tvrtko Ursulin <tvrtko.ursulin at intel.com>
> > ---
> >   drivers/gpu/drm/i915/i915_gem.c | 11 +++++------
> >   1 file 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;
> > 
> 
> Thanks for taking care of this. Pre-emptive r-b:
> 
> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin at intel.com>

And CI came back green with no new lockdep, so pushed.
Thanks,
-Chris


More information about the Intel-gfx mailing list