Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 10 2月, 2021 1 次提交
  3. 02 2月, 2021 1 次提交
  5. 16 5月, 2020 4 次提交
  7. 21 4月, 2020 1 次提交
  9. 26 3月, 2020 1 次提交
  11. 11 3月, 2020 1 次提交
  13. 27 2月, 2020 1 次提交
  15. 04 2月, 2020 1 次提交
  17. 27 1月, 2020 1 次提交
  19. 23 12月, 2019 1 次提交
  21. 22 12月, 2019 1 次提交
  23. 20 12月, 2019 1 次提交
  25. 18 12月, 2019 1 次提交
  27. 08 12月, 2019 1 次提交
    • C
      drm/i915: Avoid calling i915_gem_object_unbind holding object lock · 8b1c78e0
      由 Chris Wilson 提交于 
      In the extreme case, we may wish to wait on an rcu-barrier to reap stale
vm to purge the last of the object bindings. However, we are not allowed
to use rcu_barrier() beneath the dma_resv (i.e. object) lock and do not
take lightly the prospect of unlocking a mutex deep in the bowels of the
routine. i915_gem_object_unbind() itself does not need the object lock,
and it turns out the callers do not need to the unbind as part of a
locked sequence around set-cache-level, so rearrange the code to avoid
taking the object lock in the callers.

<4> [186.816311] ======================================================
<4> [186.816313] WARNING: possible circular locking dependency detected
<4> [186.816316] 5.4.0-rc8-CI-CI_DRM_7486+ #1 Tainted: G     U
<4> [186.816318] ------------------------------------------------------
<4> [186.816320] perf_pmu/1321 is trying to acquire lock:
<4> [186.816322] ffff88849487c4d8 (&mm->mmap_sem#2){++++}, at: __might_fault+0x39/0x90
<4> [186.816331]
but task is already holding lock:
<4> [186.816333] ffffe8ffffa05008 (&cpuctx_mutex){+.+.}, at: perf_event_ctx_lock_nested+0xa9/0x1b0
<4> [186.816339]
which lock already depends on the new lock.

<4> [186.816341]
the existing dependency chain (in reverse order) is:
<4> [186.816343]
-> #6 (&cpuctx_mutex){+.+.}:
<4> [186.816349]        __mutex_lock+0x9a/0x9d0
<4> [186.816352]        perf_event_init_cpu+0xa4/0x140
<4> [186.816357]        perf_event_init+0x19d/0x1cd
<4> [186.816362]        start_kernel+0x372/0x4f4
<4> [186.816365]        secondary_startup_64+0xa4/0xb0
<4> [186.816381]
-> #5 (pmus_lock){+.+.}:
<4> [186.816385]        __mutex_lock+0x9a/0x9d0
<4> [186.816387]        perf_event_init_cpu+0x6b/0x140
<4> [186.816404]        cpuhp_invoke_callback+0x9b/0x9d0
<4> [186.816406]        _cpu_up+0xa2/0x140
<4> [186.816409]        do_cpu_up+0x61/0xa0
<4> [186.816411]        smp_init+0x57/0x96
<4> [186.816413]        kernel_init_freeable+0xac/0x1c7
<4> [186.816416]        kernel_init+0x5/0x100
<4> [186.816419]        ret_from_fork+0x24/0x50
<4> [186.816421]
-> #4 (cpu_hotplug_lock.rw_sem){++++}:
<4> [186.816424]        cpus_read_lock+0x34/0xd0
<4> [186.816427]        rcu_barrier+0xaa/0x190
<4> [186.816429]        kernel_init+0x21/0x100
<4> [186.816431]        ret_from_fork+0x24/0x50
<4> [186.816433]
-> #3 (rcu_state.barrier_mutex){+.+.}:
<4> [186.816436]        __mutex_lock+0x9a/0x9d0
<4> [186.816438]        rcu_barrier+0x23/0x190
<4> [186.816502]        i915_gem_object_unbind+0x3a6/0x400 [i915]
<4> [186.816537]        i915_gem_object_set_cache_level+0x32/0x90 [i915]
<4> [186.816571]        i915_gem_object_pin_to_display_plane+0x5d/0x160 [i915]
<4> [186.816612]        intel_pin_and_fence_fb_obj+0x9e/0x200 [i915]
<4> [186.816679]        intel_plane_pin_fb+0x3f/0xd0 [i915]
<4> [186.816717]        intel_prepare_plane_fb+0x130/0x520 [i915]
<4> [186.816722]        drm_atomic_helper_prepare_planes+0x85/0x110
<4> [186.816761]        intel_atomic_commit+0xc6/0x350 [i915]
<4> [186.816764]        drm_atomic_helper_update_plane+0xed/0x110
<4> [186.816768]        setplane_internal+0x97/0x190
<4> [186.816770]        drm_mode_setplane+0xcd/0x190
<4> [186.816773]        drm_ioctl_kernel+0xa7/0xf0
<4> [186.816775]        drm_ioctl+0x2e1/0x390
<4> [186.816778]        do_vfs_ioctl+0xa0/0x6f0
<4> [186.816780]        ksys_ioctl+0x35/0x60
<4> [186.816782]        __x64_sys_ioctl+0x11/0x20
<4> [186.816785]        do_syscall_64+0x4f/0x210
<4> [186.816787]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [186.816789]
-> #2 (reservation_ww_class_mutex){+.+.}:
<4> [186.816793]        __ww_mutex_lock.constprop.15+0xc3/0x1090
<4> [186.816795]        ww_mutex_lock+0x39/0x70
<4> [186.816798]        dma_resv_lockdep+0x10e/0x1f7
<4> [186.816800]        do_one_initcall+0x58/0x2ff
<4> [186.816802]        kernel_init_freeable+0x137/0x1c7
<4> [186.816804]        kernel_init+0x5/0x100
<4> [186.816806]        ret_from_fork+0x24/0x50
<4> [186.816808]
-> #1 (reservation_ww_class_acquire){+.+.}:
<4> [186.816811]        dma_resv_lockdep+0xec/0x1f7
<4> [186.816813]        do_one_initcall+0x58/0x2ff
<4> [186.816815]        kernel_init_freeable+0x137/0x1c7
<4> [186.816817]        kernel_init+0x5/0x100
<4> [186.816819]        ret_from_fork+0x24/0x50
<4> [186.816820]
-> #0 (&mm->mmap_sem#2){++++}:
<4> [186.816824]        __lock_acquire+0x1328/0x15d0
<4> [186.816826]        lock_acquire+0xa7/0x1c0
<4> [186.816828]        __might_fault+0x63/0x90
<4> [186.816831]        _copy_to_user+0x1e/0x80
<4> [186.816834]        perf_read+0x200/0x2b0
<4> [186.816836]        vfs_read+0x96/0x160
<4> [186.816838]        ksys_read+0x9f/0xe0
<4> [186.816839]        do_syscall_64+0x4f/0x210
<4> [186.816841]        entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4> [186.816843]
other info that might help us debug this:

<4> [186.816846] Chain exists of:
  &mm->mmap_sem#2 --> pmus_lock --> &cpuctx_mutex

<4> [186.816849]  Possible unsafe locking scenario:

<4> [186.816851]        CPU0                    CPU1
<4> [186.816853]        ----                    ----
<4> [186.816854]   lock(&cpuctx_mutex);
<4> [186.816856]                                lock(pmus_lock);
<4> [186.816858]                                lock(&cpuctx_mutex);
<4> [186.816860]   lock(&mm->mmap_sem#2);
<4> [186.816861]
 *** DEADLOCK ***

Closes: https://gitlab.freedesktop.org/drm/intel/issues/728Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NAndi Shyti <andi.shyti@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191206105527.1130413-5-chris@chris-wilson.co.uk
      8b1c78e0
  29. 01 11月, 2019 2 次提交
  31. 24 10月, 2019 1 次提交
  33. 05 10月, 2019 1 次提交
  35. 04 10月, 2019 3 次提交
    • C
      drm/i915/overlay: Drop struct_mutex guard · cb5eb072
      由 Chris Wilson 提交于 
      The overlay uses the modeset mutex to control itself and only required
the struct_mutex for requests, which is now obsolete.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-16-chris@chris-wilson.co.uk
      cb5eb072
    • C
      drm/i915: Coordinate i915_active with its own mutex · b1e3177b
      由 Chris Wilson 提交于 
      Forgo the struct_mutex serialisation for i915_active, and interpose its
own mutex handling for active/retire.

This is a multi-layered sleight-of-hand. First, we had to ensure that no
active/retire callbacks accidentally inverted the mutex ordering rules,
nor assumed that they were themselves serialised by struct_mutex. More
challenging though, is the rule over updating elements of the active
rbtree. Instead of the whole i915_active now being serialised by
struct_mutex, allocations/rotations of the tree are serialised by the
i915_active.mutex and individual nodes are serialised by the caller
using the i915_timeline.mutex (we need to use nested spinlocks to
interact with the dma_fence callback lists).

The pain point here is that instead of a single mutex around execbuf, we
now have to take a mutex for active tracker (one for each vma, context,
etc) and a couple of spinlocks for each fence update. The improvement in
fine grained locking allowing for multiple concurrent clients
(eventually!) should be worth it in typical loads.

v2: Add some comments that barely elucidate anything :(
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-6-chris@chris-wilson.co.uk
      b1e3177b
    • C
      drm/i915: Pull i915_vma_pin under the vm->mutex · 2850748e
      由 Chris Wilson 提交于 
      Replace the struct_mutex requirement for pinning the i915_vma with the
local vm->mutex instead. Note that the vm->mutex is tainted by the
shrinker (we require unbinding from inside fs-reclaim) and so we cannot
allocate while holding that mutex. Instead we have to preallocate
workers to do allocate and apply the PTE updates after we have we
reserved their slot in the drm_mm (using fences to order the PTE writes
with the GPU work and with later unbind).

In adding the asynchronous vma binding, one subtle requirement is to
avoid coupling the binding fence into the backing object->resv. That is
the asynchronous binding only applies to the vma timeline itself and not
to the pages as that is a more global timeline (the binding of one vma
does not need to be ordered with another vma, nor does the implicit GEM
fencing depend on a vma, only on writes to the backing store). Keeping
the vma binding distinct from the backing store timelines is verified by
a number of async gem_exec_fence and gem_exec_schedule tests. The way we
do this is quite simple, we keep the fence for the vma binding separate
and only wait on it as required, and never add it to the obj->resv
itself.

Another consequence in reducing the locking around the vma is the
destruction of the vma is no longer globally serialised by struct_mutex.
A natural solution would be to add a kref to i915_vma, but that requires
decoupling the reference cycles, possibly by introducing a new
i915_mm_pages object that is own by both obj->mm and vma->pages.
However, we have not taken that route due to the overshadowing lmem/ttm
discussions, and instead play a series of complicated games with
trylocks to (hopefully) ensure that only one destruction path is called!

v2: Add some commentary, and some helpers to reduce patch churn.
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20191004134015.13204-4-chris@chris-wilson.co.uk
      2850748e
  37. 20 9月, 2019 1 次提交
    • C
      drm/i915: Mark i915_request.timeline as a volatile, rcu pointer · d19d71fc
      由 Chris Wilson 提交于 
      The request->timeline is only valid until the request is retired (i.e.
before it is completed). Upon retiring the request, the context may be
unpinned and freed, and along with it the timeline may be freed. We
therefore need to be very careful when chasing rq->timeline that the
pointer does not disappear beneath us. The vast majority of users are in
a protected context, either during request construction or retirement,
where the timeline->mutex is held and the timeline cannot disappear. It
is those few off the beaten path (where we access a second timeline) that
need extra scrutiny -- to be added in the next patch after first adding
the warnings about dangerous access.

One complication, where we cannot use the timeline->mutex itself, is
during request submission onto hardware (under spinlocks). Here, we want
to check on the timeline to finalize the breadcrumb, and so we need to
impose a second rule to ensure that the request->timeline is indeed
valid. As we are submitting the request, it's context and timeline must
be pinned, as it will be used by the hardware. Since it is pinned, we
know the request->timeline must still be valid, and we cannot submit the
idle barrier until after we release the engine->active.lock, ergo while
submitting and holding that spinlock, a second thread cannot release the
timeline.

v2: Don't be lazy inside selftests; hold the timeline->mutex for as long
as we need it, and tidy up acquiring the timeline with a bit of
refactoring (i915_active_add_request)
Signed-off-by: NChris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: NTvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190919111912.21631-1-chris@chris-wilson.co.uk
      d19d71fc
  39. 22 8月, 2019 1 次提交
  41. 17 8月, 2019 1 次提交
  43. 16 8月, 2019 1 次提交
  45. 13 8月, 2019 1 次提交
  47. 07 8月, 2019 1 次提交
  49. 05 7月, 2019 1 次提交
  51. 17 6月, 2019 1 次提交
  53. 14 6月, 2019 1 次提交
  55. 28 5月, 2019 2 次提交
  57. 30 4月, 2019 1 次提交
  59. 25 4月, 2019 1 次提交
  61. 17 4月, 2019 1 次提交
    • P
      drm/i915: add GEN2_ prefix to the I{E, I, M, S}R registers · 9d9523d8
      由 Paulo Zanoni 提交于 
      This discussion started because we use token pasting in the
GEN{2,3}_IRQ_INIT and GEN{2,3}_IRQ_RESET macros, so gen2-4 passes an
empty argument to those macros, making the code a little weird. The
original proposal was to just add a comment as the empty argument, but
Ville suggested we just add a prefix to the registers, and that indeed
sounds like a more elegant solution.

Now doing this is kinda against our rules for register naming since we
only add gens or platform names as register prefixes when the given
gen/platform changes a register that already existed before. On the
other hand, we have so many instances of IIR/IMR in comments that
adding a prefix would make the users of these register more easily
findable, in addition to make our token pasting macros actually
readable. So IMHO opening an exception here is worth it.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190410235344.31199-4-paulo.r.zanoni@intel.com
      9d9523d8
  63. 06 3月, 2019 1 次提交
  65. 06 2月, 2019 1 次提交