[Intel-gfx] [PATCH v2] drm/i915: Do not leak objects after capturing error state
Daniel Vetter
daniel at ffwll.ch
Fri Mar 20 07:47:00 PDT 2015
On Fri, Mar 20, 2015 at 09:41:03AM +0000, Michel Thierry wrote:
> While running kmemleak chasing a different memleak, I saw that the
> capture_error_state function was leaking some objects, for example:
>
> unreferenced object 0xffff8800a9b72148 (size 8192):
> comm "kworker/u16:0", pid 1499, jiffies 4295201243 (age 990.096s)
> hex dump (first 32 bytes):
> 00 00 04 00 00 00 00 00 5d f4 ff ff 00 00 00 00 ........].......
> 00 30 b0 01 00 00 00 00 37 00 00 00 00 00 00 00 .0......7.......
> backtrace:
> [<ffffffff811e5ae4>] create_object+0x104/0x2c0
> [<ffffffff8178f50a>] kmemleak_alloc+0x7a/0xc0
> [<ffffffff811cde4b>] __kmalloc+0xeb/0x220
> [<ffffffffa038f1d9>] kcalloc.constprop.12+0x2d/0x2f [i915]
> [<ffffffffa0316064>] i915_capture_error_state+0x3f4/0x1660 [i915]
> [<ffffffffa03207df>] i915_handle_error+0x7f/0x660 [i915]
> [<ffffffffa03210f7>] i915_hangcheck_elapsed+0x2e7/0x470 [i915]
> [<ffffffff8108d574>] process_one_work+0x144/0x490
> [<ffffffff8108dfbd>] worker_thread+0x11d/0x530
> [<ffffffff81094079>] kthread+0xc9/0xe0
> [<ffffffff817a2398>] ret_from_fork+0x58/0x90
> [<ffffffffffffffff>] 0xffffffffffffffff
>
> The following objects are allocated in i915_gem_capture_buffers, but not
> released in i915_error_state_free:
> - error->active_bo_count
> - error->pinned_bo
> - error->pinned_bo_count
> - error->active_bo[vm_count] (allocated in i915_gem_capture_vm).
>
> The leaks were introduced by
> commit 95f5301dd880da2dea2c9a9c29750064536d426a
> Author: Ben Widawsky <ben at bwidawsk.net>
> Date: Wed Jul 31 17:00:15 2013 -0700
>
> drm/i915: Update error capture for VMs
>
> v2: Reuse iterator and add culprit commit details (Chris)
>
> Cc: Chris Wilson <chris at chris-wilson.co.uk>
> Signed-off-by: Michel Thierry <michel.thierry at intel.com>
Queued for -next, thanks for the patch.
-Daniel
--
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch
More information about the Intel-gfx
mailing list