From: Brad Volkin Date: Mon, 22 Sep 2014 15:25:21 +0000 (-0700) Subject: drm/i915: Don't leak command parser tables on suspend/resume X-Git-Tag: fixes-for-v3.18-merge-window~71^2~1^2~1 X-Git-Url: http://git.openpandora.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=22cb99af39b5d4aae075a5bc9da615ba245227cd;p=pandora-kernel.git drm/i915: Don't leak command parser tables on suspend/resume Ring init and cleanup are not balanced because we re-init the rings on resume without having cleaned them up on suspend. This leads to the driver leaking the parser's hash tables with a kmemleak signature such as this: unreferenced object 0xffff880405960980 (size 32): comm "systemd-udevd", pid 516, jiffies 4294896961 (age 10202.044s) hex dump (first 32 bytes): d0 85 46 c0 ff ff ff ff 00 00 00 00 00 00 00 00 ..F............. 98 60 28 04 04 88 ff ff 00 00 00 00 00 00 00 00 .`(............. backtrace: [] kmemleak_alloc+0x4e/0xb0 [] kmem_cache_alloc_trace+0x168/0x2f0 [] i915_cmd_parser_init_ring+0x2a5/0x3e0 [i915] [] intel_init_ring_buffer+0x202/0x470 [i915] [] intel_init_vebox_ring_buffer+0x1e8/0x2b0 [i915] [] i915_gem_init_hw+0x2f9/0x3a0 [i915] [] i915_gem_init+0x57/0x1d0 [i915] [] i915_driver_load+0xc0a/0x10e0 [i915] [] drm_dev_register+0xad/0x100 [drm] [] drm_get_pci_dev+0x8f/0x200 [drm] [] i915_pci_probe+0x3b/0x60 [i915] [] local_pci_probe+0x45/0xa0 [] pci_device_probe+0xd9/0x130 [] driver_probe_device+0x12d/0x3e0 [] __driver_attach+0x93/0xa0 [] bus_for_each_dev+0x6b/0xb0 This patch extends the current convention of checking whether a resource is already allocated before allocating it during ring init. Longer term it might make sense to only init the rings once. Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=83794 Tested-by: Kari Suvanto Signed-off-by: Brad Volkin Reviewed-by: Daniel Vetter Cc: stable@vger.kernel.org Signed-off-by: Jani Nikula --- Reading git-diff-tree failed