[Intel-gfx] significant ioremap leak in i915?
Guys, This might be covered elsewhere, but help me come up to speed: I am trying to analyze a leak in i915 that occurs on a digital sinage system that I've built. The system basically is doing a lot of XCompositeRedirectWindow / glXBindTexImageEXT calls to render web views and mplayer output onto opengl textures for subsequent rendering. In my testing, I observe that an enormous block is being lost in ioremap by looking at /proc/vmallocinfo: 0xc920-0xc90010201000 268439552 pci_mmcfg_arch_map+0x33/0x90 phys=e000 ioremap 0xc90010f8-0xc90020f81000 268439552 i915_driver_load+0x20c/0x6d0 [i915] phys=c000 ioremap So in this example 268 megabytes have been lost. Now what is even more vexing is if I stop the software, and X11 both blocks are still present on the vmalloc list. If I then proceed to rmmod i915 the i915 entry vanishes, however, the pci_mmcfg_arch_map mapping remains. It is entirely possible that I am doing something stupid from userland (opengl) however, my test runs reliably on an NVidia based machine - no leaks, runs until I power it off. I also think that whatever wrongness I may be doing in userland I shouldn't be able to blow up the system in this way. For clarity, my setup is: A NUC 2820 (I.e. Haswell N2820 CPU, 2.13GHz). 1Gb physical ram. Operating system: Ubuntu 14.04 (as shipped): kernel version 3.13.0-37-generic (i.e. Ubuntu's build) Xorg: X.Org X Server 1.15.1 Intel xorg module: compiled for 1.15.1, module version = 2.99.916 Acceleration mode: uxa (although SNA shows no difference with regards to the leak). Any suggestions would be welcome on how to address / analyze this - in the meantime I will be digging through the i915 source code to try to better understand the problem. Cheers, -Brett ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [Intel-gfx] significant ioremap leak in i915?
On 12/10/14 11:23, Dave Airlie wrote: On 12 October 2014 19:28, Breton M. Saunders wrote: Guys, This might be covered elsewhere, but help me come up to speed: I am trying to analyze a leak in i915 that occurs on a digital sinage system that I've built. The system basically is doing a lot of XCompositeRedirectWindow / glXBindTexImageEXT calls to render web views and mplayer output onto opengl textures for subsequent rendering. In my testing, I observe that an enormous block is being lost in ioremap by looking at /proc/vmallocinfo: 0xc920-0xc90010201000 268439552 pci_mmcfg_arch_map+0x33/0x90 phys=e000 ioremap 0xc90010f8-0xc90020f81000 268439552 i915_driver_load+0x20c/0x6d0 [i915] phys=c000 ioremap So in this example 268 megabytes have been lost. This isn't RAM, its address space mapping, its not really a leak at all. It really doesn't matter whether it is ram or mapping; its a resource leak that causes the system to OOM and panic. -Brett ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Re: [Intel-gfx] significant ioremap leak in i915?
On 13/10/14 02:09, Dave Airlie wrote: So in this example 268 megabytes have been lost. This isn't RAM, its address space mapping, its not really a leak at all. It really doesn't matter whether it is ram or mapping; its a resource leak that causes the system to OOM and panic. hey I was trying to help you come up to speed as requested, you don't have to believe me. I apologize, and I appreciate your help. I do believe you. It also appears that the mapping I jumped on wasn't the root cause of the problem; I'm still investigating. -Brett ___ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/intel-gfx
