On 06/11/2010 01:15 AM, Dave Airlie wrote:
On Thu, 2010-06-10 at 15:38 -0700, Andrew Morton wrote:
(switched to email. Please respond via emailed reply-to-all, not via the bugzilla web interface).
On Mon, 7 Jun 2010 17:32:04 GMT bugzilla-daemon@bugzilla.kernel.org wrote:
https://bugzilla.kernel.org/show_bug.cgi?id=16148
Summary: page allocation failure. order:1, mode:0x50d0 Product: Memory Management Version: 2.5 Kernel Version: 2.6.35-rc1 Platform: All OS/Version: Linux Tree: Mainline Status: NEW Severity: normal Priority: P1 Component: Page Allocator AssignedTo: akpm@linux-foundation.org ReportedBy: devnull@plzk.org Regression: NoCreated an attachment (id=26687) --> (https://bugzilla.kernel.org/attachment.cgi?id=26687) dmesg
Never seen this before.
2.6.35-rc1 #1 SMP Mon May 31 21:31:02 CEST 2010 x86_64 GNU/Linux
[48126.787684] Xorg: page allocation failure. order:1, mode:0x50d0 [48126.787691] Pid: 1895, comm: Xorg Tainted: G W 2.6.35-rc1 #1 [48126.787694] Call Trace: [48126.787709] [<ffffffff811192f5>] __alloc_pages_nodemask+0x5f5/0x6f0 [48126.787716] [<ffffffff81148695>] alloc_pages_current+0x95/0x100 [48126.787720] [<ffffffff8114e04a>] new_slab+0x2ba/0x2c0 [48126.787724] [<ffffffff8114ed0b>] __slab_alloc+0x14b/0x4e0 [48126.787730] [<ffffffff81403f91>] ? security_vm_enough_memory_kern+0x21/0x30 [48126.787736] [<ffffffff81556e6a>] ? agp_alloc_page_array+0x5a/0x70 [48126.787740] [<ffffffff8115087f>] __kmalloc+0x11f/0x1c0 [48126.787744] [<ffffffff81556e6a>] agp_alloc_page_array+0x5a/0x70 [48126.787747] [<ffffffff81556ee4>] agp_generic_alloc_user+0x64/0x140 [48126.787750] [<ffffffff8155717a>] agp_allocate_memory+0x9a/0x140 [48126.787755] [<ffffffff8156c179>] drm_agp_allocate_memory+0x9/0x10 [48126.787758] [<ffffffff8156c1d7>] drm_agp_bind_pages+0x57/0x100 [48126.787765] [<ffffffff81627fe4>] i915_gem_object_bind_to_gtt+0x144/0x340 [48126.787768] [<ffffffff81628295>] i915_gem_object_pin+0xb5/0xd0 [48126.787772] [<ffffffff81629a4c>] i915_gem_do_execbuffer+0x6cc/0x14f0 [48126.787777] [<ffffffff81091ba0>] ? __is_ram+0x0/0x10 [48126.787783] [<ffffffff8106c76e>] ? lookup_memtype+0xce/0xe0 [48126.787787] [<ffffffff8162ab11>] ? i915_gem_execbuffer+0x91/0x390 [48126.787790] [<ffffffff8162ac55>] i915_gem_execbuffer+0x1d5/0x390 [48126.787794] [<ffffffff816255b0>] ? i915_gem_sw_finish_ioctl+0x90/0xc0 [48126.787799] [<ffffffff81565a0a>] drm_ioctl+0x32a/0x4b0 [48126.787802] [<ffffffff8162aa80>] ? i915_gem_execbuffer+0x0/0x390 [48126.787807] [<ffffffff8116c248>] vfs_ioctl+0x38/0xd0 [48126.787810] [<ffffffff8116c87a>] do_vfs_ioctl+0x8a/0x580 [48126.787814] [<ffffffff8116cdf1>] sys_ioctl+0x81/0xa0 [48126.787820] [<ffffffff8103af02>] system_call_fastpath+0x16/0x1b
David, I have a vague feeling that we've been round this loop before..
Why does agp_alloc_page_array() use __GFP_NORETRY? It's pretty unusual and it's what caused this spew.
There's nothing in the changelog and the only relevant commentary appears to be "This speeds things up and also saves memory for small AGP regions", which is inscrutable. Can you please add a usable comment there?
cc'ing Thomas, who added this, I expect we could drop the NORETRY or just add NOWARN. Though an order 1 page alloc failure isn't a pretty sight, not sure how a vmalloc fallback could save us.
Hmm. IIRC that was an untested speed optimization back from the time when I was reading ldd3. I think the idea was to avoid slow allocations of (order > 0) if they weren't immediately available and fall back to vmalloc single page allocations. It might be that that functionality is no longer preserved and only the __GFP_NORETRY remains. I think it should be safe to remove the NORETRY if it's annoying, but it should probably be equally safe to add a NOWARN and keep the vmalloc fallback.
Now if we still get a "definitive" page allocation failure in this codepath, that's not good, but hardly the AGP driver's fault. Has Intel added some kind of accounting for pinned pages yet?
Presumably this was added in response to some observed behaviour, but what was it??
If the __GFP_NORETRY is indeed useful and legitimate and given that we have a vmalloc fallback, I'd suggest that we add __GFP_NOWARN there as well to keep the bug reports away.
btw, agp_memory.vmalloc_flag can be done away with - it's conventional to use is_vmalloc_addr() for this.
Lols, conventional my ass, we wanted to add that thing years ago for this purpose and got told that would be an insane interface, then the same person added the interface a year later and never fixed AGP to use it.
Indeed. I even recall the phrase "Too ugly to live" :).
I'll try and write a patch.
Dave.
/Thomas