Message-ID: <CAPcyv4iqno9r_AvhQShSz1mN=4wEBv7Ld1fwG9x4um7KmfdWxA@mail.gmail.com>
Date:	Thu, 6 Mar 2014 10:48:32 -0800
From:	Dan Williams <dan.j.williams@...el.com>
To:	Alan Stern <stern@...land.harvard.edu>
Cc:	Dave Jones <davej@...hat.com>, Joerg Roedel <joerg.roedel@....com>,
	Linux Kernel <linux-kernel@...r.kernel.org>,
	USB list <linux-usb@...r.kernel.org>
Subject: Re: uhci_hcd: DMA-API: cpu touching an active dma mapped cacheline

On Thu, Mar 6, 2014 at 10:31 AM, Dan Williams <dan.j.williams@...el.com> wrote:
> On Thu, Mar 6, 2014 at 10:04 AM, Alan Stern <stern@...land.harvard.edu> wrote:
>> On Wed, 5 Mar 2014, Dave Jones wrote:
>>
>>> WARNING: CPU: 3 PID: 25477 at lib/dma-debug.c:593 debug_dma_assert_idle+0x1ba/0x223()
>>> uhci_hcd 0000:00:1d.2: DMA-API: cpu touching an active dma mapped cacheline [cln=0x0000000002355f80]
>>> Modules linked in: fuse tun l2tp_ppp l2tp_netlink l2tp_core can_raw can_bcm scsi_transport_iscsi nfc caif_socket caif af_802154 phonet af_rxrpc hidp bluetooth 6lowpan_iphc can pppoe pppox ppp_generic slhc irda crc_ccitt rds rose x25 atm netrom appletalk ipx p8023 p8022 psnap llc ax25 cfg80211 rfkill nouveau video backlight mxm_wmi wmi i2c_algo_bit ttm drm_kms_helper drm tg3 i2c_core ptp pps_core libphy kvm_intel kvm lpc_ich microcode pcspkr mfd_core parport_pc serio_raw parport shpchp rtc_cmos xfs libcrc32c raid0 floppy
>>> CPU: 3 PID: 25477 Comm: cc Not tainted 3.14.0-rc5+ #2
>>> Hardware name: Dell Inc.                 Precision WorkStation 490    /0DT031, BIOS A08 04/25/2008
>>>  00000000 2e7036e5 00000000 db851dbc c15f76ee db851dfc db851dec c1043733
>>>  c17ce4b0 db851e1c 00006385 c17ccc7a 00000251 c130a152 c130a152 eef3f650
>>>  efb53480 00000000 db851e08 c1043788 00000009 db851dfc c17ce4b0 db851e1c
>>> Call Trace:
>>>  [<c15f76ee>] dump_stack+0x4b/0x75
>>>  [<c1043733>] warn_slowpath_common+0x7e/0x95
>>>  [<c130a152>] ? debug_dma_assert_idle+0x1ba/0x223
>>>  [<c130a152>] ? debug_dma_assert_idle+0x1ba/0x223
>>>  [<c1043788>] warn_slowpath_fmt+0x3e/0x51
>>>  [<c130a152>] debug_dma_assert_idle+0x1ba/0x223
>>>  [<c1159704>] do_wp_page+0x108/0x8a1
>>>  [<c115b790>] ? handle_mm_fault+0x1ba/0xd54
>>>  [<c15ff7ea>] ? _raw_spin_lock+0x6b/0x72
>>>  [<c115bae2>] handle_mm_fault+0x50c/0xd54
>>>  [<c160357c>] ? __do_page_fault+0xee/0x55c
>>>  [<c16035da>] __do_page_fault+0x14c/0x55c
>>>  [<c16039ea>] ? __do_page_fault+0x55c/0x55c
>>>  [<c16039f7>] do_page_fault+0xd/0xf
>>>  [<c1600dfc>] error_code+0x6c/0x74
>>> ------------[ cut here ]------------
>>> WARNING: CPU: 3 PID: 25490 at lib/dma-debug.c:593 debug_dma_assert_idle+0x1ba/0x223()
>>> uhci_hcd 0000:00:1d.2: DMA-API: cpu touching an active dma mapped cacheline [cln=0x0000000002355f80]
>>> ---[ end trace 3ac75acf24cf0b9e ]---
>>> Mapped at:
>>>  [<c13081b5>] debug_dma_alloc_coherent+0x2b/0xc3
>>> Modules linked in: fuse tun l2tp_ppp l2tp_netlink l2tp_core can_raw can_bcm scsi_transport_iscsi nfc caif_socket caif af_802154 phonet af_rxrpc hidp bluetooth 6lowpan_iphc can pppoe pppox ppp_generic slhc irda crc_ccitt rds rose x25 atm netrom appletalk ipx p8023 p8022 psnap llc ax25 cfg80211 rfkill nouveau video backlight mxm_wmi wmi i2c_algo_bit ttm drm_kms_helper drm tg3 i2c_core ptp pps_core libphy kvm_intel kvm lpc_ich microcode pcspkr mfd_core parport_pc serio_raw parport shpchp rtc_cmos xfs libcrc32c raid0 floppy
>>>
>>> [<c116fcee>] dma_pool_alloc+0x14f/0x2fd
>>>  [<c1456eaa>] uhci_alloc_td.isra.35+0x24/0x60
>>>  [<c1457fa6>] uhci_start+0x272/0x56b
>>>  [<c142d8fb>] usb_add_hcd+0x252/0x774
>>>
>>> CPU: 3 PID: 25490 Comm: cc Tainted: G        W    3.14.0-rc5+ #2
>>> Hardware name: Dell Inc.                 Precision WorkStation 490    /0DT031, BIOS A08 04/25/2008
>>>  00000000 bf79585b 00000000 db81bdbc c15f76ee db81bdfc db81bdec c1043733
>>>  c17ce4b0 db81be1c 00006392 c17ccc7a 00000251 c130a152 c130a152 eef3f650
>>>  efb53480 00000000 db81be08 c1043788 00000009 db81bdfc c17ce4b0 db81be1c
>>> Call Trace:
>>>  [<c15f76ee>] dump_stack+0x4b/0x75
>>>  [<c1043733>] warn_slowpath_common+0x7e/0x95
>>>  [<c130a152>] ? debug_dma_assert_idle+0x1ba/0x223
>>>  [<c130a152>] ? debug_dma_assert_idle+0x1ba/0x223
>>>  [<c1043788>] warn_slowpath_fmt+0x3e/0x51
>>>  [<c130a152>] debug_dma_assert_idle+0x1ba/0x223
>>>  [<c1159704>] do_wp_page+0x108/0x8a1
>>>  [<c115b790>] ? handle_mm_fault+0x1ba/0xd54
>>>  [<c15ff7ea>] ? _raw_spin_lock+0x6b/0x72
>>>  [<c115bae2>] handle_mm_fault+0x50c/0xd54
>>>  [<c160357c>] ? __do_page_fault+0xee/0x55c
>>>  [<c16035da>] __do_page_fault+0x14c/0x55c
>>>  [<c1603683>] ? __do_page_fault+0x1f5/0x55c
>>>  [<c160065b>] ? restore_all+0xf/0xf
>>>  [<c12f0d89>] ? __put_user_4+0x11/0x18
>>>  [<c16039ea>] ? __do_page_fault+0x55c/0x55c
>>>  [<c16039f7>] do_page_fault+0xd/0xf
>>>  [<c1600dfc>] error_code+0x6c/0x74
>>> ---[ end trace 3ac75acf24cf0b9f ]---
>>> Mapped at:
>>>  [<c13081b5>] debug_dma_alloc_coherent+0x2b/0xc3
>>>  [<c116fcee>] dma_pool_alloc+0x14f/0x2fd
>>>  [<c1456eaa>] uhci_alloc_td.isra.35+0x24/0x60
>>>  [<c1457fa6>] uhci_start+0x272/0x56b
>>>  [<c142d8fb>] usb_add_hcd+0x252/0x774
>>
>> I don't get it.  As the name indicates, debug_dma_alloc_coherent should
>> give us consistent memory -- meaning that the CPU is allowed to access
>> the memory while DMA is in progress, without worrying about caching
>> effects (see Documentation/DMA-API.txt).
>>
>> So why should we get a warning when the CPU accesses this memory?  Is
>> this a regression in the DMA debug library?
>
> Yes, it seems so.  alloc_coherent needs to be exempt from active
> mapping tracking.  Fix coming up.
>

Actually I'm not so sure.  Yes, alloc_coherent means the cpu can
touch, but if that page is COW'd how can you be sure that the copy
gets the most up to date data from the device?  This check is
asserting that dma might be colliding with a copy-on-write event.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Powered by blists - more mailing lists