Re: [RESEND PATCH] ioatdma, fix dma mapping errors

[Dan Williams]

On Thu, Oct 23, 2014 at 4:38 AM, Prarit Bhargava <prarit@xxxxxxxxxx> wrote:
> No response from anyone the first time ...
>

Sorry about that, thanks for re-posting.

> P.
>
> ----8<----
>
> Several systems are showing the following stack trace:
>
> WARNING: CPU: 0 PID: 2352 at lib/dma-debug.c:1140 check_unmap+0x4ee/0x9e0()
> ioatdma 0000:00:04.0: DMA-API: device driver failed to check map error[device address=0x0000000465bad000] [size=4096 bytes] [mapped as page]
> Modules linked in: ioatdma(E+) nfsv3 rpcsec_gss_krb5 nfsv4 dns_resolver nfs fscache cfg80211 rfkill x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel kvm crct10dif_pclmul crc32_pclmul crc32c_intel cdc_ether ses ghash_clmulni_intel usbnet mii enclosure aesni_intel lrw gf128mul glue_helper iTCO_wdt shpchp ablk_helper iTCO_vendor_support cryptd pcspkr ipmi_devintf sb_edac lpc_ich edac_core mfd_core ipmi_si i2c_i801 wmi ipmi_msghandler nfsd auth_rpcgss nfs_acl lockd sunrpc xfs libcrc32c sd_mod crc_t10dif crct10dif_common mgag200 syscopyarea sysfillrect sysimgblt drm_kms_helper ttm igb drm ptp pps_core dca i2c_algo_bit i2ccore megaraid_sas dm_mirror dm_region_hash dm_log dm_mod [last unloaded: ioatdma]
> CPU: 0 PID: 2352 Comm: insmod Tainted: G            E  3.17.0-rc4+ #14
> Hardware name: HP ProLiant m300 Server Cartridge/, BIOS H02 01/30/2014
>  0000000000000009 ffff88007994b7d8 ffffffff816e7225 ffff88007994b820
>  ffff88007994b810 ffffffff8107e51d ffff88045fc56c00 ffff88046643ee90
>  ffffffff8338ccd0 0000000000000286 ffffffff81956629 ffff88007994b870
> Call Trace:
>  [<ffffffff816e7225>] dump_stack+0x4d/0x66
>  [<ffffffff8107e51d>] warn_slowpath_common+0x7d/0xa0
>  [<ffffffff8107e58c>] warn_slowpath_fmt+0x4c/0x50
>  [<ffffffff81381e6e>] check_unmap+0x4ee/0x9e0
>  [<ffffffff813823bf>] debug_dma_unmap_page+0x5f/0x70
>  [<ffffffffa04546d8>] ioat_xor_val_self_test+0x498/0xcf0 [ioatdma]
>  [<ffffffff81204f0a>] ? kfree+0xda/0x2b0
>  [<ffffffffa044d510>] ? ioat_dma_setup_interrupts+0x120/0x2d0 [ioatdma]
>  [<ffffffffa0454f4e>] ioat3_dma_self_test+0x1e/0x30 [ioatdma]
>  [<ffffffffa044f904>] ioat_probe+0xf4/0x110 [ioatdma]
>  [<ffffffffa04550f8>] ioat3_dma_probe+0x198/0x3a0 [ioatdma]
>  [<ffffffffa044d18e>] ioat_pci_probe+0x11e/0x1b0 [ioatdma]
>  [<ffffffff81393a15>] local_pci_probe+0x45/0xa0
>  [<ffffffff81394be5>] ? pci_match_device+0xe5/0x110
>  [<ffffffff81394d29>] pci_device_probe+0xd9/0x130
>  [<ffffffff81462860>] driver_probe_device+0x90/0x3c0
>  [<ffffffff81462c63>] __driver_attach+0x93/0xa0
>  [<ffffffff81462bd0>] ? __device_attach+0x40/0x40
>  [<ffffffff8146080b>] bus_for_each_dev+0x6b/0xb0
>  [<ffffffff814622ce>] driver_attach+0x1e/0x20
>  [<ffffffff81461ed8>] bus_add_driver+0x188/0x260
>  [<ffffffffa0423000>] ? 0xffffffffa0423000
>  [<ffffffff81463734>] driver_register+0x64/0xf0
>  [<ffffffff813933a0>] __pci_register_driver+0x60/0x70
>  [<ffffffffa0423089>] ioat_init_module+0x89/0x1000 [ioatdma]
>  [<ffffffff8100212c>] do_one_initcall+0xbc/0x200
>  [<ffffffff811e8b22>] ? __vunmap+0xd2/0x120
>  [<ffffffff8111e73c>] load_module+0x14ec/0x1b50
>  [<ffffffff81119970>] ? store_uevent+0x40/0x40
>  [<ffffffff8111ef36>] SyS_finit_module+0x86/0xb0
>  [<ffffffff816f1469>] system_call_fastpath+0x16/0x1b
> ---[ end trace 1052ccbbc3db4d08 ]---
> Mapped at:
>  [<ffffffff81380be1>] debug_dma_map_page+0x91/0x140
>  [<ffffffffa045440e>] ioat_xor_val_self_test+0x1ce/0xcf0 [ioatdma]
>  [<ffffffffa0454f4e>] ioat3_dma_self_test+0x1e/0x30 [ioatdma]
>  [<ffffffffa044f904>] ioat_probe+0xf4/0x110 [ioatdma]
>  [<ffffffffa04550f8>] ioat3_dma_probe+0x198/0x3a0 [ioatdma]
>
> This happens because the current ioatdma DMA test code does not check the return
> value of dma_map_page() calls with dma_mapping_error().  In addition, it was
> noticed that mapping for the variable dest_dma is free'd before the last use.
>
> This patch fixes these errors by initializing the dma_srcs[] array and checking
> the returns with dma_mapping_error().
>
> Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
> Cc: Vinod Koul <vinod.koul@xxxxxxxxx>
> Cc: Dave Jiang <dave.jiang@xxxxxxxxx>

Dave, can you check this out / ack so Vinod can take this?
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/