| Message ID | 1414064309-22232-1-git-send-email-prarit@redhat.com (mailing list archive) |
|---|---|
| State | Accepted |
| Headers | show |
On Thu, Oct 23, 2014 at 4:38 AM, Prarit Bhargava <prarit@redhat.com> 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@intel.com> > Cc: Vinod Koul <vinod.koul@intel.com> > Cc: Dave Jiang <dave.jiang@intel.com> Dave, can you check this out / ack so Vinod can take this? -- To unsubscribe from this list: send the line "unsubscribe dmaengine" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thu, Oct 23, 2014 at 06:36:58AM -0700, Dan Williams wrote: > On Thu, Oct 23, 2014 at 4:38 AM, Prarit Bhargava <prarit@redhat.com> wrote: > > No response from anyone the first time ... > > > > Sorry about that, thanks for re-posting. > > > Dave, can you check this out / ack so Vinod can take this? I dont think I saw a response from Dave on this??
On 11/12/2014 04:43 AM, Vinod Koul wrote: > On Thu, Oct 23, 2014 at 06:36:58AM -0700, Dan Williams wrote: >> On Thu, Oct 23, 2014 at 4:38 AM, Prarit Bhargava <prarit@redhat.com> wrote: >>> No response from anyone the first time ... >>> >> >> Sorry about that, thanks for re-posting. >> >> >> Dave, can you check this out / ack so Vinod can take this? > > I dont think I saw a response from Dave on this?? Sorry for the lower-case typing. I broke my elbow and am down to one hand. i haven't seen a response either. i was just about to ping on this ... P. > -- To unsubscribe from this list: send the line "unsubscribe dmaengine" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thu, Oct 23, 2014 at 07:38:29AM -0400, Prarit Bhargava wrote: > 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(). Please make sure you use the right subsystem name Applied now, thanks
diff --git a/drivers/dma/ioat/dma_v3.c b/drivers/dma/ioat/dma_v3.c index b9b38a1..8c51b5c 100644 --- a/drivers/dma/ioat/dma_v3.c +++ b/drivers/dma/ioat/dma_v3.c @@ -1265,9 +1265,17 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device) op = IOAT_OP_XOR; dest_dma = dma_map_page(dev, dest, 0, PAGE_SIZE, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dest_dma)) + goto dma_unmap; + for (i = 0; i < IOAT_NUM_SRC_TEST; i++) + dma_srcs[i] = DMA_ERROR_CODE; + for (i = 0; i < IOAT_NUM_SRC_TEST; i++) { dma_srcs[i] = dma_map_page(dev, xor_srcs[i], 0, PAGE_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_srcs[i])) + goto dma_unmap; + } tx = dma->device_prep_dma_xor(dma_chan, dest_dma, dma_srcs, IOAT_NUM_SRC_TEST, PAGE_SIZE, DMA_PREP_INTERRUPT); @@ -1298,7 +1306,6 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device) goto dma_unmap; } - dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE); for (i = 0; i < IOAT_NUM_SRC_TEST; i++) dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, DMA_TO_DEVICE); @@ -1313,6 +1320,8 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device) } dma_sync_single_for_device(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE); + dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE); + /* skip validate if the capability is not present */ if (!dma_has_cap(DMA_XOR_VAL, dma_chan->device->cap_mask)) goto free_resources; @@ -1327,8 +1336,13 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device) xor_val_result = 1; for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) + dma_srcs[i] = DMA_ERROR_CODE; + for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) { dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_srcs[i])) + goto dma_unmap; + } tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs, IOAT_NUM_SRC_TEST + 1, PAGE_SIZE, &xor_val_result, DMA_PREP_INTERRUPT); @@ -1374,8 +1388,13 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device) xor_val_result = 0; for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) + dma_srcs[i] = DMA_ERROR_CODE; + for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) { dma_srcs[i] = dma_map_page(dev, xor_val_srcs[i], 0, PAGE_SIZE, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_srcs[i])) + goto dma_unmap; + } tx = dma->device_prep_dma_xor_val(dma_chan, dma_srcs, IOAT_NUM_SRC_TEST + 1, PAGE_SIZE, &xor_val_result, DMA_PREP_INTERRUPT); @@ -1417,14 +1436,18 @@ static int ioat_xor_val_self_test(struct ioatdma_device *device) goto free_resources; dma_unmap: if (op == IOAT_OP_XOR) { - dma_unmap_page(dev, dest_dma, PAGE_SIZE, DMA_FROM_DEVICE); + if (dest_dma != DMA_ERROR_CODE) + dma_unmap_page(dev, dest_dma, PAGE_SIZE, + DMA_FROM_DEVICE); for (i = 0; i < IOAT_NUM_SRC_TEST; i++) - dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, - DMA_TO_DEVICE); + if (dma_srcs[i] != DMA_ERROR_CODE) + dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, + DMA_TO_DEVICE); } else if (op == IOAT_OP_XOR_VAL) { for (i = 0; i < IOAT_NUM_SRC_TEST + 1; i++) - dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, - DMA_TO_DEVICE); + if (dma_srcs[i] != DMA_ERROR_CODE) + dma_unmap_page(dev, dma_srcs[i], PAGE_SIZE, + DMA_TO_DEVICE); } free_resources: dma->device_free_chan_resources(dma_chan);
No response from anyone the first time ... 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@intel.com> Cc: Vinod Koul <vinod.koul@intel.com> Cc: Dave Jiang <dave.jiang@intel.com> Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: dmaengine@vger.kernel.org Signed-off-by: Prarit Bhargava <prarit@redhat.com> --- drivers/dma/ioat/dma_v3.c | 35 +++++++++++++++++++++++++++++------ 1 file changed, 29 insertions(+), 6 deletions(-)