On 8 October 2014 13:23, Srinivas Kandagatla <srinivas.kandagatla@xxxxxxxxxx> wrote: > Hi All, > > During recent eMMC stress testing on IFC6410 board we always hit below crash in few mins. > > Initial investigations showed that the mmci driver gets confused sometimes when > handling CMD8 as part of blkops request. The reason looks straight forward, > mmci driver caches the dma descriptor and channel for the prepared request, > so if a new blocking request like CMD8 arrives, it would think that the request > is already prepared as dma_desc_current and dma_current looks valid. As a result > the driver does not prepare the dma channel for CMD8, so at the end the driver > notices that fifo has still some bytes and driver crashes. > > Also the problem seems to be partly in the core as well, which is sending a > blocking command after preparing another request. > > These two patches changes the way the prepared request is handled in the core during bkops. > After applying these two patches I see no crashes. > > Am not sure if someone else encountered such issue, also I would like to know your opinion > on the overall approach of fixing this issue. > > > mmci-pl18x 12400000.sdcc: error during DMA transfer! > Unable to handle kernel paging request at virtual address 40000000 > pgd = c0204000 > [40000000] *pgd=00000000 > Internal error: Oops: 805 [#1] SMP ARM > Modules linked in: ipv6 ath6kl_sdio ath6kl_core > CPU: 0 PID: 0 Comm: swapper/0 Tainted: G W 3.17.0-rc7-linaro-multi-v7 #1 > task: c0c9d7e0 ti: c0c92000 task.ti: c0c92000 > PC is at v7_dma_inv_range+0x34/0x4c > LR is at __dma_page_dev_to_cpu+0x80/0x100 > pc : [<c021efc0>] lr : [<c021af18>] psr: 400f0193 > sp : c0c93e20 ip : c0c9a478 fp : c08ea538 > r10: c0c9f548 r9 : 00000002 r8 : e97d9000 > r7 : 00000200 r6 : c0c9d504 r5 : c0db0880 r4 : 00000000 > r3 : 0000003f r2 : 00000040 r1 : 40000200 r0 : 40000000 > Flags: nZcv IRQs off FIQs on Mode SVC_32 ISA ARM Segment kernel > Control: 10c5787d Table: a9ef406a DAC: 00000015 > Process swapper/0 (pid: 0, stack limit = 0xc0c92250) > Stack: (0xc0c93e20 to 0xc0c94000) > 3e20: c021f058 e9a17178 e9a171bc e99dfd6c 00000001 00000001 e995de10 00000002 > 3e40: 00000000 c021b574 00000000 c04bc4a4 00000000 e9b49ac0 c0ce6e6c e99dfda4 > 3e60: 00000088 e9810780 c0d8291c c072ea58 00000000 c072d3fc 00000000 c072f534 > 3e80: 00000000 e9b49ac0 00000100 c0c9a444 00000088 c072f6b4 c072f5d4 e9d40080 > 3ea0: e98107dc 00000000 00000000 c0280a60 00000000 7d55bf61 e9810780 e98107dc > 3ec0: 00000000 f0002000 c0d460e8 c0d460e8 c0c92000 c0280b60 e9810780 c0ce7190 > 3ee0: 00000000 c028369c c02835f4 00000088 00000088 c0280278 c0c8ec70 c020f080 > 3f00: f000200c c0c9a958 c0c93f28 c02088e4 c04bd630 c04bd5bc 200f0013 ffffffff > 3f20: c0c93f5c c0212800 00000001 a987c000 c0c93f3c c04bd574 00000000 0000015b > 3f40: ea7a0e40 00000000 c0d460e8 c0d460e8 c0c92000 c08ea538 29b12000 c0c93f70 > 3f60: c04bd630 c04bd5bc 200f0013 ffffffff c04bd574 c071bd24 7d50c9b4 c0719a44 > 3f80: 7d50c9b4 0000015b c0c9a498 c0c92028 c0c9a498 c0c9a4fc ea7a0e40 c0c8ee38 > 3fa0: c0d460e8 c0276198 00000000 c0d8291a 00000000 c0c9a400 00000000 c0be0bc4 > 3fc0: ffffffff ffffffff c0be05f8 00000000 00000000 c0c533d8 c0d82ed4 c0c9a47c > 3fe0: c0c533d4 c0c9e870 8020406a 511f06f0 00000000 80208074 00000000 00000000 > [<c021efc0>] (v7_dma_inv_range) from [<c021af18>] (__dma_page_dev_to_cpu+0x80/0x100) > [<c021af18>] (__dma_page_dev_to_cpu) from [<c021b574>] (arm_dma_unmap_sg+0x5c/0x84) > [<c021b574>] (arm_dma_unmap_sg) from [<c072ea58>] (mmci_dma_unmap.isra.16+0x60/0x74) > [<c072ea58>] (mmci_dma_unmap.isra.16) from [<c072f534>] (mmci_data_irq+0x1fc/0x29c) > [<c072f534>] (mmci_data_irq) from [<c072f6b4>] (mmci_irq+0xe0/0x114) > [<c072f6b4>] (mmci_irq) from [<c0280a60>] (handle_irq_event_percpu+0x78/0x134) > [<c0280a60>] (handle_irq_event_percpu) from [<c0280b60>] (handle_irq_event+0x44/0x64) > [<c0280b60>] (handle_irq_event) from [<c028369c>] (handle_fasteoi_irq+0xa8/0x1a8) > [<c028369c>] (handle_fasteoi_irq) from [<c0280278>] (generic_handle_irq+0x2c/0x3c) > [<c0280278>] (generic_handle_irq) from [<c020f080>] (handle_IRQ+0x40/0x90) > [<c020f080>] (handle_IRQ) from [<c02088e4>] (gic_handle_irq+0x38/0x68) > [<c02088e4>] (gic_handle_irq) from [<c0212800>] (__irq_svc+0x40/0x54) > Exception stack(0xc0c93f28 to 0xc0c93f70) > 3f20: 00000001 a987c000 c0c93f3c c04bd574 00000000 0000015b > 3f40: ea7a0e40 00000000 c0d460e8 c0d460e8 c0c92000 c08ea538 29b12000 c0c93f70 > 3f60: c04bd630 c04bd5bc 200f0013 ffffffff > [<c0212800>] (__irq_svc) from [<c04bd5bc>] (msm_cpu_pm_enter_sleep+0x48/0x4c) > [<c04bd5bc>] (msm_cpu_pm_enter_sleep) from [<c071bd24>] (qcom_lpm_enter_spc+0x20/0x2c) > [<c071bd24>] (qcom_lpm_enter_spc) from [<c0719a44>] (cpuidle_enter_state+0x44/0xf0) > [<c0719a44>] (cpuidle_enter_state) from [<c0276198>] (cpu_startup_entry+0x1f4/0x238) > [<c0276198>] (cpu_startup_entry) from [<c0be0bc4>] (start_kernel+0x384/0x390) > Code: 1e070f3e e1110003 e1c11003 1e071f3e (ee070f36) > ---[ end trace cf6cb3f6432c9834 ]--- > Kernel panic - not syncing: Fatal exception in interrup > > --srini > > Srinivas Kandagatla (2): > mmc: core: fix prepared requests while doing bkops > mmc: mmci: fix mmci_post_request > > drivers/mmc/core/core.c | 12 +++++++++++- > drivers/mmc/host/mmci.c | 7 +++++++ > 2 files changed, 18 insertions(+), 1 deletion(-) > > -- > 1.9.1 > Thanks! Applied for next! I also fixed a minor misspelling in commit messages for which checkpatch complained about. Kind regards Uffe -- To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
