From 71f8a4b81d040b3d094424197ca2f1bf811b1245 Mon Sep 17 00:00:00 2001 From: Jialing Fu Date: Fri, 28 Aug 2015 11:13:09 +0800 Subject: [PATCH] mmc: core: fix race condition in mmc_wait_data_done The following panic is captured in ker3.14, but the issue still exists in latest kernel. --------------------------------------------------------------------- [ 20.738217] c0 3136 (Compiler) Unable to handle kernel NULL pointer dereference at virtual address 00000578 ...... [ 20.738499] c0 3136 (Compiler) PC is at _raw_spin_lock_irqsave+0x24/0x60 [ 20.738527] c0 3136 (Compiler) LR is at _raw_spin_lock_irqsave+0x20/0x60 [ 20.740134] c0 3136 (Compiler) Call trace: [ 20.740165] c0 3136 (Compiler) [] _raw_spin_lock_irqsave+0x24/0x60 [ 20.740200] c0 3136 (Compiler) [] __wake_up+0x1c/0x54 [ 20.740230] c0 3136 (Compiler) [] mmc_wait_data_done+0x28/0x34 [ 20.740262] c0 3136 (Compiler) [] mmc_request_done+0xa4/0x220 [ 20.740314] c0 3136 (Compiler) [] sdhci_tasklet_finish+0xac/0x264 [ 20.740352] c0 3136 (Compiler) [] tasklet_action+0xa0/0x158 [ 20.740382] c0 3136 (Compiler) [] __do_softirq+0x10c/0x2e4 [ 20.740411] c0 3136 (Compiler) [] irq_exit+0x8c/0xc0 [ 20.740439] c0 3136 (Compiler) [] handle_IRQ+0x48/0xac [ 20.740469] c0 3136 (Compiler) [] gic_handle_irq+0x38/0x7c ---------------------------------------------------------------------- Because in SMP, "mrq" has race condition between below two paths: path1: CPU0: static void mmc_wait_data_done(struct mmc_request *mrq) { mrq->host->context_info.is_done_rcv = true; // // If CPU0 has just finished "is_done_rcv = true" in path1, and at // this moment, IRQ or ICache line missing happens in CPU0. // What happens in CPU1 (path2)? // // If the mmcqd thread in CPU1(path2) hasn't entered to sleep mode: // path2 would have chance to break from wait_event_interruptible // in mmc_wait_for_data_req_done and continue to run for next // mmc_request (mmc_blk_rw_rq_prep). // // Within mmc_blk_rq_prep, mrq is cleared to 0. // If below line still gets host from "mrq" as the result of // compiler, the panic happens as we traced. wake_up_interruptible(&mrq->host->context_info.wait); } path2: CPU1: static int mmc_wait_for_data_req_done(... { ... while (1) { wait_event_interruptible(context_info->wait, (context_info->is_done_rcv || context_info->is_new_req)); static void mmc_blk_rw_rq_prep(... { ... memset(brq, 0, sizeof(struct mmc_blk_request)); This issue happens very coincidentally; however adding mdelay(1) in mmc_wait_data_done as below could duplicate it easily. static void mmc_wait_data_done(struct mmc_request *mrq) { mrq->host->context_info.is_done_rcv = true; + mdelay(1); wake_up_interruptible(&mrq->host->context_info.wait); } At runtime, IRQ or ICache line missing may just happen at the same place of the mdelay(1). This patch gets the mmc_context_info at the beginning of function, it can avoid this race condition. Signed-off-by: Jialing Fu Tested-by: Shawn Lin Fixes: 2220eedfd7ae ("mmc: fix async request mechanism ....") Signed-off-by: Shawn Lin Signed-off-by: Ulf Hansson --- drivers/mmc/core/core.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c index 664b61729fa9..0520064dc33b 100644 --- a/drivers/mmc/core/core.c +++ b/drivers/mmc/core/core.c @@ -358,8 +358,10 @@ EXPORT_SYMBOL(mmc_start_bkops); */ static void mmc_wait_data_done(struct mmc_request *mrq) { - mrq->host->context_info.is_done_rcv = true; - wake_up_interruptible(&mrq->host->context_info.wait); + struct mmc_context_info *context_info = &mrq->host->context_info; + + context_info->is_done_rcv = true; + wake_up_interruptible(&context_info->wait); } static void mmc_wait_done(struct mmc_request *mrq) -- 2.39.5