linux-kernel - [PATCH v2] mmc: sdhci-pxav3: fix race between runtime pm and irq

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [thread-next>] [day] [month] [year] [list]

Message-ID: <1422007701-7496-1-git-send-email-jszhang@marvell.com>
Date:	Fri, 23 Jan 2015 18:08:21 +0800
From:	Jisheng Zhang <jszhang@...vell.com>
To:	<chris@...ntf.net>, <ulf.hansson@...aro.org>,
	<sebastian.hesselbarth@...il.com>
CC:	<thomas.petazzoni@...e-electrons.com>, <linux-mmc@...r.kernel.org>,
	<linux-kernel@...r.kernel.org>,
	Jisheng Zhang <jszhang@...vell.com>, <stable@...r.kernel.org>
Subject: [PATCH v2] mmc: sdhci-pxav3: fix race between runtime pm and irq

This patch is to fix a race condition that may cause an unhandled irq,
which results in big sdhci interrupt numbers and endless "mmc1: got irq
while runtime suspended" msgs before v3.15.

Consider following scenario:

      CPU0                            CPU1
                              sdhci_pxav3_runtime_suspend()
                               spin_lock_irqsave(&host->lock, flags);
 sdhci_irq()
  spining on the &host->lock
                               host->runtime_suspended = true;
                               spin_unlock_irqrestore(&host->lock, flags);
  get the &host->lock
  runtime_suspended is true now
  return IRQ_NONE;

Fix this race by using the core sdhci.c supplied sdhci_runtime_suspend_host()
in runtime suspend hook which will disable card interrupts. We also use the
sdhci_runtime_resume_host() in the runtime resume hook accordingly.

Signed-off-by: Jisheng Zhang <jszhang@...vell.com>
Cc: <stable@...r.kernel.org> # v3.9+
---
Changes in v2:
 return ret once sdhci_runtime_suspend_host() gives an error
 drivers/mmc/host/sdhci-pxav3.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 4de39fb..e2817cc 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -460,11 +460,11 @@ static int sdhci_pxav3_runtime_suspend(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_pxa *pxa = pltfm_host->priv;
-	unsigned long flags;
+	int ret;
 
-	spin_lock_irqsave(&host->lock, flags);
-	host->runtime_suspended = true;
-	spin_unlock_irqrestore(&host->lock, flags);
+	ret = sdhci_runtime_suspend_host(host);
+	if (ret)
+		return ret;
 
 	clk_disable_unprepare(pxa->clk_io);
 	if (!IS_ERR(pxa->clk_core))
@@ -478,17 +478,12 @@ static int sdhci_pxav3_runtime_resume(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_pxa *pxa = pltfm_host->priv;
-	unsigned long flags;
 
 	clk_prepare_enable(pxa->clk_io);
 	if (!IS_ERR(pxa->clk_core))
 		clk_prepare_enable(pxa->clk_core);
 
-	spin_lock_irqsave(&host->lock, flags);
-	host->runtime_suspended = false;
-	spin_unlock_irqrestore(&host->lock, flags);
-
-	return 0;
+	return sdhci_runtime_resume_host(host);
 }
 #endif
 
-- 
2.1.4

--
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/