[02/54] ata_piix: fix locking around SIDPR access
in [Kernel]
|
Prev: [099/111] reiserfs: fix oops while creating privroot with selinux enabled
Next: [40/67] signalfd: fill in ssi_int for posix timers and message queues
From: Greg KH on 11 Aug 2010 20:10 2.6.34-stable review patch. If anyone has any objections, please let us know. ------------------ From: Tejun Heo <tj(a)kernel.org> commit 213373cf974fe69e78ec894b07f45ae2f5a3a078 upstream. SIDPR window registers are shared across ports and as each access is done in two steps, accesses to different ports under EH may race. This primarily is caused by incorrect host locking in EH context and should be fixed by defining locking requirements for each EH operation which can be used during EH and enforcing them but for now work around the problem by adding a dedicated SIDPR lock and grabbing it for each SIDPR access. Signed-off-by: Tejun Heo <tj(a)kernel.org> Reported-by: Mark Knecht <markknecht(a)gmail.com> Reported-by: Paul Check <paul(a)thechecks.ca> Signed-off-by: Jeff Garzik <jgarzik(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)suse.de> --- drivers/ata/ata_piix.c | 8 ++++++++ 1 file changed, 8 insertions(+) --- a/drivers/ata/ata_piix.c +++ b/drivers/ata/ata_piix.c @@ -158,6 +158,7 @@ struct piix_map_db { struct piix_host_priv { const int *map; u32 saved_iocfg; + spinlock_t sidpr_lock; /* FIXME: remove once locking in EH is fixed */ void __iomem *sidpr; }; @@ -951,12 +952,15 @@ static int piix_sidpr_scr_read(struct at unsigned int reg, u32 *val) { struct piix_host_priv *hpriv = link->ap->host->private_data; + unsigned long flags; if (reg >= ARRAY_SIZE(piix_sidx_map)) return -EINVAL; + spin_lock_irqsave(&hpriv->sidpr_lock, flags); piix_sidpr_sel(link, reg); *val = ioread32(hpriv->sidpr + PIIX_SIDPR_DATA); + spin_unlock_irqrestore(&hpriv->sidpr_lock, flags); return 0; } @@ -964,12 +968,15 @@ static int piix_sidpr_scr_write(struct a unsigned int reg, u32 val) { struct piix_host_priv *hpriv = link->ap->host->private_data; + unsigned long flags; if (reg >= ARRAY_SIZE(piix_sidx_map)) return -EINVAL; + spin_lock_irqsave(&hpriv->sidpr_lock, flags); piix_sidpr_sel(link, reg); iowrite32(val, hpriv->sidpr + PIIX_SIDPR_DATA); + spin_unlock_irqrestore(&hpriv->sidpr_lock, flags); return 0; } @@ -1566,6 +1573,7 @@ static int __devinit piix_init_one(struc hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL); if (!hpriv) return -ENOMEM; + spin_lock_init(&hpriv->sidpr_lock); /* Save IOCFG, this will be used for cable detection, quirk * detection and restoration on detach. This is necessary -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |