From: Tejun Heo <tj@kernel.org>
To: Jeff Garzik lin <jeff@garzik.org>,
"linux-ide@vger.kernel.org" <linux-ide@vger.kernel.org>,
stable <stable@kernel.org>
Cc: Mark Knecht <markknecht@gmail.com>, Paul Check <paul@thechecks.ca>
Subject: [PATCH #upstream-fixes] ata_piix: fix locking around SIDPR access
Date: Tue, 20 Jul 2010 16:20:01 +0200 [thread overview]
Message-ID: <4C45B091.2000002@kernel.org> (raw)
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@kernel.org>
Reported-by: Mark Knecht <markknecht@gmail.com>
Reported-by: Paul Check <paul@thechecks.ca>
Cc: stable@kernel.org
---
drivers/ata/ata_piix.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 7409f98..3971bc0 100644
--- 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 ata_link *link,
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 ata_link *link,
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(struct pci_dev *pdev,
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
next reply other threads:[~2010-07-20 14:20 UTC|newest]
Thread overview: 3+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-07-20 14:20 Tejun Heo [this message]
2010-07-29 14:42 ` [PATCH #upstream-fixes] ata_piix: fix locking around SIDPR access David Milburn
2010-08-01 23:48 ` Jeff Garzik
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=4C45B091.2000002@kernel.org \
--to=tj@kernel.org \
--cc=jeff@garzik.org \
--cc=linux-ide@vger.kernel.org \
--cc=markknecht@gmail.com \
--cc=paul@thechecks.ca \
--cc=stable@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).