Hi guys,
After upgrading from 3.5.4 to 3.5.5 I started noticing log lines of the
form (just a random sample)
pci_bus 0000:00: >resource 4 [io 0x0000-0x0cf7]
pnp 00:07: >Plug and Play ACPI device, IDs PNP0303 (active)
system 00:04: >[io 0x0680-0x069f] has been reserved
pci_root PNP0A08:00: >host bridge window [io 0x0000-0x0cf7]
Note the right angle bracket between the device name and the message
string. These angle brackets were not there up till 3.5.4.
This does not happen in all dmesg lines. Only the ones that start with a
device identifier.
I assume this angle bracket was not intentional. Otherwise please excuse
the noise.
I noticed this because all of these lines now suddenly slip through my
logcheck ignore rules.
Bisection points to this commit:
commit 3d822616ca81881d8c19d0b473e79ba241c700de
Author: Markus Trippelsdorf <[email protected]>
Date: Sat Aug 18 18:35:51 2012 -0600
dyndbg: fix for SOH in logging messages
commit ebdc82899ec5ed35af1c79ed6a4eeda69dad9b90 upstream.
commit af7f2158fde was done against master, and clashed with structured
logging's change of KERN_LEVEL to SOH.
Bisected and fixed by Markus Trippelsdorf.
Reported-by: Markus Trippelsdorf <[email protected]>
Signed-off-by: Jim Cromie <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: Andrew Morton <[email protected]>
Cc: Jason Baron <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b18138a..c598122 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1895,8 +1895,8 @@ int __dev_printk(const char *level, const struct
device *dev,
"DEVICE=+%s:%s", subsys,
dev_name(dev));
}
skip:
- if (level[3])
- level_extra = &level[3]; /* skip past "<L>" */
+ if (level[2])
+ level_extra = &level[2]; /* skip past KERN_SOH "L" */
return printk_emit(0, level[1] - '0',
dictlen ? dict : NULL, dictlen,
That seems plausible, since it changes __dev_printk. Could there be some
off-by-one here?
With kind regards,
Wouter Koolen
On 2012.10.08 at 15:05 +0100, Wouter M. Koolen wrote:
> Hi guys,
>
> After upgrading from 3.5.4 to 3.5.5 I started noticing log lines of the
> form (just a random sample)
>
> pci_bus 0000:00: >resource 4 [io 0x0000-0x0cf7]
> pnp 00:07: >Plug and Play ACPI device, IDs PNP0303 (active)
> system 00:04: >[io 0x0680-0x069f] has been reserved
> pci_root PNP0A08:00: >host bridge window [io 0x0000-0x0cf7]
>
> Note the right angle bracket between the device name and the message
> string. These angle brackets were not there up till 3.5.4.
>
> This does not happen in all dmesg lines. Only the ones that start with a
> device identifier.
>
> I assume this angle bracket was not intentional. Otherwise please excuse
> the noise.
>
> I noticed this because all of these lines now suddenly slip through my
> logcheck ignore rules.
>
> Bisection points to this commit:
>
> commit 3d822616ca81881d8c19d0b473e79ba241c700de
> Author: Markus Trippelsdorf <[email protected]>
> Date: Sat Aug 18 18:35:51 2012 -0600
This patch should be reverted for stable, since the move to ASCII SOH (
commit 04d2c8c83d0) wasn't backported. So the fix just isn't necessary.
--
Markus
On Mon, Oct 08, 2012 at 04:18:29PM +0200, Markus Trippelsdorf wrote:
> On 2012.10.08 at 15:05 +0100, Wouter M. Koolen wrote:
> > Hi guys,
> >
> > After upgrading from 3.5.4 to 3.5.5 I started noticing log lines of the
> > form (just a random sample)
> >
> > pci_bus 0000:00: >resource 4 [io 0x0000-0x0cf7]
> > pnp 00:07: >Plug and Play ACPI device, IDs PNP0303 (active)
> > system 00:04: >[io 0x0680-0x069f] has been reserved
> > pci_root PNP0A08:00: >host bridge window [io 0x0000-0x0cf7]
> >
> > Note the right angle bracket between the device name and the message
> > string. These angle brackets were not there up till 3.5.4.
> >
> > This does not happen in all dmesg lines. Only the ones that start with a
> > device identifier.
> >
> > I assume this angle bracket was not intentional. Otherwise please excuse
> > the noise.
> >
> > I noticed this because all of these lines now suddenly slip through my
> > logcheck ignore rules.
> >
> > Bisection points to this commit:
> >
> > commit 3d822616ca81881d8c19d0b473e79ba241c700de
> > Author: Markus Trippelsdorf <[email protected]>
> > Date: Sat Aug 18 18:35:51 2012 -0600
>
> This patch should be reverted for stable, since the move to ASCII SOH (
> commit 04d2c8c83d0) wasn't backported. So the fix just isn't necessary.
Ick, sorry about that, I'll go revert it for the next 3.5.y release,
thanks for letting me know.
greg k-h