With this patch, kdump uses the firmware soft-reset NMI for two purposes:
1) Initiate the kdump (take a crash dump) by issuing a soft-reset.
2) Break a CPU out of a deadlock condition that is detected during kdump
processing.
When a soft-reset is initiated each CPU will enter
system_reset_exception() and set its corresponding bit in the global
bit-array cpus_in_sr then call die(). When die() finds the CPU's bit set
in cpu_in_sr crash_kexec() is called to initiate a crash dump. The first
CPU to enter crash_kexec() is called the "crashing CPU". All other CPUs
are "secondary CPUs". The secondary CPU's pass through to
crash_kexec_secondary() and sleep. The crashing CPU waits for all CPUs
to enter via soft-reset then boots the kdump kernel (see
crash_soft_reset_check())
When the system crashes due to a panic or exception, crash_kexec() is
called by panic() or die(). The crashing CPU sends an IPI to all other
CPUs to notify them of the pending shutdown. If a CPU is in a deadlock
or hung state with interrupts disabled, the IPI will not be delivered.
The result being, that the kdump kernel is not booted. This problem is
solved with the use of a firmware generated soft-reset. After the
crashing_cpu has issued the IPI, it waits for 10 sec for all CPUs to
enter crash_ipi_callback(). A CPU signifies its entry to
crash_ipi_callback() by setting its corresponding bit in the
cpus_in_crash bit array. After 10 sec, if one or more CPUs have not set
their bit in cpus_in_crash we assume that the CPU(s) is deadlocked. The
operator is then prompted to generate a soft-reset to break the
deadlock. Each CPU enters the soft reset handler as described above.
Two conditions must be handled at this point:
1) The system crashed because the operator generated a soft-reset. See
2) The system had crashed before the soft-reset was generated ( in the
case of a Panic or oops).
The first CPU to enter crash_kexec() uses the state of the kexec_lock to
determine this state. If kexec_lock is already held then condition 2 is
true and crash_kexec_secondary() is called, else; this CPU is flagged as
the crashing CPU, the kexec_lock is acquired and crash_kexec() proceeds
as described above.
Each additional CPUs responding to the soft-reset will pass through
crash_kexec() to kexec_secondary(). All secondary CPUs call
crash_ipi_callback() readying them self's for the shutdown. When ready
they clear their bit in cpus_in_sr. The crashing CPU waits in
kexec_secondary() until all other CPUs have cleared their bits in
cpus_in_sr. The kexec kernel boot is then started.
Signed-off-by: Haren Myneni <haren@us.ibm.com>
Signed-off-by: David Wilder <dwilder@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The class zero interrupt handling for spus was confusing alignment and
error interrupts, so swap them.
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
spufs_base.c calls __add_pages, which depends on CONFIG_MEMORY_HOTPLUG.
Moved the selection of CONFIG_MEMORY_HOTPLUG from CONFIG_SPUFS_MMAP
to CONFIG_SPU_FS.
Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
In the context save/restore code, the SPU MFC command queue purge
code has a bug:
static inline void wait_purge_complete(struct spu_state *csa, struct
spu *spu)
{
struct spu_priv2 __iomem *priv2 = spu->priv2;
/* Save, Step 28:
* Poll MFC_CNTL[Ps] until value '11' is
* read
* (purge complete).
*/
POLL_WHILE_FALSE(in_be64(&priv2->mfc_control_RW)
& MFC_CNTL_PURGE_DMA_COMPLETE);
}
This will exit as soon as _one_ of the 2 bits that compose
MFC_CNTL_PURGE_DMA_COMPLETE is set, and one of them happens to be
"purge in progress"... which means that we'll happily continue
restoring the MFC while it's being purged at the same time.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Arnd Bergmann <arnd.bergmann@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This fixes a bug where we don't properly map SPE MMIO space as guarded,
causing various test cases to fail, probably due to write combining and other
niceties caused by the lack of the G bit.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Now that we have the udbg callbacks we can enable XMON by default.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Enable the RTAS udbg console on IBM Cell Blade, this allows xmon
to work.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Add udbg hooks for the RTAS console, based on the RTAS put-term-char
and get-term-char calls. Along with my previous patches, this should
enable debugging as soon as early_init_dt_scan_rtas() is called.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Althought RTAS is instantiated when we enter the kernel, we can't actually
call into it until we know its entry point address. Currently we grab that
in rtas_initialize(), however that's quite late in the boot sequence.
To enable rtas_call() earlier, we can grab the RTAS entry etc. values while
we're scanning the flattened device tree. There's existing code to retrieve
the values from /chosen, however we don't store them there anymore, so remove
that code.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Move RTAS exports next to their declarations.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Currently it's unsafe to call rtas_call() prior to rtas_initialize(). This
is because the rtas.entry value hasn't been setup and so we don't know
where to enter, but we just try anyway.
We can't do anything intelligent without rtas.entry, so if it's not set, just
return. Code that calls rtas_call() early needs to be aware that the call
might fail.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
There's no need to set the boot cpu paca in asm, so do it in C so us
mere mortals can understand it.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
There's no reason kexec_setup() needs to be called explicitly from
setup_system(), it can just be a regular initcall.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
With the ppc_md htab pointers setup earlier, we can use ppc_md.hpte_insert
in htab_bolt_mapping(), rather than deciding which version to call by hand.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Initialise the ppc_md htab callbacks earlier, in the probe routines. This
allows us to call htab_finish_init() from htab_initialize(), and makes it
private to hash_utils_64.c. Move htab_finish_init() and make_bl() above
htab_initialize() to avoid forward declarations.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
If DEBUG is turned on in prom.c, export the flat device tree via debugfs.
This has been handy on several occasions.
To look at it:
# mount -t debugfs none /sys/kernel/debug
# od -a /sys/kernel/debug/powerpc/flat-device-tree
and/or
# dtc -fI dtb /sys/kernel/debug/powerpc/flat-device-tree -O dts
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
None of this seems to be necessary, so let's see if can remove it and not
break anything. Booted on iSeries & pSeries here.
NB. we don't remove the hvReleaseData, we just move it down so that the file
reads more clearly.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
During kdump boot, noticed some machines checkstop on dma protection
fault for ongoing DMA left in the first kernel. Instead of initializing
TCE entries in iommu_init() for the kdump boot, this patch fixes this
issue by walking through the each TCE table and checks whether the
entries are in use by the first kernel. If so, reserve those entries by
setting the corresponding bit in tbl->it_map such that these entries
will not be available for the kdump boot.
However it could be possible that all TCE entries might be used up due
to the driver bug that does continuous mapping. My observation is around
1700 TCE entries are used on some systems (Ex: P4) at some point of
time during kdump boot and saving dump (either write into the disk or
sending to remote machine). Hence, this patch will make sure that
minimum of 2048 entries will be available such that kdump boot could be
successful in some cases.
Signed-off-by: Haren Myneni <haren@us.ibm.com>
Acked-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The following patch avoids accessing Hypervisor privilege HID
registers when running on a Hypervisor (MSR[HV]=0).
Signed-off-by: Jimi Xenidis <jimix@watson.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch removes the old pmac ide led blink code and
adds generic LED subsystem support for the LED.
It maintains backward compatibility with the old
BLK_DEV_IDE_PMAC_BLINK Kconfig option which now
simply selects the new code and influences the
default trigger.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Builds on ARM report link problems with common configurations like
statically linked NFS (for nfsroot). The symptom is that __init
section code references __exit section code; that won't work since
the exit sections are discarded (since they can never be called).
The best fix for these particular cases would be an "__init_or_exit"
section annotation.
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Acked-by: Trond Myklebust <trond.myklebust@fys.uio.no>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
It should be done before calling class_device_unregister() because
it will destroy the device and free memory if there are no other
references to the device.
Signed-off-by: Dmitry Torokhov <dtor@mail.ru>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
This reverts commit e5c44fd88c.
Thanks to Daniel Ritz and Michal Piotrowski for noticing the problem.
Daniel says:
"[The] reason is a recent change that made modules always shows as
module.mod. it breaks modprobe and probably many scripts..besides
lsmod looking horrible
stuff like this in modprobe.conf:
install pcmcia_core /sbin/modprobe --ignore-install pcmcia_core; /sbin/modprobe pcmcia
makes modprobe fork/exec endlessly calling itself...until oom
interrupts it"
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: (56 commits)
[PATCH] fs/ocfs2/dlm/: cleanups
ocfs2: fix compiler warnings in dlm_convert_lock_handler()
ocfs2: dlm_print_one_mle() needs to be defined
ocfs2: remove whitespace in dlmunlock.c
ocfs2: move dlm work to a private work queue
ocfs2: fix incorrect error returns
ocfs2: tune down some noisy messages during dlm recovery
ocfs2: display message before waiting for recovery to complete
ocfs2: mlog in dlm_convert_lock_handler() should be ML_ERROR
ocfs2: retry operations when a lock is marked in recovery
ocfs2: use cond_resched() in dlm_thread()
ocfs2: use GFP_NOFS in some dlm operations
ocfs2: wait for recovery when starting lock mastery
ocfs2: continue recovery when a dead node is encountered
ocfs2: remove unneccesary spin_unlock() in dlm_remaster_locks()
ocfs2: dlm_remaster_locks() should never exit without completing
ocfs2: special case recovery lock in dlmlock_remote()
ocfs2: pending mastery asserts and migrations should block each other
ocfs2: temporarily disable automatic lock migration
ocfs2: do not unconditionally purge the lockres in dlmlock_remote()
...
Patch from Ben Dooks
Update the list of supported devices, and remove the
changelog. Add SMDK2413 information.--
Signed-off-by: Ben Dooks <ben-linux@fluff.org>Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
This patch #if 0's the no longer used dlm_dump_lock_resources().
Since this makes dlmdebug.h empty, this patch also removes this header.
Additionally, the needlessly global dlm_is_node_recovered() is made
static.
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
The work that is done can block for long periods of time and so is not
appropriate for keventd.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Before checking for a nonexistent lock, make sure the lockres is not marked
RECOVERING. The caller will just retry and the state should be fixed up when
recovery completes.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
We cannot restart recovery. Once we begin to recover a node, keep the state
of the recovery intact and follow through, regardless of any other node
deaths that may occur.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
If the previous master of the recovery lock dies, let calc_usage take it
down completely and let the caller completely redo the dlmlock() call.
Otherwise, there will never be an opportunity to re-master the lockres and
recovery wont be able to progress.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
Use the existing structure for blocking migrations when ASTs are pending to
achieve the same result. If we can catch the assert before it goes on the
wire, just cancel it and let the migration continue.
Signed-off-by: Kurt Hackel <kurt.hackel@oracle.com>
Signed-off-by: Mark Fasheh <mark.fasheh@oracle.com>
