- 18 Jun, 2009 40 commits
-
-
Jack Steiner authored
Add user function to explicitly unload GRU kernel contexts from the GRU. Only contexts that are not in-use will be unloaded. This function is primarily for testing. It is not expected that this will be used in normal production systems. Signed-off-by:
Jack Steiner <steiner@sgi.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Jack Steiner authored
Fix two problems related to GRU instruction failures. Cache coherency is not maintained for CBEs except when loading or unloading contexts. When reading a CBE to extract error information, the CBE must first be flushed from the cache. The function that reads kerrnel CBEs was reading the wrong CBE. Signed-off-by:
-
Jack Steiner authored
Update GRU driver to the latest version of the GRU spec. This consists of minor updates: - changes & additions to error status bits - new restriction on handling of TLB misses while in FMM mode - new field (not used by software) in TFH Signed-off-by:
-
Jack Steiner authored
Change the kernel self tests that can be optionally executed on GRU initialization. This is primarily for testing. Eliminate the BUG statements on failure and return bad status. Add ioctl interface to execute the tests on demand. Signed-off-by:
-
Jack Steiner authored
Add support for asynchronous GRU instructions. Currently, asynchronous instructions are supported only for GRU instructions issued by the kernel. [akpm@linux-foundation.org: build fix] Signed-off-by:
-
Jack Steiner authored
Add support for interrupts generated by GRU instruction completion. Previously, the only interrupts were for TLB misses. The hardware also supports interrupts on instruction completion. This will be supported for instructions issued by the kernel. Signed-off-by:
-
Jack Steiner authored
Check whether the gru state being loaded into a gru is from a new context or a previously unloaded context. If new, simply zero out the hardware context; if unloaded and valid, reload the old state. This change is primarily for reloading kernel contexts where the previous is not required to be saved. Signed-off-by:
-
Jack Steiner authored
Fix endcase in handling GRU message queue failures due to NACKs of PUT requests. Must ensure that the "present" bits are cleared before resending the message. Signed-off-by:
-
Jack Steiner authored
Support alocation of GRU contexts that contain zero DSR or CBR resources. Some instructions do not require DSR resources. Contexts without CBR resources are useful for diagnostics. Signed-off-by:
-
Jack Steiner authored
Change the way GRU resources are assigned for kernel threads. GRU contexts for kernel threads are now allocated on demand and can be stolen by user processes when idle. This allows MPI jobs to use ALL of the GRU resources when the kernel is not using them. Signed-off-by:
-
Jack Steiner authored
Change the interface to cch_allocate so that it can be used to allocate GRU contexts for kernel threads. Kernel threads use the GRU in unmapped mode and do not require ASIDs for the GRU TLB. Signed-off-by:
-
Jack Steiner authored
Remove "static" from the functions for loading/unloading GRU contexts. These functions will be called from other GRU files. Fix bug in unlocking gru context. Signed-off-by:
-
Jack Steiner authored
Change the interface to gru_alloc_gts() so that it can be used to allocate GRU contexts for kernel threads. Kernel threads do not have vdata structures for the GRU contexts. The GRU resource count are now passed explicitly instead of inside the vdata structure. Signed-off-by:
-
Jack Steiner authored
Add support for dumpping the state of an entire GRU chiplet. Signed-off-by:
-
Jack Steiner authored
Bug fixes for GRU exception handling. Additional fields from the CBR must be returned to the user to allow the user to correctly diagnose GRU exceptions. Handle endcase in TFH TLB miss handling. Verify that TFH actually indicates a pending exception. Signed-off-by:
-
Neil Horman authored
Currently the sysrq-c handler is bit over-engineered. Its behavior is dependent on a few compile time and run time factors that alter its behavior which is really unnecessecary. If CONFIG_KEXEC is not configured, sysrq-c, crashes the system with a NULL pointer dereference. If CONFIG_KEXEC is configured, it calls crash_kexec directly, which implies that the kexec kernel will either be booted (if its been previously loaded), or it will simply do nothing (the no kexec kernel has been loaded). It would be much easier to just simplify the whole thing to dereference a NULL pointer all the time regardless of configuration. That way, it will always try to crash the system, and if a kexec kernel has been loaded into reserved space, it will still boot from the page fault trap handler (assuming panic_on_oops is set appropriately). [akpm@linux-foundation.org: build fix] Signed-off-by:
Neil Horman <nhorman@tuxdriver.com> Acked-by:
Vivek Goyal <vgoyal@redhat.com> Cc: Brayan Arraes <brayan@yack.com.br> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by:
-
Daniel Mack authored
On embedded devices, sleep mode conditions can be tricky to handle, Especially when processors tend to pull-down the w1 bus during sleep. Bus slaves (such as the ds2760) may interpret this as a reason for power-down conditions and entirely switch off the device. This patch adds a callback function pointer to let users switch on and off the external pull-up resistor. This lets the outside world know whether the processor is currently actively driving the bus or not. When this callback is not provided, the code behaviour won't change. Signed-off-by:
Daniel Mack <daniel@caiaq.de> Acked-by:
Ville Syrjala <syrjala@sci.fi> Acked-by:
Evgeniy Polyakov <johnpol@2ka.mipt.ru> Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp> Acked-by:
Joerg Roedel <joerg.roedel@amd.com> Cc: Ingo Molnar <mingo@elte.hu> Acked-by:
"Luck, Tony" <tony.luck@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc; "David S. Miller" <davem@davemloft.net> Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
-
FUJITA Tomonori authored
Signed-off-by:
Ingo Molnar <mingo@elte.hu> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: James Bottomley <James.Bottomley@HansenPartnership.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Catalin Marinas <catalin.marinas@arm.com> Signed-off-by:
-
FUJITA Tomonori authored
We unified x86 and IA64's handling of multiple dma mapping operations (struct dma_map_ops in linux/dma-mapping.h) so we can remove duplication in their arch/include/asm/dma-mapping.h. This patchset adds include/asm-generic/dma-mapping-common.h that provides some generic dma mapping function definitions for the users of struct dma_map_ops. This enables us to remove about 100 lines. This also enables us to easily add CONFIG_DMA_API_DEBUG support, which only x86 supports for now. The 4th patch adds CONFIG_DMA_API_DEBUG support to IA64 by adding only 8 lines. This patch: This header file provides some mapping function definitions that the users of struct dma_map_ops can use. Signed-off-by:
-
Peter Oberparleiter authored
Enable gcov profiling of the entire kernel on x86_64. Required changes include disabling profiling for: * arch/kernel/acpi/realmode and arch/kernel/boot/compressed: not linked to main kernel * arch/vdso, arch/kernel/vsyscall_64 and arch/kernel/hpet: profiling causes segfaults during boot (incompatible context) Signed-off-by:
Peter Oberparleiter <oberpar@linux.vnet.ibm.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Huang Ying <ying.huang@intel.com> Cc: Li Wei <W.Li@Sun.COM> Cc: Michael Ellerman <michaele@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Heiko Carstens <heicars2@linux.vnet.ibm.com> Cc: Martin Schwidefsky <mschwid2@linux.vnet.ibm.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: WANG Cong <xiyou.wangcong@gmail.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by:
-
Peter Oberparleiter authored
Enable the use of GCC's coverage testing tool gcov [1] with the Linux kernel. gcov may be useful for: * debugging (has this code been reached at all?) * test improvement (how do I change my test to cover these lines?) * minimizing kernel configurations (do I need this option if the associated code is never run?) The profiling patch incorporates the following changes: * change kbuild to include profiling flags * provide functions needed by profiling code * present profiling data as files in debugfs Note that on some architectures, enabling gcc's profiling option "-fprofile-arcs" for the entire kernel may trigger compile/link/ run-time problems, some of which are caused by toolchain bugs and others which require adjustment of architecture code. For this reason profiling the entire kernel is initially restricted to those architectures for which it is known to work without changes. This restriction can be lifted once an architecture has been tested and found compatible with gcc's profiling. Profiling of single files or directories is still available on all platforms (see config help text). [1] http://gcc.gnu.org/onlinedocs/gcc/Gcov.htmlSigned-off-by:
-
Peter Oberparleiter authored
seq_write() can be used to construct seq_files containing arbitrary data. Required by the gcov-profiling interface to synthesize binary profiling data files. Signed-off-by:
-
Peter Oberparleiter authored
Call constructors (gcc-generated initcall-like functions) during kernel start and module load. Constructors are e.g. used for gcov data initialization. Disable constructor support for usermode Linux to prevent conflicts with host glibc. Signed-off-by:
Rusty Russell <rusty@rustcorp.com.au> Acked-by:
WANG Cong <xiyou.wangcong@gmail.com> Cc: Sam Ravnborg <sam@ravnborg.org> Cc: Jeff Dike <jdike@addtoit.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Huang Ying <ying.huang@intel.com> Cc: Li Wei <W.Li@Sun.COM> Cc: Michael Ellerman <michaele@au1.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Heiko Carstens <heicars2@linux.vnet.ibm.com> Cc: Martin Schwidefsky <mschwid2@linux.vnet.ibm.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by:
-
GeunSik Lim authored
Fix the meaning of EDAC(Error Detection And Correction) correctly. [akpm@linux-foundation.org: add missing space] Signed-off-by:
GeunSik Lim <geunsik.lim@samsung.com> Cc: Alan Cox <alan@lxorguk.ukuu.org.uk> Acked-by:
Doug Thompson <dougthompson@xmission.com> Signed-off-by:
-
Mike Frysinger authored
The remove function uses __devexit, so the .remove assignment needs __devexit_p() to fix a build error with hotplug disabled. Signed-off-by:
Mike Frysinger <vapier@gentoo.org> Cc: Doug Thompson <dougthompson@xmission.com> Signed-off-by:
-
Harry Ciao authored
Fix up the number of cells for the values of CPC925 Memory Controller, and setup related platform device during system booting up, against which CPC925 Memory Controller EDAC driver would be matched. Signed-off-by:
Harry Ciao <qingtao.cao@windriver.com> Cc: Doug Thompson <norsk5@yahoo.com> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Kumar Gala <galak@gate.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Signed-off-by:
-
Harry Ciao authored
Add edac_device_alloc_index(), because for MAPLE platform there may exist several EDAC driver modules that could make use of edac_device_ctl_info structure at the same time. The index allocation for these structures should be taken care of by EDAC core. [akpm@linux-foundation.org: cleanups] Signed-off-by:
-
Harry Ciao authored
Introduce IBM CPC925 EDAC driver, which makes use of ECC, CPU and HyperTransport Link error detections and corrections on the IBM CPC925 Bridge and Memory Controller. [akpm@linux-foundation.org: cleanup] Signed-off-by:
-
Matt Helsley authored
Strictly speaking list_op_pending points to the 'lock entry', not the 'lock word' (which is actually at 'offset' from 'lock entry'). We can infer this based on reading the code in kernel/futex.c: struct robust_list __user *entry, *next_entry, *pending; ... if (fetch_robust_entry(&pending, &head->list_op_pending, &pip)) return; ... if (pending) handle_futex_death((void __user *)pending + futex_offset, curr, pip); Which is also consistent with the rest of the docs on robust futex lists. Signed-off-by:Matt Helsley <matthltc@us.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linuxtronix.de> Signed-off-by:
-
Alexey Dobriyan authored
Function is really private to ipc/ and avoid struct kern_ipc_perm forward declaration. Signed-off-by:
Alexey Dobriyan <adobriyan@gmail.com> Reviewed-by:
-
Alexey Dobriyan authored
Signed-off-by:
-
Alexey Dobriyan authored
clone_nsproxy() does useless copying of old nsproxy -- every pointer will be rewritten to new ns or to old ns. Remove copying, rename clone_nsproxy(), create_nsproxy() will be used by C/R code to create fresh nsproxy on restart. Signed-off-by:
Serge Hallyn <serue@us.ibm.com> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by:
-
Alexey Dobriyan authored
clone_ipc_ns() is misnamed, it doesn't clone anything and doesn't use passed parameter. Rename it. create_ipc_ns() will be used by C/R to create fresh ipcns. Signed-off-by:
-
Alexey Dobriyan authored
copy_ipcs() doesn't actually copy anything. If new ipcns is created, it's created from scratch, in this case get/put on old ipcns isn't needed. Signed-off-by:
-
Alexey Dobriyan authored
create_uts_ns() will be used by C/R to create fresh uts_ns. Signed-off-by:
-
Alexey Dobriyan authored
copy_pid_ns() is a perfect example of a case where unwinding leads to more code and makes it less clear. Watch the diffstat. Signed-off-by:
Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Reviewed-by:
-
Alexey Dobriyan authored
create_pid_namespace() creates everything, but caller has to assign parent pidns by hand, which is unnatural. At the moment of call new ->level has to be taken from somewhere and parent pidns is already available. Signed-off-by:
-
Christoph Hellwig authored
find_task_by_pid_type_ns is only used to implement find_task_by_vpid and find_task_by_pid_ns, but both of them pass PIDTYPE_PID as first argument. So just fold find_task_by_pid_type_ns into find_task_by_pid_ns and use find_task_by_pid_ns to implement find_task_by_vpid. While we're at it also remove the exports for find_task_by_pid_ns and find_task_by_vpid - we don't have any modular callers left as the only modular caller of he old pre pid namespace find_task_by_pid (gfs2) was switched to pid_task which operates on a struct pid pointer instead of a pid_t. Given the confusion about pid_t values vs namespace that's generally the better option anyway and I think we're better of restricting modules to do it that way. Signed-off-by:
Christoph Hellwig <hch@lst.de> Cc: Pavel Emelyanov <xemul@openvz.org> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by:
-
