The following set of patches are aimed at improving kprobes scalability. We
currently serialize kprobe registration, unregistration and handler execution
using a single spinlock - kprobe_lock.
With these changes, kprobe handlers can run without any locks held. It also
allows for simultaneous kprobe handler executions on different processors as
we now track kprobe execution on a per processor basis. It is now necessary
that the handlers be re-entrant since handlers can run concurrently on
multiple processors.
All changes have been tested on i386, ia64, ppc64 and x86_64, while sparc64
has been compile tested only.
The patches can be viewed as 3 logical chunks:
patch 1: Reorder preempt_(dis/en)able calls
patches 2-7: Introduce per_cpu data areas to track kprobe execution
patches 8-9: Use RCU to synchronize kprobe (un)registration and handler
execution.
Thanks to Maneesh Soni, James Keniston and Anil Keshavamurthy for their
review and suggestions. Thanks again to Anil, Hien Nguyen and Kevin Stafford
for testing the patches.
This patch:
Reorder preempt_disable/enable() calls in arch kprobes files in preparation to
introduce locking changes. No functional changes introduced by this patch.
Signed-off-by: Ananth N Mavinakayahanalli <ananth@in.ibm.com>
Signed-off-by: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Andrew Morton suggested to move kprobes from kernel hacking menu, since
kernel hacking menu is in-appropriate for the Kprobes. This patch moves
Kprobes and Oprofile under instrumentation menu.
(akpm: it's not a natural fit, but things like djprobes and the s390 guys'
statistics library need a home)
Signed-of-by: Prasanna S Panchamukhi <prasanna@in.ibm.com>
Cc: Philippe Elie <phil.el@wanadoo.fr>
Cc: John Levon <levon@movementarian.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The current ia64 implementation of dma_get_cache_alignment does not work
for modules because it relies on a symbol which is not exported. Direct
access to a global is a little ugly anyway, so this patch re-implements
dma_get_cache_alignment in a manner similar to what is currently used for
x86_64.
Signed-off-by: John W. Linville <linville@tuxdriver.com>
Cc: "Luck, Tony" <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
I recently picked up my older work to remove unnecessary #includes of
sched.h, starting from a patch by Dave Jones to not include sched.h
from module.h. This reduces the number of indirect includes of sched.h
by ~300. Another ~400 pointless direct includes can be removed after
this disentangling (patch to follow later).
However, quite a few indirect includes need to be fixed up for this.
In order to feed the patches through -mm with as little disturbance as
possible, I've split out the fixes I accumulated up to now (complete for
i386 and x86_64, more archs to follow later) and post them before the real
patch. This way this large part of the patch is kept simple with only
adding #includes, and all hunks are independent of each other. So if any
hunk rejects or gets in the way of other patches, just drop it. My scripts
will pick it up again in the next round.
Signed-off-by: Tim Schmielau <tim@physik3.uni-rostock.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Define jiffies_64 in kernel/timer.c rather than having 24 duplicated
defines in each architecture.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Make sure we always return, as all syscalls should. Also move the common
prototype to <linux/syscalls.h>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
pgdat->node_size_lock is basically only neeeded in one place in the normal
code: show_mem(), which is the arch-specific sysrq-m printing function.
Strictly speaking, the architectures not doing memory hotplug do no need this
locking in show_mem(). However, they are all included for completeness. This
should also make any future consolidation of all of the implementations a
little more straightforward.
This lock is also held in the sparsemem code during a memory removal, as
sections are invalidated. This is the place there pfn_valid() is made false
for a memory area that's being removed. The lock is only required when doing
pfn_valid() operations on memory which the user does not already have a
reference on the page, such as in show_mem().
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
There was one small but very significant change in the previous patch:
mprotect's flush_tlb_range fell outside the page_table_lock: as it is in 2.4,
but that doesn't prove it safe in 2.6.
On some architectures flush_tlb_range comes to the same as flush_tlb_mm, which
has always been called from outside page_table_lock in dup_mmap, and is so
proved safe. Others required a deeper audit: I could find no reliance on
page_table_lock in any; but in ia64 and parisc found some code which looks a
bit as if it might want preemption disabled. That won't do any actual harm,
so pending a decision from the maintainers, disable preemption there.
Remove comments on page_table_lock from flush_tlb_mm, flush_tlb_range and
flush_tlb_page entries in cachetlb.txt: they were rather misleading (what
generic code does is different from what usually happens), the rules are now
changing, and it's not yet clear where we'll end up (will the generic
tlb_flush_mmu happen always under lock? never under lock? or sometimes under
and sometimes not?).
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
First step in pushing down the page_table_lock. init_mm.page_table_lock has
been used throughout the architectures (usually for ioremap): not to serialize
kernel address space allocation (that's usually vmlist_lock), but because
pud_alloc,pmd_alloc,pte_alloc_kernel expect caller holds it.
Reverse that: don't lock or unlock init_mm.page_table_lock in any of the
architectures; instead rely on pud_alloc,pmd_alloc,pte_alloc_kernel to take
and drop it when allocating a new one, to check lest a racing task already
did. Similarly no page_table_lock in vmalloc's map_vm_area.
Some temporary ugliness in __pud_alloc and __pmd_alloc: since they also handle
user mms, which are converted only by a later patch, for now they have to lock
differently according to whether or not it's init_mm.
If sources get muddled, there's a danger that an arch source taking
init_mm.page_table_lock will be mixed with common source also taking it (or
neither take it). So break the rules and make another change, which should
break the build for such a mismatch: remove the redundant mm arg from
pte_alloc_kernel (ppc64 scrapped its distinct ioremap_mm in 2.6.13).
Exceptions: arm26 used pte_alloc_kernel on user mm, now pte_alloc_map; ia64
used pte_alloc_map on init_mm, now pte_alloc_kernel; parisc had bad args to
pmd_alloc and pte_alloc_kernel in unused USE_HPPA_IOREMAP code; ppc64
map_io_page forgot to unlock on failure; ppc mmu_mapin_ram and ppc64 im_free
took page_table_lock for no good reason.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
ia64 has expand_backing_store function for growing its Register Backing Store
vma upwards. But more complete code for this purpose is found in the
CONFIG_STACK_GROWSUP part of mm/mmap.c. Uglify its #ifdefs further to provide
expand_upwards for ia64 as well as expand_stack for parisc.
The Register Backing Store vma should be marked VM_ACCOUNT. Implement the
intention of growing it only a page at a time, instead of passing an address
outside of the vma to handle_mm_fault, with unknown consequences.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
The original vm_stat_account has fallen into disuse, with only one user, and
only one user of vm_stat_unaccount. It's easier to keep track if we convert
them all to __vm_stat_account, then free it from its __shackles.
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
... and related annotations for amd64 - swiotlb code is shared, but
prototypes are not.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
In arch/ia64/kernel/ptrace.c there is a test for a peek or poke of a
register image (in register backing storage).
The test can be unnecessarily long (and occurs while holding the tasklist_lock).
Especially long on a large system with thousands of active tasks.
The ptrace caller (presumably a debugger) specifies the pid of
its target and an address to peek or poke. But the debugger could be
attached to several tasks.
The idea of find_thread_for_addr() is to find whether the target address
is in the RBS for any of those tasks.
Currently it searches the thread-list of the target pid. If that search
does not find a match, and the shared mm-struct's user count indicates
that there are other tasks sharing this address space (a rare occurrence),
a search is made of all the tasks in the system.
Another approach can drastically shorten this procedure.
It depends upon the fact that in order to peek or poke from/to any task,
the debugger must first attach to that task. And when it does, the
attached task is made a child of the debugger (is chained to its children list).
Therefore we can search just the debugger's children list.
Signed-off-by: Cliff Wickman <cpw@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
flush_tlb_all() can be a scaling issue on large SGI Altix systems
since it uses the global call_lock and always executes on all cpus.
When a process enters flush_tlb_range() to purge TLBs for another
process, it is possible to avoid flush_tlb_all() and instead allow
sn2_global_tlb_purge() to purge TLBs only where necessary.
This patch modifies flush_tlb_range() so that this case can be handled
by platform TLB purge functions and updates ia64_global_tlb_purge()
accordingly. sn2_global_tlb_purge() now calculates the region register
value from the mm argument introduced with this patch.
Signed-off-by: Dean Roe <roe@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
bte_copy() calls calls get_nasid(), which will get flagged if
preemption if enabled. raw_smp_processor_id() is used instead.
It is OK if we migrate off node.
Signed-off-by: Russ Anderson (rja@sgi.com)
Signed-off-by: Tony Luck <tony.luck@intel.com>
Eliminate the passing in of a scratch buffer used for locating the
reserved page setup for XPC.
Signed-off-by: Dean Nelson <dcn@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
XPC needs to be changed to support up to 16k nasids on an SGI Altix system.
Signed-off-by: Dean Nelson <dcn@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
This patch addresses a few issues with the open/close protocol that
were revealed by the newly added disengage functionality combined
with more extensive testing.
Signed-off-by: Dean Nelson <dcn@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
In arch/ia64 change the explicit use of a for-loop using NR_CPUS into the
general for_each_online_cpu() construct. This widens the scope of potential
future optimizations of the general constructs, as well as takes advantage
of the existing optimizations of first_cpu() and next_cpu(), which is
advantageous when the true CPU count is much smaller than NR_CPUS.
Signed-off-by: John Hawkes <hawkes@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
In arch/ia64 change the explicit use of for-loops and NR_CPUS into the
general for_each_cpu() or for_each_online_cpu() constructs, as
appropriate. This widens the scope of potential future optimizations
of the general constructs, as well as takes advantage of the existing
optimizations of first_cpu() and next_cpu().
Signed-off-by: John Hawkes <hawkes@sgi.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
The new ia64 assembler uses slot 1 for the offset of a long (2-slot)
instruction and the old assembler uses slot 2. The 2.6 kernel assumes
slot 2 and won't boot when the new assembler is used:
http://sources.redhat.com/bugzilla/show_bug.cgi?id=1433
This patch will work with either slot 1 or 2.
Patch provided by H.J. Lu
Signed-off-by: Tony Luck <tony.luck@intel.com>
Fix the "siblings" field value in /proc/cpuinfo so that it now shows the
number of siblings as seen by OS, instead of what is available from
hardware perspective.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
The simscsi code at present overflows an int if it's given a large
disk image. The attached patch increases the possible size to 128G.
While it's unlikely that anyone will want to use SKI with such a
large drive, the same framework is currently being used for various
virtualisation experiments.
Signed-off-by: Peter Chubb <peterc@gelato.unsw.edu.au>
Signed-off-by: Tony Luck <tony.luck@intel.com>
changes to swiotlb.c made in commit 281dd25cdc
since this file has been moved from arch/ia64/lib/swiotlb.c to
lib/swiotlb.c
Signed-off-by: Tony Luck <tony.luck@intel.com>
This introduces a limit parameter to the core bootmem allocator; The new
parameter indicates that physical memory allocated by the bootmem
allocator should be within the requested limit.
We also introduce alloc_bootmem_low_pages_limit, alloc_bootmem_node_limit,
alloc_bootmem_low_pages_node_limit apis, but alloc_bootmem_low_pages_limit
is the only api used for swiotlb.
The existing alloc_bootmem_low_pages() api could instead have been
changed and made to pass right limit to the core allocator. But that
would make the patch more intrusive for 2.6.14, as other arches use
alloc_bootmem_low_pages(). We may be done that post 2.6.14 as a
cleanup.
With this, swiotlb gets memory within 4G for both x86_64 and ia64
arches.
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Ravikiran G Thirumalai <kiran@scalex86.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
I've noticed a kernel hang during a storm of CMC interrupts, which was
tracked down to the continual execution of the interrupt handler.
There's code in the CMC handler that's supposed to disable CMC
interrupts and switch to polling mode when it sees a bunch of CMCs.
Because disabling CMCs across all CPUs isn't safe in interrupt context,
the disable is done with a schedule_work(). But with continual CMC
interrupts, the schedule_work() never gets executed.
The following patch immediately disables CMC interrupts for the current
CPU. This then allows (at least) one CPU to ignore CMC interrupts,
execute the schedule_work() code, and disable CMC interrupts on the rest
of the CPUs.
Acked-by: Keith Owens <kaos@sgi.com>
Signed-off-by: Bryan Sutula <Bryan.Sutula@hp.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
