This patch enables support for pause(0) power management state
for the Cell Broadband Processor, which is import for power efficient
operation. The pervasive infrastructure will in the future enable
us to introduce more functionality specific to the Cell's
pervasive unit.
From: Maximino Aguilar <maguilar@us.ibm.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Undefined symbols (eeh_add_device_tree_early and eeh_remove_bus_device)
when EEH is not enabled. This small patch will fix this.
Acked-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Added a common udbg_progress for use by ppc_md.progress()
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Kill L1_CACHE_SHIFT from all arches. Since L1_CACHE_SHIFT_MAX is not used
anymore with the introduction of INTERNODE_CACHE, kill L1_CACHE_SHIFT_MAX.
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
include/asm-ppc/ had #ifdef __KERNEL__ in all header files that
are not meant for use by user space, include/asm-powerpc does
not have this yet.
This patch gets us a lot closer there. There are a few cases
where I was not sure, so I left them out. I have verified
that no CONFIG_* symbols are used outside of __KERNEL__
any more and that there are no obvious compile errors when
including any of the headers in user space libraries.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch adds oprofile support for the 7450 and all its multitudinous
derivatives.
* Added 7450 (and derivatives) support for oprofile
* Changed e500 cputable to have oprofile model and cpu_type fields
* Added support for classic 32-bit performance monitor interrupt
* Cleaned up common powerpc oprofile code to be as common as possible
* Cleaned up oprofile_impl.h to reflect 32 bit classic code
* Added 32-bit MMCRx bitfield definitions and SPR numbers
Signed-off-by: Andy Fleming <afleming@freescale.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This fixes pci_address_to_pio() to return an unsigned long (to be safe)
and fixes a bug in the implementation that caused it to return a bogus
IO port number
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
On ppc64, we independently define VMALLOCBASE and VMALLOC_START to be
the same thing: the start of the vmalloc() area at 0xd000000000000000.
VMALLOC_START is used much more widely, including in generic code, so
this patch gets rid of the extraneous VMALLOCBASE.
This does require moving the definitions of region IDs from page_64.h
to pgtable.h, but they don't clearly belong in the former rather than
the latter, anyway. While we're moving them, clean up the definitions
of the REGION_IDs:
- Abolish REGION_SIZE, it was only used once, to define
REGION_MASK anyway
- Define the specific region ids in terms of the REGION_ID()
macro.
- Define KERNEL_REGION_ID in terms of PAGE_OFFSET rather than
KERNELBASE. It amounts to the same thing, but conceptually this is
about the region of the linear mapping (which starts at PAGE_OFFSET)
rather than of the kernel text itself (which is at KERNELBASE).
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds some very basic support for the new machines, including the
Quad G5 (tested), and other new dual core based machines and iMac G5
iSight (untested). This is still experimental ! There is no thermal
control yet, there is no proper handing of MSIs, etc.. but it
boots, I have all 4 cores up on my machine. Compared to the previous
version of this patch, this one adds DART IOMMU support for the U4
chipset and thus should work fine on setups with more than 2Gb of RAM.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
There is code in the RPAPHP directory that is identical to this routine;
I'll be removing that code in an upcoming patch, but this patch is needed
to expose the function to make it callable.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Cleanup the MPIC IO-APIC workarounds, make them a bit more generic,
smaller and faster.
Signed-off-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The pre-parsed addrs/n_addrs fields in struct device_node are finally
gone. Remove the dodgy heuristics that did that parsing at boot and
remove the fields themselves since we now have a good replacement with
the new OF parsing code. This patch also fixes a bunch of drivers to use
the new code instead, so that at least pmac32, pseries, iseries and g5
defconfigs build.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Milton and I were looking at the cputable code and it looks like we can
set spurious bits on 64bit.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
We used to print a NUMA cpu summary at boot before the hotplug cpu code
was added. This has been useful for catching machine configuration as
well as firmware bugs in the past.
This patch restores that functionality. An example of the output is:
Node 0 CPUs: 0-7
Node 1 CPUs: 8-15
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch reduces lock complexity of SPU scheduler, particularly
for involuntary preemptive switches. As a result the new code
does a better job of mapping the highest priority tasks to SPUs.
Lock complexity is reduced by using the system default workqueue
to perform involuntary saves. In this way we avoid nasty lock
ordering problems that the previous code had. A "minimum timeslice"
for SPU contexts is also introduced. The intent here is to avoid
thrashing.
While the new scheduler does a better job at prioritization it
still does nothing for fairness.
From: Mark Nutter <mnutter@us.ibm.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch makes it easier to preempt an SPU context by
having the scheduler hold ctx->state_sema for much shorter
periods of time.
As part of this restructuring, the control logic for the "run"
operation is moved from arch/ppc64/kernel/spu_base.c to
fs/spufs/file.c. Of course the base retains "bottom half"
handlers for class{0,1} irqs. The new run loop will re-acquire
an SPU if preempted.
From: Mark Nutter <mnutter@us.ibm.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Haren Myneni <haren@us.ibm.com>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Implementing the machine_crash_shutdown which will be called by
crash_kexec (called in case of a panic, sysrq etc.). Disable the
interrupts, shootdown cpus using debugger IPI and collect regs
for all CPUs.
elfcorehdr= specifies the location of elf core header stored by
the crashed kernel. This command line option will be passed by
the kexec-tools to capture kernel.
savemaxmem= specifies the actual memory size that the first kernel
has and this value will be used for dumping in the capture kernel.
This command line option will be passed by the kexec-tools to
capture kernel.
Signed-off-by: Haren Myneni <haren@us.ibm.com>
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
There's a few places where we need to fix things up for the kernel to work
if it's linked at 32MB:
- platforms/powermac/smp.c
To start secondary cpus on pmac we patch the reset vector, which is fine.
Except if we're above 32MB we don't have enough bits for an absolute branch,
it needs to relative.
- kernel/head_64.s
- A few branches in the cpu hold code need to load the full target address
and do a bctr.
- after_prom_start needs to load PHYSICAL_START as the dest address, not 0.
- The exception prolog needs to load the low word of the target adddress,
not just the low halfword.
- Fixup handling of the initial stab address.
- kernel/setup_64.c
smp_release_cpus() needs to write 1 to the spinloop flag near 0, not 32 MB.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Regardless of where the kernel's linked we always get interrupts at low
addresses. This patch creates a trampoline in the first 3 pages of memory,
where interrupts land, and patches those addresses to jump into the real
kernel code at PHYSICAL_START.
We also need to reserve the trampoline code and a bit more in prom.c
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The fwnmi vectors can be anywhere < 32 MB, so we need to use a trampoline
for them. The kdump kernel will register the trampoline addresses, which will
then jump up to the real code above 32 MB.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch adds a Kconfig variable, CONFIG_CRASH_DUMP, which configures the
built kernel for use as a Kdump kernel.
Currently "all" this involves is changing the value of KERNELBASE to 32 MB.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This places dynamically added memory within the appropriate
numa node. A new routine hot_add_scn_to_nid() replicates most of
the memory scanning code in parse_numa_properties().
Signed-off-by: Mike Kravetz <kravetz@us.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch separates usage of KERNELBASE and PAGE_OFFSET. I haven't
looked at any of the PPC32 code, if we ever want to support Kdump on
PPC we'll have to do another audit, ditto for iSeries.
This patch makes PAGE_OFFSET the constant, it'll always be 0xC * 1
gazillion for 64-bit.
To get a physical address from a virtual one you subtract PAGE_OFFSET,
_not_ KERNELBASE.
KERNELBASE is the virtual address of the start of the kernel, it's
often the same as PAGE_OFFSET, but _might not be_.
If you want to know something's offset from the start of the kernel
you should subtract KERNELBASE.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
There's a bunch of code that compares an address with KERNELBASE to see if
it's a "kernel address", ie. >= KERNELBASE. The proper test is actually to
compare with PAGE_OFFSET, since we're going to change KERNELBASE soon.
So replace all of them with an is_kernel_addr() macro that does that.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Currently machine_crash_shutdown() gets a struct pt_regs, but doesn't pass it
through to the ppc_md function, it should.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This updates the OF address parsers to return the IO flags
indicating the type of address obtained. It also adds a PCI
call for converting physical addresses that hit IO space into
into IO tokens, and add routines that return the translated
addresses into struct resource
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
The udbg low level io layer has an issue with udbg_getc() returning a
char (unsigned on ppc) instead of an int, thus the -1 if you had no
available input device could end up turned into 0xff, filling your
display with bogus characters. This fixes it, along with adding a little
blob to xmon to do a delay before exiting when getting an EOF and fixing
the detection of ADB keyboards in udbg_adb.c
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
23-rpaphp-migrate.patch (parts)
This patch moves some pci device add & remove code from the PCI
hotplug directory to the arch/powerpc/kernel directory, and cleans
it up a tad. The primary reason for this is that the code performs
some fairly generic operations that are shared with the PCI error
recovery code (living in the arch/powerpc/kernel directory).
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
22-rpaphp-eliminate-dupe-code.patch (parts)
The RPAPHP code contains two routines that appear to be gratuitous
copies of very similar pci code. In particular,
rpaphp_claim_resource ~~ pci_claim_resource
rpadlpar_claim_one_bus == pcibios_claim_one_bus
This makes pcibios_claim_one_bus from arch/powerpc/kernel/pci_64.c
available to the RPAPHP code.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
20-rpaphp-eeh-cleanup.patch
This patch move some code from the rpaphp directory, to the powerpc
directory, where it should have been all along (Among other things, I
need it in the powerpc directory for the PCI error recovery.)
Please note that patch affects TWO maintainers: Paul, after applying
the powerpc part, please ask that GregKH appli the PCI part. It is safe
to have the powerpc part go in first. It would be bad to have the
PCI part go in first.
Signed-off-by: Linas Vepstas <linas@austin.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch removes several unnecessary fields from the paca:
- next_jiffy_update_tb was simply unused. Remove trivially.
- The exdsi exception save area was not used. There were plans to use
it, but they never seem to have gone anywhere. If they ever do, we
can put it back. Remove from the paca, and from asm-offsets.c
- The default_decr field was used from asm, but was only ever assigned
the value of tb_ticks_per_jiffy. Just access tb_ticks_per_jiffy from
asm directly instead.
Built and booted on POWER5 LPAR and iSeries RS64.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
On iSeries, the paca contains, amongst other things an ItLpRegSave
structure used by the hypervisor to save registers. The hypervisor
locates this area through a pointer at the beginning of the paca, so
the structure itself can be located elsewhere. This patch moves the
reg_save area out into its own array. This reduces the amount of
iSeries specific gunk which is visible to general powerpc code via
paca.h
Built and booted on POWER5 LPAR and iSeries RS64.
Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
ARCH=powerpc couldn't boot from BootX as it uses a "different" way of
getting in the kernel. This patch adds the necessary trampolines,
creating a flattened device-tree from the tree passed from MacOS, and
initializing the btext engine early for really-early debugging.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch unifies udbg for both ppc32 and ppc64 when building the
merged achitecture. xmon now has a single "back end". The powermac udbg
stuff gets enriched with some ADB capabilities and btext output. In
addition, the early_init callback is now called on ppc32 as well,
approx. in the same order as ppc64 regarding device-tree manipulations.
The init sequences of ppc32 and ppc64 are getting closer, I'll unify
them in a later patch.
For now, you can force udbg to the scc using "sccdbg" or to btext using
"btextdbg" on powermacs. I'll implement a cleaner way of forcing udbg
output to something else than the autodetected OF output device in a
later patch.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This moves the discovery of legacy serial ports to a separate file,
makes it common to ppc32 and ppc64, and reworks it to use the new OF
address translators to get to the ports early. This new version can also
detect some PCI serial cards using legacy chips and will probably match
those discovered port with the default console choice.
Only ppc64 gets udbg still yet, unifying udbg isn't finished yet.
It also adds some speed-probing code to udbg so that the default console
can come up at the same speed it was set to by the firmware.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Parsing addresses extracted from Open Firmware isn't a simple matter. We
have various bits of code that try to do it in various place, including
some heuristics in prom.c that pre-parse addresses at boot and fill
device-nodes "addrs", but those are dodgy at best and I want to
deprecate them. So this patch introduces a new set of routines that
should be capable of parsing most types of addresses and translating
them into CPU physical addresses. It currently works for things on PCI
busses and ISA busses and should work on "standard" busses like the root
bus or the MacIO bus that don't put funky flags in addresses. If you
have other bus types that do use funky flags, you'll have to add new bus
type translators, which is fairly easy.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
A previous patch ended up not increasing __NR_syscalls to account
for the new SPU syscalls (probably my fault).
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds a scheduler for SPUs to make it possible to use
more logical SPUs than physical ones are present in the
system.
Currently, there is no support for preempting a running
SPU thread, they have to leave the SPU by either triggering
an event on the SPU that causes it to return to the
owning thread or by sending a signal to it.
This patch also adds operations that enable accessing an SPU
in either runnable or saved state. We use an RW semaphore
to protect the state of the SPU from changing underneath
us, while we are holding it readable. In order to change
the state, it is acquired writeable and a context save
or restore is executed before downgrading the semaphore
to read-only.
From: Mark Nutter <mnutter@us.ibm.com>,
Uli Weigand <Ulrich.Weigand@de.ibm.com>
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This adds the code needed to perform a context switch from
spufs, following the recommended 76-step sequence.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Add some infrastructure for saving and restoring the context of an
SPE. This patch creates a new structure that can hold the whole
state of a physical SPE in memory. It also contains code that
avoids races during the context switch and the binary code that
is loaded to the SPU in order to access its registers.
The actual PPE- and SPE-side context switch code are two separate
patches.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This is the current version of the spu file system, used
for driving SPEs on the Cell Broadband Engine.
This release is almost identical to the version for the
2.6.14 kernel posted earlier, which is available as part
of the Cell BE Linux distribution from
http://www.bsc.es/projects/deepcomputing/linuxoncell/.
The first patch provides all the interfaces for running
spu application, but does not have any support for
debugging SPU tasks or for scheduling. Both these
functionalities are added in the subsequent patches.
See Documentation/filesystems/spufs.txt on how to use
spufs.
Signed-off-by: Arnd Bergmann <arndb@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch adds the necessary core bus support used by device drivers
that sit on the IBM GX bus on modern pSeries machines like the Galaxy
infiniband for example. It provide transparent DMA ops (the low level
driver works with virtual addresses directly) along with a simple bus
layer using the Open Firmware matching routines.
Signed-off-by: Heiko J Schick <schickhj@de.ibm.com>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This cleanup patch speeds up the null syscall path on ppc64 by about 3%,
and brings the ppc32 and ppc64 code slightly closer together.
The ppc64 code was checking current_thread_info()->flags twice in the
syscall exit path; once for TIF_SYSCALL_T_OR_A before disabling
interrupts, and then again for TIF_SIGPENDING|TIF_NEED_RESCHED etc after
disabling interrupts. Now we do the same as ppc32 -- check the flags
only once in the fast path, and re-enable interrupts if necessary in the
ptrace case.
The patch abolishes the 'syscall_noerror' member of struct thread_info
and replaces it with a TIF_NOERROR bit in the flags, which is handled in
the slow path. This shortens the syscall entry code, which no longer
needs to clear syscall_noerror.
The patch adds a TIF_SAVE_NVGPRS flag which causes the syscall exit slow
path to save the non-volatile GPRs into a signal frame. This removes the
need for the assembly wrappers around sys_sigsuspend(),
sys_rt_sigsuspend(), et al which existed solely to save those registers
in advance. It also means I don't have to add new wrappers for ppoll()
and pselect(), which is what I was supposed to be doing when I got
distracted into this...
Finally, it unifies the ppc64 and ppc32 methods of handling syscall exit
directly into a signal handler (as required by sigsuspend et al) by
introducing a TIF_RESTOREALL flag which causes _all_ the registers to be
reloaded from the pt_regs by taking the ret_from_exception path, instead
of the normal syscall exit path which stomps on the callee-saved GPRs.
It appears to pass an LTP test run on ppc64, and passes basic testing on
ppc32 too. Brief tests of ptrace functionality with strace and gdb also
appear OK. I wouldn't send it to Linus for 2.6.15 just yet though :)
Signed-off-by: David Woodhouse <dwmw2@infradead.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Moved 83xx and QUICC Engine interrupt handling code into arch/powerpc
as a precursor of getting 83xx sub-arch building in arch/powerpc.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch merges, to some extent, the PPC32 and PPC64 kexec implementations.
We adopt the PPC32 approach of having ppc_md callbacks for the kexec functions.
The current PPC64 implementation becomes the "default" implementation for PPC64
which platforms can select if they need no special treatment.
I've added these default callbacks to pseries/maple/cell/powermac, this means
iSeries no longer supports kexec - but it never worked anyway.
I've renamed PPC32's machine_kexec_simple to default_machine_kexec, inline with
PPC64. Judging by the comments it might be better named machine_kexec_non_of,
or something, but at the moment it's the only implementation for PPC32 so it's
the "default".
Kexec requires machine_shutdown(), which is in machine_kexec.c on PPC32, but we
already have in setup-common.c on powerpc. All this does is call
ppc_md.nvram_sync, which only powermac implements, so instead make
machine_shutdown a ppc_md member and have it call core99_nvram_sync directly
on powermac.
I've also stuck relocate_kernel.S into misc_32.S for powerpc.
Built for ARCH=ppc, and 32 & 64 bit ARCH=powerpc, with KEXEC=y/n. Booted on
P5 LPAR and successfully kexec'ed.
Should apply on top of 493f25ef40.
Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Signed-off-by: Paul Mackerras <paulus@samba.org>
This patch removes the EXPORT_SYMBOL'ed but completely unused variable
ucSystemType and removes the unneeded EXPORT_SYMBOL(_prep_type).
Signed-off-by: Adrian Bunk <bunk@stusta.de>
Acked-by: Tom Rini <trini@kernel.crashing.org>
Signed-off-by: Paul Mackerras <paulus@samba.org>
Several counters already have the need to use 64 atomic variables on 64 bit
platforms (see mm_counter_t in sched.h). We have to do ugly ifdefs to fall
back to 32 bit atomic on 32 bit platforms.
The VM statistics patch that I am working on will also make more extensive
use of atomic64.
This patch introduces a new type atomic_long_t by providing definitions in
asm-generic/atomic.h that works similar to the c "long" type. Its 32 bits
on 32 bit platforms and 64 bits on 64 bit platforms.
Also cleans up the determination of the mm_counter_t in sched.h.
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Here is the patch to implement madvise(MADV_REMOVE) - which frees up a
given range of pages & its associated backing store. Current
implementation supports only shmfs/tmpfs and other filesystems return
-ENOSYS.
"Some app allocates large tmpfs files, then when some task quits and some
client disconnect, some memory can be released. However the only way to
release tmpfs-swap is to MADV_REMOVE". - Andrea Arcangeli
Databases want to use this feature to drop a section of their bufferpool
(shared memory segments) - without writing back to disk/swap space.
This feature is also useful for supporting hot-plug memory on UML.
Concerns raised by Andrew Morton:
- "We have no plan for holepunching! If we _do_ have such a plan (or
might in the future) then what would the API look like? I think
sys_holepunch(fd, start, len), so we should start out with that."
- Using madvise is very weird, because people will ask "why do I need to
mmap my file before I can stick a hole in it?"
- None of the other madvise operations call into the filesystem in this
manner. A broad question is: is this capability an MM operation or a
filesytem operation? truncate, for example, is a filesystem operation
which sometimes has MM side-effects. madvise is an mm operation and with
this patch, it gains FS side-effects, only they're really, really
significant ones."
Comments:
- Andrea suggested the fs operation too but then it's more efficient to
have it as a mm operation with fs side effects, because they don't
immediatly know fd and physical offset of the range. It's possible to
fixup in userland and to use the fs operation but it's more expensive,
the vmas are already in the kernel and we can use them.
Short term plan & Future Direction:
- We seem to need this interface only for shmfs/tmpfs files in the short
term. We have to add hooks into the filesystem for correctness and
completeness. This is what this patch does.
- In the future, plan is to support both fs and mmap apis also. This
also involves (other) filesystem specific functions to be implemented.
- Current patch doesn't support VM_NONLINEAR - which can be addressed in
the future.
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Andrea Arcangeli <andrea@suse.de>
Cc: Michael Kerrisk <mtk-manpages@gmx.net>
Cc: Ulrich Drepper <drepper@redhat.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Arnd Bergmann