The last thing we agreed on was to remove the macros entirely for 2.6.19,
on all architectures. Unfortunately, I think nobody actually _did_ that,
so they are still there.
[[email protected]: x86_64 fix]
Cc: David Woodhouse <[email protected]>
Cc: Greg Schafer <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
At least the ide driver calls pcibus_to_node, which is not
defined when CONFIG_PCI is disabled. This adds a nop function
for the !PCI case.
Signed-off-by: Arnd Bergmann <[email protected]>
It's currently not possible to build the default zImage
target if PS3 is the only selected platform. This is
a hack to fall back to building the pseries style
zImage, so the build is successful. This will probably
change in the future, if someone writes a PS3 specific
boot wrapper.
Signed-off-by: Arnd Bergmann <[email protected]>
A few code paths need to check whether or not they are running
on the PS3's LV1 hypervisor before making hcalls. This introduces
a new firmware feature bit for this, FW_FEATURE_PS3_LV1.
Now when both PS3 and IBM_CELL_BLADE are enabled, but not PSERIES,
FW_FEATURE_PS3_LV1 and FW_FEATURE_LPAR get enabled at compile time,
which is a bug. The same problem can also happen for (PPC_ISERIES &&
!PPC_PSERIES && PPC_SOMETHING_ELSE). In order to solve this, I
introduce a new CONFIG_PPC_NATIVE option that is set when at least
one platform is selected that can run without a hypervisor and then
turns the firmware feature check into a run-time option.
The new cell oprofile support that was recently merged does not
work on hypervisor based platforms like the PS3, therefore make
it depend on PPC_CELL_NATIVE instead of PPC_CELL. This may change
if we get oprofile support for PS3.
Signed-off-by: Arnd Bergmann <[email protected]>
It may be desireable to build a kernel for cell without
spufs, e.g. as the initial kboot kernel. This requires
that the SPU specific parts of the core dump and the xmon
code depend on CONFIG_SPU_BASE instead of CONFIG_PPC_CELL.
Signed-off-by: Arnd Bergmann <[email protected]>
Currently, we only send a sigtrap if the current task is being ptraced.
This is somewhat inconsistant, and it breaks utrace support in fedora.
Removing the check should do the right thing in all cases.
Cc: Ulrich Weigand <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
In the common cell kernel, I want to have ps3 enabled
to find potential bugs at compile-time.
Also enable SPU disassembly in xmon.
Signed-off-by: Arnd Bergmann <[email protected]>
Add symbol-exports for the new routines in arch/powerpc/platforms/cell/pmu.c.
They are needed for Oprofile, which can be built as a module.
Signed-off-by: Kevin Corry <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
When the user changes the runcontrol register, an SPU might be
running without a process being attached to it and waiting for
events. In order to prevent this, make sure we always disable
the priv1 master control when we're not inside of spu_run.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
When fixing spufs to map the 'mem' file backing store cacheable,
I incorrectly set the physical mapping to use both cache-inhibited
and guarded mapping, which resulted in a serious performance
degradation.
Debugged-by: Michael Ellerman <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
When we attempt an MFC DMA to an unmapped address, the event
returned from spu_run should be SPE_EVENT_SPE_DATA_STORAGE,
not SPE_EVENT_INVALID_DMA.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This moves the cell idle function to use the default cpu_idle
with a special power_save callback, like all other platforms
except iSeries already do.
It also makes it possible to disable this power_save function
with a new powerpc-specific boot option "powersave=off".
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This patch adds general support for isolated mode SPE apps.
Isolated apps are started indirectly, by a dedicated loader "kernel".
This patch starts the loader when spe_create is invoked with the
ISOLATE flag. We do this at spe_create time to allow libspe to pass the
isolated app in before calling spe_run.
The loader is read from the device tree, at the location
"/spu-isolation/loader". If the loader is not present, an attempt to
start an isolated SPE binary will fail with -ENODEV.
Update: loader needs to be correctly aligned - copy to a kmalloced buf.
Update: remove workaround for systemsim/spurom 'L-bit' bug, which has
been fixed.
Update: don't write to runcntl on spu_run_init: SPU is already running.
Update: do spu_setup_isolated earlier
Tested on systemsim.
Signed-off-by: Jeremy Kerr <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Currently, spufs_mbox_read transfers more bytes than requested on a
read. If you ask for four bytes, you get eight. This fixes it to
transfer the largest multiple of four bytes that is less than or equal
to the number you asked for.
Note: one nasty property of this file in spufs is that you can only
read multiples of four bytes in the first place, since there is no way
to atomically put back a few bytes into the hardware register. Thus,
reading less than four bytes returns -EINVAL. Asking for more than
four returns the largest possible multiple of four.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
When working on the mcs7830, I noticed the need for a mutex in its
mdio_read/mdio_write functions. A related problem seems to be present
in the asix driver in the respective functions.
This introduces a mutex in the common usbnet driver and uses it
from the two hardware specific drivers.
Acked-by: David Hollis <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
This adds generic support for the ethtool commands get_settings,
set_settings, get_link and nway_reset to usbnet. These are now
implemented using mii functions when a low-level driver supports
mdio_read/mdio_write and does not override the usbnet ethtool
commands with its own.
Currently, this applies to the asix and the mcs7830 drivers.
I have tested it on mcs7830.
Signed-off-by: Arnd Bergmann <[email protected]>
Acked-by: David Hollis <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
This driver adds support for the DeLOCK USB ethernet adapter
and potentially others based on the MosChip MCS7830 chip.
It is based on the usbnet and asix drivers as well as the
original device driver provided by MosChip, which in turn
was based on the usbnet driver.
It has been tested successfully on an OHCI, but interestingly
there seems to be a problem with the mcs7830 when connected to
the ICH6/EHCI in my thinkpad: it keeps receiving lots of
broken packets in the RX interrupt. The problem goes away when
I'm using an active USB hub, so I assume it's not related to
the device driver, but rather to the hardware.
Signed-off-by: David Brownell <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Greg Kroah-Hartman <[email protected]>
- Some long constants should be marked 'ul'.
- When using desc->handler_data to pass an __iomem
register area, we need to add casts to and from
__iomem.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This enables support for new firmware test releases.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This adds defaults for new configuration options added since
2.6.18 and it enables the option for 64kb pages by default.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This adds an 'object-id' file that the spe library can
use to store a pointer to its ELF object. This was
originally meant for use by oprofile, but is now
also used by the GNU debugger, if available.
In order for oprofile to find the location in an spu-elf
binary where an event counter triggered, we need a way
to identify the binary in the first place.
Unfortunately, that binary itself can be embedded in a
powerpc ELF binary. Since we can assume it is mapped into
the effective address space of the running process,
have that one write the pointer value into a new spufs
file.
When a context switch occurs, pass the user value to
the profiler so that can look at the mapped file (with
some care).
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The properties we used traditionally in the device tree are somewhat
nonstandard. This adds support for a more conventional format using
'interrupts' and 'reg' properties.
The interrupts are specified in three cells (class 0, 1 and 2) and
registered at the interrupt-parent.
The reg property contains either three or four register areas in the
order 'local-store', 'problem', 'priv2', and 'priv1', so the priv1 one
can be left out in case of hypervisor driven systems that access these
through hcalls.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Writing to cntl can be used to stop execution on the
spu and to restart it, reading from cntl gives the
contents of the current status register.
The access is always in ascii, as for most other files.
This was always meant to be there, but we had a little
problem with writing to runctl so it was left out so
far.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Any firmware that still uses the 'spc' nodes already
stopped running for other reasons, so let's get rid of this.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Since libspe2 will provide a function that can read/write
multiple mailbox elements at once, the kernel should handle
that efficiently.
read/write on the three mailbox files can now access the
spe context multiple times to operate on any number of
mailbox data elements.
If the spu application keeps writing to its outbound
mailbox, the read call will pick up all the data in a
single system call.
Unfortunately, if the user passes an invalid pointer,
we may lose a mailbox element on read, since we can't
put it back. This probably impossible to solve, if the
user also accesses the mailbox through direct register
access.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This hopefully fixes a long-standing bug in the spu file system.
An spu context comes with local memory that can be either saved
in kernel pages or point directly to a physical SPE.
When mapping the physical SPE, that mapping needs to be cache-inhibited.
For simplicity, we used to map the kernel backing memory that way
too, but unfortunately that was not only inefficient, but also incorrect
because the same page could then be accessed simultaneously through
a cacheable and a cache-inhibited mapping, which is not allowed
by the powerpc specification and in our case caused data inconsistency
for which we did a really ugly workaround in user space.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Add the concept of a gang to spufs as a new type of object.
So far, this has no impact whatsover on scheduling, but makes
it possible to add that later.
A new type of object in spufs is now a spu_gang. It is created
with the spu_create system call with the flags argument set
to SPU_CREATE_GANG (0x2). Inside of a spu_gang, it
is then possible to create spu_context objects, which until
now was only possible at the root of spufs.
There is a new member in struct spu_context pointing to
the spu_gang it belongs to, if any. The spu_gang maintains
a list of spu_context structures that are its children.
This information can then be used in the scheduler in the
future.
There is still a bug that needs to be resolved in this
basic infrastructure regarding the order in which objects
are removed. When the spu_gang file descriptor is closed
before the spu_context descriptors, we leak the dentry
and inode for the gang. Any ideas how to cleanly solve
this are appreciated.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This tries to fix spufs so we have an interface closer to what is
specified in the man page for events returned in the third argument of
spu_run.
Fortunately, libspe has never been using the returned contents of that
register, as they were the same as the return code of spu_run (duh!).
Unlike the specification that we never implemented correctly, we now
require a SPU_CREATE_EVENTS_ENABLED flag passed to spu_create, in
order to get the new behavior. When this flag is not passed, spu_run
will simply ignore the third argument now.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The SPU context save/restore code is currently built
for a 4k page size and we provide a _shipped version
of it since most people don't have the spu toolchain
that is needed to rebuild that code.
This patch hardcodes the data structures to a 64k
page alignment, which also guarantees 4k alignment
but unfortunately wastes 60k of memory per SPU
context that is created in the running system.
We will follow up on this with another patch to
reduce that overhead or maybe redo the context
save/restore logic to do this part entirely different,
but for now it should make experimental systems
work with either page size.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
At this time, all flags are invalid. Since we are
planning to actually add valid flags in the future,
we better check if any were passed by the user.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The save/restore sequence for SPE contexts currently attempts to save
and restore the channel count for SPE channel 1 (the SPU_WriteEventMask
channel. But the CBE architecture (section 9.11.2) clearly states
that this channel does not have an associated count. Hardware simply
ignores the attempt to write this count, but the simulator generates
a warning message.
WARNING: 279721590: SPE7: Attempt to write channel count for CH 1 with
no associated count is ignored.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The wbox channel count of an spu is now initialized
to four for the saved context. This makes it possible
to write to the mailbox right away without waiting
for the SPE to become scheduled first.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
For performance analysis, it is often interesting to know
which physical SPE a thread is currently running on, and,
more importantly, if it is running at all.
This patch adds a simple attribute to each SPU directory
with that information.
The attribute is read-only and called 'phys-id'. It contains
an ascii string with the number of the physical SPU (e.g.
"0x5"), or alternatively the string "0xffffffff" (32 bit -1)
when it is not running at all at the time that the file
is read.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
spufs currently knows only 4k pages and 16M hugetlb
pages. Make it use the regular methods for deciding on
the SLB bits.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
A recent change to the way that the mfc file gets mapped made it
impossible to map the SPE Multi-Source Synchronization register
into user space, but that may be needed by some applications.
This restores the missing functionality.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The spu_base module is rather deeply intermixed with the
core kernel, so it makes sense to have that built-in.
This will let us extend the base in the future without
having to export more core symbols just for it.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Enable some of the most requested features in defconfig
and refresh with the latest powerpc.git Kconfig files.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Checking the priority field to test for irq validity is
completely bogus and breaks with future external interrupt
controllers.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The IBM Cell blade firmware might confuse the kernel to think it's a
pSeries machine. This fixes it for now. With a bit of luck, the firmware
will be updated to avoid that in the future but currently that patch is
needed.
Signed-off-by: Benjamin Herrenschmidt <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
reflect the changes to Kconfig since the last update.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This patch disables and saves local interrupts during
hash_page processing for SPE contexts.
We have to do it explicitly in the spu_irq_class_1_bottom
function. For the interrupt handlers, we get the behaviour
implicitly by using SA_INTERRUPT to disable interrupts while
in the handler.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
All standard system calls should be declared in include/linux/syscalls.h.
Add some of the new additions that were previously missed.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This is now required to avoid
drivers/net/spider_net.c:844: error: 'IPPROTO_TCP' undeclared
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Jeff Garzik <[email protected]>
The driver incorrectly used dma_addr_t to describe
HW structures and consequently broke when that type
was changed in 2.6.15-rc.
This changed spidernet to use u32 for 32 bit HW defined
structure elements.
From: Jens Osterkamp <[email protected]>
Signed-off-by: Jens Osterkamp <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Jeff Garzik <[email protected]>
request_firmware() is sometimes problematic, especially
in initramfs, reading the firmware from Open Firmware
is much preferrable.
We still try to get the firmware from the file system
first, in order to support old SLOF releases and to allow
updates of the spidernet firmware without reflashing
the system.
From: Jens Osterkamp <[email protected]>
Signed-off-by: Jens Osterkamp <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Jeff Garzik <[email protected]>
Uploading the device firmware may fail if wrong input data
was provided by the user. This checks for the condition.
From: Jens Osterkamp <[email protected]>
Signed-off-by: Jens Osterkamp <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Jeff Garzik <[email protected]>
These symbols are only used in the file that they are defined in,
so they should not be in the global namespace.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
These symbols are only used in the file that they are defined in,
so they should not be in the global namespace.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
pmac_setup_arch is only used in the file that it is defined in,
so it should not be in the global namespace.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
These symbols are only used in the file that they are defined in,
so they should not be in the global namespace.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This moves the 32 bit ioctl compatibility handlers for
Video4Linux into a new file and adds explicit calls to them
to each v4l device driver.
Unfortunately, there does not seem to be any code handling
the v4l2 ioctls, so quite often the code goes through two
separate conversions, first from 32 bit v4l to 64 bit v4l,
and from there to 64 bit v4l2. My patch does not change
that, so there is still much room for improvement.
Also, some drivers have additional ioctl numbers, for
which the conversion should be handled internally to
that driver.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Mauro Carvalho Chehab <[email protected]>
For far, all SPU triggered interrupts always end up on
the first SMT thread, which is a bad solution.
This patch implements setting the affinity to the
CPU that was running last when entering execution on
an SPU. This should result in a significant reduction
in IPI calls and better cache locality for SPE thread
specific data.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The size of the local store is architecture defined
and independent from the page size, so it should
not be defined in terms of pages in the first place.
This mistake broke a few places when building for
64kb pages.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
One local variable is missing an __iomem modifier,
in another place, we pass a completely unused argument
with a missing __user modifier.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
In a hypervisor based setup, direct access to the first
priviledged register space can typically not be allowed
to the kernel and has to be implemented through hypervisor
calls.
As suggested by Masato Noguchi, let's abstract the register
access trough a number of function calls. Since there is
currently no public specification of actual hypervisor
calls to implement this, I only provide a place that
makes it easier to hook into.
Cc: Masato Noguchi <[email protected]>
Cc: Geoff Levand <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The logic for sys_spu_run keeps growing and it does
not really belong into file.c any more since we
moved away from using regular file operations to our
own syscall.
No functional change in here.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
checking bits manually might not be synchonized with
the use of set_bit/clear_bit. Make sure we always use
the correct bitops by removing the unnecessary
identifiers.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
If creating one entry failed in spufs_fill_dir,
we never cleaned up the freshly created entries.
Fix this by calling the cleanup function on error.
Noticed by Al Viro.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
If get_unused_fd failed in sys_spu_create, we never cleaned
up the created directory. Fix that by restructuring the
error path.
Noticed by Al Viro.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
When spu_activate fails in spu_acquire_runnable, the
state must still be SPU_STATE_SAVED, we were
incorrectly setting it to SPU_STATE_RUNNABLE.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
During an earlier cleanup, we lost the serialization
of multiple spu_run calls performed on the same
spu_context. In order to get this back, introduce a
mutex in the spu_context that is held inside of spu_run.
Noticed by Al Viro.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Only checking for SPUFS_MAGIC is not reliable, because
it might not be unique in theory. Worse than that,
we accidentally allow spu_run to be performed on
any file in spufs, not just those returned from
spu_create as intended.
Noticed by Al Viro.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
spu_forget will do mmput on the DMA address space,
which can lead to lots of other stuff getting triggered.
We better not hold a semaphore here that we might
need in the process.
Noticed by Al Viro.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
We need to check for validity of owner under down_write,
down_read is not enough.
Noticed by Al Viro.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
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 <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Building the arch/powerpc tree currently gives me
two warnings with gcc-4.0:
arch/powerpc/mm/imalloc.c: In function '__im_get_area':
arch/powerpc/mm/imalloc.c:225: warning: 'tmp' may be used uninitialized in this function
arch/powerpc/mm/hugetlbpage.c: In function 'hugetlb_get_unmapped_area':
arch/powerpc/mm/hugetlbpage.c:608: warning: unused variable 'vma'
both fixes are trivial.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
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 <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
/dev/nvram uses the user-provided read/write size
for kmalloc, which fails, if a large number is passed.
This will always use a single page at most, which
can be expected to succeed.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Output from hexdump with "%08x" depends on HOST platform's endian.
When building linux by cross toolchain, that difference makes errors.
Signed-off-by: Masato Noguchi <[email protected]>
Signed-off-by: Geoff Levand <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
One of my last patches contained a broken line
from splitting out some other changes, this
restores a working version.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
One of the two users of spufs_calls.owner still has a race
when calling try_module_get while the module is removed.
This makes it use the correct instance of owner.
Noticed by Milton Miller.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
I can't really get a conclusive answer from the firmware
people what to check for, so I just try scanning for
anything that starts with "IBM,CPB", which should be
correct for all hardware produced so far and for
systemsim.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Handling mailbox interrupts was broken in multiple respects,
the combination of which was hiding the bugs most of the time.
- The ibox interrupt mask was open initially even though there
are no waiters on a newly created SPU.
- Acknowledging the mailbox interrupt did not work because
it is level triggered and the mailbox data is never retrieved
from inside the interrupt handler.
- The interrupt handler delivered interrupts with a disabled
mask if another interrupt is triggered for the same class
but a different mask.
- The poll function did not enable the interrupt if it had not
been enabled, so we might run into the poll timeout if none of
the other bugs saved us and no signal was delivered.
We probably still have a similar problem with blocking
read/write on mailbox files, but that will result in extra
wakeup in the worst case, not in incorrect behaviour.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
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 <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
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 <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
spufs is rather noisy when debugging is enabled, this
turns off the messages for production use.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
try_module_get returns true when NULL arguments, so
we first need to check if there is a module loaded before
getting the reference count.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
With the new rules for reserved pages, the spufs now
needs working page reference counting.
I should probably look into converting to vm_insert_page,
but for now this patch makes spufs work again.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This changes all exported symbols of spufs to EXPORT_SYMBOL_GPL.
The spu_ibox_read/spu_wbox_write symbols are not exported
any more when the scheduler patch is applied.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
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 <[email protected]>,
Uli Weigand <[email protected]>
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
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 <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
The frame buffer layer already had some code dealing with compat ioctls, this
patch moves over the remaining code from fs/compat_ioctl.c
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Antonino Daplas <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
This fixes a severe bug in the bpa_iic driver that caused
all sorts of problems.
We had been using incorrect priority values for inter processor
interrupts, which resulted in always doing CALL_FUNCTION
instead of RESCHEDULE or DEBUGGER_BREAK.
The symptoms cured by this patch include bad performance on
SMP systems spurious kernel panics in the IPI code.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This adds a bpa_defconfig file and make target. The config settings
are made for the current version of the Cell Processor Based Blade,
so there are not too many drivers enabled. A few more drivers might
get added in the future though.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
xtensa is now in -rc1, with the obsolete syscalls still in there, so I
guess this about the last chance to correct the ABI. Applying the patch
obviously breaks all sorts of user space binaries and probably also
requires the appropriate changes to be made to libc.
On the other hand, if a decision is made to keep the broken interface, it
should at least be a conscious one instead of an oversight.
Signed-off-by: Arnd Bergmann <[email protected]>
Cc: Chris Zankel <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Convert nvram_create_os_partition to use list_for_each_entry
instead of list_for_each, as this reduces the code size by
two lines.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
This patch allows block device drivers to convert their ioctl functions to
unlocked_ioctl() like character devices and other subsystems. All
functions that were called with the BKL held before are still used that
way, but I would not be surprised if it could be removed from the ioctl
functions in drivers/block/ioctl.c themselves.
As a side note, I found that compat_blkdev_ioctl() acquires the BKL as
well, which looks like a bug. I have checked that every user of
disk->fops->compat_ioctl() in the current git tree gets the BKL itself, so
it could easily be removed from compat_blkdev_ioctl().
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>
Implementation of software load support for the BE iommu. This is very
different from other iommu code on ppc64, since we only do a static mapping.
The mapping is currently hardcoded but should really be read from the
firmware, but they don't set up the device nodes yet. There is a single
512MB DMA window for PCI, USB and ethernet at 0x20000000 for our RAM.
The Cell processor can put the I/O page table either in memory like
the hashed page table (hardware load) or have the operating system
write the entries into memory mapped CPU registers (software load).
I use the software load mechanism because I know that all I/O page
table entries for the amount of installed physical memory fit into
the IO TLB cache. At the point when we get machines with more than
4GB of installed memory, we can either use hardware I/O page table
access like the other platforms do or dynamically update the I/O
TLB entries when a page fault occurs in the I/O subsystem.
The software load can then use the macros that I have implemented
for the static mapping in order to do the TLB cache updates.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Add support for the integrated interrupt controller on BPA
CPUs. There is one of those for each SMT thread.
The mapping of interrupt numbers to HW interrupt sources
is described in arch/ppc64/kernel/bpa_iic.h.
This version hardcodes the 'Spider' chip as the secondary
interrupt controller. That is not really generic for the
architecture, but at the moment it is the only secondary
PIC that exists.
A little more work will be needed on this as soon as
we have boards with multiple external interrupt controllers.
Signed-off-by: Arnd Bergmann <[email protected]>
Signed-off-by: Paul Mackerras <[email protected]>
Arnd Bergmann