We support 16TB of user address space and half a million contexts
so update the comment to reflect this.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Commit d57af9b (taskstats: use real microsecond granularity for CPU times)
renamed msecs_to_cputime to usecs_to_cputime, but failed to update all
numbers on the way. This causes nonsensical cpu idle/iowait values to be
displayed in /proc/stat (the only user of usecs_to_cputime so far).
This also renames __cputime_msec_factor to __cputime_usec_factor, adapting
its value and using it directly in cputime_to_usecs instead of doing two
multiplications.
Signed-off-by: Andreas Schwab <schwab@linux-m68k.org>
Acked-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
read_n_cells() cannot be marked as .devinit.text since it is referenced
from two functions that are not in that section: of_get_lmb_size() and
hot_add_drconf_scn_to_nid().
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
mark_reserved_regions_for_nid() is only called from do_init_bootmem(),
which is in .init.text, so it must be in the same section to avoid a
section mismatch warning.
Reported-by: Subrata Modak <subrata@linux.vnet.ibm.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
PPC64 uses long long for u64 in the kernel, but powerpc's asm/types.h
prevents 64-bit userland from seeing this definition, instead defaulting
to u64 == long in userspace. Some user programs (e.g. kvmtool) may actually
want LL64, so this patch adds a check for __SANE_USERSPACE_TYPES__ so that,
if defined, int-ll64.h is included instead.
Signed-off-by: Matt Evans <matt@ozlabs.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Implement a POWER7 optimised copy_to_user/copy_from_user using VMX.
For large aligned copies this new loop is over 10% faster, and for
large unaligned copies it is over 200% faster.
If we take a fault we fall back to the old version, this keeps
things relatively simple and easy to verify.
On POWER7 unaligned stores rarely slow down - they only flush when
a store crosses a 4KB page boundary. Furthermore this flush is
handled completely in hardware and should be 20-30 cycles.
Unaligned loads on the other hand flush much more often - whenever
crossing a 128 byte cache line, or a 32 byte sector if either sector
is an L1 miss.
Considering this information we really want to get the loads aligned
and not worry about the alignment of the stores. Microbenchmarks
confirm that this approach is much faster than the current unaligned
copy loop that uses shifts and rotates to ensure both loads and
stores are aligned.
We also want to try and do the stores in cacheline aligned, cacheline
sized chunks. If the store queue is unable to merge an entire
cacheline of stores then the L2 cache will have to do a
read/modify/write. Even worse, we will serialise this with the stores
in the next iteration of the copy loop since both iterations hit
the same cacheline.
Based on this, the new loop does the following things:
1 - 127 bytes
Get the source 8 byte aligned and use 8 byte loads and stores. Pretty
boring and similar to how the current loop works.
128 - 4095 bytes
Get the source 8 byte aligned and use 8 byte loads and stores,
1 cacheline at a time. We aren't doing the stores in cacheline
aligned chunks so we will potentially serialise once per cacheline.
Even so it is much better than the loop we have today.
4096 - bytes
If both source and destination have the same alignment get them both
16 byte aligned, then get the destination cacheline aligned. Do
cacheline sized loads and stores using VMX.
If source and destination do not have the same alignment, we get the
destination cacheline aligned, and use permute to do aligned loads.
In both cases the VMX loop should be optimal - we always do aligned
loads and stores and are always doing stores in cacheline aligned,
cacheline sized chunks.
To be able to use VMX we must be careful about interrupts and
sleeping. We don't use the VMX loop when in an interrupt (which should
be rare anyway) and we wrap the VMX loop in disable/enable_pagefault
and fall back to the existing copy_tofrom_user loop if we do need to
sleep.
The VMX breakpoint of 4096 bytes was chosen using this microbenchmark:
http://ozlabs.org/~anton/junkcode/copy_to_user.c
Since we are using VMX and there is a cost to saving and restoring
the user VMX state there are two broad cases we need to benchmark:
- Best case - userspace never uses VMX
- Worst case - userspace always uses VMX
In reality a userspace process will sit somewhere between these two
extremes. Since we need to test both aligned and unaligned copies we
end up with 4 combinations. The point at which the VMX loop begins to
win is:
0% VMX
aligned 2048 bytes
unaligned 2048 bytes
100% VMX
aligned 16384 bytes
unaligned 8192 bytes
Considering this is a microbenchmark, the data is hot in cache and
the VMX loop has better store queue merging properties we set the
breakpoint to 4096 bytes, a little below the unaligned breakpoints.
Some future optimisations we can look at:
- Looking at the perf data, a significant part of the cost when a
task is always using VMX is the extra exception we take to restore
the VMX state. As such we should do something similar to the x86
optimisation that restores FPU state for heavy users. ie:
/*
* If the task has used fpu the last 5 timeslices, just do a full
* restore of the math state immediately to avoid the trap; the
* chances of needing FPU soon are obviously high now
*/
preload_fpu = tsk_used_math(next_p) && next_p->fpu_counter > 5;
and
/*
* fpu_counter contains the number of consecutive context switches
* that the FPU is used. If this is over a threshold, the lazy fpu
* saving becomes unlazy to save the trap. This is an unsigned char
* so that after 256 times the counter wraps and the behavior turns
* lazy again; this to deal with bursty apps that only use FPU for
* a short time
*/
- We could create a paca bit to mirror the VMX enabled MSR bit and check
that first, avoiding multiple calls to calling enable_kernel_altivec.
That should help with iovec based system calls like readv.
- We could have two VMX breakpoints, one for when we know the user VMX
state is loaded into the registers and one when it isn't. This could
be a second bit in the paca so we can calculate the break points quickly.
- One suggestion from Ben was to save and restore the VSX registers
we use inline instead of using enable_kernel_altivec.
[BenH: Fixed a problem with preempt and fixed build without CONFIG_ALTIVEC]
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This reverts commit 4dff523a91.
It was reported that this patch cause issues when trying to connect to
legacy devices so reverting it.
Reported-by: David Fries <david@fries.net>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
When the last RFCOMM data channel is closed, a timer is normally set
up to disconnect the control channel at a later time. If the control
channel disconnect command is sent with the timer pending, the timer
needs to be cancelled.
If the timer is not cancelled in this situation, the reference
counting logic for the RFCOMM session does not work correctly when the
remote device closes the L2CAP connection. The session is freed at
the wrong time, leading to a kernel panic.
Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
When configuring an ERTM or streaming mode connection, remote devices
are expected to send an RFC option in a successful config response. A
misbehaving remote device might not send an RFC option, and the L2CAP
code should not access uninitialized data in this case.
Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Incoming sk_buffs always have bt_cb(skb)->force_active set to 0, so
it's misleading to use that value from the control block when calling
hci_conn_enter_active_mode() for incoming data. The destination socket
is not known in the HCI layer, so the force_active setting for each
socket isn't known either. Hard-coding the force_active parameter does
not change any behavior, but makes it obvious that incoming ACL data
never exits sniff mode.
Signed-off-by: Mat Martineau <mathewm@codeaurora.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Simplify function and remove fourth level of indentation.
Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Implement block size read function. Use different variables for
packet-based and block-based flow control.
Signed-off-by: Andrei Emeltchenko <andrei.emeltchenko@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
When getting a cmd irq during an ongoing data transfer
with dma, the dma job were never terminated. This is now
corrected.
Cc: <stable@vger.kernel.org>
Tested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Per Forlin <per.forlin@stericsson.com>
Signed-off-by: Ulf Hansson <ulf.hansson@stericsson.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The interrupt was previously enabled and then correctly cleared.
Now we also handle it correctly.
Cc: <stable@vger.kernel.org>
Tested-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Ulf Hansson <ulf.hansson@stericsson.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
The overlapping iotable mapping entries for the ux500 Cortex
A9 SCU, CPU control and TWD are no longer accepted by the
kernel. Remove the overlaps so the machine boots again.
Cc: Srinidhi Kasagar <srinidhi.kasagar@stericsson.com>
Cc: Rabin Vincent <rabin.vincent@stericsson.com>
Reported-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@stericsson.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
sched_clock() is yet another blocker on the road to the single
image. This patch implements an idea by Russell King:
http://www.spinics.net/lists/linux-omap/msg49561.html
Instead of asking the platform to implement both sched_clock()
itself and the rollover callback, simply register a read()
function, and let the ARM code care about sched_clock() itself,
the conversion to ns and the rollover. sched_clock() uses
this read() function as an indirection to the platform code.
If the platform doesn't provide a read(), the code falls back
to the jiffy counter (just like the default sched_clock).
This allow some simplifications and possibly some footprint gain
when multiple platforms are compiled in. Among the drawbacks,
the removal of the *_fixed_sched_clock optimization which could
negatively impact some platforms (sa1100, tegra, versatile
and omap).
Tested on 11MPCore, OMAP4 and Tegra.
Cc: Imre Kaloz <kaloz@openwrt.org>
Cc: Eric Miao <eric.y.miao@gmail.com>
Cc: Colin Cross <ccross@android.com>
Cc: Erik Gilling <konkers@android.com>
Cc: Olof Johansson <olof@lixom.net>
Cc: Sascha Hauer <kernel@pengutronix.de>
Cc: Alessandro Rubini <rubini@unipv.it>
Cc: STEricsson <STEricsson_nomadik_linux@list.st.com>
Cc: Lennert Buytenhek <kernel@wantstofly.org>
Cc: Ben Dooks <ben-linux@fluff.org>
Tested-by: Jamie Iles <jamie@jamieiles.com>
Tested-by: Tony Lindgren <tony@atomide.com>
Tested-by: Kyungmin Park <kyungmin.park@samsung.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Nicolas Pitre <nico@linaro.org>
Acked-by: Krzysztof Halasa <khc@pm.waw.pl>
Acked-by: Kukjin Kim <kgene.kim@samsung.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
* git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi-rc-fixes-2.6: (22 commits)
[SCSI] fcoe: fix fcoe in a DCB environment by adding DCB notifiers to set skb priority
[SCSI] bnx2i: Fixed kernel panic caused by unprotected task->sc->request deref
[SCSI] qla4xxx: check for failed conn setup
[SCSI] qla4xxx: a small loop fix
[SCSI] qla4xxx: fix flash/ddb support
[SCSI] zfcp: return early from slave_destroy if slave_alloc returned early
[SCSI] fcoe: Fix preempt count leak in fcoe_filter_frames()
[SCSI] qla2xxx: Update version number to 8.03.07.12-k.
[SCSI] qla2xxx: Submit all chained IOCBs for passthrough commands on request queue 0.
[SCSI] qla2xxx: Correct fc_host port_state display.
[SCSI] qla2xxx: Disable generating pause frames when firmware hang detected for ISP82xx.
[SCSI] qla2xxx: Clear mailbox busy flag during premature mailbox completion for ISP82xx.
[SCSI] qla2xxx: Encapsulate prematurely completing mailbox commands during ISP82xx firmware hang.
[SCSI] qla2xxx: Display IPE error message for ISP82xx.
[SCSI] qla2xxx: Return the correct value for a mailbox command if 82xx is in reset recovery.
[SCSI] qla2xxx: Enable Minidump by default with default capture mask 0x1f.
[SCSI] qla2xxx: Stop unconditional completion of mailbox commands issued in interrupt mode during firmware hang.
[SCSI] qla2xxx: Revert back the request queue mapping to request queue 0.
[SCSI] qla2xxx: Don't call alloc_fw_dump for ISP82XX.
[SCSI] qla2xxx: Check for SCSI status on underruns.
...
* 'for-linus/i2c-32-rc6' of git://git.fluff.org/bjdooks/linux:
i2c-eg20t: correct the driver init order of pch_i2c_probe()
I2C: OMAP: fix FIFO usage for OMAP4
i2c-s3c2410: Fix return code of s3c24xx_i2c_parse_dt_gpio
i2c: i2c-s3c2410: Add a cpu_relax() to busy wait for bus idle
I noticed that hotplug of one setup does not work with recent change in
pci tree.
After checking the bridge conf setup, I noticed that the bridges get
assigned but do not get enabled.
The reason is the following commit, while simply ignores bridge
resources when enabling a pci device:
| commit bbef98ab0f
| Author: Ram Pai <linuxram@us.ibm.com>
| Date: Sun Nov 6 10:33:10 2011 +0800
|
| PCI: defer enablement of SRIOV BARS
|...
| NOTE: Note, there is subtle change in the pci_enable_device() API. Any
| driver that depends on SRIOV BARS to be enabled in pci_enable_device()
| can fail.
Put back bridge resource and ROM resource checking to fix the problem.
That should fix regression like BIOS does not assign correct resource to
bridge.
Discussion can be found at:
http://www.spinics.net/lists/linux-pci/msg12874.html
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Acked-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 5c48b108 ("um: take arch/um/sys-x86 to arch/x86/um") broke the
make target update-po-config, as its symlink trick (again) fails.
(Previous breakage was fixed with commit bdc69ca4 ("kconfig: change
update-po-config to reflect new layout of arch/um").)
The new UML layout allows to drop the symlick trick entirely. And if,
one day, another architecture supports UML too, that should now work
without again breaking this make target.
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Signed-off-by: Michal Marek <mmarek@suse.cz>
This patch fixes user_confirm_neg_reply to use the appropriate struct
for accessing the call parameters.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
This patch updates the ordering and opcodes of mgmt messages to match
the latest API specification.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
We do not want the service cache to be enabled indefinitely after
mgmt_read_info is called. To solve this a timer is added which will
automatically disable the cache if mgmt_set_dev_class isn't called
within 5 seconds of calling mgmt_read_info.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Due to the upcoming addition of a service cache timer the functions to
update the EIR and CoD need to be higher up in mgmt.c in order to avoid
unnecessary forward-declarations. This patch simply moves code around
without any other changes in order to make subsequent patches more
readable.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Instead of having an explicit service cache command we can make the mgmt
API simpler by implicitly enabling the cache when mgmt_read_info is
called for the first time and disabling it when mgmt_set_dev_class is
called.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Fast connectable is logically after the connectable property so that's
where it should show up in the code as well (it's also after connectable
in the settings bitfield).
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
This patch updates the mgmt_read_info and related messages to the latest
management API which uses a bitfield of settings instead of individual
boolean values.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
hdev->workqueue should be only for rx/tx, so move this one out.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
As we run in process context now we don't need worqueue to add e del from
sysfs.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Update hdev workqueue API usage to use the new interface, this new
interface also allow us to mark this workqueue as WQ_HIGHPRI, so now rx
and tx work gets higher priority when running.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
hdev->workqueue will be only for for rx/tx/cmd processing, all other small
works should go to the system workqueue for now.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
This list has much more reads than writes, so RCU makes senses here, also
it avoid deadlock against the socket lock.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
This move some checking code that was in l2cap_sock_connect() to
l2cap_chan_connect(). Thus we can invert the lock calls, i.e., call
lock_sock() before hci_dev_lock() to avoid a deadlock scenario.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Another step of remove interrupt context from Bluetooth Core.
Use the system workqueue.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
This should simplify Bluetooth core processing a lot.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
As part of the moving on all the Bluetooth processing to Process context.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
It's pointless, we aren't protecting anything since btusb_notify()
schedules a work to run, then all it operation happens without protection.
If protection is really needed here, we will fix it further.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Handling hci_conn_hash with RCU make us avoid some locking and disable
tasklets.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Instead of using tasklet_disable() to prevent acess to the channel use, we
can use RCU and improve the performance of our code.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
spin lock doesn't fit ok anymore on the new code based on workqueues.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Now we can sleep in any path inside Bluetooth core, so mutex can make
sense here.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
We run everything in the same lock now. The backlog queue is useless now
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
We now run everything in process context, so the mutex lock is the best
option. But in some places we still need the bh_lock_sock()
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
L2CAP timers also need to run in process context. As the works in l2cap
are small we are using the system worqueue.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
It doesn't really touch any sensitive information about hdev. So no need
to lock here.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
As HCI rx path is now done in process context it makes sense to do all the
timer in process context as well.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Bluetooth rx task runs now in a workqueue, so it a good approach run any
timer that share locking with process context code also in a workqueue.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Now we run everything in HCI in process context, so it's a better idea use
mutex instead spin_lock. The macro remains hci_dev_lock() (and I got rid
of hci_dev_lock_bh()), of course.
Acked-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
Run recv process in workqueue helps a lot with our processing as the recv
path will also be in the process context, i.e., now all our tx and rx are
in process context.
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Gustavo F. Padovan <padovan@profusion.mobi>
