Use clocksource_register_hz which calculates the shift/mult
factors for us. Also remove the shift = 22 assumption in
vsyscall_update - thanks to Paul Mackerras and John Stultz for
catching that.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We can use clockevents_calc_mult_shift instead of doing all
the work ourselves.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When re-enabling interrupts we have code to handle edge sensitive
decrementers by resetting the decrementer to 1 whenever it is negative.
If interrupts were disabled long enough that the decrementer wrapped to
positive we do nothing. This means interrupts can be delayed for a long
time until it finally goes negative again.
While we hope interrupts are never be disabled long enough for the
decrementer to go positive, we have a very good test team that can
drive any kernel into the ground. The softlockup data we get back
from these fails could be seconds in the future, completely missing
the cause of the lockup.
We already keep track of the timebase of the next event so use that
to work out if we should trigger a decrementer exception.
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: stable@kernel.org
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This reverts commit a15bd354f0.
It exceeded the padding on the SREGS struct, rendering the ABI
backwards-incompatible.
Conflicts:
arch/powerpc/kvm/powerpc.c
include/linux/kvm.h
Signed-off-by: Avi Kivity <avi@redhat.com>
On PPC64, put_sigset_t converts a sigset_t to a compat_sigset_t
before copying it to userspace. There is a typo in the case that
we have 4 words to copy, meaning that we corrupt the compat_sigset_t.
It appears that _NSIG_WORDS can't be greater than 2 at the moment
so this code is probably always optimised away anyway.
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The Documentation/memory-barriers.txt document requires that atomic
operations that return a value act as a memory barrier both before
and after the actual atomic operation.
Our current implementation doesn't guarantee this. More specifically,
while a load following the isync can not be issued before stwcx. has
completed, that completion doesn't architecturally means that the
result of stwcx. is visible to other processors (or any previous stores
for that matter) (typically, the other processors L1 caches can still
hold the old value).
This has caused an actual crash in RCU torture testing on Power 7
This fixes it by changing those atomic ops to use new macros instead
of RELEASE/ACQUIRE barriers, called ATOMIC_ENTRY and ATMOIC_EXIT barriers,
which are then defined respectively to lwsync and sync.
I haven't had a chance to measure the performance impact (or rather
what I measured with kernel compiles is in the noise, I yet have to
find a more precise benchmark)
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Recent binutils refuses to assemble AltiVec opcodes when in e500/SPE
mode, as some of those opcodes alias the "SPE" instructions. This
triggers an ancient binutils version check even when building a kernel
with CONFIG_ALTIVEC disabled.
In theory, the check could be conditionalized on CONFIG_ALTIVEC, but in
practice it has long outlived its utility. It is virtually impossible
to find binutils older than 2.12.1 (released 2002) in the wild anymore.
Even ancient RedHat Enterprise Linux 4 has binutils-2.14.
To fix the kernel build when done natively on e500 systems with this new
binutils, the test is simply removed.
Signed-off-by: Kyle Moffett <Kyle.D.Moffett@boeing.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
With the introduction of CONFIG_PPC_ADV_DEBUG_REGS user space debug is
broken on Book-E 64-bit parts that support delayed debug events. When
switch_booke_debug_regs() sets DBCR0 we'll start getting debug events as
MSR_DE is also set and we aren't able to handle debug events from kernel
space.
We can remove the hack that always enables MSR_DE and loads up DBCR0 and
just utilize switch_booke_debug_regs() to get user space debug working
again.
We still need to handle critical/debug exception stacks & proper
save/restore of state for those exception levles to support debug events
from kernel space like we have on 32-bit.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
All of DebugException is already protected by CONFIG_PPC_ADV_DEBUG_REGS
there is no need to have another such ifdef inside the function.
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We had an existing ifdef for 4xx & BOOKE processors that got changed to
CONFIG_PPC_ADV_DEBUG_REGS. The define has nothing to do with
CONFIG_PPC_ADV_DEBUG_REGS. The define really should be:
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
and not
#ifdef CONFIG_PPC_ADV_DEBUG_REGS
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Move the PS3 IPI message setup from ps3_smp_setup_cpu() to ps3_smp_probe().
Fixes startup warnings like these:
------------[ cut here ]------------
WARNING: at kernel/lockdep.c:2649
Modules linked in:
...
---[ end trace 31fd0ba7d8756001 ]---
Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Fixes the PS3 bootup hang introduced in 3.0-rc1 by:
commit 317f394160
sched: Move the second half of ttwu() to the remote cpu
Move the PS3's LV1 EOI call lv1_end_of_interrupt_ext() from ps3_chip_eoi()
to ps3_get_irq() for IPI messages.
If lv1_send_event_locally() is called between a previous call to
lv1_send_event_locally() and the coresponding call to
lv1_end_of_interrupt_ext() the second event will not be delivered to the
target cpu.
The PS3's SMP IPIs are implemented using lv1_send_event_locally(), so if two
IPI messages of the same type are sent to the same target in a relatively
short period of time the second IPI event can become lost when
lv1_end_of_interrupt_ext() is called from ps3_chip_eoi().
CC: stable@kernel.org
Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
If you build with KVM and UP it fails with the following due to a
missing include.
/arch/powerpc/kvm/book3s_hv.c: In function 'do_h_register_vpa':
arch/powerpc/kvm/book3s_hv.c:156:10: error: 'H_PARAMETER' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:156:10: note: each undeclared identifier is reported only once for each function it appears in
arch/powerpc/kvm/book3s_hv.c:192:12: error: 'H_RESOURCE' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:222:9: error: 'H_SUCCESS' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c: In function 'kvmppc_pseries_do_hcall':
arch/powerpc/kvm/book3s_hv.c:228:30: error: 'H_SUCCESS' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:232:7: error: 'H_CEDE' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:234:7: error: 'H_PROD' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:238:10: error: 'H_PARAMETER' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:250:7: error: 'H_CONFER' undeclared (first use in this function)
arch/powerpc/kvm/book3s_hv.c:252:7: error: 'H_REGISTER_VPA' undeclared (first use in this function)
make[2]: *** [arch/powerpc/kvm/book3s_hv.o] Error 1
Signed-off-by: Michael Neuling <mikey@neuling.org>
cc: stable@kernel.org (3.1 only)
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
kdump fails because we try to execute an HV only instruction. Feature
fixups are being applied after we copy the exception vectors down to 0
so they miss out on any updates.
We have always had this issue but it only became critical in v3.0
when we added CFAR support (breaks POWER5) and v3.1 when we added
POWERNV (breaks everyone).
Signed-off-by: Anton Blanchard <anton@samba.org>
Cc: <stable@kernel.org> [v3.0+]
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
I had to debug a strange situation where all manner of things were
failing. SMT threads, storage and network were all completely broken.
The root cause was we couldn't find enough memory to instantiate RTAS -
this was a network install so the initrd was huge.
Instead of limping along and failing in mysterious ways we should just
panic up front if RTAS exists and we can't allocate space for it.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Kexec is not supported on 47x. 47x is a variant of 44x with slightly
different MMU and SMP support. There was a typo in the config dependency
for kexec. This patch fixes the same.
Signed-off-by: Suzuki K. Poulose <suzuki@in.ibm.com>
Signed-off-by: Paul Bolle <pebolle@tiscali.nl>
Cc: Kumar Gala <galak@kernel.crashing.org>
Cc: Josh Boyer <jwboyer@gmail.com>
Cc: linux ppc dev <linuxppc-dev@lists.ozlabs.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Should do what other architectures do and wrap all that code into
the appropriate ifdef
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The "#include <linux/module.h>" was replaced by "#include <linux/export.h>"
in the patch "powerpc: various straight conversions from module.h --> export.h".
This will cause the following compile problem:
arch/powerpc/sysdev/fsl_rio.c: In function 'fsl_rio_mcheck_exception':
arch/powerpc/sysdev/fsl_rio.c:296: error: implicit declaration of function 'search_exception_tables'.
The file fsl_rio.c needs the declaration of function "search_exception_tables"
in the header file "linux/module.h".
Signed-off-by: Liu Gang <Gang.Liu@freescale.com>
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
When running with HV KVM and CBE config options enabled, I get
build failures like the following:
arch/powerpc/kernel/head_64.o: In function `cbe_system_error_hv':
(.text+0x1228): undefined reference to `do_kvm_0x1202'
arch/powerpc/kernel/head_64.o: In function `cbe_maintenance_hv':
(.text+0x1628): undefined reference to `do_kvm_0x1602'
arch/powerpc/kernel/head_64.o: In function `cbe_thermal_hv':
(.text+0x1828): undefined reference to `do_kvm_0x1802'
This is because we jump to a KVM handler when HV is enabled, but we
only generate the handler with PR KVM mode.
Signed-off-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The lv1_gpu_attribute hcall takes three, not five input
arguments. Adjust the lv1 hcall table and all calls.
Signed-off-by: Geoff Levand <geoff@infradead.org>
CC: Takashi Iwai <tiwai@suse.de>
Acked-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Since commit [e58aa3d2: genirq: Run irq handlers with interrupts disabled],
We run all interrupt handlers with interrupts disabled
and we even check and yell when an interrupt handler
returns with interrupts enabled (see commit [b738a50a:
genirq: Warn when handler enables interrupts]).
So now this flag is a NOOP and can be removed.
Signed-off-by: Yong Zhang <yong.zhang0@gmail.com>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
This patch adds support for numa topology on powernv platforms running
OPAL formware. It checks for the type of platform at run time and
sets the affinity form correctly so that NUMA topology can be discovered
correctly.
Signed-off-by: Dipankar Sarma <dipankar@in.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
We've resisted adding System RAM to /proc/iomem because it is
the wrong place for it. Unfortunately we continue to find tools
that rely on this behaviour so give up and add it in.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Add HV mode KVM to Book3 server 64bit defconfigs as a module.
Doesn't add much to the size:
text data bss dec hex filename
8244109 4686767 994000 13924876 d47a0c vmlinux.vanilla
8256092 4691607 994128 13941827 d4bc43 vmlinux.kvm
This should enable more testing of this configuration.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
* 'modsplit-Oct31_2011' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux: (230 commits)
Revert "tracing: Include module.h in define_trace.h"
irq: don't put module.h into irq.h for tracking irqgen modules.
bluetooth: macroize two small inlines to avoid module.h
ip_vs.h: fix implicit use of module_get/module_put from module.h
nf_conntrack.h: fix up fallout from implicit moduleparam.h presence
include: replace linux/module.h with "struct module" wherever possible
include: convert various register fcns to macros to avoid include chaining
crypto.h: remove unused crypto_tfm_alg_modname() inline
uwb.h: fix implicit use of asm/page.h for PAGE_SIZE
pm_runtime.h: explicitly requires notifier.h
linux/dmaengine.h: fix implicit use of bitmap.h and asm/page.h
miscdevice.h: fix up implicit use of lists and types
stop_machine.h: fix implicit use of smp.h for smp_processor_id
of: fix implicit use of errno.h in include/linux/of.h
of_platform.h: delete needless include <linux/module.h>
acpi: remove module.h include from platform/aclinux.h
miscdevice.h: delete unnecessary inclusion of module.h
device_cgroup.h: delete needless include <linux/module.h>
net: sch_generic remove redundant use of <linux/module.h>
net: inet_timewait_sock doesnt need <linux/module.h>
...
Fix up trivial conflicts (other header files, and removal of the ab3550 mfd driver) in
- drivers/media/dvb/frontends/dibx000_common.c
- drivers/media/video/{mt9m111.c,ov6650.c}
- drivers/mfd/ab3550-core.c
- include/linux/dmaengine.h
* 'trivial' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
scsi: drop unused Kconfig symbol
pci: drop unused Kconfig symbol
stmmac: drop unused Kconfig symbol
x86: drop unused Kconfig symbol
powerpc: drop unused Kconfig symbols
powerpc: 40x: drop unused Kconfig symbol
mips: drop unused Kconfig symbols
openrisc: drop unused Kconfig symbols
arm: at91: drop unused Kconfig symbol
samples: drop unused Kconfig symbol
m32r: drop unused Kconfig symbol
score: drop unused Kconfig symbols
sh: drop unused Kconfig symbol
um: drop unused Kconfig symbol
sparc: drop unused Kconfig symbol
alpha: drop unused Kconfig symbol
Fix up trivial conflict in drivers/net/ethernet/stmicro/stmmac/Kconfig
as per Michal: the STMMAC_DUAL_MAC config variable is still unused and
should be deleted.
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (106 commits)
powerpc/p3060qds: Add support for P3060QDS board
powerpc/83xx: Add shutdown request support to MCU handling on MPC8349 MITX
powerpc/85xx: Make kexec to interate over online cpus
powerpc/fsl_booke: Fix comment in head_fsl_booke.S
powerpc/85xx: issue 15 EOI after core reset for FSL CoreNet devices
powerpc/8xxx: Fix interrupt handling in MPC8xxx GPIO driver
powerpc/85xx: Add 'fsl,pq3-gpio' compatiable for GPIO driver
powerpc/86xx: Correct Gianfar support for GE boards
powerpc/cpm: Clear muram before it is in use.
drivers/virt: add ioctl for 32-bit compat on 64-bit to fsl-hv-manager
powerpc/fsl_msi: add support for "msi-address-64" property
powerpc/85xx: Setup secondary cores PIR with hard SMP id
powerpc/fsl-booke: Fix settlbcam for 64-bit
powerpc/85xx: Adding DCSR node to dtsi device trees
powerpc/85xx: clean up FPGA device tree nodes for Freecsale QorIQ boards
powerpc/85xx: fix PHYS_64BIT selection for P1022DS
powerpc/fsl-booke: Fix setup_initial_memory_limit to not blindly map
powerpc: respect mem= setting for early memory limit setup
powerpc: Update corenet64_smp_defconfig
powerpc: Update mpc85xx/corenet 32-bit defconfigs
...
Fix up trivial conflicts in:
- arch/powerpc/configs/40x/hcu4_defconfig
removed stale file, edited elsewhere
- arch/powerpc/include/asm/udbg.h, arch/powerpc/kernel/udbg.c:
added opal and gelic drivers vs added ePAPR driver
- drivers/tty/serial/8250.c
moved UPIO_TSI to powerpc vs removed UPIO_DWAPB support
* 'for-3.2/core' of git://git.kernel.dk/linux-block: (29 commits)
block: don't call blk_drain_queue() if elevator is not up
blk-throttle: use queue_is_locked() instead of lockdep_is_held()
blk-throttle: Take blkcg->lock while traversing blkcg->policy_list
blk-throttle: Free up policy node associated with deleted rule
block: warn if tag is greater than real_max_depth.
block: make gendisk hold a reference to its queue
blk-flush: move the queue kick into
blk-flush: fix invalid BUG_ON in blk_insert_flush
block: Remove the control of complete cpu from bio.
block: fix a typo in the blk-cgroup.h file
block: initialize the bounce pool if high memory may be added later
block: fix request_queue lifetime handling by making blk_queue_cleanup() properly shutdown
block: drop @tsk from attempt_plug_merge() and explain sync rules
block: make get_request[_wait]() fail if queue is dead
block: reorganize throtl_get_tg() and blk_throtl_bio()
block: reorganize queue draining
block: drop unnecessary blk_get/put_queue() in scsi_cmd_ioctl() and blk_get_tg()
block: pass around REQ_* flags instead of broken down booleans during request alloc/free
block: move blk_throtl prototypes to block/blk.h
block: fix genhd refcounting in blkio_policy_parse_and_set()
...
Fix up trivial conflicts due to "mddev_t" -> "struct mddev" conversion
and making the request functions be of type "void" instead of "int" in
- drivers/md/{faulty.c,linear.c,md.c,md.h,multipath.c,raid0.c,raid1.c,raid10.c,raid5.c}
- drivers/staging/zram/zram_drv.c
The P3060QDS is a Freescale reference board that hosts the six-core P3060 SOC.
The P3060 Processor combines six e500mc Power Architecture processor cores with
high-performance datapath acceleration architecture(DPAA), CoreNet fabric
infrastructure, as well as network and peripheral interfaces.
P3060QDS Board Overview:
Memory subsystem:
- 2G Bytes unbuffered DDR3 SDRAM SO-DIMM(64bit bus)
- 128M Bytes NOR flash single-chip memory
- 16M Bytes SPI flash
- 8K Bytes AT24C64 I2C EEPROM
Ethernet:
- 4x1G + 4x1G/2.5G Ethernet controllers
- 2xRGMII + 1xMII, three VSC8641 PHYs on board
- Suport multiple Vitesse VSC8234 SGMII Cards in Slot1/2/3
PCIe: Two PCI Express 2.0 controllers/ports
USB: Two USB2.0, USB1(TYPE-A) and USB2(TYPE-AB) on board
I2C: Four I2C controllers
UART: Supports up to four UARTs
RapidIO: Supports two serial RapidIO ports
Signed-off-by: Shengzhou Liu <Shengzhou.Liu@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
This patch add support for calling ctrl_alt_del() when the power button is
pressed for more than about 2 seconds on some freescale MPC83xx evaluation
boards and reference design.
The code uses a kthread to poll the CTRL_BTN bit each second.
Also change Kconfig entry of the driver to bool, as device's gpio
registration is broken when loading as module.
Tested on an MPC8315E RDB board.
Signed-off-by: Fabio Baltieri <fabio.baltieri@gmail.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
This is not strictly required, because this iterates over logical
cpus and they are not (currently) discontigous. But, it's cleaner
code and more obvious what is going on
Signed-off-by: Matthew McClintock <msm@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
Fix typo in comments introduced by:
commit 6dece0eb69
Author: Scott Wood <scottwood@freescale.com>
Date: Mon Jul 25 11:29:33 2011 +0000
powerpc/32: Pass device tree address as u64 to machine_init
Signed-off-by: Matthew McClintock <msm@freescale.com>
cc: Scott Wood <scottwood@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
This is listed as a requirement for Freescale CoreNet based devices (e.g
p4080ds with MPIC v4.x) after issuing a core reset to properly clear pending
interrupts.
Signed-off-by: Matthew McClintock <msm@freescale.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
The GE DTBs were not updated when the Gianfar driver was converted to an
of_platform_driver in commit b31a1d8b41. Update
the DTBs, adding the required TBI entries.
Signed-off-by: Martyn Welch <martyn.welch@ge.com>
Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
The "struct rio_mport" contains a member of master port I/O memory
resource structure "struct resource iores". This resource will be read
from device tree and be used for rapidio R/W transaction memory space.
Rapidio requests the port I/O memory resource under the root resource
"iomem_resource".
struct rio_mport *port;
port = kzalloc(sizeof(struct rio_mport), GFP_KERNEL);
request_resource(&iomem_resource, &port->iores);
When port failed to initialize, allocated "rio_mport" structure memory
will be freed, and the port I/O memory resource structure pointer
"&port->iores" will be invalid. If other requests resource under
"iomem_resource", "&port->iores" node may be operated in the child
resources list and this will cause the system to crash.
So the requested port I/O memory resource should be released before
freeing allocated "rio_mport" structure.
Signed-off-by: Liu Gang <Gang.Liu@freescale.com>
Acked-by: Alexandre Bounine <alexandre.bounine@idt.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Grant Likely <grant.likely@secretlab.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This avoids duplicating the function in every arch gup_fast.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
powerpc didn't return 0 in that case, if it's rolling back the *nr pointer
it should also return zero to avoid adding pages to the array at the wrong
offset.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: David Miller <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Up to this point the code assumed old refcounting for hugepages (pre-thp).
This updates the code directly to the thp mapcount tail page refcounting.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We only taken "refs" pins on the head page not "*nr" pins.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
"page" may have changed to point to the next hugepage after the loop
completed, The references have been taken on the head page, so the
put_page must happen there too.
This is a longstanding issue pre-thp inclusion.
It's totally unclear how these page_cache_add_speculative and
pte_val(pte) != pte_val(*ptep) checks are necessary across all the
powerpc gup_fast code, when x86 doesn't need any of that: there's no way
the page can be freed with irq disabled so we're guaranteed the
atomic_inc will happen on a page with page_count > 0 (so not needing the
speculative check).
The pte check is also meaningless on x86: no need to rollback on x86 if
the pte changed, because the pte can still change a CPU tick after the
check succeeded and it won't be rolled back in that case. The important
thing is we got a reference on a valid page that was mapped there a CPU
tick ago. So not knowing the soft tlb refill code of ppc64 in great
detail I'm not removing the "speculative" page_count increase and the
pte checks across all the code, but unless there's a strong reason for
it they should be later cleaned up too.
If a pte can change from huge to non-huge (like it could happen with
THP) passing a pte_t *ptep to gup_hugepte() would also require to repeat
the is_hugepd in gup_hugepte(), but that shouldn't happen with hugetlbfs
only so I'm not altering that.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This part of gup_fast doesn't seem capable of handling hugetlbfs ptes,
those should be handled by gup_hugepd only, so these checks are
superfluous.
Plus if this wasn't a noop, it would have oopsed because, the insistence
of using the speculative refcounting would trigger a VM_BUG_ON if a tail
page was encountered in the page_cache_get_speculative().
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Michel while working on the working set estimation code, noticed that
calling get_page_unless_zero() on a random pfn_to_page(random_pfn)
wasn't safe, if the pfn ended up being a tail page of a transparent
hugepage under splitting by __split_huge_page_refcount().
He then found the problem could also theoretically materialize with
page_cache_get_speculative() during the speculative radix tree lookups
that uses get_page_unless_zero() in SMP if the radix tree page is freed
and reallocated and get_user_pages is called on it before
page_cache_get_speculative has a chance to call get_page_unless_zero().
So the best way to fix the problem is to keep page_tail->_count zero at
all times. This will guarantee that get_page_unless_zero() can never
succeed on any tail page. page_tail->_mapcount is guaranteed zero and
is unused for all tail pages of a compound page, so we can simply
account the tail page references there and transfer them to
tail_page->_count in __split_huge_page_refcount() (in addition to the
head_page->_mapcount).
While debugging this s/_count/_mapcount/ change I also noticed get_page is
called by direct-io.c on pages returned by get_user_pages. That wasn't
entirely safe because the two atomic_inc in get_page weren't atomic. As
opposed to other get_user_page users like secondary-MMU page fault to
establish the shadow pagetables would never call any superflous get_page
after get_user_page returns. It's safer to make get_page universally safe
for tail pages and to use get_page_foll() within follow_page (inside
get_user_pages()). get_page_foll() is safe to do the refcounting for tail
pages without taking any locks because it is run within PT lock protected
critical sections (PT lock for pte and page_table_lock for
pmd_trans_huge).
The standard get_page() as invoked by direct-io instead will now take
the compound_lock but still only for tail pages. The direct-io paths
are usually I/O bound and the compound_lock is per THP so very
finegrined, so there's no risk of scalability issues with it. A simple
direct-io benchmarks with all lockdep prove locking and spinlock
debugging infrastructure enabled shows identical performance and no
overhead. So it's worth it. Ideally direct-io should stop calling
get_page() on pages returned by get_user_pages(). The spinlock in
get_page() is already optimized away for no-THP builds but doing
get_page() on tail pages returned by GUP is generally a rare operation
and usually only run in I/O paths.
This new refcounting on page_tail->_mapcount in addition to avoiding new
RCU critical sections will also allow the working set estimation code to
work without any further complexity associated to the tail page
refcounting with THP.
Signed-off-by: Andrea Arcangeli <aarcange@redhat.com>
Reported-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Michel Lespinasse <walken@google.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <jweiner@redhat.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: <stable@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The basic idea behind cross memory attach is to allow MPI programs doing
intra-node communication to do a single copy of the message rather than a
double copy of the message via shared memory.
The following patch attempts to achieve this by allowing a destination
process, given an address and size from a source process, to copy memory
directly from the source process into its own address space via a system
call. There is also a symmetrical ability to copy from the current
process's address space into a destination process's address space.
- Use of /proc/pid/mem has been considered, but there are issues with
using it:
- Does not allow for specifying iovecs for both src and dest, assuming
preadv or pwritev was implemented either the area read from or
written to would need to be contiguous.
- Currently mem_read allows only processes who are currently
ptrace'ing the target and are still able to ptrace the target to read
from the target. This check could possibly be moved to the open call,
but its not clear exactly what race this restriction is stopping
(reason appears to have been lost)
- Having to send the fd of /proc/self/mem via SCM_RIGHTS on unix
domain socket is a bit ugly from a userspace point of view,
especially when you may have hundreds if not (eventually) thousands
of processes that all need to do this with each other
- Doesn't allow for some future use of the interface we would like to
consider adding in the future (see below)
- Interestingly reading from /proc/pid/mem currently actually
involves two copies! (But this could be fixed pretty easily)
As mentioned previously use of vmsplice instead was considered, but has
problems. Since you need the reader and writer working co-operatively if
the pipe is not drained then you block. Which requires some wrapping to
do non blocking on the send side or polling on the receive. In all to all
communication it requires ordering otherwise you can deadlock. And in the
example of many MPI tasks writing to one MPI task vmsplice serialises the
copying.
There are some cases of MPI collectives where even a single copy interface
does not get us the performance gain we could. For example in an
MPI_Reduce rather than copy the data from the source we would like to
instead use it directly in a mathops (say the reduce is doing a sum) as
this would save us doing a copy. We don't need to keep a copy of the data
from the source. I haven't implemented this, but I think this interface
could in the future do all this through the use of the flags - eg could
specify the math operation and type and the kernel rather than just
copying the data would apply the specified operation between the source
and destination and store it in the destination.
Although we don't have a "second user" of the interface (though I've had
some nibbles from people who may be interested in using it for intra
process messaging which is not MPI). This interface is something which
hardware vendors are already doing for their custom drivers to implement
fast local communication. And so in addition to this being useful for
OpenMPI it would mean the driver maintainers don't have to fix things up
when the mm changes.
There was some discussion about how much faster a true zero copy would
go. Here's a link back to the email with some testing I did on that:
http://marc.info/?l=linux-mm&m=130105930902915&w=2
There is a basic man page for the proposed interface here:
http://ozlabs.org/~cyeoh/cma/process_vm_readv.txt
This has been implemented for x86 and powerpc, other architecture should
mainly (I think) just need to add syscall numbers for the process_vm_readv
and process_vm_writev. There are 32 bit compatibility versions for
64-bit kernels.
For arch maintainers there are some simple tests to be able to quickly
verify that the syscalls are working correctly here:
http://ozlabs.org/~cyeoh/cma/cma-test-20110718.tgz
Signed-off-by: Chris Yeoh <yeohc@au1.ibm.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: David Howells <dhowells@redhat.com>
Cc: James Morris <jmorris@namei.org>
Cc: <linux-man@vger.kernel.org>
Cc: <linux-arch@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Anton Blanchard