Pull NFS client updates from Trond Myklebust:
"Features include:
- Remove CONFIG_EXPERIMENTAL dependency from NFSv4.1
Aside from the issues discussed at the LKS, distros are shipping
NFSv4.1 with all the trimmings.
- Fix fdatasync()/fsync() for the corner case of a server reboot.
- NFSv4 OPEN access fix: finally distinguish correctly between
open-for-read and open-for-execute permissions in all situations.
- Ensure that the TCP socket is closed when we're in CLOSE_WAIT
- More idmapper bugfixes
- Lots of pNFS bugfixes and cleanups to remove unnecessary state and
make the code easier to read.
- In cases where a pNFS read or write fails, allow the client to
resume trying layoutgets after two minutes of read/write-
through-mds.
- More net namespace fixes to the NFSv4 callback code.
- More net namespace fixes to the NFSv3 locking code.
- More NFSv4 migration preparatory patches.
Including patches to detect network trunking in both NFSv4 and
NFSv4.1
- pNFS block updates to optimise LAYOUTGET calls."
* tag 'nfs-for-3.7-1' of git://git.linux-nfs.org/projects/trondmy/linux-nfs: (113 commits)
pnfsblock: cleanup nfs4_blkdev_get
NFS41: send real read size in layoutget
NFS41: send real write size in layoutget
NFS: track direct IO left bytes
NFSv4.1: Cleanup ugliness in pnfs_layoutgets_blocked()
NFSv4.1: Ensure that the layout sequence id stays 'close' to the current
NFSv4.1: Deal with seqid wraparound in the pNFS return-on-close code
NFSv4 set open access operation call flag in nfs4_init_opendata_res
NFSv4.1: Remove the dependency on CONFIG_EXPERIMENTAL
NFSv4 reduce attribute requests for open reclaim
NFSv4: nfs4_open_done first must check that GETATTR decoded a file type
NFSv4.1: Deal with wraparound when updating the layout "barrier" seqid
NFSv4.1: Deal with wraparound issues when updating the layout stateid
NFSv4.1: Always set the layout stateid if this is the first layoutget
NFSv4.1: Fix another refcount issue in pnfs_find_alloc_layout
NFSv4: don't put ACCESS in OPEN compound if O_EXCL
NFSv4: don't check MAY_WRITE access bit in OPEN
NFS: Set key construction data for the legacy upcall
NFSv4.1: don't do two EXCHANGE_IDs on mount
NFS: nfs41_walk_client_list(): re-lock before iterating
...
Pull pwm changes from Thierry Reding:
"All legacy PWM providers have now been moved to the PWM subsystem.
The plan for 3.8 is to adapt all board files to provide a lookup table
for PWM devices in order to get rid of the global namespace.
Subsequently, users of the legacy pwm_request() and pwm_free()
functions can be migrated to the new pwm_get() and pwm_put()
functions. Once this has been completed, the legacy API and the
compatibility code in the core can be removed.
In addition to the above, these changes also add support for
configuring the polarity of a PWM signal (currently only supported on
ECAP and EHRPWM) and include a much needed rework of the i.MX driver.
Managed functions to obtain and release a PWM device (devm_pwm_get()
and devm_pwm_put()) have been added and the pwm-backlight driver has
been updated to use them. If the PWM subsystem hasn't been enabled,
dummy functions are provided that allow the subsystem to safely
compile out.
Some common checks on input parameters have been moved to the core and
removed from the drivers. Finally, a small fix corrects the
description of the PWM specifier's second cell in the device tree
representation."
* tag 'for-3.7-rc1' of git://gitorious.org/linux-pwm/linux-pwm: (23 commits)
pwm: dt: Fix description of second PWM cell
pwm: Check for negative duty-cycle and period
pwm: Add Ingenic JZ4740 support
MIPS: JZ4740: Export timer API
pwm: Move PUV3 PWM driver to PWM framework
unicore32: pwm: Use managed resource allocations
unicore32: pwm: Remove unnecessary indirection
unicore32: pwm: Use module_platform_driver()
unicore32: pwm: Properly remap memory-mapped registers
pwm-backlight: Use devm_pwm_get() instead of pwm_get()
pwm: Move AB8500 PWM driver to PWM framework
pwm: Fix compilation error when CONFIG_PWM is not defined
pwm: i.MX: fix clock lookup
pwm: i.MX: use per clock unconditionally
pwm: i.MX: add devicetree support
pwm: i.MX: Use module_platform_driver
pwm: i.MX: add functions to enable/disable pwm.
pwm: i.MX: remove unnecessary if in pwm_[en|dis]able
pwm: i.MX: factor out SoC specific functions
pwm: pwm-tiehrpwm: Add support for configuring polarity of PWM
...
Pull LED subsystem update from Bryan Wu.
* 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/linux-leds: (24 commits)
leds: add output driver configuration for pca9633 led driver
leds: lm3642: Use regmap_update_bits() in lm3642_chip_init()
leds: Add new LED driver for lm3642 chips
leds-lp5523: Fix riskiness of the page fault
leds-lp5523: turn off the LED engines on unloading the driver
leds-lm3530: Fix smatch warnings
leds-lm3530: Use devm_regulator_get function
leds: leds-gpio: adopt pinctrl support
leds: Add new LED driver for lm355x chips
leds-lp5523: use the i2c device id rather than fixed name
leds-lp5523: add new device id for LP55231
leds-lp5523: support new LP55231 device
leds: triggers: send uevent when changing triggers
leds-lp5523: minor code style fixes
leds-lp5523: change the return type of lp5523_set_mode()
leds-lp5523: set the brightness to 0 forcely on removing the driver
leds-lp5523: add channel name in the platform data
leds: leds-gpio: Use of_get_child_count() helper
leds: leds-gpio: Use platform_{get,set}_drvdata
leds: leds-gpio: use of_match_ptr()
...
We do a very simple search for a particular string appended to the module
(which is cache-hot and about to be SHA'd anyway). There's both a config
option and a boot parameter which control whether we accept or fail with
unsigned modules and modules that are signed with an unknown key.
If module signing is enabled, the kernel will be tainted if a module is
loaded that is unsigned or has a signature for which we don't have the
key.
(Useful feedback and tweaks by David Howells <dhowells@redhat.com>)
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Pull generic execve() changes from Al Viro:
"This introduces the generic kernel_thread() and kernel_execve()
functions, and switches x86, arm, alpha, um and s390 over to them."
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/signal: (26 commits)
s390: convert to generic kernel_execve()
s390: switch to generic kernel_thread()
s390: fold kernel_thread_helper() into ret_from_fork()
s390: fold execve_tail() into start_thread(), convert to generic sys_execve()
um: switch to generic kernel_thread()
x86, um/x86: switch to generic sys_execve and kernel_execve
x86: split ret_from_fork
alpha: introduce ret_from_kernel_execve(), switch to generic kernel_execve()
alpha: switch to generic kernel_thread()
alpha: switch to generic sys_execve()
arm: get rid of execve wrapper, switch to generic execve() implementation
arm: optimized current_pt_regs()
arm: introduce ret_from_kernel_execve(), switch to generic kernel_execve()
arm: split ret_from_fork, simplify kernel_thread() [based on patch by rmk]
generic sys_execve()
generic kernel_execve()
new helper: current_pt_regs()
preparation for generic kernel_thread()
um: kill thread->forking
um: let signal_delivered() do SIGTRAP on singlestepping into handler
...
Pull networking updates from David Miller:
1) UAPI changes for networking from David Howells
2) A netlink dump is an operation we can sleep within, and therefore we
need to make sure the dump provider module doesn't disappear on us
meanwhile. Fix from Gao Feng.
3) Now that tunnels support GRO, we have to be more careful in
skb_gro_reset_offset() otherwise we OOPS, from Eric Dumazet.
4) We can end up processing packets for VLANs we aren't actually
configured to be on, fix from Florian Zumbiehl.
5) Fix routing cache removal regression in redirects and IPVS. The
core issue on the IPVS side is that it wants to rewrite who the
nexthop is and we have to explicitly accomodate that case. From
Julian Anastasov.
6) Error code return fixes all over the networking drivers from Peter
Senna Tschudin.
7) Fix routing cache removal regressions in IPSEC, from Steffen
Klassert.
8) Fix deadlock in RDS during pings, from Jeff Liu.
9) Neighbour packet queue can trigger skb_under_panic() because we do
not reset the network header of the SKB in the right spot. From
Ramesh Nagappa.
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (61 commits)
RDS: fix rds-ping spinlock recursion
netdev/phy: Prototype of_mdio_find_bus()
farsync: fix support for over 30 cards
be2net: Remove code that stops further access to BE NIC based on UE bits
pch_gbe: Fix build error by selecting all the possible dependencies.
e1000e: add device IDs for i218
ixgbe/ixgbevf: Limit maximum jumbo frame size to 9.5K to avoid Tx hangs
ixgbevf: Set the netdev number of Tx queues
UAPI: (Scripted) Disintegrate include/linux/tc_ematch
UAPI: (Scripted) Disintegrate include/linux/tc_act
UAPI: (Scripted) Disintegrate include/linux/netfilter_ipv6
UAPI: (Scripted) Disintegrate include/linux/netfilter_ipv4
UAPI: (Scripted) Disintegrate include/linux/netfilter_bridge
UAPI: (Scripted) Disintegrate include/linux/netfilter_arp
UAPI: (Scripted) Disintegrate include/linux/netfilter/ipset
UAPI: (Scripted) Disintegrate include/linux/netfilter
UAPI: (Scripted) Disintegrate include/linux/isdn
UAPI: (Scripted) Disintegrate include/linux/caif
net: fix typo in freescale/ucc_geth.c
vxlan: fix more sparse warnings
...
Pull slave-dmaengine updates from Vinod Koul:
"This time we have Andy updates on dw_dmac which is attempting to make
this IP block available as PCI and platform device though not fully
complete this time.
We also have TI EDMA moving the dma driver to use dmaengine APIs, also
have a new driver for mmp-tdma, along with bunch of small updates.
Now for your excitement the merge is little unusual here, while
merging the auto merge on linux-next picks wrong choice for pl330
(drivers/dma/pl330.c) and this causes build failure. The correct
resolution is in linux-next. (DMA: PL330: Fix build error) I didn't
back merge your tree this time as you are better than me so no point
in doing that for me :)"
Fixed the pl330 conflict as in linux-next, along with trivial header
file conflicts due to changed includes.
* 'next' of git://git.infradead.org/users/vkoul/slave-dma: (29 commits)
dma: tegra: fix interrupt name issue with apb dma.
dw_dmac: fix a regression in dwc_prep_dma_memcpy
dw_dmac: introduce software emulation of LLP transfers
dw_dmac: autoconfigure data_width or get it via platform data
dw_dmac: autoconfigure block_size or use platform data
dw_dmac: get number of channels from hardware if possible
dw_dmac: fill optional encoded parameters in register structure
dw_dmac: mark dwc_dump_chan_regs as inline
DMA: PL330: return ENOMEM instead of 0 from pl330_alloc_chan_resources
DMA: PL330: Remove redundant runtime_suspend/resume functions
DMA: PL330: Remove controller clock enable/disable
dmaengine: use kmem_cache_zalloc instead of kmem_cache_alloc/memset
DMA: PL330: Set the capability of pdm0 and pdm1 as DMA_PRIVATE
ARM: EXYNOS: Set the capability of pdm0 and pdm1 as DMA_PRIVATE
dma: tegra: use list_move_tail instead of list_del/list_add_tail
mxs/dma: Enlarge the CCW descriptor area to 4 pages
dw_dmac: utilize slave_id to pass request line
dmaengine: mmp_tdma: add dt support
dmaengine: mmp-pdma support
spi: davici - make davinci select edma
...
Pull MMC updates from Chris Ball:
"Core:
- Add DT properties for card detection (broken-cd, cd-gpios,
non-removable)
- Don't poll non-removable devices
- Fixup/rework eMMC sleep mode/"power off notify" feature
- Support eMMC background operations (BKOPS). To set the one-time
programmable fuse that enables bkops on an eMMC that doesn't
already have it set, you can use the "mmc bkops enable" command in:
git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc-utils.git
Drivers:
- atmel-mci, dw_mmc, pxa-mci, dove, s3c, spear: Add device tree
support
- bfin_sdh: Add support for the controller in bf60x
- dw_mmc: Support Samsung Exynos SoCs
- eSDHC: Add ADMA support
- sdhci: Support testing a cd-gpio (from slot-gpio) instead of
presence bit
- sdhci-pltfm: Support broken-cd DT property
- tegra: Convert to only supporting DT (mach-tegra has gone DT-only)"
* tag 'mmc-merge-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/cjb/mmc: (67 commits)
mmc: core: Fixup broken suspend and eMMC4.5 power off notify
mmc: sdhci-spear: Add clk_{un}prepare() support
mmc: sdhci-spear: add device tree bindings
mmc: sdhci-s3c: Add clk_(enable/disable) in runtime suspend/resume
mmc: core: Replace MMC_CAP2_BROKEN_VOLTAGE with test for fixed regulator
mmc: sdhci-pxav3: Use sdhci_get_of_property for parsing DT quirks
mmc: dt: Support "broken-cd" property in sdhci-pltfm
mmc: sdhci-s3c: fix the wrong number of max bus clocks
mmc: sh-mmcif: avoid oops on spurious interrupts
mmc: sh-mmcif: properly handle MMC_WRITE_MULTIPLE_BLOCK completion IRQ
mmc: sdhci-s3c: Fix crash on module insertion for second time
mmc: sdhci-s3c: Enable only required bus clock
mmc: Revert "mmc: dw_mmc: Add check for IDMAC configuration"
mmc: mxcmmc: fix bug that may block a data transfer forever
mmc: omap_hsmmc: Pass on the suspend failure to the PM core
mmc: atmel-mci: AP700x PDC is not connected to MCI
mmc: atmel-mci: DMA can be used with other controllers
mmc: mmci: use clk_prepare_enable and clk_disable_unprepare
mmc: sdhci-s3c: Add device tree support
mmc: dw_mmc: add support for exynos specific implementation of dw-mshc
...
This is to complete part of the Userspace API (UAPI) disintegration for which
the preparatory patches were pulled recently. After these patches, userspace
headers will be segregated into:
include/uapi/linux/.../foo.h
for the userspace interface stuff, and:
include/linux/.../foo.h
for the strictly kernel internal stuff.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Pulled mainline in order to get the UAPI infrastructure already
merged before I pull in David Howells's UAPI trees for networking.
Signed-off-by: David S. Miller <davem@davemloft.net>
Support the LUN parameter change event. Currently, the host fires this event
when the capacity of a disk is changed from the virtual machine monitor.
The resize then appears in the kernel log like this:
sd 0:0:0:0: [sda] 46137344 512-byte logical blocks: (23.6 GB/22.0 GIb)
sda: detected capacity change from 22548578304 to 23622320128
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: James Bottomley <JBottomley@Parallels.com>
Merge patches from Andrew Morton:
"A few misc things and very nearly all of the MM tree. A tremendous
amount of stuff (again), including a significant rbtree library
rework."
* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (160 commits)
sparc64: Support transparent huge pages.
mm: thp: Use more portable PMD clearing sequenece in zap_huge_pmd().
mm: Add and use update_mmu_cache_pmd() in transparent huge page code.
sparc64: Document PGD and PMD layout.
sparc64: Eliminate PTE table memory wastage.
sparc64: Halve the size of PTE tables
sparc64: Only support 4MB huge pages and 8KB base pages.
memory-hotplug: suppress "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" warning
mm: memcg: clean up mm_match_cgroup() signature
mm: document PageHuge somewhat
mm: use %pK for /proc/vmallocinfo
mm, thp: fix mlock statistics
mm, thp: fix mapped pages avoiding unevictable list on mlock
memory-hotplug: update memory block's state and notify userspace
memory-hotplug: preparation to notify memory block's state at memory hot remove
mm: avoid section mismatch warning for memblock_type_name
make GFP_NOTRACK definition unconditional
cma: decrease cc.nr_migratepages after reclaiming pagelist
CMA: migrate mlocked pages
kpageflags: fix wrong KPF_THP on non-huge compound pages
...
It really should return a boolean for match/no match. And since it takes
a memcg, not a cgroup, fix that parameter name as well.
[akpm@linux-foundation.org: mm_match_cgroup() is not a macro]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a transparent hugepage is mapped and it is included in an mlock()
range, follow_page() incorrectly avoids setting the page's mlock bit and
moving it to the unevictable lru.
This is evident if you try to mlock(), munlock(), and then mlock() a
range again. Currently:
#define MAP_SIZE (4 << 30) /* 4GB */
void *ptr = mmap(NULL, MAP_SIZE, PROT_READ | PROT_WRITE,
MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
mlock(ptr, MAP_SIZE);
$ grep -E "Unevictable|Inactive\(anon" /proc/meminfo
Inactive(anon): 6304 kB
Unevictable: 4213924 kB
munlock(ptr, MAP_SIZE);
Inactive(anon): 4186252 kB
Unevictable: 19652 kB
mlock(ptr, MAP_SIZE);
Inactive(anon): 4198556 kB
Unevictable: 21684 kB
Notice that less than 2MB was added to the unevictable list; this is
because these pages in the range are not transparent hugepages since the
4GB range was allocated with mmap() and has no specific alignment. If
posix_memalign() were used instead, unevictable would not have grown at
all on the second mlock().
The fix is to call mlock_vma_page() so that the mlock bit is set and the
page is added to the unevictable list. With this patch:
mlock(ptr, MAP_SIZE);
Inactive(anon): 4056 kB
Unevictable: 4213940 kB
munlock(ptr, MAP_SIZE);
Inactive(anon): 4198268 kB
Unevictable: 19636 kB
mlock(ptr, MAP_SIZE);
Inactive(anon): 4008 kB
Unevictable: 4213940 kB
Signed-off-by: David Rientjes <rientjes@google.com>
Acked-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Andrea Arcangeli <aarcange@redhat.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
remove_memory() will be called when hot removing a memory device. But
even if offlining memory, we cannot notice it. So the patch updates the
memory block's state and sends notification to userspace.
Additionally, the memory device may contain more than one memory block.
If the memory block has been offlined, __offline_pages() will fail. So we
should try to offline one memory block at a time.
Thus remove_memory() also check each memory block's state. So there is no
need to check the memory block's state before calling remove_memory().
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
remove_memory() is called in two cases:
1. echo offline >/sys/devices/system/memory/memoryXX/state
2. hot remove a memory device
In the 1st case, the memory block's state is changed and the notification
that memory block's state changed is sent to userland after calling
remove_memory(). So user can notice memory block is changed.
But in the 2nd case, the memory block's state is not changed and the
notification is not also sent to userspcae even if calling
remove_memory(). So user cannot notice memory block is changed.
For adding the notification at memory hot remove, the patch just prepare
as follows:
1st case uses offline_pages() for offlining memory.
2nd case uses remove_memory() for offlining memory and changing memory block's
state and notifing the information.
The patch does not implement notification to remove_memory().
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Jiang Liu <liuj97@gmail.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Presently CMA cannot migrate mlocked pages so it ends up failing to allocate
contiguous memory space.
This patch makes mlocked pages be migrated out. Of course, it can affect
realtime processes but in CMA usecase, contiguous memory allocation failing
is far worse than access latency to an mlocked page being variable while
CMA is running. If someone wants to make the system realtime, he shouldn't
enable CMA because stalls can still happen at random times.
[akpm@linux-foundation.org: tweak comment text, per Mel]
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During memory-hotplug, I found NR_ISOLATED_[ANON|FILE] are increasing,
causing the kernel to hang. When the system doesn't have enough free
pages, it enters reclaim but never reclaim any pages due to
too_many_isolated()==true and loops forever.
The cause is that when we do memory-hotadd after memory-remove,
__zone_pcp_update() clears a zone's ZONE_STAT_ITEMS in setup_pageset()
although the vm_stat_diff of all CPUs still have values.
In addtion, when we offline all pages of the zone, we reset them in
zone_pcp_reset without draining so we loss some zone stat item.
Reviewed-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In order to allow sleeping during mmu notifier calls, we need to avoid
invoking them under the page table spinlock. This patch solves the
problem by calling invalidate_page notification after releasing the lock
(but before freeing the page itself), or by wrapping the page invalidation
with calls to invalidate_range_begin and invalidate_range_end.
To prevent accidental changes to the invalidate_range_end arguments after
the call to invalidate_range_begin, the patch introduces a convention of
saving the arguments in consistently named locals:
unsigned long mmun_start; /* For mmu_notifiers */
unsigned long mmun_end; /* For mmu_notifiers */
...
mmun_start = ...
mmun_end = ...
mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
...
mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
The patch changes code to use this convention for all calls to
mmu_notifier_invalidate_range_start/end, except those where the calls are
close enough so that anyone who glances at the code can see the values
aren't changing.
This patchset is a preliminary step towards on-demand paging design to be
added to the RDMA stack.
Why do we want on-demand paging for Infiniband?
Applications register memory with an RDMA adapter using system calls,
and subsequently post IO operations that refer to the corresponding
virtual addresses directly to HW. Until now, this was achieved by
pinning the memory during the registration calls. The goal of on demand
paging is to avoid pinning the pages of registered memory regions (MRs).
This will allow users the same flexibility they get when swapping any
other part of their processes address spaces. Instead of requiring the
entire MR to fit in physical memory, we can allow the MR to be larger,
and only fit the current working set in physical memory.
Why should anyone care? What problems are users currently experiencing?
This can make programming with RDMA much simpler. Today, developers
that are working with more data than their RAM can hold need either to
deregister and reregister memory regions throughout their process's
life, or keep a single memory region and copy the data to it. On demand
paging will allow these developers to register a single MR at the
beginning of their process's life, and let the operating system manage
which pages needs to be fetched at a given time. In the future, we
might be able to provide a single memory access key for each process
that would provide the entire process's address as one large memory
region, and the developers wouldn't need to register memory regions at
all.
Is there any prospect that any other subsystems will utilise these
infrastructural changes? If so, which and how, etc?
As for other subsystems, I understand that XPMEM wanted to sleep in
MMU notifiers, as Christoph Lameter wrote at
http://lkml.indiana.edu/hypermail/linux/kernel/0802.1/0460.html and
perhaps Andrea knows about other use cases.
Scheduling in mmu notifications is required since we need to sync the
hardware with the secondary page tables change. A TLB flush of an IO
device is inherently slower than a CPU TLB flush, so our design works by
sending the invalidation request to the device, and waiting for an
interrupt before exiting the mmu notifier handler.
Avi said:
kvm may be a buyer. kvm::mmu_lock, which serializes guest page
faults, also protects long operations such as destroying large ranges.
It would be good to convert it into a spinlock, but as it is used inside
mmu notifiers, this cannot be done.
(there are alternatives, such as keeping the spinlock and using a
generation counter to do the teardown in O(1), which is what the "may"
is doing up there).
[akpm@linux-foundation.orgpossible speed tweak in hugetlb_cow(), cleanups]
Signed-off-by: Andrea Arcangeli <andrea@qumranet.com>
Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com>
Cc: Or Gerlitz <ogerlitz@mellanox.com>
Cc: Haggai Eran <haggaie@mellanox.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Cc: Liran Liss <liranl@mellanox.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Avi Kivity <avi@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
RECLAIM_DISTANCE represents the distance between nodes at which it is
deemed too costly to allocate from; it's preferred to try to reclaim from
a local zone before falling back to allocating on a remote node with such
a distance.
To do this, zone_reclaim_mode is set if the distance between any two
nodes on the system is greather than this distance. This, however, ends
up causing the page allocator to reclaim from every zone regardless of
its affinity.
What we really want is to reclaim only from zones that are closer than
RECLAIM_DISTANCE. This patch adds a nodemask to each node that
represents the set of nodes that are within this distance. During the
zone iteration, if the bit for a zone's node is set for the local node,
then reclaim is attempted; otherwise, the zone is skipped.
[akpm@linux-foundation.org: fix CONFIG_NUMA=n build]
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Minchan Kim <minchan@kernel.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We should not be seeing non-0 unevictable_pgs_mlockfreed any longer. So
remove free_page_mlock() from the page freeing paths: __PG_MLOCKED is
already in PAGE_FLAGS_CHECK_AT_FREE, so free_pages_check() will now be
checking it, reporting "BUG: Bad page state" if it's ever found set.
Comment UNEVICTABLE_MLOCKFREED and unevictable_pgs_mlockfreed always 0.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ying Han <yinghan@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
