| Age | Commit message (Collapse) | Author |
|---|
|
Pseudo filesystems that don't put inode on RCU list or reachable by
rcu-walk dentries do not need to RCU free their inodes.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
RCU free the struct inode. This will allow:
- Subsequent store-free path walking patch. The inode must be consulted for
permissions when walking, so an RCU inode reference is a must.
- sb_inode_list_lock to be moved inside i_lock because sb list walkers who want
to take i_lock no longer need to take sb_inode_list_lock to walk the list in
the first place. This will simplify and optimize locking.
- Could remove some nested trylock loops in dcache code
- Could potentially simplify things a bit in VM land. Do not need to take the
page lock to follow page->mapping.
The downsides of this is the performance cost of using RCU. In a simple
creat/unlink microbenchmark, performance drops by about 10% due to inability to
reuse cache-hot slab objects. As iterations increase and RCU freeing starts
kicking over, this increases to about 20%.
In cases where inode lifetimes are longer (ie. many inodes may be allocated
during the average life span of a single inode), a lot of this cache reuse is
not applicable, so the regression caused by this patch is smaller.
The cache-hot regression could largely be avoided by using SLAB_DESTROY_BY_RCU,
however this adds some complexity to list walking and store-free path walking,
so I prefer to implement this at a later date, if it is shown to be a win in
real situations. I haven't found a regression in any non-micro benchmark so I
doubt it will be a problem.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
The tricky locking for disposing of a dentry is duplicated 3 times in the
dcache (dput, pruning a dentry from the LRU, and pruning its ancestors).
Consolidate them all into a single function dentry_kill.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
prune_one_dentry can avoid quite a bit of locking in the common case where
ancestors have an elevated refcount. Alternatively, we could have gone the
other way and made fewer trylocks in the case where d_count goes to zero, but
is probably less common.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Use RCU to simplify locking in dget_parent.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
dget_locked was a shortcut to avoid the lazy lru manipulation when we already
held dcache_lock (lru manipulation was relatively cheap at that point).
However, how that the lru lock is an innermost one, we never hold it at any
caller, so the lock cost can now be avoided. We already have well working lazy
dcache LRU, so it should be fine to defer LRU manipulations to scan time.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
dcache_inode_lock can be avoided in d_delete() and d_materialise_unique()
in cases where it is not required.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
It is possible to run dput without taking data structure locks up-front. In
many cases where we don't kill the dentry anyway, these locks are not required.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Long lived dcache "multi-step" operations which retry on rename seq can
be starved with a lot of rename activity. If they fail after the 1st pass,
take the rename_lock for writing to avoid further starvation.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
dcache_lock no longer protects anything. remove it.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
The remaining usages for dcache_lock is to allow atomic, multi-step read-side
operations over the directory tree by excluding modifications to the tree.
Also, to walk in the leaf->root direction in the tree where we don't have
a natural d_lock ordering.
This could be accomplished by taking every d_lock, but this would mean a
huge number of locks and actually gets very tricky.
Solve this instead by using the rename seqlock for multi-step read-side
operations, retry in case of a rename so we don't walk up the wrong parent.
Concurrent dentry insertions are not serialised against. Concurrent deletes
are tricky when walking up the directory: our parent might have been deleted
when dropping locks so also need to check and retry for that.
We can also use the rename lock in cases where livelock is a worry (and it
is introduced in subsequent patch).
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Cover d_name with d_lock in more cases, where there may be concurrent
modification to it.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Add a new lock, dcache_inode_lock, to protect the inode's i_dentry list
from concurrent modification. d_alias is also protected by d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Protect d_subdirs and d_child with d_lock, except in filesystems that aren't
using dcache_lock for these anyway (eg. using i_mutex).
Note: if we change the locking rule in future so that ->d_child protection is
provided only with ->d_parent->d_lock, it may allow us to reduce some locking.
But it would be an exception to an otherwise regular locking scheme, so we'd
have to see some good results. Probably not worthwhile.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Protect d_unhashed(dentry) condition with d_lock. This means keeping
DCACHE_UNHASHED bit in synch with hash manipulations.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Make d_count non-atomic and protect it with d_lock. This allows us to ensure a
0 refcount dentry remains 0 without dcache_lock. It is also fairly natural when
we start protecting many other dentry members with d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Add a new lock, dcache_lru_lock, to protect the dcache LRU list from concurrent
modification. d_lru is also protected by d_lock, which allows LRU lists to be
accessed without the lru lock, using RCU in future patches.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Add a new lock, dcache_hash_lock, to protect the dcache hash table from
concurrent modification. d_hash is also protected by d_lock.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Remove dcache_lock locking from hostfs filesystem, and move it into dcache
helpers. All that is required is a coherent path name. Protection from
concurrent modification of the namespace after path name generation is not
provided in current code, because dcache_lock is dropped before the path is
used.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Change d_hash so it may be called from lock-free RCU lookups. See similar
patch for d_compare for details.
For in-tree filesystems, this is just a mechanical change.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Change d_compare so it may be called from lock-free RCU lookups. This
does put significant restrictions on what may be done from the callback,
however there don't seem to have been any problems with in-tree fses.
If some strange use case pops up that _really_ cannot cope with the
rcu-walk rules, we can just add new rcu-unaware callbacks, which would
cause name lookup to drop out of rcu-walk mode.
For in-tree filesystems, this is just a mechanical change.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
smpfs and ncpfs want to update a live dentry name in-place. Rather than
have them open code the locking, provide a documented dcache API.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Use vfat's method for dealing with negative dentries to preserve case,
rather than overwrite dentry name in d_revalidate, which is a bit ugly
and also gets in the way of doing lock-free path walking.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Use vfat's method for dealing with negative dentries to preserve case,
rather than overwrite dentry name in d_revalidate, which is a bit ugly
and also gets in the way of doing lock-free path walking.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Change d_delete from a dentry deletion notification to a dentry caching
advise, more like ->drop_inode. Require it to be constant and idempotent,
and not take d_lock. This is how all existing filesystems use the callback
anyway.
This makes fine grained dentry locking of dput and dentry lru scanning
much simpler.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Remove redundant (and incorrect, since dcache RCU lookup) dentry locking
documentation and point to the canonical document.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Switching d_op on a live dentry is racy in general, so avoid it. In this case
it is a negative dentry, which is safer, but there are still concurrent ops
which may be called on d_op in that case (eg. d_revalidate). So in general
a filesystem may not do this. Fix configfs so as not to do this.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
Switching d_op on a live dentry is racy in general, so avoid it. In this case
it is a negative dentry, which is safer, but there are still concurrent ops
which may be called on d_op in that case (eg. d_revalidate). So in general
a filesystem may not do this. Fix cgroupfs so as not to do this.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
percpu_counter library generates quite nasty code, so unless you need
to dynamically allocate counters or take fast approximate value, a
simple per cpu set of counters is much better.
The percpu_counter can never be made to work as well, because it has an
indirection from pointer to percpu memory, and it can't use direct
this_cpu_inc interfaces because it doesn't use static PER_CPU data, so
code will always be worse.
In the fastpath, it is the difference between this:
incl %gs:nr_dentry # nr_dentry
and this:
movl percpu_counter_batch(%rip), %edx # percpu_counter_batch,
movl $1, %esi #,
movq $nr_dentry, %rdi #,
call __percpu_counter_add # (plus I clobber registers)
__percpu_counter_add:
pushq %rbp #
movq %rsp, %rbp #,
subq $32, %rsp #,
movq %rbx, -24(%rbp) #,
movq %r12, -16(%rbp) #,
movq %r13, -8(%rbp) #,
movq %rdi, %rbx # fbc, fbc
#APP
# 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1
movq %gs:kernel_stack,%rax #, pfo_ret__
# 0 "" 2
#NO_APP
incl -8124(%rax) # <variable>.preempt_count
movq 32(%rdi), %r12 # <variable>.counters, tcp_ptr__
#APP
# 78 "lib/percpu_counter.c" 1
add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__
# 0 "" 2
#NO_APP
movslq (%r12),%r13 #* tcp_ptr__, tmp73
movslq %edx,%rax # batch, batch
addq %rsi, %r13 # amount, count
cmpq %rax, %r13 # batch, count
jge .L27 #,
negl %edx # tmp76
movslq %edx,%rdx # tmp76, tmp77
cmpq %rdx, %r13 # tmp77, count
jg .L28 #,
.L27:
movq %rbx, %rdi # fbc,
call _raw_spin_lock #
addq %r13, 8(%rbx) # count, <variable>.count
movq %rbx, %rdi # fbc,
movl $0, (%r12) #,* tcp_ptr__
call _raw_spin_unlock #
.L29:
#APP
# 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1
movq %gs:kernel_stack,%rax #, pfo_ret__
# 0 "" 2
#NO_APP
decl -8124(%rax) # <variable>.preempt_count
movq -8136(%rax), %rax #, D.14625
testb $8, %al #, D.14625
jne .L32 #,
.L31:
movq -24(%rbp), %rbx #,
movq -16(%rbp), %r12 #,
movq -8(%rbp), %r13 #,
leave
ret
.p2align 4,,10
.p2align 3
.L28:
movl %r13d, (%r12) # count,*
jmp .L29 #
.L32:
call preempt_schedule #
.p2align 4,,6
jmp .L31 #
.size __percpu_counter_add, .-__percpu_counter_add
.p2align 4,,15
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
The nr_unused counters count the number of objects on an LRU, and as such they
are synchronized with LRU object insertion and removal and scanning, and
protected under the LRU lock.
Making it per-cpu does not actually get any concurrency improvements because of
this lock, and summing the counter is much slower, and
incrementing/decrementing it costs more code size and is slower too.
These counters should stay per-LRU, which currently means global.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
This is a nasty and error prone API. It is no longer used, remove it.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
d_validate has been broken for a long time.
kmem_ptr_validate does not guarantee that a pointer can be dereferenced
if it can go away at any time. Even rcu_read_lock doesn't help, because
the pointer might be queued in RCU callbacks but not executed yet.
So the parent cannot be checked, nor the name hashed. The dentry pointer
can not be touched until it can be verified under lock. Hashing simply
cannot be used.
Instead, verify the parent/child relationship by traversing parent's
d_child list. It's slow, but only ncpfs and the destaged smbfs care
about it, at this point.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6
* 'omap-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tmlind/linux-omap-2.6: (243 commits)
omap2: Make OMAP2PLUS select OMAP_DM_TIMER
OMAP4: hwmod data: Fix alignment and end of line in structurefields
OMAP4: hwmod data: Move the DMA structures
OMAP4: hwmod data: Move the smartreflex structures
OMAP4: hwmod data: Fix missing SIDLE_SMART_WKUP in smartreflexsysc
arm: omap: tusb6010: add name for MUSB IRQ
arm: omap: craneboard: Add USB EHCI support
omap2+: Initialize serial port for dynamic remuxing for n8x0
omap2+: Add struct omap_board_data and use it for platform level serial init
omap2+: Allow hwmod state changes to mux pads based on the state changes
omap2+: Add support for hwmod specific muxing of devices
omap2+: Add omap_mux_get_by_name
OMAP2: PM: fix compile error when !CONFIG_SUSPEND
MAINTAINERS: OMAP: hwmod: update hwmod code, data maintainership
OMAP4: Smartreflex framework extensions
OMAP4: hwmod: Add inital data for smartreflex modules.
OMAP4: PM: Program correct init voltages for scalable VDDs
OMAP4: Adding voltage driver support
OMAP4: Register voltage PMIC parameters with the voltage layer
OMAP3: PM: Program correct init voltages for VDD1 and VDD2
...
Fix up trivial conflict in arch/arm/plat-omap/Kconfig
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6
* 'v4l_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mchehab/linux-2.6: (255 commits)
[media] radio-aimslab.c: Fix gcc 4.5+ bug
[media] cx25821: Fix compilation breakage due to BKL dependency
[media] v4l2-compat-ioctl32: fix compile warning
[media] zoran: fix compiler warning
[media] tda18218: fix compile warning
[media] ngene: fix compile warning
[media] DVB: IR support for TechnoTrend CT-3650
[media] cx23885, cimax2.c: Fix case of two CAM insertion irq
[media] ir-nec-decoder: fix repeat key issue
[media] staging: se401 depends on USB
[media] staging: usbvideo/vicam depends on USB
[media] soc_camera: Add the ability to bind regulators to soc_camedra devices
[media] V4L2: Add a v4l2-subdev (soc-camera) driver for OmniVision OV2640 sensor
[media] v4l: soc-camera: switch to .unlocked_ioctl
[media] v4l: ov772x: simplify pointer dereference
[media] ov9640: fix OmniVision OV9640 sensor driver's priv data retrieving
[media] ov9640: use macro to request OmniVision OV9640 sensor private data
[media] ivtv-i2c: Fix two warnings
[media] staging/lirc: Update lirc TODO files
[media] cx88: Remove the obsolete i2c_adapter.id field
...
|
|
* 'devel' of master.kernel.org:/home/rmk/linux-2.6-arm: (416 commits)
ARM: DMA: add support for DMA debugging
ARM: PL011: add DMA burst threshold support for ST variants
ARM: PL011: Add support for transmit DMA
ARM: PL011: Ensure IRQs are disabled in UART interrupt handler
ARM: PL011: Separate hardware FIFO size from TTY FIFO size
ARM: PL011: Allow better handling of vendor data
ARM: PL011: Ensure error flags are clear at startup
ARM: PL011: include revision number in boot-time port printk
ARM: vexpress: add sched_clock() for Versatile Express
ARM i.MX53: Make MX53 EVK bootable
ARM i.MX53: Some bug fix about MX53 MSL code
ARM: 6607/1: sa1100: Update platform device registration
ARM: 6606/1: sa1100: Fix platform device registration
ARM i.MX51: rename IPU irqs
ARM i.MX51: Add ipu clock support
ARM: imx/mx27_3ds: Add PMIC support
ARM: DMA: Replace page_to_dma()/dma_to_page() with pfn_to_dma()/dma_to_pfn()
mx51: fix usb clock support
MX51: Add support for usb host 2
arch/arm/plat-mxc/ehci.c: fix errors/typos
...
|
|
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/sparc-next-2.6: (25 commits)
atyfb: Fix bootup hangs on sparc64.
sparc: update copyright in piggyback.c
sparc: unify strip command in boot/Makefile
sparc: rename piggyback_32 to piggyback
sparc: fix tftpboot.img for sparc64 on little-endian host
sparc: add $BITS to piggyback arguments
sparc: remove obsolete ELF support in piggyback_32.c
sparc: additional comments to piggyback_32.c
sparc: use _start for the start entry (like 64 bit does)
sparc: use trapbase in setup_arch
sparc: refactor piggy_32.c
Added support for ampopts in APBUART driver. Used in AMP systems.
APBUART: added raw AMBA vendor/device number to match against.
SPARC/LEON: avoid AMBAPP name duplicates in openprom fs when REG is missing
SPARC/LEON: added support for selecting Timer Core and Timer within core
LEON: added raw AMBA vendor/device number to find TIMER, IRQCTRL
SPARC/LEON: added support for IRQAMP IRQ Controller
SPARC/LEON: find IRQCTRL and Timer via OF-Tree, instead of hardcoded.
sparc: fix sparse warnings in arch/sparc/prom for 32 bit build
sparc: remove unused prom tree functions
...
|
|
Conflicts:
arch/arm/mach-pxa/clock.c
arch/arm/mach-pxa/clock.h
|
|
|
|
Conflicts:
arch/arm/Kconfig
arch/arm/common/Makefile
arch/arm/kernel/Makefile
arch/arm/kernel/smp.c
|
|
Conflicts:
arch/arm/kernel/entry-armv.S
arch/arm/mm/ioremap.c
|
|
Add ARM support for the DMA debug infrastructure, which allows the
DMA API usage to be debugged.
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
|
|
* 'for-linus' of git://codeaurora.org/quic/kernel/davidb/linux-msm: (35 commits)
mmc: msm_sdcc: Check for only DATA_END interrupt to end a request
mmc: msm_sdcc: Fix bug in PIO mode when data size is not word aligned
mmc: msm_sdcc: Reset SDCC in case of data transfer errors
mmc: msm_sdcc: Add prog done interrupt support
mmc: msm_sdcc: Fix possible circular locking dependency warning
MSM: Add USB support for MSM7x30
MSM: Add USB suport for QSD8x50
msm: initial framebuffer support
msm: add handling for clocks tagged as CLK_MINMAX
msm: trout: change name of pmdh_clk to mddi_clk
msm: add CLK_MINMAX to pmdh_clk
msm: trout: add gpio_to_irq
msm: iommu: Use the correct memory allocation flag
msm_serial: Remove redundant unlikely()
msm: iommu: Miscellaneous code cleanup
msm: iommu: Support cache-coherent memory access
msm: iommu: Definitions for extended memory attributes
msm: iommu: Kconfig dependency for the IOMMU API
msm: iommu: Check if device is already attached
msm: iommu: Kconfig item for cacheable page tables
...
|
|
* git://git.kernel.org/pub/scm/linux/kernel/git/lethal/fbdev-2.6: (55 commits)
video: udlfb: Kill off special printk wrappers, use pr_fmt().
video: udlfb: Kill off some magic constants for EDID sizing.
video: udlfb: deifdefify (yes, that's a word).
fbdev: modedb: Add a new mode for 864x480 TAAL panels.
drivers/video/i810/i810-i2c.c: fix i2c bus handling
video: Fix the HGA framebuffer driver
drivers/video/carminefb.c: improve error handling
video: imxfb: Fix the maximum value for yres
fbdev: sh_mobile_lcdcfb: Enable 32 bpp and 24 bpp support
fbdev: sh_mipi_dsi: use platform provided register layout and values
ARM: mach-shmobile: specify sh7372 MIPI DSI register layout
fbdev: sh_mipi_dsi: support different register layouts
ARM: mach-shmobile: improve MIPI DSI clock configuration
fbdev: sh-mobile: implement MIPI DSI runtime PM support
sisfb: eliminate compiler warnings
sisfb: delete unused register I/O macros
sisfb: replace setSISIDXREG with SiS_SetRegANDOR
sisfb: replace andSISIDXREG with SiS_SetRegAND
sisfb: replace orSISIDXREG with SiS_SetRegOR
sisfb: replace outSISIDXREG with SiS_SetReg
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6
* 'sh-latest' of git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6:
sh: include Migo-R TS driver in Migo-R defconfig
sh: correct definitions to access stack pointers
sh: Tidy up SH-4A unaligned load support.
dma: shdma: NMI support.
sh: mach-sdk7786: Handle baseboard NMI source selection.
sh: mach-rsk: Add polled GPIO buttons support for RSK+7203.
sh: Break out cpuinfo_op procfs bits.
sh: Enable optional gpiolib for all CPUs with pinmux tables.
sh: migrate SH_CLK_MD to mode pin API.
sh: machvec IO death.
|
|
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1436 commits)
cassini: Use local-mac-address prom property for Cassini MAC address
net: remove the duplicate #ifdef __KERNEL__
net: bridge: check the length of skb after nf_bridge_maybe_copy_header()
netconsole: clarify stopping message
netconsole: don't announce stopping if nothing happened
cnic: Fix the type field in SPQ messages
netfilter: fix export secctx error handling
netfilter: fix the race when initializing nf_ct_expect_hash_rnd
ipv4: IP defragmentation must be ECN aware
net: r6040: Return proper error for r6040_init_one
dcb: use after free in dcb_flushapp()
dcb: unlock on error in dcbnl_ieee_get()
net: ixp4xx_eth: Return proper error for eth_init_one
include/linux/if_ether.h: Add #define ETH_P_LINK_CTL for HPNA and wlan local tunnel
net: add POLLPRI to sock_def_readable()
af_unix: Avoid socket->sk NULL OOPS in stream connect security hooks.
net_sched: pfifo_head_drop problem
mac80211: remove stray extern
mac80211: implement off-channel TX using hw r-o-c offload
mac80211: implement hardware offload for remain-on-channel
...
|
|
Fallback on the local-mac-address prom property if the Cassini device
does not have an address programmed in the VPD ROM. This uses the same
technique as implemented by the sungem driver.
The problem was reported by Frans van Berckel using Debian kernel 2.6.34-7
on Sun Fire V440. udev was assigning a new eth<n> device name on each reboot
because the cassini driver was using a random MAC address.
Fix tested on 2.6.34-7 and 2.6.37 Sun Fire V440. Compile tested against
2.6.36 davem/sparc-2.6.git
Reported-by: Frans van Berckel <fberckel@xs4all.nl>
Tested-by: Frans van Berckel <fberckel@xs4all.nl>
Reviewed-by: Julian Calaby <julian.calaby@gmail.com>
Reviewed-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Richard Mortimer <richm@oldelvet.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
|
Since we are already in #ifdef __KERNEL__, we don't need to check it
again.
Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
|
