We're safe to remove the bond->lock use from the arp targets because
arp_rcv_probe no longer acquires bond->lock, only rcu_read_lock.
Also setting the primary slave is safe because noone uses the bond->lock
as a syncing mechanism for that anymore.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Use RCU to protect against slave release, the proc show function will sync
with the bond destruction by the proc locks and the fact that the bond is
released after NETDEV_UNREGISTER which causes the bonding to remove the
proc entry.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is necessary mainly for two bonding call sites: procfs and
sysfs as it was dereferenced without any real protection.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
We can remove the lock/unlock as it's no longer necessary since
RTNL should be held while calling bond_alb_set_mac_address().
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
In 3ad mode the only syncing needed by bond->lock is for the wq
and the recv handler, so change them to use curr_slave_lock.
There're no locking dependencies here as 3ad doesn't use
curr_slave_lock at all.
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
RTNL should be already held in the notifier call so the slave list can
be traversed without a problem, remove the unnecessary bond->lock.
CC: Hariprasad S <hariprasad@chelsio.com>
Signed-off-by: Nikolay Aleksandrov <nikolay@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This enables EMAC Rockchip support on radxa rock boards.
Signed-off-by: Romain Perier <romain.perier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds support for EMAC Rockchip driver on RK3188 SoCs.
Signed-off-by: Romain Perier <romain.perier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This adds the necessary binding documentation for the EMAC Rockchip platform
driver found in RK3066 and RK3188 SoCs.
Signed-off-by: Romain Perier <romain.perier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This patch defines a platform glue layer for Rockchip SoCs which
support arc-emac driver. It ensures that regulator for the rmii is on
before trying to connect to the ethernet controller. It applies right
speed and mode changes to the grf when ethernet settings change.
Signed-off-by: Romain Perier <romain.perier@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Pull cifs/smb3 fixes from Steve French:
"This includes various cifs and smb3 bug fixes including those for bugs
found with the recently updated xfstests.
Also I am working fixes for two additional cifs problems found by
xfstests which I plan to send later (when reviewed and run additional
tests)"
* 'for-next-3.17' of git://git.samba.org/sfrench/cifs-2.6:
Clarify Kconfig help text for CIFS and SMB2/SMB3
CIFS: Fix wrong filename length for SMB2
CIFS: Fix wrong restart readdir for SMB1
CIFS: Fix directory rename error
cifs: No need to send SIGKILL to demux_thread during umount
cifs: Allow directIO read/write during cache=strict
cifs: remove unneeded check of null checking in if condition
cifs: fix a possible use of uninit variable in SMB2_sess_setup
cifs: fix memory leak when password is supplied multiple times
cifs: fix a possible null pointer deref in decode_ascii_ssetup
Trivial whitespace fix
Daniel Borkmann says:
====================
BPF updates
[ Set applies on top of current net-next but also on top of
Alexei's latest patches. Please see individual patches for
more details. ]
Changelog:
v1->v2:
- Removed paragraph in 1st commit message
- Rest stays the same
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Reported by Mikulas Patocka, kmemcheck currently barks out a
false positive since we don't have special kmemcheck annotation
for bitfields used in bpf_prog structure.
We currently have jited:1, len:31 and thus when accessing len
while CONFIG_KMEMCHECK enabled, kmemcheck throws a warning that
we're reading uninitialized memory.
As we don't need the whole bit universe for pages member, we
can just split it to u16 and use a bool flag for jited instead
of a bitfield.
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This is the ARM variant for 314beb9bca ("x86: bpf_jit_comp: secure bpf
jit against spraying attacks").
It is now possible to implement it due to commits 75374ad47c ("ARM: mm:
Define set_memory_* functions for ARM") and dca9aa92fc ("ARM: add
DEBUG_SET_MODULE_RONX option to Kconfig") which added infrastructure for
this facility.
Thus, this patch makes sure the BPF generated JIT code is marked RO, as
other kernel text sections, and also lets the generated JIT code start
at a pseudo random offset instead on a page boundary. The holes are filled
with illegal instructions.
JIT tested on armv7hl with BPF test suite.
Reference: http://mainisusuallyafunction.blogspot.com/2012/11/attacking-hardened-linux-systems-with.html
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Mircea Gherzan <mgherzan@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Introduced in commit 314beb9bca ("x86: bpf_jit_comp: secure bpf jit
against spraying attacks") and later on replicated in aa2d2c73c2
("s390/bpf,jit: address randomize and write protect jit code") for
s390 architecture, write protection for BPF JIT images got added and
a random start address of the JIT code, so that it's not on a page
boundary anymore.
Since both use a very similar allocator for the BPF binary header,
we can consolidate this code into the BPF core as it's mostly JIT
independant anyway.
This will also allow for future archs that support DEBUG_SET_MODULE_RONX
to just reuse instead of reimplementing it.
JIT tested on x86_64 and s390x with BPF test suite.
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Acked-by: Alexei Starovoitov <ast@plumgrid.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Alexander Duyck reported high false sharing on dst refcount in tcp stack
when prequeue is used. prequeue is the mechanism used when a thread is
blocked in recvmsg()/read() on a TCP socket, using a blocking model
rather than select()/poll()/epoll() non blocking one.
We already try to use RCU in input path as much as possible, but we were
forced to take a refcount on the dst when skb escaped RCU protected
region. When/if the user thread runs on different cpu, dst_release()
will then touch dst refcount again.
Commit 093162553c (tcp: force a dst refcount when prequeue packet)
was an example of a race fix.
It turns out the only remaining usage of skb->dst for a packet stored
in a TCP socket prequeue is IP early demux.
We can add a logic to detect when IP early demux is probably going
to use skb->dst. Because we do an optimistic check rather than duplicate
existing logic, we need to guard inet_sk_rx_dst_set() and
inet6_sk_rx_dst_set() from using a NULL dst.
Many thanks to Alexander for providing a nice bug report, git bisection,
and reproducer.
Tested using Alexander script on a 40Gb NIC, 8 RX queues.
Hosts have 24 cores, 48 hyper threads.
echo 0 >/proc/sys/net/ipv4/tcp_autocorking
for i in `seq 0 47`
do
for j in `seq 0 2`
do
netperf -H $DEST -t TCP_STREAM -l 1000 \
-c -C -T $i,$i -P 0 -- \
-m 64 -s 64K -D &
done
done
Before patch : ~6Mpps and ~95% cpu usage on receiver
After patch : ~9Mpps and ~35% cpu usage on receiver.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Alexander Duyck <alexander.h.duyck@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
ForcePads are found on HP EliteBook 1040 laptops. They lack any kind of
physical buttons, instead they generate primary button click when user
presses somewhat hard on the surface of the touchpad. Unfortunately they
also report primary button click whenever there are 2 or more contacts
on the pad, messing up all multi-finger gestures (2-finger scrolling,
multi-finger tapping, etc). To cope with this behavior we introduce a
delay (currently 50 msecs) in reporting primary press in case more
contacts appear.
Cc: stable@vger.kernel.org
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
When trying to use the matrix-keypad driver with GPIO drivers that
require nested irq handlers (e.g. I2C GPIO adapters like PCA9554),
request_irq() fails because the GPIO driver requires a threaded
interrupt handler.
Use request_any_context_irq() to be able to use any GPIO driver as
keypad driver.
Signed-off-by: Lothar Waßmann <LW@KARO-electronics.de>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
In the case where the CHG/interrupt line mode is not configured correctly,
this warning is output to dmesg output for each interrupt. Downgrade the
message to debug.
Signed-off-by: Nick Dyer <nick.dyer@itdev.co.uk>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
If the remote side is not distributing its IRK but is distributing the
CSRK the next PDU after master identification is the Signing
Information. This patch fixes a missing SMP_ALLOW_CMD() for this in the
smp_cmd_master_ident() function.
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
The leon_dma_ops struct is needed for leon regardless of PCI configuration.
Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This makes sure that leon_cycles_offset takes the pending bit into
account and that leon_clear_clock_irq clears the pending bit. Otherwise,
if leon_cycles_offset is executed after the timer has wrapped but before
timer_interrupt has increased timer_cs_internal_counter, time can be
perceived to go backwards.
Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
This makes memset follow the standard (instead of returning 0 on success). This
is needed when certain versions of gcc optimizes around memset calls and assume
that the address argument is preserved in %o0.
Signed-off-by: Andreas Larsson <andreas@gaisler.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
After merging the wireless-next tree, today's linux-next build (powerpc
allyesconfig) failed like this:
drivers/net/wireless/ath/ath5k/debug.c: In function 'open_file_eeprom':
drivers/net/wireless/ath/ath5k/debug.c:933:2: error: implicit declaration of function 'vmalloc' [-Werror=implicit-function-declaration]
buf = vmalloc(eesize);
^
drivers/net/wireless/ath/ath5k/debug.c:933:6: warning: assignment makes pointer from integer without a cast
buf = vmalloc(eesize);
^
drivers/net/wireless/ath/ath5k/debug.c:960:2: error: implicit declaration of function 'vfree' [-Werror=implicit-function-declaration]
vfree(buf);
^
Caused by commit db906eb210 ("ath5k: added debugfs file for dumping
eeprom"). Also reported by Guenter Roeck.
I have used Geert Uytterhoeven's suggested fix of including vmalloc.h
and so added this patch for today:
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Mon, 8 Sep 2014 18:39:23 +1000
Subject: [PATCH] ath5k: fix debugfs addition
Reported-by: Guenter Roeck <linux@roeck-us.net>
Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
The 32-bit defconfig version has these enabled
for years so make the 64-bit defconfig have them too.
This patch only adds CONFIG_VIRT_DRIVERS,
CONFIG_FSL_HV_MANAGER and CONFIG_PPC_EPAPR_HV_BYTECHAN
other changes being "make savedefconfig" artifacts.
Signed-off-by: Laurentiu Tudor <Laurentiu.Tudor@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
T1042RDB_PI is Freescale Reference Design Board supporting the T1042
QorIQ Power Architecture™ processor. T1042 is a reduced personality
of T1040 SoC without Integrated 8-port Gigabit. The board is designed
with low power features targeted for Printing Image Market.
T1042RDB_PI is similar to T1040RDB board with few differences like
it has video interface, supports T1042 personality only
T1042RDB_PI board Overview
-----------------------
- SERDES Connections, 8 lanes supporting:
- PCI
- SATA 2.0
- DDR Controller
- Supports rates of up to 1600 MHz data-rate
- Supports one DDR3LP UDIMM
-IFC/Local Bus
- NAND flash: 1GB 8-bit NAND flash
- NOR: 128MB 16-bit NOR Flash
- Ethernet
- Two on-board RGMII 10/100/1G ethernet ports.
- PHY #0 remains powered up during deep-sleep
- CPLD
- Clocks
- System and DDR clock (SYSCLK, “DDRCLK”)
- SERDES clocks
- Power Supplies
- USB
- Supports two USB 2.0 ports with integrated PHYs
- Two type A ports with 5V@1.5A per port.
- SDHC
- SDHC/SDXC connector
- SPI
- On-board 64MB SPI flash
- I2C
- Device connected: EEPROM, thermal monitor, VID controller, RTC
- Other IO
- Two Serial ports
- ProfiBus port
Add support for T1042RDB_PI board:
-add device tree
-Add entry in corenet_generic.c, as it is similar to other corenet platforms
Signed-off-by: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
T1040/T1042RDB is Freescale Reference Design Board.
The board can support both T1040/T1042 QorIQ Power Architecture™ processor.
T1040/T1042RDB board Overview
-----------------------
- SERDES Connections, 8 lanes supporting:
- PCI
- SGMII
- QSGMII
- SATA 2.0
- DDR Controller
- Supports rates of up to 1600 MHz data-rate
- Supports one DDR3LP UDIMM
-IFC/Local Bus
- NAND flash: 1GB 8-bit NAND flash
- NOR: 128MB 16-bit NOR Flash
- Ethernet
- Two on-board RGMII 10/100/1G ethernet ports.
- PHY #0 remains powered up during deep-sleep
- CPLD
- Clocks
- System and DDR clock (SYSCLK, “DDRCLK”)
- SERDES clocks
- Power Supplies
- USB
- Supports two USB 2.0 ports with integrated PHYs
- Two type A ports with 5V@1.5A per port.
- SDHC
- SDHC/SDXC connector
- SPI
- On-board 64MB SPI flash
- I2C
- Devices connected: EEPROM, thermal monitor, VID controller
- Other IO
- Two Serial ports
- ProfiBus port
Add support for T1040/T1042 RDB board:
-add device tree
-add entry in Kconfig to build
-Add entry in corenet_generic.c, as it is similar to other corenet platforms
Signed-off-by: Priyanka Jain <Priyanka.Jain@freescale.com>
Signed-off-by: Poonam Aggrwal <poonam.aggrwal@freescale.com>
Signed-off-by: Prabhakar Kushwaha <prabhakar@freescale.com>
Signed-off-by: Scott Wood <scottwood@freescale.com>
Add the helper function to what the mcount trampoline is to call
for a ftrace_ops function. This helper will be used by arch code
in the future to set up dynamic trampolines. But as this does the
same tests that are performed in choosing what function to call for
the default mcount trampoline, might as well use it to clean up
the existing code.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
Add M6 and M7 chip type in cpumap.c to correctly build CPU distribution map that spans all online CPUs.
Signed-off-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
The following patch adds support for correctly
recognising M6 and M7 cpu type.
Signed-off-by: Allen Pais <allen.pais@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
If application throws negative value of lseek with SEEK_DATA|SEEK_HOLE,
previous f2fs went into BUG_ON in get_dnode_of_data, which was reported
by Tommi Rantala.
He could make a simple code to detect this having:
lseek(fd, -17595150933902LL, SEEK_DATA);
This patch should resolve that bug.
Reported-by: Tommi Rentala <tt.rantala@gmail.com>
[Jaegeuk Kim: relocate the condition as suggested by Chao]
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
When vpif is compiled as module, those errors happen:
ERROR: "vpif_lock" [drivers/media/platform/davinci/vpif_display.ko] undefined!
ERROR: "vpif_lock" [drivers/media/platform/davinci/vpif_capture.ko] undefined!
That's because vpif_lock symbol is not exported.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
ERROR: "__bad_ndelay" [drivers/media/platform/s5p-jpeg/s5p-jpeg.ko] undefined!
That happens because asm-generic doesn't like any ndelay time
bigger than 20us.
Currently, usleep_range() couldn't simply be used, since
exynos4_jpeg_sw_reset() is called with a spinlock held.
So, let's use udelay() instead.
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
This driver depends on a legacy OMAP DMA API. So, it won't
compile-test on other archs.
While we might add stubs to the functions, this is not a
good idea, as the hole API should be replaced.
So, for now, let's just remove COMPILE_TEST and wait for
some time for people to fix. If not fixed, then we'll end
by removing this driver as a hole.
Acked-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
Add Device Tree binding documentation for the clocks
outputs in the Maxim 77802 Power Management IC.
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
The MAX77802 PMIC has two 32.768kHz Buffered Clock Outputs with
Low Jitter Mode. This patch adds support for these two clocks.
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
Like most clock drivers, the Maxim 77686 PMIC clock binding
follows the convention that the "#clock-cells" property is
used to specify the number of cells in a clock provider.
But the binding document is not clear enough that it shall
be set to 1 since the PMIC support multiple clocks outputs.
Also, explain that the clocks identifiers are defined in a
header file that can be included by Device Tree source with
client nodes to avoid using magic numbers.
Finally, add "clock-output-names" as an optional property
since now is supported by the clock driver.
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Doug Anderson <dianders@chromium.org>
Reviewed-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
Clocks drivers for Maxim PMIC are very similar so they can
be converted to use the generic Maxim clock driver.
Also, while being there use module_platform_driver() helper
macro to eliminate more boilerplate code.
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
Maxim Integrated Power Management ICs are very similar with
regard to their clock outputs. Most of the clock drivers for
these chips are duplicating code and are simpler enough that
can be converted to use a generic driver to consolidate code
and avoid duplication.
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
This patch adds a dt-binding include for Maxim 77686
PMIC clock IDs that can be used by both the max77686
clock driver and Device Tree source files.
Signed-off-by: Javier Martinez Canillas <javier.martinez@collabora.co.uk>
Reviewed-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Reviewed-by: Mike Turquette <mturquette@linaro.org>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
Since commit 54196ccbe0 (of: consolidate linker section OF match table
declarations) which went into 3.16-rc1 the following compiler warning is
generated:
In file included from drivers/clk/clk-efm32gg.c:12:0: include/linux/of.h:772:20:
warning: comparison of distinct pointer types lacks a cast [enabled by default]
.data = (fn == (fn_type)NULL) ? fn : fn }
^
include/linux/of.h:785:3: note: in expansion of macro '_OF_DECLARE'
_OF_DECLARE(table, name, compat, fn, of_init_fn_1)
^
include/linux/clk-provider.h:545:42: note: in expansion of macro 'OF_DECLARE_1'
#define CLK_OF_DECLARE(name, compat, fn) OF_DECLARE_1(clk, name, compat, fn)
^
drivers/clk/clk-efm32gg.c:81:1: note: in expansion of macro 'CLK_OF_DECLARE'
CLK_OF_DECLARE(efm32ggcmu, "efm32gg,cmu", efm32gg_cmu_init);
^
Fix it by making efm32gg_cmu_init return void.
Cc: Rob Herring <robh@kernel.org>
Reported-by: Bryan Hundven <bryanhundven@gmail.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Mike Turquette <mturquette@linaro.org>
In gc_node_segment, if node page gc is run concurrently with node page
writeback, and check_valid_map and get_node_page run after page locked
and before cur_valid_map is updated as below, it is possible for the
page to be written twice unnecessarily.
sync_node_pages
try_lock_page
...
check_valid_map f2fs_write_node_page
...
write_node_page
do_write_page
allocate_data_block
...
refresh_sit_entry /* update cur_valid_map */
...
...
unlock_page
get_node_page
...
set_page_dirty
...
f2fs_put_page
unlock_page
This can be solved via calling check_valid_map after get_node_page again.
Signed-off-by: Huang, Ying <ying.huang@intel.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
We use flush cmd control to collect many flush cmds, and flush them
together. In this case, we use two list to manage the flush cmds
(collect and dispatch), and one spin lock is used to protect this.
In fact, the lock-less list(llist) is very suitable to this case,
and we use simplify this routine.
-
v2:
-use llist_for_each_entry_safe to fix possible use-after-free issue.
-remove the unused field from struct flush_cmd.
Thanks for Yu's suggestion.
-
Signed-off-by: Gu Zheng <guz.fnst@cn.fujitsu.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
In commit aec71382c6 ("f2fs: refactor flush_nat_entries codes for reducing NAT
writes"), we descripte the issue as below:
"Although building NAT journal in cursum reduce the read/write work for NAT
block, but previous design leave us lower performance when write checkpoint
frequently for these cases:
1. if journal in cursum has already full, it's a bit of waste that we flush all
nat entries to page for persistence, but not to cache any entries.
2. if journal in cursum is not full, we fill nat entries to journal util
journal is full, then flush the left dirty entries to disk without merge
journaled entries, so these journaled entries may be flushed to disk at next
checkpoint but lost chance to flushed last time."
Actually, we have the same problem in using SIT journal area.
In this patch, firstly we will update sit journal with dirty entries as many as
possible. Secondly if there is no space in sit journal, we will remove all
entries in journal and walk through the whole dirty entry bitmap of sit,
accounting dirty sit entries located in same SIT block to sit entry set. All
entry sets are linked to list sit_entry_set in sm_info, sorted ascending order
by count of entries in set. Later we flush entries in set which have fewest
entries into journal as many as we can, and then flush dense set with merged
entries to disk.
In this way we can use sit journal area more effectively, also we will reduce
SIT update, result in gaining in performance and saving lifetime of flash
device.
In my testing environment, it shows this patch can help to reduce SIT block
update obviously.
virtual machine + hard disk:
fsstress -p 20 -n 400 -l 5
sit page num cp count sit pages/cp
based 2006.50 1349.75 1.486
patched 1566.25 1463.25 1.070
Our latency of merging op is small when handling a great number of dirty SIT
entries in flush_sit_entries:
latency(ns) dirty sit count
36038 2151
49168 2123
37174 2232
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
sit_i in macro SIT_BLOCK_OFFSET/START_SEGNO is not used, remove it.
Signed-off-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
