04 Feb, 2010
1 commit
-
hrtimers callbacks are always done from hardirq context, either the
jiffy tick interrupt or the hrtimer device interrupt.[ there is currently one exception that can still call a hrtimer
callback from softirq, but even in that case this will still
work correctly. ]Reported-by: Wei Yongjun
Signed-off-by: Peter Zijlstra
Cc: Yury Polyanskiy
Tested-by: Wei Yongjun
Acked-by: David S. Miller
LKML-Reference:
Signed-off-by: Thomas Gleixner
03 Feb, 2010
31 commits
-
…s/security-testing-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/security-testing-2.6:
kernel/cred.c: use kmem_cache_free -
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (23 commits)
connector: Delete buggy notification code.
be2net: use eq-id to calculate cev-isr reg offset
Bluetooth: Use the control channel for raw HID reports
Bluetooth: Add DFU driver for Atheros Bluetooth chipset AR3011
Bluetooth: Redo checks in IRQ handler for shared IRQ support
Bluetooth: Fix memory leak in L2CAP
Bluetooth: Remove double free of SKB pointer in L2CAP
cdc_ether: Partially revert "usbnet: Set link down initially ..."
be2net: Fix memset() arg ordering.
bonding: bond_open error return value
ixgbe: if ixgbe_copy_dcb_cfg is going to fail learn about it early
ixgbe: set the correct DCB bit for pg tx settings
igbvf: fix issue w/ mapped_as_page being left set after unmap
drivers/net: ks8851_mll ethernet network driver
be2net: Bug fix to support newer generation of BE ASIC
starfire: clean up properly if firmware loading fails
mac80211: fix NULL pointer dereference when ftrace is enabled
netfilter: ctnetlink: fix expectation mask dump
ipv6: conntrack: Add member of user to nf_ct_frag6_queue structure
ath9k: fix eeprom INI values override for 2GHz-only cards
... -
This is the counterpart to cba767175becadc5c4016cceb7bfdd2c7fe722f4
("pktcdvd: remove broken dev_t export of class devices"). Device is not
registered using dev_t, so it should not be destroyed using device_destroy
which looks up the device by dev_t. This will fail and adding the device
again will fail with the "duplicate name" error. This is fixed using
device_unregister instead of device_destroy.Signed-off-by: Thadeu Lima de Souza Cascardo
Cc: Kay Sievers
Cc: Peter Osterlund
Cc: Al Viro
Cc: Jens Axboe
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Newly added memory can not be accessed via /dev/mem, because we do not
update the variables high_memory, max_pfn and max_low_pfn.Add a function update_end_of_memory_vars() to update these variables for
64-bit kernels.[akpm@linux-foundation.org: simplify comment]
Signed-off-by: Shaohui Zheng
Cc: Andi Kleen
Cc: Li Haicheng
Reviewed-by: Wu Fengguang
Reviewed-by: KAMEZAWA Hiroyuki
Cc: Ingo Molnar
Cc: Thomas Gleixner
Cc: "H. Peter Anvin"
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
init_fault_attr_entries() should be init_fault_attr_dentries().
cleanup_fault_attr_entries() should be cleanup_fault_attr_dentries().
Signed-off-by: Anton Blanchard
Acked-by: Akinobu Mita
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
hugetlb_sysfs_add_hstate is called by hugetlb_register_node directly
during init and also indirectly via sysfs after init.This patch removes the __init tag from hugetlb_sysfs_add_hstate.
Signed-off-by: Jeff Mahoney
Cc: Lee Schermerhorn
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Move the ulite_console_setup to the .devinit section since it might be
called on probe, which is in devinit. Fixes the crash below where the
uartlite hw is probed after the .init section is freed from the kernel.uartlite: ttyUL0 at MMIO 0xc8000100 (irq = 30) is a uartlite
BUG: unable to handle kernel NULL pointer dereference at (null)
IP: [] ulite_console_setup+0x6f/0xa8
*pdpt = 0000000036fb0001 *pde = 0000000000000000
Oops: 0000 [#1] PREEMPT SMP
last sysfs file: /sys/devices/pci0000:00/0000:00:1f.1/host0/uevent
Modules linked in: puffin(+) serio_rawPid: 151, comm: modprobe Not tainted (2.6.31.5-1.0.b1-b1 #1) POULSBO
EIP: 0060:[] EFLAGS: 00010246 CPU: 0
EIP is at ulite_console_setup+0x6f/0xa8
EAX: c16ec824 EBX: c16ec824 ECX: c176719f EDX: 00000000
ESI: 00000000 EDI: c17b42c4 EBP: f6fd1cf0 ESP: f6fd1cd8
DS: 007b ES: 007b FS: 00d8 GS: 0033 SS: 0068
Process modprobe (pid: 151, ti=f6fd0000 task=f6fa1020 task.ti=f6fd0000)
Stack:
c1031f51 00000000 00000000 00000246 c182237c f7742000 f6fd1d5c c11fd316
c16ec85c f77420d4 0000001e 00000000 00000000 c1633e78 4f494d4d 63783020
30303038 00303031 f6fd1d3c c10e0786 f6fd1d48 00000000 f6fd1d48 00000000
Call Trace:
[] ? register_console+0xf6/0x1fc
[] ? uart_add_one_port+0x237/0x2bb
[] ? sysfs_add_one+0x13/0xd3
[] ? sysfs_do_create_link+0xba/0xfc
[] ? ulite_probe+0x198/0x1eb
[] ? platform_drv_probe+0xc/0xe
[] ? driver_probe_device+0x79/0x105
[] ? __device_attach+0x28/0x30
[] ? bus_for_each_drv+0x3d/0x67
[] ? device_attach+0x44/0x58
[] ? __device_attach+0x0/0x30
[] ? bus_probe_device+0x1f/0x34
[] ? device_add+0x385/0x4c0
[] ? _write_unlock+0x8/0x1f
[] ? platform_device_add+0xd9/0x11c
[] ? mfd_add_devices+0x165/0x1bc
[] ? puffin_probe+0x2d0/0x390 [puffin]
[] ? pci_match_device+0xa0/0xa7
[] ? local_pci_probe+0xe/0x10
[] ? pci_device_probe+0x43/0x66
[] ? driver_probe_device+0x79/0x105
[] ? __driver_attach+0x43/0x5f
[] ? bus_for_each_dev+0x3d/0x67
[] ? driver_attach+0x14/0x16
[] ? __driver_attach+0x0/0x5f
[] ? bus_add_driver+0xf9/0x220
[] ? driver_register+0x8b/0xeb
[] ? __pci_register_driver+0x43/0x9f
[] ? __blocking_notifier_call_chain+0x40/0x4c
[] ? puffin_init+0x0/0x48 [puffin]
[] ? puffin_init+0x17/0x48 [puffin]
[] ? do_one_initcall+0x4c/0x131
[] ? sys_init_module+0xa7/0x1b7
[] ? syscall_call+0x7/0xb
Code: 6e 74 00 00 00 92 33 00 00 18 00 0e 01 73 79 6e 63 65 2d 72 65 67 69 73 74 72 79 0c 00 49 32
00 00 14 00 09 01 61 6c 73 61 2d 69 66 6f 00 00 00 42 37 00 00 10 00 07 01 6b 69 6c 6c 61 6c 6c
EIP: [] ulite_console_setup+0x6f/0xa8 SS:ESP 0068:f6fd1cd8
CR2: 0000000000000000Signed-off-by: Richard Röjfors
Acked-by: Peter Korsgaard
Cc: Alan Cox
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The probe function passes a pointer to a struct fb_info to
platform_set_drvdata(), so don't interpret the return value of
platform_get_drvdata() as a pointer to struct imxfb_info.The original imxfb_info *fbi backlight_power was NULL but in imxfb_suspend
it was 4 resulting in an oops as imxfb_suspend calls
imxfb_disable_controller(fbi) which in turn hasif (fbi->backlight_power)
fbi->backlight_power(0);Signed-off-by: Uwe Kleine-König
Acked-by: Sascha Hauer
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
In cgroup_create(), if alloc_css_id() returns failure, the errno is not
propagated to userspace, so mkdir will fail silently.To trigger this bug, we mount blkio (or memory subsystem), and create more
then 65534 cgroups. (The number of cgroups is limited to 65535 if a
subsystem has use_id == 1)# mount -t cgroup -o blkio xxx /mnt
# for ((i = 0; i < 65534; i++)); do mkdir /mnt/$i; done
# mkdir /mnt/65534
(should return ENOSPC)
#Signed-off-by: Li Zefan
Acked-by: Serge Hallyn
Acked-by: Paul Menage
Acked-by: KAMEZAWA Hiroyuki
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
When I use markup_oops.pl parse a x8664 oops, I got:
objdump: --start-address: bad number: NaN
No matching code found
This is because:
main::(./m.pl:228): open(FILE, "objdump -dS --adjust-vma=$vmaoffset --start-address=$decodestart --stop-address=$decodestop $filename |") || die "Cannot start objdump";
DB p $decodestart
NaNThis NaN is from:
main::(./m.pl:176): my $decodestart = Math::BigInt->from_hex("0x$target") - Math::BigInt->from_hex("0x$func_offset");
DB p $func_offset
0x175There is already a "0x" in $func_offset, another 0x makes it a NaN.
The $func_offset is from line:
if ($line =~ /RIP: 0010:\[\\] \[\\] ([a-zA-Z0-9\_]+)\+(0x[0-9a-f]+)\/0x[a-f0-9]/) {
$function = $1;
$func_offset = $2;
}I make a patch to change "(0x[0-9a-f]+)\/0x[a-f0-9]/)" to "0x([0-9a-f]+)\/0x[a-f0-9]/)".
Signed-off-by: Hui Zhu
Cc: Arjan van de Ven
Cc: Michal Marek
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
When git has been set to always use color in .gitconfig then I get the
warning messageBad divisor in main::vcs_assign: 0
This is caused by vcs_file_signoffs not matching any commits due to the
pattern not understand the colour codes. Fix this by telling git log to
never use colour.Signed-off-by: Richard Kennedy
Acked-by: Joe Perches
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
write_kmem() used to assume vwrite() always return the full buffer length.
However now vwrite() could return 0 to indicate memory hole. This
creates a bug that "buf" is not advanced accordingly.Fix it to simply ignore the return value, hence the memory hole.
Signed-off-by: Wu Fengguang
Cc: Andi Kleen
Cc: Benjamin Herrenschmidt
Cc: Christoph Lameter
Cc: Ingo Molnar
Cc: Tejun Heo
Cc: Nick Piggin
Cc: KAMEZAWA Hiroyuki
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Otherwise vmalloc_to_page() will BUG().
This also makes the kmem read/write implementation aligned with mem(4):
"References to nonexistent locations cause errors to be returned." Here we
return -ENXIO (inspired by Hugh) if no bytes have been transfered to/from
user space, otherwise return partial read/write results.Signed-off-by: KAMEZAWA Hiroyuki
Signed-off-by: Wu Fengguang
Cc: Greg Kroah-Hartman
Cc: Hugh Dickins
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
The cache alias problem will happen if the changes of user shared mapping
is not flushed before copying, then user and kernel mapping may be mapped
into two different cache line, it is impossible to guarantee the coherence
after iov_iter_copy_from_user_atomic. So the right steps should be:flush_dcache_page(page);
kmap_atomic(page);
write to page;
kunmap_atomic(page);
flush_dcache_page(page);More precisely, we might create two new APIs flush_dcache_user_page and
flush_dcache_kern_page to replace the two flush_dcache_page accordingly.Here is a snippet tested on omap2430 with VIPT cache, and I think it is
not ARM-specific:int val = 0x11111111;
fd = open("abc", O_RDWR);
addr = mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0);
*(addr+0) = 0x44444444;
tmp = *(addr+0);
*(addr+1) = 0x77777777;
write(fd, &val, sizeof(int));
close(fd);The results are not always 0x11111111 0x77777777 at the beginning as expected. Sometimes we see 0x44444444 0x77777777.
Signed-off-by: Anfei
Cc: Russell King
Cc: Miklos Szeredi
Cc: Nick Piggin
Cc:
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix kfifo kernel-doc warnings:
Warning(kernel/kfifo.c:361): No description found for parameter 'total'
Warning(kernel/kfifo.c:402): bad line: @ @lenout: pointer to output variable with copied data
Warning(kernel/kfifo.c:412): No description found for parameter 'lenout'Signed-off-by: Randy Dunlap
Cc: Stefani Seibold
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Add missing braces for multiline 'if' statements in fm3130_probe.
Signed-off-by: Sergey Matyukevich
Signed-off-by: Alessandro Zummo
Cc: Sergey Lapin
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Fix the kernel oops when dev_dbg is called with mx3_fbi->txd == NULL
Fix the late initialisation of mx3fb->backlight_level. If not, in the
chain of function started by init_fb_chan(), in __blank() call
sdc_set_brightness(mx3fb, mx3fb->backlight_level) that will shut down the
CONTRAST PWM output.Signed-off-by: Alberto Panizzo
Acked-by: Guennadi Liakhovetski gmx.de>
Cc: Sascha Hauer
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Eric Paris located a bug in idr. With IDR_BITS of 6, it grows to three
layers when id 4096 is first allocated. When that happens, idr wraps
incorrectly and searches the idr array ignoring the high bits. The
following test code from Eric demonstrates the bug nicely.#include
#include
#includestatic DEFINE_IDR(test_idr);
int init_module(void)
{
int ret, forty95, forty96;
void *addr;/* add 2 entries both with 4095 as the start address */
again1:
if (!idr_pre_get(&test_idr, GFP_KERNEL))
return -ENOMEM;
ret = idr_get_new_above(&test_idr, (void *)4095, 4095, &forty95);
if (ret) {
if (ret == -EAGAIN)
goto again1;
return ret;
}
if (forty95 != 4095)
printk(KERN_ERR "hmmm, forty95=%d\n", forty95);again2:
if (!idr_pre_get(&test_idr, GFP_KERNEL))
return -ENOMEM;
ret = idr_get_new_above(&test_idr, (void *)4096, 4095, &forty96);
if (ret) {
if (ret == -EAGAIN)
goto again2;
return ret;
}
if (forty96 != 4096)
printk(KERN_ERR "hmmm, forty96=%d\n", forty96);/* try to find the 2 entries, noticing that 4096 broke */
addr = idr_find(&test_idr, forty95);
if ((int)addr != forty95)
printk(KERN_ERR "hmmm, after find forty95=%d addr=%d\n", forty95, (int)addr);
addr = idr_find(&test_idr, forty96);
if ((int)addr != forty96)
printk(KERN_ERR "hmmm, after find forty96=%d addr=%d\n", forty96, (int)addr);
/* really weird, the entry which should be at 4096 is actually at 0!! */
addr = idr_find(&test_idr, 0);
if ((int)addr)
printk(KERN_ERR "found an entry at id=0 for addr=%d\n", (int)addr);idr_remove(&test_idr, forty95);
idr_remove(&test_idr, forty96);return 0;
}void cleanup_module(void)
{
}MODULE_AUTHOR("Eric Paris ");
MODULE_DESCRIPTION("Simple idr test");
MODULE_LICENSE("GPL");This happens because when sub_alloc() back tracks it doesn't always do it
step-by-step while the over-the-limit detection assumes step-by-step
backtracking. The logic in sub_alloc() looks like the following.restart:
clear pa[top level + 1] for end cond detection
l = top level
while (true) {
search for empty slot at this level
if (not found) {
push id to the next possible value
l++
A: if (pa[l] is clear)
failed, return asking caller to grow the tree
if (going up 1 level gives more slots to search)
continue the while loop above with the incremented l
else
C: goto restart
}
adjust id accordingly to the found slot
if (l == 0)
return found id;
create lower level if not there yet
record pa[l] and l--
}Test A is the fail exit condition but this assumes that failure is
propagated upwared one level at a time but the B optimization path breaks
the assumption and restarts the whole thing with a start value which is
above the possible limit with the current layers. sub_alloc() assumes the
start id value is inside the limit when called and test A is the only exit
condition check, so it ends up searching for empty slot while ignoring
high set bit.So, for 4095->4096 test, level0 search fails but pa[1] contains a valid
pointer. However, going up 1 level wouldn't give any more empty slot so
it takes C and when the whole thing restarts nobody notices the high bit
set beyond the top level.This patch fixes the bug by changing the fail exit condition check to full
id limit check.Based-on-patch-from: Eric Paris
Reported-by: Eric Paris
Signed-off-by: Tejun Heo
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
On Tue, Feb 02, 2010 at 02:57:14PM -0800, Greg KH (gregkh@suse.de) wrote:
> > There are at least two ways to fix it: using a big cannon and a small
> > one. The former way is to disable notification registration, since it is
> > not used by anyone at all. Second way is to check whether calling
> > process is root and its destination group is -1 (kind of priveledged
> > one) before command is dispatched to workqueue.
>
> Well if no one is using it, removing it makes the most sense, right?
>
> No objection from me, care to make up a patch either way for this?Getting it is not used, let's drop support for notifications about
(un)registered events from connector.
Another option was to check credentials on receiving, but we can always
restore it without bugs if needed, but genetlink has a wider code base
and none complained, that userspace can not get notification when some
other clients were (un)registered.Kudos for Sebastian Krahmer , who found a bug in the
code.Signed-off-by: Evgeniy Polyakov
Acked-by: Greg Kroah-Hartman
Signed-off-by: David S. Miller -
Free memory allocated using kmem_cache_zalloc using kmem_cache_free rather
than kfree.The semantic patch that makes this change is as follows:
(http://coccinelle.lip6.fr/)//
@@
expression x,E,c;
@@x = \(kmem_cache_alloc\|kmem_cache_zalloc\|kmem_cache_alloc_node\)(c,...)
... when != x = E
when != &x
?-kfree(x)
+kmem_cache_free(c,x)
//Signed-off-by: Julia Lawall
Acked-by: David Howells
Cc: James Morris
Cc: Steve Dickson
Cc:
Signed-off-by: Andrew Morton
Signed-off-by: James Morris -
* 'for-linus' of git://git.kernel.dk/linux-2.6-block:
cfq-iosched: Do not idle on async queues
blk-cgroup: Fix potential deadlock in blk-cgroup
block: fix bugs in bio-integrity mempool usage
block: fix bio_add_page for non trivial merge_bvec_fn case
drbd: null dereference bug
drbd: fix max_segment_size initialization -
Improve handling of fragmented per-CPU vmaps. We previously don't free
up per-CPU maps until all its addresses have been used and freed. So
fragmented blocks could fill up vmalloc space even if they actually had
no active vmap regions within them.Add some logic to allow all CPUs to have these blocks purged in the case
of failure to allocate a new vm area, and also put some logic to trim
such blocks of a current CPU if we hit them in the allocation path (so
as to avoid a large build up of them).Christoph reported some vmap allocation failures when using the per CPU
vmap APIs in XFS, which cannot be reproduced after this patch and the
previous bug fix.Cc: linux-mm@kvack.org
Cc: stable@kernel.org
Tested-by: Christoph Hellwig
Signed-off-by: Nick Piggin
--
Signed-off-by: Linus Torvalds -
RCU list walking of the per-cpu vmap cache was broken. It did not use
RCU primitives, and also the union of free_list and rcu_head is
obviously wrong (because free_list is indeed the list we are RCU
walking).While we are there, remove a couple of unused fields from an earlier
iteration.These APIs aren't actually used anywhere, because of problems with the
XFS conversion. Christoph has now verified that the problems are solved
with these patches. Also it is an exported interface, so I think it
will be good to be merged now (and Christoph wants to get the XFS
changes into their local tree).Cc: stable@kernel.org
Cc: linux-mm@kvack.org
Tested-by: Christoph Hellwig
Signed-off-by: Nick Piggin
--
Signed-off-by: Linus Torvalds -
* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6:
random: Remove unused inode variable
crypto: padlock-sha - Add import/export support
random: drop weird m_time/a_time manipulation -
* git://git.kernel.org/pub/scm/linux/kernel/git/steve/gfs2-2.6-fixes:
GFS2: Use GFP_NOFS for alloc structure
GFS2: Fix previous patch
GFS2: Don't withdraw on partial rindex entries
GFS2: Fix refcnt leak on gfs2_follow_link() error path -
* 'sh/for-2.6.33' of git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6:
sh: Fix access to released memory in clk_debugfs_register_one()
sh: Fix access to released memory in dwarf_unwinder_cleanup()
usb: r8a66597-hdc disable interrupts fix
spi: spi_sh_msiof: Fixed data sampling on the correct edge -
* 'upstream' of git://ftp.linux-mips.org/pub/scm/upstream-linus:
MIPS: 64-bit: Detect virtual memory size
MIPS: AR7: Fix USB slave mem range typo
MIPS: Alchemy: Fix dbdma ring destruction memory debugcheck. -
Commit 221af7f87b9 ("Split 'flush_old_exec' into two functions") split
the function at the point of no return - ie right where there were no
more error cases to check. That made sense from a technical standpoint,
but when we then also combined it with the actual personality setting
going in between flush_old_exec() and setup_new_exec(), it needs to be a
bit more careful.In particular, we need to make sure that we really flush the old
personality bits in the 'flush' stage, rather than later in the 'setup'
stage, since otherwise we might be flushing the _new_ personality state
that we're just setting up.So this moves the flags and personality flushing (and 'flush_thread()',
which is the arch-specific function that generally resets lazy FP state
etc) of the old process into flush_old_exec(), so that it doesn't affect
any state that execve() is setting up for the new process environment.This was reported by Michal Simek as breaking his Microblaze qemu
environment.Reported-and-tested-by: Michal Simek
Cc: Peter Anvin
Signed-off-by: Linus Torvalds -
Few weeks back, Shaohua Li had posted similar patch. I am reposting it
with more test results.This patch does two things.
- Do not idle on async queues.
- It also changes the write queue depth CFQ drives (cfq_may_dispatch()).
Currently, we seem to driving queue depth of 1 always for WRITES. This is
true even if there is only one write queue in the system and all the logic
of infinite queue depth in case of single busy queue as well as slowly
increasing queue depth based on last delayed sync request does not seem to
be kicking in at all.This patch will allow deeper WRITE queue depths (subjected to the other
WRITE queue depth contstraints like cfq_quantum and last delayed sync
request).Shaohua Li had reported getting more out of his SSD. For me, I have got
one Lun exported from an HP EVA and when pure buffered writes are on, I
can get more out of the system. Following are test results of pure
buffered writes (with end_fsync=1) with vanilla and patched kernel. These
results are average of 3 sets of run with increasing number of threads.AVERAGE[bufwfs][vanilla]
-------
job Set NR ReadBW(KB/s) MaxClat(us) WriteBW(KB/s) MaxClat(us)
--- --- -- ------------ ----------- ------------- -----------
bufwfs 3 1 0 0 95349 474141
bufwfs 3 2 0 0 100282 806926
bufwfs 3 4 0 0 109989 2.7301e+06
bufwfs 3 8 0 0 116642 3762231
bufwfs 3 16 0 0 118230 6902970AVERAGE[bufwfs] [patched kernel]
-------
bufwfs 3 1 0 0 270722 404352
bufwfs 3 2 0 0 206770 1.06552e+06
bufwfs 3 4 0 0 195277 1.62283e+06
bufwfs 3 8 0 0 260960 2.62979e+06
bufwfs 3 16 0 0 299260 1.70731e+06I also ran buffered writes along with some sequential reads and some
buffered reads going on in the system on a SATA disk because the potential
risk could be that we should not be driving queue depth higher in presence
of sync IO going to keep the max clat low.With some random and sequential reads going on in the system on one SATA
disk I did not see any significant increase in max clat. So it looks like
other WRITE queue depth control logic is doing its job. Here are the
results.AVERAGE[brr, bsr, bufw together] [vanilla]
-------
job Set NR ReadBW(KB/s) MaxClat(us) WriteBW(KB/s) MaxClat(us)
--- --- -- ------------ ----------- ------------- -----------
brr 3 1 850 546345 0 0
bsr 3 1 14650 729543 0 0
bufw 3 1 0 0 23908 8274517brr 3 2 981.333 579395 0 0
bsr 3 2 14149.7 1175689 0 0
bufw 3 2 0 0 21921 1.28108e+07brr 3 4 898.333 1.75527e+06 0 0
bsr 3 4 12230.7 1.40072e+06 0 0
bufw 3 4 0 0 19722.3 2.4901e+07brr 3 8 900 3160594 0 0
bsr 3 8 9282.33 1.91314e+06 0 0
bufw 3 8 0 0 18789.3 23890622AVERAGE[brr, bsr, bufw mixed] [patched kernel]
-------
job Set NR ReadBW(KB/s) MaxClat(us) WriteBW(KB/s) MaxClat(us)
--- --- -- ------------ ----------- ------------- -----------
brr 3 1 837 417973 0 0
bsr 3 1 14357.7 591275 0 0
bufw 3 1 0 0 24869.7 8910662brr 3 2 1038.33 543434 0 0
bsr 3 2 13351.3 1205858 0 0
bufw 3 2 0 0 18626.3 13280370brr 3 4 913 1.86861e+06 0 0
bsr 3 4 12652.3 1430974 0 0
bufw 3 4 0 0 15343.3 2.81305e+07brr 3 8 890 2.92695e+06 0 0
bsr 3 8 9635.33 1.90244e+06 0 0
bufw 3 8 0 0 17200.3 24424392So looks like it might make sense to include this patch.
Thanks
VivekSigned-off-by: Vivek Goyal
Signed-off-by: Jens Axboe -
Linux kernel 2.6.32 and later allocate address space from the top of the
kernel virtual memory address space.This patch implements virtual memory size detection for 64 bit MIPS CPUs
to avoid resulting crashes.Signed-off-by: Guenter Roeck
Cc: linux-mips@linux-mips.org
Patchwork: http://patchwork.linux-mips.org/patch/935/
Reviewed-by: David Daney
Signed-off-by: Ralf Baechle
02 Feb, 2010
8 commits
-
cev-isr reg offset for each function is better calculated using (any) eq-id
alloted to that function instead of using pci-func number(which
does not work in some configurations...)Signed-off-by: Sathya Perla
Signed-off-by: David S. Miller -
Signed-off-by: Marek Skuczynski
Signed-off-by: Paul Mundt -
Signed-off-by: Marek Skuczynski
Acked-by: Matt Fleming
Signed-off-by: Paul Mundt -
This patch improves disable_controller() in the r8a66597-hdc
driver to disable all interrupts and clear status flags. It
also makes sure that disable_controller() is called during
probe(). This fixes the relatively rare case of unexpected
pending interrupts after kexec reboot.Signed-off-by: Magnus Damm
Acked-by: Yoshihiro Shimoda
Signed-off-by: Paul Mundt -
The spi_sh_msiof.c driver presently misconfigures REDG and TEDG. TEDG==0
outputs data at the **rising edge** of the clock and REDG==0 samples data
at the **falling edge** of the clock. Therefore for SPI, TEDG must be
equal to REDG, otherwise the last byte received is not sampled in SPI
mode 3.This brings the driver in line with the SH7723 HW Reference Manual
settings documented in Figures 20.20 and 20.21 ("SPI Clock and data
timing").Signed-off-by: Markus Pietrek
Acked-by: Magnus Damm
Signed-off-by: Paul Mundt -
The previous changeset left behind an unused inode variable.
This patch removes it.Reported-by: Stephen Rothwell
Signed-off-by: Herbert Xu -
As the padlock driver for SHA uses a software fallback to perform
partial hashing, it must implement custom import/export functions.
Otherwise hmac which depends on import/export for prehashing will
not work with padlock-sha.Reported-by: Wolfgang Walter
Signed-off-by: Herbert Xu -
No other driver does anything remotely like this that I know of except
for the tty drivers, and I can't see any reason for random/urandom to do
it. In fact, it's a (trivial, harmless) timing information leak. And
obviously, it generates power- and flash-cycle wasting I/O, especially
if combined with something like hwrngd. Also, it breaks ubifs's
expectations.Signed-off-by: Matt Mackall
Signed-off-by: Herbert Xu
