Do a similar optimization as earlier for touch_atime. Getting the lock in
mnt_get_write is relatively costly, so try all avenues to avoid it first.
This patch is careful to still only update inode fields inside the lock
region.
This didn't show up in benchmarks, but it's easy enough to do.
[akpm@linux-foundation.org: fix typo in comment]
[hugh.dickins@tiscali.co.uk: fix inverted test of mnt_want_write_file()]
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Valerie Aurora <vaurora@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Some benchmark testing shows touch_atime to be high up in profile logs for
IO intensive workloads. Most likely that's due to the lock in
mnt_want_write(). Unfortunately touch_atime first takes the lock, and
then does all the other tests that could avoid atime updates (like noatime
or relatime).
Do it the other way round -- first try to avoid the update and only then
if that didn't succeed take the lock. That works because none of the
atime avoidance tests rely on locking.
This also eliminates a goto.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Cc: Christoph Hellwig <hch@infradead.org>
Reviewed-by: Valerie Aurora <vaurora@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Hugetlbfs needs to do special things instead of truncate_inode_pages().
Currently, it copied generic_forget_inode() except for
truncate_inode_pages() call which is asking for trouble (the code there
isn't trivial). So create a separate function generic_detach_inode()
which does all the list magic done in generic_forget_inode() and call
it from hugetlbfs_forget_inode().
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Add device-id and inode number for better debugging. This was suggested
by Andreas in one of the threads
http://article.gmane.org/gmane.comp.file-systems.ext4/12062 .
"If anyone has a chance, fixing this error message to be not-useless would
be good... Including the device name and the inode number would help
track down the source of the problem."
Signed-off-by: Manish Katiyar <mkatiyar@gmail.com>
Cc: Andreas Dilger <adilger@sun.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Impact: have simple_read_from_buffer conform to standards
It was brought to my attention by Andrew Morton, Theodore Tso, and H.
Peter Anvin that a read from userspace should only return -EFAULT if
nothing was actually read.
Looking at the simple_read_from_buffer I noticed that this function does
not conform to that rule. This patch fixes that function.
[akpm@linux-foundation.org: simplification suggested by hpa]
[hpa@zytor.com: fix count==0 handling]
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
If you use the kernel argument:
earlyprintk=serial,ttyS0,115200
This will cause a recursive hang printing the same line
again and again:
BIOS-e820: 000000003fff3000 - 0000000040000000 (ACPI data)
BIOS-e820: 00000000e0000000 - 00000000f0000000 (reserved)
BIOS-e820: 00000000fec00000 - 0000000100000000 (reserved)
bootconsole [earlyser0] enabled
Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009
Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009
Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009
Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009
Linux version 2.6.31-07863-gb64ada6 (mingo@sirius) (gcc version 4.3.2 20081105 (Red Hat 4.3.2-7) (GCC) ) #16789 SMP Wed Sep 23 21:09:43 CEST 2009
Instead warn the end user that they specified the device
a second time, and ignore that second console.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Greg KH <gregkh@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <4ABAAB89.1080407@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Inform util/module.c::mod_dso__load_module_paths() that relative
paths do exist in some modules.dep, and make it fail noisily should
it encounter a path that it doesn't understand, or a module it
cannot open.
Reported-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: rostedt@goodmis.org
Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
LKML-Reference: <1253779628.10513.8.camel@marge.simson.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On modern systems, the kernel prints the message
x86 PAT enabled: cpu 0, old 0x7040600070406, new 0x7010600070106
once for every CPU.
This gets kind of ridiculous on huge systems; for example, on a
64-thread system I was lucky enough to get:
dmesg| grep 'PAT enabled' | wc
64 704 5174
There is already a BUG() if non-boot CPUs have PAT capabilities
that don't match the boot CPU, so just print the message on the
boot CPU. (I kept the print after the wrmsrl() that enables PAT,
so that the log output continues to mean that the system survived
enabling PAT on the boot CPU)
Signed-off-by: Roland Dreier <rolandd@cisco.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
LKML-Reference: <adavdj92sso.fsf@cisco.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On modern systems, the kernel prints the message
Skipping synchronization checks as TSC is reliable.
once for every non-boot CPU.
This gets kind of ridiculous on huge systems; for example, on a
64-thread system I was lucky enough to get:
$ dmesg | grep 'TSC is reliable' | wc
63 567 4221
There's no point to doing this for every CPU, since the code is
just checking the boot CPU anyway, so change this to a
printk_once() to make the message appears only once.
Signed-off-by: Roland Dreier <rolandd@cisco.com>
LKML-Reference: <adazl8l2swc.fsf@cisco.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In the unaligned kernel exception fixup case the printk() was ordered
before the copy_from_user(), resulting in a nonsensical instruction
value. This fixes up the ordering properly.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
This adds some sanity checking in the unaligned instruction handler to
verify the instruction size, which enables basic support for 16-bit
fixups on SH-2A parts.
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Instead of remembering to specify DTB= on the make commandline, this commit
allows the much friendlier make simpleImage.<dts>
where <dts>.dts is expected to be found in arch/microblaze/boot/dts/
The resulting vmlinux, with the compiled DTS linked in, will be copied to
boot/simpleImage.<dts>
This mirrors the same functionality as on PowerPC,
albeit achieving it in a slightly different way.
+ strip simpleImage file
The size of output file is very similar to linux.bin.
vmlinux - full elf without fdt blob
simpleImage.<dtb name>.unstrip - full elf with fdt blob
simpleImage.<dtb name> - stripped elf with fdt blob
Add symlink to generic system.dts in platform folder
Signed-off-by: John Williams <john.williams@petalogix.com>
Signed-off-by: Michal Simek <monstr@monstr.eu>
Git commit 79741dd changes idle cputime accounting, but unfortunately
the /proc/uptime file hasn't caught up. Here the idle time calculation
from /proc/stat is copied over.
Signed-off-by: Michael Abbott <michael.abbott@diamond.ac.uk>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Currently the audit subsystem prints uncompressed IPv6 addresses which not
only differs from common usage but also results in ridiculously large audit
strings which is not a good thing. This patch fixes this by simply converting
audit to always print compressed IPv6 addresses.
Old message example:
audit(1253576792.161:30): avc: denied { ingress } for
saddr=0000:0000:0000:0000:0000:0000:0000:0001 src=5000
daddr=0000:0000:0000:0000:0000:0000:0000:0001 dest=35502 netif=lo
scontext=system_u:object_r:unlabeled_t:s15:c0.c1023
tcontext=system_u:object_r:lo_netif_t:s0-s15:c0.c1023 tclass=netif
New message example:
audit(1253576792.161:30): avc: denied { ingress } for
saddr=::1 src=5000 daddr=::1 dest=35502 netif=lo
scontext=system_u:object_r:unlabeled_t:s15:c0.c1023
tcontext=system_u:object_r:lo_netif_t:s0-s15:c0.c1023 tclass=netif
Signed-off-by: Paul Moore <paul.moore@hp.com>
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Audit will not respond to signal requests if selinux is disabled since it is
unable to translate the 0 sid from the sending process to a context. This
patch just doesn't send the context info if there isn't any.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
pahole pointed out that on x86_64 struct audit_context can be rearrainged
to save 16 bytes per struct. Since we have an audit_context per task this
can acually be a pretty significant gain.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
pahole showed that struct audit_watch had two holes:
struct audit_watch {
atomic_t count; /* 0 4 */
/* XXX 4 bytes hole, try to pack */
char * path; /* 8 8 */
dev_t dev; /* 16 4 */
/* XXX 4 bytes hole, try to pack */
long unsigned int ino; /* 24 8 */
struct audit_parent * parent; /* 32 8 */
struct list_head wlist; /* 40 16 */
struct list_head rules; /* 56 16 */
/* --- cacheline 1 boundary (64 bytes) was 8 bytes ago --- */
/* size: 72, cachelines: 2, members: 7 */
/* sum members: 64, holes: 2, sum holes: 8 */
/* last cacheline: 8 bytes */
}; /* definitions: 1 */
by moving dev after count we save 8 bytes, actually improving cacheline
usage. There are typically very few of these in the kernel so it won't be
a large savings, but it's a good thing no matter what.
Signed-off-by: Eric Paris <eparis@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
fix the following 'make includecheck' warning:
arch/sh/kernel/dwarf.c: asm/dwarf.h is included more than once.
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Commit ebd2c8f6d2 "serial: kill off uart_info"
broke the build of this driver, this fixes it.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
After upgrading to the latest kernel on my mpc875 userspace started
running incredibly slow (hours to get to a shell, even!).
I tracked it down to commit 8d30c14cab,
that patch removed a work-around for the 8xx. Adding it
back makes my problem go away.
Signed-off-by: Rex Feany <rfeany@mrv.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The xmon code relies on MSR_RI being non-zero to indicate that an exception
is recoverable. If it is not, it prints a warning message. However, the
PowerPC 4xx cores do not have an MSR_RI bit and this warning is produced for
every xmon event.
This introduces an unrecoverable_excp function to determine if an exception
is recoverable or not. This gets rid of the erroneous warnings on 4xx.
Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The test to check whether we have _PAGE_SPECIAL defined is broken,
since we always define it, just not always to a meaninful value :-)
That broke 8xx and 40x under some circumstances.
This fixes it by adding _PAGE_SPECIAL for both of these since they
had a free PTE bit, and removing the condition around advertising
it.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Tim Abbott <tabbott@ksplice.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: linuxppc-dev@ozlabs.org
Cc: Sam Ravnborg <sam@ravnborg.org>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
On machines without the ibm,client-architecture-support call we were missing a
newline. We may as well print the full name in all its glory too - its
ibm,client-architecture-support, not ibm,client-architecture as I mistakenly
wrote (a name only an IBM architect could love).
For my penance I will write out ibm,client-architecture-support 100 times.
Before:
Calling ibm,client-architecture...command line: root=/dev/sda6 console=hvc0 quiet
After:
Calling ibm,client-architecture-support... not implemented
command line: root=/dev/sda6 console=hvc0
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Some System p configurations can already have more than 16 nodes so we
need to increase NODES_SHIFT. I chose 256 to give us some room to grow in the
future, although we can look at something smaller if the memory bloat is
considered too much.
Unless we clamp MAX_ACTIVE_REGIONS we end up with 300kB of extra bloat in
early_node_map in mm/page_alloc.c:
< 6144 early_node_map
> 307200 early_node_map
due to:
#if MAX_NUMNODES >= 32
/* If there can be many nodes, allow up to 50 holes per node */
#define MAX_ACTIVE_REGIONS (MAX_NUMNODES*50)
#else
/* By default, allow up to 256 distinct regions */
#define MAX_ACTIVE_REGIONS 256
Since our memory is mostly contiguous it seems reasonable to keep this
at 256 for now. I also set 32bit to 32 to save space (is there any chance
a 32bit system will have more than 32 discontiguous memory ranges?).
Even with that fixed we have a few data structures that grow:
< 896 bootmem_node_data
> 14336 bootmem_node_data
< 1280 node_devices
> 20480 node_devices
< 25088 kmalloc_caches
> 59648 kmalloc_caches
< 1632 hstates
> 21792 hstates
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
perf_counter uses arch_vma_name() to detect a vdso region which in turn uses
current->mm->context.vdso_base. We need to initialise this before doing
the mmap or else we fail to detect the vdso.
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
If we are using 1TB segments and we are allowed to randomise the heap, we can
put it above 1TB so it is backed by a 1TB segment. Otherwise the heap will be
in the bottom 1TB which always uses 256MB segments and this may result in a
performance penalty.
This functionality is disabled when heap randomisation is turned off:
echo 1 > /proc/sys/kernel/randomize_va_space
which may be useful when trying to allocate the maximum amount of 16M or 16G
pages.
On a microbenchmark that repeatedly touches 32GB of memory with a stride of
256MB + 4kB (designed to stress 256MB segments while still mapping nicely into
the L1 cache), we see the improvement:
Force malloc to use heap all the time:
# export MALLOC_MMAP_MAX_=0 MALLOC_TRIM_THRESHOLD_=-1
Disable heap randomization:
# echo 1 > /proc/sys/kernel/randomize_va_space
# time ./test
12.51s
Enable heap randomization:
# echo 2 > /proc/sys/kernel/randomize_va_space
# time ./test
1.70s
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Sometimes this is used to hold a simple offset, and sometimes
it is used to hold a pointer. This patch changes it to a union containing
void * and dma_addr_t. get/set accessors are also provided, because it was
getting a bit ugly to get to the actual data.
Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
The former is no longer really accurate with the swiotlb case now
a possibility. I also move it into dma-mapping.h - it no longer
needs to be in dma.c, and there are about to be some more accessors
that should all end up in the same place. A comment is added to
indicate that this function is not used in configs where there is no
simple dma offset, such as the iommu case.
Signed-off-by: Becky Bruce <beckyb@kernel.crashing.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
When using CONFIG_RELOCATABLE, we build the kernel as a position
independent executable. The kernel then uses a little bit of relocation
code to relocate itself. That code only deals with R_PPC64_RELATIVE
relocations though. If for some reason you use assembly constructs
such as LOAD_REG_IMMEDIATE() to load the address of a symbol, you'll
generate different kinds of relocations that won't be processed properly
and bad things will happen. (We have 2 such bugs today).
The perl script tries to filter out "known" bad ones. It's possible
that we are missing some in the case of a weak function that nobody
implements, we'll see if we get false positive and fix it.
Signed-off-by: Tony Breeds <tony@bakeyournoodle.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Rename the locking free hvc_resize() function to __hvc_resize() and
provide an inline function that locks the hvc_struct and calls
__hvc_resize().
The rationale for this patch is that virtio_console calls the hvc_resize()
function without locking the hvc_struct. So it needs to call the lock
itself.
According to naming rules, the unlocked version is renamed and
prefixed with "__".
References to unlocked function calls in hvc back-ends has been updated.
Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
* git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-for-linus: (39 commits)
cpumask: Move deprecated functions to end of header.
cpumask: remove unused deprecated functions, avoid accusations of insanity
cpumask: use new-style cpumask ops in mm/quicklist.
cpumask: use mm_cpumask() wrapper: x86
cpumask: use mm_cpumask() wrapper: um
cpumask: use mm_cpumask() wrapper: mips
cpumask: use mm_cpumask() wrapper: mn10300
cpumask: use mm_cpumask() wrapper: m32r
cpumask: use mm_cpumask() wrapper: arm
cpumask: Use accessors for cpu_*_mask: um
cpumask: Use accessors for cpu_*_mask: powerpc
cpumask: Use accessors for cpu_*_mask: mips
cpumask: Use accessors for cpu_*_mask: m32r
cpumask: remove arch_send_call_function_ipi
cpumask: arch_send_call_function_ipi_mask: s390
cpumask: arch_send_call_function_ipi_mask: powerpc
cpumask: arch_send_call_function_ipi_mask: mips
cpumask: arch_send_call_function_ipi_mask: m32r
cpumask: arch_send_call_function_ipi_mask: alpha
cpumask: remove obsolete topology_core_siblings and topology_thread_siblings: ia64
...
* remove asm/atomic.h inclusion from linux/utsname.h --
not needed after kref conversion
* remove linux/utsname.h inclusion from files which do not need it
NOTE: it looks like fs/binfmt_elf.c do not need utsname.h, however
due to some personality stuff it _is_ needed -- cowardly leave ELF-related
headers and files alone.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This reverts commit c02e3f361c ("kmod: fix race in usermodehelper code")
The patch is wrong. UMH_WAIT_EXEC is called with VFORK what ensures
that the child finishes prior returing back to the parent. No race.
In fact, the patch makes it even worse because it does the thing it
claims not do:
- It calls ->complete() on UMH_WAIT_EXEC
- the complete() callback may de-allocated subinfo as seen in the
following call chain:
[<c009f904>] (__link_path_walk+0x20/0xeb4) from [<c00a094c>] (path_walk+0x48/0x94)
[<c00a094c>] (path_walk+0x48/0x94) from [<c00a0a34>] (do_path_lookup+0x24/0x4c)
[<c00a0a34>] (do_path_lookup+0x24/0x4c) from [<c00a158c>] (do_filp_open+0xa4/0x83c)
[<c00a158c>] (do_filp_open+0xa4/0x83c) from [<c009ba90>] (open_exec+0x24/0xe0)
[<c009ba90>] (open_exec+0x24/0xe0) from [<c009bfa8>] (do_execve+0x7c/0x2e4)
[<c009bfa8>] (do_execve+0x7c/0x2e4) from [<c0026a80>] (kernel_execve+0x34/0x80)
[<c0026a80>] (kernel_execve+0x34/0x80) from [<c004b514>] (____call_usermodehelper+0x130/0x148)
[<c004b514>] (____call_usermodehelper+0x130/0x148) from [<c0024858>] (kernel_thread_exit+0x0/0x8)
and the path pointer was NULL. Good that ARM's kernel_execve()
doesn't check the pointer for NULL or else I wouldn't notice it.
The only race there might be is with UMH_NO_WAIT but it is too late for
me to investigate it now. UMH_WAIT_PROC could probably also use VFORK
and we could save one exec. So the only race I see is with UMH_NO_WAIT
and recent scheduler changes where the child does not always run first
might have trigger here something but as I said, it is late....
Signed-off-by: Sebastian Andrzej Siewior <sebastian@breakpoint.cc>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
During releasepage, we try to drop any extent_state structs for the
bye offsets of the page we're releaseing. But the code was incorrectly
telling clear_extent_bit to delete the state struct unconditionallly.
Normally this would be fine because we have the page locked, but other
parts of btrfs will lock down an entire extent, the most common place
being IO completion.
releasepage was deleting the extent state without first locking the extent,
which may result in removing a state struct that another process had
locked down. The fix here is to leave the NODATASUM and EXTENT_LOCKED
bits alone in releasepage.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
If test_range_bit finds an extent that goes all the way to (u64)-1, it
can incorrectly wrap the u64 instead of treaing it like the end of
the address space.
This just adds a check for the highest possible offset so we don't wrap.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Both set and clear_extent_bit allow passing a cached
state struct to reduce rbtree search times. clear_extent_bit
was improperly bypassing some of the checks around making sure
the extent state fields were correct for a given operation.
The fix used here (from Yan Zheng) is to use the hit_next
goto target instead of jumping all the way down to start clearing
bits without making sure the cached state was exactly correct
for the operation we were doing.
This also fixes up the setting of the start variable for both
ops in the case where we find an overlapping extent that
begins before the range we want to change. In both cases
we were incorrectly going backwards from the original
requested change.
Signed-off-by: Chris Mason <chris.mason@oracle.com>
Saves us one cycle of alloc-add-free if the queue was full.
Signed-off-by: Amit Shah <amit.shah@redhat.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au> (modified)
Now we can tell the theoretical capacity remaining in the output
queue, virtio_net can waste entries by stopping the queue early.
It doesn't work in the case of indirect buffers and kmalloc failure,
but that's rare (we could drop the packet in that case, but other
drivers return TX_BUSY for similar reasons).
For the record, I think this patch reflects poorly on the linux
network API.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Dinesh Subhraveti <dineshs@us.ibm.com>
We put the virtio_net_hdr into the skb's cb region; turn this into a
union to clean up the code slightly and allow future expansion.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Mark McLoughlin <markmc@redhat.com>
Cc: Dinesh Subhraveti <dineshs@us.ibm.com>
The virtio_net driver is complicated by the two methods of freeing old
xmit buffers (in addition to freeing old ones at the start of the xmit
path).
The original code used a 1/10 second timer attached to xmit_free(),
reset on every xmit. Before we orphaned skbs on xmit, the
transmitting userspace could block with a full socket until the timer
fired, the skb destructor was called, and they were re-woken.
So we added the VIRTIO_F_NOTIFY_ON_EMPTY feature: supporting devices
send an interrupt (even if normally suppressed) on an empty xmit ring
which makes us schedule xmit_tasklet(). This was a benchmark win.
Unfortunately, VIRTIO_F_NOTIFY_ON_EMPTY makes quite a lot of work: a
host which is faster than the guest will fire the interrupt every xmit
packet (slowing the guest down further). Attempting mitigation in the
host adds overhead of userspace timers (possibly with the additional
pain of signals), and risks increasing latency anyway if you get it
wrong.
In practice, this effect was masked by benchmarks which take advantage
of GSO (with its inherent transmit batching), but it's still there.
Now we orphan xmitted skbs, the pressure is off: remove both paths and
no longer request VIRTIO_F_NOTIFY_ON_EMPTY. Note that the current
QEMU will notify us even if we don't negotiate this feature (legal,
but suboptimal); a patch is outstanding to improve that.
Move the skb_orphan/nf_reset to after we've done the send and notified
the other end, for a slight optimization.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Mark McLoughlin <markmc@redhat.com>
This effectively reverts 99ffc696d1
"virtio: wean net driver off NETDEV_TX_BUSY".
The complexity of queuing an skb (setting a tasklet to re-xmit) is
questionable, especially once we get rid of the other reason for the
tasklet in the next patch.
If the skb won't fit in the tx queue, just return NETDEV_TX_BUSY.
This is frowned upon, so a followup patch uses a more complex solution.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
The complex transmit free logic was introduced to avoid hangs on
removing the ip_conntrack module and also because drivers aren't
generally supposed to keep stale skbs for unbounded times.
After some debate, it was decided that while doing skb_orphan()
generally is a rat's nest, we can do it in this driver. Following
patches take advantage of this.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Andi Kleen