Johannes Berg [Wed, 10 Sep 2008 22:01:49 +0000 (00:01 +0200)]
mac80211: split off mesh handling entirely
This patch splits off mesh handling from the STA/IBSS.
Unfortunately it increases mesh code size a bit, but I
think it makes things clearer. The patch also reduces
per-interface run-time memory usage.
Also clean up a few places where ifdef is not required.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Johannes Berg [Wed, 10 Sep 2008 22:01:48 +0000 (00:01 +0200)]
mac80211: dont set REQ_RUN when scan finishes
The timer restart is done wrongly, we shouldn't set the REQ_RUN
bit when the scan has finished if it hadn't been set before the
scan started. If the timer fires during the scan, it will set
REQ_RUN and then we can run the work for it, if it didn't fire
then we shouldn't run its work either.
Signed-off-by: Johannes Berg <johannes@sipsolutions.net> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Dan Williams [Wed, 10 Sep 2008 13:04:33 +0000 (09:04 -0400)]
libertas: remove unused generic RESET command
The generic reset command is unused. Each interface type needs to
handle the reset command differently since after reset, the firmware is
dead and interface-specific mechanisms must be used to reinitialize the
card.
Signed-off-by: Dan Williams <dcbw@redhat.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
cfg80211: Add new wireless regulatory infrastructure
This adds the new wireless regulatory infrastructure. The
main motiviation behind this was to centralize regulatory
code as each driver was implementing their own regulatory solution,
and to replace the initial centralized code we have where:
* only 3 regulatory domains are supported: US, JP and EU
* regulatory domains can only be changed through module parameter
* all rules were built statically in the kernel
We now have support for regulatory domains for many countries
and regulatory domains are now queried through a userspace agent
through udev allowing distributions to update regulatory rules
without updating the kernel.
Each driver can regulatory_hint() a regulatory domain
based on either their EEPROM mapped regulatory domain value to a
respective ISO/IEC 3166-1 country code or pass an internally built
regulatory domain. We also add support to let the user set the
regulatory domain through userspace in case of faulty EEPROMs to
further help compliance.
Support for world roaming will be added soon for cards capable of
this.
For now we leave an option to enable the old module parameter,
ieee80211_regdom, and to build the 3 old regdomains statically
(US, JP and EU). This option is CONFIG_WIRELESS_OLD_REGULATORY.
These old static definitions and the module parameter is being
scheduled for removal for 2.6.29. Note that if you use this
you won't make use of a world regulatory domain as its pointless.
If you leave this option enabled and if CRDA is present and you
use US or JP we will try to ask CRDA to update us a regulatory
domain for us.
Signed-off-by: Luis R. Rodriguez <lrodriguez@atheros.com> Signed-off-by: John W. Linville <linville@tuxdriver.com>
Herbert Xu [Mon, 15 Sep 2008 18:48:46 +0000 (11:48 -0700)]
udp: Fix rcv socket locking
The previous patch in response to the recursive locking on IPsec
reception is broken as it tries to drop the BH socket lock while in
user context.
This patch fixes it by shrinking the section protected by the
socket lock to sock_queue_rcv_skb only. The only reason we added
the lock is for the accounting which happens in that function.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
Martin Langer [Sun, 7 Sep 2008 07:51:32 +0000 (17:51 +1000)]
powerpc: Fix major revision number for Freescale cores
Some 74xx cores by Freescale are using the configuration field instead
of the major revision field for their revision number. This corrects
the wrong behaviour for those ppc cores including my one.
There is a reference document at Freecale. It describes the PVR
register. This is based on that pdf. You can find the document at:
David Gibson [Fri, 5 Sep 2008 01:49:54 +0000 (11:49 +1000)]
powerpc: Clean up hugepage pagetable allocation for powerpc with 16G pages
There is a small bug in the handling of 16G hugepages recently added
to the kernel. This doesn't cause a crash or other user-visible
problems, but it does mean that more levels of pagetable are allocated
than makes sense for 16G pages. The hugepage pagetables for the 16G
pages are allocated much lower in the pagetable tree than they should
be, with the intervening levels allocated with full pmd and pud pages
which will only ever have one entry filled in.
This corrects this problem, at the same time cleaning up the handling
of which level 64k versus 16M hugepage pagetables are allocated at.
The new way of formatting the tests should be more robust against
changes in pagetable structure, or any newly added hugepage sizes.
Signed-off-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
powerpc: Make the irq reverse mapping radix tree lockless
The radix trees used by interrupt controllers for their irq reverse
mapping (currently only the XICS found on pSeries) have a complex
locking scheme dating back to before the advent of the lockless radix
tree.
This takes advantage of the lockless radix tree and of the fact that
the items of the tree are pointers to a static array (irq_map)
elements which can never go under us to simplify the locking.
Concurrency between readers and writers is handled by the intrinsic
properties of the lockless radix tree. Concurrency between writers is
handled with a global mutex.
Signed-off-by: Sebastien Dugue <sebastien.dugue@bull.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
powerpc: Separate the irq radix tree insertion and lookup
irq_radix_revmap() currently serves 2 purposes, irq mapping lookup
and insertion which happen in interrupt and process context respectively.
Separate the function into its 2 components, one for lookup only and one
for insertion only.
Fix the only user of the revmap tree (XICS) to use the new functions.
Also, move the insertion into the radix tree of those irqs that were
requested before it was initialized at said tree initialization.
Mutual exclusion between the tree initialization and readers/writers is
handled via a state variable (revmap_trees_allocated) set to 1 when the tree
has been initialized and set to 2 after the already requested irqs have been
inserted in the tree by the init path. This state is checked before any reader
or writer access just like we used to check for tree.gfp_mask != 0 before.
Finally, now that we're not any longer inserting nodes into the radix-tree
in interrupt context, turn the GFP_ATOMIC allocations into GFP_KERNEL ones.
Signed-off-by: Sebastien Dugue <sebastien.dugue@bull.net> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
Becky Bruce [Wed, 3 Sep 2008 15:37:53 +0000 (01:37 +1000)]
powerpc: Rename PTE_SIZE to HPTE_SIZE
It's the size of the hardware PTE; make that clear in the name.
Signed-off-by: Becky Bruce <becky.bruce@freescale.com> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
Paul Mackerras [Sat, 30 Aug 2008 01:43:47 +0000 (11:43 +1000)]
powerpc: Make the 64-bit kernel as a position-independent executable
This implements CONFIG_RELOCATABLE for 64-bit by making the kernel as
a position-independent executable (PIE) when it is set. This involves
processing the dynamic relocations in the image in the early stages of
booting, even if the kernel is being run at the address it is linked at,
since the linker does not necessarily fill in words in the image for
which there are dynamic relocations. (In fact the linker does fill in
such words for 64-bit executables, though not for 32-bit executables,
so in principle we could avoid calling relocate() entirely when we're
running a 64-bit kernel at the linked address.)
The dynamic relocations are processed by a new function relocate(addr),
where the addr parameter is the virtual address where the image will be
run. In fact we call it twice; once before calling prom_init, and again
when starting the main kernel. This means that reloc_offset() returns
0 in prom_init (since it has been relocated to the address it is running
at), which necessitated a few adjustments.
This also changes __va and __pa to use an equivalent definition that is
simpler. With the relocatable kernel, PAGE_OFFSET and MEMORY_START are
constants (for 64-bit) whereas PHYSICAL_START is a variable (and
KERNELBASE ideally should be too, but isn't yet).
With this, relocatable kernels still copy themselves down to physical
address 0 and run there.
Paul Mackerras [Sat, 30 Aug 2008 01:41:12 +0000 (11:41 +1000)]
powerpc: Use LOAD_REG_IMMEDIATE only for constants on 64-bit
Using LOAD_REG_IMMEDIATE to get the address of kernel symbols
generates 5 instructions where LOAD_REG_ADDR can do it in one,
and will generate R_PPC64_ADDR16_* relocations in the output when
we get to making the kernel as a position-independent executable,
which we'd rather not have to handle. This changes various bits
of assembly code to use LOAD_REG_ADDR when we need to get the
address of a symbol, or to use suitable position-independent code
for cases where we can't access the TOC for various reasons, or
if we're not running at the address we were linked at.
It also cleans up a few minor things; there's no reason to save and
restore SRR0/1 around RTAS calls, __mmu_off can get the return
address from LR more conveniently than the caller can supply it in
R4 (and we already assume elsewhere that EA == RA if the MMU is on
in early boot), and enable_64b_mode was using 5 instructions where
2 would do.
Paul Mackerras [Sat, 30 Aug 2008 01:40:24 +0000 (11:40 +1000)]
powerpc: Make it possible to move the interrupt handlers away from the kernel
This changes the way that the exception prologs transfer control to
the handlers in 64-bit kernels with the aim of making it possible to
have the prologs separate from the main body of the kernel. Now,
instead of computing the address of the handler by taking the top
32 bits of the paca address (to get the 0xc0000000........ part) and
ORing in something in the bottom 16 bits, we get the base address of
the kernel by doing a load from the paca and add an offset.
This also replaces an mfmsr and an ori to compute the MSR value for
the handler with a load from the paca. That makes it unnecessary to
have a separate version of EXCEPTION_PROLOG_PSERIES that forces 64-bit
mode.
We can no longer use a direct branches in the exception prolog code,
which means that the SLB miss handlers can't branch directly to
.slb_miss_realmode any more. Instead we have to compute the address
and do an indirect branch. This is conditional on CONFIG_RELOCATABLE;
for non-relocatable kernels we use a direct branch as before. (A later
change will allow CONFIG_RELOCATABLE to be set on 64-bit powerpc.)
Since the secondary CPUs on pSeries start execution in the first 0x100
bytes of real memory and then have to get to wherever the kernel is,
we can't use a direct branch to get there. Instead this changes
__secondary_hold_spinloop from a flag to a function pointer. When it
is set to a non-NULL value, the secondary CPUs jump to the function
pointed to by that value.
Finally this eliminates one code difference between 32-bit and 64-bit
by making __secondary_hold be the text address of the secondary CPU
spinloop rather than a function descriptor for it.
Paul Mackerras [Sat, 30 Aug 2008 01:39:26 +0000 (11:39 +1000)]
powerpc: Rearrange head_64.S to move interrupt handler code to the beginning
This rearranges head_64.S so that we have all the first-level exception
prologs together starting at 0x100, followed by all the second-level
handlers that are invoked from the first-level prologs, followed by
other code. This doesn't make any functional change but will make
following changes for relocatable kernel support easier.
Chandru [Fri, 29 Aug 2008 14:28:16 +0000 (00:28 +1000)]
powerpc: Add support for dynamic reconfiguration memory in kexec/kdump kernels
Kdump kernel needs to use only those memory regions that it is allowed
to use (crashkernel, rtas, tce, etc.). Each of these regions have
their own sizes and are currently added under 'linux,usable-memory'
property under each memory@xxx node of the device tree.
The ibm,dynamic-memory property of ibm,dynamic-reconfiguration-memory
node (on POWER6) now stores in it the representation for most of the
logical memory blocks with the size of each memory block being a
constant (lmb_size). If one or more or part of the above mentioned
regions lie under one of the lmb from ibm,dynamic-memory property,
there is a need to identify those regions within the given lmb.
This makes the kernel recognize a new 'linux,drconf-usable-memory'
property added by kexec-tools. Each entry in this property is of the
form of a count followed by that many (base, size) pairs for the above
mentioned regions. The number of cells in the count value is given by
the #size-cells property of the root node.
Signed-off-by: Chandru Siddalingappa <chandru@in.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
Nathan Fontenot [Mon, 25 Aug 2008 19:33:34 +0000 (05:33 +1000)]
powerpc: Check rc of notifier chain for memory remove
The return code from invocation of the notifier for
pSeries_reconfig_chain during update of the device tree is not
checked. This causes writes to /proc/ppc64/ofdt to update memory
properties (i.e. ibm,dyamic-reconfiguration-memory) to always
return success, instead of the result of the notifier chain.
This happens specifically when we remove/add memory from the
device tree on machines using memory specified in the
ibm,dynamic-reconfiguration-memory property of the device tree.
Signed-off-by: Nathan Fontenot <nfont@austin.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
Mark Nelson [Fri, 22 Aug 2008 04:39:00 +0000 (14:39 +1000)]
powerpc: New copy_4K_page()
This new copy_4K_page() function was originally tuned for the best
performance on the Cell processor, but after testing on more 64bit
powerpc chips it was found that with a small modification it either
matched the performance offered by the current mainline version or
bettered it by a small amount.
It was found that on a Cell-based QS22 blade the amount of system
time measured when compiling a 2.6.26 pseries_defconfig decreased
by 4%. Using the same test, a 4-way 970MP machine saw a decrease of
2% in system time. No noticeable change was seen on Power4, Power5
or Power6.
The 4096 byte page is copied in thirty-two 128 byte strides. An
initial setup loop executes dcbt instructions for the whole source
page and dcbz instructions for the whole destination page. To do
this, the cache line size is retrieved from ppc64_caches.
A new CPU feature bit, CPU_FTR_CP_USE_DCBTZ, (introduced in the
previous patch) is used to make the modification to this new copy
routine - on Power4, 970 and Cell the feature bit is set so the
setup loop is executed, but on all other 64bit chips the setup
loop is nop'ed out.
Signed-off-by: Mark Nelson <markn@au1.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
Mark Nelson [Fri, 22 Aug 2008 04:36:19 +0000 (14:36 +1000)]
powerpc: Add new CPU feature: CPU_FTR_CP_USE_DCBTZ
Add a new CPU feature bit, CPU_FTR_CP_USE_DCBTZ, to be added to the
64bit powerpc chips that benefit from having dcbt and dcbz
instructions used in their memory copy routines.
This will be used in a subsequent patch that updates copy_4K_page().
The new bit is added to Cell, PPC970 and Power4 because they show
better performance with the new copy_4K_page() when dcbt and dcbz
instructions are used.
Signed-off-by: Mark Nelson <markn@au1.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
Abhijith Das [Mon, 15 Sep 2008 13:54:06 +0000 (08:54 -0500)]
GFS2: GFS2 will panic if you misspell any mount options
The gfs2 superblock pointer is NULL after a failed mount. When control
eventually goes to gfs2_kill_sb, we dereference this NULL pointer. This
patch ensures that the gfs2 superblock pointer is not NULL before being
dereferenced in gfs2_kill_sb.
Signed-off-by: Abhijith Das <adas@redhat.com> Signed-off-by: Steven Whitehouse <swhiteho@redhat.com>
Kim Phillips [Sun, 14 Sep 2008 20:41:19 +0000 (13:41 -0700)]
crypto: talitos - Avoid consecutive packets going out with same IV
The SEC's h/w IV out implementation DMAs the trailing encrypted payload
block of the last encryption to ctx->iv. Since the last encryption may
still be pending completion, we can sufficiently prevent successive
packets from being transmitted with the same IV by xoring with sequence
number.
Also initialize alg_list earlier to prevent oopsing on a failed probe.
Signed-off-by: Kim Phillips <kim.phillips@freescale.com> Signed-off-by: Lee Nipper <lee.nipper@freescale.com> Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
generic: make PFN_PHYS explicitly return phys_addr_t
PFN_PHYS, as its name suggests, turns a pfn into a physical address.
However, it is a macro which just operates on its argument without
modifying its type. pfns are typed unsigned long, but an unsigned
long may not be long enough to hold a physical address (32-bit systems
with more than 32 bits of physcial address).
Make sure we cast to phys_addr_t to return a complete result.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
generic: add phys_addr_t for holding physical addresses
Add a kernel-wide "phys_addr_t" which is guaranteed to be able to hold
any physical address. By default it equals the word size of the
architecture, but a 32-bit architecture can set ARCH_PHYS_ADDR_T_64BIT
if it needs a 64-bit phys_addr_t.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
In file included from arch/x86/kernel/asm-offsets_32.c:9,
from arch/x86/kernel/asm-offsets.c:3:
include/linux/sched.h: In function ‘thread_group_cputime_clone_thread’:
include/linux/sched.h:2272: warning: no return statement in function returning non-void
include/linux/sched.h: In function ‘thread_group_cputime_account_user’:
include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h: In function ‘thread_group_cputime_account_system’:
include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h: In function ‘thread_group_cputime_account_exec_runtime’:
include/linux/sched.h:2298: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
distcc[14501] ERROR: compile arch/x86/kernel/asm-offsets.c on a/30 failed
make[1]: *** [arch/x86/kernel/asm-offsets.s] Error 1
PFN_PHYS() can truncate large addresses unless its passed a suitable
large type. This is fixed more generally in the patch series
introducing phys_addr_t, but we need a short-term fix to solve a
Xen regression reported by Roberto De Ioris.
Reported-by: Roberto De Ioris <roberto@unbit.it> Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
x86: avoid unnecessary low zone allocation in Calgary's alloc_coherent
x86's common alloc_coherent (dma_alloc_coherent in dma-mapping.h) sets
up the gfp flag according to the device dma_mask but Calgary doesn't
need it because of virtual mappings. This patch avoids unnecessary low
zone allocation.
x86: make GART to respect device's dma_mask about virtual mappings
Currently, GART IOMMU ingores device's dma_mask when it does virtual
mappings. So it could give a device a virtual address that the device
can't access to.
kernel/fork.c:843: error: ‘struct signal_struct’ has no member named ‘sum_sched_runtime’
kernel/irq/handle.c:117: warning: ‘sparse_irq_lock’ defined but not used
Frank Mayhar [Fri, 12 Sep 2008 16:54:39 +0000 (09:54 -0700)]
timers: fix itimer/many thread hang
Overview
This patch reworks the handling of POSIX CPU timers, including the
ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together
with the help of Roland McGrath, the owner and original writer of this code.
The problem we ran into, and the reason for this rework, has to do with using
a profiling timer in a process with a large number of threads. It appears
that the performance of the old implementation of run_posix_cpu_timers() was
at least O(n*3) (where "n" is the number of threads in a process) or worse.
Everything is fine with an increasing number of threads until the time taken
for that routine to run becomes the same as or greater than the tick time, at
which point things degrade rather quickly.
This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF."
Code Changes
This rework corrects the implementation of run_posix_cpu_timers() to make it
run in constant time for a particular machine. (Performance may vary between
one machine and another depending upon whether the kernel is built as single-
or multiprocessor and, in the latter case, depending upon the number of
running processors.) To do this, at each tick we now update fields in
signal_struct as well as task_struct. The run_posix_cpu_timers() function
uses those fields to make its decisions.
We define a new structure, "task_cputime," to contain user, system and
scheduler times and use these in appropriate places:
struct task_cputime {
cputime_t utime;
cputime_t stime;
unsigned long long sum_exec_runtime;
};
This is included in the structure "thread_group_cputime," which is a new
substructure of signal_struct and which varies for uniprocessor versus
multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as
a simple substructure, while for multiprocessor kernels it is a pointer:
We also add a new task_cputime substructure directly to signal_struct, to
cache the earliest expiration of process-wide timers, and task_cputime also
replaces the it_*_expires fields of task_struct (used for earliest expiration
of thread timers). The "thread_group_cputime" structure contains process-wide
timers that are updated via account_user_time() and friends. In the non-SMP
case the structure is a simple aggregator; unfortunately in the SMP case that
simplicity was not achievable due to cache-line contention between CPUs (in
one measured case performance was actually _worse_ on a 16-cpu system than
the same test on a 4-cpu system, due to this contention). For SMP, the
thread_group_cputime counters are maintained as a per-cpu structure allocated
using alloc_percpu(). The timer functions update only the timer field in
the structure corresponding to the running CPU, obtained using per_cpu_ptr().
We define a set of inline functions in sched.h that we use to maintain the
thread_group_cputime structure and hide the differences between UP and SMP
implementations from the rest of the kernel. The thread_group_cputime_init()
function initializes the thread_group_cputime structure for the given task.
The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the
out-of-line function thread_group_cputime_alloc_smp() to allocate and fill
in the per-cpu structures and fields. The thread_group_cputime_free()
function, also a no-op for UP, in SMP frees the per-cpu structures. The
thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls
thread_group_cputime_alloc() if the per-cpu structures haven't yet been
allocated. The thread_group_cputime() function fills the task_cputime
structure it is passed with the contents of the thread_group_cputime fields;
in UP it's that simple but in SMP it must also safely check that tsk->signal
is non-NULL (if it is it just uses the appropriate fields of task_struct) and,
if so, sums the per-cpu values for each online CPU. Finally, the three
functions account_group_user_time(), account_group_system_time() and
account_group_exec_runtime() are used by timer functions to update the
respective fields of the thread_group_cputime structure.
Non-SMP operation is trivial and will not be mentioned further.
The per-cpu structure is always allocated when a task creates its first new
thread, via a call to thread_group_cputime_clone_thread() from copy_signal().
It is freed at process exit via a call to thread_group_cputime_free() from
cleanup_signal().
All functions that formerly summed utime/stime/sum_sched_runtime values from
from all threads in the thread group now use thread_group_cputime() to
snapshot the values in the thread_group_cputime structure or the values in
the task structure itself if the per-cpu structure hasn't been allocated.
Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit.
The run_posix_cpu_timers() function has been split into a fast path and a
slow path; the former safely checks whether there are any expired thread
timers and, if not, just returns, while the slow path does the heavy lifting.
With the dedicated thread group fields, timers are no longer "rebalanced" and
the process_timer_rebalance() function and related code has gone away. All
summing loops are gone and all code that used them now uses the
thread_group_cputime() inline. When process-wide timers are set, the new
task_cputime structure in signal_struct is used to cache the earliest
expiration; this is checked in the fast path.
Performance
The fix appears not to add significant overhead to existing operations. It
generally performs the same as the current code except in two cases, one in
which it performs slightly worse (Case 5 below) and one in which it performs
very significantly better (Case 2 below). Overall it's a wash except in those
two cases.
I've since done somewhat more involved testing on a dual-core Opteron system.
Case 1: With no itimer running, for a test with 100,000 threads, the fixed
kernel took 1428.5 seconds, 513 seconds more than the unfixed system,
all of which was spent in the system. There were twice as many
voluntary context switches with the fix as without it.
Case 2: With an itimer running at .01 second ticks and 4000 threads (the most
an unmodified kernel can handle), the fixed kernel ran the test in
eight percent of the time (5.8 seconds as opposed to 70 seconds) and
had better tick accuracy (.012 seconds per tick as opposed to .023
seconds per tick).
Case 3: A 4000-thread test with an initial timer tick of .01 second and an
interval of 10,000 seconds (i.e. a timer that ticks only once) had
very nearly the same performance in both cases: 6.3 seconds elapsed
for the fixed kernel versus 5.5 seconds for the unfixed kernel.
With fewer threads (eight in these tests), the Case 1 test ran in essentially
the same time on both the modified and unmodified kernels (5.2 seconds versus
5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds
versus 5.4 seconds but again with much better tick accuracy, .013 seconds per
tick versus .025 seconds per tick for the unmodified kernel.
Since the fix affected the rlimit code, I also tested soft and hard CPU limits.
Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer
running), the modified kernel was very slightly favored in that while
it killed the process in 19.997 seconds of CPU time (5.002 seconds of
wall time), only .003 seconds of that was system time, the rest was
user time. The unmodified kernel killed the process in 20.001 seconds
of CPU (5.014 seconds of wall time) of which .016 seconds was system
time. Really, though, the results were too close to call. The results
were essentially the same with no itimer running.
Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds
(where the hard limit would never be reached) and an itimer running,
the modified kernel exhibited worse tick accuracy than the unmodified
kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise,
performance was almost indistinguishable. With no itimer running this
test exhibited virtually identical behavior and times in both cases.
In times past I did some limited performance testing. those results are below.
On a four-cpu Opteron system without this fix, a sixteen-thread test executed
in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On
the same system with the fix, user and elapsed time were about the same, but
system time dropped to 0.007 seconds. Performance with eight, four and one
thread were comparable. Interestingly, the timer ticks with the fix seemed
more accurate: The sixteen-thread test with the fix received 149543 ticks
for 0.024 seconds per tick, while the same test without the fix received 58720
for 0.061 seconds per tick. Both cases were configured for an interval of
0.01 seconds. Again, the other tests were comparable. Each thread in this
test computed the primes up to 25,000,000.
I also did a test with a large number of threads, 100,000 threads, which is
impossible without the fix. In this case each thread computed the primes only
up to 10,000 (to make the runtime manageable). System time dominated, at
1546.968 seconds out of a total 2176.906 seconds (giving a user time of
629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite
accurate. There is obviously no comparable test without the fix.
Signed-off-by: Frank Mayhar <fmayhar@google.com> Cc: Roland McGrath <roland@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
mv643xx_eth: add support for chips without transmit bandwidth control
Add support for mv643xx_eth versions that have no transmit bandwidth
control registers at all, such as the ethernet block found in the
Marvell 88F6183 ARM SoC.
mv643xx_eth: avoid reading ->byte_cnt twice during receive processing
Currently, the receive processing reads ->byte_cnt twice (once to
update interface statistics and once to properly size the data area
of the received skb), but since receive descriptors live in uncached
memory, caching this value in a local variable saves one uncached
access, and increases routing performance a tiny little bit more.
x86: signal: put give_sigsegv of setup frames together
When setup frame fails, force_sigsegv is called and returns -EFAULT.
There is similar code in ia32_setup_frame(), ia32_setup_rt_frame(),
__setup_frame() and __setup_rt_frame().
mv643xx_eth: shrink default receive and transmit queue sizes
Since the size of the receive queue is directly related to the data
cache footprint of the driver (between refilling a receive ring entry
with a fresh skb and receiving a packet in that entry, queue_size - 1
other skbs will have been touched), shrink the default receive queue
size to a saner number of entries, as 400 is definite overkill for
almost all workloads.
While we are at it, trim the default transmit queue size a bit as well.
mv643xx_eth: replace array of skbs awaiting transmit completion with a queue
Get rid of the skb pointer array that we currently use for transmit
reclaim, and replace it with an skb queue, to which skbuffs are appended
when they are passed to the xmit function, and removed from the front
and freed when we do transmit queue reclaim and hit a descriptor with
the 'owned by device' bit clear and 'last descriptor' bit set.
mv643xx_eth: avoid dropping tx lock during transmit reclaim
By moving DMA unmapping during transmit reclaim back under the netif
tx lock, we avoid the situation where we read the DMA address and buffer
length from the descriptor under the lock and then not do anything with
that data after dropping the lock on platforms where the DMA unmapping
routines are all NOPs (which is the case on all ARM platforms that
mv643xx_eth is used on at least).
This saves two uncached reads, which makes a small but measurable
performance difference in routing benchmarks.
mv643xx_eth: switch to netif tx queue lock, get rid of private spinlock
Since our ->hard_start_xmit() method is already called under spinlock
protection (the netif tx queue lock), we can simply make that lock
cover the private transmit state (descriptor ring indexes et al.) as
well, which avoids having to use a private lock to protect that state.
Since this was the last user of the driver-private spinlock, it can
be killed off.
mv643xx_eth: move all work to the napi poll handler
Move link status handling, transmit reclaim and TX_END handling from
the interrupt handler to the napi poll handler. This allows switching
->lock over to a non-IRQ-safe lock and removes all explicit interrupt
disabling from the driver.
Julia Lawall [Sun, 14 Sep 2008 03:05:34 +0000 (20:05 -0700)]
drivers/dma/ioat_dma.c: drop code after return
The break after the return serves no purpose.
Signed-off-by: Julia Lawall <julia@diku.dk> Reviewed-by: Richard Genoud <richard.genoud@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Dan Williams <dan.j.williams@intel.com>
* master.kernel.org:/home/rmk/linux-2.6-arm:
[ARM] Fix PCI_DMA_BUS_IS_PHYS for ARM
[ARM] 5247/1: tosa: SW_EAR_IN support
[ARM] 5246/1: tosa: add proper clock alias for tc6393xb clock
[ARM] 5245/1: Fix warning about unused return value in drivers/pcmcia
[ARM] OMAP: Fix MMC device data
imx serial: fix rts handling for non imx1 based hardware
imx serial: set RXD mux bit on i.MX27 and i.MX31
i.MX serial: fix init failure
pcm037: add rts/cts support for serial port
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6:
niu: panic on reset
netlink: fix overrun in attribute iteration
[Bluetooth] Fix regression from using default link policy
ath9k: Assign seq# when mac80211 requests this
Alex Dubov [Sat, 13 Sep 2008 09:33:26 +0000 (02:33 -0700)]
memstick: fix MSProHG 8-bit interface mode support
- 8-bit interface mode never worked properly. The only adapter I have
which supports the 8b mode (the Jmicron) had some problems with its
clock wiring and they discovered it only now. We also discovered that
ProHG media is more sensitive to the ordering of initialization
commands.
- Make the driver fall back to highest supported mode instead of always
falling back to serial. The driver will attempt the switch to 8b mode
for any new MSPro card, but not all of them support it. Previously,
these new cards ended up in serial mode, which is not the best idea
(they work fine with 4b, after all).
- Edit some macros for better conformance to Sony documentation
Signed-off-by: Alex Dubov <oakad@yahoo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Andrew Morton [Sat, 13 Sep 2008 09:33:25 +0000 (02:33 -0700)]
rescan_partitions(): make device capacity errors non-fatal
Herton Krzesinski reports that the error-checking changes in 04ebd4aee52b06a2c38127d9208546e5b96f3a19 ("block/ioctl.c and
fs/partition/check.c: check value returned by add_partition") cause his
buggy USB camera to no longer mount. "The camera is an Olympus X-840.
The original issue comes from the camera itself: its format program
creates a partition with an off by one error".
Buggy devices happen. It is better for the kernel to warn and to proceed
with the mount.
Reported-by: Herton Ronaldo Krzesinski <herton@mandriva.com.br> Cc: Abdel Benamrouche <draconux@gmail.com> Cc: Jens Axboe <jens.axboe@oracle.com> Cc: Alan Stern <stern@rowland.harvard.edu> Cc: David Brownell <david-b@pacbell.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ben Dooks [Sat, 13 Sep 2008 09:33:24 +0000 (02:33 -0700)]
spi_s3c24xx: fix section warning
Fix the section mismatch warning generated by the incorrect naming of
s3c24xx_spidrv which should be s3c24xx_spi_driver:
WARNING: drivers/spi/spi_s3c24xx.o(.data+0x4):
Section mismatch in reference from the variable s3c24xx_spidrv
to the (unknown reference) .exit.text:(unknown)
Signed-off-by: Ben Dooks <ben-linux@fluff.org> Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
atmel_lcdfb: disable LCD and DMA engines when suspending
When suspending the system with atmel_lcdfb enabled, I sometimes see
this:
atmel_lcdfb atmel_lcdfb.0: FIFO underflow 0x10
Which can be explained by the fact that we're not stopping the LCD
controller and its DMA engine when suspending, we're just gating the
clocks to them.
There's another potential issue which may be harder to trigger but
much more nasty: If we gate the clocks at _just_ the right moment,
e.g. when the DMA engine is doing a bus transaction, we may cause the
DMA engine to violate the system bus protocol and cause a lockup.
Avoid these issues by shutting down the LCD controller before entering
suspend (and restarting it when resuming). This prevents the underrun
from happening in the first place, and prevents whatever nastiness is
happening when the bus clock stops in the middle of a DMA transfer.
Signed-off-by: Haavard Skinnemoen <haavard.skinnemoen@atmel.com> Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Robin Holt [Sat, 13 Sep 2008 09:33:22 +0000 (02:33 -0700)]
ia64: fix panic during `modprobe -r xpc'
If you are on ia64 and you modprobe xpc then modprobe -r xpc, you
immediately get a panic. xpc depends on xp which depends on gru for a
symbol. That symbol is only used when we are running on UV hardware.
Currently, the GRU driver detects we are not on UV hardware and does no
initializing. It does not do the same check when unloading. As a result,
the gru driver attempts to tear down stuff that was not setup.
This is a simple two-line workaround to get us through this release. Once
2.6.28 is opened, we need to rework the symbols that xp is depending on
from gru so the gru driver can properly fail to load when hardware is not
available.
Signed-off-by: Robin Holt <holt@sgi.com> Cc: "Luck, Tony" <tony.luck@intel.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
mm: mark the correct zone as full when scanning zonelists
The iterator for_each_zone_zonelist() uses a struct zoneref *z cursor when
scanning zonelists to keep track of where in the zonelist it is. The
zoneref that is returned corresponds to the the next zone that is to be
scanned, not the current one. It was intended to be treated as an opaque
list.
When the page allocator is scanning a zonelist, it marks elements in the
zonelist corresponding to zones that are temporarily full. As the
zonelist is being updated, it uses the cursor here;
if (NUMA_BUILD)
zlc_mark_zone_full(zonelist, z);
This is intended to prevent rescanning in the near future but the zoneref
cursor does not correspond to the zone that has been found to be full.
This is an easy misunderstanding to make so this patch corrects the
problem by changing zoneref cursor to be the current zone being scanned
instead of the next one.
Ned Forrester [Sat, 13 Sep 2008 09:33:18 +0000 (02:33 -0700)]
pxa2xx_spi: dma bugfixes
Fixes two DMA bugs in the pxa2xx_spi driver. The first bug is in all
versions of this driver; the second was introduced in the 2.6.20 kernel,
and prevents using the driver with chips like m25p16 flash (which can
issue large DMA reads).
1. Zero length transfers are permitted for use to insert timing,
but pxa2xx_spi.c will fail if this is requested in DMA mode.
Fixed by using programmed I/O (PIO) mode for such transfers.
2. Transfers larger than 8191 are not permitted in DMA mode. A
test for length rejects all large transfers regardless of DMA
or PIO mode. Worked around by rejecting only large transfers
with DMA mapped buffers, and forcing all other transfers
larger than 8191 to use PIO mode. A rate limited warning is
issued for DMA transfers forced to PIO mode.
This patch should apply to all kernels back to and including 2.6.20;
it was test patched against 2.6.20. An additional patch would be
required for older kernels, but those versions are very buggy anyway.
Signed-off-by: Ned Forrester <nforrester@whoi.edu> Cc: Vernon Sauder <vernoninhand@gmail.com> Cc: Eric Miao <eric.y.miao@gmail.com> Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Cc: <stable@kernel.org> [2.6.25.x, 2.6.26.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Ned Forrester [Sat, 13 Sep 2008 09:33:17 +0000 (02:33 -0700)]
pxa2xx_spi: chipselect bugfixes
Fixes several chipselect bugs in the pxa2xx_spi driver. These bugs are in
all versions of this driver and prevent using it with chips like m25p16
flash.
1. The spi_transfer.cs_change flag is handled too early:
before spi_transfer.delay_usecs applies, thus making the
delay ineffective at holding chip select.
2. spi_transfer.delay_usecs is ignored on the last transfer
of a message (likewise not holding chipselect long enough).
3. If spi_transfer.cs_change is set on the last transfer, the
chip select is always disabled, instead of the intended
meaning: optionally holding chip select enabled for the
next message.
Those first three bugs were fixed with a relocation of delays
and chip select de-assertions.
4. If a message has the cs_change flag set on the last transfer,
and had the chip select stayed enabled as requested (see 3,
above), it would not have been disabled if the next message is
for a different chip. Fixed by dropping chip select regardless
of cs_change at end of a message, if there is no next message
or if the next message is for a different chip.
This patch should apply to all kernels back to and including 2.6.20;
it was test patched against 2.6.20. An additional patch would be
required for older kernels, but those versions are very buggy anyway.
Signed-off-by: Ned Forrester <nforrester@whoi.edu> Cc: Vernon Sauder <vernoninhand@gmail.com> Cc: Eric Miao <eric.y.miao@gmail.com> Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Cc: <stable@kernel.org> [2.6.25.x, 2.6.26.x] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Peter Korsgaard [Sat, 13 Sep 2008 09:33:14 +0000 (02:33 -0700)]
spi_mpc83xx: fix clockrate calculation for low speed
Commit a61f5345 (spi_mpc83xx clockrate fixes) broke clockrate calculation
for low speeds. SPMODE_DIV16 should be set if the divider is higher than
64, not only if the divider gets clipped to 1024.
Furthermore, the clipping check was off by a factor 16 as well.
Signed-off-by: Peter Korsgaard <jacmet@sunsite.dk> Signed-off-by: David Brownell <dbrownell@users.sourceforge.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A "Quicklists: 0 kB" line has just started appearing in
/proc/meminfo, but most architectures (including x86) don't have
them configured, so #ifdef it, like the highmem lines.
And those architectures which do have quicklists configured are
using them for page tables: so let's place it next to PageTables.
Signed-off-by: Hugh Dickins <hugh@veritas.com> Acked-by: Christoph Lameter <cl@linux-foundation.org> Acked-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Eric Sesterhenn [Sat, 13 Sep 2008 09:33:12 +0000 (02:33 -0700)]
bfs: fix Lockdep warning
This fixes:
=============================================
[ INFO: possible recursive locking detected ] 2.6.27-rc5-00283-g70bb089 #68
---------------------------------------------
touch/6855 is trying to acquire lock:
(&info->bfs_lock){--..}, at: [<c02262f5>] bfs_delete_inode+0x9e/0x18c
but task is already holding lock:
(&info->bfs_lock){--..}, at: [<c0226c00>] bfs_create+0x45/0x187
other info that might help us debug this:
2 locks held by touch/6855:
#0: (&type->i_mutex_dir_key#5){--..}, at: [<c018ad13>] do_filp_open+0x10b/0x62f
#1: (&info->bfs_lock){--..}, at: [<c0226c00>] bfs_create+0x45/0x187
Li Zefan [Sat, 13 Sep 2008 09:33:09 +0000 (02:33 -0700)]
cpuset: hotplug documentation fix
If all the cpus in a cpuset are offlined, the tasks in it will be moved to
the nearest ancestor with non-empty cpus.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Paul Jackson <pj@sgi.com> Cc: Paul Menage <menage@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
cpusets: restructure the function update_cpumask() and update_nodemask()
It might happen that 'echo 0 > /cpuset/sub/cpus' returned failure but 'cpus'
has been changed, because cpus was changed before calling heap_init() which
may return -ENOMEM.
This patch restores the orginal behavior.
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com> Acked-by: Paul Menage <menage@google.com> Cc: Paul Jackson <pj@sgi.com> Cc: Miao Xie <miaox@cn.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
proc: more debugging for "already registered" case
Print parent directory name as well.
The aim is to catch non-creation of parent directory when proc_mkdir will
return NULL and all subsequent registrations go directly in /proc instead
of intended directory.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
[ Fixed insane printk string while at it. - Linus ] Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I recently bought 3 HGST P7K500-series 500GB SATA drives and
had trouble accessing the block right on the LBA28-LBA48 border.
Here's how it fails (same for all 3 drives):
# dd if=/dev/sdc bs=512 count=1 skip=268435455 > /dev/null
dd: reading `/dev/sdc': Input/output error
0+0 records in
0+0 records out
0 bytes (0 B) copied, 0.288033 seconds, 0.0 kB/s
# dmesg
ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x0
ata1.00: BMDMA stat 0x25
ata1.00: cmd c8/00:08:f8:ff:ff/00:00:00:00:00/ef tag 0 dma 4096 in
res 51/04:08:f8:ff:ff/00:00:00:00:00/ef Emask 0x1 (device error)
ata1.00: status: { DRDY ERR }
ata1.00: error: { ABRT }
ata1.00: configured for UDMA/33
ata1: EH complete
...
After some investigations, it turned out this seems to be caused
by misinterpretation of the ATA specification on LBA28 access.
Following part is the code in question:
HGST drive (sometimes) fails with LBA28 access of {block = 0xfffffff,
n_block = 1}, and this behavior seems to be comformant. Other drives,
including other HGST drives are not that strict, through.
>From the ATA specification:
(http://www.t13.org/Documents/UploadedDocuments/project/d1410r3b-ATA-ATAPI-6.pdf)
8.15.29 Word (61:60): Total number of user addressable sectors
This field contains a value that is one greater than the total number
of user addressable sectors (see 6.2). The maximum value that shall
be placed in this field is 0FFFFFFFh.
So the driver shouldn't use the value of 0xfffffff for LBA28 request
as this exceeds maximum user addressable sector. The logical maximum
value for LBA28 is 0xffffffe.
The obvious fix is to cut "- 1" part, and the patch attached just do
that. I've been using the patched kernel for about a month now, and
the same fix is also floating on the net for some time. So I believe
this fix works reliably.
Just FYI, many Windows/Intel platform users also seems to be struck
by this, and HGST has issued a note pointing to Intel ICH8/9 driver.
Russell King [Sat, 13 Sep 2008 20:23:06 +0000 (21:23 +0100)]
[ARM] Fix PCI_DMA_BUS_IS_PHYS for ARM
PCI_DMA_BUS_IS_PHYS was defined to be zero, which meant we ignored
the DMA mask for IDE and SCSI transfers. This is wrong - we have
no DMA translation hardware. We want to obey DMA masks so that the
block layer performs bouncing itself.
Reported-by: Mikael Pettersson <mikpe@it.uu.se> Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Eric Sandeen [Sat, 13 Sep 2008 19:23:29 +0000 (15:23 -0400)]
ext4: use percpu data structures for lg_prealloc_list
lg_prealloc_list seems to cry out for a per-cpu data structure; on a large
smp system I think this should be better. I've lightly tested this change
on a 4-cpu system.