Peter Zijlstra [Tue, 10 Mar 2009 18:03:43 +0000 (19:03 +0100)]
trace_clock: fix preemption bug
Using the function_graph tracer in recent kernels generates a spew of
preemption BUGs. Fix this by not requiring trace_clock_local() users
to disable preemption themselves.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Frederic Weisbecker <fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Sitsofe Wheeler found and bisected that while unifying the
vsprintf format decoding in:
fef20d9: vsprintf: unify the format decoding layer for its 3 users
The sign flag has been dropped out in favour of
precise types (ie: LONG/ULONG).
But the format helper number() still needs this flag to keep track of
the signedness unless it will consider all numbers as unsigned.
Also add an explicit cast to int (for %d) while parsing with va_arg()
to ensure the highest bit is well extended on the 64 bits number that
hosts the value in case of negative values.
Steven Rostedt [Tue, 10 Mar 2009 04:15:34 +0000 (00:15 -0400)]
tracing: remove obsolete TRACE_EVENT_FORMAT macro
Impact: clean up
The TRACE_EVENT_FORMAT macro is no longer used by trace points
and only the DECLARE_TRACE, TRACE_FORMAT or TRACE_EVENT macros should
be used by them. Although the TRACE_EVENT_FORMAT macro is still used
by the internal tracing utility, it should not be used in core
kernel code.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Steven Rostedt [Tue, 10 Mar 2009 03:23:30 +0000 (23:23 -0400)]
tracing: convert irq trace points to new macros
Impact: enhancement
Converted the two irq trace point macros. The entry macro copies
the name of the irq handler, thus it is better to simply use the
TRACE_FORMAT macro which uses the trace_printk.
The return of the handler does not need to record the name, thus
the faster C style handler is more approriate.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Steven Rostedt [Mon, 9 Mar 2009 21:14:30 +0000 (17:14 -0400)]
tracing: new format for specialized trace points
Impact: clean up and enhancement
The TRACE_EVENT_FORMAT macro looks quite ugly and is limited in its
ability to save data as well as to print the record out. Working with
Ingo Molnar, we came up with a new format that is much more pleasing to
the eye of C developers. This new macro is more C style than the old
macro, and is more obvious to what it does.
Here's the example. The only updated macro in this patch is the
sched_switch trace point.
The above method is hard to read and requires two format fields.
The new method:
/*
* Tracepoint for task switches, performed by the scheduler:
*
* (NOTE: the 'rq' argument is not used by generic trace events,
* but used by the latency tracer plugin. )
*/
TRACE_EVENT(sched_switch,
This macro is called TRACE_EVENT, it is broken up into 5 parts:
TP_PROTO: the proto type of the trace point
TP_ARGS: the arguments of the trace point
TP_STRUCT_entry: the structure layout of the entry in the ring buffer
TP_printk: the printk format
TP_fast_assign: the method used to write the entry into the ring buffer
The structure is the definition of how the event will be saved in the
ring buffer. The printk is used by the internal tracing in case of
an oops, and the kernel needs to print out the format of the record
to the console. This the TP_printk gives a means to show the records
in a human readable format. It is also used to print out the data
from the trace file.
The TP_fast_assign is executed directly. It is basically like a C function,
where the __entry is the handle to the record.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Steven Rostedt [Fri, 6 Mar 2009 15:50:53 +0000 (10:50 -0500)]
tracing: typecast sizeof and offsetof to unsigned int
Impact: fix compiler warnings
On x86_64 sizeof and offsetof are treated as long, where as on x86_32
they are int. This patch typecasts them to unsigned int to avoid
one arch giving warnings while the other does not.
Reported-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Steven Rostedt <srostedt@redhat.com>
KOSAKI Motohiro [Mon, 9 Mar 2009 09:15:34 +0000 (18:15 +0900)]
tracing: Don't use tracing_record_cmdline() in workqueue tracer
Impact: improve workqueue tracer output
Currently, /sys/kernel/debug/tracing/trace_stat/workqueues can display
wrong and strange thread names.
Why?
Currently, ftrace has tracing_record_cmdline()/trace_find_cmdline()
convenience function that implements a task->comm string cache.
This can avoid unnecessary memcpy overhead and the workqueue tracer
uses it.
However, in general, any trace statistics feature shouldn't use
tracing_record_cmdline() because trace statistics can display
very old process. Then comm cache can return wrong string because
recent process overrides the cache.
Fortunately, workqueue trace guarantees that displayed processes
are live. Thus we can search comm string from PID at display time.
<before>
% cat workqueues
# CPU INSERTED EXECUTED NAME
# | | | |
Stuart Bennett [Sun, 8 Mar 2009 18:21:35 +0000 (20:21 +0200)]
x86 mmiotrace: fix remove_kmmio_fault_pages()
Impact: fix race+crash in mmiotrace
The list manipulation in remove_kmmio_fault_pages() was broken. If more
than one consecutive kmmio_fault_page was re-added during the grace
period between unregister_kmmio_probe() and remove_kmmio_fault_pages(),
the list manipulation failed to remove pages from the release list.
After a second grace period the pages get into rcu_free_kmmio_fault_pages()
and raise a BUG_ON() kernel crash.
The list manipulation is fixed to properly remove pages from the release
list.
This bug has been present from the very beginning of mmiotrace in the
mainline kernel. It was introduced in 0fd0e3da ("x86: mmiotrace full
patch, preview 1");
An urgent fix for Linus. Tested by Stuart (on 32-bit) and Pekka
(on amd and intel 64-bit systems, nouveau and nvidia proprietary).
Signed-off-by: Stuart Bennett <stuart@freedesktop.org> Signed-off-by: Pekka Paalanen <pq@iki.fi>
LKML-Reference: <20090308202135.34933feb@daedalus.pq.iki.fi> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Linus Torvalds [Sun, 8 Mar 2009 17:27:13 +0000 (10:27 -0700)]
Merge branch 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
x86, pebs: correct qualifier passed to ds_write_config() from ds_request_pebs()
x86, bts: remove bad warning
x86: add Dell XPS710 reboot quirk
x86, math-emu: fix init_fpu for task != current
x86: EFI: Back efi_ioremap with init_memory_mapping instead of FIX_MAP
x86: fix DMI on EFI
Linus Torvalds [Sun, 8 Mar 2009 17:24:39 +0000 (10:24 -0700)]
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/blackfin-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/cooloney/blackfin-2.6: (28 commits)
Blackfin arch: SPI_MMC is now mainlined MMC_SPI
Blackfin arch: disable legacy /proc/scsi/ support by default
Blackfin arch: remove duplicated ANOMALY_05000448 ifdef check
Blackfin arch: add stubs for anomalies 447 and 448
Blackfin arch: cleanup bfin_sport.h header and export it to userspace
Blackfin arch: fix bug - gdb signull case make trunk kernel panic frequently
Blackfin arch: remove spurious dash when dcache is off
Blackfin arch: mark init_pda as __init as only __init funcs all it
Blackfin arch: fix bug - On bf548-ezkit, ethernet fails to work after wakeup from "mem"
Blackfin arch: Random read/write errors are a bad thing
Blackfin arch: update default kernel config, select KSZ8893M driver for BF518
Blackfin arch: Fix bug - KGDB single step into the middle of a 4 bytes instruction on bf561 after soft bp is hit
Blackfin arch: Fix bug - make ksz8893m driver available when bfin_mac is enabled
Blackfin arch: make sure people do not set the kernel load address too high
Blackfin arch: fix bug - The SPORT_HYS bit is not set for BF561 0.5
Blackfin arch: update anomaly sheets to match latest public info
Blackfin arch: Fix BUG - kernel fails to build in pm.c when allow wakeup fromi standby by GPIO
Blackfin arch: PM_BFIN_WAKE_GP: update help
Blackfin arch: fix bug - kgdb fails to continue after setting breakpoint on bf561-ezkit kernel with smp patch
Blackfin arch: Enable Write Back Cache on all Blackfin Boards
...
Linus Torvalds [Sun, 8 Mar 2009 17:23:05 +0000 (10:23 -0700)]
Merge branch 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx
* 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx:
dmatest: fix use after free in dmatest_exit
ipu_idmac: fix spinlock type
iop-adma, mv_xor: fix mem leak on self-test setup failure
fsldma: fix off by one in dma_halt
I/OAT: fail self-test if callback test reaches timeout
I/OAT: update driver version and copyright dates
I/OAT: list usage cleanup
I/OAT: set tcp_dma_copybreak to 256k for I/OAT ver.3
I/OAT: cancel watchdog before dma remove
I/OAT: fail initialization on zero channels detection
I/OAT: do not set DCACTRL_CMPL_WRITE_ENABLE for I/OAT ver.3
I/OAT: add verification for proper APICID_TAG_MAP setting by BIOS
dmaengine: update kerneldoc
* git://git.kernel.org/pub/scm/linux/kernel/git/bart/ide-2.6:
ata: add CFA specific identify data words
remove stale comment from <linux/hdreg.h>
AT91: initialize Compact Flash on AT91SAM9263 cpu
ide: add at91_ide driver
ide: allow to wrap interrupt handler
ide-iops: fix odd-length ATAPI PIO transfers
ide: NULL noise: drivers/ide/ide-*.c
ide: expiry() returns int, negative expiry() return values won't be noticed
Linus Torvalds [Sun, 8 Mar 2009 17:22:01 +0000 (10:22 -0700)]
Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev
* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/jgarzik/libata-dev:
libata: Don't trust current capacity values in identify words 57-58
libata: make sure port is thawed when skipping resets
sata_nv: fix module parameter description
ahci: Add the Device IDs for MCP89 and remove IDs of MCP7B to/from ahci.c
libata: don't use on-stack sense buffer
libata: align ap->sector_buf
libata: fix dma_unmap_sg misuse
libata: change drive ready wait after hard reset to 5s
* git://git.kernel.org/pub/scm/linux/kernel/git/pkl/squashfs-linus:
Squashfs: frag_size should be signed, as it can hold an error result
Squashfs: fix documentation typo, Cramfs filesystem limit is 256 MiB
Squashfs: Fix oops when reading fsfuzzer corrupted filesystems
Linus Torvalds [Sun, 8 Mar 2009 17:03:31 +0000 (10:03 -0700)]
Merge branch 'fix/hda' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6
* 'fix/hda' of git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound-2.6:
ALSA: hda - Fix headphone-detect regression with multiple HP jacks
ALSA: hda - Fix typos in slave controls in patch_sigmatel.c
Ralf Baechle [Thu, 5 Mar 2009 10:45:48 +0000 (11:45 +0100)]
MIPS: compat: Implement is_compat_task.
This is a build fix required after "x86-64: seccomp: fix 32/64 syscall
hole" (commit 5b1017404aea6d2e552e991b3fd814d839e9cd67). MIPS doesn't
have the issue that was fixed for x86-64 by that patch.
This also doesn't solve the N32 issue which is that N32 seccomp processes
will be treated as non-compat processes thus only have access to N64
syscalls.
Cliff Wickman [Fri, 6 Mar 2009 23:30:56 +0000 (17:30 -0600)]
x86: UV: remove uv_flush_tlb_others() WARN_ON
In uv_flush_tlb_others() (arch/x86/kernel/tlb_uv.c),
the "WARN_ON(!in_atomic())" fails if CONFIG_PREEMPT is not enabled.
And CONFIG_PREEMPT is not enabled by default in the distribution that
most UV owners will use.
We could #ifdef CONFIG_PREEMPT the warning, but that is not good form.
And there seems to be no suitable fix to in_atomic() when CONFIG_PREMPT
is not on.
As Ingo commented:
> and we have no proper primitive to test for atomicity. (mainly
> because we dont know about atomicity on a non-preempt kernel)
Tejun Heo [Fri, 6 Mar 2009 15:44:13 +0000 (00:44 +0900)]
percpu: finer grained locking to break deadlock and allow atomic free
Impact: fix deadlock and allow atomic free
Percpu allocation always uses GFP_KERNEL and whole alloc/free paths
were protected by single mutex. All percpu allocations have been from
GFP_KERNEL-safe context and the original allocator had this assumption
too. However, by protecting both alloc and free paths with the same
mutex, the new allocator creates free -> alloc -> GFP_KERNEL
dependency which the original allocator didn't have. This can lead to
deadlock if free is called from FS or IO paths. Also, in general,
allocators are expected to allow free to be called from atomic
context.
This patch implements finer grained locking to break the deadlock and
allow atomic free. For details, please read the "Synchronization
rules" comment.
While at it, also add CONTEXT: to function comments to describe which
context they expect to be called from and what they do to it.
This problem was reported by Thomas Gleixner and Peter Zijlstra.
http://thread.gmane.org/gmane.linux.kernel/802384
Signed-off-by: Tejun Heo <tj@kernel.org> Reported-by: Thomas Gleixner <tglx@linutronix.de> Reported-by: Peter Zijlstra <peterz@infradead.org>
tracing/core: drop the old trace_printk() implementation in favour of trace_bprintk()
Impact: faster and lighter tracing
Now that we have trace_bprintk() which is faster and consume lesser
memory than trace_printk() and has the same purpose, we can now drop
the old implementation in favour of the binary one from trace_bprintk(),
which means we move all the implementation of trace_bprintk() to
trace_printk(), so the Api doesn't change except that we must now use
trace_seq_bprintk() to print the TRACE_PRINT entries.
Some changes result of this:
- Previously, trace_bprintk depended of a single tracer and couldn't
work without. This tracer has been dropped and the whole implementation
of trace_printk() (like the module formats management) is now integrated
in the tracing core (comes with CONFIG_TRACING), though we keep the file
trace_printk (previously trace_bprintk.c) where we can find the module
management. Thus we don't overflow trace.c
- changes some parts to use trace_seq_bprintk() to print TRACE_PRINT entries.
- change a bit trace_printk/trace_vprintk macros to support non-builtin formats
constants, and fix 'const' qualifiers warnings. But this is all transparent for
developers.
- etc...
V2:
- Rebase against last changes
- Fix mispell on the changelog
V3:
- Rebase against last changes (moving trace_printk() to kernel.h)
Lai Jiangshan [Fri, 6 Mar 2009 16:21:48 +0000 (17:21 +0100)]
tracing: add trace_bprintk()
Impact: add a generic printk() for tracing, like trace_printk()
trace_bprintk() uses the infrastructure to record events on ring_buffer.
[ fweisbec@gmail.com: ported to latest -tip, made it work if
!CONFIG_MODULES, never free the format strings from modules
because we can't keep track of them and conditionnaly create
the ftrace format strings section (reported by Steven Rostedt) ]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1236356510-8381-4-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Lai Jiangshan [Fri, 6 Mar 2009 16:21:47 +0000 (17:21 +0100)]
tracing: infrastructure for supporting binary record
Impact: save on memory for tracing
Current tracers are typically using a struct(like struct ftrace_entry,
struct ctx_switch_entry, struct special_entr etc...)to record a binary
event. These structs can only record a their own kind of events.
A new kind of tracer need a new struct and a lot of code too handle it.
So we need a generic binary record for events. This infrastructure
is for this purpose.
[fweisbec@gmail.com: rebase against latest -tip, make it safe while sched
tracing as reported by Steven Rostedt]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Acked-by: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <1236356510-8381-3-git-send-email-fweisbec@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
vsprintf: unify the format decoding layer for its 3 users
An new optimization is making its way to ftrace. Its purpose is to
make trace_printk() consuming less memory and be faster.
Written by Lai Jiangshan, the approach is to delay the formatting
job from tracing time to output time.
Currently, a call to trace_printk() will format the whole string and
insert it into the ring buffer. Then you can read it on /debug/tracing/trace
file.
The new implementation stores the address of the format string and
the binary parameters into the ring buffer, making the packet more compact
and faster to insert.
Later, when the user exports the traces, the format string is retrieved
with the binary parameters and the formatting job is eventually done.
The new implementation rewrites a lot of format decoding bits from
vsnprintf() function, making now 3 differents functions to maintain
in their duplicated parts of printf format decoding bits.
Suggested by Ingo Molnar, this patch tries to factorize the most
possible common bits from these functions.
The real common part between them is the format decoding. Although
they do somewhat similar jobs, their way to export or import the parameters
is very different. Thus, only the decoding layer is extracted, unless you see
other parts that could be worth factorized.
Changes in V2:
- Address a suggestion from Linus to group the format_decode() parameters inside
a structure.
Changes in v3:
- Address other cleanups suggested by Ingo and Linus such as passing the
printf_spec struct to the format helpers: pointer()/number()/string()
Note that this struct is passed by copy and not by address. This is to
avoid side effects because these functions often change these values and the
changes shoudn't be persistant when a callee helper returns.
It would be too risky.
- Various cleanups (code alignement, switch/case instead of if/else fountains).
- Fix a bug that printed the first format specifier following a %p
Changes in v4:
- drop unapropriate const qualifier loss while casting fmt to a char *
(thanks to Vegard Nossum for having pointed this out).
Cyrill Gorcunov [Fri, 6 Mar 2009 16:08:34 +0000 (19:08 +0300)]
x86: linkage.h - guard assembler specifics by __ASSEMBLY__
Stephen Rothwell reported:
|Today's linux-next build (x86_64 allmodconfig) produced this warning:
|
|In file included from drivers/char/epca.c:49:
|drivers/char/digiFep1.h:7:1: warning: "GLOBAL" redefined
|In file included from include/linux/linkage.h:5,
| from include/linux/kernel.h:11,
| from arch/x86/include/asm/system.h:10,
| from arch/x86/include/asm/processor.h:17,
| from include/linux/prefetch.h:14,
| from include/linux/list.h:6,
| from include/linux/module.h:9,
| from drivers/char/epca.c:29:
|arch/x86/include/asm/linkage.h:55:1: warning: this is the location of the previous definition
|
|Probably introduced by commit 95695547a7db44b88a7ee36cf5df188de267e99e
|("x86: asm linkage - introduce GLOBAL macro") from the x86 tree.
Any assembler specific snippets being placed in headers
are to be protected by __ASSEMBLY__. Fixed.
Also move __ALIGN definition under the same protection as well.
tracing, Text Edit Lock - SMP alternatives support
Use the mutual exclusion provided by the text edit lock in alternatives code.
Since alternative_smp_* will be called from module init code, etc,
we'd better protect it from other subsystems.
tracing, Text Edit Lock - Architecture Independent Code
This is an architecture independant synchronization around kernel text
modifications through use of a global mutex.
A mutex has been chosen so that kprobes, the main user of this, can sleep
during memory allocation between the memory read of the instructions it
must replace and the memory write of the breakpoint.
Other user of this interface: immediate values.
Paravirt and alternatives are always done when SMP is inactive, so there
is no need to use locks.
Tejun Heo [Fri, 6 Mar 2009 15:44:09 +0000 (00:44 +0900)]
percpu: move chunk area map extension out of area allocation
Impact: code reorganization for later changes
Separate out chunk area map extension into a separate function -
pcpu_extend_area_map() - and call it directly from pcpu_alloc() such
that pcpu_alloc_area() is guaranteed to have enough area map slots on
invocation.
With this change, pcpu_alloc_area() does only area allocation and the
only failure mode is when the chunk doens't have enough room, so
there's no need to distinguish it from memory allocation failures.
Make it return -1 on such cases instead of hacky -ENOSPC.
Tejun Heo [Fri, 6 Mar 2009 15:44:09 +0000 (00:44 +0900)]
percpu: replace pcpu_realloc() with pcpu_mem_alloc() and pcpu_mem_free()
Impact: code reorganization for later changes
With static map handling moved to pcpu_split_block(), pcpu_realloc()
only clutters the code and it's also unsuitable for scheduled locking
changes. Implement and use pcpu_mem_alloc/free() instead.
Markus Metzger [Thu, 5 Mar 2009 07:57:21 +0000 (08:57 +0100)]
x86, pebs: correct qualifier passed to ds_write_config() from ds_request_pebs()
ds_write_config() can write the BTS as well as the PEBS part of
the DS config. ds_request_pebs() passes the wrong qualifier, which
results in the wrong configuration to be written.
Markus Metzger [Thu, 5 Mar 2009 07:49:54 +0000 (08:49 +0100)]
x86, bts: remove bad warning
In case a ptraced task is reaped (while the tracer is still attached),
ds_exit_thread() is called before ptrace_exit(). The latter will
release the bts_tracer and remove the thread's ds_ctx.
The former will WARN() if the context is not NULL.
Oleg Nesterov submitted patches that move ptrace_exit() before
exit_thread() and thus reverse the order of the above calls.
Remove the bad warning. I will add it again when Oleg's changes are in.
Signed-off-by: Markus Metzger <markus.t.metzger@intel.com>
LKML-Reference: <20090305084954.A22000@sedona.ch.intel.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
Takashi Iwai [Fri, 6 Mar 2009 08:43:58 +0000 (09:43 +0100)]
ALSA: hda - Fix headphone-detect regression with multiple HP jacks
The recent changes over the DAC detection mechanism in patch_sigmatel.c
breaks the HP detection on the machines with multiple HP jacks.
It's basically because of the workaround to support the multi-channel
output. Since the HP detection is more important feature, disable
the HP-swap workaroud temporarily.
Jens Axboe [Fri, 6 Mar 2009 07:55:24 +0000 (08:55 +0100)]
block: fix missing bio back/front segment size setting in blk_recount_segments()
Commit 1e42807918d17e8c93bf14fbb74be84b141334c1 introduced a bug where we
don't get front/back segment sizes in the bio in blk_recount_segments().
Fix this by tracking the back bio as well as the front bio in
__blk_recalc_rq_segments(), this also cleans up the interface by getting
rid of the segment size pointer passing.
Tejun Heo [Fri, 6 Mar 2009 05:33:59 +0000 (14:33 +0900)]
x86, percpu: setup reserved percpu area for x86_64
Impact: fix relocation overflow during module load
x86_64 uses 32bit relocations for symbol access and static percpu
symbols whether in core or modules must be inside 2GB of the percpu
segement base which the dynamic percpu allocator doesn't guarantee.
This patch makes x86_64 reserve PERCPU_MODULE_RESERVE bytes in the
first chunk so that module percpu areas are always allocated from the
first chunk which is always inside the relocatable range.
This problem exists for any percpu allocator but is easily triggered
when using the embedding allocator because the second chunk is located
beyond 2GB on it.
This patch also changes the meaning of PERCPU_DYNAMIC_RESERVE such
that it only indicates the size of the area to reserve for dynamic
allocation as static and dynamic areas can be separate. New
PERCPU_DYNAMIC_RESERVED is increased by 4k for both 32 and 64bits as
the reserved area separation eats away some allocatable space and
having slightly more headroom (currently between 4 and 8k after
minimal boot sans module area) makes sense for common case
performance.
x86_32 can address anywhere from anywhere and doesn't need reserving.
Mike Galbraith first reported the problem first and bisected it to the
embedding percpu allocator commit.
Tejun Heo [Fri, 6 Mar 2009 05:33:59 +0000 (14:33 +0900)]
percpu, module: implement reserved allocation and use it for module percpu variables
Impact: add reserved allocation functionality and use it for module
percpu variables
This patch implements reserved allocation from the first chunk. When
setting up the first chunk, arch can ask to set aside certain number
of bytes right after the core static area which is available only
through a separate reserved allocator. This will be used primarily
for module static percpu variables on architectures with limited
relocation range to ensure that the module perpcu symbols are inside
the relocatable range.
If reserved area is requested, the first chunk becomes reserved and
isn't available for regular allocation. If the first chunk also
includes piggy-back dynamic allocation area, a separate chunk mapping
the same region is created to serve dynamic allocation. The first one
is called static first chunk and the second dynamic first chunk.
Although they share the page map, their different area map
initializations guarantee they serve disjoint areas according to their
purposes.
If arch doesn't setup reserved area, reserved allocation is handled
like any other allocation.
Tejun Heo [Fri, 6 Mar 2009 05:33:59 +0000 (14:33 +0900)]
x86: make embedding percpu allocator return excessive free space
Impact: reduce unnecessary memory usage on certain configurations
Embedding percpu allocator allocates unit_size *
smp_num_possible_cpus() bytes consecutively and use it for the first
chunk. However, if the static area is small, this can result in
excessive prellocated free space in the first chunk due to
PCPU_MIN_UNIT_SIZE restriction.
This patch makes embedding percpu allocator preallocate only what's
necessary as described by PERPCU_DYNAMIC_RESERVE and return the
leftover to the bootmem allocator.
Tejun Heo [Fri, 6 Mar 2009 05:33:59 +0000 (14:33 +0900)]
percpu: use negative for auto for pcpu_setup_first_chunk() arguments
Impact: argument semantic cleanup
In pcpu_setup_first_chunk(), zero @unit_size and @dyn_size meant
auto-sizing. It's okay for @unit_size as 0 doesn't make sense but 0
dynamic reserve size is valid. Alos, if arch @dyn_size is calculated
from other parameters, it might end up passing in 0 @dyn_size and
malfunction when the size is automatically adjusted.
This patch makes both @unit_size and @dyn_size ssize_t and use -1 for
auto sizing.
Tejun Heo [Fri, 6 Mar 2009 05:33:59 +0000 (14:33 +0900)]
percpu: improve first chunk initial area map handling
Impact: no functional change
When the first chunk is created, its initial area map is not allocated
because kmalloc isn't online yet. The map is allocated and
initialized on the first allocation request on the chunk. This works
fine but the scattering of initialization logic between the init
function and allocation path is a bit confusing.
This patch makes the first chunk initialize and use minimal statically
allocated map from pcpu_setpu_first_chunk(). The map resizing path
still needs to handle this specially but it's more straight-forward
and gives more latitude to the init path. This will ease future
changes.
Steven Rostedt [Fri, 6 Mar 2009 02:35:29 +0000 (21:35 -0500)]
tracing: add format files for ftrace default entries
Impact: allow user apps to read binary format of basic ftrace entries
Currently, only defined raw events export their formats so a binary
reader can parse them. There's no reason that the default ftrace entries
can't export their formats.
This patch adds a subsystem called "ftrace" in the events directory
that includes the ftrace entries for basic ftrace recorded items.
These only have three files in the events directory:
type : printf
available_types : printf
format : format for the event entry
Steven Rostedt [Thu, 5 Mar 2009 16:45:43 +0000 (11:45 -0500)]
tracing: move print of event format to separate file
Impact: clean up
Move the macro that creates the event format file to a separate header.
This will allow the default ftrace events to use this same macro
to create the formats to read those events.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
The tick rate define (ORION5X_TCLK) was removed in favor of a runtime
detection. The quick fix is to add the define in the watchdog driver.
The fix is not correct for all supported orion5x platforms, but since
the supported platforms right now are 133 Mhz and 166 Mhz, it won't
be _that_ far off. ;-) A fix that uses the runtime-determined timer
tick rate will be applied later.
Signed-off-by: Wim Van Sebroeck <wim@iguana.be> Cc: Kristof Provost <kristof@sigsegv.be> Acked-by: Lennert Buytenhek <buytenh@wantstofly.org> Cc: Nicolas Pitre <nico@cam.org> Cc: Russell King <rmk@arm.linux.org.uk> Cc: Andrew Morton <akpm@linux-foundation.org>
projects / linux-beck.git / log