Commit Graph

126 Commits

Author SHA1 Message Date
Arnd Bergmann 6038f373a3 llseek: automatically add .llseek fop
All file_operations should get a .llseek operation so we can make
nonseekable_open the default for future file operations without a
.llseek pointer.

The three cases that we can automatically detect are no_llseek, seq_lseek
and default_llseek. For cases where we can we can automatically prove that
the file offset is always ignored, we use noop_llseek, which maintains
the current behavior of not returning an error from a seek.

New drivers should normally not use noop_llseek but instead use no_llseek
and call nonseekable_open at open time.  Existing drivers can be converted
to do the same when the maintainer knows for certain that no user code
relies on calling seek on the device file.

The generated code is often incorrectly indented and right now contains
comments that clarify for each added line why a specific variant was
chosen. In the version that gets submitted upstream, the comments will
be gone and I will manually fix the indentation, because there does not
seem to be a way to do that using coccinelle.

Some amount of new code is currently sitting in linux-next that should get
the same modifications, which I will do at the end of the merge window.

Many thanks to Julia Lawall for helping me learn to write a semantic
patch that does all this.

===== begin semantic patch =====
// This adds an llseek= method to all file operations,
// as a preparation for making no_llseek the default.
//
// The rules are
// - use no_llseek explicitly if we do nonseekable_open
// - use seq_lseek for sequential files
// - use default_llseek if we know we access f_pos
// - use noop_llseek if we know we don't access f_pos,
//   but we still want to allow users to call lseek
//
@ open1 exists @
identifier nested_open;
@@
nested_open(...)
{
<+...
nonseekable_open(...)
...+>
}

@ open exists@
identifier open_f;
identifier i, f;
identifier open1.nested_open;
@@
int open_f(struct inode *i, struct file *f)
{
<+...
(
nonseekable_open(...)
|
nested_open(...)
)
...+>
}

@ read disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
<+...
(
   *off = E
|
   *off += E
|
   func(..., off, ...)
|
   E = *off
)
...+>
}

@ read_no_fpos disable optional_qualifier exists @
identifier read_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t read_f(struct file *f, char *p, size_t s, loff_t *off)
{
... when != off
}

@ write @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
expression E;
identifier func;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
<+...
(
  *off = E
|
  *off += E
|
  func(..., off, ...)
|
  E = *off
)
...+>
}

@ write_no_fpos @
identifier write_f;
identifier f, p, s, off;
type ssize_t, size_t, loff_t;
@@
ssize_t write_f(struct file *f, const char *p, size_t s, loff_t *off)
{
... when != off
}

@ fops0 @
identifier fops;
@@
struct file_operations fops = {
 ...
};

@ has_llseek depends on fops0 @
identifier fops0.fops;
identifier llseek_f;
@@
struct file_operations fops = {
...
 .llseek = llseek_f,
...
};

@ has_read depends on fops0 @
identifier fops0.fops;
identifier read_f;
@@
struct file_operations fops = {
...
 .read = read_f,
...
};

@ has_write depends on fops0 @
identifier fops0.fops;
identifier write_f;
@@
struct file_operations fops = {
...
 .write = write_f,
...
};

@ has_open depends on fops0 @
identifier fops0.fops;
identifier open_f;
@@
struct file_operations fops = {
...
 .open = open_f,
...
};

// use no_llseek if we call nonseekable_open
////////////////////////////////////////////
@ nonseekable1 depends on !has_llseek && has_open @
identifier fops0.fops;
identifier nso ~= "nonseekable_open";
@@
struct file_operations fops = {
...  .open = nso, ...
+.llseek = no_llseek, /* nonseekable */
};

@ nonseekable2 depends on !has_llseek @
identifier fops0.fops;
identifier open.open_f;
@@
struct file_operations fops = {
...  .open = open_f, ...
+.llseek = no_llseek, /* open uses nonseekable */
};

// use seq_lseek for sequential files
/////////////////////////////////////
@ seq depends on !has_llseek @
identifier fops0.fops;
identifier sr ~= "seq_read";
@@
struct file_operations fops = {
...  .read = sr, ...
+.llseek = seq_lseek, /* we have seq_read */
};

// use default_llseek if there is a readdir
///////////////////////////////////////////
@ fops1 depends on !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier readdir_e;
@@
// any other fop is used that changes pos
struct file_operations fops = {
... .readdir = readdir_e, ...
+.llseek = default_llseek, /* readdir is present */
};

// use default_llseek if at least one of read/write touches f_pos
/////////////////////////////////////////////////////////////////
@ fops2 depends on !fops1 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read.read_f;
@@
// read fops use offset
struct file_operations fops = {
... .read = read_f, ...
+.llseek = default_llseek, /* read accesses f_pos */
};

@ fops3 depends on !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write.write_f;
@@
// write fops use offset
struct file_operations fops = {
... .write = write_f, ...
+	.llseek = default_llseek, /* write accesses f_pos */
};

// Use noop_llseek if neither read nor write accesses f_pos
///////////////////////////////////////////////////////////

@ fops4 depends on !fops1 && !fops2 && !fops3 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
identifier write_no_fpos.write_f;
@@
// write fops use offset
struct file_operations fops = {
...
 .write = write_f,
 .read = read_f,
...
+.llseek = noop_llseek, /* read and write both use no f_pos */
};

@ depends on has_write && !has_read && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier write_no_fpos.write_f;
@@
struct file_operations fops = {
... .write = write_f, ...
+.llseek = noop_llseek, /* write uses no f_pos */
};

@ depends on has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
identifier read_no_fpos.read_f;
@@
struct file_operations fops = {
... .read = read_f, ...
+.llseek = noop_llseek, /* read uses no f_pos */
};

@ depends on !has_read && !has_write && !fops1 && !fops2 && !has_llseek && !nonseekable1 && !nonseekable2 && !seq @
identifier fops0.fops;
@@
struct file_operations fops = {
...
+.llseek = noop_llseek, /* no read or write fn */
};
===== End semantic patch =====

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Julia Lawall <julia@diku.dk>
Cc: Christoph Hellwig <hch@infradead.org>
2010-10-15 15:53:27 +02:00
Len Brown 7fcca7d900 intel_idle: enable Atom C6
ATM-C6 was commented out, pending public documentation.

https://bugzilla.kernel.org/show_bug.cgi?id=19762

Tested-by: Dennis Jansen <Dennis.Jansen@...>
Signed-off-by: Len Brown <len.brown@intel.com>
2010-10-08 22:16:27 -04:00
Suresh Siddha 6110a1f43c intel_idle: Voluntary leave_mm before entering deeper
Avoid TLB flush IPIs for the cores in deeper c-states by voluntary leave_mm()
before entering into that state. CPUs tend to flush TLB in those c-states
anyways.

acpi_idle does this with C3-type states, but it was not caried over
when intel_idle was introduced.  intel_idle can apply it
to C-states in addition to those that ACPI might export as C3...

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2010-09-30 21:19:22 -04:00
Namhyung Kim 3265eba0be intel_idle: add missing __percpu markup
intel_idle_cpuidle_devices is a percpu pointer
but was missing __percpu markup.

Signed-off-by: Namhyung Kim <namhyung@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Len Brown <len.brown@intel.com>
2010-09-28 23:30:39 -04:00
Thomas Weber 68f160125f intel_idle: Change mode 755 => 644
Remove execution permission from source file.

Signed-off-by: Thomas Weber <weber@corscience.de>
Signed-off-by: Len Brown <len.brown@intel.com>
2010-09-28 23:30:39 -04:00
H. Peter Anvin bc83cccc76 x86, mwait: Move mwait constants to a common header file
We have MWAIT constants spread across three different .c files, for no
good reason.  Move them all into a common header file.

Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Reviewed-by: Arjan van de Ven <arjan@linux.intel.com>
Cc: Len Brown <lenb@kernel.org>
LKML-Reference: <tip-*@git.kernel.org>
2010-09-17 15:36:40 -07:00
Linus Torvalds 5a4179460c Merge branch 'idle-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6
* 'idle-release' of git://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux-idle-2.6:
  intel_idle: recognize Lincroft Atom Processor
  intel_idle: no longer EXPERIMENTAL
  intel_idle: disable module support
  intel_idle: add support for Westmere-EX
  intel_idle: delete power_policy modparam, and choose substate functions
  intel_idle: delete substates DEBUG modparam
2010-08-15 11:17:52 -07:00
Arjan van de Ven 4725fd3ce9 intel_idle: recognize Lincroft Atom Processor
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2010-08-14 22:54:52 -04:00
Len Brown 5a5e28daea intel_idle: no longer EXPERIMENTAL
This is a fully supported driver.

Signed-off-by: Len Brown <len.brown@intel.com>
2010-08-14 14:44:08 -04:00
Len Brown 6ce9cd8669 intel_idle: disable module support
Right now the module capability is cauing more trouble
than it is worth.  At least one distro built intel_idle as a module
where it lost the init race with ACPI, making it useless.

Make intel_idle bool so that if you select it, you will use it.

We can restore module capability after cpuidle is enhanced
to handle run-time changing of idle drivers.

Signed-off-by: Len Brown <len.brown@intel.com>
2010-08-14 14:40:36 -04:00
Linus Torvalds 8d91530c5f Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq
* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/davej/cpufreq:
  [CPUFREQ] Remove pointless printk from p4-clockmod.
  [CPUFREQ] Fix section mismatch for powernow_cpu_init in powernow-k7.c
  [CPUFREQ] Fix section mismatch for longhaul_cpu_init.
  [CPUFREQ] Fix section mismatch for longrun_cpu_init.
  [CPUFREQ] powernow-k8: Fix misleading variable naming
  [CPUFREQ] Convert pci_table entries to PCI_VDEVICE (if PCI_ANY_ID is used)
  [CPUFREQ] arch/x86/kernel/cpu/cpufreq: use for_each_pci_dev()
  [CPUFREQ] fix brace coding style issue.
  [CPUFREQ] x86 cpufreq: Make trace_power_frequency cpufreq driver independent
  [CPUFREQ] acpi-cpufreq: Fix CPU_ANY CPUFREQ_{PRE,POST}CHANGE notification
  [CPUFREQ] ondemand: don't synchronize sample rate unless multiple cpus present
  [CPUFREQ] unexport (un)lock_policy_rwsem* functions
  [CPUFREQ] ondemand: Refactor frequency increase code
  [CPUFREQ] powernow-k8: On load failure, remind the user to enable support in BIOS setup
  [CPUFREQ] powernow-k8: Limit Pstate transition latency check
  [CPUFREQ] Fix PCC driver error path
  [CPUFREQ] fix double freeing in error path of pcc-cpufreq
  [CPUFREQ] pcc driver should check for pcch method before calling _OSC
  [CPUFREQ] fix memory leak in cpufreq_add_dev
  [CPUFREQ] revert "[CPUFREQ] remove rwsem lock from CPUFREQ_GOV_STOP call (second call site)"

Manually fix up non-data merge conflict introduced by new calling
conventions for trace_power_start() in commit 6f4f2723d0 ("x86
cpufreq: Make trace_power_frequency cpufreq driver independent"), which
didn't update the intel_idle native hardware cpuidle driver.
2010-08-04 11:13:36 -07:00
Len Brown ec67a2ba36 intel_idle: add support for Westmere-EX
Signed-off-by: Len Brown <len.brown@intel.com>
2010-07-26 23:40:19 -04:00
Len Brown 0394c6676e intel_idle: delete power_policy modparam, and choose substate functions
The idea behind power policy was that it would start off as a modparam,
and then hook into the new "global" in-kernel power vs energy tunable.
But that tunable isn't happening, so delete the hook here.

With the policy hook gone, the sub-state choice functions
do not do anything useful, so delete them from the critical path.

To handle sub-states in the future, we will advertise them
with dedicated cpuidle_state entries.  That is necessary
because some of the sub-states will have substantially different
properties than their peer sub-states.

Signed-off-by: Len Brown <len.brown@intel.com>
2010-07-23 16:04:46 -04:00
Len Brown c4236282e5 intel_idle: delete substates DEBUG modparam
it isn't useful anymore

Signed-off-by: Len Brown <len.brown@intel.com>
2010-07-23 16:00:33 -04:00
Len Brown 2671717265 intel_idle: native hardware cpuidle driver for latest Intel processors
This EXPERIMENTAL driver supersedes acpi_idle on
Intel Atom Processors, Intel Core i3/i5/i7 Processors
and associated Intel Xeon processors.

It does not support the Intel Core2 processor or earlier.

For kernels configured with ACPI, CONFIG_INTEL_IDLE=y
allows intel_idle to probe before the ACPI processor driver.
Booting with "intel_idle.max_cstate=0" disables intel_idle
and the system will fall back on ACPI's "acpi_idle".

Typical Linux distributions load ACPI processor module early,
making CONFIG_INTEL_IDLE=m not easily useful on ACPI platforms.

intel_idle probes all processors at module_init time.
Processors that are hot-added later will be limited
to using C1 in idle.

Signed-off-by: Len Brown <len.brown@intel.com>
2010-05-28 14:26:20 -04:00
Tejun Heo 5a0e3ad6af include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files.  percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.

percpu.h -> slab.h dependency is about to be removed.  Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability.  As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.

  http://userweb.kernel.org/~tj/misc/slabh-sweep.py

The script does the followings.

* Scan files for gfp and slab usages and update includes such that
  only the necessary includes are there.  ie. if only gfp is used,
  gfp.h, if slab is used, slab.h.

* When the script inserts a new include, it looks at the include
  blocks and try to put the new include such that its order conforms
  to its surrounding.  It's put in the include block which contains
  core kernel includes, in the same order that the rest are ordered -
  alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
  doesn't seem to be any matching order.

* If the script can't find a place to put a new include (mostly
  because the file doesn't have fitting include block), it prints out
  an error message indicating which .h file needs to be added to the
  file.

The conversion was done in the following steps.

1. The initial automatic conversion of all .c files updated slightly
   over 4000 files, deleting around 700 includes and adding ~480 gfp.h
   and ~3000 slab.h inclusions.  The script emitted errors for ~400
   files.

2. Each error was manually checked.  Some didn't need the inclusion,
   some needed manual addition while adding it to implementation .h or
   embedding .c file was more appropriate for others.  This step added
   inclusions to around 150 files.

3. The script was run again and the output was compared to the edits
   from #2 to make sure no file was left behind.

4. Several build tests were done and a couple of problems were fixed.
   e.g. lib/decompress_*.c used malloc/free() wrappers around slab
   APIs requiring slab.h to be added manually.

5. The script was run on all .h files but without automatically
   editing them as sprinkling gfp.h and slab.h inclusions around .h
   files could easily lead to inclusion dependency hell.  Most gfp.h
   inclusion directives were ignored as stuff from gfp.h was usually
   wildly available and often used in preprocessor macros.  Each
   slab.h inclusion directive was examined and added manually as
   necessary.

6. percpu.h was updated not to include slab.h.

7. Build test were done on the following configurations and failures
   were fixed.  CONFIG_GCOV_KERNEL was turned off for all tests (as my
   distributed build env didn't work with gcov compiles) and a few
   more options had to be turned off depending on archs to make things
   build (like ipr on powerpc/64 which failed due to missing writeq).

   * x86 and x86_64 UP and SMP allmodconfig and a custom test config.
   * powerpc and powerpc64 SMP allmodconfig
   * sparc and sparc64 SMP allmodconfig
   * ia64 SMP allmodconfig
   * s390 SMP allmodconfig
   * alpha SMP allmodconfig
   * um on x86_64 SMP allmodconfig

8. percpu.h modifications were reverted so that it could be applied as
   a separate patch and serve as bisection point.

Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.

Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-30 22:02:32 +09:00
Rusty Russell cc216b86e5 cpumask: convert drivers/idle/i7300_idle.c to cpumask_var_t
Fairly simple transformation:
1) cpumask_t -> cpumask_var_t and alloc_cpumask_var/free_cpumask_var
   (which are a NOOP unless CONFIG_CPUMASK_OFFSTACK=y).
2) cpu_set -> cpumask_set_cpu
3) cpus_weight -> cpumask_weight
4) cpu_clear -> cpumask_clear_cpu

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
To: Andy Henroid <andrew.d.henroid@intel.com>
2009-12-17 11:43:25 +10:30
Dan Williams 09c8a5b85e ioat: switch watchdog and reset handler from workqueue to timer
In order to support dynamic resizing of the descriptor ring or polling
for a descriptor in the presence of a hung channel the reset handler
needs to make progress while in a non-preemptible context.  The current
workqueue implementation precludes polling channel reset completion
under spin_lock().

This conversion also allows us to return to opportunistic cleanup in the
ioat2 case as the timer implementation guarantees at least one cleanup
after every descriptor is submitted.  This means the worst case
completion latency becomes the timer frequency (for exceptional
circumstances), but with the benefit of avoiding busy waiting when the
lock is contended.

Signed-off-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2009-09-08 17:30:24 -07:00
Dan Williams 584ec22759 ioat: move to drivers/dma/ioat/
When first created the ioat driver was the only inhabitant of
drivers/dma/.  Now, it is the only multi-file (more than a .c and a .h)
driver in the directory.  Moving it to an ioat/ subdirectory allows the
naming convention to be cleaned up, and allows for future splitting of
the source files by hardware version (v1, v2, and v3).

Signed-off-by: Maciej Sosnowski <maciej.sosnowski@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
2009-07-28 14:32:12 -07:00
Len Brown 2f102607ac i7300_idle: allow testing on i5000-series hardware w/o re-compile
Testing the i7300_idle driver on i5000-series hardware required
an edit to i7300_idle.h to "#define SUPPORT_I5000 1" and a re-build
of both i7300_idle and ioat_dma.

Replace that build-time scheme with a load-time module parameter:
"7300_idle.forceload=1" to make it easier to test the driver
on hardware that while not officially validated, works fine
and is much more commonly available.

By default (no modparam) the driver will continue to load
only on the i7300.

Note that ioat_dma runs a copy of i7300_idle's probe routine
to know to reserve an IOAT channel for i7300_idle.
This change makes ioat_dma do that always on the i5000,
just like it does on the i7300.

Signed-off-by: Len Brown <len.brown@intel.com>
Acked-by: Andrew Henroid <andrew.d.henroid@intel.com>
2009-05-28 20:52:40 -04:00
Yang Hongyang 6a35528a83 dma-mapping: replace all DMA_64BIT_MASK macro with DMA_BIT_MASK(64)
Replace all DMA_64BIT_MASK macro with DMA_BIT_MASK(64)

Signed-off-by: Yang Hongyang<yanghy@cn.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-04-07 08:31:10 -07:00
Kay Sievers 24f81a7047 i7300_idle: struct device - replace bus_id with dev_name(), dev_set_name()
CC: Andy Henroid <andrew.d.henroid@intel.com>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2009-01-06 10:44:39 -08:00
Venki Pallipadi 2830c9fb8e i7300_idle: Kconfig, show menu only on x86_64
...since today it contains only a single driver
which is visible to just x86_64

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2008-10-28 00:14:47 -04:00
Venki Pallipadi 33093e186c i7300_idle: Cleanup based review comments
Cleanup of i7300 idle driver based on review comments from Randy Dunlap,
Andi Kleen and Len Brown.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2008-10-24 12:55:14 -04:00
Venki Pallipadi 3ad0b02e4c i7300_idle: Disable ioat channel only on platforms where ile driver can load
Based on input from Andi Kleen:
share the platform detection code with ioat_dma and disable the channel in
dma engine only for specific platforms.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
2008-10-24 12:54:18 -04:00
Andy Henroid 27471fdb32 i7300_idle driver v1.55
The Intel 7300 Memory Controller supports dynamic throttling of memory which can
be used to save power when system is idle. This driver does the memory
throttling when all CPUs are idle on such a system.

Refer to "Intel 7300 Memory Controller Hub (MCH)" datasheet
for the config space description.

Signed-off-by: Andy Henroid <andrew.d.henroid@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
2008-10-21 23:58:41 -04:00