2019-05-27 14:55:05 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-or-later
|
2008-07-08 13:45:11 +08:00
|
|
|
/* IBM POWER Barrier Synchronization Register Driver
|
|
|
|
*
|
|
|
|
* Copyright IBM Corporation 2008
|
|
|
|
*
|
|
|
|
* Author: Sonny Rao <sonnyrao@us.ibm.com>
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/kernel.h>
|
|
|
|
#include <linux/of.h>
|
2013-09-18 03:28:33 +08:00
|
|
|
#include <linux/of_address.h>
|
2008-07-08 13:45:11 +08:00
|
|
|
#include <linux/of_device.h>
|
|
|
|
#include <linux/of_platform.h>
|
2010-07-30 01:49:01 +08:00
|
|
|
#include <linux/fs.h>
|
2008-07-08 13:45:11 +08:00
|
|
|
#include <linux/module.h>
|
|
|
|
#include <linux/cdev.h>
|
|
|
|
#include <linux/list.h>
|
|
|
|
#include <linux/mm.h>
|
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>
2010-03-24 16:04:11 +08:00
|
|
|
#include <linux/slab.h>
|
2008-07-08 13:45:11 +08:00
|
|
|
#include <asm/io.h>
|
|
|
|
|
|
|
|
/*
|
|
|
|
This driver exposes a special register which can be used for fast
|
|
|
|
synchronization across a large SMP machine. The hardware is exposed
|
|
|
|
as an array of bytes where each process will write to one of the bytes to
|
|
|
|
indicate it has finished the current stage and this update is broadcast to
|
|
|
|
all processors without having to bounce a cacheline between them. In
|
|
|
|
POWER5 and POWER6 there is one of these registers per SMP, but it is
|
|
|
|
presented in two forms; first, it is given as a whole and then as a number
|
|
|
|
of smaller registers which alias to parts of the single whole register.
|
|
|
|
This can potentially allow multiple groups of processes to each have their
|
|
|
|
own private synchronization device.
|
|
|
|
|
|
|
|
Note that this hardware *must* be written to using *only* single byte writes.
|
|
|
|
It may be read using 1, 2, 4, or 8 byte loads which must be aligned since
|
|
|
|
this region is treated as cache-inhibited processes should also use a
|
|
|
|
full sync before and after writing to the BSR to ensure all stores and
|
|
|
|
the BSR update have made it to all chips in the system
|
|
|
|
*/
|
|
|
|
|
|
|
|
/* This is arbitrary number, up to Power6 it's been 17 or fewer */
|
|
|
|
#define BSR_MAX_DEVS (32)
|
|
|
|
|
|
|
|
struct bsr_dev {
|
|
|
|
u64 bsr_addr; /* Real address */
|
|
|
|
u64 bsr_len; /* length of mem region we can map */
|
|
|
|
unsigned bsr_bytes; /* size of the BSR reg itself */
|
|
|
|
unsigned bsr_stride; /* interval at which BSR repeats in the page */
|
|
|
|
unsigned bsr_type; /* maps to enum below */
|
|
|
|
unsigned bsr_num; /* bsr id number for its type */
|
|
|
|
int bsr_minor;
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
struct list_head bsr_list;
|
|
|
|
|
2008-07-08 13:45:11 +08:00
|
|
|
dev_t bsr_dev;
|
|
|
|
struct cdev bsr_cdev;
|
|
|
|
struct device *bsr_device;
|
|
|
|
char bsr_name[32];
|
|
|
|
|
|
|
|
};
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
static unsigned total_bsr_devs;
|
|
|
|
static struct list_head bsr_devs = LIST_HEAD_INIT(bsr_devs);
|
2008-07-08 13:45:11 +08:00
|
|
|
static struct class *bsr_class;
|
|
|
|
static int bsr_major;
|
|
|
|
|
|
|
|
enum {
|
2009-06-18 23:14:36 +08:00
|
|
|
BSR_8 = 0,
|
|
|
|
BSR_16 = 1,
|
|
|
|
BSR_64 = 2,
|
|
|
|
BSR_128 = 3,
|
|
|
|
BSR_4096 = 4,
|
|
|
|
BSR_UNKNOWN = 5,
|
|
|
|
BSR_MAX = 6,
|
2008-07-08 13:45:11 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static unsigned bsr_types[BSR_MAX];
|
|
|
|
|
|
|
|
static ssize_t
|
|
|
|
bsr_size_show(struct device *dev, struct device_attribute *attr, char *buf)
|
|
|
|
{
|
|
|
|
struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
|
|
|
|
return sprintf(buf, "%u\n", bsr_dev->bsr_bytes);
|
|
|
|
}
|
2013-07-25 06:05:06 +08:00
|
|
|
static DEVICE_ATTR_RO(bsr_size);
|
2008-07-08 13:45:11 +08:00
|
|
|
|
|
|
|
static ssize_t
|
|
|
|
bsr_stride_show(struct device *dev, struct device_attribute *attr, char *buf)
|
|
|
|
{
|
|
|
|
struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
|
|
|
|
return sprintf(buf, "%u\n", bsr_dev->bsr_stride);
|
|
|
|
}
|
2013-07-25 06:05:06 +08:00
|
|
|
static DEVICE_ATTR_RO(bsr_stride);
|
2008-07-08 13:45:11 +08:00
|
|
|
|
|
|
|
static ssize_t
|
2013-07-25 06:05:06 +08:00
|
|
|
bsr_length_show(struct device *dev, struct device_attribute *attr, char *buf)
|
2008-07-08 13:45:11 +08:00
|
|
|
{
|
|
|
|
struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
|
2009-01-06 22:28:48 +08:00
|
|
|
return sprintf(buf, "%llu\n", bsr_dev->bsr_len);
|
2008-07-08 13:45:11 +08:00
|
|
|
}
|
2013-07-25 06:05:06 +08:00
|
|
|
static DEVICE_ATTR_RO(bsr_length);
|
2008-07-08 13:45:11 +08:00
|
|
|
|
2013-07-25 06:05:06 +08:00
|
|
|
static struct attribute *bsr_dev_attrs[] = {
|
|
|
|
&dev_attr_bsr_size.attr,
|
|
|
|
&dev_attr_bsr_stride.attr,
|
|
|
|
&dev_attr_bsr_length.attr,
|
|
|
|
NULL,
|
2008-07-08 13:45:11 +08:00
|
|
|
};
|
2013-07-25 06:05:06 +08:00
|
|
|
ATTRIBUTE_GROUPS(bsr_dev);
|
2008-07-08 13:45:11 +08:00
|
|
|
|
|
|
|
static int bsr_mmap(struct file *filp, struct vm_area_struct *vma)
|
|
|
|
{
|
|
|
|
unsigned long size = vma->vm_end - vma->vm_start;
|
|
|
|
struct bsr_dev *dev = filp->private_data;
|
powerpc/BSR: Fix BSR to allow mmap of small BSR on 64k kernel
On Mon, Nov 17, 2008 at 01:26:13AM -0600, Sonny Rao wrote:
> On Fri, Nov 07, 2008 at 04:28:29PM +1100, Paul Mackerras wrote:
> > Sonny Rao writes:
> >
> > > Fix the BSR driver to allow small BSR devices, which are limited to a
> > > single 4k space, on a 64k page kernel. Previously the driver would
> > > reject the mmap since the size was smaller than PAGESIZE (or because
> > > the size was greater than the size of the device). Now, we check for
> > > this case use remap_4k_pfn(). Also, take out code to set vm_flags,
> > > as the remap_pfn functions will do this for us.
> >
> > Thanks.
> >
> > Do we know that the BSR size will always be 4k if it's not a multiple
> > of 64k? Is it possible that we could get 8k, 16k or 32k or BSRs?
> > If it is possible, what does the user need to be able to do? Do they
> > just want to map 4k, or might then want to map the whole thing?
>
>
> Hi Paul, I took a look at changing the driver to reject a request for
> mapping more than a single 4k page, however the only indication we get
> of the requested size in the mmap function is the vma size, and this
> is always one page at minimum. So, it's not possible to determine if
> the user wants one 4k page or more. As I noted in my first response,
> there is only one case where this is even possible and I don't think
> it is a significant concern.
>
> I did notice that I left out the check to see if the user is trying to
> map more than the device length, so I fixed that. Here's the revised
> patch.
Alright, I've reworked this now so that if we get one of these cases
where there's a bsr that's > 4k and < 64k on a 64k kernel we'll only
advertise that it is a 4k BSR to userspace. I think this is the best
solution since user programs are only supposed to look at sysfs to
determine how much can be mapped, and libbsr does this as well.
Please consider for 2.6.31 as a fix, thanks.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-06-18 23:13:04 +08:00
|
|
|
int ret;
|
2008-07-08 13:45:11 +08:00
|
|
|
|
|
|
|
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
|
|
|
|
|
powerpc/BSR: Fix BSR to allow mmap of small BSR on 64k kernel
On Mon, Nov 17, 2008 at 01:26:13AM -0600, Sonny Rao wrote:
> On Fri, Nov 07, 2008 at 04:28:29PM +1100, Paul Mackerras wrote:
> > Sonny Rao writes:
> >
> > > Fix the BSR driver to allow small BSR devices, which are limited to a
> > > single 4k space, on a 64k page kernel. Previously the driver would
> > > reject the mmap since the size was smaller than PAGESIZE (or because
> > > the size was greater than the size of the device). Now, we check for
> > > this case use remap_4k_pfn(). Also, take out code to set vm_flags,
> > > as the remap_pfn functions will do this for us.
> >
> > Thanks.
> >
> > Do we know that the BSR size will always be 4k if it's not a multiple
> > of 64k? Is it possible that we could get 8k, 16k or 32k or BSRs?
> > If it is possible, what does the user need to be able to do? Do they
> > just want to map 4k, or might then want to map the whole thing?
>
>
> Hi Paul, I took a look at changing the driver to reject a request for
> mapping more than a single 4k page, however the only indication we get
> of the requested size in the mmap function is the vma size, and this
> is always one page at minimum. So, it's not possible to determine if
> the user wants one 4k page or more. As I noted in my first response,
> there is only one case where this is even possible and I don't think
> it is a significant concern.
>
> I did notice that I left out the check to see if the user is trying to
> map more than the device length, so I fixed that. Here's the revised
> patch.
Alright, I've reworked this now so that if we get one of these cases
where there's a bsr that's > 4k and < 64k on a 64k kernel we'll only
advertise that it is a 4k BSR to userspace. I think this is the best
solution since user programs are only supposed to look at sysfs to
determine how much can be mapped, and libbsr does this as well.
Please consider for 2.6.31 as a fix, thanks.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-06-18 23:13:04 +08:00
|
|
|
/* check for the case of a small BSR device and map one 4k page for it*/
|
|
|
|
if (dev->bsr_len < PAGE_SIZE && size == PAGE_SIZE)
|
|
|
|
ret = remap_4k_pfn(vma, vma->vm_start, dev->bsr_addr >> 12,
|
|
|
|
vma->vm_page_prot);
|
|
|
|
else if (size <= dev->bsr_len)
|
|
|
|
ret = io_remap_pfn_range(vma, vma->vm_start,
|
|
|
|
dev->bsr_addr >> PAGE_SHIFT,
|
|
|
|
size, vma->vm_page_prot);
|
|
|
|
else
|
|
|
|
return -EINVAL;
|
|
|
|
|
|
|
|
if (ret)
|
2008-07-08 13:45:11 +08:00
|
|
|
return -EAGAIN;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-05-17 12:50:07 +08:00
|
|
|
static int bsr_open(struct inode *inode, struct file *filp)
|
2008-07-08 13:45:11 +08:00
|
|
|
{
|
|
|
|
struct cdev *cdev = inode->i_cdev;
|
|
|
|
struct bsr_dev *dev = container_of(cdev, struct bsr_dev, bsr_cdev);
|
|
|
|
|
|
|
|
filp->private_data = dev;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2009-02-10 05:01:08 +08:00
|
|
|
static const struct file_operations bsr_fops = {
|
2008-07-08 13:45:11 +08:00
|
|
|
.owner = THIS_MODULE,
|
|
|
|
.mmap = bsr_mmap,
|
|
|
|
.open = bsr_open,
|
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>
2010-08-16 00:52:59 +08:00
|
|
|
.llseek = noop_llseek,
|
2008-07-08 13:45:11 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
static void bsr_cleanup_devs(void)
|
|
|
|
{
|
2008-11-09 22:15:11 +08:00
|
|
|
struct bsr_dev *cur, *n;
|
|
|
|
|
|
|
|
list_for_each_entry_safe(cur, n, &bsr_devs, bsr_list) {
|
2008-07-08 13:45:11 +08:00
|
|
|
if (cur->bsr_device) {
|
|
|
|
cdev_del(&cur->bsr_cdev);
|
|
|
|
device_del(cur->bsr_device);
|
|
|
|
}
|
2008-11-09 22:15:11 +08:00
|
|
|
list_del(&cur->bsr_list);
|
|
|
|
kfree(cur);
|
2008-07-08 13:45:11 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
static int bsr_add_node(struct device_node *bn)
|
2008-07-08 13:45:11 +08:00
|
|
|
{
|
2008-11-09 22:15:11 +08:00
|
|
|
int bsr_stride_len, bsr_bytes_len, num_bsr_devs;
|
2008-07-08 13:45:11 +08:00
|
|
|
const u32 *bsr_stride;
|
|
|
|
const u32 *bsr_bytes;
|
|
|
|
unsigned i;
|
2008-11-09 22:15:11 +08:00
|
|
|
int ret = -ENODEV;
|
2008-07-08 13:45:11 +08:00
|
|
|
|
|
|
|
bsr_stride = of_get_property(bn, "ibm,lock-stride", &bsr_stride_len);
|
|
|
|
bsr_bytes = of_get_property(bn, "ibm,#lock-bytes", &bsr_bytes_len);
|
|
|
|
|
|
|
|
if (!bsr_stride || !bsr_bytes ||
|
|
|
|
(bsr_stride_len != bsr_bytes_len)) {
|
|
|
|
printk(KERN_ERR "bsr of-node has missing/incorrect property\n");
|
2008-11-09 22:15:11 +08:00
|
|
|
return ret;
|
2008-07-08 13:45:11 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
num_bsr_devs = bsr_bytes_len / sizeof(u32);
|
|
|
|
|
|
|
|
for (i = 0 ; i < num_bsr_devs; i++) {
|
2008-11-09 22:15:11 +08:00
|
|
|
struct bsr_dev *cur = kzalloc(sizeof(struct bsr_dev),
|
|
|
|
GFP_KERNEL);
|
2008-07-08 13:45:11 +08:00
|
|
|
struct resource res;
|
|
|
|
int result;
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
if (!cur) {
|
|
|
|
printk(KERN_ERR "Unable to alloc bsr dev\n");
|
|
|
|
ret = -ENOMEM;
|
|
|
|
goto out_err;
|
|
|
|
}
|
|
|
|
|
2008-07-08 13:45:11 +08:00
|
|
|
result = of_address_to_resource(bn, i, &res);
|
|
|
|
if (result < 0) {
|
2008-11-09 22:15:11 +08:00
|
|
|
printk(KERN_ERR "bsr of-node has invalid reg property, skipping\n");
|
|
|
|
kfree(cur);
|
|
|
|
continue;
|
2008-07-08 13:45:11 +08:00
|
|
|
}
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
cur->bsr_minor = i + total_bsr_devs;
|
2008-07-08 13:45:11 +08:00
|
|
|
cur->bsr_addr = res.start;
|
2011-06-10 00:13:32 +08:00
|
|
|
cur->bsr_len = resource_size(&res);
|
2008-07-08 13:45:11 +08:00
|
|
|
cur->bsr_bytes = bsr_bytes[i];
|
|
|
|
cur->bsr_stride = bsr_stride[i];
|
2008-11-09 22:15:11 +08:00
|
|
|
cur->bsr_dev = MKDEV(bsr_major, i + total_bsr_devs);
|
2008-07-08 13:45:11 +08:00
|
|
|
|
powerpc/BSR: Fix BSR to allow mmap of small BSR on 64k kernel
On Mon, Nov 17, 2008 at 01:26:13AM -0600, Sonny Rao wrote:
> On Fri, Nov 07, 2008 at 04:28:29PM +1100, Paul Mackerras wrote:
> > Sonny Rao writes:
> >
> > > Fix the BSR driver to allow small BSR devices, which are limited to a
> > > single 4k space, on a 64k page kernel. Previously the driver would
> > > reject the mmap since the size was smaller than PAGESIZE (or because
> > > the size was greater than the size of the device). Now, we check for
> > > this case use remap_4k_pfn(). Also, take out code to set vm_flags,
> > > as the remap_pfn functions will do this for us.
> >
> > Thanks.
> >
> > Do we know that the BSR size will always be 4k if it's not a multiple
> > of 64k? Is it possible that we could get 8k, 16k or 32k or BSRs?
> > If it is possible, what does the user need to be able to do? Do they
> > just want to map 4k, or might then want to map the whole thing?
>
>
> Hi Paul, I took a look at changing the driver to reject a request for
> mapping more than a single 4k page, however the only indication we get
> of the requested size in the mmap function is the vma size, and this
> is always one page at minimum. So, it's not possible to determine if
> the user wants one 4k page or more. As I noted in my first response,
> there is only one case where this is even possible and I don't think
> it is a significant concern.
>
> I did notice that I left out the check to see if the user is trying to
> map more than the device length, so I fixed that. Here's the revised
> patch.
Alright, I've reworked this now so that if we get one of these cases
where there's a bsr that's > 4k and < 64k on a 64k kernel we'll only
advertise that it is a 4k BSR to userspace. I think this is the best
solution since user programs are only supposed to look at sysfs to
determine how much can be mapped, and libbsr does this as well.
Please consider for 2.6.31 as a fix, thanks.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
2009-06-18 23:13:04 +08:00
|
|
|
/* if we have a bsr_len of > 4k and less then PAGE_SIZE (64k pages) */
|
|
|
|
/* we can only map 4k of it, so only advertise the 4k in sysfs */
|
|
|
|
if (cur->bsr_len > 4096 && cur->bsr_len < PAGE_SIZE)
|
|
|
|
cur->bsr_len = 4096;
|
|
|
|
|
2008-07-08 13:45:11 +08:00
|
|
|
switch(cur->bsr_bytes) {
|
|
|
|
case 8:
|
|
|
|
cur->bsr_type = BSR_8;
|
|
|
|
break;
|
|
|
|
case 16:
|
|
|
|
cur->bsr_type = BSR_16;
|
|
|
|
break;
|
|
|
|
case 64:
|
|
|
|
cur->bsr_type = BSR_64;
|
|
|
|
break;
|
|
|
|
case 128:
|
|
|
|
cur->bsr_type = BSR_128;
|
|
|
|
break;
|
2009-06-18 23:14:36 +08:00
|
|
|
case 4096:
|
|
|
|
cur->bsr_type = BSR_4096;
|
|
|
|
break;
|
2008-07-08 13:45:11 +08:00
|
|
|
default:
|
|
|
|
cur->bsr_type = BSR_UNKNOWN;
|
|
|
|
}
|
|
|
|
|
|
|
|
cur->bsr_num = bsr_types[cur->bsr_type];
|
|
|
|
snprintf(cur->bsr_name, 32, "bsr%d_%d",
|
|
|
|
cur->bsr_bytes, cur->bsr_num);
|
|
|
|
|
|
|
|
cdev_init(&cur->bsr_cdev, &bsr_fops);
|
|
|
|
result = cdev_add(&cur->bsr_cdev, cur->bsr_dev, 1);
|
2008-11-09 22:15:11 +08:00
|
|
|
if (result) {
|
|
|
|
kfree(cur);
|
2008-07-08 13:45:11 +08:00
|
|
|
goto out_err;
|
2008-11-09 22:15:11 +08:00
|
|
|
}
|
2008-07-08 13:45:11 +08:00
|
|
|
|
2008-07-22 11:03:34 +08:00
|
|
|
cur->bsr_device = device_create(bsr_class, NULL, cur->bsr_dev,
|
2014-06-11 01:51:08 +08:00
|
|
|
cur, "%s", cur->bsr_name);
|
2010-03-12 00:15:53 +08:00
|
|
|
if (IS_ERR(cur->bsr_device)) {
|
2008-07-08 13:45:11 +08:00
|
|
|
printk(KERN_ERR "device_create failed for %s\n",
|
|
|
|
cur->bsr_name);
|
|
|
|
cdev_del(&cur->bsr_cdev);
|
2008-11-09 22:15:11 +08:00
|
|
|
kfree(cur);
|
2008-07-08 13:45:11 +08:00
|
|
|
goto out_err;
|
|
|
|
}
|
2008-11-09 22:15:11 +08:00
|
|
|
|
|
|
|
bsr_types[cur->bsr_type] = cur->bsr_num + 1;
|
|
|
|
list_add_tail(&cur->bsr_list, &bsr_devs);
|
2008-07-08 13:45:11 +08:00
|
|
|
}
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
total_bsr_devs += num_bsr_devs;
|
|
|
|
|
2008-07-08 13:45:11 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_err:
|
|
|
|
|
|
|
|
bsr_cleanup_devs();
|
2008-11-09 22:15:11 +08:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int bsr_create_devs(struct device_node *bn)
|
|
|
|
{
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
while (bn) {
|
|
|
|
ret = bsr_add_node(bn);
|
|
|
|
if (ret) {
|
|
|
|
of_node_put(bn);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
bn = of_find_compatible_node(bn, NULL, "ibm,bsr");
|
|
|
|
}
|
|
|
|
return 0;
|
2008-07-08 13:45:11 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int __init bsr_init(void)
|
|
|
|
{
|
|
|
|
struct device_node *np;
|
2011-04-21 18:00:18 +08:00
|
|
|
dev_t bsr_dev;
|
2008-07-08 13:45:11 +08:00
|
|
|
int ret = -ENODEV;
|
|
|
|
|
2008-11-09 22:15:11 +08:00
|
|
|
np = of_find_compatible_node(NULL, NULL, "ibm,bsr");
|
2008-07-08 13:45:11 +08:00
|
|
|
if (!np)
|
|
|
|
goto out_err;
|
|
|
|
|
|
|
|
bsr_class = class_create(THIS_MODULE, "bsr");
|
|
|
|
if (IS_ERR(bsr_class)) {
|
|
|
|
printk(KERN_ERR "class_create() failed for bsr_class\n");
|
2012-07-15 21:22:02 +08:00
|
|
|
ret = PTR_ERR(bsr_class);
|
2008-07-08 13:45:11 +08:00
|
|
|
goto out_err_1;
|
|
|
|
}
|
2013-07-25 06:05:06 +08:00
|
|
|
bsr_class->dev_groups = bsr_dev_groups;
|
2008-07-08 13:45:11 +08:00
|
|
|
|
2012-07-15 21:22:02 +08:00
|
|
|
ret = alloc_chrdev_region(&bsr_dev, 0, BSR_MAX_DEVS, "bsr");
|
2008-07-08 13:45:11 +08:00
|
|
|
bsr_major = MAJOR(bsr_dev);
|
2012-07-15 21:22:02 +08:00
|
|
|
if (ret < 0) {
|
2008-07-08 13:45:11 +08:00
|
|
|
printk(KERN_ERR "alloc_chrdev_region() failed for bsr\n");
|
|
|
|
goto out_err_2;
|
|
|
|
}
|
|
|
|
|
2019-05-16 00:17:46 +08:00
|
|
|
ret = bsr_create_devs(np);
|
|
|
|
if (ret < 0) {
|
2008-11-09 22:15:11 +08:00
|
|
|
np = NULL;
|
2008-07-08 13:45:11 +08:00
|
|
|
goto out_err_3;
|
2008-11-09 22:15:11 +08:00
|
|
|
}
|
2008-07-08 13:45:11 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_err_3:
|
|
|
|
unregister_chrdev_region(bsr_dev, BSR_MAX_DEVS);
|
|
|
|
|
|
|
|
out_err_2:
|
|
|
|
class_destroy(bsr_class);
|
|
|
|
|
|
|
|
out_err_1:
|
|
|
|
of_node_put(np);
|
|
|
|
|
|
|
|
out_err:
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void __exit bsr_exit(void)
|
|
|
|
{
|
|
|
|
|
|
|
|
bsr_cleanup_devs();
|
|
|
|
|
|
|
|
if (bsr_class)
|
|
|
|
class_destroy(bsr_class);
|
|
|
|
|
|
|
|
if (bsr_major)
|
|
|
|
unregister_chrdev_region(MKDEV(bsr_major, 0), BSR_MAX_DEVS);
|
|
|
|
}
|
|
|
|
|
|
|
|
module_init(bsr_init);
|
|
|
|
module_exit(bsr_exit);
|
|
|
|
MODULE_LICENSE("GPL");
|
|
|
|
MODULE_AUTHOR("Sonny Rao <sonnyrao@us.ibm.com>");
|