linux/drivers/char/bsr.c

356 lines
8.8 KiB
C
Raw Normal View History

/* IBM POWER Barrier Synchronization Register Driver
*
* Copyright IBM Corporation 2008
*
* Author: Sonny Rao <sonnyrao@us.ibm.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/kernel.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/of_platform.h>
#include <linux/fs.h>
#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 08:04:11 +00:00
#include <linux/slab.h>
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 15:13:04 +00:00
#include <asm/pgtable.h>
#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;
struct list_head bsr_list;
dev_t bsr_dev;
struct cdev bsr_cdev;
struct device *bsr_device;
char bsr_name[32];
};
static unsigned total_bsr_devs;
static struct list_head bsr_devs = LIST_HEAD_INIT(bsr_devs);
static struct class *bsr_class;
static int bsr_major;
enum {
BSR_8 = 0,
BSR_16 = 1,
BSR_64 = 2,
BSR_128 = 3,
BSR_4096 = 4,
BSR_UNKNOWN = 5,
BSR_MAX = 6,
};
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);
}
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);
}
static ssize_t
bsr_len_show(struct device *dev, struct device_attribute *attr, char *buf)
{
struct bsr_dev *bsr_dev = dev_get_drvdata(dev);
return sprintf(buf, "%llu\n", bsr_dev->bsr_len);
}
static struct device_attribute bsr_dev_attrs[] = {
__ATTR(bsr_size, S_IRUGO, bsr_size_show, NULL),
__ATTR(bsr_stride, S_IRUGO, bsr_stride_show, NULL),
__ATTR(bsr_length, S_IRUGO, bsr_len_show, NULL),
__ATTR_NULL
};
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 15:13:04 +00:00
int ret;
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 15:13:04 +00:00
/* 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)
return -EAGAIN;
return 0;
}
static int bsr_open(struct inode * inode, struct file * filp)
{
struct cdev *cdev = inode->i_cdev;
struct bsr_dev *dev = container_of(cdev, struct bsr_dev, bsr_cdev);
filp->private_data = dev;
return 0;
}
static const struct file_operations bsr_fops = {
.owner = THIS_MODULE,
.mmap = bsr_mmap,
.open = bsr_open,
};
static void bsr_cleanup_devs(void)
{
struct bsr_dev *cur, *n;
list_for_each_entry_safe(cur, n, &bsr_devs, bsr_list) {
if (cur->bsr_device) {
cdev_del(&cur->bsr_cdev);
device_del(cur->bsr_device);
}
list_del(&cur->bsr_list);
kfree(cur);
}
}
static int bsr_add_node(struct device_node *bn)
{
int bsr_stride_len, bsr_bytes_len, num_bsr_devs;
const u32 *bsr_stride;
const u32 *bsr_bytes;
unsigned i;
int ret = -ENODEV;
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");
return ret;
}
num_bsr_devs = bsr_bytes_len / sizeof(u32);
for (i = 0 ; i < num_bsr_devs; i++) {
struct bsr_dev *cur = kzalloc(sizeof(struct bsr_dev),
GFP_KERNEL);
struct resource res;
int result;
if (!cur) {
printk(KERN_ERR "Unable to alloc bsr dev\n");
ret = -ENOMEM;
goto out_err;
}
result = of_address_to_resource(bn, i, &res);
if (result < 0) {
printk(KERN_ERR "bsr of-node has invalid reg property, skipping\n");
kfree(cur);
continue;
}
cur->bsr_minor = i + total_bsr_devs;
cur->bsr_addr = res.start;
cur->bsr_len = res.end - res.start + 1;
cur->bsr_bytes = bsr_bytes[i];
cur->bsr_stride = bsr_stride[i];
cur->bsr_dev = MKDEV(bsr_major, i + total_bsr_devs);
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 15:13:04 +00:00
/* 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;
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;
case 4096:
cur->bsr_type = BSR_4096;
break;
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);
if (result) {
kfree(cur);
goto out_err;
}
cur->bsr_device = device_create(bsr_class, NULL, cur->bsr_dev,
cur, cur->bsr_name);
if (IS_ERR(cur->bsr_device)) {
printk(KERN_ERR "device_create failed for %s\n",
cur->bsr_name);
cdev_del(&cur->bsr_cdev);
kfree(cur);
goto out_err;
}
bsr_types[cur->bsr_type] = cur->bsr_num + 1;
list_add_tail(&cur->bsr_list, &bsr_devs);
}
total_bsr_devs += num_bsr_devs;
return 0;
out_err:
bsr_cleanup_devs();
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;
}
static int __init bsr_init(void)
{
struct device_node *np;
dev_t bsr_dev = MKDEV(bsr_major, 0);
int ret = -ENODEV;
int result;
np = of_find_compatible_node(NULL, NULL, "ibm,bsr");
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");
goto out_err_1;
}
bsr_class->dev_attrs = bsr_dev_attrs;
result = alloc_chrdev_region(&bsr_dev, 0, BSR_MAX_DEVS, "bsr");
bsr_major = MAJOR(bsr_dev);
if (result < 0) {
printk(KERN_ERR "alloc_chrdev_region() failed for bsr\n");
goto out_err_2;
}
if ((ret = bsr_create_devs(np)) < 0) {
np = NULL;
goto out_err_3;
}
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>");