mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-04 18:09:57 +00:00
![Arnd Bergmann](/assets/img/avatar_default.png)
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>
356 lines
8.8 KiB
C
356 lines
8.8 KiB
C
/* 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 <linux/slab.h>
|
|
#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;
|
|
int ret;
|
|
|
|
vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
|
|
|
|
/* 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,
|
|
.llseek = noop_llseek,
|
|
};
|
|
|
|
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);
|
|
|
|
/* 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>");
|