linux/drivers/s390/char/monwriter.c

399 lines
9.5 KiB
C
Raw Normal View History

/*
* Character device driver for writing z/VM *MONITOR service records.
*
* Copyright IBM Corp. 2006, 2009
*
* Author(s): Melissa Howland <Melissa.Howland@us.ibm.com>
*/
#define KMSG_COMPONENT "monwriter"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/miscdevice.h>
#include <linux/ctype.h>
#include <linux/poll.h>
#include <linux/mutex.h>
#include <linux/platform_device.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>
#include <asm/uaccess.h>
#include <asm/ebcdic.h>
#include <asm/io.h>
#include <asm/appldata.h>
#include <asm/monwriter.h>
#define MONWRITE_MAX_DATALEN 4010
static int mon_max_bufs = 255;
static int mon_buf_count;
struct mon_buf {
struct list_head list;
struct monwrite_hdr hdr;
int diag_done;
char *data;
};
static LIST_HEAD(mon_priv_list);
struct mon_private {
struct list_head priv_list;
struct list_head list;
struct monwrite_hdr hdr;
size_t hdr_to_read;
size_t data_to_read;
struct mon_buf *current_buf;
struct mutex thread_mutex;
};
/*
* helper functions
*/
static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
{
struct appldata_product_id id;
int rc;
strncpy(id.prod_nr, "LNXAPPL", 7);
id.prod_fn = myhdr->applid;
id.record_nr = myhdr->record_num;
id.version_nr = myhdr->version;
id.release_nr = myhdr->release;
id.mod_lvl = myhdr->mod_level;
rc = appldata_asm(&id, fcn, (void *) buffer, myhdr->datalen);
if (rc <= 0)
return rc;
pr_err("Writing monitor data failed with rc=%i\n", rc);
if (rc == 5)
return -EPERM;
return -EINVAL;
}
static struct mon_buf *monwrite_find_hdr(struct mon_private *monpriv,
struct monwrite_hdr *monhdr)
{
struct mon_buf *entry, *next;
list_for_each_entry_safe(entry, next, &monpriv->list, list)
if ((entry->hdr.mon_function == monhdr->mon_function ||
monhdr->mon_function == MONWRITE_STOP_INTERVAL) &&
entry->hdr.applid == monhdr->applid &&
entry->hdr.record_num == monhdr->record_num &&
entry->hdr.version == monhdr->version &&
entry->hdr.release == monhdr->release &&
entry->hdr.mod_level == monhdr->mod_level)
return entry;
return NULL;
}
static int monwrite_new_hdr(struct mon_private *monpriv)
{
struct monwrite_hdr *monhdr = &monpriv->hdr;
struct mon_buf *monbuf;
int rc = 0;
if (monhdr->datalen > MONWRITE_MAX_DATALEN ||
monhdr->mon_function > MONWRITE_START_CONFIG ||
monhdr->hdrlen != sizeof(struct monwrite_hdr))
return -EINVAL;
monbuf = NULL;
if (monhdr->mon_function != MONWRITE_GEN_EVENT)
monbuf = monwrite_find_hdr(monpriv, monhdr);
if (monbuf) {
if (monhdr->mon_function == MONWRITE_STOP_INTERVAL) {
monhdr->datalen = monbuf->hdr.datalen;
rc = monwrite_diag(monhdr, monbuf->data,
APPLDATA_STOP_REC);
list_del(&monbuf->list);
mon_buf_count--;
kfree(monbuf->data);
kfree(monbuf);
monbuf = NULL;
}
} else if (monhdr->mon_function != MONWRITE_STOP_INTERVAL) {
if (mon_buf_count >= mon_max_bufs)
return -ENOSPC;
monbuf = kzalloc(sizeof(struct mon_buf), GFP_KERNEL);
if (!monbuf)
return -ENOMEM;
monbuf->data = kzalloc(monhdr->datalen,
GFP_KERNEL | GFP_DMA);
if (!monbuf->data) {
kfree(monbuf);
return -ENOMEM;
}
monbuf->hdr = *monhdr;
list_add_tail(&monbuf->list, &monpriv->list);
if (monhdr->mon_function != MONWRITE_GEN_EVENT)
mon_buf_count++;
}
monpriv->current_buf = monbuf;
return rc;
}
static int monwrite_new_data(struct mon_private *monpriv)
{
struct monwrite_hdr *monhdr = &monpriv->hdr;
struct mon_buf *monbuf = monpriv->current_buf;
int rc = 0;
switch (monhdr->mon_function) {
case MONWRITE_START_INTERVAL:
if (!monbuf->diag_done) {
rc = monwrite_diag(monhdr, monbuf->data,
APPLDATA_START_INTERVAL_REC);
monbuf->diag_done = 1;
}
break;
case MONWRITE_START_CONFIG:
if (!monbuf->diag_done) {
rc = monwrite_diag(monhdr, monbuf->data,
APPLDATA_START_CONFIG_REC);
monbuf->diag_done = 1;
}
break;
case MONWRITE_GEN_EVENT:
rc = monwrite_diag(monhdr, monbuf->data,
APPLDATA_GEN_EVENT_REC);
list_del(&monpriv->current_buf->list);
kfree(monpriv->current_buf->data);
kfree(monpriv->current_buf);
monpriv->current_buf = NULL;
break;
default:
/* monhdr->mon_function is checked in monwrite_new_hdr */
BUG();
}
return rc;
}
/*
* file operations
*/
static int monwrite_open(struct inode *inode, struct file *filp)
{
struct mon_private *monpriv;
monpriv = kzalloc(sizeof(struct mon_private), GFP_KERNEL);
if (!monpriv)
return -ENOMEM;
INIT_LIST_HEAD(&monpriv->list);
monpriv->hdr_to_read = sizeof(monpriv->hdr);
mutex_init(&monpriv->thread_mutex);
filp->private_data = monpriv;
list_add_tail(&monpriv->priv_list, &mon_priv_list);
return nonseekable_open(inode, filp);
}
static int monwrite_close(struct inode *inode, struct file *filp)
{
struct mon_private *monpriv = filp->private_data;
struct mon_buf *entry, *next;
list_for_each_entry_safe(entry, next, &monpriv->list, list) {
if (entry->hdr.mon_function != MONWRITE_GEN_EVENT)
monwrite_diag(&entry->hdr, entry->data,
APPLDATA_STOP_REC);
mon_buf_count--;
list_del(&entry->list);
kfree(entry->data);
kfree(entry);
}
list_del(&monpriv->priv_list);
kfree(monpriv);
return 0;
}
static ssize_t monwrite_write(struct file *filp, const char __user *data,
size_t count, loff_t *ppos)
{
struct mon_private *monpriv = filp->private_data;
size_t len, written;
void *to;
int rc;
mutex_lock(&monpriv->thread_mutex);
for (written = 0; written < count; ) {
if (monpriv->hdr_to_read) {
len = min(count - written, monpriv->hdr_to_read);
to = (char *) &monpriv->hdr +
sizeof(monpriv->hdr) - monpriv->hdr_to_read;
if (copy_from_user(to, data + written, len)) {
rc = -EFAULT;
goto out_error;
}
monpriv->hdr_to_read -= len;
written += len;
if (monpriv->hdr_to_read > 0)
continue;
rc = monwrite_new_hdr(monpriv);
if (rc)
goto out_error;
monpriv->data_to_read = monpriv->current_buf ?
monpriv->current_buf->hdr.datalen : 0;
}
if (monpriv->data_to_read) {
len = min(count - written, monpriv->data_to_read);
to = monpriv->current_buf->data +
monpriv->hdr.datalen - monpriv->data_to_read;
if (copy_from_user(to, data + written, len)) {
rc = -EFAULT;
goto out_error;
}
monpriv->data_to_read -= len;
written += len;
if (monpriv->data_to_read > 0)
continue;
rc = monwrite_new_data(monpriv);
if (rc)
goto out_error;
}
monpriv->hdr_to_read = sizeof(monpriv->hdr);
}
mutex_unlock(&monpriv->thread_mutex);
return written;
out_error:
monpriv->data_to_read = 0;
monpriv->hdr_to_read = sizeof(struct monwrite_hdr);
mutex_unlock(&monpriv->thread_mutex);
return rc;
}
static const struct file_operations monwrite_fops = {
.owner = THIS_MODULE,
.open = &monwrite_open,
.release = &monwrite_close,
.write = &monwrite_write,
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,
};
static struct miscdevice mon_dev = {
.name = "monwriter",
.fops = &monwrite_fops,
.minor = MISC_DYNAMIC_MINOR,
};
/*
* suspend/resume
*/
static int monwriter_freeze(struct device *dev)
{
struct mon_private *monpriv;
struct mon_buf *monbuf;
list_for_each_entry(monpriv, &mon_priv_list, priv_list) {
list_for_each_entry(monbuf, &monpriv->list, list) {
if (monbuf->hdr.mon_function != MONWRITE_GEN_EVENT)
monwrite_diag(&monbuf->hdr, monbuf->data,
APPLDATA_STOP_REC);
}
}
return 0;
}
static int monwriter_restore(struct device *dev)
{
struct mon_private *monpriv;
struct mon_buf *monbuf;
list_for_each_entry(monpriv, &mon_priv_list, priv_list) {
list_for_each_entry(monbuf, &monpriv->list, list) {
if (monbuf->hdr.mon_function == MONWRITE_START_INTERVAL)
monwrite_diag(&monbuf->hdr, monbuf->data,
APPLDATA_START_INTERVAL_REC);
if (monbuf->hdr.mon_function == MONWRITE_START_CONFIG)
monwrite_diag(&monbuf->hdr, monbuf->data,
APPLDATA_START_CONFIG_REC);
}
}
return 0;
}
static int monwriter_thaw(struct device *dev)
{
return monwriter_restore(dev);
}
static const struct dev_pm_ops monwriter_pm_ops = {
.freeze = monwriter_freeze,
.thaw = monwriter_thaw,
.restore = monwriter_restore,
};
static struct platform_driver monwriter_pdrv = {
.driver = {
.name = "monwriter",
.pm = &monwriter_pm_ops,
},
};
static struct platform_device *monwriter_pdev;
/*
* module init/exit
*/
static int __init mon_init(void)
{
int rc;
if (!MACHINE_IS_VM)
return -ENODEV;
rc = platform_driver_register(&monwriter_pdrv);
if (rc)
return rc;
monwriter_pdev = platform_device_register_simple("monwriter", -1, NULL,
0);
if (IS_ERR(monwriter_pdev)) {
rc = PTR_ERR(monwriter_pdev);
goto out_driver;
}
/*
* misc_register() has to be the last action in module_init(), because
* file operations will be available right after this.
*/
rc = misc_register(&mon_dev);
if (rc)
goto out_device;
return 0;
out_device:
platform_device_unregister(monwriter_pdev);
out_driver:
platform_driver_unregister(&monwriter_pdrv);
return rc;
}
static void __exit mon_exit(void)
{
misc_deregister(&mon_dev);
platform_device_unregister(monwriter_pdev);
platform_driver_unregister(&monwriter_pdrv);
}
module_init(mon_init);
module_exit(mon_exit);
module_param_named(max_bufs, mon_max_bufs, int, 0644);
MODULE_PARM_DESC(max_bufs, "Maximum number of sample monitor data buffers "
"that can be active at one time");
MODULE_AUTHOR("Melissa Howland <Melissa.Howland@us.ibm.com>");
MODULE_DESCRIPTION("Character device driver for writing z/VM "
"APPLDATA monitor records.");
MODULE_LICENSE("GPL");