linux-sg2042/net/rds/info.c

244 lines
6.4 KiB
C
Raw Normal View History

/*
* Copyright (c) 2006 Oracle. All rights reserved.
*
* This software is available to you under a choice of one of two
* licenses. You may choose to be licensed under the terms of the GNU
* General Public License (GPL) Version 2, available from the file
* COPYING in the main directory of this source tree, or the
* OpenIB.org BSD license below:
*
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
*
* - Redistributions of source code must retain the above
* copyright notice, this list of conditions and the following
* disclaimer.
*
* - Redistributions in binary form must reproduce the above
* copyright notice, this list of conditions and the following
* disclaimer in the documentation and/or other materials
* provided with the distribution.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
* EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
* MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
* NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
* BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
* ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
* CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*
*/
#include <linux/percpu.h>
#include <linux/seq_file.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 <linux/proc_fs.h>
#include <linux/export.h>
#include "rds.h"
/*
* This file implements a getsockopt() call which copies a set of fixed
* sized structs into a user-specified buffer as a means of providing
* read-only information about RDS.
*
* For a given information source there are a given number of fixed sized
* structs at a given time. The structs are only copied if the user-specified
* buffer is big enough. The destination pages that make up the buffer
* are pinned for the duration of the copy.
*
* This gives us the following benefits:
*
* - simple implementation, no copy "position" across multiple calls
* - consistent snapshot of an info source
* - atomic copy works well with whatever locking info source has
* - one portable tool to get rds info across implementations
* - long-lived tool can get info without allocating
*
* at the following costs:
*
* - info source copy must be pinned, may be "large"
*/
struct rds_info_iterator {
struct page **pages;
void *addr;
unsigned long offset;
};
static DEFINE_SPINLOCK(rds_info_lock);
static rds_info_func rds_info_funcs[RDS_INFO_LAST - RDS_INFO_FIRST + 1];
void rds_info_register_func(int optname, rds_info_func func)
{
int offset = optname - RDS_INFO_FIRST;
BUG_ON(optname < RDS_INFO_FIRST || optname > RDS_INFO_LAST);
spin_lock(&rds_info_lock);
BUG_ON(rds_info_funcs[offset]);
rds_info_funcs[offset] = func;
spin_unlock(&rds_info_lock);
}
EXPORT_SYMBOL_GPL(rds_info_register_func);
void rds_info_deregister_func(int optname, rds_info_func func)
{
int offset = optname - RDS_INFO_FIRST;
BUG_ON(optname < RDS_INFO_FIRST || optname > RDS_INFO_LAST);
spin_lock(&rds_info_lock);
BUG_ON(rds_info_funcs[offset] != func);
rds_info_funcs[offset] = NULL;
spin_unlock(&rds_info_lock);
}
EXPORT_SYMBOL_GPL(rds_info_deregister_func);
/*
* Typically we hold an atomic kmap across multiple rds_info_copy() calls
* because the kmap is so expensive. This must be called before using blocking
* operations while holding the mapping and as the iterator is torn down.
*/
void rds_info_iter_unmap(struct rds_info_iterator *iter)
{
if (iter->addr) {
kunmap_atomic(iter->addr, KM_USER0);
iter->addr = NULL;
}
}
/*
* get_user_pages() called flush_dcache_page() on the pages for us.
*/
void rds_info_copy(struct rds_info_iterator *iter, void *data,
unsigned long bytes)
{
unsigned long this;
while (bytes) {
if (!iter->addr)
iter->addr = kmap_atomic(*iter->pages, KM_USER0);
this = min(bytes, PAGE_SIZE - iter->offset);
rdsdebug("page %p addr %p offset %lu this %lu data %p "
"bytes %lu\n", *iter->pages, iter->addr,
iter->offset, this, data, bytes);
memcpy(iter->addr + iter->offset, data, this);
data += this;
bytes -= this;
iter->offset += this;
if (iter->offset == PAGE_SIZE) {
kunmap_atomic(iter->addr, KM_USER0);
iter->addr = NULL;
iter->offset = 0;
iter->pages++;
}
}
}
EXPORT_SYMBOL_GPL(rds_info_copy);
/*
* @optval points to the userspace buffer that the information snapshot
* will be copied into.
*
* @optlen on input is the size of the buffer in userspace. @optlen
* on output is the size of the requested snapshot in bytes.
*
* This function returns -errno if there is a failure, particularly -ENOSPC
* if the given userspace buffer was not large enough to fit the snapshot.
* On success it returns the positive number of bytes of each array element
* in the snapshot.
*/
int rds_info_getsockopt(struct socket *sock, int optname, char __user *optval,
int __user *optlen)
{
struct rds_info_iterator iter;
struct rds_info_lengths lens;
unsigned long nr_pages = 0;
unsigned long start;
unsigned long i;
rds_info_func func;
struct page **pages = NULL;
int ret;
int len;
int total;
if (get_user(len, optlen)) {
ret = -EFAULT;
goto out;
}
/* check for all kinds of wrapping and the like */
start = (unsigned long)optval;
if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
ret = -EINVAL;
goto out;
}
/* a 0 len call is just trying to probe its length */
if (len == 0)
goto call_func;
nr_pages = (PAGE_ALIGN(start + len) - (start & PAGE_MASK))
>> PAGE_SHIFT;
pages = kmalloc(nr_pages * sizeof(struct page *), GFP_KERNEL);
if (!pages) {
ret = -ENOMEM;
goto out;
}
ret = get_user_pages_fast(start, nr_pages, 1, pages);
if (ret != nr_pages) {
if (ret > 0)
nr_pages = ret;
else
nr_pages = 0;
ret = -EAGAIN; /* XXX ? */
goto out;
}
rdsdebug("len %d nr_pages %lu\n", len, nr_pages);
call_func:
func = rds_info_funcs[optname - RDS_INFO_FIRST];
if (!func) {
ret = -ENOPROTOOPT;
goto out;
}
iter.pages = pages;
iter.addr = NULL;
iter.offset = start & (PAGE_SIZE - 1);
func(sock, len, &iter, &lens);
BUG_ON(lens.each == 0);
total = lens.nr * lens.each;
rds_info_iter_unmap(&iter);
if (total > len) {
len = total;
ret = -ENOSPC;
} else {
len = total;
ret = lens.each;
}
if (put_user(len, optlen))
ret = -EFAULT;
out:
for (i = 0; pages && i < nr_pages; i++)
put_page(pages[i]);
kfree(pages);
return ret;
}