2009-02-24 08:30:26 -07:00
|
|
|
/*
|
|
|
|
* 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/highmem.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 01:04:11 -07:00
|
|
|
#include <linux/gfp.h>
|
2009-02-24 08:30:26 -07:00
|
|
|
|
|
|
|
#include "rds.h"
|
|
|
|
|
|
|
|
struct rds_page_remainder {
|
|
|
|
struct page *r_page;
|
|
|
|
unsigned long r_offset;
|
|
|
|
};
|
|
|
|
|
2009-06-23 23:13:47 -07:00
|
|
|
DEFINE_PER_CPU_SHARED_ALIGNED(struct rds_page_remainder, rds_page_remainders);
|
2009-02-24 08:30:26 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* returns 0 on success or -errno on failure.
|
|
|
|
*
|
|
|
|
* We don't have to worry about flush_dcache_page() as this only works
|
|
|
|
* with private pages. If, say, we were to do directed receive to pinned
|
|
|
|
* user pages we'd have to worry more about cache coherence. (Though
|
|
|
|
* the flush_dcache_page() in get_user_pages() would probably be enough).
|
|
|
|
*/
|
|
|
|
int rds_page_copy_user(struct page *page, unsigned long offset,
|
|
|
|
void __user *ptr, unsigned long bytes,
|
|
|
|
int to_user)
|
|
|
|
{
|
|
|
|
unsigned long ret;
|
|
|
|
void *addr;
|
|
|
|
|
|
|
|
if (to_user)
|
|
|
|
rds_stats_add(s_copy_to_user, bytes);
|
|
|
|
else
|
|
|
|
rds_stats_add(s_copy_from_user, bytes);
|
|
|
|
|
|
|
|
addr = kmap_atomic(page, KM_USER0);
|
|
|
|
if (to_user)
|
|
|
|
ret = __copy_to_user_inatomic(ptr, addr + offset, bytes);
|
|
|
|
else
|
|
|
|
ret = __copy_from_user_inatomic(addr + offset, ptr, bytes);
|
|
|
|
kunmap_atomic(addr, KM_USER0);
|
|
|
|
|
|
|
|
if (ret) {
|
|
|
|
addr = kmap(page);
|
|
|
|
if (to_user)
|
|
|
|
ret = copy_to_user(ptr, addr + offset, bytes);
|
|
|
|
else
|
|
|
|
ret = copy_from_user(addr + offset, ptr, bytes);
|
|
|
|
kunmap(page);
|
|
|
|
if (ret)
|
|
|
|
return -EFAULT;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2009-08-21 05:28:32 -07:00
|
|
|
EXPORT_SYMBOL_GPL(rds_page_copy_user);
|
2009-02-24 08:30:26 -07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Message allocation uses this to build up regions of a message.
|
|
|
|
*
|
|
|
|
* @bytes - the number of bytes needed.
|
|
|
|
* @gfp - the waiting behaviour of the allocation
|
|
|
|
*
|
|
|
|
* @gfp is always ored with __GFP_HIGHMEM. Callers must be prepared to
|
|
|
|
* kmap the pages, etc.
|
|
|
|
*
|
|
|
|
* If @bytes is at least a full page then this just returns a page from
|
|
|
|
* alloc_page().
|
|
|
|
*
|
|
|
|
* If @bytes is a partial page then this stores the unused region of the
|
|
|
|
* page in a per-cpu structure. Future partial-page allocations may be
|
|
|
|
* satisfied from that cached region. This lets us waste less memory on
|
|
|
|
* small allocations with minimal complexity. It works because the transmit
|
|
|
|
* path passes read-only page regions down to devices. They hold a page
|
|
|
|
* reference until they are done with the region.
|
|
|
|
*/
|
|
|
|
int rds_page_remainder_alloc(struct scatterlist *scat, unsigned long bytes,
|
|
|
|
gfp_t gfp)
|
|
|
|
{
|
|
|
|
struct rds_page_remainder *rem;
|
|
|
|
unsigned long flags;
|
|
|
|
struct page *page;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
gfp |= __GFP_HIGHMEM;
|
|
|
|
|
|
|
|
/* jump straight to allocation if we're trying for a huge page */
|
|
|
|
if (bytes >= PAGE_SIZE) {
|
|
|
|
page = alloc_page(gfp);
|
|
|
|
if (page == NULL) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
} else {
|
|
|
|
sg_set_page(scat, page, PAGE_SIZE, 0);
|
|
|
|
ret = 0;
|
|
|
|
}
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
rem = &per_cpu(rds_page_remainders, get_cpu());
|
|
|
|
local_irq_save(flags);
|
|
|
|
|
|
|
|
while (1) {
|
|
|
|
/* avoid a tiny region getting stuck by tossing it */
|
|
|
|
if (rem->r_page && bytes > (PAGE_SIZE - rem->r_offset)) {
|
|
|
|
rds_stats_inc(s_page_remainder_miss);
|
|
|
|
__free_page(rem->r_page);
|
|
|
|
rem->r_page = NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* hand out a fragment from the cached page */
|
|
|
|
if (rem->r_page && bytes <= (PAGE_SIZE - rem->r_offset)) {
|
|
|
|
sg_set_page(scat, rem->r_page, bytes, rem->r_offset);
|
|
|
|
get_page(sg_page(scat));
|
|
|
|
|
|
|
|
if (rem->r_offset != 0)
|
|
|
|
rds_stats_inc(s_page_remainder_hit);
|
|
|
|
|
|
|
|
rem->r_offset += bytes;
|
|
|
|
if (rem->r_offset == PAGE_SIZE) {
|
|
|
|
__free_page(rem->r_page);
|
|
|
|
rem->r_page = NULL;
|
|
|
|
}
|
|
|
|
ret = 0;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* alloc if there is nothing for us to use */
|
|
|
|
local_irq_restore(flags);
|
|
|
|
put_cpu();
|
|
|
|
|
|
|
|
page = alloc_page(gfp);
|
|
|
|
|
|
|
|
rem = &per_cpu(rds_page_remainders, get_cpu());
|
|
|
|
local_irq_save(flags);
|
|
|
|
|
|
|
|
if (page == NULL) {
|
|
|
|
ret = -ENOMEM;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* did someone race to fill the remainder before us? */
|
|
|
|
if (rem->r_page) {
|
|
|
|
__free_page(page);
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* otherwise install our page and loop around to alloc */
|
|
|
|
rem->r_page = page;
|
|
|
|
rem->r_offset = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
local_irq_restore(flags);
|
|
|
|
put_cpu();
|
|
|
|
out:
|
|
|
|
rdsdebug("bytes %lu ret %d %p %u %u\n", bytes, ret,
|
|
|
|
ret ? NULL : sg_page(scat), ret ? 0 : scat->offset,
|
|
|
|
ret ? 0 : scat->length);
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int rds_page_remainder_cpu_notify(struct notifier_block *self,
|
|
|
|
unsigned long action, void *hcpu)
|
|
|
|
{
|
|
|
|
struct rds_page_remainder *rem;
|
|
|
|
long cpu = (long)hcpu;
|
|
|
|
|
|
|
|
rem = &per_cpu(rds_page_remainders, cpu);
|
|
|
|
|
|
|
|
rdsdebug("cpu %ld action 0x%lx\n", cpu, action);
|
|
|
|
|
|
|
|
switch (action) {
|
|
|
|
case CPU_DEAD:
|
|
|
|
if (rem->r_page)
|
|
|
|
__free_page(rem->r_page);
|
|
|
|
rem->r_page = NULL;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct notifier_block rds_page_remainder_nb = {
|
|
|
|
.notifier_call = rds_page_remainder_cpu_notify,
|
|
|
|
};
|
|
|
|
|
|
|
|
void rds_page_exit(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for_each_possible_cpu(i)
|
|
|
|
rds_page_remainder_cpu_notify(&rds_page_remainder_nb,
|
|
|
|
(unsigned long)CPU_DEAD,
|
|
|
|
(void *)(long)i);
|
|
|
|
}
|