OpenCloudOS-Kernel/drivers/infiniband/hw/ehca/ipz_pt_fn.c

295 lines
7.5 KiB
C
Raw Normal View History

/*
* IBM eServer eHCA Infiniband device driver for Linux on POWER
*
* internal queue handling
*
* Authors: Waleri Fomin <fomin@de.ibm.com>
* Reinhard Ernst <rernst@de.ibm.com>
* Christoph Raisch <raisch@de.ibm.com>
*
* Copyright (c) 2005 IBM Corporation
*
* This source code is distributed under a dual license of GPL v2.0 and OpenIB
* BSD.
*
* OpenIB BSD License
*
* 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.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
* BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER
* IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
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 "ehca_tools.h"
#include "ipz_pt_fn.h"
#include "ehca_classes.h"
#define PAGES_PER_KPAGE (PAGE_SIZE >> EHCA_PAGESHIFT)
struct kmem_cache *small_qp_cache;
void *ipz_qpageit_get_inc(struct ipz_queue *queue)
{
void *ret = ipz_qeit_get(queue);
queue->current_q_offset += queue->pagesize;
if (queue->current_q_offset > queue->queue_length) {
queue->current_q_offset -= queue->pagesize;
ret = NULL;
}
if (((u64)ret) % queue->pagesize) {
ehca_gen_err("ERROR!! not at PAGE-Boundary");
return NULL;
}
return ret;
}
void *ipz_qeit_eq_get_inc(struct ipz_queue *queue)
{
void *ret = ipz_qeit_get(queue);
u64 last_entry_in_q = queue->queue_length - queue->qe_size;
queue->current_q_offset += queue->qe_size;
if (queue->current_q_offset > last_entry_in_q) {
queue->current_q_offset = 0;
queue->toggle_state = (~queue->toggle_state) & 1;
}
return ret;
}
int ipz_queue_abs_to_offset(struct ipz_queue *queue, u64 addr, u64 *q_offset)
{
int i;
for (i = 0; i < queue->queue_length / queue->pagesize; i++) {
u64 page = (u64)virt_to_abs(queue->queue_pages[i]);
if (addr >= page && addr < page + queue->pagesize) {
*q_offset = addr - page + i * queue->pagesize;
return 0;
}
}
return -EINVAL;
}
#if PAGE_SHIFT < EHCA_PAGESHIFT
#error Kernel pages must be at least as large than eHCA pages (4K) !
#endif
/*
* allocate pages for queue:
* outer loop allocates whole kernel pages (page aligned) and
* inner loop divides a kernel page into smaller hca queue pages
*/
static int alloc_queue_pages(struct ipz_queue *queue, const u32 nr_of_pages)
{
int k, f = 0;
u8 *kpage;
while (f < nr_of_pages) {
kpage = (u8 *)get_zeroed_page(GFP_KERNEL);
if (!kpage)
goto out;
for (k = 0; k < PAGES_PER_KPAGE && f < nr_of_pages; k++) {
queue->queue_pages[f] = (struct ipz_page *)kpage;
kpage += EHCA_PAGESIZE;
f++;
}
}
return 1;
out:
for (f = 0; f < nr_of_pages && queue->queue_pages[f];
f += PAGES_PER_KPAGE)
free_page((unsigned long)(queue->queue_pages)[f]);
return 0;
}
static int alloc_small_queue_page(struct ipz_queue *queue, struct ehca_pd *pd)
{
int order = ilog2(queue->pagesize) - 9;
struct ipz_small_queue_page *page;
unsigned long bit;
mutex_lock(&pd->lock);
if (!list_empty(&pd->free[order]))
page = list_entry(pd->free[order].next,
struct ipz_small_queue_page, list);
else {
page = kmem_cache_zalloc(small_qp_cache, GFP_KERNEL);
if (!page)
goto out;
page->page = get_zeroed_page(GFP_KERNEL);
if (!page->page) {
kmem_cache_free(small_qp_cache, page);
goto out;
}
list_add(&page->list, &pd->free[order]);
}
bit = find_first_zero_bit(page->bitmap, IPZ_SPAGE_PER_KPAGE >> order);
__set_bit(bit, page->bitmap);
page->fill++;
if (page->fill == IPZ_SPAGE_PER_KPAGE >> order)
list_move(&page->list, &pd->full[order]);
mutex_unlock(&pd->lock);
queue->queue_pages[0] = (void *)(page->page | (bit << (order + 9)));
queue->small_page = page;
queue->offset = bit << (order + 9);
return 1;
out:
ehca_err(pd->ib_pd.device, "failed to allocate small queue page");
mutex_unlock(&pd->lock);
return 0;
}
static void free_small_queue_page(struct ipz_queue *queue, struct ehca_pd *pd)
{
int order = ilog2(queue->pagesize) - 9;
struct ipz_small_queue_page *page = queue->small_page;
unsigned long bit;
int free_page = 0;
bit = ((unsigned long)queue->queue_pages[0] & ~PAGE_MASK)
>> (order + 9);
mutex_lock(&pd->lock);
__clear_bit(bit, page->bitmap);
page->fill--;
if (page->fill == 0) {
list_del(&page->list);
free_page = 1;
}
if (page->fill == (IPZ_SPAGE_PER_KPAGE >> order) - 1)
/* the page was full until we freed the chunk */
list_move_tail(&page->list, &pd->free[order]);
mutex_unlock(&pd->lock);
if (free_page) {
free_page(page->page);
kmem_cache_free(small_qp_cache, page);
}
}
int ipz_queue_ctor(struct ehca_pd *pd, struct ipz_queue *queue,
const u32 nr_of_pages, const u32 pagesize,
const u32 qe_size, const u32 nr_of_sg,
int is_small)
{
if (pagesize > PAGE_SIZE) {
ehca_gen_err("FATAL ERROR: pagesize=%x "
"is greater than kernel page size", pagesize);
return 0;
}
/* init queue fields */
queue->queue_length = nr_of_pages * pagesize;
queue->pagesize = pagesize;
queue->qe_size = qe_size;
queue->act_nr_of_sg = nr_of_sg;
queue->current_q_offset = 0;
queue->toggle_state = 1;
queue->small_page = NULL;
/* allocate queue page pointers */
queue->queue_pages = kzalloc(nr_of_pages * sizeof(void *), GFP_KERNEL);
if (!queue->queue_pages) {
queue->queue_pages = vzalloc(nr_of_pages * sizeof(void *));
if (!queue->queue_pages) {
ehca_gen_err("Couldn't allocate queue page list");
return 0;
}
}
/* allocate actual queue pages */
if (is_small) {
if (!alloc_small_queue_page(queue, pd))
goto ipz_queue_ctor_exit0;
} else
if (!alloc_queue_pages(queue, nr_of_pages))
goto ipz_queue_ctor_exit0;
return 1;
ipz_queue_ctor_exit0:
ehca_gen_err("Couldn't alloc pages queue=%p "
"nr_of_pages=%x", queue, nr_of_pages);
if (is_vmalloc_addr(queue->queue_pages))
vfree(queue->queue_pages);
else
kfree(queue->queue_pages);
return 0;
}
int ipz_queue_dtor(struct ehca_pd *pd, struct ipz_queue *queue)
{
int i, nr_pages;
if (!queue || !queue->queue_pages) {
ehca_gen_dbg("queue or queue_pages is NULL");
return 0;
}
if (queue->small_page)
free_small_queue_page(queue, pd);
else {
nr_pages = queue->queue_length / queue->pagesize;
for (i = 0; i < nr_pages; i += PAGES_PER_KPAGE)
free_page((unsigned long)queue->queue_pages[i]);
}
if (is_vmalloc_addr(queue->queue_pages))
vfree(queue->queue_pages);
else
kfree(queue->queue_pages);
return 1;
}
int ehca_init_small_qp_cache(void)
{
small_qp_cache = kmem_cache_create("ehca_cache_small_qp",
sizeof(struct ipz_small_queue_page),
0, SLAB_HWCACHE_ALIGN, NULL);
if (!small_qp_cache)
return -ENOMEM;
return 0;
}
void ehca_cleanup_small_qp_cache(void)
{
kmem_cache_destroy(small_qp_cache);
}