WSL2-Linux-Kernel/drivers/infiniband/core/fmr_pool.c

510 строки
14 KiB
C
Исходник Обычный вид История

/*
* Copyright (c) 2004 Topspin Communications. All rights reserved.
* Copyright (c) 2005 Sun Microsystems, Inc. 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/errno.h>
#include <linux/spinlock.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/jhash.h>
#include <linux/kthread.h>
#include <rdma/ib_fmr_pool.h>
#include "core_priv.h"
#define PFX "fmr_pool: "
enum {
IB_FMR_MAX_REMAPS = 32,
IB_FMR_HASH_BITS = 8,
IB_FMR_HASH_SIZE = 1 << IB_FMR_HASH_BITS,
IB_FMR_HASH_MASK = IB_FMR_HASH_SIZE - 1
};
/*
* If an FMR is not in use, then the list member will point to either
* its pool's free_list (if the FMR can be mapped again; that is,
* remap_count < pool->max_remaps) or its pool's dirty_list (if the
* FMR needs to be unmapped before being remapped). In either of
* these cases it is a bug if the ref_count is not 0. In other words,
* if ref_count is > 0, then the list member must not be linked into
* either free_list or dirty_list.
*
* The cache_node member is used to link the FMR into a cache bucket
* (if caching is enabled). This is independent of the reference
* count of the FMR. When a valid FMR is released, its ref_count is
* decremented, and if ref_count reaches 0, the FMR is placed in
* either free_list or dirty_list as appropriate. However, it is not
* removed from the cache and may be "revived" if a call to
* ib_fmr_register_physical() occurs before the FMR is remapped. In
* this case we just increment the ref_count and remove the FMR from
* free_list/dirty_list.
*
* Before we remap an FMR from free_list, we remove it from the cache
* (to prevent another user from obtaining a stale FMR). When an FMR
* is released, we add it to the tail of the free list, so that our
* cache eviction policy is "least recently used."
*
* All manipulation of ref_count, list and cache_node is protected by
* pool_lock to maintain consistency.
*/
struct ib_fmr_pool {
spinlock_t pool_lock;
int pool_size;
int max_pages;
int max_remaps;
int dirty_watermark;
int dirty_len;
struct list_head free_list;
struct list_head dirty_list;
struct hlist_head *cache_bucket;
void (*flush_function)(struct ib_fmr_pool *pool,
void * arg);
void *flush_arg;
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
struct kthread_worker *worker;
struct kthread_work work;
atomic_t req_ser;
atomic_t flush_ser;
wait_queue_head_t force_wait;
};
static inline u32 ib_fmr_hash(u64 first_page)
{
return jhash_2words((u32) first_page, (u32) (first_page >> 32), 0) &
(IB_FMR_HASH_SIZE - 1);
}
/* Caller must hold pool_lock */
static inline struct ib_pool_fmr *ib_fmr_cache_lookup(struct ib_fmr_pool *pool,
u64 *page_list,
int page_list_len,
u64 io_virtual_address)
{
struct hlist_head *bucket;
struct ib_pool_fmr *fmr;
if (!pool->cache_bucket)
return NULL;
bucket = pool->cache_bucket + ib_fmr_hash(*page_list);
hlist: drop the node parameter from iterators I'm not sure why, but the hlist for each entry iterators were conceived list_for_each_entry(pos, head, member) The hlist ones were greedy and wanted an extra parameter: hlist_for_each_entry(tpos, pos, head, member) Why did they need an extra pos parameter? I'm not quite sure. Not only they don't really need it, it also prevents the iterator from looking exactly like the list iterator, which is unfortunate. Besides the semantic patch, there was some manual work required: - Fix up the actual hlist iterators in linux/list.h - Fix up the declaration of other iterators based on the hlist ones. - A very small amount of places were using the 'node' parameter, this was modified to use 'obj->member' instead. - Coccinelle didn't handle the hlist_for_each_entry_safe iterator properly, so those had to be fixed up manually. The semantic patch which is mostly the work of Peter Senna Tschudin is here: @@ iterator name hlist_for_each_entry, hlist_for_each_entry_continue, hlist_for_each_entry_from, hlist_for_each_entry_rcu, hlist_for_each_entry_rcu_bh, hlist_for_each_entry_continue_rcu_bh, for_each_busy_worker, ax25_uid_for_each, ax25_for_each, inet_bind_bucket_for_each, sctp_for_each_hentry, sk_for_each, sk_for_each_rcu, sk_for_each_from, sk_for_each_safe, sk_for_each_bound, hlist_for_each_entry_safe, hlist_for_each_entry_continue_rcu, nr_neigh_for_each, nr_neigh_for_each_safe, nr_node_for_each, nr_node_for_each_safe, for_each_gfn_indirect_valid_sp, for_each_gfn_sp, for_each_host; type T; expression a,c,d,e; identifier b; statement S; @@ -T b; <+... when != b ( hlist_for_each_entry(a, - b, c, d) S | hlist_for_each_entry_continue(a, - b, c) S | hlist_for_each_entry_from(a, - b, c) S | hlist_for_each_entry_rcu(a, - b, c, d) S | hlist_for_each_entry_rcu_bh(a, - b, c, d) S | hlist_for_each_entry_continue_rcu_bh(a, - b, c) S | for_each_busy_worker(a, c, - b, d) S | ax25_uid_for_each(a, - b, c) S | ax25_for_each(a, - b, c) S | inet_bind_bucket_for_each(a, - b, c) S | sctp_for_each_hentry(a, - b, c) S | sk_for_each(a, - b, c) S | sk_for_each_rcu(a, - b, c) S | sk_for_each_from -(a, b) +(a) S + sk_for_each_from(a) S | sk_for_each_safe(a, - b, c, d) S | sk_for_each_bound(a, - b, c) S | hlist_for_each_entry_safe(a, - b, c, d, e) S | hlist_for_each_entry_continue_rcu(a, - b, c) S | nr_neigh_for_each(a, - b, c) S | nr_neigh_for_each_safe(a, - b, c, d) S | nr_node_for_each(a, - b, c) S | nr_node_for_each_safe(a, - b, c, d) S | - for_each_gfn_sp(a, c, d, b) S + for_each_gfn_sp(a, c, d) S | - for_each_gfn_indirect_valid_sp(a, c, d, b) S + for_each_gfn_indirect_valid_sp(a, c, d) S | for_each_host(a, - b, c) S | for_each_host_safe(a, - b, c, d) S | for_each_mesh_entry(a, - b, c, d) S ) ...+> [akpm@linux-foundation.org: drop bogus change from net/ipv4/raw.c] [akpm@linux-foundation.org: drop bogus hunk from net/ipv6/raw.c] [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix warnings] [akpm@linux-foudnation.org: redo intrusive kvm changes] Tested-by: Peter Senna Tschudin <peter.senna@gmail.com> Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Sasha Levin <sasha.levin@oracle.com> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Gleb Natapov <gleb@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-02-28 05:06:00 +04:00
hlist_for_each_entry(fmr, bucket, cache_node)
if (io_virtual_address == fmr->io_virtual_address &&
page_list_len == fmr->page_list_len &&
!memcmp(page_list, fmr->page_list,
page_list_len * sizeof *page_list))
return fmr;
return NULL;
}
static void ib_fmr_batch_release(struct ib_fmr_pool *pool)
{
int ret;
struct ib_pool_fmr *fmr;
LIST_HEAD(unmap_list);
LIST_HEAD(fmr_list);
spin_lock_irq(&pool->pool_lock);
list_for_each_entry(fmr, &pool->dirty_list, list) {
hlist_del_init(&fmr->cache_node);
fmr->remap_count = 0;
list_add_tail(&fmr->fmr->list, &fmr_list);
#ifdef DEBUG
if (fmr->ref_count !=0) {
pr_warn(PFX "Unmapping FMR 0x%08x with ref count %d\n",
fmr, fmr->ref_count);
}
#endif
}
list_splice_init(&pool->dirty_list, &unmap_list);
pool->dirty_len = 0;
spin_unlock_irq(&pool->pool_lock);
if (list_empty(&unmap_list)) {
return;
}
ret = ib_unmap_fmr(&fmr_list);
if (ret)
pr_warn(PFX "ib_unmap_fmr returned %d\n", ret);
spin_lock_irq(&pool->pool_lock);
list_splice(&unmap_list, &pool->free_list);
spin_unlock_irq(&pool->pool_lock);
}
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
static void ib_fmr_cleanup_func(struct kthread_work *work)
{
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
struct ib_fmr_pool *pool = container_of(work, struct ib_fmr_pool, work);
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
ib_fmr_batch_release(pool);
atomic_inc(&pool->flush_ser);
wake_up_interruptible(&pool->force_wait);
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
if (pool->flush_function)
pool->flush_function(pool, pool->flush_arg);
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
if (atomic_read(&pool->flush_ser) - atomic_read(&pool->req_ser) < 0)
kthread_queue_work(pool->worker, &pool->work);
}
/**
* ib_create_fmr_pool - Create an FMR pool
* @pd:Protection domain for FMRs
* @params:FMR pool parameters
*
* Create a pool of FMRs. Return value is pointer to new pool or
* error code if creation failed.
*/
struct ib_fmr_pool *ib_create_fmr_pool(struct ib_pd *pd,
struct ib_fmr_pool_param *params)
{
struct ib_device *device;
struct ib_fmr_pool *pool;
int i;
int ret;
int max_remaps;
if (!params)
return ERR_PTR(-EINVAL);
device = pd->device;
if (!device->alloc_fmr || !device->dealloc_fmr ||
!device->map_phys_fmr || !device->unmap_fmr) {
dev_info(&device->dev, "Device does not support FMRs\n");
return ERR_PTR(-ENOSYS);
}
if (!device->attrs.max_map_per_fmr)
max_remaps = IB_FMR_MAX_REMAPS;
else
max_remaps = device->attrs.max_map_per_fmr;
pool = kmalloc(sizeof *pool, GFP_KERNEL);
if (!pool)
return ERR_PTR(-ENOMEM);
pool->cache_bucket = NULL;
pool->flush_function = params->flush_function;
pool->flush_arg = params->flush_arg;
INIT_LIST_HEAD(&pool->free_list);
INIT_LIST_HEAD(&pool->dirty_list);
if (params->cache) {
pool->cache_bucket =
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-12 23:55:00 +03:00
kmalloc_array(IB_FMR_HASH_SIZE,
sizeof(*pool->cache_bucket),
GFP_KERNEL);
if (!pool->cache_bucket) {
ret = -ENOMEM;
goto out_free_pool;
}
for (i = 0; i < IB_FMR_HASH_SIZE; ++i)
INIT_HLIST_HEAD(pool->cache_bucket + i);
}
pool->pool_size = 0;
pool->max_pages = params->max_pages_per_fmr;
pool->max_remaps = max_remaps;
pool->dirty_watermark = params->dirty_watermark;
pool->dirty_len = 0;
spin_lock_init(&pool->pool_lock);
atomic_set(&pool->req_ser, 0);
atomic_set(&pool->flush_ser, 0);
init_waitqueue_head(&pool->force_wait);
pool->worker =
kthread_create_worker(0, "ib_fmr(%s)", dev_name(&device->dev));
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
if (IS_ERR(pool->worker)) {
pr_warn(PFX "couldn't start cleanup kthread worker\n");
ret = PTR_ERR(pool->worker);
goto out_free_pool;
}
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
kthread_init_work(&pool->work, ib_fmr_cleanup_func);
{
struct ib_pool_fmr *fmr;
struct ib_fmr_attr fmr_attr = {
.max_pages = params->max_pages_per_fmr,
.max_maps = pool->max_remaps,
.page_shift = params->page_shift
};
int bytes_per_fmr = sizeof *fmr;
if (pool->cache_bucket)
bytes_per_fmr += params->max_pages_per_fmr * sizeof (u64);
for (i = 0; i < params->pool_size; ++i) {
fmr = kmalloc(bytes_per_fmr, GFP_KERNEL);
if (!fmr)
goto out_fail;
fmr->pool = pool;
fmr->remap_count = 0;
fmr->ref_count = 0;
INIT_HLIST_NODE(&fmr->cache_node);
fmr->fmr = ib_alloc_fmr(pd, params->access, &fmr_attr);
if (IS_ERR(fmr->fmr)) {
pr_warn(PFX "fmr_create failed for FMR %d\n",
i);
kfree(fmr);
goto out_fail;
}
list_add_tail(&fmr->list, &pool->free_list);
++pool->pool_size;
}
}
return pool;
out_free_pool:
kfree(pool->cache_bucket);
kfree(pool);
return ERR_PTR(ret);
out_fail:
ib_destroy_fmr_pool(pool);
return ERR_PTR(-ENOMEM);
}
EXPORT_SYMBOL(ib_create_fmr_pool);
/**
* ib_destroy_fmr_pool - Free FMR pool
* @pool:FMR pool to free
*
* Destroy an FMR pool and free all associated resources.
*/
void ib_destroy_fmr_pool(struct ib_fmr_pool *pool)
{
struct ib_pool_fmr *fmr;
struct ib_pool_fmr *tmp;
LIST_HEAD(fmr_list);
int i;
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
kthread_destroy_worker(pool->worker);
ib_fmr_batch_release(pool);
i = 0;
list_for_each_entry_safe(fmr, tmp, &pool->free_list, list) {
if (fmr->remap_count) {
INIT_LIST_HEAD(&fmr_list);
list_add_tail(&fmr->fmr->list, &fmr_list);
ib_unmap_fmr(&fmr_list);
}
ib_dealloc_fmr(fmr->fmr);
list_del(&fmr->list);
kfree(fmr);
++i;
}
if (i < pool->pool_size)
pr_warn(PFX "pool still has %d regions registered\n",
pool->pool_size - i);
kfree(pool->cache_bucket);
kfree(pool);
}
EXPORT_SYMBOL(ib_destroy_fmr_pool);
/**
* ib_flush_fmr_pool - Invalidate all unmapped FMRs
* @pool:FMR pool to flush
*
* Ensure that all unmapped FMRs are fully invalidated.
*/
int ib_flush_fmr_pool(struct ib_fmr_pool *pool)
{
int serial;
struct ib_pool_fmr *fmr, *next;
/*
* The free_list holds FMRs that may have been used
* but have not been remapped enough times to be dirty.
* Put them on the dirty list now so that the cleanup
* thread will reap them too.
*/
spin_lock_irq(&pool->pool_lock);
list_for_each_entry_safe(fmr, next, &pool->free_list, list) {
if (fmr->remap_count > 0)
list_move(&fmr->list, &pool->dirty_list);
}
spin_unlock_irq(&pool->pool_lock);
serial = atomic_inc_return(&pool->req_ser);
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
kthread_queue_work(pool->worker, &pool->work);
if (wait_event_interruptible(pool->force_wait,
atomic_read(&pool->flush_ser) - serial >= 0))
return -EINTR;
return 0;
}
EXPORT_SYMBOL(ib_flush_fmr_pool);
/**
* ib_fmr_pool_map_phys - Map an FMR from an FMR pool.
* @pool_handle: FMR pool to allocate FMR from
* @page_list: List of pages to map
* @list_len: Number of pages in @page_list
* @io_virtual_address: I/O virtual address for new FMR
*/
struct ib_pool_fmr *ib_fmr_pool_map_phys(struct ib_fmr_pool *pool_handle,
u64 *page_list,
int list_len,
u64 io_virtual_address)
{
struct ib_fmr_pool *pool = pool_handle;
struct ib_pool_fmr *fmr;
unsigned long flags;
int result;
if (list_len < 1 || list_len > pool->max_pages)
return ERR_PTR(-EINVAL);
spin_lock_irqsave(&pool->pool_lock, flags);
fmr = ib_fmr_cache_lookup(pool,
page_list,
list_len,
io_virtual_address);
if (fmr) {
/* found in cache */
++fmr->ref_count;
if (fmr->ref_count == 1) {
list_del(&fmr->list);
}
spin_unlock_irqrestore(&pool->pool_lock, flags);
return fmr;
}
if (list_empty(&pool->free_list)) {
spin_unlock_irqrestore(&pool->pool_lock, flags);
return ERR_PTR(-EAGAIN);
}
fmr = list_entry(pool->free_list.next, struct ib_pool_fmr, list);
list_del(&fmr->list);
hlist_del_init(&fmr->cache_node);
spin_unlock_irqrestore(&pool->pool_lock, flags);
result = ib_map_phys_fmr(fmr->fmr, page_list, list_len,
io_virtual_address);
if (result) {
spin_lock_irqsave(&pool->pool_lock, flags);
list_add(&fmr->list, &pool->free_list);
spin_unlock_irqrestore(&pool->pool_lock, flags);
pr_warn(PFX "fmr_map returns %d\n", result);
return ERR_PTR(result);
}
++fmr->remap_count;
fmr->ref_count = 1;
if (pool->cache_bucket) {
fmr->io_virtual_address = io_virtual_address;
fmr->page_list_len = list_len;
memcpy(fmr->page_list, page_list, list_len * sizeof(*page_list));
spin_lock_irqsave(&pool->pool_lock, flags);
hlist_add_head(&fmr->cache_node,
pool->cache_bucket + ib_fmr_hash(fmr->page_list[0]));
spin_unlock_irqrestore(&pool->pool_lock, flags);
}
return fmr;
}
EXPORT_SYMBOL(ib_fmr_pool_map_phys);
/**
* ib_fmr_pool_unmap - Unmap FMR
* @fmr:FMR to unmap
*
* Unmap an FMR. The FMR mapping may remain valid until the FMR is
* reused (or until ib_flush_fmr_pool() is called).
*/
int ib_fmr_pool_unmap(struct ib_pool_fmr *fmr)
{
struct ib_fmr_pool *pool;
unsigned long flags;
pool = fmr->pool;
spin_lock_irqsave(&pool->pool_lock, flags);
--fmr->ref_count;
if (!fmr->ref_count) {
if (fmr->remap_count < pool->max_remaps) {
list_add_tail(&fmr->list, &pool->free_list);
} else {
list_add_tail(&fmr->list, &pool->dirty_list);
if (++pool->dirty_len >= pool->dirty_watermark) {
atomic_inc(&pool->req_ser);
IB/fmr_pool: Convert the cleanup thread into kthread worker API Kthreads are currently implemented as an infinite loop. Each has its own variant of checks for terminating, freezing, awakening. In many cases it is unclear to say in which state it is and sometimes it is done a wrong way. The plan is to convert kthreads into kthread_worker or workqueues API. It allows to split the functionality into separate operations. It helps to make a better structure. Also it defines a clean state where no locks are taken, IRQs blocked, the kthread might sleep or even be safely migrated. The kthread worker API is useful when we want to have a dedicated single thread for the work. It helps to make sure that it is available when needed. Also it allows a better control, e.g. define a scheduling priority. This patch converts the frm_pool kthread into the kthread worker API because I am not sure how busy the thread is. It is well possible that it does not need a dedicated kthread and workqueues would be perfectly fine. Well, the conversion between kthread worker API and workqueues is pretty trivial. The patch moves one iteration from the kthread into the work function. It is queued only when there is a pending work. Therefore we do not need to compare flush_ser and req_ser at the beginning. On the contrary, the same work could be queued only once at a time. Therefore it has to re-queue itself if some requests are pending. Otherwise, wake_up_process() is replaced by queuing the work. Important: The change is only compile tested. I did not find an easy way how to check it in a real life. Signed-off-by: Petr Mladek <pmladek@suse.com> TO: Doug Ledford <dledford@redhat.com> CC: Sean Hefty <sean.hefty@intel.com> CC: Hal Rosenstock <hal.rosenstock@gmail.com> CC: linux-rdma@vger.kernel.org Signed-off-by: Doug Ledford <dledford@redhat.com>
2016-10-17 18:39:32 +03:00
kthread_queue_work(pool->worker, &pool->work);
}
}
}
#ifdef DEBUG
if (fmr->ref_count < 0)
pr_warn(PFX "FMR %p has ref count %d < 0\n",
fmr, fmr->ref_count);
#endif
spin_unlock_irqrestore(&pool->pool_lock, flags);
return 0;
}
EXPORT_SYMBOL(ib_fmr_pool_unmap);