diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2016-05-28 11:04:16 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2016-05-28 11:04:16 -0700 |
commit | 1cbe06c3cf542d48eb22180163e00f91760ef8cd (patch) | |
tree | ba093bf9e32790950b99bfec838a0354df5bf0dc /drivers/infiniband/hw/hfi1/user_pages.c | |
parent | ed2608faa0f701b1dbc65277a9e5c7ff7118bfd4 (diff) | |
parent | 7a226f9c32b0481b0744e2726cd7f8349b866af5 (diff) | |
download | linux-1cbe06c3cf542d48eb22180163e00f91760ef8cd.tar.gz linux-1cbe06c3cf542d48eb22180163e00f91760ef8cd.tar.bz2 linux-1cbe06c3cf542d48eb22180163e00f91760ef8cd.zip |
Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma
Pull more rdma updates from Doug Ledford:
"This is the second group of code for the 4.7 merge window. It looks
large, but only in one sense. I'll get to that in a minute. The list
of changes here breaks down as follows:
- Dynamic counter infrastructure in the IB drivers
This is a sysfs based code to allow free form access to the
hardware counters RDMA devices might support so drivers don't need
to code this up repeatedly themselves
- SendOnlyFullMember multicast support
- IB router support
- A couple misc fixes
- The big item on the list: hfi1 driver updates, plus moving the hfi1
driver out of staging
There was a group of 15 patches in the hfi1 list that I thought I had
in the first pull request but they weren't. So that added to the
length of the hfi1 section here.
As far as these go, everything but the hfi1 is pretty straight
forward.
The hfi1 is, if you recall, the driver that Al had complaints about
how it used the write/writev interfaces in an overloaded fashion. The
write portion of their interface behaved like the write handler in the
IB stack proper and did bi-directional communications. The writev
interface, on the other hand, only accepts SDMA request structures.
The completions for those structures are sent back via an entirely
different event mechanism.
With the security patch, we put security checks on the write
interface, however, we also knew they would be going away soon. Now,
we've converted the write handler in the hfi1 driver to use ioctls
from the IB reserved magic area for its bidirectional communications.
With that change, Intel has addressed all of the items originally on
their TODO when they went into staging (as well as many items added to
the list later).
As such, I moved them out, and since they were the last item in the
staging/rdma directory, and I don't have immediate plans to use the
staging area again, I removed the staging/rdma area.
Because of the move out of staging, as well as a series of 5 patches
in the hfi1 driver that removed code people thought should be done in
a different way and was optional to begin with (a snoop debug
interface, an eeprom driver for an eeprom connected directory to their
hfi1 chip and not via an i2c bus, and a few other things like that),
the line count, especially the removal count, is high"
* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (56 commits)
staging/rdma: Remove the entire rdma subdirectory of staging
IB/core: Make device counter infrastructure dynamic
IB/hfi1: Fix pio map initialization
IB/hfi1: Correct 8051 link parameter settings
IB/hfi1: Update pkey table properly after link down or FM start
IB/rdamvt: Fix rdmavt s_ack_queue sizing
IB/rdmavt: Max atomic value should be a u8
IB/hfi1: Fix hard lockup due to not using save/restore spin lock
IB/hfi1: Add tracing support for send with invalidate opcode
IB/hfi1, qib: Add ieth to the packet header definitions
IB/hfi1: Move driver out of staging
IB/hfi1: Do not free hfi1 cdev parent structure early
IB/hfi1: Add trace message in user IOCTL handling
IB/hfi1: Remove write(), use ioctl() for user cmds
IB/hfi1: Add ioctl() interface for user commands
IB/hfi1: Remove unused user command
IB/hfi1: Remove snoop/diag interface
IB/hfi1: Remove EPROM functionality from data device
IB/hfi1: Remove UI char device
IB/hfi1: Remove multiple device cdev
...
Diffstat (limited to 'drivers/infiniband/hw/hfi1/user_pages.c')
-rw-r--r-- | drivers/infiniband/hw/hfi1/user_pages.c | 135 |
1 files changed, 135 insertions, 0 deletions
diff --git a/drivers/infiniband/hw/hfi1/user_pages.c b/drivers/infiniband/hw/hfi1/user_pages.c new file mode 100644 index 000000000000..88e10b5f55f1 --- /dev/null +++ b/drivers/infiniband/hw/hfi1/user_pages.c @@ -0,0 +1,135 @@ +/* + * Copyright(c) 2015, 2016 Intel Corporation. + * + * This file is provided under a dual BSD/GPLv2 license. When using or + * redistributing this file, you may do so under either license. + * + * GPL LICENSE SUMMARY + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of version 2 of the GNU General Public License as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + * 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. + * - Neither the name of Intel Corporation nor the names of its + * contributors may be used to endorse or promote products derived + * from this software without specific prior written permission. + * + * 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 <linux/mm.h> +#include <linux/sched.h> +#include <linux/device.h> +#include <linux/module.h> + +#include "hfi.h" + +static unsigned long cache_size = 256; +module_param(cache_size, ulong, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(cache_size, "Send and receive side cache size limit (in MB)"); + +/* + * Determine whether the caller can pin pages. + * + * This function should be used in the implementation of buffer caches. + * The cache implementation should call this function prior to attempting + * to pin buffer pages in order to determine whether they should do so. + * The function computes cache limits based on the configured ulimit and + * cache size. Use of this function is especially important for caches + * which are not limited in any other way (e.g. by HW resources) and, thus, + * could keeping caching buffers. + * + */ +bool hfi1_can_pin_pages(struct hfi1_devdata *dd, u32 nlocked, u32 npages) +{ + unsigned long ulimit = rlimit(RLIMIT_MEMLOCK), pinned, cache_limit, + size = (cache_size * (1UL << 20)); /* convert to bytes */ + unsigned usr_ctxts = dd->num_rcv_contexts - dd->first_user_ctxt; + bool can_lock = capable(CAP_IPC_LOCK); + + /* + * Calculate per-cache size. The calculation below uses only a quarter + * of the available per-context limit. This leaves space for other + * pinning. Should we worry about shared ctxts? + */ + cache_limit = (ulimit / usr_ctxts) / 4; + + /* If ulimit isn't set to "unlimited" and is smaller than cache_size. */ + if (ulimit != (-1UL) && size > cache_limit) + size = cache_limit; + + /* Convert to number of pages */ + size = DIV_ROUND_UP(size, PAGE_SIZE); + + down_read(¤t->mm->mmap_sem); + pinned = current->mm->pinned_vm; + up_read(¤t->mm->mmap_sem); + + /* First, check the absolute limit against all pinned pages. */ + if (pinned + npages >= ulimit && !can_lock) + return false; + + return ((nlocked + npages) <= size) || can_lock; +} + +int hfi1_acquire_user_pages(unsigned long vaddr, size_t npages, bool writable, + struct page **pages) +{ + int ret; + + ret = get_user_pages_fast(vaddr, npages, writable, pages); + if (ret < 0) + return ret; + + down_write(¤t->mm->mmap_sem); + current->mm->pinned_vm += ret; + up_write(¤t->mm->mmap_sem); + + return ret; +} + +void hfi1_release_user_pages(struct mm_struct *mm, struct page **p, + size_t npages, bool dirty) +{ + size_t i; + + for (i = 0; i < npages; i++) { + if (dirty) + set_page_dirty_lock(p[i]); + put_page(p[i]); + } + + if (mm) { /* during close after signal, mm can be NULL */ + down_write(&mm->mmap_sem); + mm->pinned_vm -= npages; + up_write(&mm->mmap_sem); + } +} |