linux-stable/mm/hmm.c

1099 lines
29 KiB
C
Raw Normal View History

treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 157 Based on 3 normalized pattern(s): this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version 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 this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] 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 this program is free software you can redistribute it and or modify it under the terms of the gnu general public license as published by the free software foundation either version 2 of the license or at your option any later version [author] [graeme] [gregory] [gg]@[slimlogic] [co] [uk] [author] [kishon] [vijay] [abraham] [i] [kishon]@[ti] [com] [based] [on] [twl6030]_[usb] [c] [author] [hema] [hk] [hemahk]@[ti] [com] 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 extracted by the scancode license scanner the SPDX license identifier GPL-2.0-or-later has been chosen to replace the boilerplate/reference in 1105 file(s). Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Reviewed-by: Allison Randal <allison@lohutok.net> Reviewed-by: Richard Fontana <rfontana@redhat.com> Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Cc: linux-spdx@vger.kernel.org Link: https://lkml.kernel.org/r/20190527070033.202006027@linutronix.de Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-27 06:55:06 +00:00
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Copyright 2013 Red Hat Inc.
*
* Authors: Jérôme Glisse <jglisse@redhat.com>
*/
/*
* Refer to include/linux/hmm.h for information about heterogeneous memory
* management or HMM for short.
*/
#include <linux/pagewalk.h>
#include <linux/hmm.h>
#include <linux/init.h>
#include <linux/rmap.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/sched.h>
mm/hmm/devmem: device memory hotplug using ZONE_DEVICE This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:58 +00:00
#include <linux/mmzone.h>
#include <linux/pagemap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>
mm/hmm/devmem: device memory hotplug using ZONE_DEVICE This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:58 +00:00
#include <linux/memremap.h>
#include <linux/sched/mm.h>
#include <linux/jump_label.h>
#include <linux/dma-mapping.h>
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
#include <linux/mmu_notifier.h>
mm/hmm/devmem: device memory hotplug using ZONE_DEVICE This introduce a simple struct and associated helpers for device driver to use when hotpluging un-addressable device memory as ZONE_DEVICE. It will find a unuse physical address range and trigger memory hotplug for it which allocates and initialize struct page for the device memory. Device driver should use this helper during device initialization to hotplug the device memory. It should only need to remove the memory once the device is going offline (shutdown or hotremove). There should not be any userspace API to hotplug memory expect maybe for host device driver to allow to add more memory to a guest device driver. Device's memory is manage by the device driver and HMM only provides helpers to that effect. Link: http://lkml.kernel.org/r/20170817000548.32038-12-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Signed-off-by: Balbir Singh <bsingharora@gmail.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:58 +00:00
#include <linux/memory_hotplug.h>
static struct mmu_notifier *hmm_alloc_notifier(struct mm_struct *mm)
{
struct hmm *hmm;
hmm = kzalloc(sizeof(*hmm), GFP_KERNEL);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
if (!hmm)
return ERR_PTR(-ENOMEM);
init_waitqueue_head(&hmm->wq);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
INIT_LIST_HEAD(&hmm->mirrors);
init_rwsem(&hmm->mirrors_sem);
INIT_LIST_HEAD(&hmm->ranges);
spin_lock_init(&hmm->ranges_lock);
hmm->notifiers = 0;
return &hmm->mmu_notifier;
}
static void hmm_free_notifier(struct mmu_notifier *mn)
{
struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
WARN_ON(!list_empty(&hmm->ranges));
WARN_ON(!list_empty(&hmm->mirrors));
kfree(hmm);
}
static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
struct hmm_mirror *mirror;
/*
* Since hmm_range_register() holds the mmget() lock hmm_release() is
* prevented as long as a range exists.
*/
WARN_ON(!list_empty_careful(&hmm->ranges));
down_read(&hmm->mirrors_sem);
list_for_each_entry(mirror, &hmm->mirrors, list) {
/*
* Note: The driver is not allowed to trigger
* hmm_mirror_unregister() from this thread.
*/
if (mirror->ops->release)
mirror->ops->release(mirror);
}
up_read(&hmm->mirrors_sem);
}
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
static void notifiers_decrement(struct hmm *hmm)
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
{
unsigned long flags;
spin_lock_irqsave(&hmm->ranges_lock, flags);
hmm->notifiers--;
if (!hmm->notifiers) {
struct hmm_range *range;
list_for_each_entry(range, &hmm->ranges, list) {
if (range->valid)
continue;
range->valid = true;
}
wake_up_all(&hmm->wq);
}
spin_unlock_irqrestore(&hmm->ranges_lock, flags);
}
mm, oom: distinguish blockable mode for mmu notifiers There are several blockable mmu notifiers which might sleep in mmu_notifier_invalidate_range_start and that is a problem for the oom_reaper because it needs to guarantee a forward progress so it cannot depend on any sleepable locks. Currently we simply back off and mark an oom victim with blockable mmu notifiers as done after a short sleep. That can result in selecting a new oom victim prematurely because the previous one still hasn't torn its memory down yet. We can do much better though. Even if mmu notifiers use sleepable locks there is no reason to automatically assume those locks are held. Moreover majority of notifiers only care about a portion of the address space and there is absolutely zero reason to fail when we are unmapping an unrelated range. Many notifiers do really block and wait for HW which is harder to handle and we have to bail out though. This patch handles the low hanging fruit. __mmu_notifier_invalidate_range_start gets a blockable flag and callbacks are not allowed to sleep if the flag is set to false. This is achieved by using trylock instead of the sleepable lock for most callbacks and continue as long as we do not block down the call chain. I think we can improve that even further because there is a common pattern to do a range lookup first and then do something about that. The first part can be done without a sleeping lock in most cases AFAICS. The oom_reaper end then simply retries if there is at least one notifier which couldn't make any progress in !blockable mode. A retry loop is already implemented to wait for the mmap_sem and this is basically the same thing. The simplest way for driver developers to test this code path is to wrap userspace code which uses these notifiers into a memcg and set the hard limit to hit the oom. This can be done e.g. after the test faults in all the mmu notifier managed memory and set the hard limit to something really small. Then we are looking for a proper process tear down. [akpm@linux-foundation.org: coding style fixes] [akpm@linux-foundation.org: minor code simplification] Link: http://lkml.kernel.org/r/20180716115058.5559-1-mhocko@kernel.org Signed-off-by: Michal Hocko <mhocko@suse.com> Acked-by: Christian König <christian.koenig@amd.com> # AMD notifiers Acked-by: Leon Romanovsky <leonro@mellanox.com> # mlx and umem_odp Reported-by: David Rientjes <rientjes@google.com> Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Alex Deucher <alexander.deucher@amd.com> Cc: David Airlie <airlied@linux.ie> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Doug Ledford <dledford@redhat.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Mike Marciniszyn <mike.marciniszyn@intel.com> Cc: Dennis Dalessandro <dennis.dalessandro@intel.com> Cc: Sudeep Dutt <sudeep.dutt@intel.com> Cc: Ashutosh Dixit <ashutosh.dixit@intel.com> Cc: Dimitri Sivanich <sivanich@sgi.com> Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com> Cc: Juergen Gross <jgross@suse.com> Cc: "Jérôme Glisse" <jglisse@redhat.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Felix Kuehling <felix.kuehling@amd.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-22 04:52:33 +00:00
static int hmm_invalidate_range_start(struct mmu_notifier *mn,
const struct mmu_notifier_range *nrange)
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
{
struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
struct hmm_mirror *mirror;
struct hmm_range *range;
unsigned long flags;
int ret = 0;
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
spin_lock_irqsave(&hmm->ranges_lock, flags);
hmm->notifiers++;
list_for_each_entry(range, &hmm->ranges, list) {
if (nrange->end < range->start || nrange->start >= range->end)
continue;
range->valid = false;
}
spin_unlock_irqrestore(&hmm->ranges_lock, flags);
mm/mmu_notifier: convert user range->blockable to helper function Use the mmu_notifier_range_blockable() helper function instead of directly dereferencing the range->blockable field. This is done to make it easier to change the mmu_notifier range field. This patch is the outcome of the following coccinelle patch: %<------------------------------------------------------------------- @@ identifier I1, FN; @@ FN(..., struct mmu_notifier_range *I1, ...) { <... -I1->blockable +mmu_notifier_range_blockable(I1) ...> } ------------------------------------------------------------------->% spatch --in-place --sp-file blockable.spatch --dir . Link: http://lkml.kernel.org/r/20190326164747.24405-3-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Reviewed-by: Ralph Campbell <rcampbell@nvidia.com> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Cc: Christian König <christian.koenig@amd.com> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Cc: Jani Nikula <jani.nikula@linux.intel.com> Cc: Rodrigo Vivi <rodrigo.vivi@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Peter Xu <peterx@redhat.com> Cc: Felix Kuehling <Felix.Kuehling@amd.com> Cc: Jason Gunthorpe <jgg@mellanox.com> Cc: Ross Zwisler <zwisler@kernel.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Paolo Bonzini <pbonzini@redhat.com> Cc: Radim Krcmar <rkrcmar@redhat.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Christian Koenig <christian.koenig@amd.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 00:20:38 +00:00
if (mmu_notifier_range_blockable(nrange))
down_read(&hmm->mirrors_sem);
else if (!down_read_trylock(&hmm->mirrors_sem)) {
ret = -EAGAIN;
goto out;
}
list_for_each_entry(mirror, &hmm->mirrors, list) {
int rc;
rc = mirror->ops->sync_cpu_device_pagetables(mirror, nrange);
if (rc) {
if (WARN_ON(mmu_notifier_range_blockable(nrange) ||
rc != -EAGAIN))
continue;
ret = -EAGAIN;
break;
}
}
up_read(&hmm->mirrors_sem);
out:
if (ret)
notifiers_decrement(hmm);
return ret;
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
}
static void hmm_invalidate_range_end(struct mmu_notifier *mn,
const struct mmu_notifier_range *nrange)
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
{
struct hmm *hmm = container_of(mn, struct hmm, mmu_notifier);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
notifiers_decrement(hmm);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
}
static const struct mmu_notifier_ops hmm_mmu_notifier_ops = {
.release = hmm_release,
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
.invalidate_range_start = hmm_invalidate_range_start,
.invalidate_range_end = hmm_invalidate_range_end,
.alloc_notifier = hmm_alloc_notifier,
.free_notifier = hmm_free_notifier,
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
};
/*
* hmm_mirror_register() - register a mirror against an mm
*
* @mirror: new mirror struct to register
* @mm: mm to register against
* Return: 0 on success, -ENOMEM if no memory, -EINVAL if invalid arguments
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
*
* To start mirroring a process address space, the device driver must register
* an HMM mirror struct.
*
* The caller cannot unregister the hmm_mirror while any ranges are
* registered.
*
* Callers using this function must put a call to mmu_notifier_synchronize()
* in their module exit functions.
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
*/
int hmm_mirror_register(struct hmm_mirror *mirror, struct mm_struct *mm)
{
struct mmu_notifier *mn;
HMM patches for 5.3 Improvements and bug fixes for the hmm interface in the kernel: - Improve clarity, locking and APIs related to the 'hmm mirror' feature merged last cycle. In linux-next we now see AMDGPU and nouveau to be using this API. - Remove old or transitional hmm APIs. These are hold overs from the past with no users, or APIs that existed only to manage cross tree conflicts. There are still a few more of these cleanups that didn't make the merge window cut off. - Improve some core mm APIs: * export alloc_pages_vma() for driver use * refactor into devm_request_free_mem_region() to manage DEVICE_PRIVATE resource reservations * refactor duplicative driver code into the core dev_pagemap struct - Remove hmm wrappers of improved core mm APIs, instead have drivers use the simplified API directly - Remove DEVICE_PUBLIC - Simplify the kconfig flow for the hmm users and core code -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEfB7FMLh+8QxL+6i3OG33FX4gmxoFAl0k1zkACgkQOG33FX4g mxrO+w//QF/yI/9Hh30RWEBq8W107cODkDlaT0Z/7cVEXfGetZzIUpqzxnJofRfQ xTw1XmYkc9WpJe/mTTuFZFewNQwWuMM6X0Xi25fV438/Y64EclevlcJTeD49TIH1 CIMsz8bX7CnCEq5sz+UypLg9LPnaD9L/JLyuSbyjqjms/o+yzqa7ji7p/DSINuhZ Qva9OZL1ZSEDJfNGi8uGpYBqryHoBAonIL12R9sCF5pbJEnHfWrH7C06q7AWOAjQ 4vjN/p3F4L9l/v2IQ26Kn/S0AhmN7n3GT//0K66e2gJPfXa8fxRKGuFn/Kd79EGL YPASn5iu3cM23up1XkbMNtzacL8yiIeTOcMdqw26OaOClojy/9OJduv5AChe6qL/ VUQIAn1zvPsJTyC5U7mhmkrGuTpP6ivHpxtcaUp+Ovvi1cyK40nLCmSNvLnbN5ES bxbb0SjE4uupDG5qU6Yct/hFp6uVMSxMqXZOb9Xy8ZBkbMsJyVOLj71G1/rVIfPU hO1AChX5CRG1eJoMo6oBIpiwmSvcOaPp3dqIOQZvwMOqrO869LR8qv7RXyh/g9gi FAEKnwLl4GK3YtEO4Kt/1YI5DXYjSFUbfgAs0SPsRKS6hK2+RgRk2M/B/5dAX0/d lgOf9WPODPwiSXBYLtJB8qHVDX0DIY8faOyTx6BYIKClUtgbBI8= =wKvp -----END PGP SIGNATURE----- Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma Pull HMM updates from Jason Gunthorpe: "Improvements and bug fixes for the hmm interface in the kernel: - Improve clarity, locking and APIs related to the 'hmm mirror' feature merged last cycle. In linux-next we now see AMDGPU and nouveau to be using this API. - Remove old or transitional hmm APIs. These are hold overs from the past with no users, or APIs that existed only to manage cross tree conflicts. There are still a few more of these cleanups that didn't make the merge window cut off. - Improve some core mm APIs: - export alloc_pages_vma() for driver use - refactor into devm_request_free_mem_region() to manage DEVICE_PRIVATE resource reservations - refactor duplicative driver code into the core dev_pagemap struct - Remove hmm wrappers of improved core mm APIs, instead have drivers use the simplified API directly - Remove DEVICE_PUBLIC - Simplify the kconfig flow for the hmm users and core code" * tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (42 commits) mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR mm: remove the HMM config option mm: sort out the DEVICE_PRIVATE Kconfig mess mm: simplify ZONE_DEVICE page private data mm: remove hmm_devmem_add mm: remove hmm_vma_alloc_locked_page nouveau: use devm_memremap_pages directly nouveau: use alloc_page_vma directly PCI/P2PDMA: use the dev_pagemap internal refcount device-dax: use the dev_pagemap internal refcount memremap: provide an optional internal refcount in struct dev_pagemap memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag memremap: remove the data field in struct dev_pagemap memremap: add a migrate_to_ram method to struct dev_pagemap_ops memremap: lift the devmap_enable manipulation into devm_memremap_pages memremap: pass a struct dev_pagemap to ->kill and ->cleanup memremap: move dev_pagemap callbacks into a separate structure memremap: validate the pagemap type passed to devm_memremap_pages mm: factor out a devm_request_free_mem_region helper mm: export alloc_pages_vma ...
2019-07-15 02:42:11 +00:00
lockdep_assert_held_write(&mm->mmap_sem);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
/* Sanity check */
if (!mm || !mirror || !mirror->ops)
return -EINVAL;
mn = mmu_notifier_get_locked(&hmm_mmu_notifier_ops, mm);
if (IS_ERR(mn))
return PTR_ERR(mn);
mirror->hmm = container_of(mn, struct hmm, mmu_notifier);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
down_write(&mirror->hmm->mirrors_sem);
list_add(&mirror->list, &mirror->hmm->mirrors);
up_write(&mirror->hmm->mirrors_sem);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
return 0;
}
EXPORT_SYMBOL(hmm_mirror_register);
/*
* hmm_mirror_unregister() - unregister a mirror
*
* @mirror: mirror struct to unregister
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
*
* Stop mirroring a process address space, and cleanup.
*/
void hmm_mirror_unregister(struct hmm_mirror *mirror)
{
struct hmm *hmm = mirror->hmm;
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
down_write(&hmm->mirrors_sem);
list_del(&mirror->list);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
up_write(&hmm->mirrors_sem);
mmu_notifier_put(&hmm->mmu_notifier);
mm/hmm/mirror: mirror process address space on device with HMM helpers This is a heterogeneous memory management (HMM) process address space mirroring. In a nutshell this provide an API to mirror process address space on a device. This boils down to keeping CPU and device page table synchronize (we assume that both device and CPU are cache coherent like PCIe device can be). This patch provide a simple API for device driver to achieve address space mirroring thus avoiding each device driver to grow its own CPU page table walker and its own CPU page table synchronization mechanism. This is useful for NVidia GPU >= Pascal, Mellanox IB >= mlx5 and more hardware in the future. [jglisse@redhat.com: fix hmm for "mmu_notifier kill invalidate_page callback"] Link: http://lkml.kernel.org/r/20170830231955.GD9445@redhat.com Link: http://lkml.kernel.org/r/20170817000548.32038-4-jglisse@redhat.com Signed-off-by: Jérôme Glisse <jglisse@redhat.com> Signed-off-by: Evgeny Baskakov <ebaskakov@nvidia.com> Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Mark Hairgrove <mhairgrove@nvidia.com> Signed-off-by: Sherry Cheung <SCheung@nvidia.com> Signed-off-by: Subhash Gutti <sgutti@nvidia.com> Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com> Cc: Balbir Singh <bsingharora@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: David Nellans <dnellans@nvidia.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ross Zwisler <ross.zwisler@linux.intel.com> Cc: Vladimir Davydov <vdavydov.dev@gmail.com> Cc: Bob Liu <liubo95@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2017-09-08 23:11:27 +00:00
}
EXPORT_SYMBOL(hmm_mirror_unregister);
struct hmm_vma_walk {
struct hmm_range *range;
struct dev_pagemap *pgmap;
unsigned long last;
unsigned int flags;
};
static int hmm_vma_do_fault(struct mm_walk *walk, unsigned long addr,
bool write_fault, uint64_t *pfn)
{
unsigned int flags = FAULT_FLAG_REMOTE;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
mm: convert return type of handle_mm_fault() caller to vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t") In this patch all the caller of handle_mm_fault() are changed to return vm_fault_t type. Link: http://lkml.kernel.org/r/20180617084810.GA6730@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Tony Luck <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: James Hogan <jhogan@kernel.org> Cc: Ley Foon Tan <lftan@altera.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: David S. Miller <davem@davemloft.net> Cc: Richard Weinberger <richard@nod.at> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:44:47 +00:00
vm_fault_t ret;
if (!vma)
goto err;
if (hmm_vma_walk->flags & HMM_FAULT_ALLOW_RETRY)
flags |= FAULT_FLAG_ALLOW_RETRY;
if (write_fault)
flags |= FAULT_FLAG_WRITE;
mm: convert return type of handle_mm_fault() caller to vm_fault_t Use new return type vm_fault_t for fault handler. For now, this is just documenting that the function returns a VM_FAULT value rather than an errno. Once all instances are converted, vm_fault_t will become a distinct type. Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t") In this patch all the caller of handle_mm_fault() are changed to return vm_fault_t type. Link: http://lkml.kernel.org/r/20180617084810.GA6730@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Richard Henderson <rth@twiddle.net> Cc: Tony Luck <tony.luck@intel.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Russell King <linux@armlinux.org.uk> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Michal Simek <monstr@monstr.eu> Cc: James Hogan <jhogan@kernel.org> Cc: Ley Foon Tan <lftan@altera.com> Cc: Jonas Bonn <jonas@southpole.se> Cc: James E.J. Bottomley <jejb@parisc-linux.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Cc: David S. Miller <davem@davemloft.net> Cc: Richard Weinberger <richard@nod.at> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Levin, Alexander (Sasha Levin)" <alexander.levin@verizon.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-08-17 22:44:47 +00:00
ret = handle_mm_fault(vma, addr, flags);
if (ret & VM_FAULT_RETRY) {
/* Note, handle_mm_fault did up_read(&mm->mmap_sem)) */
return -EAGAIN;
}
if (ret & VM_FAULT_ERROR)
goto err;
return -EBUSY;
err:
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
}
static int hmm_pfns_bad(unsigned long addr,
unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
unsigned long i;
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, i++)
pfns[i] = range->values[HMM_PFN_ERROR];
return 0;
}
/*
* hmm_vma_walk_hole_() - handle a range lacking valid pmd or pte(s)
* @addr: range virtual start address (inclusive)
* @end: range virtual end address (exclusive)
* @fault: should we fault or not ?
* @write_fault: write fault ?
* @walk: mm_walk structure
* Return: 0 on success, -EBUSY after page fault, or page fault error
*
* This function will be called whenever pmd_none() or pte_none() returns true,
* or whenever there is no page directory covering the virtual address range.
*/
static int hmm_vma_walk_hole_(unsigned long addr, unsigned long end,
bool fault, bool write_fault,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
unsigned long i;
hmm_vma_walk->last = addr;
i = (addr - range->start) >> PAGE_SHIFT;
if (write_fault && walk->vma && !(walk->vma->vm_flags & VM_WRITE))
return -EPERM;
for (; addr < end; addr += PAGE_SIZE, i++) {
pfns[i] = range->values[HMM_PFN_NONE];
if (fault || write_fault) {
int ret;
ret = hmm_vma_do_fault(walk, addr, write_fault,
&pfns[i]);
if (ret != -EBUSY)
return ret;
}
}
return (fault || write_fault) ? -EBUSY : 0;
}
static inline void hmm_pte_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
uint64_t pfns, uint64_t cpu_flags,
bool *fault, bool *write_fault)
{
struct hmm_range *range = hmm_vma_walk->range;
if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT)
return;
/*
* So we not only consider the individual per page request we also
* consider the default flags requested for the range. The API can
* be used 2 ways. The first one where the HMM user coalesces
* multiple page faults into one request and sets flags per pfn for
* those faults. The second one where the HMM user wants to pre-
* fault a range with specific flags. For the latter one it is a
* waste to have the user pre-fill the pfn arrays with a default
* flags value.
*/
pfns = (pfns & range->pfn_flags_mask) | range->default_flags;
/* We aren't ask to do anything ... */
if (!(pfns & range->flags[HMM_PFN_VALID]))
return;
/* If this is device memory then only fault if explicitly requested */
if ((cpu_flags & range->flags[HMM_PFN_DEVICE_PRIVATE])) {
/* Do we fault on device memory ? */
if (pfns & range->flags[HMM_PFN_DEVICE_PRIVATE]) {
*write_fault = pfns & range->flags[HMM_PFN_WRITE];
*fault = true;
}
return;
}
/* If CPU page table is not valid then we need to fault */
*fault = !(cpu_flags & range->flags[HMM_PFN_VALID]);
/* Need to write fault ? */
if ((pfns & range->flags[HMM_PFN_WRITE]) &&
!(cpu_flags & range->flags[HMM_PFN_WRITE])) {
*write_fault = true;
*fault = true;
}
}
static void hmm_range_need_fault(const struct hmm_vma_walk *hmm_vma_walk,
const uint64_t *pfns, unsigned long npages,
uint64_t cpu_flags, bool *fault,
bool *write_fault)
{
unsigned long i;
if (hmm_vma_walk->flags & HMM_FAULT_SNAPSHOT) {
*fault = *write_fault = false;
return;
}
*fault = *write_fault = false;
for (i = 0; i < npages; ++i) {
hmm_pte_need_fault(hmm_vma_walk, pfns[i], cpu_flags,
fault, write_fault);
if ((*write_fault))
return;
}
}
static int hmm_vma_walk_hole(unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
bool fault, write_fault;
unsigned long i, npages;
uint64_t *pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
0, &fault, &write_fault);
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
}
static inline uint64_t pmd_to_hmm_pfn_flags(struct hmm_range *range, pmd_t pmd)
{
if (pmd_protnone(pmd))
return 0;
return pmd_write(pmd) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, uint64_t *pfns, pmd_t pmd)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long pfn, npages, i;
bool fault, write_fault;
uint64_t cpu_flags;
npages = (end - addr) >> PAGE_SHIFT;
cpu_flags = pmd_to_hmm_pfn_flags(range, pmd);
hmm_range_need_fault(hmm_vma_walk, pfns, npages, cpu_flags,
&fault, &write_fault);
if (pmd_protnone(pmd) || fault || write_fault)
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
pfn = pmd_pfn(pmd) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
for (i = 0; addr < end; addr += PAGE_SIZE, i++, pfn++) {
if (pmd_devmap(pmd)) {
hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
hmm_vma_walk->pgmap);
if (unlikely(!hmm_vma_walk->pgmap))
return -EBUSY;
}
pfns[i] = hmm_device_entry_from_pfn(range, pfn) | cpu_flags;
}
if (hmm_vma_walk->pgmap) {
put_dev_pagemap(hmm_vma_walk->pgmap);
hmm_vma_walk->pgmap = NULL;
}
hmm_vma_walk->last = end;
return 0;
}
#else /* CONFIG_TRANSPARENT_HUGEPAGE */
/* stub to allow the code below to compile */
int hmm_vma_handle_pmd(struct mm_walk *walk, unsigned long addr,
unsigned long end, uint64_t *pfns, pmd_t pmd);
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline uint64_t pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte)
{
if (pte_none(pte) || !pte_present(pte) || pte_protnone(pte))
return 0;
return pte_write(pte) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
static int hmm_vma_handle_pte(struct mm_walk *walk, unsigned long addr,
unsigned long end, pmd_t *pmdp, pte_t *ptep,
uint64_t *pfn)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
bool fault, write_fault;
uint64_t cpu_flags;
pte_t pte = *ptep;
uint64_t orig_pfn = *pfn;
*pfn = range->values[HMM_PFN_NONE];
fault = write_fault = false;
if (pte_none(pte)) {
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, 0,
&fault, &write_fault);
if (fault || write_fault)
goto fault;
return 0;
}
if (!pte_present(pte)) {
swp_entry_t entry = pte_to_swp_entry(pte);
if (!non_swap_entry(entry)) {
cpu_flags = pte_to_hmm_pfn_flags(range, pte);
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
&fault, &write_fault);
if (fault || write_fault)
goto fault;
return 0;
}
/*
* This is a special swap entry, ignore migration, use
* device and report anything else as error.
*/
if (is_device_private_entry(entry)) {
cpu_flags = range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_DEVICE_PRIVATE];
cpu_flags |= is_write_device_private_entry(entry) ?
range->flags[HMM_PFN_WRITE] : 0;
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
&fault, &write_fault);
if (fault || write_fault)
goto fault;
*pfn = hmm_device_entry_from_pfn(range,
swp_offset(entry));
*pfn |= cpu_flags;
return 0;
}
if (is_migration_entry(entry)) {
if (fault || write_fault) {
pte_unmap(ptep);
hmm_vma_walk->last = addr;
migration_entry_wait(walk->mm, pmdp, addr);
return -EBUSY;
}
return 0;
}
/* Report error for everything else */
*pfn = range->values[HMM_PFN_ERROR];
return -EFAULT;
} else {
cpu_flags = pte_to_hmm_pfn_flags(range, pte);
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
&fault, &write_fault);
}
if (fault || write_fault)
goto fault;
if (pte_devmap(pte)) {
hmm_vma_walk->pgmap = get_dev_pagemap(pte_pfn(pte),
hmm_vma_walk->pgmap);
if (unlikely(!hmm_vma_walk->pgmap))
return -EBUSY;
} else if (IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pte_special(pte)) {
*pfn = range->values[HMM_PFN_SPECIAL];
return -EFAULT;
}
*pfn = hmm_device_entry_from_pfn(range, pte_pfn(pte)) | cpu_flags;
return 0;
fault:
if (hmm_vma_walk->pgmap) {
put_dev_pagemap(hmm_vma_walk->pgmap);
hmm_vma_walk->pgmap = NULL;
}
pte_unmap(ptep);
/* Fault any virtual address we were asked to fault */
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
}
static int hmm_vma_walk_pmd(pmd_t *pmdp,
unsigned long start,
unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
uint64_t *pfns = range->pfns;
unsigned long addr = start, i;
pte_t *ptep;
pmd_t pmd;
again:
pmd = READ_ONCE(*pmdp);
if (pmd_none(pmd))
return hmm_vma_walk_hole(start, end, walk);
if (thp_migration_supported() && is_pmd_migration_entry(pmd)) {
bool fault, write_fault;
unsigned long npages;
uint64_t *pfns;
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
0, &fault, &write_fault);
if (fault || write_fault) {
hmm_vma_walk->last = addr;
pmd_migration_entry_wait(walk->mm, pmdp);
return -EBUSY;
}
return 0;
} else if (!pmd_present(pmd))
return hmm_pfns_bad(start, end, walk);
if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
/*
* No need to take pmd_lock here, even if some other thread
* is splitting the huge pmd we will get that event through
* mmu_notifier callback.
*
* So just read pmd value and check again it's a transparent
* huge or device mapping one and compute corresponding pfn
* values.
*/
pmd = pmd_read_atomic(pmdp);
barrier();
if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
goto again;
i = (addr - range->start) >> PAGE_SHIFT;
return hmm_vma_handle_pmd(walk, addr, end, &pfns[i], pmd);
}
/*
* We have handled all the valid cases above ie either none, migration,
* huge or transparent huge. At this point either it is a valid pmd
* entry pointing to pte directory or it is a bad pmd that will not
* recover.
*/
if (pmd_bad(pmd))
return hmm_pfns_bad(start, end, walk);
ptep = pte_offset_map(pmdp, addr);
i = (addr - range->start) >> PAGE_SHIFT;
for (; addr < end; addr += PAGE_SIZE, ptep++, i++) {
int r;
r = hmm_vma_handle_pte(walk, addr, end, pmdp, ptep, &pfns[i]);
if (r) {
/* hmm_vma_handle_pte() did unmap pte directory */
hmm_vma_walk->last = addr;
return r;
}
}
if (hmm_vma_walk->pgmap) {
/*
* We do put_dev_pagemap() here and not in hmm_vma_handle_pte()
* so that we can leverage get_dev_pagemap() optimization which
* will not re-take a reference on a pgmap if we already have
* one.
*/
put_dev_pagemap(hmm_vma_walk->pgmap);
hmm_vma_walk->pgmap = NULL;
}
pte_unmap(ptep - 1);
hmm_vma_walk->last = addr;
return 0;
}
#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
static inline uint64_t pud_to_hmm_pfn_flags(struct hmm_range *range, pud_t pud)
{
if (!pud_present(pud))
return 0;
return pud_write(pud) ? range->flags[HMM_PFN_VALID] |
range->flags[HMM_PFN_WRITE] :
range->flags[HMM_PFN_VALID];
}
static int hmm_vma_walk_pud(pud_t *pudp, unsigned long start, unsigned long end,
struct mm_walk *walk)
{
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
unsigned long addr = start, next;
pmd_t *pmdp;
pud_t pud;
int ret;
again:
pud = READ_ONCE(*pudp);
if (pud_none(pud))
return hmm_vma_walk_hole(start, end, walk);
if (pud_huge(pud) && pud_devmap(pud)) {
unsigned long i, npages, pfn;
uint64_t *pfns, cpu_flags;
bool fault, write_fault;
if (!pud_present(pud))
return hmm_vma_walk_hole(start, end, walk);
i = (addr - range->start) >> PAGE_SHIFT;
npages = (end - addr) >> PAGE_SHIFT;
pfns = &range->pfns[i];
cpu_flags = pud_to_hmm_pfn_flags(range, pud);
hmm_range_need_fault(hmm_vma_walk, pfns, npages,
cpu_flags, &fault, &write_fault);
if (fault || write_fault)
return hmm_vma_walk_hole_(addr, end, fault,
write_fault, walk);
pfn = pud_pfn(pud) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
for (i = 0; i < npages; ++i, ++pfn) {
hmm_vma_walk->pgmap = get_dev_pagemap(pfn,
hmm_vma_walk->pgmap);
if (unlikely(!hmm_vma_walk->pgmap))
return -EBUSY;
pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
}
if (hmm_vma_walk->pgmap) {
put_dev_pagemap(hmm_vma_walk->pgmap);
hmm_vma_walk->pgmap = NULL;
}
hmm_vma_walk->last = end;
return 0;
}
split_huge_pud(walk->vma, pudp, addr);
if (pud_none(*pudp))
goto again;
pmdp = pmd_offset(pudp, addr);
do {
next = pmd_addr_end(addr, end);
ret = hmm_vma_walk_pmd(pmdp, addr, next, walk);
if (ret)
return ret;
} while (pmdp++, addr = next, addr != end);
return 0;
}
#else
#define hmm_vma_walk_pud NULL
#endif
#ifdef CONFIG_HUGETLB_PAGE
static int hmm_vma_walk_hugetlb_entry(pte_t *pte, unsigned long hmask,
unsigned long start, unsigned long end,
struct mm_walk *walk)
{
unsigned long addr = start, i, pfn;
struct hmm_vma_walk *hmm_vma_walk = walk->private;
struct hmm_range *range = hmm_vma_walk->range;
struct vm_area_struct *vma = walk->vma;
uint64_t orig_pfn, cpu_flags;
bool fault, write_fault;
spinlock_t *ptl;
pte_t entry;
int ret = 0;
ptl = huge_pte_lock(hstate_vma(vma), walk->mm, pte);
entry = huge_ptep_get(pte);
i = (start - range->start) >> PAGE_SHIFT;
orig_pfn = range->pfns[i];
range->pfns[i] = range->values[HMM_PFN_NONE];
cpu_flags = pte_to_hmm_pfn_flags(range, entry);
fault = write_fault = false;
hmm_pte_need_fault(hmm_vma_walk, orig_pfn, cpu_flags,
&fault, &write_fault);
if (fault || write_fault) {
ret = -ENOENT;
goto unlock;
}
pfn = pte_pfn(entry) + ((start & ~hmask) >> PAGE_SHIFT);
for (; addr < end; addr += PAGE_SIZE, i++, pfn++)
range->pfns[i] = hmm_device_entry_from_pfn(range, pfn) |
cpu_flags;
hmm_vma_walk->last = end;
unlock:
spin_unlock(ptl);
if (ret == -ENOENT)
return hmm_vma_walk_hole_(addr, end, fault, write_fault, walk);
return ret;
}
#else
#define hmm_vma_walk_hugetlb_entry NULL
#endif /* CONFIG_HUGETLB_PAGE */
static void hmm_pfns_clear(struct hmm_range *range,
uint64_t *pfns,
unsigned long addr,
unsigned long end)
{
for (; addr < end; addr += PAGE_SIZE, pfns++)
*pfns = range->values[HMM_PFN_NONE];
}
/*
* hmm_range_register() - start tracking change to CPU page table over a range
* @range: range
* @mm: the mm struct for the range of virtual address
*
* Return: 0 on success, -EFAULT if the address space is no longer valid
*
* Track updates to the CPU page table see include/linux/hmm.h
*/
int hmm_range_register(struct hmm_range *range, struct hmm_mirror *mirror)
{
struct hmm *hmm = mirror->hmm;
unsigned long flags;
range->valid = false;
range->hmm = NULL;
if ((range->start & (PAGE_SIZE - 1)) || (range->end & (PAGE_SIZE - 1)))
return -EINVAL;
if (range->start >= range->end)
return -EINVAL;
/* Prevent hmm_release() from running while the range is valid */
if (!mmget_not_zero(hmm->mmu_notifier.mm))
return -EFAULT;
/* Initialize range to track CPU page table updates. */
spin_lock_irqsave(&hmm->ranges_lock, flags);
range->hmm = hmm;
list_add(&range->list, &hmm->ranges);
/*
* If there are any concurrent notifiers we have to wait for them for
* the range to be valid (see hmm_range_wait_until_valid()).
*/
if (!hmm->notifiers)
range->valid = true;
spin_unlock_irqrestore(&hmm->ranges_lock, flags);
return 0;
}
EXPORT_SYMBOL(hmm_range_register);
/*
* hmm_range_unregister() - stop tracking change to CPU page table over a range
* @range: range
*
* Range struct is used to track updates to the CPU page table after a call to
* hmm_range_register(). See include/linux/hmm.h for how to use it.
*/
void hmm_range_unregister(struct hmm_range *range)
{
struct hmm *hmm = range->hmm;
unsigned long flags;
spin_lock_irqsave(&hmm->ranges_lock, flags);
list_del_init(&range->list);
spin_unlock_irqrestore(&hmm->ranges_lock, flags);
/* Drop reference taken by hmm_range_register() */
mmput(hmm->mmu_notifier.mm);
/*
* The range is now invalid and the ref on the hmm is dropped, so
* poison the pointer. Leave other fields in place, for the caller's
* use.
*/
range->valid = false;
memset(&range->hmm, POISON_INUSE, sizeof(range->hmm));
}
EXPORT_SYMBOL(hmm_range_unregister);
static const struct mm_walk_ops hmm_walk_ops = {
.pud_entry = hmm_vma_walk_pud,
.pmd_entry = hmm_vma_walk_pmd,
.pte_hole = hmm_vma_walk_hole,
.hugetlb_entry = hmm_vma_walk_hugetlb_entry,
};
/**
* hmm_range_fault - try to fault some address in a virtual address range
* @range: range being faulted
* @flags: HMM_FAULT_* flags
*
* Return: the number of valid pages in range->pfns[] (from range start
* address), which may be zero. On error one of the following status codes
* can be returned:
*
* -EINVAL: Invalid arguments or mm or virtual address is in an invalid vma
* (e.g., device file vma).
* -ENOMEM: Out of memory.
* -EPERM: Invalid permission (e.g., asking for write and range is read
* only).
* -EAGAIN: A page fault needs to be retried and mmap_sem was dropped.
* -EBUSY: The range has been invalidated and the caller needs to wait for
* the invalidation to finish.
* -EFAULT: Invalid (i.e., either no valid vma or it is illegal to access
* that range) number of valid pages in range->pfns[] (from
* range start address).
*
* This is similar to a regular CPU page fault except that it will not trigger
* any memory migration if the memory being faulted is not accessible by CPUs
* and caller does not ask for migration.
*
* On error, for one virtual address in the range, the function will mark the
* corresponding HMM pfn entry with an error flag.
*/
long hmm_range_fault(struct hmm_range *range, unsigned int flags)
{
const unsigned long device_vma = VM_IO | VM_PFNMAP | VM_MIXEDMAP;
unsigned long start = range->start, end;
struct hmm_vma_walk hmm_vma_walk;
struct hmm *hmm = range->hmm;
struct vm_area_struct *vma;
int ret;
lockdep_assert_held(&hmm->mmu_notifier.mm->mmap_sem);
do {
/* If range is no longer valid force retry. */
if (!range->valid)
return -EBUSY;
vma = find_vma(hmm->mmu_notifier.mm, start);
if (vma == NULL || (vma->vm_flags & device_vma))
return -EFAULT;
if (!(vma->vm_flags & VM_READ)) {
/*
* If vma do not allow read access, then assume that it
* does not allow write access, either. HMM does not
* support architecture that allow write without read.
*/
hmm_pfns_clear(range, range->pfns,
range->start, range->end);
return -EPERM;
}
hmm_vma_walk.pgmap = NULL;
hmm_vma_walk.last = start;
hmm_vma_walk.flags = flags;
hmm_vma_walk.range = range;
end = min(range->end, vma->vm_end);
walk_page_range(vma->vm_mm, start, end, &hmm_walk_ops,
&hmm_vma_walk);
do {
ret = walk_page_range(vma->vm_mm, start, end,
&hmm_walk_ops, &hmm_vma_walk);
start = hmm_vma_walk.last;
/* Keep trying while the range is valid. */
} while (ret == -EBUSY && range->valid);
if (ret) {
unsigned long i;
i = (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
hmm_pfns_clear(range, &range->pfns[i],
hmm_vma_walk.last, range->end);
return ret;
}
start = end;
} while (start < range->end);
return (hmm_vma_walk.last - range->start) >> PAGE_SHIFT;
}
EXPORT_SYMBOL(hmm_range_fault);
/**
* hmm_range_dma_map - hmm_range_fault() and dma map page all in one.
* @range: range being faulted
* @device: device to map page to
* @daddrs: array of dma addresses for the mapped pages
* @flags: HMM_FAULT_*
*
* Return: the number of pages mapped on success (including zero), or any
* status return from hmm_range_fault() otherwise.
*/
long hmm_range_dma_map(struct hmm_range *range, struct device *device,
dma_addr_t *daddrs, unsigned int flags)
{
unsigned long i, npages, mapped;
long ret;
ret = hmm_range_fault(range, flags);
if (ret <= 0)
return ret ? ret : -EBUSY;
npages = (range->end - range->start) >> PAGE_SHIFT;
for (i = 0, mapped = 0; i < npages; ++i) {
enum dma_data_direction dir = DMA_TO_DEVICE;
struct page *page;
/*
* FIXME need to update DMA API to provide invalid DMA address
* value instead of a function to test dma address value. This
* would remove lot of dumb code duplicated accross many arch.
*
* For now setting it to 0 here is good enough as the pfns[]
* value is what is use to check what is valid and what isn't.
*/
daddrs[i] = 0;
page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
/* Check if range is being invalidated */
if (!range->valid) {
ret = -EBUSY;
goto unmap;
}
/* If it is read and write than map bi-directional. */
if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
dir = DMA_BIDIRECTIONAL;
daddrs[i] = dma_map_page(device, page, 0, PAGE_SIZE, dir);
if (dma_mapping_error(device, daddrs[i])) {
ret = -EFAULT;
goto unmap;
}
mapped++;
}
return mapped;
unmap:
for (npages = i, i = 0; (i < npages) && mapped; ++i) {
enum dma_data_direction dir = DMA_TO_DEVICE;
struct page *page;
page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
if (dma_mapping_error(device, daddrs[i]))
continue;
/* If it is read and write than map bi-directional. */
if (range->pfns[i] & range->flags[HMM_PFN_WRITE])
dir = DMA_BIDIRECTIONAL;
dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
mapped--;
}
return ret;
}
EXPORT_SYMBOL(hmm_range_dma_map);
/**
* hmm_range_dma_unmap() - unmap range of that was map with hmm_range_dma_map()
* @range: range being unmapped
* @device: device against which dma map was done
* @daddrs: dma address of mapped pages
* @dirty: dirty page if it had the write flag set
* Return: number of page unmapped on success, -EINVAL otherwise
*
* Note that caller MUST abide by mmu notifier or use HMM mirror and abide
* to the sync_cpu_device_pagetables() callback so that it is safe here to
* call set_page_dirty(). Caller must also take appropriate locks to avoid
* concurrent mmu notifier or sync_cpu_device_pagetables() to make progress.
*/
long hmm_range_dma_unmap(struct hmm_range *range,
struct device *device,
dma_addr_t *daddrs,
bool dirty)
{
unsigned long i, npages;
long cpages = 0;
/* Sanity check. */
if (range->end <= range->start)
return -EINVAL;
if (!daddrs)
return -EINVAL;
if (!range->pfns)
return -EINVAL;
npages = (range->end - range->start) >> PAGE_SHIFT;
for (i = 0; i < npages; ++i) {
enum dma_data_direction dir = DMA_TO_DEVICE;
struct page *page;
page = hmm_device_entry_to_page(range, range->pfns[i]);
if (page == NULL)
continue;
/* If it is read and write than map bi-directional. */
if (range->pfns[i] & range->flags[HMM_PFN_WRITE]) {
dir = DMA_BIDIRECTIONAL;
/*
* See comments in function description on why it is
* safe here to call set_page_dirty()
*/
if (dirty)
set_page_dirty(page);
}
/* Unmap and clear pfns/dma address */
dma_unmap_page(device, daddrs[i], PAGE_SIZE, dir);
range->pfns[i] = range->values[HMM_PFN_NONE];
/* FIXME see comments in hmm_vma_dma_map() */
daddrs[i] = 0;
cpages++;
}
return cpages;
}
EXPORT_SYMBOL(hmm_range_dma_unmap);