linux-stable/virt/kvm/async_pf.c
Lorenzo Stoakes ca5e863233 mm/gup: remove vmas parameter from get_user_pages_remote()
The only instances of get_user_pages_remote() invocations which used the
vmas parameter were for a single page which can instead simply look up the
VMA directly. In particular:-

- __update_ref_ctr() looked up the VMA but did nothing with it so we simply
  remove it.

- __access_remote_vm() was already using vma_lookup() when the original
  lookup failed so by doing the lookup directly this also de-duplicates the
  code.

We are able to perform these VMA operations as we already hold the
mmap_lock in order to be able to call get_user_pages_remote().

As part of this work we add get_user_page_vma_remote() which abstracts the
VMA lookup, error handling and decrementing the page reference count should
the VMA lookup fail.

This forms part of a broader set of patches intended to eliminate the vmas
parameter altogether.

[akpm@linux-foundation.org: avoid passing NULL to PTR_ERR]
Link: https://lkml.kernel.org/r/d20128c849ecdbf4dd01cc828fcec32127ed939a.1684350871.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com> (for arm64)
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com> (for s390)
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Christian König <christian.koenig@amd.com>
Cc: Dennis Dalessandro <dennis.dalessandro@cornelisnetworks.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Sakari Ailus <sakari.ailus@linux.intel.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-06-09 16:25:26 -07:00

227 lines
5.2 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* kvm asynchronous fault support
*
* Copyright 2010 Red Hat, Inc.
*
* Author:
* Gleb Natapov <gleb@redhat.com>
*/
#include <linux/kvm_host.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/mmu_context.h>
#include <linux/sched/mm.h>
#include "async_pf.h"
#include <trace/events/kvm.h>
static struct kmem_cache *async_pf_cache;
int kvm_async_pf_init(void)
{
async_pf_cache = KMEM_CACHE(kvm_async_pf, 0);
if (!async_pf_cache)
return -ENOMEM;
return 0;
}
void kvm_async_pf_deinit(void)
{
kmem_cache_destroy(async_pf_cache);
async_pf_cache = NULL;
}
void kvm_async_pf_vcpu_init(struct kvm_vcpu *vcpu)
{
INIT_LIST_HEAD(&vcpu->async_pf.done);
INIT_LIST_HEAD(&vcpu->async_pf.queue);
spin_lock_init(&vcpu->async_pf.lock);
}
static void async_pf_execute(struct work_struct *work)
{
struct kvm_async_pf *apf =
container_of(work, struct kvm_async_pf, work);
struct mm_struct *mm = apf->mm;
struct kvm_vcpu *vcpu = apf->vcpu;
unsigned long addr = apf->addr;
gpa_t cr2_or_gpa = apf->cr2_or_gpa;
int locked = 1;
bool first;
might_sleep();
/*
* This work is run asynchronously to the task which owns
* mm and might be done in another context, so we must
* access remotely.
*/
mmap_read_lock(mm);
get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked);
if (locked)
mmap_read_unlock(mm);
if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
kvm_arch_async_page_present(vcpu, apf);
spin_lock(&vcpu->async_pf.lock);
first = list_empty(&vcpu->async_pf.done);
list_add_tail(&apf->link, &vcpu->async_pf.done);
apf->vcpu = NULL;
spin_unlock(&vcpu->async_pf.lock);
if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
kvm_arch_async_page_present_queued(vcpu);
/*
* apf may be freed by kvm_check_async_pf_completion() after
* this point
*/
trace_kvm_async_pf_completed(addr, cr2_or_gpa);
__kvm_vcpu_wake_up(vcpu);
mmput(mm);
kvm_put_kvm(vcpu->kvm);
}
void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
{
spin_lock(&vcpu->async_pf.lock);
/* cancel outstanding work queue item */
while (!list_empty(&vcpu->async_pf.queue)) {
struct kvm_async_pf *work =
list_first_entry(&vcpu->async_pf.queue,
typeof(*work), queue);
list_del(&work->queue);
/*
* We know it's present in vcpu->async_pf.done, do
* nothing here.
*/
if (!work->vcpu)
continue;
spin_unlock(&vcpu->async_pf.lock);
#ifdef CONFIG_KVM_ASYNC_PF_SYNC
flush_work(&work->work);
#else
if (cancel_work_sync(&work->work)) {
mmput(work->mm);
kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
kmem_cache_free(async_pf_cache, work);
}
#endif
spin_lock(&vcpu->async_pf.lock);
}
while (!list_empty(&vcpu->async_pf.done)) {
struct kvm_async_pf *work =
list_first_entry(&vcpu->async_pf.done,
typeof(*work), link);
list_del(&work->link);
kmem_cache_free(async_pf_cache, work);
}
spin_unlock(&vcpu->async_pf.lock);
vcpu->async_pf.queued = 0;
}
void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
{
struct kvm_async_pf *work;
while (!list_empty_careful(&vcpu->async_pf.done) &&
kvm_arch_can_dequeue_async_page_present(vcpu)) {
spin_lock(&vcpu->async_pf.lock);
work = list_first_entry(&vcpu->async_pf.done, typeof(*work),
link);
list_del(&work->link);
spin_unlock(&vcpu->async_pf.lock);
kvm_arch_async_page_ready(vcpu, work);
if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
kvm_arch_async_page_present(vcpu, work);
list_del(&work->queue);
vcpu->async_pf.queued--;
kmem_cache_free(async_pf_cache, work);
}
}
/*
* Try to schedule a job to handle page fault asynchronously. Returns 'true' on
* success, 'false' on failure (page fault has to be handled synchronously).
*/
bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
unsigned long hva, struct kvm_arch_async_pf *arch)
{
struct kvm_async_pf *work;
if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
return false;
/* Arch specific code should not do async PF in this case */
if (unlikely(kvm_is_error_hva(hva)))
return false;
/*
* do alloc nowait since if we are going to sleep anyway we
* may as well sleep faulting in page
*/
work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT | __GFP_NOWARN);
if (!work)
return false;
work->wakeup_all = false;
work->vcpu = vcpu;
work->cr2_or_gpa = cr2_or_gpa;
work->addr = hva;
work->arch = *arch;
work->mm = current->mm;
mmget(work->mm);
kvm_get_kvm(work->vcpu->kvm);
INIT_WORK(&work->work, async_pf_execute);
list_add_tail(&work->queue, &vcpu->async_pf.queue);
vcpu->async_pf.queued++;
work->notpresent_injected = kvm_arch_async_page_not_present(vcpu, work);
schedule_work(&work->work);
return true;
}
int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu)
{
struct kvm_async_pf *work;
bool first;
if (!list_empty_careful(&vcpu->async_pf.done))
return 0;
work = kmem_cache_zalloc(async_pf_cache, GFP_ATOMIC);
if (!work)
return -ENOMEM;
work->wakeup_all = true;
INIT_LIST_HEAD(&work->queue); /* for list_del to work */
spin_lock(&vcpu->async_pf.lock);
first = list_empty(&vcpu->async_pf.done);
list_add_tail(&work->link, &vcpu->async_pf.done);
spin_unlock(&vcpu->async_pf.lock);
if (!IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC) && first)
kvm_arch_async_page_present_queued(vcpu);
vcpu->async_pf.queued++;
return 0;
}