![Mark Rutland](/assets/img/avatar_default.png)
Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
267 lines
6.7 KiB
C
267 lines
6.7 KiB
C
/*
|
|
* Support KVM gust page tracking
|
|
*
|
|
* This feature allows us to track page access in guest. Currently, only
|
|
* write access is tracked.
|
|
*
|
|
* Copyright(C) 2015 Intel Corporation.
|
|
*
|
|
* Author:
|
|
* Xiao Guangrong <guangrong.xiao@linux.intel.com>
|
|
*
|
|
* This work is licensed under the terms of the GNU GPL, version 2. See
|
|
* the COPYING file in the top-level directory.
|
|
*/
|
|
|
|
#include <linux/kvm_host.h>
|
|
#include <linux/rculist.h>
|
|
|
|
#include <asm/kvm_host.h>
|
|
#include <asm/kvm_page_track.h>
|
|
|
|
#include "mmu.h"
|
|
|
|
void kvm_page_track_free_memslot(struct kvm_memory_slot *free,
|
|
struct kvm_memory_slot *dont)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < KVM_PAGE_TRACK_MAX; i++)
|
|
if (!dont || free->arch.gfn_track[i] !=
|
|
dont->arch.gfn_track[i]) {
|
|
kvfree(free->arch.gfn_track[i]);
|
|
free->arch.gfn_track[i] = NULL;
|
|
}
|
|
}
|
|
|
|
int kvm_page_track_create_memslot(struct kvm_memory_slot *slot,
|
|
unsigned long npages)
|
|
{
|
|
int i;
|
|
|
|
for (i = 0; i < KVM_PAGE_TRACK_MAX; i++) {
|
|
slot->arch.gfn_track[i] = kvzalloc(npages *
|
|
sizeof(*slot->arch.gfn_track[i]), GFP_KERNEL);
|
|
if (!slot->arch.gfn_track[i])
|
|
goto track_free;
|
|
}
|
|
|
|
return 0;
|
|
|
|
track_free:
|
|
kvm_page_track_free_memslot(slot, NULL);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
static inline bool page_track_mode_is_valid(enum kvm_page_track_mode mode)
|
|
{
|
|
if (mode < 0 || mode >= KVM_PAGE_TRACK_MAX)
|
|
return false;
|
|
|
|
return true;
|
|
}
|
|
|
|
static void update_gfn_track(struct kvm_memory_slot *slot, gfn_t gfn,
|
|
enum kvm_page_track_mode mode, short count)
|
|
{
|
|
int index, val;
|
|
|
|
index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
|
|
|
|
val = slot->arch.gfn_track[mode][index];
|
|
|
|
if (WARN_ON(val + count < 0 || val + count > USHRT_MAX))
|
|
return;
|
|
|
|
slot->arch.gfn_track[mode][index] += count;
|
|
}
|
|
|
|
/*
|
|
* add guest page to the tracking pool so that corresponding access on that
|
|
* page will be intercepted.
|
|
*
|
|
* It should be called under the protection both of mmu-lock and kvm->srcu
|
|
* or kvm->slots_lock.
|
|
*
|
|
* @kvm: the guest instance we are interested in.
|
|
* @slot: the @gfn belongs to.
|
|
* @gfn: the guest page.
|
|
* @mode: tracking mode, currently only write track is supported.
|
|
*/
|
|
void kvm_slot_page_track_add_page(struct kvm *kvm,
|
|
struct kvm_memory_slot *slot, gfn_t gfn,
|
|
enum kvm_page_track_mode mode)
|
|
{
|
|
|
|
if (WARN_ON(!page_track_mode_is_valid(mode)))
|
|
return;
|
|
|
|
update_gfn_track(slot, gfn, mode, 1);
|
|
|
|
/*
|
|
* new track stops large page mapping for the
|
|
* tracked page.
|
|
*/
|
|
kvm_mmu_gfn_disallow_lpage(slot, gfn);
|
|
|
|
if (mode == KVM_PAGE_TRACK_WRITE)
|
|
if (kvm_mmu_slot_gfn_write_protect(kvm, slot, gfn))
|
|
kvm_flush_remote_tlbs(kvm);
|
|
}
|
|
EXPORT_SYMBOL_GPL(kvm_slot_page_track_add_page);
|
|
|
|
/*
|
|
* remove the guest page from the tracking pool which stops the interception
|
|
* of corresponding access on that page. It is the opposed operation of
|
|
* kvm_slot_page_track_add_page().
|
|
*
|
|
* It should be called under the protection both of mmu-lock and kvm->srcu
|
|
* or kvm->slots_lock.
|
|
*
|
|
* @kvm: the guest instance we are interested in.
|
|
* @slot: the @gfn belongs to.
|
|
* @gfn: the guest page.
|
|
* @mode: tracking mode, currently only write track is supported.
|
|
*/
|
|
void kvm_slot_page_track_remove_page(struct kvm *kvm,
|
|
struct kvm_memory_slot *slot, gfn_t gfn,
|
|
enum kvm_page_track_mode mode)
|
|
{
|
|
if (WARN_ON(!page_track_mode_is_valid(mode)))
|
|
return;
|
|
|
|
update_gfn_track(slot, gfn, mode, -1);
|
|
|
|
/*
|
|
* allow large page mapping for the tracked page
|
|
* after the tracker is gone.
|
|
*/
|
|
kvm_mmu_gfn_allow_lpage(slot, gfn);
|
|
}
|
|
EXPORT_SYMBOL_GPL(kvm_slot_page_track_remove_page);
|
|
|
|
/*
|
|
* check if the corresponding access on the specified guest page is tracked.
|
|
*/
|
|
bool kvm_page_track_is_active(struct kvm_vcpu *vcpu, gfn_t gfn,
|
|
enum kvm_page_track_mode mode)
|
|
{
|
|
struct kvm_memory_slot *slot;
|
|
int index;
|
|
|
|
if (WARN_ON(!page_track_mode_is_valid(mode)))
|
|
return false;
|
|
|
|
slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
|
|
if (!slot)
|
|
return false;
|
|
|
|
index = gfn_to_index(gfn, slot->base_gfn, PT_PAGE_TABLE_LEVEL);
|
|
return !!READ_ONCE(slot->arch.gfn_track[mode][index]);
|
|
}
|
|
|
|
void kvm_page_track_cleanup(struct kvm *kvm)
|
|
{
|
|
struct kvm_page_track_notifier_head *head;
|
|
|
|
head = &kvm->arch.track_notifier_head;
|
|
cleanup_srcu_struct(&head->track_srcu);
|
|
}
|
|
|
|
void kvm_page_track_init(struct kvm *kvm)
|
|
{
|
|
struct kvm_page_track_notifier_head *head;
|
|
|
|
head = &kvm->arch.track_notifier_head;
|
|
init_srcu_struct(&head->track_srcu);
|
|
INIT_HLIST_HEAD(&head->track_notifier_list);
|
|
}
|
|
|
|
/*
|
|
* register the notifier so that event interception for the tracked guest
|
|
* pages can be received.
|
|
*/
|
|
void
|
|
kvm_page_track_register_notifier(struct kvm *kvm,
|
|
struct kvm_page_track_notifier_node *n)
|
|
{
|
|
struct kvm_page_track_notifier_head *head;
|
|
|
|
head = &kvm->arch.track_notifier_head;
|
|
|
|
spin_lock(&kvm->mmu_lock);
|
|
hlist_add_head_rcu(&n->node, &head->track_notifier_list);
|
|
spin_unlock(&kvm->mmu_lock);
|
|
}
|
|
EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier);
|
|
|
|
/*
|
|
* stop receiving the event interception. It is the opposed operation of
|
|
* kvm_page_track_register_notifier().
|
|
*/
|
|
void
|
|
kvm_page_track_unregister_notifier(struct kvm *kvm,
|
|
struct kvm_page_track_notifier_node *n)
|
|
{
|
|
struct kvm_page_track_notifier_head *head;
|
|
|
|
head = &kvm->arch.track_notifier_head;
|
|
|
|
spin_lock(&kvm->mmu_lock);
|
|
hlist_del_rcu(&n->node);
|
|
spin_unlock(&kvm->mmu_lock);
|
|
synchronize_srcu(&head->track_srcu);
|
|
}
|
|
EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier);
|
|
|
|
/*
|
|
* Notify the node that write access is intercepted and write emulation is
|
|
* finished at this time.
|
|
*
|
|
* The node should figure out if the written page is the one that node is
|
|
* interested in by itself.
|
|
*/
|
|
void kvm_page_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new,
|
|
int bytes)
|
|
{
|
|
struct kvm_page_track_notifier_head *head;
|
|
struct kvm_page_track_notifier_node *n;
|
|
int idx;
|
|
|
|
head = &vcpu->kvm->arch.track_notifier_head;
|
|
|
|
if (hlist_empty(&head->track_notifier_list))
|
|
return;
|
|
|
|
idx = srcu_read_lock(&head->track_srcu);
|
|
hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
|
|
if (n->track_write)
|
|
n->track_write(vcpu, gpa, new, bytes, n);
|
|
srcu_read_unlock(&head->track_srcu, idx);
|
|
}
|
|
|
|
/*
|
|
* Notify the node that memory slot is being removed or moved so that it can
|
|
* drop write-protection for the pages in the memory slot.
|
|
*
|
|
* The node should figure out it has any write-protected pages in this slot
|
|
* by itself.
|
|
*/
|
|
void kvm_page_track_flush_slot(struct kvm *kvm, struct kvm_memory_slot *slot)
|
|
{
|
|
struct kvm_page_track_notifier_head *head;
|
|
struct kvm_page_track_notifier_node *n;
|
|
int idx;
|
|
|
|
head = &kvm->arch.track_notifier_head;
|
|
|
|
if (hlist_empty(&head->track_notifier_list))
|
|
return;
|
|
|
|
idx = srcu_read_lock(&head->track_srcu);
|
|
hlist_for_each_entry_rcu(n, &head->track_notifier_list, node)
|
|
if (n->track_flush_slot)
|
|
n->track_flush_slot(kvm, slot, n);
|
|
srcu_read_unlock(&head->track_srcu, idx);
|
|
}
|