| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210728142631.41860-10-imbrenda@linux.ibm.com>
Date: Wed, 28 Jul 2021 16:26:27 +0200
From: Claudio Imbrenda <imbrenda@...ux.ibm.com>
To: kvm@...r.kernel.org
Cc: cohuck@...hat.com, borntraeger@...ibm.com, frankja@...ux.ibm.com,
thuth@...hat.com, pasic@...ux.ibm.com, david@...hat.com,
linux-s390@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH v2 09/13] KVM: s390: pv: lazy destroy for reboot
Until now, destroying a protected guest was an entirely synchronous
operation that could potentially take a very long time, depending on
the size of the guest, due to the time needed to clean up the address
space from protected pages.
This patch implements a lazy destroy mechanism, that allows a protected
guest to reboot significantly faster than previously.
This is achieved by clearing the pages of the old guest in background.
In case of reboot, the new guest will be able to run in the same
address space almost immediately.
The old protected guest is then only destroyed when all of its memory has
been destroyed or otherwise made non protected.
Signed-off-by: Claudio Imbrenda <imbrenda@...ux.ibm.com>
---
arch/s390/kvm/kvm-s390.c | 6 +-
arch/s390/kvm/kvm-s390.h | 2 +-
arch/s390/kvm/pv.c | 129 ++++++++++++++++++++++++++++++++++++++-
3 files changed, 131 insertions(+), 6 deletions(-)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index b655a7d82bf0..238297a7bb46 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2281,7 +2281,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
r = kvm_s390_cpus_to_pv(kvm, &cmd->rc, &cmd->rrc);
if (r)
- kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy);
+ kvm_s390_pv_deinit_vm_deferred(kvm, &dummy, &dummy);
/* we need to block service interrupts from now on */
set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
@@ -2300,7 +2300,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
*/
if (r)
break;
- r = kvm_s390_pv_deinit_vm(kvm, &cmd->rc, &cmd->rrc);
+ r = kvm_s390_pv_deinit_vm_deferred(kvm, &cmd->rc, &cmd->rrc);
/* no need to block service interrupts any more */
clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
@@ -2829,7 +2829,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
* complaining we do not use kvm_s390_pv_is_protected.
*/
if (kvm_s390_pv_get_handle(kvm))
- kvm_s390_pv_deinit_vm(kvm, &rc, &rrc);
+ kvm_s390_pv_deinit_vm_deferred(kvm, &rc, &rrc);
debug_unregister(kvm->arch.dbf);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 9fad25109b0d..d2380f5e7e1f 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -211,7 +211,7 @@ static inline int kvm_s390_user_cpu_state_ctrl(struct kvm *kvm)
/* implemented in pv.c */
int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
int kvm_s390_pv_create_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc);
-int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc);
+int kvm_s390_pv_deinit_vm_deferred(struct kvm *kvm, u16 *rc, u16 *rrc);
int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc);
int kvm_s390_pv_set_sec_parms(struct kvm *kvm, void *hdr, u64 length, u16 *rc,
u16 *rrc);
diff --git a/arch/s390/kvm/pv.c b/arch/s390/kvm/pv.c
index 52e7d15a6dc7..8c37850dbbcf 100644
--- a/arch/s390/kvm/pv.c
+++ b/arch/s390/kvm/pv.c
@@ -14,8 +14,17 @@
#include <asm/mman.h>
#include <linux/pagewalk.h>
#include <linux/sched/mm.h>
+#include <linux/kthread.h>
#include "kvm-s390.h"
+struct deferred_priv {
+ struct mm_struct *mm;
+ unsigned long old_table;
+ u64 handle;
+ void *stor_var;
+ unsigned long stor_base;
+};
+
int kvm_s390_pv_destroy_cpu(struct kvm_vcpu *vcpu, u16 *rc, u16 *rrc)
{
int cc = 0;
@@ -207,7 +216,7 @@ static int kvm_s390_pv_replace_asce(struct kvm *kvm)
}
/* this should not fail, but if it does, we must not free the donated memory */
-int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
+static int kvm_s390_pv_deinit_vm_now(struct kvm *kvm, u16 *rc, u16 *rrc)
{
int cc;
@@ -235,6 +244,122 @@ int kvm_s390_pv_deinit_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
return cc ? -EIO : 0;
}
+static int kvm_s390_pv_destroy_vm_thread(void *priv)
+{
+ struct deferred_priv *p = priv;
+ u16 rc, rrc;
+ int r;
+
+ /* Clear all the pages as long as we are not the only users of the mm */
+ s390_uv_destroy_range(p->mm, 1, 0, TASK_SIZE_MAX);
+ /*
+ * If we were the last user of the mm, synchronously free (and clear
+ * if needed) all pages.
+ * Otherwise simply decrease the reference counter; in this case we
+ * have already cleared all pages.
+ */
+ mmput(p->mm);
+
+ r = uv_cmd_nodata(p->handle, UVC_CMD_DESTROY_SEC_CONF, &rc, &rrc);
+ WARN_ONCE(r, "protvirt destroy vm failed rc %x rrc %x", rc, rrc);
+ if (r) {
+ mmdrop(p->mm);
+ return r;
+ }
+ atomic_dec(&p->mm->context.is_protected);
+ mmdrop(p->mm);
+
+ /*
+ * Intentional leak in case the destroy secure VM call fails. The
+ * call should never fail if the hardware is not broken.
+ */
+ free_pages(p->stor_base, get_order(uv_info.guest_base_stor_len));
+ free_pages(p->old_table, CRST_ALLOC_ORDER);
+ vfree(p->stor_var);
+ kfree(p);
+ return 0;
+}
+
+static int deferred_destroy(struct kvm *kvm, struct deferred_priv *priv, u16 *rc, u16 *rrc)
+{
+ struct task_struct *t;
+
+ priv->stor_var = kvm->arch.pv.stor_var;
+ priv->stor_base = kvm->arch.pv.stor_base;
+ priv->handle = kvm_s390_pv_get_handle(kvm);
+ priv->old_table = (unsigned long)kvm->arch.gmap->table;
+ WRITE_ONCE(kvm->arch.gmap->guest_handle, 0);
+
+ if (kvm_s390_pv_replace_asce(kvm))
+ goto fail;
+
+ t = kthread_create(kvm_s390_pv_destroy_vm_thread, priv,
+ "kvm_s390_pv_destroy_vm_thread");
+ if (IS_ERR_OR_NULL(t))
+ goto fail;
+
+ memset(&kvm->arch.pv, 0, sizeof(kvm->arch.pv));
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT DESTROY VM DEFERRED %d", t->pid);
+ wake_up_process(t);
+ /*
+ * no actual UVC is performed at this point, just return a successful
+ * rc value to make userspace happy, and an arbitrary rrc
+ */
+ *rc = 1;
+ *rrc = 42;
+
+ return 0;
+
+fail:
+ kfree(priv);
+ return kvm_s390_pv_deinit_vm_now(kvm, rc, rrc);
+}
+
+/* Clear the first 2GB of guest memory, to avoid prefix issues after reboot */
+static void kvm_s390_clear_2g(struct kvm *kvm)
+{
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ unsigned long lim;
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(slot, slots) {
+ if (slot->base_gfn >= (SZ_2G / PAGE_SIZE))
+ continue;
+ if (slot->base_gfn + slot->npages > (SZ_2G / PAGE_SIZE))
+ lim = slot->userspace_addr + SZ_2G - slot->base_gfn * PAGE_SIZE;
+ else
+ lim = slot->userspace_addr + slot->npages * PAGE_SIZE;
+ s390_uv_destroy_range(kvm->mm, 1, slot->userspace_addr, lim);
+ }
+
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
+int kvm_s390_pv_deinit_vm_deferred(struct kvm *kvm, u16 *rc, u16 *rrc)
+{
+ struct deferred_priv *priv;
+
+ priv = kmalloc(sizeof(*priv), GFP_KERNEL | __GFP_ZERO);
+ if (!priv)
+ return kvm_s390_pv_deinit_vm_now(kvm, rc, rrc);
+
+ mmgrab(kvm->mm);
+ if (mmget_not_zero(kvm->mm)) {
+ kvm_s390_clear_2g(kvm);
+ } else {
+ /* No deferred work to do */
+ mmdrop(kvm->mm);
+ kfree(priv);
+ return kvm_s390_pv_deinit_vm_now(kvm, rc, rrc);
+ }
+ priv->mm = kvm->mm;
+ return deferred_destroy(kvm, priv, rc, rrc);
+}
+
int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct uv_cb_cgc uvcb = {
@@ -268,7 +393,7 @@ int kvm_s390_pv_init_vm(struct kvm *kvm, u16 *rc, u16 *rrc)
atomic_inc(&kvm->mm->context.is_protected);
if (cc) {
if (uvcb.header.rc & UVC_RC_NEED_DESTROY) {
- kvm_s390_pv_deinit_vm(kvm, &dummy, &dummy);
+ kvm_s390_pv_deinit_vm_now(kvm, &dummy, &dummy);
} else {
atomic_dec(&kvm->mm->context.is_protected);
kvm_s390_pv_dealloc_vm(kvm);
--
2.31.1
Powered by blists - more mailing lists