| 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: <20071113225049.2776414543E5@imap.suse.de>
Date: Tue, 13 Nov 2007 14:50:37 -0800
From: <gregkh@...e.de>
To: jeremy@...p.org, ak@....de, akpm@...ux-foundation.org,
chrisw@...s-sol.org, gregkh@...e.de, jeremy@...source.com,
keir@...source.com, linux-kernel@...r.kernel.org, stable@...nel.org
Cc: <stable@...nel.org>, <stable-commits@...r.kernel.org>
Subject: patch xen-handle-lazy-cr3-on-unpin.patch queued to -stable tree
This is a note to let you know that we have just queued up the patch titled
Subject: xen: deal with stale cr3 values when unpinning pagetables
to the 2.6.23-stable tree. Its filename is
xen-handle-lazy-cr3-on-unpin.patch
A git repo of this tree can be found at
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
>From stable-bounces@...ux.kernel.org Fri Oct 12 14:33:57 2007
From: Jeremy Fitzhardinge <jeremy@...p.org>
Date: Fri, 12 Oct 2007 14:11:37 -0700
Subject: xen: deal with stale cr3 values when unpinning pagetables
To: LKML <linux-kernel@...r.kernel.org>
Cc: xen-devel@...ts.xensource.com, virtualization@...ts.osdl.org, Chris Wright <chrisw@...s-sol.org>, Andi Kleen <ak@....de>, Andrew Morton <akpm@...ux-foundation.org>, Keir Fraser <keir@...source.com>, Stable Kernel <stable@...nel.org>
Message-ID: <20071012211148.208637000@...p.org>
Content-Disposition: inline; filename=xen-handle-lazy-cr3-on-unpin.patch
From: Jeremy Fitzhardinge <jeremy@...p.org>
patch 9f79991d4186089e228274196413572cc000143b in mainline.
When a pagetable is no longer in use, it must be unpinned so that its
pages can be freed. However, this is only possible if there are no
stray uses of the pagetable. The code currently deals with all the
usual cases, but there's a rare case where a vcpu is changing cr3, but
is doing so lazily, and the change hasn't actually happened by the time
the pagetable is unpinned, even though it appears to have been completed.
This change adds a second per-cpu cr3 variable - xen_current_cr3 -
which tracks the actual state of the vcpu cr3. It is only updated once
the actual hypercall to set cr3 has been completed. Other processors
wishing to unpin a pagetable can check other vcpu's xen_current_cr3
values to see if any cross-cpu IPIs are needed to clean things up.
Signed-off-by: Jeremy Fitzhardinge <jeremy@...source.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...e.de>
---
arch/i386/xen/enlighten.c | 55 +++++++++++++++++++++++++++++++---------------
arch/i386/xen/mmu.c | 29 +++++++++++++++++++++---
arch/i386/xen/xen-ops.h | 1
3 files changed, 65 insertions(+), 20 deletions(-)
--- a/arch/i386/xen/enlighten.c
+++ b/arch/i386/xen/enlighten.c
@@ -56,7 +56,23 @@ DEFINE_PER_CPU(enum paravirt_lazy_mode,
DEFINE_PER_CPU(struct vcpu_info *, xen_vcpu);
DEFINE_PER_CPU(struct vcpu_info, xen_vcpu_info);
-DEFINE_PER_CPU(unsigned long, xen_cr3);
+
+/*
+ * Note about cr3 (pagetable base) values:
+ *
+ * xen_cr3 contains the current logical cr3 value; it contains the
+ * last set cr3. This may not be the current effective cr3, because
+ * its update may be being lazily deferred. However, a vcpu looking
+ * at its own cr3 can use this value knowing that it everything will
+ * be self-consistent.
+ *
+ * xen_current_cr3 contains the actual vcpu cr3; it is set once the
+ * hypercall to set the vcpu cr3 is complete (so it may be a little
+ * out of date, but it will never be set early). If one vcpu is
+ * looking at another vcpu's cr3 value, it should use this variable.
+ */
+DEFINE_PER_CPU(unsigned long, xen_cr3); /* cr3 stored as physaddr */
+DEFINE_PER_CPU(unsigned long, xen_current_cr3); /* actual vcpu cr3 */
struct start_info *xen_start_info;
EXPORT_SYMBOL_GPL(xen_start_info);
@@ -632,32 +648,36 @@ static unsigned long xen_read_cr3(void)
return x86_read_percpu(xen_cr3);
}
+static void set_current_cr3(void *v)
+{
+ x86_write_percpu(xen_current_cr3, (unsigned long)v);
+}
+
static void xen_write_cr3(unsigned long cr3)
{
+ struct mmuext_op *op;
+ struct multicall_space mcs;
+ unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
+
BUG_ON(preemptible());
- if (cr3 == x86_read_percpu(xen_cr3)) {
- /* just a simple tlb flush */
- xen_flush_tlb();
- return;
- }
+ mcs = xen_mc_entry(sizeof(*op)); /* disables interrupts */
+ /* Update while interrupts are disabled, so its atomic with
+ respect to ipis */
x86_write_percpu(xen_cr3, cr3);
+ op = mcs.args;
+ op->cmd = MMUEXT_NEW_BASEPTR;
+ op->arg1.mfn = mfn;
- {
- struct mmuext_op *op;
- struct multicall_space mcs = xen_mc_entry(sizeof(*op));
- unsigned long mfn = pfn_to_mfn(PFN_DOWN(cr3));
-
- op = mcs.args;
- op->cmd = MMUEXT_NEW_BASEPTR;
- op->arg1.mfn = mfn;
+ MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
- MULTI_mmuext_op(mcs.mc, op, 1, NULL, DOMID_SELF);
+ /* Update xen_update_cr3 once the batch has actually
+ been submitted. */
+ xen_mc_callback(set_current_cr3, (void *)cr3);
- xen_mc_issue(PARAVIRT_LAZY_CPU);
- }
+ xen_mc_issue(PARAVIRT_LAZY_CPU); /* interrupts restored */
}
/* Early in boot, while setting up the initial pagetable, assume
@@ -1113,6 +1133,7 @@ asmlinkage void __init xen_start_kernel(
/* keep using Xen gdt for now; no urgent need to change it */
x86_write_percpu(xen_cr3, __pa(pgd));
+ x86_write_percpu(xen_current_cr3, __pa(pgd));
#ifdef CONFIG_SMP
/* Don't do the full vcpu_info placement stuff until we have a
--- a/arch/i386/xen/mmu.c
+++ b/arch/i386/xen/mmu.c
@@ -515,20 +515,43 @@ static void drop_other_mm_ref(void *info
if (__get_cpu_var(cpu_tlbstate).active_mm == mm)
leave_mm(smp_processor_id());
+
+ /* If this cpu still has a stale cr3 reference, then make sure
+ it has been flushed. */
+ if (x86_read_percpu(xen_current_cr3) == __pa(mm->pgd)) {
+ load_cr3(swapper_pg_dir);
+ arch_flush_lazy_cpu_mode();
+ }
}
static void drop_mm_ref(struct mm_struct *mm)
{
+ cpumask_t mask;
+ unsigned cpu;
+
if (current->active_mm == mm) {
if (current->mm == mm)
load_cr3(swapper_pg_dir);
else
leave_mm(smp_processor_id());
+ arch_flush_lazy_cpu_mode();
+ }
+
+ /* Get the "official" set of cpus referring to our pagetable. */
+ mask = mm->cpu_vm_mask;
+
+ /* It's possible that a vcpu may have a stale reference to our
+ cr3, because its in lazy mode, and it hasn't yet flushed
+ its set of pending hypercalls yet. In this case, we can
+ look at its actual current cr3 value, and force it to flush
+ if needed. */
+ for_each_online_cpu(cpu) {
+ if (per_cpu(xen_current_cr3, cpu) == __pa(mm->pgd))
+ cpu_set(cpu, mask);
}
- if (!cpus_empty(mm->cpu_vm_mask))
- xen_smp_call_function_mask(mm->cpu_vm_mask, drop_other_mm_ref,
- mm, 1);
+ if (!cpus_empty(mask))
+ xen_smp_call_function_mask(mask, drop_other_mm_ref, mm, 1);
}
#else
static void drop_mm_ref(struct mm_struct *mm)
--- a/arch/i386/xen/xen-ops.h
+++ b/arch/i386/xen/xen-ops.h
@@ -11,6 +11,7 @@ void xen_copy_trap_info(struct trap_info
DECLARE_PER_CPU(struct vcpu_info *, xen_vcpu);
DECLARE_PER_CPU(unsigned long, xen_cr3);
+DECLARE_PER_CPU(unsigned long, xen_current_cr3);
extern struct start_info *xen_start_info;
extern struct shared_info *HYPERVISOR_shared_info;
Patches currently in stable-queue which might be from jeremy@...p.org are
queue-2.6.23/xen-handle-lazy-cr3-on-unpin.patch
queue-2.6.23/xen-multicall-callbacks.patch
queue-2.6.23/xen-fix-register_vcpu_info.patch
queue-2.6.23/xen-xfs-unmap.patch
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists