| 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: <20230526234435.662652-2-yuzhao@google.com>
Date: Fri, 26 May 2023 17:44:26 -0600
From: Yu Zhao <yuzhao@...gle.com>
To: Andrew Morton <akpm@...ux-foundation.org>,
Paolo Bonzini <pbonzini@...hat.com>
Cc: Alistair Popple <apopple@...dia.com>,
Anup Patel <anup@...infault.org>,
Ben Gardon <bgardon@...gle.com>,
Borislav Petkov <bp@...en8.de>,
Catalin Marinas <catalin.marinas@....com>,
Chao Peng <chao.p.peng@...ux.intel.com>,
Christophe Leroy <christophe.leroy@...roup.eu>,
Dave Hansen <dave.hansen@...ux.intel.com>,
Fabiano Rosas <farosas@...ux.ibm.com>,
Gaosheng Cui <cuigaosheng1@...wei.com>,
Gavin Shan <gshan@...hat.com>,
"H. Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...hat.com>,
James Morse <james.morse@....com>,
"Jason A. Donenfeld" <Jason@...c4.com>,
Jason Gunthorpe <jgg@...pe.ca>,
Jonathan Corbet <corbet@....net>,
Marc Zyngier <maz@...nel.org>,
Masami Hiramatsu <mhiramat@...nel.org>,
Michael Ellerman <mpe@...erman.id.au>,
Michael Larabel <michael@...haellarabel.com>,
Mike Rapoport <rppt@...nel.org>,
Nicholas Piggin <npiggin@...il.com>,
Oliver Upton <oliver.upton@...ux.dev>,
Paul Mackerras <paulus@...abs.org>,
Peter Xu <peterx@...hat.com>,
Sean Christopherson <seanjc@...gle.com>,
Steven Rostedt <rostedt@...dmis.org>,
Suzuki K Poulose <suzuki.poulose@....com>,
Thomas Gleixner <tglx@...utronix.de>,
Thomas Huth <thuth@...hat.com>, Will Deacon <will@...nel.org>,
Zenghui Yu <yuzenghui@...wei.com>, kvmarm@...ts.linux.dev,
kvm@...r.kernel.org, linux-arm-kernel@...ts.infradead.org,
linux-doc@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, linuxppc-dev@...ts.ozlabs.org,
linux-trace-kernel@...r.kernel.org, x86@...nel.org,
linux-mm@...gle.com, Yu Zhao <yuzhao@...gle.com>
Subject: [PATCH mm-unstable v2 01/10] mm/kvm: add mmu_notifier_ops->test_clear_young()
Add mmu_notifier_ops->test_clear_young() to supersede test_young()
and clear_young().
test_clear_young() has a fast path, which if supported, allows its
callers to safely clear the accessed bit without taking
kvm->mmu_lock.
The fast path requires arch-specific code that generally relies on
RCU and CAS: the former protects KVM page tables from being freed
while the latter clears the accessed bit atomically against both the
hardware and other software page table walkers. If the fast path is
unsupported, test_clear_young() falls back to the existing slow path
where kvm->mmu_lock is then taken.
test_clear_young() can also operate on a range of KVM PTEs
individually according to a bitmap, if the caller provides it.
Signed-off-by: Yu Zhao <yuzhao@...gle.com>
---
include/linux/kvm_host.h | 22 +++++++++++
include/linux/mmu_notifier.h | 52 ++++++++++++++++++++++++
mm/mmu_notifier.c | 24 ++++++++++++
virt/kvm/kvm_main.c | 76 +++++++++++++++++++++++++++++++++++-
4 files changed, 173 insertions(+), 1 deletion(-)
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0e571e973bc2..374262545f96 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -258,6 +258,7 @@ int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
struct kvm_gfn_range {
struct kvm_memory_slot *slot;
+ void *args;
gfn_t start;
gfn_t end;
pte_t pte;
@@ -267,6 +268,27 @@ bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
+bool kvm_should_clear_young(struct kvm_gfn_range *range, gfn_t gfn);
+bool kvm_arch_test_clear_young(struct kvm *kvm, struct kvm_gfn_range *range);
+#endif
+
+/*
+ * Architectures that implement kvm_arch_test_clear_young() should override
+ * kvm_arch_has_test_clear_young().
+ *
+ * kvm_arch_has_test_clear_young() is allowed to return false positive, i.e., it
+ * can return true if kvm_arch_test_clear_young() is supported but disabled due
+ * to some runtime constraint. In this case, kvm_arch_test_clear_young() should
+ * return true; otherwise, it should return false.
+ *
+ * For each young KVM PTE, kvm_arch_test_clear_young() should call
+ * kvm_should_clear_young() to decide whether to clear the accessed bit.
+ */
+#ifndef kvm_arch_has_test_clear_young
+static inline bool kvm_arch_has_test_clear_young(void)
+{
+ return false;
+}
#endif
enum {
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 64a3e051c3c4..dfdbb370682d 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -60,6 +60,8 @@ enum mmu_notifier_event {
};
#define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
+#define MMU_NOTIFIER_RANGE_LOCKLESS (1 << 1)
+#define MMU_NOTIFIER_RANGE_YOUNG (1 << 2)
struct mmu_notifier_ops {
/*
@@ -122,6 +124,10 @@ struct mmu_notifier_ops {
struct mm_struct *mm,
unsigned long address);
+ int (*test_clear_young)(struct mmu_notifier *mn, struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool clear, unsigned long *bitmap);
+
/*
* change_pte is called in cases that pte mapping to page is changed:
* for example, when ksm remaps pte to point to a new shared page.
@@ -392,6 +398,9 @@ extern int __mmu_notifier_clear_young(struct mm_struct *mm,
unsigned long end);
extern int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address);
+extern int __mmu_notifier_test_clear_young(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool clear, unsigned long *bitmap);
extern void __mmu_notifier_change_pte(struct mm_struct *mm,
unsigned long address, pte_t pte);
extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r);
@@ -440,6 +449,35 @@ static inline int mmu_notifier_test_young(struct mm_struct *mm,
return 0;
}
+/*
+ * mmu_notifier_test_clear_young() returns nonzero if any of the KVM PTEs within
+ * a given range was young. Specifically, it returns MMU_NOTIFIER_RANGE_LOCKLESS
+ * if the fast path was successful, MMU_NOTIFIER_RANGE_YOUNG otherwise.
+ *
+ * The last parameter to the function is a bitmap and only the fast path
+ * supports it: if it is NULL, the function falls back to the slow path if the
+ * fast path was unsuccessful; otherwise, the function bails out.
+ *
+ * The bitmap has the following specifications:
+ * 1. The number of bits should be at least (end-start)/PAGE_SIZE.
+ * 2. The offset of each bit should be relative to the end, i.e., the offset
+ * corresponding to addr should be (end-addr)/PAGE_SIZE-1. This is convenient
+ * for batching while forward looping.
+ *
+ * When testing, this function sets the corresponding bit in the bitmap for each
+ * young KVM PTE. When clearing, this function clears the accessed bit for each
+ * young KVM PTE whose corresponding bit in the bitmap is set.
+ */
+static inline int mmu_notifier_test_clear_young(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool clear, unsigned long *bitmap)
+{
+ if (mm_has_notifiers(mm))
+ return __mmu_notifier_test_clear_young(mm, start, end, clear, bitmap);
+
+ return 0;
+}
+
static inline void mmu_notifier_change_pte(struct mm_struct *mm,
unsigned long address, pte_t pte)
{
@@ -684,12 +722,26 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
return 0;
}
+static inline int mmu_notifier_clear_young(struct mm_struct *mm,
+ unsigned long start,
+ unsigned long end)
+{
+ return 0;
+}
+
static inline int mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address)
{
return 0;
}
+static inline int mmu_notifier_test_clear_young(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool clear, unsigned long *bitmap)
+{
+ return 0;
+}
+
static inline void mmu_notifier_change_pte(struct mm_struct *mm,
unsigned long address, pte_t pte)
{
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 50c0dde1354f..7e6aba4bddcb 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -424,6 +424,30 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
return young;
}
+int __mmu_notifier_test_clear_young(struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool clear, unsigned long *bitmap)
+{
+ int idx;
+ struct mmu_notifier *mn;
+ int young = 0;
+
+ idx = srcu_read_lock(&srcu);
+
+ hlist_for_each_entry_srcu(mn, &mm->notifier_subscriptions->list, hlist,
+ srcu_read_lock_held(&srcu)) {
+ if (mn->ops->test_clear_young)
+ young |= mn->ops->test_clear_young(mn, mm, start, end, clear, bitmap);
+
+ if (young && !clear)
+ break;
+ }
+
+ srcu_read_unlock(&srcu, idx);
+
+ return young;
+}
+
void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
pte_t pte)
{
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 51e4882d0873..31ee58754b19 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -541,6 +541,7 @@ typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
typedef void (*on_unlock_fn_t)(struct kvm *kvm);
struct kvm_hva_range {
+ void *args;
unsigned long start;
unsigned long end;
pte_t pte;
@@ -549,6 +550,7 @@ struct kvm_hva_range {
on_unlock_fn_t on_unlock;
bool flush_on_ret;
bool may_block;
+ bool lockless;
};
/*
@@ -602,6 +604,8 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
hva_end = min(range->end, slot->userspace_addr +
(slot->npages << PAGE_SHIFT));
+ gfn_range.args = range->args;
+
/*
* To optimize for the likely case where the address
* range is covered by zero or one memslots, don't
@@ -619,7 +623,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
gfn_range.slot = slot;
- if (!locked) {
+ if (!range->lockless && !locked) {
locked = true;
KVM_MMU_LOCK(kvm);
if (!IS_KVM_NULL_FN(range->on_lock))
@@ -628,6 +632,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
break;
}
ret |= range->handler(kvm, &gfn_range);
+
+ if (range->lockless && ret)
+ break;
}
}
@@ -880,6 +887,72 @@ static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
kvm_test_age_gfn);
}
+struct test_clear_young_args {
+ unsigned long *bitmap;
+ unsigned long end;
+ bool clear;
+ bool young;
+};
+
+bool kvm_should_clear_young(struct kvm_gfn_range *range, gfn_t gfn)
+{
+ struct test_clear_young_args *args = range->args;
+
+ VM_WARN_ON_ONCE(gfn < range->start || gfn >= range->end);
+
+ args->young = true;
+
+ if (args->bitmap) {
+ int offset = hva_to_gfn_memslot(args->end - 1, range->slot) - gfn;
+
+ if (args->clear)
+ return test_bit(offset, args->bitmap);
+
+ __set_bit(offset, args->bitmap);
+ }
+
+ return args->clear;
+}
+
+static int kvm_mmu_notifier_test_clear_young(struct mmu_notifier *mn, struct mm_struct *mm,
+ unsigned long start, unsigned long end,
+ bool clear, unsigned long *bitmap)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ struct kvm_hva_range range = {
+ .start = start,
+ .end = end,
+ .on_lock = (void *)kvm_null_fn,
+ .on_unlock = (void *)kvm_null_fn,
+ };
+
+ trace_kvm_age_hva(start, end);
+
+ if (kvm_arch_has_test_clear_young()) {
+ struct test_clear_young_args args = {
+ .bitmap = bitmap,
+ .end = end,
+ .clear = clear,
+ };
+
+ range.args = &args;
+ range.lockless = true;
+ range.handler = kvm_arch_test_clear_young;
+
+ if (!__kvm_handle_hva_range(kvm, &range))
+ return args.young ? MMU_NOTIFIER_RANGE_LOCKLESS : 0;
+ }
+
+ if (bitmap)
+ return 0;
+
+ range.args = NULL;
+ range.lockless = false;
+ range.handler = clear ? kvm_age_gfn : kvm_test_age_gfn;
+
+ return __kvm_handle_hva_range(kvm, &range) ? MMU_NOTIFIER_RANGE_YOUNG : 0;
+}
+
static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
@@ -898,6 +971,7 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
.clear_young = kvm_mmu_notifier_clear_young,
.test_young = kvm_mmu_notifier_test_young,
+ .test_clear_young = kvm_mmu_notifier_test_clear_young,
.change_pte = kvm_mmu_notifier_change_pte,
.release = kvm_mmu_notifier_release,
};
--
2.41.0.rc0.172.g3f132b7071-goog
Powered by blists - more mailing lists