From: Chao Peng <chao.p.peng@linux.intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-fsdevel@vger.kernel.org,
linux-api@vger.kernel.org, linux-doc@vger.kernel.org,
qemu-devel@nongnu.org
Cc: Paolo Bonzini <pbonzini@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
Sean Christopherson <seanjc@google.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
Wanpeng Li <wanpengli@tencent.com>,
Jim Mattson <jmattson@google.com>, Joerg Roedel <joro@8bytes.org>,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
Hugh Dickins <hughd@google.com>, Jeff Layton <jlayton@kernel.org>,
"J . Bruce Fields" <bfields@fieldses.org>,
Andrew Morton <akpm@linux-foundation.org>,
Shuah Khan <shuah@kernel.org>, Mike Rapoport <rppt@kernel.org>,
Steven Price <steven.price@arm.com>,
"Maciej S . Szmigiero" <mail@maciej.szmigiero.name>,
Vlastimil Babka <vbabka@suse.cz>,
Vishal Annapurve <vannapurve@google.com>,
Yu Zhang <yu.c.zhang@linux.intel.com>,
Chao Peng <chao.p.peng@linux.intel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
luto@kernel.org, jun.nakajima@intel.com, dave.hansen@intel.com,
ak@linux.intel.com, david@redhat.com, aarcange@redhat.com,
ddutile@redhat.com, dhildenb@redhat.com,
Quentin Perret <qperret@google.com>,
Michael Roth <michael.roth@amd.com>,
mhocko@suse.com, Muchun Song <songmuchun@bytedance.com>,
wei.w.wang@intel.com
Subject: [PATCH v8 6/8] KVM: Update lpage info when private/shared memory are mixed
Date: Thu, 15 Sep 2022 22:29:11 +0800 [thread overview]
Message-ID: <20220915142913.2213336-7-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20220915142913.2213336-1-chao.p.peng@linux.intel.com>
When private/shared memory are mixed in a large page, the lpage_info may
not be accurate and should be updated with this mixed info. A large page
has mixed pages can't be really mapped as large page since its
private/shared pages are from different physical memory.
This patch updates lpage_info when private/shared memory attribute is
changed. If both private and shared pages are within a large page
region, it can't be mapped as large page. It's a bit challenge to track
the mixed info in a 'count' like variable, this patch instead reserves a
bit in disallow_lpage to indicate a large page include mixed
private/share pages.
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
arch/x86/include/asm/kvm_host.h | 8 +++
arch/x86/kvm/mmu/mmu.c | 119 +++++++++++++++++++++++++++++++-
arch/x86/kvm/x86.c | 2 +
include/linux/kvm_host.h | 17 +++++
virt/kvm/kvm_main.c | 11 ++-
5 files changed, 154 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index cfad6ba1a70a..85119ed9527a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -38,6 +38,7 @@
#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
#define __KVM_HAVE_ZAP_GFN_RANGE
+#define __KVM_HAVE_ARCH_UPDATE_MEM_ATTR
#define KVM_MAX_VCPUS 1024
@@ -945,6 +946,13 @@ struct kvm_vcpu_arch {
#endif
};
+/*
+ * Use a bit in disallow_lpage to indicate private/shared pages mixed at the
+ * level. The remaining bits will be used as a reference count for other users.
+ */
+#define KVM_LPAGE_PRIVATE_SHARED_MIXED (1U << 31)
+#define KVM_LPAGE_COUNT_MAX ((1U << 31) - 1)
+
struct kvm_lpage_info {
int disallow_lpage;
};
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 08abad4f3e6f..a0f198cede3d 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -762,11 +762,16 @@ static void update_gfn_disallow_lpage_count(const struct kvm_memory_slot *slot,
{
struct kvm_lpage_info *linfo;
int i;
+ int disallow_count;
for (i = PG_LEVEL_2M; i <= KVM_MAX_HUGEPAGE_LEVEL; ++i) {
linfo = lpage_info_slot(gfn, slot, i);
+
+ disallow_count = linfo->disallow_lpage & KVM_LPAGE_COUNT_MAX;
+ WARN_ON(disallow_count + count < 0 ||
+ disallow_count > KVM_LPAGE_COUNT_MAX - count);
+
linfo->disallow_lpage += count;
- WARN_ON(linfo->disallow_lpage < 0);
}
}
@@ -6894,3 +6899,115 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
if (kvm->arch.nx_lpage_recovery_thread)
kthread_stop(kvm->arch.nx_lpage_recovery_thread);
}
+
+static bool mem_attr_is_mixed(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+ XA_STATE(xas, &kvm->mem_attr_array, start);
+ gfn_t gfn = start;
+ void *entry;
+ bool shared, private;
+ bool mixed = false;
+
+ if (attr == KVM_MEM_ATTR_SHARED) {
+ shared = true;
+ private = false;
+ } else {
+ shared = false;
+ private = true;
+ }
+
+ rcu_read_lock();
+ entry = xas_load(&xas);
+ while (gfn < end) {
+ if (xas_retry(&xas, entry))
+ continue;
+
+ KVM_BUG_ON(gfn != xas.xa_index, kvm);
+
+ if (entry)
+ private = true;
+ else
+ shared = true;
+
+ if (private && shared) {
+ mixed = true;
+ goto out;
+ }
+
+ entry = xas_next(&xas);
+ gfn++;
+ }
+out:
+ rcu_read_unlock();
+ return mixed;
+}
+
+static inline void update_mixed(struct kvm_lpage_info *linfo, bool mixed)
+{
+ if (mixed)
+ linfo->disallow_lpage |= KVM_LPAGE_PRIVATE_SHARED_MIXED;
+ else
+ linfo->disallow_lpage &= ~KVM_LPAGE_PRIVATE_SHARED_MIXED;
+}
+
+static void update_mem_lpage_info(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+ unsigned long lpage_start, lpage_end;
+ unsigned long gfn, pages, mask;
+ int level;
+
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ pages = KVM_PAGES_PER_HPAGE(level);
+ mask = ~(pages - 1);
+ lpage_start = start & mask;
+ lpage_end = (end - 1) & mask;
+
+ /*
+ * We only need to scan the head and tail page, for middle pages
+ * we know they are not mixed.
+ */
+ update_mixed(lpage_info_slot(lpage_start, slot, level),
+ mem_attr_is_mixed(kvm, attr, lpage_start,
+ lpage_start + pages));
+
+ if (lpage_start == lpage_end)
+ return;
+
+ for (gfn = lpage_start + pages; gfn < lpage_end; gfn += pages)
+ update_mixed(lpage_info_slot(gfn, slot, level), false);
+
+ update_mixed(lpage_info_slot(lpage_end, slot, level),
+ mem_attr_is_mixed(kvm, attr, lpage_end,
+ lpage_end + pages));
+ }
+}
+
+void kvm_arch_update_mem_attr(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+ struct kvm_memory_slot *slot;
+ struct kvm_memslots *slots;
+ struct kvm_memslot_iter iter;
+ int i;
+
+ WARN_ONCE(!(attr & (KVM_MEM_ATTR_PRIVATE | KVM_MEM_ATTR_SHARED)),
+ "Unsupported mem attribute.\n");
+
+ for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+ slots = __kvm_memslots(kvm, i);
+
+ kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) {
+ slot = iter.slot;
+ start = max(start, slot->base_gfn);
+ end = min(end, slot->base_gfn + slot->npages);
+ if (WARN_ON_ONCE(start >= end))
+ continue;
+
+ update_mem_lpage_info(kvm, slot, attr, start, end);
+ }
+ }
+}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 081f62ccc9a1..ef11cda6f13f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12321,6 +12321,8 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm,
if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
linfo[lpages - 1].disallow_lpage = 1;
ugfn = slot->userspace_addr >> PAGE_SHIFT;
+ if (kvm_slot_can_be_private(slot))
+ ugfn |= slot->private_offset >> PAGE_SHIFT;
/*
* If the gfn and userspace address are not aligned wrt each
* other, disable large page support for this slot.
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index d65690cae80b..fd36ce6597ad 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2277,4 +2277,21 @@ static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
/* Max number of entries allowed for each kvm dirty ring */
#define KVM_DIRTY_RING_MAX_ENTRIES 65536
+#ifdef CONFIG_HAVE_KVM_PRIVATE_MEM
+
+#define KVM_MEM_ATTR_SHARED 0x0001
+#define KVM_MEM_ATTR_PRIVATE 0x0002
+
+#ifdef __KVM_HAVE_ARCH_UPDATE_MEM_ATTR
+void kvm_arch_update_mem_attr(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end);
+#else
+static inline void kvm_arch_update_mem_attr(struct kvm *kvm, unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+}
+#endif
+
+#endif /* CONFIG_HAVE_KVM_PRIVATE_MEM */
+
#endif
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index de5cce8c82c7..97d893f7482c 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -938,13 +938,13 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
#endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */
#ifdef CONFIG_HAVE_KVM_PRIVATE_MEM
-#define KVM_MEM_ATTR_SHARED 0x0001
static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
bool is_private)
{
gfn_t start, end;
unsigned long index;
void *entry;
+ int attr;
int r;
if (size == 0 || gpa + size < gpa)
@@ -959,7 +959,13 @@ static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
* Guest memory defaults to private, kvm->mem_attr_array only stores
* shared memory.
*/
- entry = is_private ? NULL : xa_mk_value(KVM_MEM_ATTR_SHARED);
+ if (is_private) {
+ attr = KVM_MEM_ATTR_PRIVATE;
+ entry = NULL;
+ } else {
+ attr = KVM_MEM_ATTR_SHARED;
+ entry = xa_mk_value(KVM_MEM_ATTR_SHARED);
+ }
for (index = start; index < end; index++) {
r = xa_err(xa_store(&kvm->mem_attr_array, index, entry,
@@ -969,6 +975,7 @@ static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
}
kvm_zap_gfn_range(kvm, start, end);
+ kvm_arch_update_mem_attr(kvm, attr, start, end);
return r;
err:
--
2.25.1
next prev parent reply other threads:[~2022-09-15 14:36 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-15 14:29 [PATCH v8 0/8] KVM: mm: fd-based approach for supporting KVM Chao Peng
2022-09-15 14:29 ` [PATCH v8 1/8] mm/memfd: Introduce userspace inaccessible memfd Chao Peng
2022-09-19 9:12 ` David Hildenbrand
2022-09-19 19:10 ` Sean Christopherson
2022-09-21 21:10 ` Andy Lutomirski
2022-09-22 13:23 ` Wang, Wei W
2022-09-23 15:20 ` Fuad Tabba
2022-09-23 15:19 ` Fuad Tabba
2022-09-26 14:23 ` Chao Peng
2022-09-26 15:51 ` Fuad Tabba
2022-09-27 22:47 ` Sean Christopherson
2022-09-30 16:19 ` Fuad Tabba
2022-10-13 13:34 ` Chao Peng
2022-10-17 10:31 ` Fuad Tabba
2022-10-17 14:58 ` Chao Peng
2022-10-17 19:05 ` Fuad Tabba
2022-10-19 13:30 ` Chao Peng
2022-10-18 0:33 ` Sean Christopherson
2022-10-19 15:04 ` Fuad Tabba
2022-09-23 0:58 ` Kirill A . Shutemov
2022-09-26 10:35 ` David Hildenbrand
2022-09-26 14:48 ` Kirill A. Shutemov
2022-09-26 14:53 ` David Hildenbrand
2022-09-27 23:23 ` Sean Christopherson
2022-09-28 13:36 ` Kirill A. Shutemov
2022-09-22 13:26 ` Wang, Wei W
2022-09-22 19:49 ` Sean Christopherson
2022-09-23 0:53 ` Kirill A . Shutemov
2022-09-23 15:20 ` Fuad Tabba
2022-09-30 16:14 ` Fuad Tabba
2022-09-30 16:23 ` Kirill A . Shutemov
2022-10-03 7:33 ` Fuad Tabba
2022-10-03 11:01 ` Kirill A. Shutemov
2022-10-04 15:39 ` Fuad Tabba
2022-10-06 8:50 ` Fuad Tabba
2022-10-06 13:04 ` Kirill A. Shutemov
2022-10-17 13:00 ` Vlastimil Babka
2022-10-17 16:19 ` Kirill A . Shutemov
2022-10-17 16:39 ` Gupta, Pankaj
2022-10-17 21:56 ` Kirill A . Shutemov
2022-10-18 13:42 ` Vishal Annapurve
2022-10-19 15:32 ` Kirill A . Shutemov
2022-10-20 10:50 ` Vishal Annapurve
2022-10-21 13:54 ` Chao Peng
2022-10-21 16:53 ` Sean Christopherson
2022-10-19 12:23 ` Vishal Annapurve
2022-10-21 13:47 ` Chao Peng
2022-10-21 16:18 ` Sean Christopherson
2022-10-24 14:59 ` Kirill A . Shutemov
2022-10-24 15:26 ` David Hildenbrand
2022-11-03 16:27 ` Vishal Annapurve
2022-09-15 14:29 ` [PATCH v8 2/8] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-09-16 9:14 ` Bagas Sanjaya
2022-09-16 9:53 ` Chao Peng
2022-09-26 10:26 ` Fuad Tabba
2022-09-26 14:04 ` Chao Peng
2022-09-29 22:45 ` Isaku Yamahata
2022-09-29 23:22 ` Sean Christopherson
2022-10-05 13:04 ` Jarkko Sakkinen
2022-10-05 22:05 ` Jarkko Sakkinen
2022-10-06 9:00 ` Fuad Tabba
2022-10-06 14:58 ` Jarkko Sakkinen
2022-10-06 15:07 ` Jarkko Sakkinen
2022-10-06 15:34 ` Sean Christopherson
2022-10-07 11:14 ` Jarkko Sakkinen
2022-10-07 14:58 ` Sean Christopherson
2022-10-07 21:54 ` Jarkko Sakkinen
2022-10-08 16:15 ` Jarkko Sakkinen
2022-10-08 17:35 ` Jarkko Sakkinen
2022-10-10 8:25 ` Chao Peng
2022-10-12 8:14 ` Jarkko Sakkinen
2022-09-15 14:29 ` [PATCH v8 3/8] KVM: Add KVM_EXIT_MEMORY_FAULT exit Chao Peng
2022-09-16 9:17 ` Bagas Sanjaya
2022-09-16 9:54 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 4/8] KVM: Use gfn instead of hva for mmu_notifier_retry Chao Peng
2022-09-15 14:29 ` [PATCH v8 5/8] KVM: Register/unregister the guest private memory regions Chao Peng
2022-09-26 10:36 ` Fuad Tabba
2022-09-26 14:07 ` Chao Peng
2022-10-11 9:48 ` Fuad Tabba
2022-10-12 2:35 ` Chao Peng
2022-10-17 10:15 ` Fuad Tabba
2022-10-17 22:17 ` Sean Christopherson
2022-10-19 13:23 ` Chao Peng
2022-10-19 15:02 ` Fuad Tabba
2022-10-19 16:09 ` Sean Christopherson
2022-10-19 18:32 ` Fuad Tabba
2022-09-15 14:29 ` Chao Peng [this message]
2022-09-29 16:52 ` [PATCH v8 6/8] KVM: Update lpage info when private/shared memory are mixed Isaku Yamahata
2022-09-30 8:59 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 7/8] KVM: Handle page fault for private memory Chao Peng
2022-10-14 18:57 ` Sean Christopherson
2022-10-17 14:48 ` Chao Peng
2022-09-15 14:29 ` [PATCH v8 8/8] KVM: Enable and expose KVM_MEM_PRIVATE Chao Peng
2022-10-04 14:55 ` Jarkko Sakkinen
2022-10-10 8:31 ` Chao Peng
2022-10-06 8:55 ` Fuad Tabba
2022-10-10 8:33 ` Chao Peng
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20220915142913.2213336-7-chao.p.peng@linux.intel.com \
--to=chao.p.peng@linux.intel.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=bfields@fieldses.org \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@intel.com \
--cc=david@redhat.com \
--cc=ddutile@redhat.com \
--cc=dhildenb@redhat.com \
--cc=hpa@zytor.com \
--cc=hughd@google.com \
--cc=jlayton@kernel.org \
--cc=jmattson@google.com \
--cc=joro@8bytes.org \
--cc=jun.nakajima@intel.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=kvm@vger.kernel.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mail@maciej.szmigiero.name \
--cc=mhocko@suse.com \
--cc=michael.roth@amd.com \
--cc=mingo@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=qperret@google.com \
--cc=rppt@kernel.org \
--cc=seanjc@google.com \
--cc=shuah@kernel.org \
--cc=songmuchun@bytedance.com \
--cc=steven.price@arm.com \
--cc=tglx@linutronix.de \
--cc=vannapurve@google.com \
--cc=vbabka@suse.cz \
--cc=vkuznets@redhat.com \
--cc=wanpengli@tencent.com \
--cc=wei.w.wang@intel.com \
--cc=x86@kernel.org \
--cc=yu.c.zhang@linux.intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).