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-arch@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>,
tabba@google.com, Michael Roth <michael.roth@amd.com>,
mhocko@suse.com, Muchun Song <songmuchun@bytedance.com>,
wei.w.wang@intel.com
Subject: [PATCH v9 6/8] KVM: Update lpage info when private/shared memory are mixed
Date: Tue, 25 Oct 2022 23:13:42 +0800 [thread overview]
Message-ID: <20221025151344.3784230-7-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20221025151344.3784230-1-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.
Update 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 has 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 | 112 +++++++++++++++++++++++++++++++-
arch/x86/kvm/x86.c | 2 +
include/linux/kvm_host.h | 19 ++++++
virt/kvm/kvm_main.c | 16 +++--
5 files changed, 152 insertions(+), 5 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7551b6f9c31c..db811a54e3fd 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -37,6 +37,7 @@
#include <asm/hyperv-tlfs.h>
#define __KVM_HAVE_ARCH_VCPU_DEBUGFS
+#define __KVM_HAVE_ARCH_UPDATE_MEM_ATTR
#define KVM_MAX_VCPUS 1024
@@ -952,6 +953,13 @@ struct kvm_vcpu_arch {
#endif
};
+/*
+ * Use a bit in disallow_lpage to indicate private/shared pages mixed at the
+ * level. The remaining bits are used as a reference count.
+ */
+#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 33b1aec44fb8..67a9823a8c35 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);
}
}
@@ -6910,3 +6915,108 @@ 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 inline bool linfo_is_mixed(struct kvm_lpage_info *linfo)
+{
+ return linfo->disallow_lpage & KVM_LPAGE_PRIVATE_SHARED_MIXED;
+}
+
+static inline void linfo_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 bool mem_attr_is_mixed_2m(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 = attr == KVM_MEM_ATTR_SHARED;
+ bool mixed = false;
+
+ 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 && !shared) || (!entry && shared)) {
+ mixed = true;
+ goto out;
+ }
+
+ entry = xas_next(&xas);
+ gfn++;
+ }
+out:
+ rcu_read_unlock();
+ return mixed;
+}
+
+static bool mem_attr_is_mixed(struct kvm *kvm, struct kvm_memory_slot *slot,
+ int level, unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+ unsigned long gfn;
+ void *entry;
+
+ if (level == PG_LEVEL_2M)
+ return mem_attr_is_mixed_2m(kvm, attr, start, end);
+
+ entry = xa_load(&kvm->mem_attr_array, start);
+ for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) {
+ if (linfo_is_mixed(lpage_info_slot(gfn, slot, level - 1)))
+ return true;
+ if (xa_load(&kvm->mem_attr_array, gfn) != entry)
+ return true;
+ }
+ return false;
+}
+
+void kvm_arch_update_mem_attr(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;
+
+ WARN_ONCE(!(attr & (KVM_MEM_ATTR_PRIVATE | KVM_MEM_ATTR_SHARED)),
+ "Unsupported mem attribute.\n");
+
+ /*
+ * The sequence matters here: we update the higher level basing on the
+ * lower level's scanning result.
+ */
+ for (level = PG_LEVEL_2M; level <= KVM_MAX_HUGEPAGE_LEVEL; level++) {
+ pages = KVM_PAGES_PER_HPAGE(level);
+ mask = ~(pages - 1);
+ lpage_start = max(start & mask, slot->base_gfn);
+ lpage_end = (end - 1) & mask;
+
+ /*
+ * We only need to scan the head and tail page, for middle pages
+ * we know they are not mixed.
+ */
+ linfo_update_mixed(lpage_info_slot(lpage_start, slot, level),
+ mem_attr_is_mixed(kvm, slot, level, attr,
+ lpage_start, start));
+
+ if (lpage_start == lpage_end)
+ return;
+
+ for (gfn = lpage_start + pages; gfn < lpage_end; gfn += pages)
+ linfo_update_mixed(lpage_info_slot(gfn, slot, level),
+ false);
+
+ linfo_update_mixed(lpage_info_slot(lpage_end, slot, level),
+ mem_attr_is_mixed(kvm, slot, level, attr,
+ end, lpage_end + pages));
+ }
+}
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02ad31f46dd7..4276ca73bd7b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12563,6 +12563,8 @@ 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->restricted_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 4ce98fa0153c..6ce36065532c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2284,4 +2284,23 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
/* Max number of entries allowed for each kvm dirty ring */
#define KVM_DIRTY_RING_MAX_ENTRIES 65536
+#ifdef CONFIG_KVM_GENERIC_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, struct kvm_memory_slot *slot,
+ unsigned int attr, gfn_t start, gfn_t end);
+#else
+static inline void kvm_arch_update_mem_attr(struct kvm *kvm,
+ struct kvm_memory_slot *slot,
+ unsigned int attr,
+ gfn_t start, gfn_t end)
+{
+}
+#endif
+
+#endif /* CONFIG_KVM_GENERIC_PRIVATE_MEM */
+
#endif
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fc3835826ace..13a37b4d9e97 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -939,7 +939,8 @@ static int kvm_init_mmu_notifier(struct kvm *kvm)
#ifdef CONFIG_KVM_GENERIC_PRIVATE_MEM
-static void kvm_unmap_mem_range(struct kvm *kvm, gfn_t start, gfn_t end)
+static void kvm_unmap_mem_range(struct kvm *kvm, gfn_t start, gfn_t end,
+ unsigned int attr)
{
struct kvm_gfn_range gfn_range;
struct kvm_memory_slot *slot;
@@ -963,6 +964,7 @@ static void kvm_unmap_mem_range(struct kvm *kvm, gfn_t start, gfn_t end)
gfn_range.slot = slot;
r |= kvm_unmap_gfn_range(kvm, &gfn_range);
+ kvm_arch_update_mem_attr(kvm, slot, attr, start, end);
}
}
@@ -970,7 +972,6 @@ static void kvm_unmap_mem_range(struct kvm *kvm, gfn_t start, gfn_t end)
kvm_flush_remote_tlbs(kvm);
}
-#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)
{
@@ -979,6 +980,7 @@ static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
void *entry;
int idx;
int r = 0;
+ unsigned int attr;
if (size == 0 || gpa + size < gpa)
return -EINVAL;
@@ -992,7 +994,13 @@ 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);
+ }
idx = srcu_read_lock(&kvm->srcu);
KVM_MMU_LOCK(kvm);
@@ -1005,7 +1013,7 @@ static int kvm_vm_ioctl_set_mem_attr(struct kvm *kvm, gpa_t gpa, gpa_t size,
goto err;
}
- kvm_unmap_mem_range(kvm, start, end);
+ kvm_unmap_mem_range(kvm, start, end, attr);
goto ret;
err:
--
2.25.1
next prev parent reply other threads:[~2022-10-25 15:19 UTC|newest]
Thread overview: 101+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-25 15:13 [PATCH v9 0/8] KVM: mm: fd-based approach for supporting KVM Chao Peng
2022-10-25 15:13 ` [PATCH v9 1/8] mm: Introduce memfd_restricted system call to create restricted user memory Chao Peng
2022-10-26 17:31 ` Isaku Yamahata
2022-10-28 6:12 ` Chao Peng
2022-10-27 10:20 ` Fuad Tabba
2022-10-31 17:47 ` Michael Roth
2022-11-01 11:37 ` Chao Peng
2022-11-01 15:19 ` Michael Roth
2022-11-01 19:30 ` Michael Roth
2022-11-02 14:53 ` Chao Peng
2022-11-02 21:19 ` Michael Roth
2022-11-14 14:02 ` Vlastimil Babka
2022-11-14 15:28 ` Kirill A. Shutemov
2022-11-14 22:16 ` Michael Roth
2022-11-15 9:48 ` Chao Peng
2022-11-14 22:16 ` Michael Roth
2022-11-02 21:14 ` Kirill A. Shutemov
2022-11-02 21:26 ` Michael Roth
2022-11-02 22:07 ` Michael Roth
2022-11-03 16:30 ` Kirill A. Shutemov
2022-11-29 0:06 ` Michael Roth
2022-11-29 11:21 ` Kirill A. Shutemov
2022-11-29 11:39 ` David Hildenbrand
2022-11-29 13:59 ` Chao Peng
2022-11-29 13:58 ` Chao Peng
2022-11-29 0:37 ` Michael Roth
2022-11-29 14:06 ` Chao Peng
2022-11-29 19:06 ` Michael Roth
2022-11-29 19:18 ` Michael Roth
2022-11-30 9:39 ` Chao Peng
2022-11-30 14:31 ` Michael Roth
2022-11-29 18:01 ` Vishal Annapurve
2022-12-02 2:16 ` Vishal Annapurve
2022-12-02 6:49 ` Chao Peng
2022-12-02 13:44 ` Kirill A . Shutemov
2022-10-25 15:13 ` [PATCH v9 2/8] KVM: Extend the memslot to support fd-based private memory Chao Peng
2022-10-27 10:25 ` Fuad Tabba
2022-10-28 7:04 ` Xiaoyao Li
2022-10-31 14:14 ` Chao Peng
2022-11-14 16:04 ` Alex Bennée
2022-11-15 9:29 ` Chao Peng
2022-10-25 15:13 ` [PATCH v9 3/8] KVM: Add KVM_EXIT_MEMORY_FAULT exit Chao Peng
2022-10-25 15:26 ` Peter Maydell
2022-10-25 16:17 ` Sean Christopherson
2022-10-27 10:27 ` Fuad Tabba
2022-10-28 6:14 ` Chao Peng
2022-11-15 16:56 ` Alex Bennée
2022-11-16 3:14 ` Chao Peng
2022-11-16 19:03 ` Alex Bennée
2022-11-17 13:45 ` Chao Peng
2022-11-17 15:08 ` Alex Bennée
2022-11-18 1:32 ` Chao Peng
2022-11-18 13:23 ` Alex Bennée
2022-11-18 15:59 ` Sean Christopherson
2022-11-22 9:50 ` Chao Peng
2022-11-23 18:02 ` Sean Christopherson
2022-11-16 18:15 ` Andy Lutomirski
2022-11-16 18:48 ` Sean Christopherson
2022-11-17 13:42 ` Chao Peng
2022-10-25 15:13 ` [PATCH v9 4/8] KVM: Use gfn instead of hva for mmu_notifier_retry Chao Peng
2022-10-27 10:29 ` Fuad Tabba
2022-11-04 2:28 ` Chao Peng
2022-11-04 22:29 ` Sean Christopherson
2022-11-08 7:16 ` Chao Peng
2022-11-10 17:53 ` Sean Christopherson
2022-11-10 20:06 ` Sean Christopherson
2022-11-11 8:27 ` Chao Peng
2022-10-25 15:13 ` [PATCH v9 5/8] KVM: Register/unregister the guest private memory regions Chao Peng
2022-10-27 10:31 ` Fuad Tabba
2022-11-03 23:04 ` Sean Christopherson
2022-11-04 8:28 ` Chao Peng
2022-11-04 21:19 ` Sean Christopherson
2022-11-08 8:24 ` Chao Peng
2022-11-08 1:35 ` Yuan Yao
2022-11-08 9:41 ` Chao Peng
2022-11-09 5:52 ` Yuan Yao
2022-11-16 22:24 ` Sean Christopherson
2022-11-17 13:20 ` Chao Peng
2022-10-25 15:13 ` Chao Peng [this message]
2022-10-26 20:46 ` [PATCH v9 6/8] KVM: Update lpage info when private/shared memory are mixed Isaku Yamahata
2022-10-28 6:38 ` Chao Peng
2022-11-08 12:08 ` Yuan Yao
2022-11-09 4:13 ` Chao Peng
2022-10-25 15:13 ` [PATCH v9 7/8] KVM: Handle page fault for private memory Chao Peng
2022-10-26 21:54 ` Isaku Yamahata
2022-10-28 6:55 ` Chao Peng
2022-11-01 0:02 ` Isaku Yamahata
2022-11-01 11:38 ` Chao Peng
2022-11-16 20:50 ` Ackerley Tng
2022-11-16 22:13 ` Sean Christopherson
2022-11-17 13:25 ` Chao Peng
2022-10-25 15:13 ` [PATCH v9 8/8] KVM: Enable and expose KVM_MEM_PRIVATE Chao Peng
2022-10-27 10:31 ` Fuad Tabba
2022-11-03 12:13 ` [PATCH v9 0/8] KVM: mm: fd-based approach for supporting KVM Vishal Annapurve
2022-11-08 0:41 ` Isaku Yamahata
2022-11-09 15:54 ` Kirill A. Shutemov
2022-11-15 14:36 ` Kirill A. Shutemov
2022-11-14 11:43 ` Alex Bennée
2022-11-16 5:00 ` Chao Peng
2022-11-16 9:40 ` Alex Bennée
2022-11-17 14:16 ` 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=20221025151344.3784230-7-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-arch@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=tabba@google.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).