qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
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,
	qemu-devel@nongnu.org
Cc: Wanpeng Li <wanpengli@tencent.com>,
	jun.nakajima@intel.com, david@redhat.com,
	"J . Bruce Fields" <bfields@fieldses.org>,
	dave.hansen@intel.com, "H . Peter Anvin" <hpa@zytor.com>,
	Chao Peng <chao.p.peng@linux.intel.com>,
	ak@linux.intel.com, Jonathan Corbet <corbet@lwn.net>,
	Joerg Roedel <joro@8bytes.org>,
	x86@kernel.org, Hugh Dickins <hughd@google.com>,
	Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	luto@kernel.org, Thomas Gleixner <tglx@linutronix.de>,
	Vitaly Kuznetsov <vkuznets@redhat.com>,
	Jim Mattson <jmattson@google.com>,
	Sean Christopherson <seanjc@google.com>,
	susie.li@intel.com, Jeff Layton <jlayton@kernel.org>,
	john.ji@intel.com, Yu Zhang <yu.c.zhang@linux.intel.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCH v3 kvm/queue 14/16] KVM: Handle page fault for private memory
Date: Thu, 23 Dec 2021 20:30:09 +0800	[thread overview]
Message-ID: <20211223123011.41044-15-chao.p.peng@linux.intel.com> (raw)
In-Reply-To: <20211223123011.41044-1-chao.p.peng@linux.intel.com>

When a page fault from the secondary page table while the guest is
running happens in a memslot with KVM_MEM_PRIVATE, we need go
different paths for private access and shared access.

  - For private access, KVM checks if the page is already allocated in
    the memory backend, if yes KVM establishes the mapping, otherwise
    exits to userspace to convert a shared page to private one.

  - For shared access, KVM also checks if the page is already allocated
    in the memory backend, if yes then exit to userspace to convert a
    private page to shared one, otherwise it's treated as a traditional
    hva-based shared memory, KVM lets existing code to obtain a pfn with
    get_user_pages() and establish the mapping.

The above code assume private memory is persistent and pre-allocated in
the memory backend so KVM can use this information as an indicator for
a page is private or shared. The above check is then performed by
calling kvm_memfd_get_pfn() which currently is implemented as a
pagecache search but in theory that can be implemented differently
(i.e. when the page is even not mapped into host pagecache there should
be some different implementation).

Signed-off-by: Yu Zhang <yu.c.zhang@linux.intel.com>
Signed-off-by: Chao Peng <chao.p.peng@linux.intel.com>
---
 arch/x86/kvm/mmu/mmu.c         | 73 ++++++++++++++++++++++++++++++++--
 arch/x86/kvm/mmu/paging_tmpl.h | 11 +++--
 2 files changed, 77 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 2856eb662a21..fbcdf62f8281 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2920,6 +2920,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
 	if (max_level == PG_LEVEL_4K)
 		return PG_LEVEL_4K;
 
+	if (kvm_slot_is_private(slot))
+		return max_level;
+
 	host_level = host_pfn_mapping_level(kvm, gfn, pfn, slot);
 	return min(host_level, max_level);
 }
@@ -3950,7 +3953,59 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, int *r)
+static bool kvm_vcpu_is_private_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+	/*
+	 * At this time private gfn has not been supported yet. Other patch
+	 * that enables it should change this.
+	 */
+	return false;
+}
+
+static bool kvm_faultin_pfn_private(struct kvm_vcpu *vcpu,
+				    struct kvm_page_fault *fault,
+				    bool *is_private_pfn, int *r)
+{
+	int order;
+	int mem_convert_type;
+	struct kvm_memory_slot *slot = fault->slot;
+	long pfn = kvm_memfd_get_pfn(slot, fault->gfn, &order);
+
+	if (kvm_vcpu_is_private_gfn(vcpu, fault->addr >> PAGE_SHIFT)) {
+		if (pfn < 0)
+			mem_convert_type = KVM_EXIT_MEM_MAP_PRIVATE;
+		else {
+			fault->pfn = pfn;
+			if (slot->flags & KVM_MEM_READONLY)
+				fault->map_writable = false;
+			else
+				fault->map_writable = true;
+
+			if (order == 0)
+				fault->max_level = PG_LEVEL_4K;
+			*is_private_pfn = true;
+			*r = RET_PF_FIXED;
+			return true;
+		}
+	} else {
+		if (pfn < 0)
+			return false;
+
+		kvm_memfd_put_pfn(pfn);
+		mem_convert_type = KVM_EXIT_MEM_MAP_SHARED;
+	}
+
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_ERROR;
+	vcpu->run->mem.type = mem_convert_type;
+	vcpu->run->mem.u.map.gpa = fault->gfn << PAGE_SHIFT;
+	vcpu->run->mem.u.map.size = PAGE_SIZE;
+	fault->pfn = -1;
+	*r = -1;
+	return true;
+}
+
+static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
+			    bool *is_private_pfn, int *r)
 {
 	struct kvm_memory_slot *slot = fault->slot;
 	bool async;
@@ -3984,6 +4039,10 @@ static bool kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
 		}
 	}
 
+	if (kvm_slot_is_private(slot) &&
+	    kvm_faultin_pfn_private(vcpu, fault, is_private_pfn, r))
+		return *r == RET_PF_FIXED ? false : true;
+
 	async = false;
 	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
 					  fault->write, &fault->map_writable,
@@ -4044,6 +4103,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	bool is_tdp_mmu_fault = is_tdp_mmu(vcpu->arch.mmu);
 
 	unsigned long mmu_seq;
+	bool is_private_pfn = false;
 	int r;
 
 	fault->gfn = fault->addr >> PAGE_SHIFT;
@@ -4063,7 +4123,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (kvm_faultin_pfn(vcpu, fault, &r))
+	if (kvm_faultin_pfn(vcpu, fault, &is_private_pfn, &r))
 		return r;
 
 	if (handle_abnormal_pfn(vcpu, fault, ACC_ALL, &r))
@@ -4076,7 +4136,7 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	else
 		write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_page_fault_stale(vcpu, fault, mmu_seq))
+	if (!is_private_pfn && is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
 	r = make_mmu_pages_available(vcpu);
@@ -4093,7 +4153,12 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 		read_unlock(&vcpu->kvm->mmu_lock);
 	else
 		write_unlock(&vcpu->kvm->mmu_lock);
-	kvm_release_pfn_clean(fault->pfn);
+
+	if (is_private_pfn)
+		kvm_memfd_put_pfn(fault->pfn);
+	else
+		kvm_release_pfn_clean(fault->pfn);
+
 	return r;
 }
 
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 5b5bdac97c7b..640fd1e2fe4c 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -825,6 +825,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	int r;
 	unsigned long mmu_seq;
 	bool is_self_change_mapping;
+	bool is_private_pfn = false;
+
 
 	pgprintk("%s: addr %lx err %x\n", __func__, fault->addr, fault->error_code);
 	WARN_ON_ONCE(fault->is_tdp);
@@ -873,7 +875,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;
 	smp_rmb();
 
-	if (kvm_faultin_pfn(vcpu, fault, &r))
+	if (kvm_faultin_pfn(vcpu, fault, &is_private_pfn, &r))
 		return r;
 
 	if (handle_abnormal_pfn(vcpu, fault, walker.pte_access, &r))
@@ -901,7 +903,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_page_fault_stale(vcpu, fault, mmu_seq))
+	if (!is_private_pfn && is_page_fault_stale(vcpu, fault, mmu_seq))
 		goto out_unlock;
 
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PAGE_FAULT);
@@ -913,7 +915,10 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 
 out_unlock:
 	write_unlock(&vcpu->kvm->mmu_lock);
-	kvm_release_pfn_clean(fault->pfn);
+	if (is_private_pfn)
+		kvm_memfd_put_pfn(fault->pfn);
+	else
+		kvm_release_pfn_clean(fault->pfn);
 	return r;
 }
 
-- 
2.17.1



  parent reply	other threads:[~2021-12-23 12:55 UTC|newest]

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-23 12:29 [PATCH v3 kvm/queue 00/16] KVM: mm: fd-based approach for supporting KVM guest private memory Chao Peng
2021-12-23 12:29 ` [PATCH v3 kvm/queue 01/16] mm/shmem: Introduce F_SEAL_INACCESSIBLE Chao Peng
2022-01-04 14:22   ` David Hildenbrand
2022-01-06 13:06     ` Chao Peng
2022-01-13 15:56       ` David Hildenbrand
2021-12-23 12:29 ` [PATCH v3 kvm/queue 02/16] mm/memfd: Introduce MFD_INACCESSIBLE flag Chao Peng
2021-12-23 12:29 ` [PATCH v3 kvm/queue 03/16] mm/memfd: Introduce MEMFD_OPS Chao Peng
2021-12-24  3:53   ` Robert Hoo
2021-12-31  2:38     ` Chao Peng
2022-01-04 17:38       ` Sean Christopherson
2022-01-05  6:07         ` Chao Peng
2021-12-23 12:29 ` [PATCH v3 kvm/queue 04/16] KVM: Extend the memslot to support fd-based private memory Chao Peng
2021-12-23 17:35   ` Sean Christopherson
2021-12-31  2:53     ` Chao Peng
2022-01-04 17:34       ` Sean Christopherson
2021-12-23 12:30 ` [PATCH v3 kvm/queue 05/16] KVM: Maintain ofs_tree for fast memslot lookup by file offset Chao Peng
2021-12-23 18:02   ` Sean Christopherson
2021-12-24  3:54     ` Chao Peng
2021-12-27 23:50       ` Yao Yuan
2021-12-28 21:48       ` Sean Christopherson
2021-12-31  2:26         ` Chao Peng
2022-01-04 17:43           ` Sean Christopherson
2022-01-05  6:09             ` Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 06/16] KVM: Implement fd-based memory using MEMFD_OPS interfaces Chao Peng
2021-12-23 18:34   ` Sean Christopherson
2021-12-23 23:09     ` Paolo Bonzini
2021-12-24  4:25       ` Chao Peng
2021-12-28 22:14         ` Sean Christopherson
2021-12-24  4:12     ` Chao Peng
2021-12-24  4:22     ` Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 07/16] KVM: Refactor hva based memory invalidation code Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 08/16] KVM: Special handling for fd-based memory invalidation Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 09/16] KVM: Split out common memory invalidation code Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 10/16] KVM: Implement fd-based memory invalidation Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 11/16] KVM: Add kvm_map_gfn_range Chao Peng
2021-12-23 18:06   ` Sean Christopherson
2021-12-24  4:13     ` Chao Peng
2021-12-31  2:33       ` Chao Peng
2022-01-04 17:31         ` Sean Christopherson
2022-01-05  6:14           ` Chao Peng
2022-01-05 17:03             ` Sean Christopherson
2022-01-06 12:35               ` Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 12/16] KVM: Implement fd-based memory fallocation Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 13/16] KVM: Add KVM_EXIT_MEMORY_ERROR exit Chao Peng
2021-12-23 18:28   ` Sean Christopherson
2021-12-23 12:30 ` Chao Peng [this message]
2022-01-04  1:46   ` [PATCH v3 kvm/queue 14/16] KVM: Handle page fault for private memory Yan Zhao
2022-01-04  9:10     ` Chao Peng
2022-01-04 10:06       ` Yan Zhao
2022-01-05  6:28         ` Chao Peng
2022-01-05  7:53           ` Yan Zhao
2022-01-05 20:52             ` Sean Christopherson
2022-01-14  5:53               ` Yan Zhao
2021-12-23 12:30 ` [PATCH v3 kvm/queue 15/16] KVM: Use kvm_userspace_memory_region_ext Chao Peng
2021-12-23 12:30 ` [PATCH v3 kvm/queue 16/16] KVM: Register/unregister private memory slot to memfd 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=20211223123011.41044-15-chao.p.peng@linux.intel.com \
    --to=chao.p.peng@linux.intel.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=hpa@zytor.com \
    --cc=hughd@google.com \
    --cc=jlayton@kernel.org \
    --cc=jmattson@google.com \
    --cc=john.ji@intel.com \
    --cc=joro@8bytes.org \
    --cc=jun.nakajima@intel.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=kvm@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=mingo@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=seanjc@google.com \
    --cc=susie.li@intel.com \
    --cc=tglx@linutronix.de \
    --cc=vkuznets@redhat.com \
    --cc=wanpengli@tencent.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).