KVM Archive on lore.kernel.org
 help / color / Atom feed
From: Yang Weijiang <weijiang.yang@intel.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org,
	pbonzini@redhat.com, jmattson@google.com,
	sean.j.christopherson@intel.com
Cc: yu.c.zhang@linux.intel.com, alazar@bitdefender.com,
	edwin.zhai@intel.com, Yang Weijiang <weijiang.yang@intel.com>
Subject: [RESEND PATCH v10 03/10] mmu: spp: Add SPP Table setup functions
Date: Thu,  2 Jan 2020 14:13:12 +0800
Message-ID: <20200102061319.10077-4-weijiang.yang@intel.com> (raw)
In-Reply-To: <20200102061319.10077-1-weijiang.yang@intel.com>

SPPT is a 4-level paging structure similar to EPT, when SPP is
armed for target physical page, bit 61 of the corresponding
EPT entry is flaged, then SPPT is traversed with the gfn,
the leaf entry of SPPT contains the access bitmap of subpages
inside the target 4KB physical page, one bit per 128-byte subpage.

Co-developed-by: He Chen <he.chen@linux.intel.com>
Signed-off-by: He Chen <he.chen@linux.intel.com>
Co-developed-by: Zhang Yi <yi.z.zhang@linux.intel.com>
Signed-off-by: Zhang Yi <yi.z.zhang@linux.intel.com>
Signed-off-by: Yang Weijiang <weijiang.yang@intel.com>
---
 arch/x86/include/asm/kvm_host.h |   5 +-
 arch/x86/kvm/mmu/spp.c          | 228 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/mmu/spp.h          |  10 ++
 3 files changed, 242 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/kvm/mmu/spp.c
 create mode 100644 arch/x86/kvm/mmu/spp.h

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b79cd6aa4075..9506c9d40895 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -261,7 +261,8 @@ union kvm_mmu_page_role {
 		unsigned smap_andnot_wp:1;
 		unsigned ad_disabled:1;
 		unsigned guest_mode:1;
-		unsigned :6;
+		unsigned spp:1;
+		unsigned reserved:5;
 
 		/*
 		 * This is left at the top of the word so that
@@ -956,6 +957,8 @@ struct kvm_arch {
 
 	struct kvm_pmu_event_filter *pmu_event_filter;
 	struct task_struct *nx_lpage_recovery_thread;
+
+	hpa_t sppt_root;
 };
 
 struct kvm_vm_stat {
diff --git a/arch/x86/kvm/mmu/spp.c b/arch/x86/kvm/mmu/spp.c
new file mode 100644
index 000000000000..5fca08af705c
--- /dev/null
+++ b/arch/x86/kvm/mmu/spp.c
@@ -0,0 +1,228 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "spp.h"
+
+#define for_each_shadow_spp_entry(_vcpu, _addr, _walker)    \
+	for (shadow_spp_walk_init(&(_walker), _vcpu, _addr);	\
+	     shadow_walk_okay(&(_walker));			\
+	     shadow_walk_next(&(_walker)))
+
+static void shadow_spp_walk_init(struct kvm_shadow_walk_iterator *iterator,
+				 struct kvm_vcpu *vcpu, u64 addr)
+{
+	iterator->addr = addr;
+	iterator->shadow_addr = vcpu->kvm->arch.sppt_root;
+
+	/* SPP Table is a 4-level paging structure */
+	iterator->level = PT64_ROOT_4LEVEL;
+}
+
+static bool __rmap_open_subpage_bit(struct kvm *kvm,
+				    struct kvm_rmap_head *rmap_head)
+{
+	struct rmap_iterator iter;
+	bool flush = false;
+	u64 *sptep;
+	u64 spte;
+
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
+		/*
+		 * SPP works only when the page is write-protected
+		 * and SPP bit is set in EPT leaf entry.
+		 */
+		flush |= spte_write_protect(sptep, false);
+		spte = *sptep | PT_SPP_MASK;
+		flush |= mmu_spte_update(sptep, spte);
+	}
+
+	return flush;
+}
+
+static int kvm_spp_open_write_protect(struct kvm *kvm,
+				      struct kvm_memory_slot *slot,
+				      gfn_t gfn)
+{
+	struct kvm_rmap_head *rmap_head;
+	bool flush = false;
+
+	/*
+	 * SPP is only supported with 4KB level1 memory page, check
+	 * if the page is mapped in EPT leaf entry.
+	 */
+	rmap_head = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot);
+
+	if (!rmap_head->val)
+		return -EFAULT;
+
+	flush |= __rmap_open_subpage_bit(kvm, rmap_head);
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+static bool __rmap_clear_subpage_bit(struct kvm *kvm,
+				     struct kvm_rmap_head *rmap_head)
+{
+	struct rmap_iterator iter;
+	bool flush = false;
+	u64 *sptep;
+	u64 spte;
+
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
+		spte = (*sptep & ~PT_SPP_MASK);
+		flush |= mmu_spte_update(sptep, spte);
+	}
+
+	return flush;
+}
+
+static int kvm_spp_clear_write_protect(struct kvm *kvm,
+				       struct kvm_memory_slot *slot,
+				       gfn_t gfn)
+{
+	struct kvm_rmap_head *rmap_head;
+	bool flush = false;
+
+	rmap_head = __gfn_to_rmap(gfn, PT_PAGE_TABLE_LEVEL, slot);
+
+	if (!rmap_head->val)
+		return -EFAULT;
+
+	flush |= __rmap_clear_subpage_bit(kvm, rmap_head);
+
+	if (flush)
+		kvm_flush_remote_tlbs(kvm);
+
+	return 0;
+}
+
+struct kvm_mmu_page *kvm_spp_get_page(struct kvm_vcpu *vcpu,
+				      gfn_t gfn,
+				      unsigned int level)
+{
+	struct kvm_mmu_page *sp;
+	union kvm_mmu_page_role role;
+
+	role = vcpu->arch.mmu->mmu_role.base;
+	role.level = level;
+	role.direct = true;
+	role.spp = true;
+
+	for_each_valid_sp(vcpu->kvm, sp, gfn) {
+		if (sp->gfn != gfn)
+			continue;
+		if (sp->role.word != role.word)
+			continue;
+		if (sp->role.spp && sp->role.level == level)
+			goto out;
+	}
+
+	sp = kvm_mmu_alloc_page(vcpu, true);
+	sp->gfn = gfn;
+	sp->role = role;
+	hlist_add_head(&sp->hash_link,
+		       &vcpu->kvm->arch.mmu_page_hash
+		       [kvm_page_table_hashfn(gfn)]);
+	clear_page(sp->spt);
+out:
+	return sp;
+}
+EXPORT_SYMBOL_GPL(kvm_spp_get_page);
+
+static void link_spp_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
+				 struct kvm_mmu_page *sp)
+{
+	u64 spte;
+
+	spte = __pa(sp->spt) | PT_PRESENT_MASK;
+
+	mmu_spte_set(sptep, spte);
+
+	mmu_page_add_parent_pte(vcpu, sp, sptep);
+}
+
+static u64 format_spp_spte(u32 spp_wp_bitmap)
+{
+	u64 new_spte = 0;
+	int i = 0;
+
+	/*
+	 * One 4K page contains 32 sub-pages, in SPP table L4E, old bits
+	 * are reserved, so we need to transfer u32 subpage write
+	 * protect bitmap to u64 SPP L4E format.
+	 */
+	while (i < 32) {
+		if (spp_wp_bitmap & (1ULL << i))
+			new_spte |= 1ULL << (i * 2);
+		i++;
+	}
+
+	return new_spte;
+}
+
+static void spp_spte_set(u64 *sptep, u64 new_spte)
+{
+	__set_spte(sptep, new_spte);
+}
+
+bool is_spp_spte(struct kvm_mmu_page *sp)
+{
+	return sp->role.spp;
+}
+
+#define SPPT_ENTRY_PHA_MASK (0xFFFFFFFFFF << 12)
+
+int kvm_spp_setup_structure(struct kvm_vcpu *vcpu,
+			    u32 access_map, gfn_t gfn)
+{
+	struct kvm_shadow_walk_iterator iter;
+	struct kvm_mmu_page *sp;
+	gfn_t pseudo_gfn;
+	u64 old_spte, spp_spte;
+	int ret = -EFAULT;
+
+	/* direct_map spp start */
+	if (!VALID_PAGE(vcpu->kvm->arch.sppt_root))
+		return -EFAULT;
+
+	for_each_shadow_spp_entry(vcpu, (u64)gfn << PAGE_SHIFT, iter) {
+		if (iter.level == PT_PAGE_TABLE_LEVEL) {
+			spp_spte = format_spp_spte(access_map);
+			old_spte = mmu_spte_get_lockless(iter.sptep);
+			if (old_spte != spp_spte)
+				spp_spte_set(iter.sptep, spp_spte);
+			ret = 0;
+			break;
+		}
+
+		if (!is_shadow_present_pte(*iter.sptep)) {
+			u64 base_addr = iter.addr;
+
+			base_addr &= PT64_LVL_ADDR_MASK(iter.level);
+			pseudo_gfn = base_addr >> PAGE_SHIFT;
+			spp_spte = *iter.sptep;
+			sp = kvm_spp_get_page(vcpu, pseudo_gfn,
+					      iter.level - 1);
+			link_spp_shadow_page(vcpu, iter.sptep, sp);
+		} else if (iter.level == PT_DIRECTORY_LEVEL  &&
+			   !(spp_spte & PT_PRESENT_MASK) &&
+			   (spp_spte & SPPT_ENTRY_PHA_MASK)) {
+			spp_spte = *iter.sptep;
+			spp_spte |= PT_PRESENT_MASK;
+			spp_spte_set(iter.sptep, spp_spte);
+		}
+	}
+
+	kvm_flush_remote_tlbs(vcpu->kvm);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_spp_setup_structure);
+
+inline u64 construct_spptp(unsigned long root_hpa)
+{
+	return root_hpa & PAGE_MASK;
+}
+EXPORT_SYMBOL_GPL(construct_spptp);
+
diff --git a/arch/x86/kvm/mmu/spp.h b/arch/x86/kvm/mmu/spp.h
new file mode 100644
index 000000000000..8ef94b7a2057
--- /dev/null
+++ b/arch/x86/kvm/mmu/spp.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_SPP_H
+#define __KVM_X86_VMX_SPP_H
+
+bool is_spp_spte(struct kvm_mmu_page *sp);
+u64 construct_spptp(unsigned long root_hpa);
+int kvm_spp_setup_structure(struct kvm_vcpu *vcpu,
+			    u32 access_map, gfn_t gfn);
+
+#endif /* __KVM_X86_VMX_SPP_H */
-- 
2.17.2


  parent reply index

Thread overview: 34+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-01-02  6:13 [RESEND PATCH v10 00/10] Enable Sub-Page Write Protection Support Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 01/10] Documentation: Add EPT based Subpage Protection and related APIs Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 02/10] vmx: spp: Add control flags for Sub-Page Protection(SPP) Yang Weijiang
2020-01-10 16:58   ` Sean Christopherson
2020-01-13  5:44     ` Yang Weijiang
2020-01-02  6:13 ` Yang Weijiang [this message]
2020-01-10 17:26   ` [RESEND PATCH v10 03/10] mmu: spp: Add SPP Table setup functions Sean Christopherson
2020-01-13  6:00     ` Yang Weijiang
2020-01-10 17:40   ` Sean Christopherson
2020-01-13  6:04     ` Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 04/10] mmu: spp: Add functions to operate SPP access bitmap Yang Weijiang
2020-01-10 17:38   ` Sean Christopherson
2020-01-13  6:15     ` Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 05/10] x86: spp: Introduce user-space SPP IOCTLs Yang Weijiang
2020-01-10 18:10   ` Sean Christopherson
2020-01-13  8:21     ` Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 06/10] vmx: spp: Set up SPP paging table at vmentry/vmexit Yang Weijiang
2020-01-10 17:55   ` Sean Christopherson
2020-01-13  6:50     ` Yang Weijiang
2020-01-21 14:01     ` Paolo Bonzini
2020-01-10 18:04   ` Sean Christopherson
2020-01-13  8:10     ` Yang Weijiang
2020-01-13 17:33       ` Sean Christopherson
2020-01-13 18:55         ` Adalbert Lazăr
2020-01-13 21:47           ` Sean Christopherson
2020-01-14  3:08         ` Yang Weijiang
2020-01-14 18:58           ` Sean Christopherson
2020-01-15  1:36             ` Yang Weijiang
2020-01-21 14:14             ` Paolo Bonzini
2020-01-02  6:13 ` [RESEND PATCH v10 07/10] mmu: spp: Enable Lazy mode SPP protection Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 08/10] mmu: spp: Handle SPP protected pages when VM memory changes Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 09/10] x86: spp: Add SPP protection check in emulation Yang Weijiang
2020-01-02  6:13 ` [RESEND PATCH v10 10/10] kvm: selftests: selftest for Sub-Page protection Yang Weijiang
  -- strict thread matches above, loose matches on Subject: below --
2020-01-02  5:18 [RESEND PATCH v10 00/10] Enable Sub-Page Write Protection Support Yang Weijiang
2020-01-02  5:18 ` [RESEND PATCH v10 03/10] mmu: spp: Add SPP Table setup functions Yang Weijiang

Reply instructions:

You may reply publically 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=20200102061319.10077-4-weijiang.yang@intel.com \
    --to=weijiang.yang@intel.com \
    --cc=alazar@bitdefender.com \
    --cc=edwin.zhai@intel.com \
    --cc=jmattson@google.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=sean.j.christopherson@intel.com \
    --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

KVM Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/kvm/0 kvm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 kvm kvm/ https://lore.kernel.org/kvm \
		kvm@vger.kernel.org
	public-inbox-index kvm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.kvm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git