linux-kernel - [PATCH] KVM: x86/mmu: Warn on nx_huge

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

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20211019141101.327397-1-liyu.yukiteru@bytedance.com>
Date:   Tue, 19 Oct 2021 22:11:01 +0800
From:   Li Yu <liyu.yukiteru@...edance.com>
To:     pbonzini@...hat.com
Cc:     liyu.yukiteru@...edance.com,
        Sean Christopherson <seanjc@...gle.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        x86@...nel.org, "H. Peter Anvin" <hpa@...or.com>,
        kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH] KVM: x86/mmu: Warn on nx_huge_pages for possible problems

Add warning when `nx_huge_pages` is enabled by `auto` for hint that
huge pages may be splited by kernel.

Add warning when CVE-2018-12207 may arise but `nx_huge_pages` is
disabled for hint that malicious guest may cause a CPU lookup.

Signed-off-by: Li Yu <liyu.yukiteru@...edance.com>
---
 arch/x86/kvm/mmu/mmu.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1a64ba5b9437..32026592e566 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6056,19 +6056,26 @@ static void __set_nx_huge_pages(bool val)
 	nx_huge_pages = itlb_multihit_kvm_mitigation = val;
 }
 
+#define ITLB_MULTIHIT_NX_ON  "iTLB multi-hit CPU bug present and cpu mitigations enabled, huge pages may be splited by kernel for security. See CVE-2018-12207 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/multihit.html for details.\n"
+#define ITLB_MULTIHIT_NX_OFF "iTLB multi-hit CPU bug present and cpu mitigations enabled, malicious guest may cause a CPU lookup. See CVE-2018-12207 and https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/multihit.html for details.\n"
+
 static int set_nx_huge_pages(const char *val, const struct kernel_param *kp)
 {
 	bool old_val = nx_huge_pages;
 	bool new_val;
 
 	/* In "auto" mode deploy workaround only if CPU has the bug. */
-	if (sysfs_streq(val, "off"))
+	if (sysfs_streq(val, "off")) {
 		new_val = 0;
-	else if (sysfs_streq(val, "force"))
+		if (get_nx_auto_mode() && new_val != old_val)
+			pr_warn(ITLB_MULTIHIT_NX_OFF);
+	} else if (sysfs_streq(val, "force"))
 		new_val = 1;
-	else if (sysfs_streq(val, "auto"))
+	else if (sysfs_streq(val, "auto")) {
 		new_val = get_nx_auto_mode();
-	else if (strtobool(val, &new_val) < 0)
+		if (new_val && new_val != old_val)
+			pr_warn(ITLB_MULTIHIT_NX_ON);
+	} else if (strtobool(val, &new_val) < 0)
 		return -EINVAL;
 
 	__set_nx_huge_pages(new_val);
@@ -6095,8 +6102,11 @@ int kvm_mmu_module_init(void)
 {
 	int ret = -ENOMEM;
 
-	if (nx_huge_pages == -1)
+	if (nx_huge_pages == -1) {
 		__set_nx_huge_pages(get_nx_auto_mode());
+		if (is_nx_huge_page_enabled())
+			pr_warn_once(ITLB_MULTIHIT_NX_ON);
+	}
 
 	/*
 	 * MMU roles use union aliasing which is, generally speaking, an
-- 
2.11.0