x86/speculation/mmio: Add mitigation for Processor MMIO Stale Data

commit 8cb861e9e3c9a55099ad3d08e1a3b653d29c33ca upstream

Processor MMIO Stale Data is a class of vulnerabilities that may
expose data after an MMIO operation. For details please refer to
Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst.

These vulnerabilities are broadly categorized as:

Device Register Partial Write (DRPW):
  Some endpoint MMIO registers incorrectly handle writes that are
  smaller than the register size. Instead of aborting the write or only
  copying the correct subset of bytes (for example, 2 bytes for a 2-byte
  write), more bytes than specified by the write transaction may be
  written to the register. On some processors, this may expose stale
  data from the fill buffers of the core that created the write
  transaction.

Shared Buffers Data Sampling (SBDS):
  After propagators may have moved data around the uncore and copied
  stale data into client core fill buffers, processors affected by MFBDS
  can leak data from the fill buffer.

Shared Buffers Data Read (SBDR):
  It is similar to Shared Buffer Data Sampling (SBDS) except that the
  data is directly read into the architectural software-visible state.

An attacker can use these vulnerabilities to extract data from CPU fill
buffers using MDS and TAA methods. Mitigate it by clearing the CPU fill
buffers using the VERW instruction before returning to a user or a
guest.

On CPUs not affected by MDS and TAA, user application cannot sample data
from CPU fill buffers using MDS or TAA. A guest with MMIO access can
still use DRPW or SBDR to extract data architecturally. Mitigate it with
VERW instruction to clear fill buffers before VMENTER for MMIO capable
guests.

Add a kernel parameter mmio_stale_data={off|full|full,nosmt} to control
the mitigation.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[cascardo: arch/x86/kvm/vmx.c has been moved]
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

4 files changed, 148 insertions, 4 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index f2b10986ab88..97c0ff0787ea 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2520,6 +2520,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					       kvm.nx_huge_pages=off [X86]
 					       no_entry_flush [PPC]
 					       no_uaccess_flush [PPC]
+					       mmio_stale_data=off [X86]
 
 				Exceptions:
 					       This does not have any effect on
@@ -2541,6 +2542,7 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 				Equivalent to: l1tf=flush,nosmt [X86]
 					       mds=full,nosmt [X86]
 					       tsx_async_abort=full,nosmt [X86]
+					       mmio_stale_data=full,nosmt [X86]
 
 	mminit_loglevel=
 			[KNL] When CONFIG_DEBUG_MEMORY_INIT is set, this
@@ -2550,6 +2552,40 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			log everything. Information is printed at KERN_DEBUG
 			so loglevel=8 may also need to be specified.
 
+	mmio_stale_data=
+			[X86,INTEL] Control mitigation for the Processor
+			MMIO Stale Data vulnerabilities.
+
+			Processor MMIO Stale Data is a class of
+			vulnerabilities that may expose data after an MMIO
+			operation. Exposed data could originate or end in
+			the same CPU buffers as affected by MDS and TAA.
+			Therefore, similar to MDS and TAA, the mitigation
+			is to clear the affected CPU buffers.
+
+			This parameter controls the mitigation. The
+			options are:
+
+			full       - Enable mitigation on vulnerable CPUs
+
+			full,nosmt - Enable mitigation and disable SMT on
+				     vulnerable CPUs.
+
+			off        - Unconditionally disable mitigation
+
+			On MDS or TAA affected machines,
+			mmio_stale_data=off can be prevented by an active
+			MDS or TAA mitigation as these vulnerabilities are
+			mitigated with the same mechanism so in order to
+			disable this mitigation, you need to specify
+			mds=off and tsx_async_abort=off too.
+
+			Not specifying this option is equivalent to
+			mmio_stale_data=full.
+
+			For details see:
+			Documentation/admin-guide/hw-vuln/processor_mmio_stale_data.rst
+
 	module.sig_enforce
 			[KNL] When CONFIG_MODULE_SIG is set, this means that
 			modules without (valid) signatures will fail to load.
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 19829b00e4fe..8a618fbf569f 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -323,6 +323,8 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 DECLARE_STATIC_KEY_FALSE(mds_user_clear);
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
+DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+
 #include <asm/segment.h>
 
 /**
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 17f412efa493..3e4710b22a08 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -41,6 +41,7 @@ static void __init l1tf_select_mitigation(void);
 static void __init mds_select_mitigation(void);
 static void __init md_clear_update_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
@@ -75,6 +76,10 @@ EXPORT_SYMBOL_GPL(mds_user_clear);
 DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
 EXPORT_SYMBOL_GPL(mds_idle_clear);
 
+/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */
+DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -109,11 +114,13 @@ void __init check_bugs(void)
 	l1tf_select_mitigation();
 	mds_select_mitigation();
 	taa_select_mitigation();
+	mmio_select_mitigation();
 	srbds_select_mitigation();
 
 	/*
-	 * As MDS and TAA mitigations are inter-related, update and print their
-	 * mitigation after TAA mitigation selection is done.
+	 * As MDS, TAA and MMIO Stale Data mitigations are inter-related, update
+	 * and print their mitigation after MDS, TAA and MMIO Stale Data
+	 * mitigation selection is done.
 	 */
 	md_clear_update_mitigation();
 
@@ -373,6 +380,90 @@ static int __init tsx_async_abort_parse_cmdline(char *str)
 early_param("tsx_async_abort", tsx_async_abort_parse_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"MMIO Stale Data: " fmt
+
+enum mmio_mitigations {
+	MMIO_MITIGATION_OFF,
+	MMIO_MITIGATION_UCODE_NEEDED,
+	MMIO_MITIGATION_VERW,
+};
+
+/* Default mitigation for Processor MMIO Stale Data vulnerabilities */
+static enum mmio_mitigations mmio_mitigation __ro_after_init = MMIO_MITIGATION_VERW;
+static bool mmio_nosmt __ro_after_init = false;
+
+static const char * const mmio_strings[] = {
+	[MMIO_MITIGATION_OFF]		= "Vulnerable",
+	[MMIO_MITIGATION_UCODE_NEEDED]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+	[MMIO_MITIGATION_VERW]		= "Mitigation: Clear CPU buffers",
+};
+
+static void __init mmio_select_mitigation(void)
+{
+	u64 ia32_cap;
+
+	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
+	    cpu_mitigations_off()) {
+		mmio_mitigation = MMIO_MITIGATION_OFF;
+		return;
+	}
+
+	if (mmio_mitigation == MMIO_MITIGATION_OFF)
+		return;
+
+	ia32_cap = x86_read_arch_cap_msr();
+
+	/*
+	 * Enable CPU buffer clear mitigation for host and VMM, if also affected
+	 * by MDS or TAA. Otherwise, enable mitigation for VMM only.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
+					      boot_cpu_has(X86_FEATURE_RTM)))
+		static_branch_enable(&mds_user_clear);
+	else
+		static_branch_enable(&mmio_stale_data_clear);
+
+	/*
+	 * Check if the system has the right microcode.
+	 *
+	 * CPU Fill buffer clear mitigation is enumerated by either an explicit
+	 * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
+	 * affected systems.
+	 */
+	if ((ia32_cap & ARCH_CAP_FB_CLEAR) ||
+	    (boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
+	     boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
+	     !(ia32_cap & ARCH_CAP_MDS_NO)))
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+	else
+		mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
+
+	if (mmio_nosmt || cpu_mitigations_auto_nosmt())
+		cpu_smt_disable(false);
+}
+
+static int __init mmio_stale_data_parse_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off")) {
+		mmio_mitigation = MMIO_MITIGATION_OFF;
+	} else if (!strcmp(str, "full")) {
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+	} else if (!strcmp(str, "full,nosmt")) {
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+		mmio_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("mmio_stale_data", mmio_stale_data_parse_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "" fmt
 
 static void __init md_clear_update_mitigation(void)
@@ -384,19 +475,31 @@ static void __init md_clear_update_mitigation(void)
 		goto out;
 
 	/*
-	 * mds_user_clear is now enabled. Update MDS mitigation, if
-	 * necessary.
+	 * mds_user_clear is now enabled. Update MDS, TAA and MMIO Stale Data
+	 * mitigation, if necessary.
 	 */
 	if (mds_mitigation == MDS_MITIGATION_OFF &&
 	    boot_cpu_has_bug(X86_BUG_MDS)) {
 		mds_mitigation = MDS_MITIGATION_FULL;
 		mds_select_mitigation();
 	}
+	if (taa_mitigation == TAA_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_TAA)) {
+		taa_mitigation = TAA_MITIGATION_VERW;
+		taa_select_mitigation();
+	}
+	if (mmio_mitigation == MMIO_MITIGATION_OFF &&
+	    boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
+		mmio_mitigation = MMIO_MITIGATION_VERW;
+		mmio_select_mitigation();
+	}
 out:
 	if (boot_cpu_has_bug(X86_BUG_MDS))
 		pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
 	if (boot_cpu_has_bug(X86_BUG_TAA))
 		pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
+	if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
+		pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
 }
 
 #undef pr_fmt
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 622e5a7eb7db..a7a5e9ebbd89 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9177,6 +9177,9 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmx_l1d_flush(vcpu);
 	else if (static_branch_unlikely(&mds_user_clear))
 		mds_clear_cpu_buffers();
+	else if (static_branch_unlikely(&mmio_stale_data_clear) &&
+		 kvm_arch_has_assigned_device(vcpu->kvm))
+		mds_clear_cpu_buffers();
 
 	asm(
 		/* Store host registers */