Merge branch 'x86-mds-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 MDS mitigations from Thomas Gleixner:
 "Microarchitectural Data Sampling (MDS) is a hardware vulnerability
  which allows unprivileged speculative access to data which is
  available in various CPU internal buffers. This new set of misfeatures
  has the following CVEs assigned:

     CVE-2018-12126  MSBDS  Microarchitectural Store Buffer Data Sampling
     CVE-2018-12130  MFBDS  Microarchitectural Fill Buffer Data Sampling
     CVE-2018-12127  MLPDS  Microarchitectural Load Port Data Sampling
     CVE-2019-11091  MDSUM  Microarchitectural Data Sampling Uncacheable Memory

  MDS attacks target microarchitectural buffers which speculatively
  forward data under certain conditions. Disclosure gadgets can expose
  this data via cache side channels.

  Contrary to other speculation based vulnerabilities the MDS
  vulnerability does not allow the attacker to control the memory target
  address. As a consequence the attacks are purely sampling based, but
  as demonstrated with the TLBleed attack samples can be postprocessed
  successfully.

  The mitigation is to flush the microarchitectural buffers on return to
  user space and before entering a VM. It's bolted on the VERW
  instruction and requires a microcode update. As some of the attacks
  exploit data structures shared between hyperthreads, full protection
  requires to disable hyperthreading. The kernel does not do that by
  default to avoid breaking unattended updates.

  The mitigation set comes with documentation for administrators and a
  deeper technical view"

* 'x86-mds-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  x86/speculation/mds: Fix documentation typo
  Documentation: Correct the possible MDS sysfs values
  x86/mds: Add MDSUM variant to the MDS documentation
  x86/speculation/mds: Add 'mitigations=' support for MDS
  x86/speculation/mds: Print SMT vulnerable on MSBDS with mitigations off
  x86/speculation/mds: Fix comment
  x86/speculation/mds: Add SMT warning message
  x86/speculation: Move arch_smt_update() call to after mitigation decisions
  x86/speculation/mds: Add mds=full,nosmt cmdline option
  Documentation: Add MDS vulnerability documentation
  Documentation: Move L1TF to separate directory
  x86/speculation/mds: Add mitigation mode VMWERV
  x86/speculation/mds: Add sysfs reporting for MDS
  x86/speculation/mds: Add mitigation control for MDS
  x86/speculation/mds: Conditionally clear CPU buffers on idle entry
  x86/kvm/vmx: Add MDS protection when L1D Flush is not active
  x86/speculation/mds: Clear CPU buffers on exit to user
  x86/speculation/mds: Add mds_clear_cpu_buffers()
  x86/kvm: Expose X86_FEATURE_MD_CLEAR to guests
  x86/speculation/mds: Add BUG_MSBDS_ONLY
  ...

4 files changed, 214 insertions, 54 deletions

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 29630393f300..03b4cc0ec3a7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -37,6 +37,7 @@
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
 static void __init l1tf_select_mitigation(void);
+static void __init mds_select_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR that always has to be preserved. */
 u64 x86_spec_ctrl_base;
@@ -63,6 +64,13 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 /* Control unconditional IBPB in switch_mm() */
 DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
+/* Control MDS CPU buffer clear before returning to user space */
+DEFINE_STATIC_KEY_FALSE(mds_user_clear);
+EXPORT_SYMBOL_GPL(mds_user_clear);
+/* Control MDS CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
+EXPORT_SYMBOL_GPL(mds_idle_clear);
+
 void __init check_bugs(void)
 {
 	identify_boot_cpu();
@@ -101,6 +109,10 @@ void __init check_bugs(void)
 
 	l1tf_select_mitigation();
 
+	mds_select_mitigation();
+
+	arch_smt_update();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -207,6 +219,61 @@ static void x86_amd_ssb_disable(void)
 }
 
 #undef pr_fmt
+#define pr_fmt(fmt)	"MDS: " fmt
+
+/* Default mitigation for MDS-affected CPUs */
+static enum mds_mitigations mds_mitigation __ro_after_init = MDS_MITIGATION_FULL;
+static bool mds_nosmt __ro_after_init = false;
+
+static const char * const mds_strings[] = {
+	[MDS_MITIGATION_OFF]	= "Vulnerable",
+	[MDS_MITIGATION_FULL]	= "Mitigation: Clear CPU buffers",
+	[MDS_MITIGATION_VMWERV]	= "Vulnerable: Clear CPU buffers attempted, no microcode",
+};
+
+static void __init mds_select_mitigation(void)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
+		mds_mitigation = MDS_MITIGATION_OFF;
+		return;
+	}
+
+	if (mds_mitigation == MDS_MITIGATION_FULL) {
+		if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+			mds_mitigation = MDS_MITIGATION_VMWERV;
+
+		static_branch_enable(&mds_user_clear);
+
+		if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
+		    (mds_nosmt || cpu_mitigations_auto_nosmt()))
+			cpu_smt_disable(false);
+	}
+
+	pr_info("%s\n", mds_strings[mds_mitigation]);
+}
+
+static int __init mds_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_MDS))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		mds_mitigation = MDS_MITIGATION_OFF;
+	else if (!strcmp(str, "full"))
+		mds_mitigation = MDS_MITIGATION_FULL;
+	else if (!strcmp(str, "full,nosmt")) {
+		mds_mitigation = MDS_MITIGATION_FULL;
+		mds_nosmt = true;
+	}
+
+	return 0;
+}
+early_param("mds", mds_cmdline);
+
+#undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
 static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
@@ -575,9 +642,6 @@ specv2_set_mode:
 
 	/* Set up IBPB and STIBP depending on the general spectre V2 command */
 	spectre_v2_user_select_mitigation(cmd);
-
-	/* Enable STIBP if appropriate */
-	arch_smt_update();
 }
 
 static void update_stibp_msr(void * __unused)
@@ -611,6 +675,31 @@ static void update_indir_branch_cond(void)
 		static_branch_disable(&switch_to_cond_stibp);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+/* Update the static key controlling the MDS CPU buffer clear in idle */
+static void update_mds_branch_idle(void)
+{
+	/*
+	 * Enable the idle clearing if SMT is active on CPUs which are
+	 * affected only by MSBDS and not any other MDS variant.
+	 *
+	 * The other variants cannot be mitigated when SMT is enabled, so
+	 * clearing the buffers on idle just to prevent the Store Buffer
+	 * repartitioning leak would be a window dressing exercise.
+	 */
+	if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
+		return;
+
+	if (sched_smt_active())
+		static_branch_enable(&mds_idle_clear);
+	else
+		static_branch_disable(&mds_idle_clear);
+}
+
+#define MDS_MSG_SMT "MDS CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/mds.html for more details.\n"
+
 void arch_smt_update(void)
 {
 	/* Enhanced IBRS implies STIBP. No update required. */
@@ -632,6 +721,17 @@ void arch_smt_update(void)
 		break;
 	}
 
+	switch (mds_mitigation) {
+	case MDS_MITIGATION_FULL:
+	case MDS_MITIGATION_VMWERV:
+		if (sched_smt_active() && !boot_cpu_has(X86_BUG_MSBDS_ONLY))
+			pr_warn_once(MDS_MSG_SMT);
+		update_mds_branch_idle();
+		break;
+	case MDS_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -1043,7 +1143,7 @@ static void __init l1tf_select_mitigation(void)
 		pr_info("You may make it effective by booting the kernel with mem=%llu parameter.\n",
 				half_pa);
 		pr_info("However, doing so will make a part of your RAM unusable.\n");
-		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html might help you decide.\n");
+		pr_info("Reading https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/l1tf.html might help you decide.\n");
 		return;
 	}
 
@@ -1076,6 +1176,7 @@ static int __init l1tf_cmdline(char *str)
 early_param("l1tf", l1tf_cmdline);
 
 #undef pr_fmt
+#define pr_fmt(fmt) fmt
 
 #ifdef CONFIG_SYSFS
 
@@ -1114,6 +1215,23 @@ static ssize_t l1tf_show_state(char *buf)
 }
 #endif
 
+static ssize_t mds_show_state(char *buf)
+{
+	if (!hypervisor_is_type(X86_HYPER_NATIVE)) {
+		return sprintf(buf, "%s; SMT Host state unknown\n",
+			       mds_strings[mds_mitigation]);
+	}
+
+	if (boot_cpu_has(X86_BUG_MSBDS_ONLY)) {
+		return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+			       (mds_mitigation == MDS_MITIGATION_OFF ? "vulnerable" :
+			        sched_smt_active() ? "mitigated" : "disabled"));
+	}
+
+	return sprintf(buf, "%s; SMT %s\n", mds_strings[mds_mitigation],
+		       sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_enabled == SPECTRE_V2_IBRS_ENHANCED)
@@ -1180,6 +1298,10 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
 			return l1tf_show_state(buf);
 		break;
+
+	case X86_BUG_MDS:
+		return mds_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1211,4 +1333,9 @@ ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *b
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
 }
+
+ssize_t cpu_show_mds(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_MDS);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8739bdfe9bdf..d7f55ad2dfb1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -940,61 +940,77 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c)
 #endif
 }
 
-static const __initconst struct x86_cpu_id cpu_no_speculation[] = {
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_TABLET,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_SALTWELL_MID,	X86_FEATURE_ANY },
-	{ X86_VENDOR_INTEL,	6, INTEL_FAM6_ATOM_BONNELL,	X86_FEATURE_ANY },
-	{ X86_VENDOR_CENTAUR,	5 },
-	{ X86_VENDOR_INTEL,	5 },
-	{ X86_VENDOR_NSC,	5 },
-	{ X86_VENDOR_ANY,	4 },
+#define NO_SPECULATION	BIT(0)
+#define NO_MELTDOWN	BIT(1)
+#define NO_SSB		BIT(2)
+#define NO_L1TF		BIT(3)
+#define NO_MDS		BIT(4)
+#define MSBDS_ONLY	BIT(5)
+
+#define VULNWL(_vendor, _family, _model, _whitelist)	\
+	{ X86_VENDOR_##_vendor, _family, _model, X86_FEATURE_ANY, _whitelist }
+
+#define VULNWL_INTEL(model, whitelist)		\
+	VULNWL(INTEL, 6, INTEL_FAM6_##model, whitelist)
+
+#define VULNWL_AMD(family, whitelist)		\
+	VULNWL(AMD, family, X86_MODEL_ANY, whitelist)
+
+#define VULNWL_HYGON(family, whitelist)		\
+	VULNWL(HYGON, family, X86_MODEL_ANY, whitelist)
+
+static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
+	VULNWL(ANY,	4, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(CENTAUR,	5, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(INTEL,	5, X86_MODEL_ANY,	NO_SPECULATION),
+	VULNWL(NSC,	5, X86_MODEL_ANY,	NO_SPECULATION),
+
+	/* Intel Family 6 */
+	VULNWL_INTEL(ATOM_SALTWELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_TABLET,	NO_SPECULATION),
+	VULNWL_INTEL(ATOM_SALTWELL_MID,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL,		NO_SPECULATION),
+	VULNWL_INTEL(ATOM_BONNELL_MID,		NO_SPECULATION),
+
+	VULNWL_INTEL(ATOM_SILVERMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT_X,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_SILVERMONT_MID,	NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(ATOM_AIRMONT,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(XEON_PHI_KNL,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+	VULNWL_INTEL(XEON_PHI_KNM,		NO_SSB | NO_L1TF | MSBDS_ONLY),
+
+	VULNWL_INTEL(CORE_YONAH,		NO_SSB),
+
+	VULNWL_INTEL(ATOM_AIRMONT_MID,		NO_L1TF | MSBDS_ONLY),
+
+	VULNWL_INTEL(ATOM_GOLDMONT,		NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT_X,		NO_MDS | NO_L1TF),
+	VULNWL_INTEL(ATOM_GOLDMONT_PLUS,	NO_MDS | NO_L1TF),
+
+	/* AMD Family 0xf - 0x12 */
+	VULNWL_AMD(0x0f,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x10,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x11,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+	VULNWL_AMD(0x12,	NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS),
+
+	/* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */
+	VULNWL_AMD(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
+	VULNWL_HYGON(X86_FAMILY_ANY,	NO_MELTDOWN | NO_L1TF | NO_MDS),
 	{}
 };
 
-static const __initconst struct x86_cpu_id cpu_no_meltdown[] = {
-	{ X86_VENDOR_AMD },
-	{ X86_VENDOR_HYGON },
-	{}
-};
-
-/* Only list CPUs which speculate but are non susceptible to SSB */
-static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_CORE_YONAH		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
-	{ X86_VENDOR_AMD,	0x12,					},
-	{ X86_VENDOR_AMD,	0x11,					},
-	{ X86_VENDOR_AMD,	0x10,					},
-	{ X86_VENDOR_AMD,	0xf,					},
-	{}
-};
+static bool __init cpu_matches(unsigned long which)
+{
+	const struct x86_cpu_id *m = x86_match_cpu(cpu_vuln_whitelist);
 
-static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
-	/* in addition to cpu_no_speculation */
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT_MID	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_X	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT_PLUS	},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
-	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
-	{}
-};
+	return m && !!(m->driver_data & which);
+}
 
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
 
-	if (x86_match_cpu(cpu_no_speculation))
+	if (cpu_matches(NO_SPECULATION))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_SPECTRE_V1);
@@ -1003,15 +1019,20 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	if (cpu_has(c, X86_FEATURE_ARCH_CAPABILITIES))
 		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap);
 
-	if (!x86_match_cpu(cpu_no_spec_store_bypass) &&
-	   !(ia32_cap & ARCH_CAP_SSB_NO) &&
+	if (!cpu_matches(NO_SSB) && !(ia32_cap & ARCH_CAP_SSB_NO) &&
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
 	if (ia32_cap & ARCH_CAP_IBRS_ALL)
 		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
 
-	if (x86_match_cpu(cpu_no_meltdown))
+	if (!cpu_matches(NO_MDS) && !(ia32_cap & ARCH_CAP_MDS_NO)) {
+		setup_force_cpu_bug(X86_BUG_MDS);
+		if (cpu_matches(MSBDS_ONLY))
+			setup_force_cpu_bug(X86_BUG_MSBDS_ONLY);
+	}
+
+	if (cpu_matches(NO_MELTDOWN))
 		return;
 
 	/* Rogue Data Cache Load? No! */
@@ -1020,7 +1041,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 
-	if (x86_match_cpu(cpu_no_l1tf))
+	if (cpu_matches(NO_L1TF))
 		return;
 
 	setup_force_cpu_bug(X86_BUG_L1TF);
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 3755d0310026..05b09896cfaf 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -35,6 +35,7 @@
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/cache.h>
+#include <asm/nospec-branch.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -551,6 +552,9 @@ nmi_restart:
 		write_cr2(this_cpu_read(nmi_cr2));
 	if (this_cpu_dec_return(nmi_state))
 		goto nmi_restart;
+
+	if (user_mode(regs))
+		mds_user_clear_cpu_buffers();
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 8b6d03e55d2f..7de466eb960b 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -58,6 +58,7 @@
 #include <asm/alternative.h>
 #include <asm/fpu/xstate.h>
 #include <asm/trace/mpx.h>
+#include <asm/nospec-branch.h>
 #include <asm/mpx.h>
 #include <asm/vm86.h>
 #include <asm/umip.h>
@@ -367,6 +368,13 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code)
 		regs->ip = (unsigned long)general_protection;
 		regs->sp = (unsigned long)&gpregs->orig_ax;
 
+		/*
+		 * This situation can be triggered by userspace via
+		 * modify_ldt(2) and the return does not take the regular
+		 * user space exit, so a CPU buffer clear is required when
+		 * MDS mitigation is enabled.
+		 */
+		mds_user_clear_cpu_buffers();
 		return;
 	}
 #endif