11 files changed, 401 insertions, 167 deletions

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index d879a6c93609..74c62cc47a5f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -41,8 +41,10 @@ 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);
-static void __init mds_print_mitigation(void);
+static void __init md_clear_update_mitigation(void);
+static void __init md_clear_select_mitigation(void);
 static void __init taa_select_mitigation(void);
+static void __init mmio_select_mitigation(void);
 static void __init srbds_select_mitigation(void);
 static void __init l1d_flush_select_mitigation(void);
 
@@ -85,6 +87,10 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
  */
 DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
 
+/* 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();
@@ -117,17 +123,10 @@ void __init check_bugs(void)
 	spectre_v2_select_mitigation();
 	ssb_select_mitigation();
 	l1tf_select_mitigation();
-	mds_select_mitigation();
-	taa_select_mitigation();
+	md_clear_select_mitigation();
 	srbds_select_mitigation();
 	l1d_flush_select_mitigation();
 
-	/*
-	 * As MDS and TAA mitigations are inter-related, print MDS
-	 * mitigation until after TAA mitigation selection is done.
-	 */
-	mds_print_mitigation();
-
 	arch_smt_update();
 
 #ifdef CONFIG_X86_32
@@ -267,14 +266,6 @@ static void __init mds_select_mitigation(void)
 	}
 }
 
-static void __init mds_print_mitigation(void)
-{
-	if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off())
-		return;
-
-	pr_info("%s\n", mds_strings[mds_mitigation]);
-}
-
 static int __init mds_cmdline(char *str)
 {
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
@@ -329,7 +320,7 @@ static void __init taa_select_mitigation(void)
 	/* TSX previously disabled by tsx=off */
 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
 		taa_mitigation = TAA_MITIGATION_TSX_DISABLED;
-		goto out;
+		return;
 	}
 
 	if (cpu_mitigations_off()) {
@@ -343,7 +334,7 @@ static void __init taa_select_mitigation(void)
 	 */
 	if (taa_mitigation == TAA_MITIGATION_OFF &&
 	    mds_mitigation == MDS_MITIGATION_OFF)
-		goto out;
+		return;
 
 	if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
 		taa_mitigation = TAA_MITIGATION_VERW;
@@ -375,18 +366,6 @@ static void __init taa_select_mitigation(void)
 
 	if (taa_nosmt || cpu_mitigations_auto_nosmt())
 		cpu_smt_disable(false);
-
-	/*
-	 * Update MDS mitigation, if necessary, as the mds_user_clear is
-	 * now enabled for TAA mitigation.
-	 */
-	if (mds_mitigation == MDS_MITIGATION_OFF &&
-	    boot_cpu_has_bug(X86_BUG_MDS)) {
-		mds_mitigation = MDS_MITIGATION_FULL;
-		mds_select_mitigation();
-	}
-out:
-	pr_info("%s\n", taa_strings[taa_mitigation]);
 }
 
 static int __init tsx_async_abort_parse_cmdline(char *str)
@@ -411,6 +390,151 @@ 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);
+
+	/*
+	 * If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can
+	 * be propagated to uncore buffers, clearing the Fill buffers on idle
+	 * is required irrespective of SMT state.
+	 */
+	if (!(ia32_cap & ARCH_CAP_FBSDP_NO))
+		static_branch_enable(&mds_idle_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)
+{
+	if (cpu_mitigations_off())
+		return;
+
+	if (!static_key_enabled(&mds_user_clear))
+		goto out;
+
+	/*
+	 * 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]);
+}
+
+static void __init md_clear_select_mitigation(void)
+{
+	mds_select_mitigation();
+	taa_select_mitigation();
+	mmio_select_mitigation();
+
+	/*
+	 * 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();
+}
+
+#undef pr_fmt
 #define pr_fmt(fmt)	"SRBDS: " fmt
 
 enum srbds_mitigations {
@@ -478,11 +602,13 @@ static void __init srbds_select_mitigation(void)
 		return;
 
 	/*
-	 * Check to see if this is one of the MDS_NO systems supporting
-	 * TSX that are only exposed to SRBDS when TSX is enabled.
+	 * Check to see if this is one of the MDS_NO systems supporting TSX that
+	 * are only exposed to SRBDS when TSX is enabled or when CPU is affected
+	 * by Processor MMIO Stale Data vulnerability.
 	 */
 	ia32_cap = x86_read_arch_cap_msr();
-	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM))
+	if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) &&
+	    !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
 		srbds_mitigation = SRBDS_MITIGATION_TSX_OFF;
 	else if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
@@ -1116,6 +1242,8 @@ static void update_indir_branch_cond(void)
 /* Update the static key controlling the MDS CPU buffer clear in idle */
 static void update_mds_branch_idle(void)
 {
+	u64 ia32_cap = x86_read_arch_cap_msr();
+
 	/*
 	 * Enable the idle clearing if SMT is active on CPUs which are
 	 * affected only by MSBDS and not any other MDS variant.
@@ -1127,14 +1255,17 @@ static void update_mds_branch_idle(void)
 	if (!boot_cpu_has_bug(X86_BUG_MSBDS_ONLY))
 		return;
 
-	if (sched_smt_active())
+	if (sched_smt_active()) {
 		static_branch_enable(&mds_idle_clear);
-	else
+	} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
+		   (ia32_cap & ARCH_CAP_FBSDP_NO)) {
 		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"
 #define TAA_MSG_SMT "TAA CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/tsx_async_abort.html for more details.\n"
+#define MMIO_MSG_SMT "MMIO Stale Data CPU bug present and SMT on, data leak possible. See https://www.kernel.org/doc/html/latest/admin-guide/hw-vuln/processor_mmio_stale_data.html for more details.\n"
 
 void cpu_bugs_smt_update(void)
 {
@@ -1179,6 +1310,16 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (mmio_mitigation) {
+	case MMIO_MITIGATION_VERW:
+	case MMIO_MITIGATION_UCODE_NEEDED:
+		if (sched_smt_active())
+			pr_warn_once(MMIO_MSG_SMT);
+		break;
+	case MMIO_MITIGATION_OFF:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -1781,6 +1922,20 @@ static ssize_t tsx_async_abort_show_state(char *buf)
 		       sched_smt_active() ? "vulnerable" : "disabled");
 }
 
+static ssize_t mmio_stale_data_show_state(char *buf)
+{
+	if (mmio_mitigation == MMIO_MITIGATION_OFF)
+		return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
+
+	if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+		return sysfs_emit(buf, "%s; SMT Host state unknown\n",
+				  mmio_strings[mmio_mitigation]);
+	}
+
+	return sysfs_emit(buf, "%s; SMT %s\n", mmio_strings[mmio_mitigation],
+			  sched_smt_active() ? "vulnerable" : "disabled");
+}
+
 static char *stibp_state(void)
 {
 	if (spectre_v2_in_eibrs_mode(spectre_v2_enabled))
@@ -1881,6 +2036,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_SRBDS:
 		return srbds_show_state(buf);
 
+	case X86_BUG_MMIO_STALE_DATA:
+		return mmio_stale_data_show_state(buf);
+
 	default:
 		break;
 	}
@@ -1932,4 +2090,9 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SRBDS);
 }
+
+ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2e9142797c99..4730b0a58f24 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1211,18 +1211,42 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 					    X86_FEATURE_ANY, issues)
 
 #define SRBDS		BIT(0)
+/* CPU is affected by X86_BUG_MMIO_STALE_DATA */
+#define MMIO		BIT(1)
+/* CPU is affected by Shared Buffers Data Sampling (SBDS), a variant of X86_BUG_MMIO_STALE_DATA */
+#define MMIO_SBDS	BIT(2)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPPINGS(IVYBRIDGE,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL,		X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL_L,	X86_STEPPING_ANY,		SRBDS),
 	VULNBL_INTEL_STEPPINGS(HASWELL_G,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(HASWELL_X,	BIT(2) | BIT(4),		MMIO),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_D,	X86_STEPPINGS(0x3, 0x5),	MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL_G,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(BROADWELL_X,	X86_STEPPING_ANY,		MMIO),
 	VULNBL_INTEL_STEPPINGS(BROADWELL,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPINGS(0x3, 0x3),	SRBDS | MMIO),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE_L,	X86_STEPPING_ANY,		SRBDS),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE_X,	BIT(3) | BIT(4) | BIT(6) |
+						BIT(7) | BIT(0xB),              MMIO),
+	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPINGS(0x3, 0x3),	SRBDS | MMIO),
 	VULNBL_INTEL_STEPPINGS(SKYLAKE,		X86_STEPPING_ANY,		SRBDS),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x0, 0xC),	SRBDS),
-	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x0, 0xD),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x9, 0xC),	SRBDS | MMIO),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE_L,	X86_STEPPINGS(0x0, 0x8),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x9, 0xD),	SRBDS | MMIO),
+	VULNBL_INTEL_STEPPINGS(KABYLAKE,	X86_STEPPINGS(0x0, 0x8),	SRBDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_L,	X86_STEPPINGS(0x5, 0x5),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_D,	X86_STEPPINGS(0x1, 0x1),	MMIO),
+	VULNBL_INTEL_STEPPINGS(ICELAKE_X,	X86_STEPPINGS(0x4, 0x6),	MMIO),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE,	BIT(2) | BIT(3) | BIT(5),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(COMETLAKE_L,	X86_STEPPINGS(0x0, 0x0),	MMIO),
+	VULNBL_INTEL_STEPPINGS(LAKEFIELD,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ROCKETLAKE,	X86_STEPPINGS(0x1, 0x1),	MMIO),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT,	X86_STEPPINGS(0x1, 0x1),	MMIO | MMIO_SBDS),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_D,	X86_STEPPING_ANY,		MMIO),
+	VULNBL_INTEL_STEPPINGS(ATOM_TREMONT_L,	X86_STEPPINGS(0x0, 0x0),	MMIO | MMIO_SBDS),
 	{}
 };
 
@@ -1243,6 +1267,13 @@ u64 x86_read_arch_cap_msr(void)
 	return ia32_cap;
 }
 
+static bool arch_cap_mmio_immune(u64 ia32_cap)
+{
+	return (ia32_cap & ARCH_CAP_FBSDP_NO &&
+		ia32_cap & ARCH_CAP_PSDP_NO &&
+		ia32_cap & ARCH_CAP_SBDR_SSDP_NO);
+}
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = x86_read_arch_cap_msr();
@@ -1296,12 +1327,27 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	/*
 	 * SRBDS affects CPUs which support RDRAND or RDSEED and are listed
 	 * in the vulnerability blacklist.
+	 *
+	 * Some of the implications and mitigation of Shared Buffers Data
+	 * Sampling (SBDS) are similar to SRBDS. Give SBDS same treatment as
+	 * SRBDS.
 	 */
 	if ((cpu_has(c, X86_FEATURE_RDRAND) ||
 	     cpu_has(c, X86_FEATURE_RDSEED)) &&
-	    cpu_matches(cpu_vuln_blacklist, SRBDS))
+	    cpu_matches(cpu_vuln_blacklist, SRBDS | MMIO_SBDS))
 		    setup_force_cpu_bug(X86_BUG_SRBDS);
 
+	/*
+	 * Processor MMIO Stale Data bug enumeration
+	 *
+	 * Affected CPU list is generally enough to enumerate the vulnerability,
+	 * but for virtualization case check for ARCH_CAP MSR bits also, VMM may
+	 * not want the guest to enumerate the bug.
+	 */
+	if (cpu_matches(cpu_vuln_blacklist, MMIO) &&
+	    !arch_cap_mmio_immune(ia32_cap))
+		setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
@@ -2222,6 +2268,7 @@ void cpu_init_secondary(void)
 }
 #endif
 
+#ifdef CONFIG_MICROCODE_LATE_LOADING
 /*
  * The microcode loader calls this upon late microcode load to recheck features,
  * only when microcode has been updated. Caller holds microcode_mutex and CPU
@@ -2251,6 +2298,7 @@ void microcode_check(void)
 	pr_warn("x86/CPU: CPU features have changed after loading microcode, but might not take effect.\n");
 	pr_warn("x86/CPU: Please consider either early loading through initrd/built-in or a potential BIOS update.\n");
 }
+#endif
 
 /*
  * Invoked from core CPU hotplug code after hotplug operations
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 239ff5fcec6a..ad57e0e4d674 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -373,101 +373,10 @@ static int apply_microcode_on_target(int cpu)
 	return ret;
 }
 
-#ifdef CONFIG_MICROCODE_OLD_INTERFACE
-static int do_microcode_update(const void __user *buf, size_t size)
-{
-	int error = 0;
-	int cpu;
-
-	for_each_online_cpu(cpu) {
-		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-		enum ucode_state ustate;
-
-		if (!uci->valid)
-			continue;
-
-		ustate = microcode_ops->request_microcode_user(cpu, buf, size);
-		if (ustate == UCODE_ERROR) {
-			error = -1;
-			break;
-		} else if (ustate == UCODE_NEW) {
-			apply_microcode_on_target(cpu);
-		}
-	}
-
-	return error;
-}
-
-static int microcode_open(struct inode *inode, struct file *file)
-{
-	return capable(CAP_SYS_RAWIO) ? stream_open(inode, file) : -EPERM;
-}
-
-static ssize_t microcode_write(struct file *file, const char __user *buf,
-			       size_t len, loff_t *ppos)
-{
-	ssize_t ret = -EINVAL;
-	unsigned long nr_pages = totalram_pages();
-
-	if ((len >> PAGE_SHIFT) > nr_pages) {
-		pr_err("too much data (max %ld pages)\n", nr_pages);
-		return ret;
-	}
-
-	cpus_read_lock();
-	mutex_lock(&microcode_mutex);
-
-	if (do_microcode_update(buf, len) == 0)
-		ret = (ssize_t)len;
-
-	if (ret > 0)
-		perf_check_microcode();
-
-	mutex_unlock(&microcode_mutex);
-	cpus_read_unlock();
-
-	return ret;
-}
-
-static const struct file_operations microcode_fops = {
-	.owner			= THIS_MODULE,
-	.write			= microcode_write,
-	.open			= microcode_open,
-	.llseek		= no_llseek,
-};
-
-static struct miscdevice microcode_dev = {
-	.minor			= MICROCODE_MINOR,
-	.name			= "microcode",
-	.nodename		= "cpu/microcode",
-	.fops			= &microcode_fops,
-};
-
-static int __init microcode_dev_init(void)
-{
-	int error;
-
-	error = misc_register(&microcode_dev);
-	if (error) {
-		pr_err("can't misc_register on minor=%d\n", MICROCODE_MINOR);
-		return error;
-	}
-
-	return 0;
-}
-
-static void __exit microcode_dev_exit(void)
-{
-	misc_deregister(&microcode_dev);
-}
-#else
-#define microcode_dev_init()	0
-#define microcode_dev_exit()	do { } while (0)
-#endif
-
 /* fake device for request_firmware */
 static struct platform_device	*microcode_pdev;
 
+#ifdef CONFIG_MICROCODE_LATE_LOADING
 /*
  * Late loading dance. Why the heavy-handed stomp_machine effort?
  *
@@ -584,6 +493,9 @@ static int microcode_reload_late(void)
 {
 	int ret;
 
+	pr_err("Attempting late microcode loading - it is dangerous and taints the kernel.\n");
+	pr_err("You should switch to early loading, if possible.\n");
+
 	atomic_set(&late_cpus_in,  0);
 	atomic_set(&late_cpus_out, 0);
 
@@ -632,9 +544,14 @@ put:
 	if (ret == 0)
 		ret = size;
 
+	add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+
 	return ret;
 }
 
+static DEVICE_ATTR_WO(reload);
+#endif
+
 static ssize_t version_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
@@ -651,7 +568,6 @@ static ssize_t pf_show(struct device *dev,
 	return sprintf(buf, "0x%x\n", uci->cpu_sig.pf);
 }
 
-static DEVICE_ATTR_WO(reload);
 static DEVICE_ATTR(version, 0444, version_show, NULL);
 static DEVICE_ATTR(processor_flags, 0444, pf_show, NULL);
 
@@ -804,7 +720,9 @@ static int mc_cpu_down_prep(unsigned int cpu)
 }
 
 static struct attribute *cpu_root_microcode_attrs[] = {
+#ifdef CONFIG_MICROCODE_LATE_LOADING
 	&dev_attr_reload.attr,
+#endif
 	NULL
 };
 
@@ -838,10 +756,7 @@ static int __init microcode_init(void)
 
 	cpus_read_lock();
 	mutex_lock(&microcode_mutex);
-
 	error = subsys_interface_register(&mc_cpu_interface);
-	if (!error)
-		perf_check_microcode();
 	mutex_unlock(&microcode_mutex);
 	cpus_read_unlock();
 
@@ -856,10 +771,6 @@ static int __init microcode_init(void)
 		goto out_driver;
 	}
 
-	error = microcode_dev_init();
-	if (error)
-		goto out_ucode_group;
-
 	register_syscore_ops(&mc_syscore_ops);
 	cpuhp_setup_state_nocalls(CPUHP_AP_MICROCODE_LOADER, "x86/microcode:starting",
 				  mc_cpu_starting, NULL);
@@ -870,10 +781,6 @@ static int __init microcode_init(void)
 
 	return 0;
 
- out_ucode_group:
-	sysfs_remove_group(&cpu_subsys.dev_root->kobj,
-			   &cpu_root_microcode_group);
-
  out_driver:
 	cpus_read_lock();
 	mutex_lock(&microcode_mutex);
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 3c24e6124d95..19876ebfb504 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -152,7 +152,7 @@ static int __sgx_encl_eldu(struct sgx_encl_page *encl_page,
 
 	page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
 
-	ret = sgx_encl_get_backing(encl, page_index, &b);
+	ret = sgx_encl_lookup_backing(encl, page_index, &b);
 	if (ret)
 		return ret;
 
@@ -718,7 +718,7 @@ static struct page *sgx_encl_get_backing_page(struct sgx_encl *encl,
  *   0 on success,
  *   -errno otherwise.
  */
-int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
+static int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
 			 struct sgx_backing *backing)
 {
 	pgoff_t page_pcmd_off = sgx_encl_get_backing_page_pcmd_offset(encl, page_index);
@@ -743,6 +743,107 @@ int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
 	return 0;
 }
 
+/*
+ * When called from ksgxd, returns the mem_cgroup of a struct mm stored
+ * in the enclave's mm_list. When not called from ksgxd, just returns
+ * the mem_cgroup of the current task.
+ */
+static struct mem_cgroup *sgx_encl_get_mem_cgroup(struct sgx_encl *encl)
+{
+	struct mem_cgroup *memcg = NULL;
+	struct sgx_encl_mm *encl_mm;
+	int idx;
+
+	/*
+	 * If called from normal task context, return the mem_cgroup
+	 * of the current task's mm. The remainder of the handling is for
+	 * ksgxd.
+	 */
+	if (!current_is_ksgxd())
+		return get_mem_cgroup_from_mm(current->mm);
+
+	/*
+	 * Search the enclave's mm_list to find an mm associated with
+	 * this enclave to charge the allocation to.
+	 */
+	idx = srcu_read_lock(&encl->srcu);
+
+	list_for_each_entry_rcu(encl_mm, &encl->mm_list, list) {
+		if (!mmget_not_zero(encl_mm->mm))
+			continue;
+
+		memcg = get_mem_cgroup_from_mm(encl_mm->mm);
+
+		mmput_async(encl_mm->mm);
+
+		break;
+	}
+
+	srcu_read_unlock(&encl->srcu, idx);
+
+	/*
+	 * In the rare case that there isn't an mm associated with
+	 * the enclave, set memcg to the current active mem_cgroup.
+	 * This will be the root mem_cgroup if there is no active
+	 * mem_cgroup.
+	 */
+	if (!memcg)
+		return get_mem_cgroup_from_mm(NULL);
+
+	return memcg;
+}
+
+/**
+ * sgx_encl_alloc_backing() - allocate a new backing storage page
+ * @encl:	an enclave pointer
+ * @page_index:	enclave page index
+ * @backing:	data for accessing backing storage for the page
+ *
+ * When called from ksgxd, sets the active memcg from one of the
+ * mms in the enclave's mm_list prior to any backing page allocation,
+ * in order to ensure that shmem page allocations are charged to the
+ * enclave.
+ *
+ * Return:
+ *   0 on success,
+ *   -errno otherwise.
+ */
+int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
+			   struct sgx_backing *backing)
+{
+	struct mem_cgroup *encl_memcg = sgx_encl_get_mem_cgroup(encl);
+	struct mem_cgroup *memcg = set_active_memcg(encl_memcg);
+	int ret;
+
+	ret = sgx_encl_get_backing(encl, page_index, backing);
+
+	set_active_memcg(memcg);
+	mem_cgroup_put(encl_memcg);
+
+	return ret;
+}
+
+/**
+ * sgx_encl_lookup_backing() - retrieve an existing backing storage page
+ * @encl:	an enclave pointer
+ * @page_index:	enclave page index
+ * @backing:	data for accessing backing storage for the page
+ *
+ * Retrieve a backing page for loading data back into an EPC page with ELDU.
+ * It is the caller's responsibility to ensure that it is appropriate to use
+ * sgx_encl_lookup_backing() rather than sgx_encl_alloc_backing(). If lookup is
+ * not used correctly, this will cause an allocation which is not accounted for.
+ *
+ * Return:
+ *   0 on success,
+ *   -errno otherwise.
+ */
+int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+			   struct sgx_backing *backing)
+{
+	return sgx_encl_get_backing(encl, page_index, backing);
+}
+
 /**
  * sgx_encl_put_backing() - Unpin the backing storage
  * @backing:	data for accessing backing storage for the page
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index d44e7372151f..332ef3568267 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -103,10 +103,13 @@ static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
 int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
 		     unsigned long end, unsigned long vm_flags);
 
+bool current_is_ksgxd(void);
 void sgx_encl_release(struct kref *ref);
 int sgx_encl_mm_add(struct sgx_encl *encl, struct mm_struct *mm);
-int sgx_encl_get_backing(struct sgx_encl *encl, unsigned long page_index,
-			 struct sgx_backing *backing);
+int sgx_encl_lookup_backing(struct sgx_encl *encl, unsigned long page_index,
+			    struct sgx_backing *backing);
+int sgx_encl_alloc_backing(struct sgx_encl *encl, unsigned long page_index,
+			   struct sgx_backing *backing);
 void sgx_encl_put_backing(struct sgx_backing *backing);
 int sgx_encl_test_and_clear_young(struct mm_struct *mm,
 				  struct sgx_encl_page *page);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index ab4ec54bbdd9..a78652d43e61 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -313,7 +313,7 @@ static void sgx_reclaimer_write(struct sgx_epc_page *epc_page,
 	sgx_encl_put_backing(backing);
 
 	if (!encl->secs_child_cnt && test_bit(SGX_ENCL_INITIALIZED, &encl->flags)) {
-		ret = sgx_encl_get_backing(encl, PFN_DOWN(encl->size),
+		ret = sgx_encl_alloc_backing(encl, PFN_DOWN(encl->size),
 					   &secs_backing);
 		if (ret)
 			goto out;
@@ -384,7 +384,7 @@ static void sgx_reclaim_pages(void)
 		page_index = PFN_DOWN(encl_page->desc - encl_page->encl->base);
 
 		mutex_lock(&encl_page->encl->lock);
-		ret = sgx_encl_get_backing(encl_page->encl, page_index, &backing[i]);
+		ret = sgx_encl_alloc_backing(encl_page->encl, page_index, &backing[i]);
 		if (ret) {
 			mutex_unlock(&encl_page->encl->lock);
 			goto skip;
@@ -475,6 +475,11 @@ static bool __init sgx_page_reclaimer_init(void)
 	return true;
 }
 
+bool current_is_ksgxd(void)
+{
+	return current == ksgxd_tsk;
+}
+
 static struct sgx_epc_page *__sgx_alloc_epc_page_from_node(int nid)
 {
 	struct sgx_numa_node *node = &sgx_numa_nodes[nid];
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0fdc807ae13f..0531d6a06df5 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -556,7 +556,7 @@ static inline void fpu_inherit_perms(struct fpu *dst_fpu)
 }
 
 /* Clone current's FPU state on fork */
-int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
+int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal)
 {
 	struct fpu *src_fpu = &current->thread.fpu;
 	struct fpu *dst_fpu = &dst->thread.fpu;
@@ -579,7 +579,7 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags)
 	 * No FPU state inheritance for kernel threads and IO
 	 * worker threads.
 	 */
-	if (dst->flags & (PF_KTHREAD | PF_IO_WORKER)) {
+	if (minimal) {
 		/* Clear out the minimal state */
 		memcpy(&dst_fpu->fpstate->regs, &init_fpstate.regs,
 		       init_fpstate_copy_size());
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index 566bb8e17149..0611fd83858e 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -376,9 +376,6 @@ void machine_kexec(struct kimage *image)
 #ifdef CONFIG_KEXEC_FILE
 void *arch_kexec_kernel_image_load(struct kimage *image)
 {
-	vfree(image->elf_headers);
-	image->elf_headers = NULL;
-
 	if (!image->fops || !image->fops->load)
 		return ERR_PTR(-ENOEXEC);
 
@@ -514,6 +511,15 @@ overflow:
 	       (int)ELF64_R_TYPE(rel[i].r_info), value);
 	return -ENOEXEC;
 }
+
+int arch_kimage_file_post_load_cleanup(struct kimage *image)
+{
+	vfree(image->elf_headers);
+	image->elf_headers = NULL;
+	image->elf_headers_sz = 0;
+
+	return kexec_image_post_load_cleanup_default(image);
+}
 #endif /* CONFIG_KEXEC_FILE */
 
 static int
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 58fb48d3004f..9b2772b7e1f3 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -131,9 +131,11 @@ static int set_new_tls(struct task_struct *p, unsigned long tls)
 		return do_set_thread_area_64(p, ARCH_SET_FS, tls);
 }
 
-int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
-		struct task_struct *p, unsigned long tls)
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
 {
+	unsigned long clone_flags = args->flags;
+	unsigned long sp = args->stack;
+	unsigned long tls = args->tls;
 	struct inactive_task_frame *frame;
 	struct fork_frame *fork_frame;
 	struct pt_regs *childregs;
@@ -171,13 +173,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	frame->flags = X86_EFLAGS_FIXED;
 #endif
 
-	fpu_clone(p, clone_flags);
+	fpu_clone(p, clone_flags, args->fn);
 
 	/* Kernel thread ? */
 	if (unlikely(p->flags & PF_KTHREAD)) {
 		p->thread.pkru = pkru_get_init_value();
 		memset(childregs, 0, sizeof(struct pt_regs));
-		kthread_frame_init(frame, sp, arg);
+		kthread_frame_init(frame, args->fn, args->fn_arg);
 		return 0;
 	}
 
@@ -193,10 +195,10 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 	if (sp)
 		childregs->sp = sp;
 
-	if (unlikely(p->flags & PF_IO_WORKER)) {
+	if (unlikely(args->fn)) {
 		/*
-		 * An IO thread is a user space thread, but it doesn't
-		 * return to ret_after_fork().
+		 * A user space thread, but it doesn't return to
+		 * ret_after_fork().
 		 *
 		 * In order to indicate that to tools like gdb,
 		 * we reset the stack and instruction pointers.
@@ -206,7 +208,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp, unsigned long arg,
 		 */
 		childregs->sp = 0;
 		childregs->ip = 0;
-		kthread_frame_init(frame, sp, arg);
+		kthread_frame_init(frame, args->fn, args->fn_arg);
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 249981bf3d8a..3ebb85327edb 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -903,18 +903,18 @@ void __init setup_arch(char **cmdline_p)
 
 #ifdef CONFIG_CMDLINE_BOOL
 #ifdef CONFIG_CMDLINE_OVERRIDE
-	strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+	strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
 #else
 	if (builtin_cmdline[0]) {
 		/* append boot loader cmdline to builtin */
 		strlcat(builtin_cmdline, " ", COMMAND_LINE_SIZE);
 		strlcat(builtin_cmdline, boot_command_line, COMMAND_LINE_SIZE);
-		strlcpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
+		strscpy(boot_command_line, builtin_cmdline, COMMAND_LINE_SIZE);
 	}
 #endif
 #endif
 
-	strlcpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
+	strscpy(command_line, boot_command_line, COMMAND_LINE_SIZE);
 	*cmdline_p = command_line;
 
 	/*
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 0f3c307b37b3..8e2b2552b5ee 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -180,8 +180,7 @@ void set_task_blockstep(struct task_struct *task, bool on)
 	 *
 	 * NOTE: this means that set/clear TIF_BLOCKSTEP is only safe if
 	 * task is current or it can't be running, otherwise we can race
-	 * with __switch_to_xtra(). We rely on ptrace_freeze_traced() but
-	 * PTRACE_KILL is not safe.
+	 * with __switch_to_xtra(). We rely on ptrace_freeze_traced().
 	 */
 	local_irq_disable();
 	debugctl = get_debugctlmsr();