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

Pull x86 CPU feature updates from Thomas Gleixner:
 "Updates for x86 CPU features:

   - Support for UMWAIT/UMONITOR, which allows to use MWAIT and MONITOR
     instructions in user space to save power e.g. in HPC workloads
     which spin wait on synchronization points.

     The maximum time a MWAIT can halt in userspace is controlled by the
     kernel and can be adjusted by the sysadmin.

   - Speed up the MTRR handling code on CPUs which support cache
     self-snooping correctly.

     On those CPUs the wbinvd() invocations can be omitted which speeds
     up the MTRR setup by a factor of 50.

   - Support for the new x86 vendor Zhaoxin who develops processors
     based on the VIA Centaur technology.

   - Prevent 'cat /proc/cpuinfo' from affecting isolated NOHZ_FULL CPUs
     by sending IPIs to retrieve the CPU frequency and use the cached
     values instead.

   - The addition and late revert of the FSGSBASE support. The revert
     was required as it turned out that the code still has hard to
     diagnose issues. Yet another engineering trainwreck...

   - Small fixes, cleanups, improvements and the usual new Intel CPU
     family/model addons"

* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits)
  x86/fsgsbase: Revert FSGSBASE support
  selftests/x86/fsgsbase: Fix some test case bugs
  x86/entry/64: Fix and clean up paranoid_exit
  x86/entry/64: Don't compile ignore_sysret if 32-bit emulation is enabled
  selftests/x86: Test SYSCALL and SYSENTER manually with TF set
  x86/mtrr: Skip cache flushes on CPUs with cache self-snooping
  x86/cpu/intel: Clear cache self-snoop capability in CPUs with known errata
  Documentation/ABI: Document umwait control sysfs interfaces
  x86/umwait: Add sysfs interface to control umwait maximum time
  x86/umwait: Add sysfs interface to control umwait C0.2 state
  x86/umwait: Initialize umwait control values
  x86/cpufeatures: Enumerate user wait instructions
  x86/cpu: Disable frequency requests via aperfmperf IPI for nohz_full CPUs
  x86/acpi/cstate: Add Zhaoxin processors support for cache flush policy in C3
  ACPI, x86: Add Zhaoxin processors support for NONSTOP TSC
  x86/cpu: Create Zhaoxin processors architecture support file
  x86/cpu: Split Tremont based Atoms from the rest
  Documentation/x86/64: Add documentation for GS/FS addressing mode
  x86/elf: Enumerate kernel FSGSBASE capability in AT_HWCAP2
  x86/cpu: Enable FSGSBASE on 64bit by default and add a chicken bit
  ...

29 files changed, 871 insertions, 88 deletions

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 1528239f69b2..923fe2001472 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -538,3 +538,26 @@ Description:	Intel Energy and Performance Bias Hint (EPB)
 
 		This attribute is present for all online CPUs supporting the
 		Intel EPB feature.
+
+What:		/sys/devices/system/cpu/umwait_control
+		/sys/devices/system/cpu/umwait_control/enable_c02
+		/sys/devices/system/cpu/umwait_control/max_time
+Date:		May 2019
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Umwait control
+
+		enable_c02: Read/write interface to control umwait C0.2 state
+			Read returns C0.2 state status:
+				0: C0.2 is disabled
+				1: C0.2 is enabled
+
+			Write 'y' or '1'  or 'on' to enable C0.2 state.
+			Write 'n' or '0'  or 'off' to disable C0.2 state.
+
+			The interface is case insensitive.
+
+		max_time: Read/write interface to control umwait maximum time
+			  in TSC-quanta that the CPU can reside in either C0.1
+			  or C0.2 state. The time is an unsigned 32-bit number.
+			  Note that a value of zero means there is no limit.
+			  Low order two bits must be zero.
diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index 18735dc460a0..0a18075c485e 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -31,7 +31,7 @@ you probably needn't concern yourself with isdn4k-utils.
 ====================== ===============  ========================================
 GNU C                  4.6              gcc --version
 GNU make               3.81             make --version
-binutils               2.20             ld -v
+binutils               2.21             ld -v
 flex                   2.5.35           flex --version
 bison                  2.0              bison --version
 util-linux             2.10o            fdformat --version
@@ -77,9 +77,7 @@ You will need GNU make 3.81 or later to build the kernel.
 Binutils
 --------
 
-The build system has, as of 4.13, switched to using thin archives (`ar T`)
-rather than incremental linking (`ld -r`) for built-in.a intermediate steps.
-This requires binutils 2.20 or newer.
+Binutils 2.21 or newer is needed to build the kernel.
 
 pkg-config
 ----------
diff --git a/MAINTAINERS b/MAINTAINERS
index 8b8a17349e4f..a2b97d38a704 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17523,6 +17523,12 @@ Q:	https://patchwork.linuxtv.org/project/linux-media/list/
 S:	Maintained
 F:	drivers/media/dvb-frontends/zd1301_demod*
 
+ZHAOXIN PROCESSOR SUPPORT
+M:	Tony W Wang-oc <TonyWWang-oc@zhaoxin.com>
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+F:	arch/x86/kernel/cpu/zhaoxin.c
+
 ZPOOL COMPRESSED PAGE STORAGE API
 M:	Dan Streetman <ddstreet@ieee.org>
 L:	linux-mm@kvack.org
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 6adce15268bd..8e29c991ba3e 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -480,3 +480,16 @@ config CPU_SUP_UMC_32
 	  CPU might render the kernel unbootable.
 
 	  If unsure, say N.
+
+config CPU_SUP_ZHAOXIN
+	default y
+	bool "Support Zhaoxin processors" if PROCESSOR_SELECT
+	help
+	  This enables detection, tunings and quirks for Zhaoxin processors
+
+	  You need this enabled if you want your kernel to run on a
+	  Zhaoxin CPU. Disabling this option on other types of CPUs
+	  makes the kernel a tiny bit smaller. Disabling it on a Zhaoxin
+	  CPU might render the kernel unbootable.
+
+	  If unsure, say N.
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8dbca86c249b..15f0749d0a15 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1692,11 +1692,17 @@ nmi_restore:
 	iretq
 END(nmi)
 
+#ifndef CONFIG_IA32_EMULATION
+/*
+ * This handles SYSCALL from 32-bit code.  There is no way to program
+ * MSRs to fully disable 32-bit SYSCALL.
+ */
 ENTRY(ignore_sysret)
 	UNWIND_HINT_EMPTY
 	mov	$-ENOSYS, %eax
 	sysret
 END(ignore_sysret)
+#endif
 
 ENTRY(rewind_stack_do_exit)
 	UNWIND_HINT_FUNC
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 9e3fbd47cb56..089bfcdf2f7f 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1400,6 +1400,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_MOBILE, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_KABYLAKE_DESKTOP, skl_uncore_init),
 	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_MOBILE, icl_uncore_init),
+	X86_UNCORE_MODEL_MATCH(INTEL_FAM6_ICELAKE_NNPI, icl_uncore_init),
 	{},
 };
 
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 1d337c51f7e6..58acda503817 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -22,8 +22,8 @@ enum cpuid_leafs
 	CPUID_LNX_3,
 	CPUID_7_0_EBX,
 	CPUID_D_1_EAX,
-	CPUID_F_0_EDX,
-	CPUID_F_1_EDX,
+	CPUID_LNX_4,
+	CPUID_7_1_EAX,
 	CPUID_8000_0008_EBX,
 	CPUID_6_EAX,
 	CPUID_8000_000A_EDX,
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 75f27ee2c263..998c2cc08363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -239,12 +239,14 @@
 #define X86_FEATURE_BMI1		( 9*32+ 3) /* 1st group bit manipulation extensions */
 #define X86_FEATURE_HLE			( 9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_AVX2		( 9*32+ 5) /* AVX2 instructions */
+#define X86_FEATURE_FDP_EXCPTN_ONLY	( 9*32+ 6) /* "" FPU data pointer updated only on x87 exceptions */
 #define X86_FEATURE_SMEP		( 9*32+ 7) /* Supervisor Mode Execution Protection */
 #define X86_FEATURE_BMI2		( 9*32+ 8) /* 2nd group bit manipulation extensions */
 #define X86_FEATURE_ERMS		( 9*32+ 9) /* Enhanced REP MOVSB/STOSB instructions */
 #define X86_FEATURE_INVPCID		( 9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM			( 9*32+11) /* Restricted Transactional Memory */
 #define X86_FEATURE_CQM			( 9*32+12) /* Cache QoS Monitoring */
+#define X86_FEATURE_ZERO_FCS_FDS	( 9*32+13) /* "" Zero out FPU CS and FPU DS */
 #define X86_FEATURE_MPX			( 9*32+14) /* Memory Protection Extension */
 #define X86_FEATURE_RDT_A		( 9*32+15) /* Resource Director Technology Allocation */
 #define X86_FEATURE_AVX512F		( 9*32+16) /* AVX-512 Foundation */
@@ -269,13 +271,19 @@
 #define X86_FEATURE_XGETBV1		(10*32+ 2) /* XGETBV with ECX = 1 instruction */
 #define X86_FEATURE_XSAVES		(10*32+ 3) /* XSAVES/XRSTORS instructions */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:0 (EDX), word 11 */
-#define X86_FEATURE_CQM_LLC		(11*32+ 1) /* LLC QoS if 1 */
+/*
+ * Extended auxiliary flags: Linux defined - for features scattered in various
+ * CPUID levels like 0xf, etc.
+ *
+ * Reuse free bits when adding new feature flags!
+ */
+#define X86_FEATURE_CQM_LLC		(11*32+ 0) /* LLC QoS if 1 */
+#define X86_FEATURE_CQM_OCCUP_LLC	(11*32+ 1) /* LLC occupancy monitoring */
+#define X86_FEATURE_CQM_MBM_TOTAL	(11*32+ 2) /* LLC Total MBM monitoring */
+#define X86_FEATURE_CQM_MBM_LOCAL	(11*32+ 3) /* LLC Local MBM monitoring */
 
-/* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (EDX), word 12 */
-#define X86_FEATURE_CQM_OCCUP_LLC	(12*32+ 0) /* LLC occupancy monitoring */
-#define X86_FEATURE_CQM_MBM_TOTAL	(12*32+ 1) /* LLC Total MBM monitoring */
-#define X86_FEATURE_CQM_MBM_LOCAL	(12*32+ 2) /* LLC Local MBM monitoring */
+/* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 #define X86_FEATURE_CLZERO		(13*32+ 0) /* CLZERO instruction */
@@ -322,6 +330,7 @@
 #define X86_FEATURE_UMIP		(16*32+ 2) /* User Mode Instruction Protection */
 #define X86_FEATURE_PKU			(16*32+ 3) /* Protection Keys for Userspace */
 #define X86_FEATURE_OSPKE		(16*32+ 4) /* OS Protection Keys Enable */
+#define X86_FEATURE_WAITPKG		(16*32+ 5) /* UMONITOR/UMWAIT/TPAUSE Instructions */
 #define X86_FEATURE_AVX512_VBMI2	(16*32+ 6) /* Additional AVX512 Vector Bit Manipulation Instructions */
 #define X86_FEATURE_GFNI		(16*32+ 8) /* Galois Field New Instructions */
 #define X86_FEATURE_VAES		(16*32+ 9) /* Vector AES */
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index 310118805f57..0278aa66ef62 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -56,6 +56,7 @@
 #define INTEL_FAM6_ICELAKE_XEON_D	0x6C
 #define INTEL_FAM6_ICELAKE_DESKTOP	0x7D
 #define INTEL_FAM6_ICELAKE_MOBILE	0x7E
+#define INTEL_FAM6_ICELAKE_NNPI		0x9D
 
 /* "Small Core" Processors (Atom) */
 
@@ -76,6 +77,7 @@
 #define INTEL_FAM6_ATOM_GOLDMONT	0x5C /* Apollo Lake */
 #define INTEL_FAM6_ATOM_GOLDMONT_X	0x5F /* Denverton */
 #define INTEL_FAM6_ATOM_GOLDMONT_PLUS	0x7A /* Gemini Lake */
+
 #define INTEL_FAM6_ATOM_TREMONT_X	0x86 /* Jacobsville */
 
 /* Xeon Phi */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 979ef971cc78..6b4fc2788078 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -61,6 +61,15 @@
 #define MSR_PLATFORM_INFO_CPUID_FAULT_BIT	31
 #define MSR_PLATFORM_INFO_CPUID_FAULT		BIT_ULL(MSR_PLATFORM_INFO_CPUID_FAULT_BIT)
 
+#define MSR_IA32_UMWAIT_CONTROL			0xe1
+#define MSR_IA32_UMWAIT_CONTROL_C02_DISABLE	BIT(0)
+#define MSR_IA32_UMWAIT_CONTROL_RESERVED	BIT(1)
+/*
+ * The time field is bit[31:2], but representing a 32bit value with
+ * bit[1:0] zero.
+ */
+#define MSR_IA32_UMWAIT_CONTROL_TIME_MASK	(~0x03U)
+
 #define MSR_PKG_CST_CONFIG_CONTROL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
 #define NHM_C1_AUTO_DEMOTE		(1UL << 26)
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index c34a35c78618..e57d2ca2ed87 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -144,7 +144,8 @@ enum cpuid_regs_idx {
 #define X86_VENDOR_TRANSMETA	7
 #define X86_VENDOR_NSC		8
 #define X86_VENDOR_HYGON	9
-#define X86_VENDOR_NUM		10
+#define X86_VENDOR_ZHAOXIN	10
+#define X86_VENDOR_NUM		11
 
 #define X86_VENDOR_UNKNOWN	0xff
 
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index a5e5484988fd..caf2edccbad2 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -64,6 +64,21 @@ void acpi_processor_power_init_bm_check(struct acpi_processor_flags *flags,
 		    c->x86_stepping >= 0x0e))
 			flags->bm_check = 1;
 	}
+
+	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
+		/*
+		 * All Zhaoxin CPUs that support C3 share cache.
+		 * And caches should not be flushed by software while
+		 * entering C3 type state.
+		 */
+		flags->bm_check = 1;
+		/*
+		 * On all recent Zhaoxin platforms, ARB_DISABLE is a nop.
+		 * So, set bm_control to zero to indicate that ARB_DISABLE
+		 * is not required while entering C3 type state.
+		 */
+		flags->bm_control = 0;
+	}
 }
 EXPORT_SYMBOL(acpi_processor_power_init_bm_check);
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5102bf7c8192..4b4eb06e117c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,6 +24,7 @@ obj-y			+= match.o
 obj-y			+= bugs.o
 obj-y			+= aperfmperf.o
 obj-y			+= cpuid-deps.o
+obj-y			+= umwait.o
 
 obj-$(CONFIG_PROC_FS)	+= proc.o
 obj-$(CONFIG_X86_FEATURE_NAMES) += capflags.o powerflags.o
@@ -38,6 +39,7 @@ obj-$(CONFIG_CPU_SUP_CYRIX_32)		+= cyrix.o
 obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
+obj-$(CONFIG_CPU_SUP_ZHAOXIN)		+= zhaoxin.o
 
 obj-$(CONFIG_X86_MCE)			+= mce/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index e71a6ff8a67e..e2f319dc992d 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -13,6 +13,7 @@
 #include <linux/percpu.h>
 #include <linux/cpufreq.h>
 #include <linux/smp.h>
+#include <linux/sched/isolation.h>
 
 #include "cpu.h"
 
@@ -85,6 +86,9 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		return 0;
+
 	aperfmperf_snapshot_cpu(cpu, ktime_get(), true);
 	return per_cpu(samples.khz, cpu);
 }
@@ -101,9 +105,12 @@ void arch_freq_prepare_all(void)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return;
 
-	for_each_online_cpu(cpu)
+	for_each_online_cpu(cpu) {
+		if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+			continue;
 		if (!aperfmperf_snapshot_cpu(cpu, now, false))
 			wait = true;
+	}
 
 	if (wait)
 		msleep(APERFMPERF_REFRESH_DELAY_MS);
@@ -117,6 +124,9 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
+	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		return 0;
+
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))
 		return per_cpu(samples.khz, cpu);
 
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index 395d46f78582..c7503be92f35 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -658,8 +658,7 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, int cpu, u8 node_id)
 	if (c->x86 < 0x17) {
 		/* LLC is at the node level. */
 		per_cpu(cpu_llc_id, cpu) = node_id;
-	} else if (c->x86 == 0x17 &&
-		   c->x86_model >= 0 && c->x86_model <= 0x1F) {
+	} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
 		/*
 		 * LLC is at the core complex level.
 		 * Core complex ID is ApicId[3] for these processors.
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 2c57fffebf9b..dad20bc891d5 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -801,6 +801,30 @@ static void init_speculation_control(struct cpuinfo_x86 *c)
 	}
 }
 
+static void init_cqm(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_CQM_LLC)) {
+		c->x86_cache_max_rmid  = -1;
+		c->x86_cache_occ_scale = -1;
+		return;
+	}
+
+	/* will be overridden if occupancy monitoring exists */
+	c->x86_cache_max_rmid = cpuid_ebx(0xf);
+
+	if (cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL) ||
+	    cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)) {
+		u32 eax, ebx, ecx, edx;
+
+		/* QoS sub-leaf, EAX=0Fh, ECX=1 */
+		cpuid_count(0xf, 1, &eax, &ebx, &ecx, &edx);
+
+		c->x86_cache_max_rmid  = ecx;
+		c->x86_cache_occ_scale = ebx;
+	}
+}
+
 void get_cpu_cap(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
@@ -823,6 +847,12 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 		c->x86_capability[CPUID_7_ECX] = ecx;
 		c->x86_capability[CPUID_7_EDX] = edx;
+
+		/* Check valid sub-leaf index before accessing it */
+		if (eax >= 1) {
+			cpuid_count(0x00000007, 1, &eax, &ebx, &ecx, &edx);
+			c->x86_capability[CPUID_7_1_EAX] = eax;
+		}
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -832,33 +862,6 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_D_1_EAX] = eax;
 	}
 
-	/* Additional Intel-defined flags: level 0x0000000F */
-	if (c->cpuid_level >= 0x0000000F) {
-
-		/* QoS sub-leaf, EAX=0Fh, ECX=0 */
-		cpuid_count(0x0000000F, 0, &eax, &ebx, &ecx, &edx);
-		c->x86_capability[CPUID_F_0_EDX] = edx;
-
-		if (cpu_has(c, X86_FEATURE_CQM_LLC)) {
-			/* will be overridden if occupancy monitoring exists */
-			c->x86_cache_max_rmid = ebx;
-
-			/* QoS sub-leaf, EAX=0Fh, ECX=1 */
-			cpuid_count(0x0000000F, 1, &eax, &ebx, &ecx, &edx);
-			c->x86_capability[CPUID_F_1_EDX] = edx;
-
-			if ((cpu_has(c, X86_FEATURE_CQM_OCCUP_LLC)) ||
-			      ((cpu_has(c, X86_FEATURE_CQM_MBM_TOTAL)) ||
-			       (cpu_has(c, X86_FEATURE_CQM_MBM_LOCAL)))) {
-				c->x86_cache_max_rmid = ecx;
-				c->x86_cache_occ_scale = ebx;
-			}
-		} else {
-			c->x86_cache_max_rmid = -1;
-			c->x86_cache_occ_scale = -1;
-		}
-	}
-
 	/* AMD-defined flags: level 0x80000001 */
 	eax = cpuid_eax(0x80000000);
 	c->extended_cpuid_level = eax;
@@ -889,6 +892,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 
 	init_scattered_cpuid_features(c);
 	init_speculation_control(c);
+	init_cqm(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, after probe.
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index e794e3860fc8..b5353244749b 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -64,6 +64,10 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AVX512_4VNNIW,	X86_FEATURE_AVX512F   },
 	{ X86_FEATURE_AVX512_4FMAPS,	X86_FEATURE_AVX512F   },
 	{ X86_FEATURE_AVX512_VPOPCNTDQ, X86_FEATURE_AVX512F   },
+	{ X86_FEATURE_CQM_OCCUP_LLC,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_CQM_MBM_TOTAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_CQM_MBM_LOCAL,	X86_FEATURE_CQM_LLC   },
+	{ X86_FEATURE_AVX512_BF16,	X86_FEATURE_AVX512VL  },
 	{}
 };
 
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f17c1a714779..8d6d92ebeb54 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -66,6 +66,32 @@ void check_mpx_erratum(struct cpuinfo_x86 *c)
 	}
 }
 
+/*
+ * Processors which have self-snooping capability can handle conflicting
+ * memory type across CPUs by snooping its own cache. However, there exists
+ * CPU models in which having conflicting memory types still leads to
+ * unpredictable behavior, machine check errors, or hangs. Clear this
+ * feature to prevent its use on machines with known erratas.
+ */
+static void check_memory_type_self_snoop_errata(struct cpuinfo_x86 *c)
+{
+	switch (c->x86_model) {
+	case INTEL_FAM6_CORE_YONAH:
+	case INTEL_FAM6_CORE2_MEROM:
+	case INTEL_FAM6_CORE2_MEROM_L:
+	case INTEL_FAM6_CORE2_PENRYN:
+	case INTEL_FAM6_CORE2_DUNNINGTON:
+	case INTEL_FAM6_NEHALEM:
+	case INTEL_FAM6_NEHALEM_G:
+	case INTEL_FAM6_NEHALEM_EP:
+	case INTEL_FAM6_NEHALEM_EX:
+	case INTEL_FAM6_WESTMERE:
+	case INTEL_FAM6_WESTMERE_EP:
+	case INTEL_FAM6_SANDYBRIDGE:
+		setup_clear_cpu_cap(X86_FEATURE_SELFSNOOP);
+	}
+}
+
 static bool ring3mwait_disabled __read_mostly;
 
 static int __init ring3mwait_disable(char *__unused)
@@ -304,6 +330,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_mpx_erratum(c);
+	check_memory_type_self_snoop_errata(c);
 
 	/*
 	 * Get the number of SMT siblings early from the extended topology
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 9356c1c9024d..aa5c064a6a22 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -743,7 +743,15 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 	/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
 	cr0 = read_cr0() | X86_CR0_CD;
 	write_cr0(cr0);
-	wbinvd();
+
+	/*
+	 * Cache flushing is the most time-consuming step when programming
+	 * the MTRRs. Fortunately, as per the Intel Software Development
+	 * Manual, we can skip it if the processor supports cache self-
+	 * snooping.
+	 */
+	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+		wbinvd();
 
 	/* Save value of CR4 and clear Page Global Enable (bit 7) */
 	if (boot_cpu_has(X86_FEATURE_PGE)) {
@@ -760,7 +768,10 @@ static void prepare_set(void) __acquires(set_atomicity_lock)
 
 	/* Disable MTRRs, and set the default type to uncached */
 	mtrr_wrmsr(MSR_MTRRdefType, deftype_lo & ~0xcff, deftype_hi);
-	wbinvd();
+
+	/* Again, only flush caches if we have to. */
+	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+		wbinvd();
 }
 
 static void post_set(void) __releases(set_atomicity_lock)
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 94aa1c72ca98..adf9b71386ef 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -26,6 +26,10 @@ struct cpuid_bit {
 static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_APERFMPERF,       CPUID_ECX,  0, 0x00000006, 0 },
 	{ X86_FEATURE_EPB,		CPUID_ECX,  3, 0x00000006, 0 },
+	{ X86_FEATURE_CQM_LLC,		CPUID_EDX,  1, 0x0000000f, 0 },
+	{ X86_FEATURE_CQM_OCCUP_LLC,	CPUID_EDX,  0, 0x0000000f, 1 },
+	{ X86_FEATURE_CQM_MBM_TOTAL,	CPUID_EDX,  1, 0x0000000f, 1 },
+	{ X86_FEATURE_CQM_MBM_LOCAL,	CPUID_EDX,  2, 0x0000000f, 1 },
 	{ X86_FEATURE_CAT_L3,		CPUID_EBX,  1, 0x00000010, 0 },
 	{ X86_FEATURE_CAT_L2,		CPUID_EBX,  2, 0x00000010, 0 },
 	{ X86_FEATURE_CDP_L3,		CPUID_ECX,  2, 0x00000010, 1 },
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
new file mode 100644
index 000000000000..6a204e7336c1
--- /dev/null
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/syscore_ops.h>
+#include <linux/suspend.h>
+#include <linux/cpu.h>
+
+#include <asm/msr.h>
+
+#define UMWAIT_C02_ENABLE	0
+
+#define UMWAIT_CTRL_VAL(max_time, c02_disable)				\
+	(((max_time) & MSR_IA32_UMWAIT_CONTROL_TIME_MASK) |		\
+	((c02_disable) & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE))
+
+/*
+ * Cache IA32_UMWAIT_CONTROL MSR. This is a systemwide control. By default,
+ * umwait max time is 100000 in TSC-quanta and C0.2 is enabled
+ */
+static u32 umwait_control_cached = UMWAIT_CTRL_VAL(100000, UMWAIT_C02_ENABLE);
+
+/*
+ * Serialize access to umwait_control_cached and IA32_UMWAIT_CONTROL MSR in
+ * the sysfs write functions.
+ */
+static DEFINE_MUTEX(umwait_lock);
+
+static void umwait_update_control_msr(void * unused)
+{
+	lockdep_assert_irqs_disabled();
+	wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+}
+
+/*
+ * The CPU hotplug callback sets the control MSR to the global control
+ * value.
+ *
+ * Disable interrupts so the read of umwait_control_cached and the WRMSR
+ * are protected against a concurrent sysfs write. Otherwise the sysfs
+ * write could update the cached value after it had been read on this CPU
+ * and issue the IPI before the old value had been written. The IPI would
+ * interrupt, write the new value and after return from IPI the previous
+ * value would be written by this CPU.
+ *
+ * With interrupts disabled the upcoming CPU either sees the new control
+ * value or the IPI is updating this CPU to the new control value after
+ * interrupts have been reenabled.
+ */
+static int umwait_cpu_online(unsigned int cpu)
+{
+	local_irq_disable();
+	umwait_update_control_msr(NULL);
+	local_irq_enable();
+	return 0;
+}
+
+/*
+ * On resume, restore IA32_UMWAIT_CONTROL MSR on the boot processor which
+ * is the only active CPU at this time. The MSR is set up on the APs via the
+ * CPU hotplug callback.
+ *
+ * This function is invoked on resume from suspend and hibernation. On
+ * resume from suspend the restore should be not required, but we neither
+ * trust the firmware nor does it matter if the same value is written
+ * again.
+ */
+static void umwait_syscore_resume(void)
+{
+	umwait_update_control_msr(NULL);
+}
+
+static struct syscore_ops umwait_syscore_ops = {
+	.resume	= umwait_syscore_resume,
+};
+
+/* sysfs interface */
+
+/*
+ * When bit 0 in IA32_UMWAIT_CONTROL MSR is 1, C0.2 is disabled.
+ * Otherwise, C0.2 is enabled.
+ */
+static inline bool umwait_ctrl_c02_enabled(u32 ctrl)
+{
+	return !(ctrl & MSR_IA32_UMWAIT_CONTROL_C02_DISABLE);
+}
+
+static inline u32 umwait_ctrl_max_time(u32 ctrl)
+{
+	return ctrl & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+}
+
+static inline void umwait_update_control(u32 maxtime, bool c02_enable)
+{
+	u32 ctrl = maxtime & MSR_IA32_UMWAIT_CONTROL_TIME_MASK;
+
+	if (!c02_enable)
+		ctrl |= MSR_IA32_UMWAIT_CONTROL_C02_DISABLE;
+
+	WRITE_ONCE(umwait_control_cached, ctrl);
+	/* Propagate to all CPUs */
+	on_each_cpu(umwait_update_control_msr, NULL, 1);
+}
+
+static ssize_t
+enable_c02_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	u32 ctrl = READ_ONCE(umwait_control_cached);
+
+	return sprintf(buf, "%d\n", umwait_ctrl_c02_enabled(ctrl));
+}
+
+static ssize_t enable_c02_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	bool c02_enable;
+	u32 ctrl;
+	int ret;
+
+	ret = kstrtobool(buf, &c02_enable);
+	if (ret)
+		return ret;
+
+	mutex_lock(&umwait_lock);
+
+	ctrl = READ_ONCE(umwait_control_cached);
+	if (c02_enable != umwait_ctrl_c02_enabled(ctrl))
+		umwait_update_control(ctrl, c02_enable);
+
+	mutex_unlock(&umwait_lock);
+
+	return count;
+}
+static DEVICE_ATTR_RW(enable_c02);
+
+static ssize_t
+max_time_show(struct device *k