23 files changed, 424 insertions, 100 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b1b78ffe01d0..616ebd22ef9a 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -16,9 +16,21 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_early_printk.o = -pg
 endif
 
-KASAN_SANITIZE_head$(BITS).o := n
-KASAN_SANITIZE_dumpstack.o := n
-KASAN_SANITIZE_dumpstack_$(BITS).o := n
+KASAN_SANITIZE_head$(BITS).o				:= n
+KASAN_SANITIZE_dumpstack.o				:= n
+KASAN_SANITIZE_dumpstack_$(BITS).o			:= n
+KASAN_SANITIZE_stacktrace.o := n
+
+OBJECT_FILES_NON_STANDARD_head_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_relocate_kernel_$(BITS).o	:= y
+OBJECT_FILES_NON_STANDARD_mcount_$(BITS).o		:= y
+OBJECT_FILES_NON_STANDARD_test_nx.o			:= y
+
+# If instrumentation of this dir is enabled, boot hangs during first second.
+# Probably could be more selective here, but note that files related to irqs,
+# boot, dumpstack/stacktrace, etc are either non-interesting or can lead to
+# non-deterministic coverage.
+KCOV_INSTRUMENT		:= n
 
 CFLAGS_irq.o := -I$(src)/../include/asm/trace
 
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8c35df468104..169963f471bb 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -5,6 +5,7 @@
 #include <asm/page_types.h>
 #include <asm/msr.h>
 #include <asm/asm-offsets.h>
+#include <asm/frame.h>
 
 # Copyright 2003 Pavel Machek <pavel@suse.cz>, distribute under GPLv2
 
@@ -39,6 +40,7 @@ bogus_64_magic:
 	jmp	bogus_64_magic
 
 ENTRY(do_suspend_lowlevel)
+	FRAME_BEGIN
 	subq	$8, %rsp
 	xorl	%eax, %eax
 	call	save_processor_state
@@ -109,6 +111,7 @@ ENTRY(do_suspend_lowlevel)
 
 	xorl	%eax, %eax
 	addq	$8, %rsp
+	FRAME_END
 	jmp	restore_processor_state
 ENDPROC(do_suspend_lowlevel)
 
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 29fa475ec518..a147e676fc7b 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -170,15 +170,13 @@ int amd_get_subcaches(int cpu)
 {
 	struct pci_dev *link = node_to_amd_nb(amd_get_nb_id(cpu))->link;
 	unsigned int mask;
-	int cuid;
 
 	if (!amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
 		return 0;
 
 	pci_read_config_dword(link, 0x1d4, &mask);
 
-	cuid = cpu_data(cpu).compute_unit_id;
-	return (mask >> (4 * cuid)) & 0xf;
+	return (mask >> (4 * cpu_data(cpu).cpu_core_id)) & 0xf;
 }
 
 int amd_set_subcaches(int cpu, unsigned long mask)
@@ -204,7 +202,7 @@ int amd_set_subcaches(int cpu, unsigned long mask)
 		pci_write_config_dword(nb->misc, 0x1b8, reg & ~0x180000);
 	}
 
-	cuid = cpu_data(cpu).compute_unit_id;
+	cuid = cpu_data(cpu).cpu_core_id;
 	mask <<= 4 * cuid;
 	mask |= (0xf ^ (1 << cuid)) << 26;
 
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 6e85f713641d..0a2bb1f62e72 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -227,19 +227,11 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp)
 	return 0;
 }
 
-static int gart_fix_e820 __initdata = 1;
+static bool gart_fix_e820 __initdata = true;
 
 static int __init parse_gart_mem(char *p)
 {
-	if (!p)
-		return -EINVAL;
-
-	if (!strncmp(p, "off", 3))
-		gart_fix_e820 = 0;
-	else if (!strncmp(p, "on", 2))
-		gart_fix_e820 = 1;
-
-	return 0;
+	return kstrtobool(p, &gart_fix_e820);
 }
 early_param("gart_fix_e820", parse_gart_mem);
 
diff --git a/arch/x86/kernel/apic/Makefile b/arch/x86/kernel/apic/Makefile
index 8bb12ddc5db8..8e63ebdcbd0b 100644
--- a/arch/x86/kernel/apic/Makefile
+++ b/arch/x86/kernel/apic/Makefile
@@ -2,6 +2,10 @@
 # Makefile for local APIC drivers and for the IO-APIC code
 #
 
+# Leads to non-deterministic coverage that is not a function of syscall inputs.
+# In particualr, smp_apic_timer_interrupt() is called in random places.
+KCOV_INSTRUMENT		:= n
+
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o apic_noop.o ipi.o vector.o
 obj-y				+= hw_nmi.o
 
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 0d373d7affc8..4a8697f7d4ef 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -8,6 +8,10 @@ CFLAGS_REMOVE_common.o = -pg
 CFLAGS_REMOVE_perf_event.o = -pg
 endif
 
+# If these files are instrumented, boot hangs during the first second.
+KCOV_INSTRUMENT_common.o := n
+KCOV_INSTRUMENT_perf_event.o := n
+
 # Make sure load_percpu_segment has no stackprotector
 nostackp := $(call cc-option, -fno-stack-protector)
 CFLAGS_common.o		:= $(nostackp)
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 68fe8d3bed56..7b76eb67a9b3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -75,7 +75,10 @@ static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
  */
 
 extern __visible void vide(void);
-__asm__(".globl vide\n\t.align 4\nvide: ret");
+__asm__(".globl vide\n"
+	".type vide, @function\n"
+	".align 4\n"
+	"vide: ret\n");
 
 static void init_amd_k5(struct cpuinfo_x86 *c)
 {
@@ -297,7 +300,6 @@ static int nearby_node(int apicid)
 #ifdef CONFIG_SMP
 static void amd_get_topology(struct cpuinfo_x86 *c)
 {
-	u32 cores_per_cu = 1;
 	u8 node_id;
 	int cpu = smp_processor_id();
 
@@ -310,8 +312,8 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 		/* get compute unit information */
 		smp_num_siblings = ((ebx >> 8) & 3) + 1;
-		c->compute_unit_id = ebx & 0xff;
-		cores_per_cu += ((ebx >> 8) & 3);
+		c->x86_max_cores /= smp_num_siblings;
+		c->cpu_core_id = ebx & 0xff;
 	} else if (cpu_has(c, X86_FEATURE_NODEID_MSR)) {
 		u64 value;
 
@@ -322,19 +324,16 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 
 	/* fixup multi-node processor information */
 	if (nodes_per_socket > 1) {
-		u32 cores_per_node;
 		u32 cus_per_node;
 
 		set_cpu_cap(c, X86_FEATURE_AMD_DCM);
-		cores_per_node = c->x86_max_cores / nodes_per_socket;
-		cus_per_node = cores_per_node / cores_per_cu;
+		cus_per_node = c->x86_max_cores / nodes_per_socket;
 
 		/* store NodeID, use llc_shared_map to store sibling info */
 		per_cpu(cpu_llc_id, cpu) = node_id;
 
 		/* core id has to be in the [0 .. cores_per_node - 1] range */
-		c->cpu_core_id %= cores_per_node;
-		c->compute_unit_id %= cus_per_node;
+		c->cpu_core_id %= cus_per_node;
 	}
 }
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e601c1286e29..8394b3d1f94f 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -304,6 +304,48 @@ static __always_inline void setup_smap(struct cpuinfo_x86 *c)
 }
 
 /*
+ * Protection Keys are not available in 32-bit mode.
+ */
+static bool pku_disabled;
+
+static __always_inline void setup_pku(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has(c, X86_FEATURE_PKU))
+		return;
+	if (pku_disabled)
+		return;
+
+	cr4_set_bits(X86_CR4_PKE);
+	/*
+	 * Seting X86_CR4_PKE will cause the X86_FEATURE_OSPKE
+	 * cpuid bit to be set.  We need to ensure that we
+	 * update that bit in this CPU's "cpu_info".
+	 */
+	get_cpu_cap(c);
+}
+
+#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
+static __init int setup_disable_pku(char *arg)
+{
+	/*
+	 * Do not clear the X86_FEATURE_PKU bit.  All of the
+	 * runtime checks are against OSPKE so clearing the
+	 * bit does nothing.
+	 *
+	 * This way, we will see "pku" in cpuinfo, but not
+	 * "ospke", which is exactly what we want.  It shows
+	 * that the CPU has PKU, but the OS has not enabled it.
+	 * This happens to be exactly how a system would look
+	 * if we disabled the config option.
+	 */
+	pr_info("x86: 'nopku' specified, disabling Memory Protection Keys\n");
+	pku_disabled = true;
+	return 1;
+}
+__setup("nopku", setup_disable_pku);
+#endif /* CONFIG_X86_64 */
+
+/*
  * Some CPU features depend on higher CPUID levels, which may not always
  * be available due to CPUID level capping or broken virtualization
  * software.  Add those features to this table to auto-disable them.
@@ -625,6 +667,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 		c->x86_capability[CPUID_7_0_EBX] = ebx;
 
 		c->x86_capability[CPUID_6_EAX] = cpuid_eax(0x00000006);
+		c->x86_capability[CPUID_7_ECX] = ecx;
 	}
 
 	/* Extended state features: level 0x0000000d */
@@ -984,6 +1027,7 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	init_hypervisor(c);
 	x86_init_rdrand(c);
 	x86_init_cache_qos(c);
+	setup_pku(c);
 
 	/*
 	 * Clear/Set all flags overridden by options, need do it
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 0b445c2ff735..ac780cad3b86 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -384,6 +384,9 @@ static void intel_thermal_interrupt(void)
 {
 	__u64 msr_val;
 
+	if (static_cpu_has(X86_FEATURE_HWP))
+		wrmsrl_safe(MSR_HWP_STATUS, 0);
+
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
 	/* Check for violation of core thermal thresholds*/
diff --git a/arch/x86/kernel/cpu/powerflags.c b/arch/x86/kernel/cpu/powerflags.c
index 31f0f335ed22..1dd8294fd730 100644
--- a/arch/x86/kernel/cpu/powerflags.c
+++ b/arch/x86/kernel/cpu/powerflags.c
@@ -18,4 +18,6 @@ const char *const x86_power_flags[32] = {
 	"",	/* tsc invariant mapped to constant_tsc */
 	"cpb",  /* core performance boost */
 	"eff_freq_ro", /* Readonly aperf/mperf */
+	"proc_feedback", /* processor feedback interface */
+	"acc_power", /* accumulated power mechanism */
 };
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 9c30acfadae2..8efa57a5f29e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -135,7 +135,8 @@ print_context_stack_bp(struct thread_info *tinfo,
 		if (!__kernel_text_address(addr))
 			break;
 
-		ops->address(data, addr, 1);
+		if (ops->address(data, addr, 1))
+			break;
 		frame = frame->next_frame;
 		ret_addr = &frame->return_address;
 		print_ftrace_graph_addr(addr, data, ops, tinfo, graph);
@@ -154,10 +155,11 @@ static int print_trace_stack(void *data, char *name)
 /*
  * Print one address/symbol entries per line.
  */
-static void print_trace_address(void *data, unsigned long addr, int reliable)
+static int print_trace_address(void *data, unsigned long addr, int reliable)
 {
 	touch_nmi_watchdog();
 	printk_stack_address(addr, reliable, data);
+	return 0;
 }
 
 static const struct stacktrace_ops print_trace_ops = {
@@ -265,9 +267,8 @@ int __die(const char *str, struct pt_regs *regs, long err)
 #ifdef CONFIG_SMP
 	printk("SMP ");
 #endif
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk("DEBUG_PAGEALLOC ");
-#endif
+	if (debug_pagealloc_enabled())
+		printk("DEBUG_PAGEALLOC ");
 #ifdef CONFIG_KASAN
 	printk("KASAN");
 #endif
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 0b1b9abd4d5f..8e37cc8a539a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -354,6 +354,69 @@ void fpu__activate_fpstate_write(struct fpu *fpu)
 }
 
 /*
+ * This function must be called before we write the current
+ * task's fpstate.
+ *
+ * This call gets the current FPU register state and moves
+ * it in to the 'fpstate'.  Preemption is disabled so that
+ * no writes to the 'fpstate' can occur from context
+ * swiches.
+ *
+ * Must be followed by a fpu__current_fpstate_write_end().
+ */
+void fpu__current_fpstate_write_begin(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	/*
+	 * Ensure that the context-switching code does not write
+	 * over the fpstate while we are doing our update.
+	 */
+	preempt_disable();
+
+	/*
+	 * Move the fpregs in to the fpu's 'fpstate'.
+	 */
+	fpu__activate_fpstate_read(fpu);
+
+	/*
+	 * The caller is about to write to 'fpu'.  Ensure that no
+	 * CPU thinks that its fpregs match the fpstate.  This
+	 * ensures we will not be lazy and skip a XRSTOR in the
+	 * future.
+	 */
+	fpu->last_cpu = -1;
+}
+
+/*
+ * This function must be paired with fpu__current_fpstate_write_begin()
+ *
+ * This will ensure that the modified fpstate gets placed back in
+ * the fpregs if necessary.
+ *
+ * Note: This function may be called whether or not an _actual_
+ * write to the fpstate occurred.
+ */
+void fpu__current_fpstate_write_end(void)
+{
+	struct fpu *fpu = &current->thread.fpu;
+
+	/*
+	 * 'fpu' now has an updated copy of the state, but the
+	 * registers may still be out of date.  Update them with
+	 * an XRSTOR if they are active.
+	 */
+	if (fpregs_active())
+		copy_kernel_to_fpregs(&fpu->state);
+
+	/*
+	 * Our update is done and the fpregs/fpstate are in sync
+	 * if necessary.  Context switches can happen again.
+	 */
+	preempt_enable();
+}
+
+/*
  * 'fpu__restore()' is called to copy FPU registers from
  * the FPU fpstate to the live hw registers and to activate
  * access to the hardware registers, so that FPU instructions
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6e8354f5a593..b48ef35b28d4 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -5,6 +5,7 @@
  */
 #include <linux/compat.h>
 #include <linux/cpu.h>
+#include <linux/pkeys.h>
 
 #include <asm/fpu/api.h>
 #include <asm/fpu/internal.h>
@@ -13,6 +14,11 @@
 
 #include <asm/tlbflush.h>
 
+/*
+ * Although we spell it out in here, the Processor Trace
+ * xfeature is completely unused.  We use other mechanisms
+ * to save/restore PT state in Linux.
+ */
 static const char *xfeature_names[] =
 {
 	"x87 floating point registers"	,
@@ -23,6 +29,8 @@ static const char *xfeature_names[] =
 	"AVX-512 opmask"		,
 	"AVX-512 Hi256"			,
 	"AVX-512 ZMM_Hi256"		,
+	"Processor Trace (unused)"	,
+	"Protection Keys User registers",
 	"unknown xstate feature"	,
 };
 
@@ -56,6 +64,7 @@ void fpu__xstate_clear_all_cpu_caps(void)
 	setup_clear_cpu_cap(X86_FEATURE_AVX512VL);
 	setup_clear_cpu_cap(X86_FEATURE_MPX);
 	setup_clear_cpu_cap(X86_FEATURE_XGETBV1);
+	setup_clear_cpu_cap(X86_FEATURE_PKU);
 }
 
 /*
@@ -234,7 +243,7 @@ static void __init print_xstate_feature(u64 xstate_mask)
 	const char *feature_name;
 
 	if (cpu_has_xfeatures(xstate_mask, &feature_name))
-		pr_info("x86/fpu: Supporting XSAVE feature 0x%02Lx: '%s'\n", xstate_mask, feature_name);
+		pr_info("x86/fpu: Supporting XSAVE feature 0x%03Lx: '%s'\n", xstate_mask, feature_name);
 }
 
 /*
@@ -250,6 +259,7 @@ static void __init print_xstate_features(void)
 	print_xstate_feature(XFEATURE_MASK_OPMASK);
 	print_xstate_feature(XFEATURE_MASK_ZMM_Hi256);
 	print_xstate_feature(XFEATURE_MASK_Hi16_ZMM);
+	print_xstate_feature(XFEATURE_MASK_PKRU);
 }
 
 /*
@@ -466,6 +476,7 @@ static void check_xstate_against_struct(int nr)
 	XCHECK_SZ(sz, nr, XFEATURE_OPMASK,    struct avx_512_opmask_state);
 	XCHECK_SZ(sz, nr, XFEATURE_ZMM_Hi256, struct avx_512_zmm_uppers_state);
 	XCHECK_SZ(sz, nr, XFEATURE_Hi16_ZMM,  struct avx_512_hi16_state);
+	XCHECK_SZ(sz, nr, XFEATURE_PKRU,      struct pkru_state);
 
 	/*
 	 * Make *SURE* to add any feature numbers in below if
@@ -473,7 +484,8 @@ static void check_xstate_against_struct(int nr)
 	 * numbers.
 	 */
 	if ((nr < XFEATURE_YMM) ||
-	    (nr >= XFEATURE_MAX)) {
+	    (nr >= XFEATURE_MAX) ||
+	    (nr == XFEATURE_PT_UNIMPLEMENTED_SO_FAR)) {
 		WARN_ONCE(1, "no structure for xstate: %d\n", nr);
 		XSTATE_WARN_ON(1);
 	}
@@ -671,6 +683,19 @@ void fpu__resume_cpu(void)
 }
 
 /*
+ * Given an xstate feature mask, calculate where in the xsave
+ * buffer the state is.  Callers should ensure that the buffer
+ * is valid.
+ *
+ * Note: does not work for compacted buffers.
+ */
+void *__raw_xsave_addr(struct xregs_state *xsave, int xstate_feature_mask)
+{
+	int feature_nr = fls64(xstate_feature_mask) - 1;
+
+	return (void *)xsave + xstate_comp_offsets[feature_nr];
+}
+/*
  * Given the xsave area and a state inside, this function returns the
  * address of the state.
  *
@@ -690,7 +715,6 @@ void fpu__resume_cpu(void)
  */
 void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 {
-	int feature_nr = fls64(xstate_feature) - 1;
 	/*
 	 * Do we even *have* xsave state?
 	 */
@@ -718,7 +742,7 @@ void *get_xsave_addr(struct xregs_state *xsave, int xstate_feature)
 	if (!(xsave->header.xfeatures & xstate_feature))
 		return NULL;
 
-	return (void *)xsave + xstate_comp_offsets[feature_nr];
+	return __raw_xsave_addr(xsave, xstate_feature);
 }
 EXPORT_SYMBOL_GPL(get_xsave_addr);
 
@@ -753,3 +777,156 @@ const void *get_xsave_field_ptr(int xsave_state)
 
 	return get_xsave_addr(&fpu->state.xsave, xsave_state);
 }
+
+
+/*
+ * Set xfeatures (aka XSTATE_BV) bit for a feature that we want
+ * to take out of its "init state".  This will ensure that an
+ * XRSTOR actually restores the state.
+ */
+static void fpu__xfeature_set_non_init(struct xregs_state *xsave,
+		int xstate_feature_mask)
+{
+	xsave->header.xfeatures |= xstate_feature_mask;
+}
+
+/*
+ * This function is safe to call whether the FPU is in use or not.
+ *
+ * Note that this only works on the current task.
+ *
+ * Inputs:
+ *	@xsave_state: state which is defined in xsave.h (e.g. XFEATURE_MASK_FP,
+ *	XFEATURE_MASK_SSE, etc...)
+ *	@xsave_state_ptr: a pointer to a copy of the state that you would
+ *	like written in to the current task's FPU xsave state.  This pointer
+ *	must not be located in the current tasks's xsave area.
+ * Output:
+ *	address of the state in the xsave area or NULL if the state
+ *	is not present or is in its 'init state'.
+ */
+static void fpu__xfeature_set_state(int xstate_feature_mask,
+		void *xstate_feature_src, size_t len)
+{
+	struct xregs_state *xsave = &current->thread.fpu.state.xsave;
+	struct fpu *fpu = &current->thread.fpu;
+	void *dst;
+
+	if (!boot_cpu_has(X86_FEATURE_XSAVE)) {
+		WARN_ONCE(1, "%s() attempted with no xsave support", __func__);
+		return;
+	}
+
+	/*
+	 * Tell the FPU code that we need the FPU state to be in
+	 * 'fpu' (not in the registers), and that we need it to
+	 * be stable while we write to it.
+	 */
+	fpu__current_fpstate_write_begin();
+
+	/*
+	 * This method *WILL* *NOT* work for compact-format
+	 * buffers.  If the 'xstate_feature_mask' is unset in
+	 * xcomp_bv then we may need to move other feature state
+	 * "up" in the buffer.
+	 */
+	if (xsave->header.xcomp_bv & xstate_feature_mask) {
+		WARN_ON_ONCE(1);
+		goto out;
+	}
+
+	/* find the location in the xsave buffer of the desired state */
+	dst = __raw_xsave_addr(&fpu->state.xsave, xstate_feature_mask);
+
+	/*
+	 * Make sure that the pointer being passed in did not
+	 * come from the xsave buffer itself.
+	 */
+	WARN_ONCE(xstate_feature_src == dst, "set from xsave buffer itself");
+
+	/* put the caller-provided data in the location */
+	memcpy(dst, xstate_feature_src, len);
+
+	/*
+	 * Mark the xfeature so that the CPU knows there is state
+	 * in the buffer now.
+	 */
+	fpu__xfeature_set_non_init(xsave, xstate_feature_mask);
+out:
+	/*
+	 * We are done writing to the 'fpu'.  Reenable preeption
+	 * and (possibly) move the fpstate back in to the fpregs.
+	 */
+	fpu__current_fpstate_write_end();
+}
+
+#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2)
+#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1)
+
+/*
+ * This will go out and modify the XSAVE buffer so that PKRU is
+ * set to a particular state for access to 'pkey'.
+ *
+ * PKRU state does affect kernel access to user memory.  We do
+ * not modfiy PKRU *itself* here, only the XSAVE state that will
+ * be restored in to PKRU when we return back to userspace.
+ */
+int arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
+		unsigned long init_val)
+{
+	struct xregs_state *xsave = &tsk->thread.fpu.state.xsave;
+	struct pkru_state *old_pkru_state;
+	struct pkru_state new_pkru_state;
+	int pkey_shift = (pkey * PKRU_BITS_PER_PKEY);
+	u32 new_pkru_bits = 0;
+
+	/*
+	 * This check implies XSAVE support.  OSPKE only gets
+	 * set if we enable XSAVE and we enable PKU in XCR0.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_OSPKE))
+		return -EINVAL;
+
+	/* Set the bits we need in PKRU  */
+	if (init_val & PKEY_DISABLE_ACCESS)
+		new_pkru_bits |= PKRU_AD_BIT;
+	if (init_val & PKEY_DISABLE_WRITE)
+		new_pkru_bits |= PKRU_WD_BIT;
+
+	/* Shift the bits in to the correct place in PKRU for pkey. */
+	new_pkru_bits <<= pkey_shift;
+
+	/* Locate old copy of the state in the xsave buffer */
+	old_pkru_state = get_xsave_addr(xsave, XFEATURE_MASK_PKRU);
+
+	/*
+	 * When state is not in the buffer, it is in the init
+	 * state, set it manually.  Otherwise, copy out the old
+	 * state.
+	 */
+	if (!old_pkru_state)
+		new_pkru_state.pkru = 0;
+	else
+		new_pkru_state.pkru = old_pkru_state->pkru;
+
+	/* mask off any old bits in place */
+	new_pkru_state.pkru &= ~((PKRU_AD_BIT|PKRU_WD_BIT) << pkey_shift);
+	/* Set the newly-requested bits */
+	new_pkru_state.pkru |= new_pkru_bits;
+
+	/*
+	 * We could theoretically live without zeroing pkru.pad.
+	 * The current XSAVE feature state definition says that
+	 * only bytes 0->3 are used.  But we do not want to
+	 * chance leaking kernel stack out to userspace in case a
+	 * memcpy() of the whole xsave buffer was done.
+	 *
+	 * They're in the same cacheline anyway.
+	 */
+	new_pkru_state.pad = 0;
+
+	fpu__xfeature_set_state(XFEATURE_MASK_PKRU, &new_pkru_state,
+			sizeof(new_pkru_state));
+
+	return 0;
+}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 702547ce33c9..d036cfb4495d 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -1,5 +1,5 @@
 /*
- * Code for replacing ftrace calls with jumps.
+ * Dynamic function tracing support.
  *
  * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
  *
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0f05deeff5ce..ae703acb85c1 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -49,6 +49,7 @@
 #include <linux/kdebug.h>
 #include <linux/kallsyms.h>
 #include <linux/ftrace.h>
+#include <linux/frame.h>
 
 #include <asm/cacheflush.h>
 #include <asm/desc.h>
@@ -671,39 +672,39 @@ NOKPROBE_SYMBOL(kprobe_int3_handler);
  * When a retprobed function returns, this code saves registers and
  * calls trampoline_handler() runs, which calls the kretprobe's handler.
  */
-static void __used kretprobe_trampoline_holder(void)
-{
-	asm volatile (
-			".global kretprobe_trampoline\n"
-			"kretprobe_trampoline: \n"
+asm(
+	".global kretprobe_trampoline\n"
+	".type kretprobe_trampoline, @function\n"
+	"kretprobe_trampoline:\n"
 #ifdef CONFIG_X86_64
-			/* We don't bother saving the ss register */
-			"	pushq %rsp\n"
-			"	pushfq\n"
-			SAVE_REGS_STRING
-			"	movq %rsp, %rdi\n"
-			"	call trampoline_handler\n"
-			/* Replace saved sp with true return address. */
-			"	movq %rax, 152(%rsp)\n"
-			RESTORE_REGS_STRING
-			"	popfq\n"
+	/* We don't bother saving the ss register */
+	"	pushq %rsp\n"
+	"	pushfq\n"
+	SAVE_REGS_STRING
+	"	movq %rsp, %rdi\n"
+	"	call trampoline_handler\n"
+	/* Replace saved sp with true return address. */
+	"	movq %rax, 152(%rsp)\n"
+	RESTORE_REGS_STRING
+	"	popfq\n"
 #else
-			"	pushf\n"
-			SAVE_REGS_STRING
-			"	movl %esp, %eax\n"
-			"	call trampoline_handler\n"
-			/* Move flags to cs */
-			"	movl 56(%esp), %edx\n"
-			"	movl %edx, 52(%esp)\n"
-			/* Replace saved flags with true return address. */
-			"	movl %eax, 56(%esp)\n"
-			RESTORE_REGS_STRING
-			"	popf\n"
+	"	pushf\n"
+	SAVE_REGS_STRING
+	"	movl %esp, %eax\n"
+	"	call trampoline_handler\n"
+	/* Move flags to cs */
+	"	movl 56(%esp), %edx\n"
+	"	movl %edx, 52(%esp)\n"
+	/* Replace saved flags with true return address. */
+	"	movl %eax, 56(%esp)\n"
+	RESTORE_REGS_STRING
+	"	popf\n"
 #endif
-			"	ret\n");
-}
-NOKPROBE_SYMBOL(kretprobe_trampoline_holder);
+	"	ret\n"
+	".size kretprobe_trampoline, .-kretprobe_trampoline\n"
+);
 NOKPROBE_SYMBOL(kretprobe_trampoline);
+STACK_FRAME_NON_STANDARD(kretprobe_trampoline);
 
 /*
  * Called from kretprobe_trampoline
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 47190bd399e7..807950860fb7 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -36,6 +36,7 @@
 #include <linux/kprobes.h>
 #include <linux/debugfs.h>
 #include <linux/nmi.h>
+#include <linux/swait.h>
 #include <asm/timer.h>
 #include <asm/cpu.h>
 #include <asm/traps.h>
@@ -91,14 +92,14 @@ static void kvm_io_delay(void)
 
 struct kvm_task_sleep_node {
 	struct hlist_node link;
-	wait_queue_head_t wq;
+	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
 	bool halted;
 };
 
 static struct kvm_task_sleep_head {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct hlist_head list;
 } async_pf_sleepers[KVM_TASK_SLEEP_HASHSIZE];
 
@@ -122,17 +123,17 @@ void kvm_async_pf_task_wait(u32 token)
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
 	struct kvm_task_sleep_node n, *e;
-	DEFINE_WAIT(wait);
+	DECLARE_SWAITQUEUE(wait);
 
 	rcu_irq_enter();
 
-	spin_lock(&b->lock);
+	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
 		/* dummy entry exist -> wake up was delivered ahead of PF */
 		hlist_del(&e->link);
 		kfree(e);
-		spin_unlock(&b->lock);
+		raw_spin_unlock(&b->lock);
 
 		rcu_irq_exit();
 		return;
@@ -141,13 +142,13 @@ void kvm_async_pf_task_wait(u32 token)
 	n.token = token;
 	n.cpu = smp_processor_id();
 	n.halted = is_idle_task(current) || preempt_count() > 1;
-	init_waitqueue_head(&n.wq);
+	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
-	spin_unlock(&b->lock);
+	raw_spin_unlock(&b->lock);
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_wait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 
@@ -166,7 +167,7 @@ void kvm_async_pf_task_wait(u32 token)
 		}
 	}
 	if (!n.halted)
-		finish_wait(&n.wq, &wait);
+		finish_swait(&n.wq, &wait);
 
 	rcu_irq_exit();
 	return;
@@ -178,8 +179,8 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	hlist_del_init(&n->link);
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
-	else if (waitqueue_active(&n->wq))
-		wake_up(&n->wq);
+	else if (swait_active(&n->wq))
+		swake_up(&n->wq);
 }
 
 static void apf_task_wake_all(void)
@@ -189,14 +190,14 @@ static void apf_task_wake_all(void)
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++) {
 		struct hlist_node *p, *next;
 		struct kvm_task_sleep_head *b = &async_pf_sleepers[i];
-		spin_lock(&b->lock);
+		raw_spin_lock(&b->lock);
 		hlist_for_each_safe(p, next, &b->list) {
 			struct kvm_task_sleep_node *n =
 				hlist_entry(p, typeof(*n), link);
 			if (n->cpu == smp_processor_id())
 				apf_task_wake_one(n);
 		}
-		spin_unlock(&b->lock);
+		raw_spin_unlock(&b->lock);
 	}
 }
 
@@ -212,7 +213,7 @@ void kvm_async_pf_task_wake(u32 token)
 	}
 
 again:
-	spin_lock(&b->lock);
+	raw_spin_lock(&b->lock);
 	n = _find_apf_task(b, token);
 	if (!n) {
 		/*
@@ -225,17 +226,17 @@ again:
 			 * Allocation failed! Busy wait while other cpu
 			 * handles async PF.
 			 */
-			spin_unlock(&b->lock);
+			raw_spin_unlock(&b->lock);
 			cpu_relax();
 			goto again;
 		}
 		n->token = token;
 		n->cpu = smp_processor_id();
-		init_waitqueue_head(&n->wq);
+		init_swait_queue_head(&n->wq);
 		hlist_add_head(&n->link, &b->list);
 	} else
 		apf_task_wake_one(n);
-	spin_unlock(&b->lock);
+	raw_spin_unlock(&b->lock);
 	return;
 }
 EXPORT_SYMBOL_GPL(kvm_async_pf_task_wake);
@@ -486,7 +487,7 @@ void __init kvm_guest_init(void)
 	paravirt_ops_setup();
 	register_reboot_notifier(&kvm_pv_reboot_nb);
 	for (i = 0; i < KVM_TASK_SLEEP_HASHSIZE; i++)
-		spin_lock_init(&async_pf_sleepers[i].lock);
+		raw_spin_lock_init(&async_pf_sleepers[i].lock);
 	if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF))
 		x86_init.irqs.trap_init = kvm_apf_trap_init;
 
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 6acc9dd91f36..6707039b9032 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -103,7 +103,7 @@ static void free_ldt_struct(struct ldt_struct *ldt)
  * we do not have to muck with descriptors here, that is
  * done in switch_mm() as needed.
  */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+int init_new_context_ldt(struct task_struct *tsk, struct mm_struct *mm)
 {
 	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
@@ -144,7 +144,7 @@ out_unlock:
  *
  * 64bit: Don't touch the LDT register - we're already in the next thread.
  */
-void destroy_context(struct mm_struct *mm)
+void destroy_context_ldt(struct mm_struct *mm)
 {
 	free_ldt_struct(mm->context.ldt);
 	mm->context.ldt = NULL;
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 9f751876066f..6cbab31ac23a 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -117,6 +117,8 @@ void __show_regs(struct pt_regs *regs, int all)
 	printk(KERN_DEFAULT "DR0: %016lx DR1: %016lx DR2: %016lx\n", d0, d1, d2);
 	printk(KERN_DEFAULT "DR3: %016lx DR6: %016lx DR7: %016lx\n", d3, d6, d7);
 
+	if (boot_cpu_has(X86_FEATURE_OSPKE))
+		printk(KERN_DEFAULT "PKRU: %08x\n", read_pkru());
 }
 
 void release_thread(struct task_struct *dead_task)
@@ -488,7 +490,7 @@ void set_personality_ia32(bool x32)
 		if (current->mm)
 			current->mm->context.ia32_compat = TIF_X32;
 		current->personality &= ~READ_IMPLIES_EXEC;
-		/* is_compat_task() uses the presence of the x32
+		/* in_compat_syscall() uses the presence of the x32
 		   syscall bit flag to determine compat status */
 		current_thread_info()->status &= ~TS_COMPAT;
 	} else {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index aa52c1009475..2367ae07eb76 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -112,6 +112,7 @@
 #include <asm/alternative.h>
 #include <asm/prom.h>
 #include <asm/microcode.h>
+#include <asm/mmu_context.h>
 
 /*
  * max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -1282,3 +1283,11 @@ static int __init register_kernel_offset_dumper(void)
 	return 0;
 }
 __initcall(register_kernel_offset_dumper);
+
+void arch_show_smap(struct seq_file *m, struct vm_area_struct *vma)
+{
+	if (!boot_cpu_has(X86_FEATURE_OSPKE))
+		return;
+
+	seq_printf(m, "ProtectionKey:  %8u\n", vma_pkey(vma));
+}
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index b2c99f811c3f..a2065d3b3b39 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -422,7 +422,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 		if (c->phys_proc_id == o->phys_proc_id &&
 		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
-		    c->compute_unit_id == o->compute_unit_id)
+		    c->cpu_core_id == o->cpu_core_id)
 			return topology_sane(c, o, "smt");
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index fdd0c6430e5a..9ee98eefc44d 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -14,30 +14,34 @@ static int save_stack_stack(void *data, char *name)
 	return 0;
 }
 
-static void
+static int
 __save_stack_address(void *data, unsigned long addr, bool reliable, bool nosched)
 {
 	struct stack_trace *trace = data;
 #ifdef CONFIG_FRAME_POINTER
 	if (!reliable)
-		return;
+		return 0;
 #endif
 	if (nosched && in_sched_functions(addr))
-		return;
+		return 0;
 	if (trace->skip > 0) {
 		trace->skip--;
-		return;
+		return 0;
 	}
-	if (trace->nr_entries < trace->max_entries)
+	if (trace->nr_entries < trace->max_entries) {
 		trace->entries[trace->nr_entries++] = addr;
+		return 0;
+	} else {
+		return -1; /* no more room, stop walking the stack */
+	}
 }
 
-static void save_stack_address(void *data, unsigned long addr, int reliable)
+static int save_stack_address(void *data, unsigned long addr, int reliable)
 {
 	return __save_stack_address(data, addr, reliable, false);
 }
 
-static void
+static int
 save_stack_address_nosched(void *data, unsigned long addr, int reliable)
 {
 	return __save_stack_address(data, addr, reliable, true);
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 91a4496db434..e72a07f20b05 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -135,7 +135,7 @@ static int map_tboot_page(unsigned long vaddr, unsigned long pfn,
 	pmd = pmd_alloc(&tboot_mm, pud, vaddr);
 	if (!pmd)
 		return -1;
-	pte = pte_alloc_map(&tboot_mm, NULL, pmd, vaddr);
+	pte = pte_alloc_map(&tboot_mm, pmd, vaddr);
 	if (!pte)
 		return -1;
 	set_pte_at(&tboot_mm, vaddr, pte, pfn_pte(pfn, prot));
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 5af9958cbdb6..4c941f88d405 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -81,11 +81,11 @@ PHDRS {
 SECTIONS
 {
 #ifdef CONFIG_X86_32
-        . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
-        phys_startup_32 = startup_32 - LOAD_OFFSET;
+	. = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
+	phys_startup_32 = ABSOLUTE(startup_32 - LOAD_OFFSET);
 #else
-        . = __START_KERNEL;
-        phys_startup_64 = startup_64 - LOAD_OFFSET;
+	. = __START_KERNEL;
+	phys_startup_64 = ABSOLUTE(startup_64 - LOAD_OFFSET);
 #endif
 
 	/* Text and read-only data */
@@ -101,6 +101,7 @@ SECTIONS
 		KPROBES_TEXT
 		ENTRY_TEXT
 		IRQENTRY_TEXT
+		SOFTIRQENTRY_TEXT
 		*(.fixup)
 		*(.gnu.warning)
 		/* End of text section */
@@ -333,6 +334,7 @@ SECTIONS
 		__brk_limit = .;
 	}
 
+	. = ALIGN(PAGE_SIZE);
 	_end = .;
 
         STABS_DEBUG
@@ -340,7 +342,10 @@ SECTIONS
 
 	/* Sections to be discarded */
 	DISCARDS
-	/DISCARD/ : { *(.eh_frame) }
+	/DISCARD/ : {
+		*(.eh_frame)
+		*(__func_stack_frame_non_standard)
+	}
 }